diff options
443 files changed, 4435 insertions, 2229 deletions
@@ -169,6 +169,10 @@ Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com> Kay Sievers <kay.sievers@vrfy.org> +Kees Cook <keescook@chromium.org> <kees.cook@canonical.com> +Kees Cook <keescook@chromium.org> <keescook@google.com> +Kees Cook <keescook@chromium.org> <kees@outflux.net> +Kees Cook <keescook@chromium.org> <kees@ubuntu.com> Kenneth W Chen <kenneth.w.chen@intel.com> Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru> Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 6be43781ec7f..baa07b30845e 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1324,15 +1324,26 @@ PAGE_SIZE multiple when read back. pgmajfault Number of major page faults incurred - workingset_refault - Number of refaults of previously evicted pages + workingset_refault_anon + Number of refaults of previously evicted anonymous pages. - workingset_activate - Number of refaulted pages that were immediately activated + workingset_refault_file + Number of refaults of previously evicted file pages. - workingset_restore - Number of restored pages which have been detected as an active - workingset before they got reclaimed. + workingset_activate_anon + Number of refaulted anonymous pages that were immediately + activated. + + workingset_activate_file + Number of refaulted file pages that were immediately activated. + + workingset_restore_anon + Number of restored anonymous pages which have been detected as + an active workingset before they got reclaimed. + + workingset_restore_file + Number of restored file pages which have been detected as an + active workingset before they got reclaimed. workingset_nodereclaim Number of times a shadow node has been reclaimed diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst index 8f4a3f889d43..bc28a9527ee5 100644 --- a/Documentation/admin-guide/device-mapper/dm-crypt.rst +++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst @@ -67,7 +67,7 @@ Parameters:: the value passed in <key_size>. <key_type> - Either 'logon' or 'user' kernel key type. + Either 'logon', 'user' or 'encrypted' kernel key type. <key_description> The kernel keyring key description crypt target should look for @@ -121,6 +121,14 @@ submit_from_crypt_cpus thread because it benefits CFQ to have writes submitted using the same context. +no_read_workqueue + Bypass dm-crypt internal workqueue and process read requests synchronously. + +no_write_workqueue + Bypass dm-crypt internal workqueue and process write requests synchronously. + This option is automatically enabled for host-managed zoned block devices + (e.g. host-managed SMR hard-disks). + integrity:<bytes>:<type> The device requires additional <bytes> metadata per-sector stored in per-bio integrity structure. This metadata must by provided diff --git a/Documentation/bpf/ringbuf.rst b/Documentation/bpf/ringbuf.rst index 75f943f0009d..6a615cd62bda 100644 --- a/Documentation/bpf/ringbuf.rst +++ b/Documentation/bpf/ringbuf.rst @@ -182,9 +182,6 @@ in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. -Reservation/commit/consumer protocol is verified by litmus tests in -Documentation/litmus_tests/bpf-rb/_. - One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This @@ -200,7 +197,7 @@ a self-pacing notifications of new data being availability. being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. -Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that +Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbufs.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of diff --git a/Documentation/devicetree/bindings/media/i2c/imx274.txt b/Documentation/devicetree/bindings/media/i2c/imx274.txt deleted file mode 100644 index 0727079d2410..000000000000 --- a/Documentation/devicetree/bindings/media/i2c/imx274.txt +++ /dev/null @@ -1,38 +0,0 @@ -* Sony 1/2.5-Inch 8.51Mp CMOS Digital Image Sensor - -The Sony imx274 is a 1/2.5-inch CMOS active pixel digital image sensor with -an active array size of 3864H x 2202V. It is programmable through I2C -interface. The I2C address is fixed to 0x1a as per sensor data sheet. -Image data is sent through MIPI CSI-2, which is configured as 4 lanes -at 1440 Mbps. - - -Required Properties: -- compatible: value should be "sony,imx274" for imx274 sensor -- reg: I2C bus address of the device - -Optional Properties: -- reset-gpios: Sensor reset GPIO -- clocks: Reference to the input clock. -- clock-names: Should be "inck". -- VANA-supply: Sensor 2.8v analog supply. -- VDIG-supply: Sensor 1.8v digital core supply. -- VDDL-supply: Sensor digital IO 1.2v supply. - -The imx274 device node should contain one 'port' child node with -an 'endpoint' subnode. For further reading on port node refer to -Documentation/devicetree/bindings/media/video-interfaces.txt. - -Example: - sensor@1a { - compatible = "sony,imx274"; - reg = <0x1a>; - #address-cells = <1>; - #size-cells = <0>; - reset-gpios = <&gpio_sensor 0 0>; - port { - sensor_out: endpoint { - remote-endpoint = <&csiss_in>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml new file mode 100644 index 000000000000..f697e1a20beb --- /dev/null +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/media/i2c/sony,imx274.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Sony 1/2.5-Inch 8.51MP CMOS Digital Image Sensor + +maintainers: + - Leon Luo <leonl@leopardimaging.com> + +description: | + The Sony IMX274 is a 1/2.5-inch CMOS active pixel digital image sensor with an + active array size of 3864H x 2202V. It is programmable through I2C interface. + Image data is sent through MIPI CSI-2, which is configured as 4 lanes at 1440 + Mbps. + +properties: + compatible: + const: sony,imx274 + + reg: + const: 0x1a + + reset-gpios: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: inck + + vana-supply: + description: Sensor 2.8 V analog supply. + maxItems: 1 + + vdig-supply: + description: Sensor 1.8 V digital core supply. + maxItems: 1 + + vddl-supply: + description: Sensor digital IO 1.2 V supply. + maxItems: 1 + + port: + type: object + description: Output video port. See ../video-interfaces.txt. + +required: + - compatible + - reg + - port + +additionalProperties: false + +examples: + - | + i2c0 { + #address-cells = <1>; + #size-cells = <0>; + + imx274: camera-sensor@1a { + compatible = "sony,imx274"; + reg = <0x1a>; + reset-gpios = <&gpio_sensor 0 0>; + + port { + sensor_out: endpoint { + remote-endpoint = <&csiss_in>; + }; + }; + }; + }; + +... diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt index 53da483c8326..1c49723e7534 100644 --- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt +++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt @@ -22,7 +22,7 @@ | nios2: | TODO | | openrisc: | TODO | | parisc: | TODO | - | powerpc: | ok | + | powerpc: | TODO | | riscv: | ok | | s390: | ok | | sh: | TODO | diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index 334df758dce3..dae90c21aed3 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -39,10 +39,10 @@ which can help simplify cross compiling. :: ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang ``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead -``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For +``CROSS_COMPILE`` is used to set a command line flag: ``--target=<triple>``. For example: :: - clang --target aarch64-linux-gnu foo.c + clang --target=aarch64-linux-gnu foo.c LLVM Utilities -------------- diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d53bcb31645a..b5a79881551f 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -206,6 +206,7 @@ Userspace to kernel: ``ETHTOOL_MSG_TSINFO_GET`` get timestamping info ``ETHTOOL_MSG_CABLE_TEST_ACT`` action start cable test ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` action start raw TDR cable test + ``ETHTOOL_MSG_TUNNEL_INFO_GET`` get tunnel offload info ===================================== ================================ Kernel to userspace: @@ -239,6 +240,7 @@ Kernel to userspace: ``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info ``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF`` Cable test TDR results + ``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info ===================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1363,4 +1365,5 @@ are netlink only. ``ETHTOOL_SFECPARAM`` n/a n/a ''ETHTOOL_MSG_CABLE_TEST_ACT'' n/a ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT'' + n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` =================================== ===================================== diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst index 57e752aaf414..2044ed13cd9d 100644 --- a/Documentation/userspace-api/media/v4l/buffer.rst +++ b/Documentation/userspace-api/media/v4l/buffer.rst @@ -701,23 +701,6 @@ Memory Consistency Flags :stub-columns: 0 :widths: 3 1 4 - * .. _`V4L2-FLAG-MEMORY-NON-CONSISTENT`: - - - ``V4L2_FLAG_MEMORY_NON_CONSISTENT`` - - 0x00000001 - - A buffer is allocated either in consistent (it will be automatically - coherent between the CPU and the bus) or non-consistent memory. The - latter can provide performance gains, for instance the CPU cache - sync/flush operations can be avoided if the buffer is accessed by the - corresponding device only and the CPU does not read/write to/from that - buffer. However, this requires extra care from the driver -- it must - guarantee memory consistency by issuing a cache flush/sync when - consistency is needed. If this flag is set V4L2 will attempt to - allocate the buffer in non-consistent memory. The flag takes effect - only if the buffer is used for :ref:`memory mapping <mmap>` I/O and the - queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS - <V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS>` capability. - .. c:type:: v4l2_memory enum v4l2_memory diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst index f2a702870fad..12cf6b44f414 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst @@ -120,13 +120,9 @@ than the number requested. If you want to just query the capabilities without making any other changes, then set ``count`` to 0, ``memory`` to ``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type. - * - __u32 - - ``flags`` - - Specifies additional buffer management attributes. - See :ref:`memory-flags`. * - __u32 - - ``reserved``\ [6] + - ``reserved``\ [7] - A place holder for future extensions. Drivers and applications must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 75d894d9c36c..0e3e2fde65e8 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -112,17 +112,10 @@ aborting or finishing any DMA in progress, an implicit ``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will free any previously allocated buffers, so this is typically something that will be done at the start of the application. - * - union { - - (anonymous) - * - __u32 - - ``flags`` - - Specifies additional buffer management attributes. - See :ref:`memory-flags`. * - __u32 - ``reserved``\ [1] - - Kept for backwards compatibility. Use ``flags`` instead. - * - } - - + - A place holder for future extensions. Drivers and applications + must set the array to zero. .. tabularcolumns:: |p{6.1cm}|p{2.2cm}|p{8.7cm}| @@ -169,7 +162,6 @@ aborting or finishing any DMA in progress, an implicit - This capability is set by the driver to indicate that the queue supports cache and memory management hints. However, it's only valid when the queue is used for :ref:`memory mapping <mmap>` streaming I/O. See - :ref:`V4L2_FLAG_MEMORY_NON_CONSISTENT <V4L2-FLAG-MEMORY-NON-CONSISTENT>`, :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE <V4L2-BUF-FLAG-NO-CACHE-INVALIDATE>` and :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN <V4L2-BUF-FLAG-NO-CACHE-CLEAN>`. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index d2b733dc7892..51191b56e61c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6173,3 +6173,23 @@ specific interfaces must be consistent, i.e. if one says the feature is supported, than the other should as well and vice versa. For arm64 see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL". For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME". + +8.25 KVM_CAP_S390_DIAG318 +------------------------- + +:Architectures: s390 + +This capability enables a guest to set information about its control program +(i.e. guest kernel type and version). The information is helpful during +system/firmware service events, providing additional data about the guest +environments running on the machine. + +The information is associated with the DIAGNOSE 0x318 instruction, which sets +an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and +a 7-byte Control Program Version Code (CPVC). The CPNC determines what +environment the control program is running in (e.g. Linux, z/VM...), and the +CPVC is used for information specific to OS (e.g. Linux version, Linux +distribution...) + +If this capability is available, then the CPNC and CPVC can be synchronized +between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318). diff --git a/MAINTAINERS b/MAINTAINERS index d746519253c3..190c7fa2ea01 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4408,12 +4408,6 @@ T: git git://git.infradead.org/users/hch/configfs.git F: fs/configfs/ F: include/linux/configfs.h -CONNECTOR -M: Evgeniy Polyakov <zbr@ioremap.net> -L: netdev@vger.kernel.org -S: Maintained -F: drivers/connector/ - CONSOLE SUBSYSTEM M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> S: Supported @@ -8329,8 +8323,9 @@ S: Supported F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver -M: Thomas Falcon <tlfalcon@linux.ibm.com> -M: John Allen <jallen@linux.ibm.com> +M: Dany Madden <drt@linux.ibm.com> +M: Lijun Pan <ljp@linux.ibm.com> +M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* @@ -8344,7 +8339,7 @@ F: arch/powerpc/platforms/powernv/copy-paste.h F: arch/powerpc/platforms/powernv/vas* IBM Power Virtual Ethernet Device Driver -M: Thomas Falcon <tlfalcon@linux.ibm.com> +M: Cristobal Forno <cforno12@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmveth.* @@ -11042,6 +11037,7 @@ F: drivers/char/hw_random/mtk-rng.c MEDIATEK SWITCH DRIVER M: Sean Wang <sean.wang@mediatek.com> +M: Landen Chao <Landen.Chao@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530.* @@ -12055,6 +12051,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ +F: drivers/connector/ F: drivers/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h @@ -16157,7 +16154,7 @@ M: Leon Luo <leonl@leopardimaging.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git -F: Documentation/devicetree/bindings/media/i2c/imx274.txt +F: Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml F: drivers/media/i2c/imx274.c SONY IMX290 SENSOR DRIVER @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts index 8d19925fc09e..6783cf16ff81 100644 --- a/arch/arm/boot/dts/at91-sama5d2_icp.dts +++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts @@ -116,7 +116,6 @@ switch0: ksz8563@0 { compatible = "microchip,ksz8563"; reg = <0>; - phy-mode = "mii"; reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>; spi-max-frequency = <500000>; @@ -140,6 +139,7 @@ reg = <2>; label = "cpu"; ethernet = <&macb0>; + phy-mode = "mii"; fixed-link { speed = <100>; full-duplex; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 49a55be2b9a2..1cc5f5f72d0b 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -298,15 +298,15 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW); } +/* Always check for S1PTW *before* using this. */ static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) || - kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR; } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) @@ -335,6 +335,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC; @@ -372,6 +377,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { + if (kvm_vcpu_abt_iss1tw(vcpu)) + return true; + if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index c332d49780dc..560ba69e13c1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,8 +910,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), - .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | - ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), + /* + * We need to allow affected CPUs to come in late, but + * also need the non-affected CPUs to be able to come + * in at any point in time. Wonderful. + */ + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 295d66490584..c07d7a034941 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu) struct pv_time_stolen_time_region *reg; reg = per_cpu_ptr(&stolen_time_region, cpu); - if (!reg->kaddr) { - pr_warn_once("stolen time enabled but not configured for cpu %d\n", - cpu); + + /* + * paravirt_steal_clock() may be called before the CPU + * online notification callback runs. Until the callback + * has run we just return zero. + */ + if (!reg->kaddr) return 0; - } return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); } -static int stolen_time_dying_cpu(unsigned int cpu) +static int stolen_time_cpu_down_prepare(unsigned int cpu) { struct pv_time_stolen_time_region *reg; @@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigned int cpu) return 0; } -static int init_stolen_time_cpu(unsigned int cpu) +static int stolen_time_cpu_online(unsigned int cpu) { struct pv_time_stolen_time_region *reg; struct arm_smccc_res res; @@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned int cpu) return 0; } -static int pv_time_init_stolen_time(void) +static int __init pv_time_init_stolen_time(void) { int ret; - ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING, - "hypervisor/arm/pvtime:starting", - init_stolen_time_cpu, stolen_time_dying_cpu); + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "hypervisor/arm/pvtime:online", + stolen_time_cpu_online, + stolen_time_cpu_down_prepare); if (ret < 0) return ret; return 0; } -static bool has_pv_steal_clock(void) +static bool __init has_pv_steal_clock(void) { struct arm_smccc_res res; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 5b6b8fa00f0a..0261308bf944 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -449,7 +449,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_abt_issea(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); + !kvm_vcpu_abt_iss1tw(vcpu); if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 9a636b8064f1..3d26b47a1343 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1849,7 +1849,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_fault = kvm_is_write_fault(vcpu); - exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_status == FSC_PERM && !write_fault && !exec_fault) { @@ -2131,7 +2131,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) goto out; } - if (kvm_vcpu_dabt_iss1tw(vcpu)) { + if (kvm_vcpu_abt_iss1tw(vcpu)) { kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index f8912e45be7a..ef9f1d5e989d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -143,14 +143,17 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val, } } -static inline int bpf2a64_offset(int bpf_to, int bpf_from, +static inline int bpf2a64_offset(int bpf_insn, int off, const struct jit_ctx *ctx) { - int to = ctx->offset[bpf_to]; - /* -1 to account for the Branch instruction */ - int from = ctx->offset[bpf_from] - 1; - - return to - from; + /* BPF JMP offset is relative to the next instruction */ + bpf_insn++; + /* + * Whereas arm64 branch instructions encode the offset + * from the branch itself, so we must subtract 1 from the + * instruction offset. + */ + return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1); } static void jit_fill_hole(void *area, unsigned int size) @@ -642,7 +645,7 @@ emit_bswap_uxt: /* JUMP off */ case BPF_JMP | BPF_JA: - jmp_offset = bpf2a64_offset(i + off, i, ctx); + jmp_offset = bpf2a64_offset(i, off, ctx); check_imm26(jmp_offset); emit(A64_B(jmp_offset), ctx); break; @@ -669,7 +672,7 @@ emit_bswap_uxt: case BPF_JMP32 | BPF_JSLE | BPF_X: emit(A64_CMP(is64, dst, src), ctx); emit_cond_jmp: - jmp_offset = bpf2a64_offset(i + off, i, ctx); + jmp_offset = bpf2a64_offset(i, off, ctx); check_imm19(jmp_offset); switch (BPF_OP(code)) { case BPF_JEQ: @@ -908,10 +911,21 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass) const struct bpf_prog *prog = ctx->prog; int i; + /* + * - offset[0] offset of the end of prologue, + * start of the 1st instruction. + * - offset[1] - offset of the end of 1st instruction, + * start of the 2nd instruction + * [....] + * - offset[3] - offset of the end of 3rd instruction, + * start of 4th instruction + */ for (i = 0; i < prog->len; i++) { const struct bpf_insn *insn = &prog->insnsi[i]; int ret; + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; ret = build_insn(insn, ctx, extra_pass); if (ret > 0) { i++; @@ -919,11 +933,16 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass) ctx->offset[i] = ctx->idx; continue; } - if (ctx->image == NULL) - ctx->offset[i] = ctx->idx; if (ret) return ret; } + /* + * offset is allocated with prog->len + 1 so fill in + * the last element with the offset after the last + * instruction (end of program) + */ + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; return 0; } @@ -1002,7 +1021,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) memset(&ctx, 0, sizeof(ctx)); ctx.prog = prog; - ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL); if (ctx.offset == NULL) { prog = orig_prog; goto out_off; @@ -1089,7 +1108,7 @@ skip_init_ctx: prog->jited_len = prog_size; if (!prog->is_func || extra_pass) { - bpf_prog_fill_jited_linfo(prog, ctx.offset); + bpf_prog_fill_jited_linfo(prog, ctx.offset + 1); out_off: kfree(ctx.offset); kfree(jit_data); diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h index b66ba907019c..87927eb824cc 100644 --- a/arch/ia64/include/asm/acpi.h +++ b/arch/ia64/include/asm/acpi.h @@ -74,8 +74,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf) buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; } -#define acpi_unlazy_tlb(x) - #ifdef CONFIG_ACPI_NUMA extern cpumask_t early_cpu_possible_map; #define for_each_possible_early_cpu(cpu) \ diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 0b3fb4c7af29..8e7b8c6c576e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); return 0; } @@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, - NULL); + memmap_init_zone(size, nid, zone, start_pfn, + MEMINIT_EARLY, NULL); } else { struct page *start; struct memmap_init_callback_data args; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c95fa3a2484c..8f328298f8cc 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -877,6 +877,7 @@ config SNI_RM select I8253 select I8259 select ISA + select MIPS_L1_CACHE_SHIFT_6 select SWAP_IO_SPACE if CPU_BIG_ENDIAN select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 82627c264964..01427bde2397 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -148,7 +148,7 @@ void __init plat_mem_setup(void) { struct cpuinfo_mips *c = ¤t_cpu_data; - if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) { + if (c->cputype == CPU_74K) { pr_info("Using bcma bus\n"); #ifdef CONFIG_BCM47XX_BCMA bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA; diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 75a7a382da09..3288cef4b168 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform index 4ab55f1123a0..ae023b9a1c51 100644 --- a/arch/mips/loongson2ef/Platform +++ b/arch/mips/loongson2ef/Platform @@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif endif +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-y += $(call cc-option,-mno-loongson-mmi) + # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c index f130f62129b8..00055d4b6042 100644 --- a/arch/mips/loongson64/cop2-ex.c +++ b/arch/mips/loongson64/cop2-ex.c @@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt, value); - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq, value_next); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next); compute_return_epc(regs); own_fpu(1); } @@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value_next = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq); + value_next = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0); StoreDW(addr + 8, value_next, res); if (res) goto fault; - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0); StoreDW(addr, value, res); if (res) @@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); @@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); break; @@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreW(addr, value, res); if (res) @@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreDW(addr, value, res); if (res) diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index b09dc844985a..eeeec18c420a 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = { }, }; -static u32 a20r_ack_hwint(void) +/* + * Trigger chipset to update CPU's CAUSE IP field + */ +static u32 a20r_update_cause_ip(void) { u32 status = read_c0_status(); @@ -205,12 +208,14 @@ static void a20r_hwint(void) int irq; clear_c0_status(IE_IRQ0); - status = a20r_ack_hwint(); + status = a20r_update_cause_ip(); cause = read_c0_cause(); irq = ffs(((cause & status) >> 8) & 0xf8); if (likely(irq > 0)) do_IRQ(SNI_A20R_IRQ_BASE + irq - 1); + + a20r_update_cause_ip(); set_c0_status(IE_IRQ0); } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 65bed1fdeaad..787e829b6f25 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -116,7 +116,6 @@ config PPC # select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL - select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 55442d45c597..b392384a3b15 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -239,14 +239,14 @@ static inline void early_init_mmu_secondary(void) extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); -extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size); static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { - if (early_radix_enabled()) - return radix__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); + /* + * Hash has more strict restrictions. At this point we don't + * know which translations we will pick. Hence go with hash + * restrictions. + */ return hash__setup_initial_memory_limit(first_memblock_base, first_memblock_size); } diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 569fecd7b5b2..9053fc9d20c7 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -120,7 +120,8 @@ u64 dma_iommu_get_required_mask(struct device *dev) if (!tbl) return 0; - mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) + + tbl->it_page_shift - 1); mask += mask - 1; return mask; diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 87ab1152d5ce..e147bbdc12cd 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) + cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 4c985467a668..5206c2eb2a1d 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -111,7 +111,6 @@ SECTIONS *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 38c317f25141..32ebb3522ea1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 4e3a8d4ee614..256fb9720298 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -30,7 +30,7 @@ SECTIONS . = ALIGN(16); .text : { *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*) - *(.sfpr) + *(.sfpr .glink) } :text PROVIDE(__etext = .); PROVIDE(_etext = .); @@ -111,7 +111,6 @@ SECTIONS *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 28c784976bed..d5f0c10d752a 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -734,21 +734,6 @@ void radix__mmu_cleanup_all(void) } } -void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) -{ - /* - * We don't currently support the first MEMBLOCK not mapping 0 - * physical on those processors - */ - BUG_ON(first_memblock_base != 0); - - /* - * Radix mode is not limited by RMA / VRMA addressing. - */ - ppc64_rma_size = ULONG_MAX; -} - #ifdef CONFIG_MEMORY_HOTPLUG static void free_pte_table(pte_t *pte_start, pmd_t *pmd) { diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 02e127fa5777..8459056cce67 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -433,9 +433,16 @@ void __init mmu_early_init_devtree(void) if (!(mfmsr() & MSR_HV)) early_check_vec5(); - if (early_radix_enabled()) + if (early_radix_enabled()) { radix__early_init_devtree(); - else + /* + * We have finalized the translation we are going to use by now. + * Radix mode is not limited by RMA / VRMA addressing. + * Hence don't limit memblock allocations. + */ + ppc64_rma_size = ULONG_MAX; + memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); + } else hash__early_init_devtree(); } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f439f0dfea7d..a88a707a608a 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -822,7 +822,7 @@ free_stats: kfree(stats); return rc ? rc : seq_buf_used(&s); } -DEVICE_ATTR_RO(perf_stats); +DEVICE_ATTR_ADMIN_RO(perf_stats); static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index df18372861d8..7766e1289468 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -32,6 +32,7 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select CLONE_BACKWARDS + select CLINT_TIMER if !MMU select COMMON_CLK select EDAC_SUPPORT select GENERIC_ARCH_TOPOLOGY if SMP diff --git a/arch/riscv/boot/dts/kendryte/k210.dtsi b/arch/riscv/boot/dts/kendryte/k210.dtsi index c1df56ccb8d5..d2d0ff645632 100644 --- a/arch/riscv/boot/dts/kendryte/k210.dtsi +++ b/arch/riscv/boot/dts/kendryte/k210.dtsi @@ -95,10 +95,12 @@ #clock-cells = <1>; }; - clint0: interrupt-controller@2000000 { + clint0: clint@2000000 { + #interrupt-cells = <1>; compatible = "riscv,clint0"; reg = <0x2000000 0xC000>; - interrupts-extended = <&cpu0_intc 3>, <&cpu1_intc 3>; + interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 + &cpu1_intc 3 &cpu1_intc 7>; clocks = <&sysctl K210_CLK_ACLK>; }; diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h new file mode 100644 index 000000000000..0789fd37b40a --- /dev/null +++ b/arch/riscv/include/asm/clint.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Google, Inc + */ + +#ifndef _ASM_RISCV_CLINT_H +#define _ASM_RISCV_CLINT_H + +#include <linux/types.h> +#include <asm/mmio.h> + +#ifdef CONFIG_RISCV_M_MODE +/* + * This lives in the CLINT driver, but is accessed directly by timex.h to avoid + * any overhead when accessing the MMIO timer. + * + * The ISA defines mtime as a 64-bit memory-mapped register that increments at + * a constant frequency, but it doesn't define some other constraints we depend + * on (most notably ordering constraints, but also some simpler stuff like the + * memory layout). Thus, this is called "clint_time_val" instead of something + * like "riscv_mtime", to signify that these non-ISA assumptions must hold. + */ +extern u64 __iomem *clint_time_val; +#endif + +#endif diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index ace8a6e2d11d..845002cc2e57 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -66,6 +66,13 @@ do { \ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. */ #define MCOUNT_INSN_SIZE 8 + +#ifndef __ASSEMBLY__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #endif #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index a3fb85d505d4..7f659dda0032 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -10,6 +10,31 @@ typedef unsigned long cycles_t; +#ifdef CONFIG_RISCV_M_MODE + +#include <asm/clint.h> + +#ifdef CONFIG_64BIT +static inline cycles_t get_cycles(void) +{ + return readq_relaxed(clint_time_val); +} +#else /* !CONFIG_64BIT */ +static inline u32 get_cycles(void) +{ + return readl_relaxed(((u32 *)clint_time_val)); +} +#define get_cycles get_cycles + +static inline u32 get_cycles_hi(void) +{ + return readl_relaxed(((u32 *)clint_time_val) + 1); +} +#define get_cycles_hi get_cycles_hi +#endif /* CONFIG_64BIT */ + +#else /* CONFIG_RISCV_M_MODE */ + static inline cycles_t get_cycles(void) { return csr_read(CSR_TIME); @@ -41,6 +66,8 @@ static inline u64 get_cycles64(void) } #endif /* CONFIG_64BIT */ +#endif /* !CONFIG_RISCV_M_MODE */ + #define ARCH_HAS_READ_CURRENT_TIMER static inline int read_current_timer(unsigned long *timer_val) { diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 2ff63d0cbb50..99e12faa5498 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -97,6 +97,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return __ftrace_modify_call(rec->ip, addr, false); } + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + ftrace_arch_code_modify_prepare(); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ftrace_arch_code_modify_post_process(); + + return out; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 787c75f751a5..ca03762a3733 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -226,12 +226,11 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) ptep = &fixmap_pte[pte_index(addr)]; - if (pgprot_val(prot)) { + if (pgprot_val(prot)) set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot)); - } else { + else pte_clear(&init_mm, addr, ptep); - local_flush_tlb_page(addr); - } + local_flush_tlb_page(addr); } static pte_t *__init get_pte_virt(phys_addr_t pa) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7eb01a5459cd..b55561cc8786 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address) #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address) -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) - return (p4d_t *) pgd_deref(*pgd) + p4d_index(address); - return (p4d_t *) pgd; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) + return (p4d_t *) pgd_deref(pgd) + p4d_index(address); + return (p4d_t *) pgdp; } +#define p4d_offset_lockless p4d_offset_lockless -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address) { - if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) - return (pud_t *) p4d_deref(*p4d) + pud_index(address); - return (pud_t *) p4d; + return p4d_offset_lockless(pgdp, *pgdp, address); +} + +static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) + return (pud_t *) p4d_deref(p4d) + pud_index(address); + return (pud_t *) p4dp; +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address) +{ + return pud_offset_lockless(p4dp, *p4dp, address); } #define pud_offset pud_offset -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address) +{ + if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) + return (pmd_t *) pud_deref(pud) + pmd_index(address); + return (pmd_t *) pudp; +} +#define pmd_offset_lockless pmd_offset_lockless + +static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address) { - if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) - return (pmd_t *) pud_deref(*pud) + pmd_index(address); - return (pmd_t *) pud; + return pmd_offset_lockless(pudp, *pudp, address); } #define pmd_offset pmd_offset diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index faca269d5f27..a44ddc2f2dec 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -26,6 +26,7 @@ void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); void do_secure_storage_access(struct pt_regs *regs); void do_non_secure_storage_access(struct pt_regs *regs); +void do_secure_storage_violation(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index c73f50649e7e..f7f1e64e0d98 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -39,14 +39,13 @@ void enabled_wait(void) local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ - /* XXX seqcount has tracepoints that require RCU */ - write_seqcount_begin(&idle->seqcount); + raw_write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; account_idle_time(cputime_to_nsecs(idle_time)); - write_seqcount_end(&idle->seqcount); + raw_write_seqcount_end(&idle->seqcount); } NOKPROBE_SYMBOL(enabled_wait); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index 2c27907a5ffc..9a92638360ee 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -80,7 +80,7 @@ PGM_CHECK(do_dat_exception) /* 3b */ PGM_CHECK_DEFAULT /* 3c */ PGM_CHECK(do_secure_storage_access) /* 3d */ PGM_CHECK(do_non_secure_storage_access) /* 3e */ -PGM_CHECK_DEFAULT /* 3f */ +PGM_CHECK(do_secure_storage_violation) /* 3f */ PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ PGM_CHECK_DEFAULT /* 42 */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e600f6953d7c..c2c1b4e723ea 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -619,7 +619,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { if (memory_end_set) memblock_reserve(memory_end, ULONG_MAX); @@ -628,7 +628,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -640,7 +640,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 4c8c063bce5b..996884dcc9fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -859,6 +859,21 @@ void do_non_secure_storage_access(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_non_secure_storage_access); +void do_secure_storage_violation(struct pt_regs *regs) +{ + /* + * Either KVM messed up the secure guest mapping or the same + * page is mapped into multiple secure guests. + * + * This exception is only triggered when a guest 2 is running + * and can therefore never occur in kernel context. + */ + printk_ratelimited(KERN_WARNING + "Secure storage violation in task: %s, pid %d\n", + current->comm, current->pid); + send_sig(SIGSEGV, current, 0); +} + #else void do_secure_storage_access(struct pt_regs *regs) { @@ -869,4 +884,9 @@ void do_non_secure_storage_access(struct pt_regs *regs) { default_trap_handler(regs); } + +void do_secure_storage_violation(struct pt_regs *regs) +{ + default_trap_handler(regs); +} #endif diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 4b62d6b55024..1804230dd8d8 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -668,6 +668,10 @@ EXPORT_SYMBOL_GPL(zpci_enable_device); int zpci_disable_device(struct zpci_dev *zdev) { zpci_dma_exit_device(zdev); + /* + * The zPCI function may already be disabled by the platform, this is + * detected in clp_disable_fh() which becomes a no-op. + */ return clp_disable_fh(zdev); } EXPORT_SYMBOL_GPL(zpci_disable_device); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 9a3a291cad43..d9ae7456dd4c 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -143,6 +143,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zpci_remove_device(zdev); } + zdev->fh = ccdf->fh; + zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; if (!clp_get_state(ccdf->fid, &state) && state == ZPCI_FN_STATE_RESERVED) { diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 1a0d7cf71c10..100bf241340b 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -8,7 +8,6 @@ #ifdef CONFIG_SMP -#include <linux/spinlock.h> #include <linux/atomic.h> #include <asm/current.h> #include <asm/percpu.h> diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index ad963104d22d..91ab2607a1ff 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -370,7 +370,6 @@ syscall_trace_entry: nop cmp/eq #-1, r0 bt syscall_exit - mov.l r0, @(OFF_R0,r15) ! Save return value ! Reload R0-R4 from kernel stack, where the ! parent may have modified them using ! ptrace(POKEUSR). (Note that R0-R2 are diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index b05bf92f9c32..5281685f6ad1 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -455,16 +455,11 @@ long arch_ptrace(struct task_struct *child, long request, asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - /* - * Tracing decided this syscall should not happen. - * We'll return a bogus call number to get an ENOSYS - * error, but leave the original number in regs->regs[0]. - */ - ret = -1L; + tracehook_report_syscall_entry(regs)) { + regs->regs[0] = -ENOSYS; + return -1; + } if (secure_computing() == -1) return -1; @@ -475,7 +470,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); - return ret ?: regs->regs[0]; + return 0; } asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3962f592633d..ff7894f39e0e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -43,6 +43,8 @@ KBUILD_CFLAGS += -Wno-pointer-sign KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS +# Disable relocation relaxation in case the link is not PIE. +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index f556827dea58..78210793d357 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +# CONFIG_64BIT is not set CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 2f84c7ca74ea..870efeec8bda 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -299,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) old_regs = set_irq_regs(regs); instrumentation_begin(); - run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs); + run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); instrumentation_begin(); set_irq_regs(old_regs); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 70dea9337816..d977079a7d02 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs) * rdx: Function argument (can be NULL if none) */ SYM_FUNC_START(asm_call_on_stack) +SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL) +SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL) /* * Save the frame pointer unconditionally. This allows the ORC * unwinder to handle the stack switch. diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index ca0976456a6b..6d2df1ee427b 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -159,8 +159,6 @@ static inline u64 x86_default_get_root_pointer(void) extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ -#define acpi_unlazy_tlb(x) leave_mm(x) - #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 296b346184b2..fb42659f6e98 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -60,12 +60,26 @@ #define FRAME_END "pop %" _ASM_BP "\n" #ifdef CONFIG_X86_64 + #define ENCODE_FRAME_POINTER \ "lea 1(%rsp), %rbp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs + 1; +} + #else /* !CONFIG_X86_64 */ + #define ENCODE_FRAME_POINTER \ "movl %esp, %ebp\n\t" \ "andl $0x7fffffff, %ebp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs & 0x7fffffff; +} + #endif /* CONFIG_X86_64 */ #endif /* __ASSEMBLY__ */ @@ -83,6 +97,11 @@ #define ENCODE_FRAME_POINTER +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return 0; +} + #endif #define FRAME_BEGIN diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index a43366191212..a0638640f1ed 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs) \ instrumentation_begin(); \ irq_enter_rcu(); \ kvm_set_cpu_l1tf_flush_l1d(); \ - run_on_irqstack_cond(__##func, regs, regs); \ + run_sysvec_on_irqstack_cond(__##func, regs); \ irq_exit_rcu(); \ instrumentation_end(); \ irqentry_exit(regs, state); \ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 4ae66f097101..775816965c6a 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void) return __this_cpu_read(irq_count) != -1; } -void asm_call_on_stack(void *sp, void *func, void *arg); +void asm_call_on_stack(void *sp, void (*func)(void), void *arg); +void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs), + struct pt_regs *regs); +void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc), + struct irq_desc *desc); -static __always_inline void __run_on_irqstack(void *func, void *arg) +static __always_inline void __run_on_irqstack(void (*func)(void)) { void *tos = __this_cpu_read(hardirq_stack_ptr); __this_cpu_add(irq_count, 1); - asm_call_on_stack(tos - 8, func, arg); + asm_call_on_stack(tos - 8, func, NULL); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_sysvec_on_stack(tos - 8, func, regs); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_irq_on_stack(tos - 8, func, desc); __this_cpu_sub(irq_count, 1); } #else /* CONFIG_X86_64 */ static inline bool irqstack_active(void) { return false; } -static inline void __run_on_irqstack(void *func, void *arg) { } +static inline void __run_on_irqstack(void (*func)(void)) { } +static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) { } +static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) { } #endif /* !CONFIG_X86_64 */ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) @@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) return !user_mode(regs) && !irqstack_active(); } -static __always_inline void run_on_irqstack_cond(void *func, void *arg, + +static __always_inline void run_on_irqstack_cond(void (*func)(void), struct pt_regs *regs) { - void (*__func)(void *arg) = func; + lockdep_assert_irqs_disabled(); + + if (irq_needs_irq_stack(regs)) + __run_on_irqstack(func); + else + func(); +} + +static __always_inline void +run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + if (irq_needs_irq_stack(regs)) + __run_sysvec_on_irqstack(func, regs); + else + func(regs); +} + +static __always_inline void +run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc, + struct pt_regs *regs) +{ lockdep_assert_irqs_disabled(); if (irq_needs_irq_stack(regs)) - __run_on_irqstack(__func, arg); + __run_irq_on_irqstack(func, desc); else - __func(arg); + func(desc); } #endif diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 779a89e31c4c..21f9c7f11779 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2243,6 +2243,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 181060247e3c..c5dd50369e2f 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -227,7 +227,7 @@ static __always_inline void handle_irq(struct irq_desc *desc, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_X86_64)) - run_on_irqstack_cond(desc->handle_irq, desc, regs); + run_irq_on_irqstack_cond(desc->handle_irq, desc, regs); else __handle_irq(desc, regs); } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 1b4fe93a86c5..440eed558558 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu) void do_softirq_own_stack(void) { - run_on_irqstack_cond(__do_softirq, NULL, NULL); + run_on_irqstack_cond(__do_softirq, NULL); } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1b51b727b140..9663ba31347c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -652,6 +652,7 @@ static void __init kvm_guest_init(void) } if (pv_tlb_flush_supported()) { + pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; pv_ops.mmu.tlb_remove_table = tlb_remove_table; pr_info("KVM setup pv remote TLB flush\n"); } @@ -764,14 +765,6 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); -static void kvm_free_pv_cpu_mask(void) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) - free_cpumask_var(per_cpu(__pv_cpu_mask, cpu)); -} - static __init int kvm_alloc_cpumask(void) { int cpu; @@ -790,20 +783,11 @@ static __init int kvm_alloc_cpumask(void) if (alloc) for_each_possible_cpu(cpu) { - if (!zalloc_cpumask_var_node( - per_cpu_ptr(&__pv_cpu_mask, cpu), - GFP_KERNEL, cpu_to_node(cpu))) { - goto zalloc_cpumask_fail; - } + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu)); } - apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself; - pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; return 0; - -zalloc_cpumask_fail: - kvm_free_pv_cpu_mask(); - return -ENOMEM; } arch_initcall(kvm_alloc_cpumask); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 13ce616cc7af..ba4593a913fa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -42,6 +42,7 @@ #include <asm/spec-ctrl.h> #include <asm/io_bitmap.h> #include <asm/proto.h> +#include <asm/frame.h> #include "process.h" @@ -133,7 +134,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; - frame->bp = 0; + frame->bp = encode_frame_pointer(childregs); frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c44f3e9140d5..91ea74ae71b8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 8646a797b7a8..7b2a068f08c1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1; module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif +extern bool __read_mostly allow_smaller_maxphyaddr; +module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); + #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ @@ -4803,6 +4806,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * EPT will cause page fault only if we need to * detect illegal GPAs. */ + WARN_ON_ONCE(!allow_smaller_maxphyaddr); kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } else @@ -5331,7 +5335,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -8305,11 +8309,12 @@ static int __init vmx_init(void) vmx_check_vmcs12_offsets(); /* - * Intel processors don't have problems with - * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable - * it for VMX by default + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default */ - allow_smaller_maxphyaddr = true; + if (!enable_ept) + allow_smaller_maxphyaddr = true; return 0; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a2f82127c170..a0e47720f60c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) { - return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + if (!enable_ept) + return true; + + return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; } void dump_vmcs(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1994602a0851..ce856e0ece84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs; u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); -bool __read_mostly allow_smaller_maxphyaddr; +bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); static u64 __read_mostly host_xss; @@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; - case MSR_IA32_TSC: - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + case MSR_IA32_TSC: { + /* + * Intel SDM states that MSR_IA32_TSC read adds the TSC offset + * even when not intercepted. AMD manual doesn't explicitly + * state this but appears to behave the same. + * + * On userspace reads and writes, however, we unconditionally + * operate L1's TSC value to ensure backwards-compatible + * behavior for migration. + */ + u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : + vcpu->arch.tsc_offset; + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; break; + } case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/block/blk-settings.c b/block/blk-settings.c index 76a7e03bcd6c..34b721a2743a 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); +/** + * blk_queue_set_zoned - configure a disk queue zoned model. + * @disk: the gendisk of the queue to configure + * @model: the zoned model to set + * + * Set the zoned model of the request queue of @disk according to @model. + * When @model is BLK_ZONED_HM (host managed), this should be called only + * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option). + * If @model specifies BLK_ZONED_HA (host aware), the effective model used + * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions + * on the disk. + */ +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) +{ + switch (model) { + case BLK_ZONED_HM: + /* + * Host managed devices are supported only if + * CONFIG_BLK_DEV_ZONED is enabled. + */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)); + break; + case BLK_ZONED_HA: + /* + * Host aware devices can be treated either as regular block + * devices (similar to drive managed devices) or as zoned block + * devices to take advantage of the zone command set, similarly + * to host managed devices. We try the latter if there are no + * partitions and zoned block device support is enabled, else + * we do nothing special as far as the block layer is concerned. + */ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || + disk_has_partitions(disk)) + model = BLK_ZONED_NONE; + break; + case BLK_ZONED_NONE: + default: + if (WARN_ON_ONCE(model != BLK_ZONED_NONE)) + model = BLK_ZONED_NONE; + break; + } + + disk->queue->limits.zoned = model; +} +EXPORT_SYMBOL_GPL(blk_queue_set_zoned); + static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 71a30b0d0f05..f66236cff69b 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -161,18 +161,10 @@ static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) } /* Power(C) State timer broadcast control */ -static void lapic_timer_state_broadcast(struct acpi_processor *pr, - struct acpi_processor_cx *cx, - int broadcast) +static bool lapic_timer_needs_broadcast(struct acpi_processor *pr, + struct acpi_processor_cx *cx) { - int state = cx - pr->power.states; - - if (state >= pr->power.timer_broadcast_on_state) { - if (broadcast) - tick_broadcast_enter(); - else - tick_broadcast_exit(); - } + return cx - pr->power.states >= pr->power.timer_broadcast_on_state; } #else @@ -180,10 +172,11 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, static void lapic_timer_check_state(int state, struct acpi_processor *pr, struct acpi_processor_cx *cstate) { } static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { } -static void lapic_timer_state_broadcast(struct acpi_processor *pr, - struct acpi_processor_cx *cx, - int broadcast) + +static bool lapic_timer_needs_broadcast(struct acpi_processor *pr, + struct acpi_processor_cx *cx) { + return false; } #endif @@ -566,32 +559,43 @@ static DEFINE_RAW_SPINLOCK(c3_lock); /** * acpi_idle_enter_bm - enters C3 with proper BM handling + * @drv: cpuidle driver * @pr: Target processor * @cx: Target state context - * @timer_bc: Whether or not to change timer mode to broadcast + * @index: index of target state */ -static void acpi_idle_enter_bm(struct acpi_processor *pr, - struct acpi_processor_cx *cx, bool timer_bc) +static int acpi_idle_enter_bm(struct cpuidle_driver *drv, + struct acpi_processor *pr, + struct acpi_processor_cx *cx, + int index) { - acpi_unlazy_tlb(smp_processor_id()); - - /* - * Must be done before busmaster disable as we might need to - * access HPET ! - */ - if (timer_bc) - lapic_timer_state_broadcast(pr, cx, 1); + static struct acpi_processor_cx safe_cx = { + .entry_method = ACPI_CSTATE_HALT, + }; /* * disable bus master * bm_check implies we need ARB_DIS * bm_control implies whether we can do ARB_DIS * - * That leaves a case where bm_check is set and bm_control is - * not set. In that case we cannot do much, we enter C3 - * without doing anything. + * That leaves a case where bm_check is set and bm_control is not set. + * In that case we cannot do much, we enter C3 without doing anything. */ - if (pr->flags.bm_control) { + bool dis_bm = pr->flags.bm_control; + + /* If we can skip BM, demote to a safe state. */ + if (!cx->bm_sts_skip && acpi_idle_bm_check()) { + dis_bm = false; + index = drv->safe_state_index; + if (index >= 0) { + cx = this_cpu_read(acpi_cstate[index]); + } else { + cx = &safe_cx; + index = -EBUSY; + } + } + + if (dis_bm) { raw_spin_lock(&c3_lock); c3_cpu_count++; /* Disable bus master arbitration when all CPUs are in C3 */ @@ -600,18 +604,21 @@ static void acpi_idle_enter_bm(struct acpi_processor *pr, raw_spin_unlock(&c3_lock); } + rcu_idle_enter(); + acpi_idle_do_entry(cx); + rcu_idle_exit(); + /* Re-enable bus master arbitration */ - if (pr->flags.bm_control) { + if (dis_bm) { raw_spin_lock(&c3_lock); acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); c3_cpu_count--; raw_spin_unlock(&c3_lock); } - if (timer_bc) - lapic_timer_state_broadcast(pr, cx, 0); + return index; } static int acpi_idle_enter(struct cpuidle_device *dev, @@ -625,32 +632,21 @@ static int acpi_idle_enter(struct cpuidle_device *dev, return -EINVAL; if (cx->type != ACPI_STATE_C1) { + if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check) + return acpi_idle_enter_bm(drv, pr, cx, index); + + /* C2 to C1 demotion. */ if (acpi_idle_fallback_to_c1(pr) && num_online_cpus() > 1) { index = ACPI_IDLE_STATE_START; cx = per_cpu(acpi_cstate[index], dev->cpu); - } else if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check) { - if (cx->bm_sts_skip || !acpi_idle_bm_check()) { - acpi_idle_enter_bm(pr, cx, true); - return index; - } else if (drv->safe_state_index >= 0) { - index = drv->safe_state_index; - cx = per_cpu(acpi_cstate[index], dev->cpu); - } else { - acpi_safe_halt(); - return -EBUSY; - } } } - lapic_timer_state_broadcast(pr, cx, 1); - if (cx->type == ACPI_STATE_C3) ACPI_FLUSH_CPU_CACHE(); acpi_idle_do_entry(cx); - lapic_timer_state_broadcast(pr, cx, 0); - return index; } @@ -666,7 +662,13 @@ static int acpi_idle_enter_s2idle(struct cpuidle_device *dev, return 0; if (pr->flags.bm_check) { - acpi_idle_enter_bm(pr, cx, false); + u8 bm_sts_skip = cx->bm_sts_skip; + + /* Don't check BM_STS, do an unconditional ARB_DIS for S2IDLE */ + cx->bm_sts_skip = 1; + acpi_idle_enter_bm(drv, pr, cx, index); + cx->bm_sts_skip = bm_sts_skip; + return 0; } else { ACPI_FLUSH_CPU_CACHE(); @@ -682,11 +684,13 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, { int i, count = ACPI_IDLE_STATE_START; struct acpi_processor_cx *cx; + struct cpuidle_state *state; if (max_cstate == 0) max_cstate = 1; for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) { + state = &acpi_idle_driver.states[count]; cx = &pr->power.states[i]; if (!cx->valid) @@ -694,6 +698,15 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, per_cpu(acpi_cstate[count], dev->cpu) = cx; + if (lapic_timer_needs_broadcast(pr, cx)) + state->flags |= CPUIDLE_FLAG_TIMER_STOP; + + if (cx->type == ACPI_STATE_C3) { + state->flags |= CPUIDLE_FLAG_TLB_FLUSHED; + if (pr->flags.bm_check) + state->flags |= CPUIDLE_FLAG_RCU_IDLE; + } + count++; if (count == CPUIDLE_STATE_MAX) break; diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 39be444534d0..316a9947541f 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2224,7 +2224,7 @@ static int eni_init_one(struct pci_dev *pci_dev, rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (rc < 0) - goto out; + goto err_disable; rc = -ENOMEM; eni_dev = kmalloc(sizeof(struct eni_dev), GFP_KERNEL); diff --git a/drivers/base/node.c b/drivers/base/node.c index 508b80f6329b..50af16e68d98 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn) return pfn_to_nid(pfn); } +static int do_register_memory_block_under_node(int nid, + struct memory_block *mem_blk) +{ + int ret; + + /* + * If this memory block spans multiple nodes, we only indicate + * the last processed node. + */ + mem_blk->nid = nid; + + ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, + &mem_blk->dev.kobj, + kobject_name(&mem_blk->dev.kobj)); + if (ret) + return ret; + + return sysfs_create_link_nowarn(&mem_blk->dev.kobj, + &node_devices[nid]->dev.kobj, + kobject_name(&node_devices[nid]->dev.kobj)); +} + /* register memory section under specified node if it spans that node */ -static int register_mem_sect_under_node(struct memory_block *mem_blk, - void *arg) +static int register_mem_block_under_node_early(struct memory_block *mem_blk, + void *arg) { unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE; unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); unsigned long end_pfn = start_pfn + memory_block_pfns - 1; - int ret, nid = *(int *)arg; + int nid = *(int *)arg; unsigned long pfn; for (pfn = start_pfn; pfn <= end_pfn; pfn++) { @@ -785,39 +807,34 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk, } /* - * We need to check if page belongs to nid only for the boot - * case, during hotplug we know that all pages in the memory - * block belong to the same node. - */ - if (system_state == SYSTEM_BOOTING) { - page_nid = get_nid_for_pfn(pfn); - if (page_nid < 0) - continue; - if (page_nid != nid) - continue; - } - - /* - * If this memory block spans multiple nodes, we only indicate - * the last processed node. + * We need to check if page belongs to nid only at the boot + * case because node's ranges can be interleaved. */ - mem_blk->nid = nid; - - ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, - &mem_blk->dev.kobj, - kobject_name(&mem_blk->dev.kobj)); - if (ret) - return ret; + page_nid = get_nid_for_pfn(pfn); + if (page_nid < 0) + continue; + if (page_nid != nid) + continue; - return sysfs_create_link_nowarn(&mem_blk->dev.kobj, - &node_devices[nid]->dev.kobj, - kobject_name(&node_devices[nid]->dev.kobj)); + return do_register_memory_block_under_node(nid, mem_blk); } /* mem section does not span the specified node */ return 0; } /* + * During hotplug we know that all pages in the memory block belong to the same + * node. + */ +static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk, + void *arg) +{ + int nid = *(int *)arg; + + return do_register_memory_block_under_node(nid, mem_blk); +} + +/* * Unregister a memory block device under the node it spans. Memory blocks * with multiple nodes cannot be offlined and therefore also never be removed. */ @@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk) kobject_name(&node_devices[mem_blk->nid]->dev.kobj)); } -int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn) +int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, + enum meminit_context context) { + walk_memory_blocks_func_t func; + + if (context == MEMINIT_HOTPLUG) + func = register_mem_block_under_node_hotplug; + else + func = register_mem_block_under_node_early; + return walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), (void *)&nid, - register_mem_sect_under_node); + func); } #ifdef CONFIG_HUGETLBFS diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 3d80c4b43f72..7be2fcfeea52 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -217,7 +217,7 @@ struct regmap_field { #ifdef CONFIG_DEBUG_FS extern void regmap_debugfs_initcall(void); -extern void regmap_debugfs_init(struct regmap *map, const char *name); +extern void regmap_debugfs_init(struct regmap *map); extern void regmap_debugfs_exit(struct regmap *map); static inline void regmap_debugfs_disable(struct regmap *map) @@ -227,7 +227,7 @@ static inline void regmap_debugfs_disable(struct regmap *map) #else static inline void regmap_debugfs_initcall(void) { } -static inline void regmap_debugfs_init(struct regmap *map, const char *name) { } +static inline void regmap_debugfs_init(struct regmap *map) { } static inline void regmap_debugfs_exit(struct regmap *map) { } static inline void regmap_debugfs_disable(struct regmap *map) { } #endif @@ -259,7 +259,7 @@ bool regcache_set_val(struct regmap *map, void *base, unsigned int idx, int regcache_lookup_reg(struct regmap *map, unsigned int reg); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len); + const void *val, size_t val_len, bool noinc); void regmap_async_complete_cb(struct regmap_async *async, int ret); diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index a93cafd7be4f..7f4b3b62492c 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -717,7 +717,7 @@ static int regcache_sync_block_raw_flush(struct regmap *map, const void **data, map->cache_bypass = true; - ret = _regmap_raw_write(map, base, *data, count * val_bytes); + ret = _regmap_raw_write(map, base, *data, count * val_bytes, false); if (ret) dev_err(map->dev, "Unable to sync registers %#x-%#x. %d\n", base, cur - map->reg_stride, ret); diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index f58baff2be0a..b6d63ef16b44 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -17,7 +17,6 @@ struct regmap_debugfs_node { struct regmap *map; - const char *name; struct list_head link; }; @@ -544,11 +543,12 @@ static const struct file_operations regmap_cache_bypass_fops = { .write = regmap_cache_bypass_write_file, }; -void regmap_debugfs_init(struct regmap *map, const char *name) +void regmap_debugfs_init(struct regmap *map) { struct rb_node *next; struct regmap_range_node *range_node; const char *devname = "dummy"; + const char *name = map->name; /* * Userspace can initiate reads from the hardware over debugfs. @@ -569,7 +569,6 @@ void regmap_debugfs_init(struct regmap *map, const char *name) if (!node) return; node->map = map; - node->name = name; mutex_lock(®map_debugfs_early_lock); list_add(&node->link, ®map_debugfs_early_list); mutex_unlock(®map_debugfs_early_lock); @@ -679,7 +678,7 @@ void regmap_debugfs_initcall(void) mutex_lock(®map_debugfs_early_lock); list_for_each_entry_safe(node, tmp, ®map_debugfs_early_list, link) { - regmap_debugfs_init(node->map, node->name); + regmap_debugfs_init(node->map); list_del(&node->link); kfree(node); } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index e93700af7e6e..b71f9ecddff5 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -581,14 +581,34 @@ static void regmap_range_exit(struct regmap *map) kfree(map->selector_work_buf); } +static int regmap_set_name(struct regmap *map, const struct regmap_config *config) +{ + if (config->name) { + const char *name = kstrdup_const(config->name, GFP_KERNEL); + + if (!name) + return -ENOMEM; + + kfree_const(map->name); + map->name = name; + } + + return 0; +} + int regmap_attach_dev(struct device *dev, struct regmap *map, const struct regmap_config *config) { struct regmap **m; + int ret; map->dev = dev; - regmap_debugfs_init(map, config->name); + ret = regmap_set_name(map, config); + if (ret) + return ret; + + regmap_debugfs_init(map); /* Add a devres resource for dev_get_regmap() */ m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL); @@ -687,13 +707,9 @@ struct regmap *__regmap_init(struct device *dev, goto err; } - if (config->name) { - map->name = kstrdup_const(config->name, GFP_KERNEL); - if (!map->name) { - ret = -ENOMEM; - goto err_map; - } - } + ret = regmap_set_name(map, config); + if (ret) + goto err_map; if (config->disable_locking) { map->lock = map->unlock = regmap_lock_unlock_none; @@ -1137,7 +1153,7 @@ skip_format_initialization: if (ret != 0) goto err_regcache; } else { - regmap_debugfs_init(map, config->name); + regmap_debugfs_init(map); } return map; @@ -1297,6 +1313,8 @@ EXPORT_SYMBOL_GPL(regmap_field_free); */ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) { + int ret; + regcache_exit(map); regmap_debugfs_exit(map); @@ -1309,7 +1327,11 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; - regmap_debugfs_init(map, config->name); + ret = regmap_set_name(map, config); + if (ret) + return ret; + + regmap_debugfs_init(map); map->cache_bypass = false; map->cache_only = false; @@ -1464,7 +1486,7 @@ static void regmap_set_work_buf_flag_mask(struct regmap *map, int max_bytes, } static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { struct regmap_range_node *range; unsigned long flags; @@ -1523,7 +1545,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue, val_len / map->format.val_bytes); ret = _regmap_raw_write_impl(map, reg, val, win_residue * - map->format.val_bytes); + map->format.val_bytes, noinc); if (ret != 0) return ret; @@ -1537,7 +1559,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue = range->window_len - win_offset; } - ret = _regmap_select_page(map, ®, range, val_num); + ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_num); if (ret != 0) return ret; } @@ -1745,7 +1767,8 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, map->work_buf + map->format.reg_bytes + map->format.pad_bytes, - map->format.val_bytes); + map->format.val_bytes, + false); } static inline void *_regmap_map_get_context(struct regmap *map) @@ -1839,7 +1862,7 @@ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val) EXPORT_SYMBOL_GPL(regmap_write_async); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; @@ -1860,7 +1883,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write as many bytes as possible with chunk_size */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes); + ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes, noinc); if (ret) return ret; @@ -1871,7 +1894,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write remaining bytes */ if (val_len) - ret = _regmap_raw_write_impl(map, reg, val, val_len); + ret = _regmap_raw_write_impl(map, reg, val, val_len, noinc); return ret; } @@ -1904,7 +1927,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, map->lock(map->lock_arg); - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->unlock(map->lock_arg); @@ -1962,7 +1985,7 @@ int regmap_noinc_write(struct regmap *map, unsigned int reg, write_len = map->max_raw_write; else write_len = val_len; - ret = _regmap_raw_write(map, reg, val, write_len); + ret = _regmap_raw_write(map, reg, val, write_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + write_len; @@ -2439,7 +2462,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, map->async = true; - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->async = false; @@ -2450,7 +2473,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, EXPORT_SYMBOL_GPL(regmap_raw_write_async); static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, - unsigned int val_len) + unsigned int val_len, bool noinc) { struct regmap_range_node *range; int ret; @@ -2463,7 +2486,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, - val_len / map->format.val_bytes); + noinc ? 1 : val_len / map->format.val_bytes); if (ret != 0) return ret; } @@ -2501,7 +2524,7 @@ static int _regmap_bus_read(void *context, unsigned int reg, if (!map->format.parse_val) return -EINVAL; - ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes); + ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false); if (ret == 0) *val = map->format.parse_val(work_val); @@ -2617,7 +2640,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read bytes that fit into whole chunks */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_read(map, reg, val, chunk_bytes); + ret = _regmap_raw_read(map, reg, val, chunk_bytes, false); if (ret != 0) goto out; @@ -2628,7 +2651,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read remaining bytes */ if (val_len) { - ret = _regmap_raw_read(map, reg, val, val_len); + ret = _regmap_raw_read(map, reg, val, val_len, false); if (ret != 0) goto out; } @@ -2703,7 +2726,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, read_len = map->max_raw_read; else read_len = val_len; - ret = _regmap_raw_read(map, reg, val, read_len); + ret = _regmap_raw_read(map, reg, val, read_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + read_len; diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c index 1d740a8c42ab..47114c2a7cb5 100644 --- a/drivers/clocksource/h8300_timer8.c +++ b/drivers/clocksource/h8300_timer8.c @@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node) return PTR_ERR(clk); } - ret = ENXIO; + ret = -ENXIO; base = of_iomap(node, 0); if (!base) { pr_err("failed to map registers for clockevent\n"); diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c index 8eeafa82c03d..d17367dee02c 100644 --- a/drivers/clocksource/timer-clint.c +++ b/drivers/clocksource/timer-clint.c @@ -19,6 +19,11 @@ #include <linux/interrupt.h> #include <linux/of_irq.h> #include <linux/smp.h> +#include <linux/timex.h> + +#ifndef CONFIG_RISCV_M_MODE +#include <asm/clint.h> +#endif #define CLINT_IPI_OFF 0 #define CLINT_TIMER_CMP_OFF 0x4000 @@ -31,6 +36,10 @@ static u64 __iomem *clint_timer_val; static unsigned long clint_timer_freq; static unsigned int clint_timer_irq; +#ifdef CONFIG_RISCV_M_MODE +u64 __iomem *clint_time_val; +#endif + static void clint_send_ipi(const struct cpumask *target) { unsigned int cpu; @@ -184,6 +193,14 @@ static int __init clint_timer_init_dt(struct device_node *np) clint_timer_val = base + CLINT_TIMER_VAL_OFF; clint_timer_freq = riscv_timebase; +#ifdef CONFIG_RISCV_M_MODE + /* + * Yes, that's an odd naming scheme. time_val is public, but hopefully + * will die in favor of something cleaner. + */ + clint_time_val = clint_timer_val; +#endif + pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq); rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq); diff --git a/drivers/clocksource/timer-gx6605s.c b/drivers/clocksource/timer-gx6605s.c index 80d0939d040b..8d386adbe800 100644 --- a/drivers/clocksource/timer-gx6605s.c +++ b/drivers/clocksource/timer-gx6605s.c @@ -28,6 +28,7 @@ static irqreturn_t gx6605s_timer_interrupt(int irq, void *dev) void __iomem *base = timer_of_base(to_timer_of(ce)); writel_relaxed(GX6605S_STATUS_CLR, base + TIMER_STATUS); + writel_relaxed(0, base + TIMER_INI); ce->event_handler(ce); diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index f6fd1c1cc527..33b3e8aa2cc5 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -69,12 +69,33 @@ static bool dmtimer_systimer_revision1(struct dmtimer_systimer *t) return !(tidr >> 16); } +static void dmtimer_systimer_enable(struct dmtimer_systimer *t) +{ + u32 val; + + if (dmtimer_systimer_revision1(t)) + val = DMTIMER_TYPE1_ENABLE; + else + val = DMTIMER_TYPE2_ENABLE; + + writel_relaxed(val, t->base + t->sysc); +} + +static void dmtimer_systimer_disable(struct dmtimer_systimer *t) +{ + if (!dmtimer_systimer_revision1(t)) + return; + + writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc); +} + static int __init dmtimer_systimer_type1_reset(struct dmtimer_systimer *t) { void __iomem *syss = t->base + OMAP_TIMER_V1_SYS_STAT_OFFSET; int ret; u32 l; + dmtimer_systimer_enable(t); writel_relaxed(BIT(1) | BIT(2), t->base + t->ifctrl); ret = readl_poll_timeout_atomic(syss, l, l & BIT(0), 100, DMTIMER_RESET_WAIT); @@ -88,6 +109,7 @@ static int __init dmtimer_systimer_type2_reset(struct dmtimer_systimer *t) void __iomem *sysc = t->base + t->sysc; u32 l; + dmtimer_systimer_enable(t); l = readl_relaxed(sysc); l |= BIT(0); writel_relaxed(l, sysc); @@ -336,26 +358,6 @@ static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t, return 0; } -static void dmtimer_systimer_enable(struct dmtimer_systimer *t) -{ - u32 val; - - if (dmtimer_systimer_revision1(t)) - val = DMTIMER_TYPE1_ENABLE; - else - val = DMTIMER_TYPE2_ENABLE; - - writel_relaxed(val, t->base + t->sysc); -} - -static void dmtimer_systimer_disable(struct dmtimer_systimer *t) -{ - if (!dmtimer_systimer_revision1(t)) - return; - - writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc); -} - static int __init dmtimer_systimer_setup(struct device_node *np, struct dmtimer_systimer *t) { @@ -409,8 +411,8 @@ static int __init dmtimer_systimer_setup(struct device_node *np, t->wakeup = regbase + _OMAP_TIMER_WAKEUP_EN_OFFSET; t->ifctrl = regbase + _OMAP_TIMER_IF_CTRL_OFFSET; - dmtimer_systimer_enable(t); dmtimer_systimer_reset(t); + dmtimer_systimer_enable(t); pr_debug("dmtimer rev %08x sysc %08x\n", readl_relaxed(t->base), readl_relaxed(t->base + t->sysc)); diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index 74463841805f..d928b37718bd 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -66,7 +66,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev, return -1; /* Do runtime PM to manage a hierarchical CPU toplogy. */ - pm_runtime_put_sync_suspend(pd_dev); + RCU_NONIDLE(pm_runtime_put_sync_suspend(pd_dev)); state = psci_get_domain_state(); if (!state) @@ -74,7 +74,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev, ret = psci_cpu_suspend_enter(state) ? -1 : idx; - pm_runtime_get_sync(pd_dev); + RCU_NONIDLE(pm_runtime_get_sync(pd_dev)); cpu_pm_exit(); diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index ff6d99e923a4..a2b5c6f60cf0 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -361,7 +361,10 @@ static void __init fixup_cede0_latency(void) for (i = 0; i < nr_xcede_records; i++) { struct xcede_latency_record *record = &payload->records[i]; u64 latency_tb = be64_to_cpu(record->latency_ticks); - u64 latency_us = tb_to_ns(latency_tb) / NSEC_PER_USEC; + u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC); + + if (latency_us == 0) + pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i); if (latency_us < min_latency_us) min_latency_us = latency_us; @@ -378,10 +381,14 @@ static void __init fixup_cede0_latency(void) * Perform the fix-up. */ if (min_latency_us < dedicated_states[1].exit_latency) { - u64 cede0_latency = min_latency_us - 1; + /* + * We set a minimum of 1us wakeup latency for cede0 to + * distinguish it from snooze + */ + u64 cede0_latency = 1; - if (cede0_latency <= 0) - cede0_latency = min_latency_us; + if (min_latency_us > cede0_latency) + cede0_latency = min_latency_us - 1; dedicated_states[1].exit_latency = cede0_latency; dedicated_states[1].target_residency = 10 * (cede0_latency); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 04becd70cc41..29e84687f3c3 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -138,14 +138,10 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) { ktime_t time_start, time_end; + struct cpuidle_state *target_state = &drv->states[index]; time_start = ns_to_ktime(local_clock()); - /* - * trace_suspend_resume() called by tick_freeze() for the last CPU - * executing it contains RCU usage regarded as invalid in the idle - * context, so tell RCU about that. - */ tick_freeze(); /* * The state used here cannot be a "coupled" one, because the "coupled" @@ -153,16 +149,13 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv, * suspended is generally unsafe. */ stop_critical_timings(); - rcu_idle_enter(); - drv->states[index].enter_s2idle(dev, drv, index); + if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) + rcu_idle_enter(); + target_state->enter_s2idle(dev, drv, index); if (WARN_ON_ONCE(!irqs_disabled())) local_irq_disable(); - /* - * timekeeping_resume() that will be called by tick_unfreeze() for the - * first CPU executing it calls functions containing RCU read-side - * critical sections, so tell RCU about that. - */ - rcu_idle_exit(); + if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) + rcu_idle_exit(); tick_unfreeze(); start_critical_timings(); @@ -239,9 +232,11 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, time_start = ns_to_ktime(local_clock()); stop_critical_timings(); - rcu_idle_enter(); + if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) + rcu_idle_enter(); entered_state = target_state->enter(dev, drv, index); - rcu_idle_exit(); + if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) + rcu_idle_exit(); start_critical_timings(); sched_clock_idle_wakeup_event(); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e5767c83ea23..e84070b55463 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -85,6 +85,12 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, return false; } + if (!dax_dev) { + pr_debug("%s: error: dax unsupported by block device\n", + bdevname(bdev, buf)); + return false; + } + err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff); if (err) { pr_info("%s: error: unaligned partition for dax\n", @@ -100,12 +106,6 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, return false; } - if (!dax_dev || !bdev_dax_supported(bdev, blocksize)) { - pr_debug("%s: error: dax unsupported by block device\n", - bdevname(bdev, buf)); - return false; - } - id = dax_read_lock(); len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn); len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn); @@ -325,11 +325,15 @@ EXPORT_SYMBOL_GPL(dax_direct_access); bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len) { + if (!dax_dev) + return false; + if (!dax_alive(dax_dev)) return false; return dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len); } +EXPORT_SYMBOL_GPL(dax_supported); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 561d91b2d3bf..071b59fe84d2 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -1766,20 +1766,23 @@ static int devfreq_summary_show(struct seq_file *s, void *data) struct devfreq *p_devfreq = NULL; unsigned long cur_freq, min_freq, max_freq; unsigned int polling_ms; + unsigned int timer; - seq_printf(s, "%-30s %-30s %-15s %10s %12s %12s %12s\n", + seq_printf(s, "%-30s %-30s %-15s %-10s %10s %12s %12s %12s\n", "dev", "parent_dev", "governor", + "timer", "polling_ms", "cur_freq_Hz", "min_freq_Hz", "max_freq_Hz"); - seq_printf(s, "%30s %30s %15s %10s %12s %12s %12s\n", + seq_printf(s, "%30s %30s %15s %10s %10s %12s %12s %12s\n", "------------------------------", "------------------------------", "---------------", "----------", + "----------", "------------", "------------", "------------"); @@ -1803,13 +1806,15 @@ static int devfreq_summary_show(struct seq_file *s, void *data) cur_freq = devfreq->previous_freq; get_freq_range(devfreq, &min_freq, &max_freq); polling_ms = devfreq->profile->polling_ms; + timer = devfreq->profile->timer; mutex_unlock(&devfreq->lock); seq_printf(s, - "%-30s %-30s %-15s %10d %12ld %12ld %12ld\n", + "%-30s %-30s %-15s %-10s %10d %12ld %12ld %12ld\n", dev_name(&devfreq->dev), p_devfreq ? dev_name(&p_devfreq->dev) : "null", devfreq->governor_name, + polling_ms ? timer_name[timer] : "null", polling_ms, cur_freq, min_freq, diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index e94a27804c20..dedd39de7367 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -836,7 +836,8 @@ static int tegra_devfreq_probe(struct platform_device *pdev) rate = clk_round_rate(tegra->emc_clock, ULONG_MAX); if (rate < 0) { dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate); - return rate; + err = rate; + goto disable_clk; } tegra->max_freq = rate / KHZ; @@ -897,6 +898,7 @@ remove_opps: dev_pm_opp_remove_all_dynamic(&pdev->dev); reset_control_reset(tegra->reset); +disable_clk: clk_disable_unprepare(tegra->clock); return err; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 58564d82a3a2..844967f98866 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -59,6 +59,8 @@ static void dma_buf_release(struct dentry *dentry) struct dma_buf *dmabuf; dmabuf = dentry->d_fsdata; + if (unlikely(!dmabuf)) + return; BUG_ON(dmabuf->vmapping_counter); diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 54ebc8afc6b1..94d1e3165052 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -508,6 +508,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) if (!force_load && idx < 0) return -ENODEV; } else { + force_load = true; idx = 0; } @@ -629,9 +630,13 @@ void ghes_edac_unregister(struct ghes *ghes) struct mem_ctl_info *mci; unsigned long flags; + if (!force_load) + return; + mutex_lock(&ghes_reg_mutex); system_scanned = false; + memset(&ghes_hw, 0, sizeof(struct ghes_hw_desc)); if (!refcount_dec_and_test(&ghes_refcount)) goto unlock; diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c index 35dccc88ac0a..15a47539dc56 100644 --- a/drivers/firmware/efi/efibc.c +++ b/drivers/firmware/efi/efibc.c @@ -84,7 +84,7 @@ static int __init efibc_init(void) { int ret; - if (!efi_enabled(EFI_RUNTIME_SERVICES)) + if (!efivars_kobject() || !efivar_supports_writes()) return -ENODEV; ret = register_reboot_notifier(&efibc_reboot_notifier); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index d8c6520ff74a..06757681b2ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -178,7 +178,7 @@ static int psp_sw_init(void *handle) return ret; } - if (adev->asic_type == CHIP_NAVI10) { + if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) { ret= psp_sysfs_init(adev); if (ret) { return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index e16874f30d5d..6c5d9612abcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin"); MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin"); +MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e0e60b0d0669..0f4508b4903e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1216,6 +1216,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) dqm->sched_running = false; dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets, hanging); @@ -1326,7 +1328,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (q->properties.is_active) { increment_queue_count(dqm, q->properties.type); - retval = execute_queues_cpsch(dqm, + execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b51c527a3f0d..4ba8b54a2695 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5278,19 +5278,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -5354,19 +5341,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 9140b3fc767a..f31f48dd0da2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -409,8 +409,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h index d3192b9d0c3d..47f8ee2832ff 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h @@ -27,7 +27,7 @@ #define MOD_HDCP_LOG_H_ #ifdef CONFIG_DRM_AMD_DC_HDCP -#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__) +#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index fb1161dd7ea8..3a367a5968ae 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS; if (!psp->dtm_context.dtm_initialized) { - DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); + DRM_INFO("Failed to add display topology, DTM TA is not initialized."); display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 0826625573dc..63f945f9f331 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1126,7 +1126,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && - (adev->asic_type <= CHIP_NAVI12)) + (adev->asic_type <= CHIP_NAVY_FLOUNDER)) return 0; /* @@ -1211,7 +1211,9 @@ static int smu_hw_fini(void *handle) int smu_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int ret = 0; + int ret; + + amdgpu_gfx_off_ctrl(smu->adev, false); ret = smu_hw_fini(adev); if (ret) @@ -1222,8 +1224,12 @@ int smu_reset(struct smu_context *smu) return ret; ret = smu_late_init(adev); + if (ret) + return ret; - return ret; + amdgpu_gfx_off_ctrl(smu->adev, true); + + return 0; } static int smu_suspend(void *handle) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index d0bdb6d447ed..ef755dd5e68f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine) return __reset_engine(engine); } -static struct intel_engine_cs *__active_engine(struct i915_request *rq) +static bool +__active_engine(struct i915_request *rq, struct intel_engine_cs **active) { struct intel_engine_cs *engine, *locked; + bool ret = false; /* * Serialise with __i915_request_submit() so that it sees * is-banned?, or we know the request is already inflight. + * + * Note that rq->engine is unstable, and so we double + * check that we have acquired the lock on the final engine. */ locked = READ_ONCE(rq->engine); spin_lock_irq(&locked->active.lock); while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) { spin_unlock(&locked->active.lock); - spin_lock(&engine->active.lock); locked = engine; + spin_lock(&locked->active.lock); } - engine = NULL; - if (i915_request_is_active(rq) && rq->fence.error != -EIO) - engine = rq->engine; + if (!i915_request_completed(rq)) { + if (i915_request_is_active(rq) && rq->fence.error != -EIO) + *active = locked; + ret = true; + } spin_unlock_irq(&locked->active.lock); - return engine; + return ret; } static struct intel_engine_cs *active_engine(struct intel_context *ce) @@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (!ce->timeline) return NULL; - mutex_lock(&ce->timeline->mutex); - list_for_each_entry_reverse(rq, &ce->timeline->requests, link) { - if (i915_request_completed(rq)) - break; + rcu_read_lock(); + list_for_each_entry_rcu(rq, &ce->timeline->requests, link) { + if (i915_request_is_active(rq) && i915_request_completed(rq)) + continue; /* Check with the backend if the request is inflight */ - engine = __active_engine(rq); - if (engine) + if (__active_engine(rq, &engine)) break; } - mutex_unlock(&ce->timeline->mutex); + rcu_read_unlock(); return engine; } @@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915) ctx->i915 = i915; ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL); mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->link); spin_lock_init(&ctx->stale.lock); INIT_LIST_HEAD(&ctx->stale.engines); @@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915) for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; - spin_lock(&i915->gem.contexts.lock); - list_add_tail(&ctx->link, &i915->gem.contexts.list); - spin_unlock(&i915->gem.contexts.lock); - return ctx; err_free: @@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx, struct drm_i915_file_private *fpriv, u32 *id) { + struct drm_i915_private *i915 = ctx->i915; struct i915_address_space *vm; int ret; @@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx, /* And finally expose ourselves to userspace via the idr */ ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL); if (ret) - put_pid(fetch_and_zero(&ctx->pid)); + goto err_pid; + + spin_lock(&i915->gem.contexts.lock); + list_add_tail(&ctx->link, &i915->gem.contexts.list); + spin_unlock(&i915->gem.contexts.lock); + + return 0; +err_pid: + put_pid(fetch_and_zero(&ctx->pid)); return ret; } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 24322ef08aa4..9eeaca957a7e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count) memset_p((void **)ports, NULL, count); } +static inline void +copy_ports(struct i915_request **dst, struct i915_request **src, int count) +{ + /* A memcpy_p() would be very useful here! */ + while (count--) + WRITE_ONCE(*dst++, *src++); /* avoid write tearing */ +} + static void execlists_dequeue(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine) /* switch pending to inflight */ GEM_BUG_ON(!assert_pending_valid(execlists, "promote")); - memcpy(execlists->inflight, - execlists->pending, - execlists_num_ports(execlists) * - sizeof(*execlists->pending)); + copy_ports(execlists->inflight, + execlists->pending, + execlists_num_ports(execlists)); smp_wmb(); /* complete the seqlock */ WRITE_ONCE(execlists->active, execlists->inflight); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 8fa9b31a2484..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_creation_params *param) { + struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_vgpu *vgpu; int ret; @@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); + if (IS_BROADWELL(dev_priv)) + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); + else + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 0b2fe55e6194..781a6783affe 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal) * As we know that there are always preemption points between * requests, we know that only the currently executing request * may be still active even though we have cleared the flag. - * However, we can't rely on our tracking of ELSP[0] to known + * However, we can't rely on our tracking of ELSP[0] to know * which request is currently active and so maybe stuck, as * the tracking maybe an event behind. Instead assume that * if the context is still inflight, then it is still active * even if the active flag has been cleared. + * + * To further complicate matters, if there a pending promotion, the HW + * may either perform a context switch to the second inflight execlists, + * or it may switch to the pending set of execlists. In the case of the + * latter, it may send the ACK and we process the event copying the + * pending[] over top of inflight[], _overwriting_ our *active. Since + * this implies the HW is arbitrating and not struck in *active, we do + * not worry about complete accuracy, but we do require no read/write + * tearing of the pointer [the read of the pointer must be valid, even + * as the array is being overwritten, for which we require the writes + * to avoid tearing.] + * + * Note that the read of *execlists->active may race with the promotion + * of execlists->pending[] to execlists->inflight[], overwritting + * the value at *execlists->active. This is fine. The promotion implies + * that we received an ACK from the HW, and so the context is not + * stuck -- if we do not see ourselves in *active, the inflight status + * is valid. If instead we see ourselves being copied into *active, + * we are inflight and may signal the callback. */ if (!intel_context_inflight(signal->context)) return false; rcu_read_lock(); - for (port = __engine_active(signal->engine); (rq = *port); port++) { + for (port = __engine_active(signal->engine); + (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */ + port++) { if (rq->context == signal->context) { inflight = i915_seqno_passed(rq->fence.seqno, signal->fence.seqno); diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 295b9829e2da..4cd2038cbe35 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, do { list_for_each_entry_safe(pos, next, &x->head, entry) { - pos->func(pos, - TASK_NORMAL, fence->error, - &extra); + int wake_flags; + + wake_flags = fence->error; + if (pos->func == autoremove_wake_function) + wake_flags = 0; + + pos->func(pos, TASK_NORMAL, wake_flags, &extra); } if (list_empty(&extra)) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index f127e633f7ca..397c313a8b69 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { - struct drm_i915_private *i915; - struct pci_dev *pdev; #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - struct dev_iommu iommu; + static struct dev_iommu fake_iommu = { .priv = (void *)-1 }; #endif + struct drm_i915_private *i915; + struct pci_dev *pdev; int err; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); @@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ - memset(&iommu, 0, sizeof(iommu)); - iommu.priv = (void *)-1; - pdev->dev.iommu = &iommu; + /* HACK to disable iommu for the fake device; force identity mapping */ + pdev->dev.iommu = &fake_iommu; #endif pci_set_drvdata(pdev, i915); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 3fc5511330b9..4d29568be3f5 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -831,13 +831,19 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_index(&mtk_crtc->base)); mtk_crtc->cmdq_client = NULL; } - ret = of_property_read_u32_index(priv->mutex_node, - "mediatek,gce-events", - drm_crtc_index(&mtk_crtc->base), - &mtk_crtc->cmdq_event); - if (ret) - dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", - drm_crtc_index(&mtk_crtc->base)); + + if (mtk_crtc->cmdq_client) { + ret = of_property_read_u32_index(priv->mutex_node, + "mediatek,gce-events", + drm_crtc_index(&mtk_crtc->base), + &mtk_crtc->cmdq_event); + if (ret) { + dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", + drm_crtc_index(&mtk_crtc->base)); + cmdq_mbox_destroy(mtk_crtc->cmdq_client); + mtk_crtc->cmdq_client = NULL; + } + } #endif return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 57c88de9a329..526648885b97 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -496,6 +496,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, #if IS_REACHABLE(CONFIG_MTK_CMDQ) if (of_address_to_resource(node, 0, &res) != 0) { dev_err(dev, "Missing reg in %s node\n", node->full_name); + put_device(&larb_pdev->dev); return -EINVAL; } comp->regs_pa = res.start; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 040a8f393fe2..2d982740b1a4 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -27,7 +27,6 @@ #include "mtk_drm_crtc.h" #include "mtk_drm_ddp.h" -#include "mtk_drm_ddp.h" #include "mtk_drm_ddp_comp.h" #include "mtk_drm_drv.h" #include "mtk_drm_gem.h" @@ -165,7 +164,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto put_mutex_dev; drm->mode_config.min_width = 64; drm->mode_config.min_height = 64; @@ -182,7 +181,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = component_bind_all(drm->dev, drm); if (ret) - return ret; + goto put_mutex_dev; /* * We currently support two fixed data streams, each optional, @@ -229,7 +228,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) } if (!dma_dev->dma_parms) { ret = -ENOMEM; - goto err_component_unbind; + goto put_dma_dev; } ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); @@ -256,9 +255,12 @@ static int mtk_drm_kms_init(struct drm_device *drm) err_unset_dma_parms: if (private->dma_parms_allocated) dma_dev->dma_parms = NULL; +put_dma_dev: + put_device(private->dma_dev); err_component_unbind: component_unbind_all(drm->dev, drm); - +put_mutex_dev: + put_device(private->mutex_dev); return ret; } @@ -544,8 +546,13 @@ err_pm: pm_runtime_disable(dev); err_node: of_node_put(private->mutex_node); - for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) + for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) { of_node_put(private->comp_node[i]); + if (private->ddp_comp[i]) { + put_device(private->ddp_comp[i]->larb_dev); + private->ddp_comp[i] = NULL; + } + } return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 16fd99dcdacf..80b7a082e874 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -466,14 +466,13 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = - (vm->hback_porch * dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; else - horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * + dsi_tmp_buf_bpp; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit + 3; + timing->da_hs_zero + timing->da_hs_exit; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index f2e9b429960b..a97725680d4e 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1507,25 +1507,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to get system configuration registers: %d\n", ret); - return ret; + goto put_device; } hdmi->sys_regmap = regmap; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); hdmi->regs = devm_ioremap_resource(dev, mem); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + if (IS_ERR(hdmi->regs)) { + ret = PTR_ERR(hdmi->regs); + goto put_device; + } remote = of_graph_get_remote_node(np, 1, 0); - if (!remote) - return -EINVAL; + if (!remote) { + ret = -EINVAL; + goto put_device; + } if (!of_device_is_compatible(remote, "hdmi-connector")) { hdmi->next_bridge = of_drm_find_bridge(remote); if (!hdmi->next_bridge) { dev_err(dev, "Waiting for external bridge\n"); of_node_put(remote); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto put_device; } } @@ -1534,7 +1539,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n", remote); of_node_put(remote); - return -EINVAL; + ret = -EINVAL; + goto put_device; } of_node_put(remote); @@ -1542,10 +1548,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, of_node_put(i2c_np); if (!hdmi->ddc_adpt) { dev_err(dev, "Failed to get ddc i2c adapter by node\n"); - return -EINVAL; + ret = -EINVAL; + goto put_device; } return 0; +put_device: + put_device(hdmi->cec_dev); + return ret; } /* diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 7b69d6dfe44a..e0ae911ef427 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -933,7 +933,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div, /* get matching reference and feedback divider */ *ref_div = min(max(den/post_div, 1u), ref_div_max); - *fb_div = max(nom * *ref_div * post_div / den, 1u); + *fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den); /* limit fb divider to its maximum */ if (*fb_div > fb_div_max) { diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h index f42441b1b14d..a55a38ad849c 100644 --- a/drivers/gpu/drm/sun4i/sun8i_csc.h +++ b/drivers/gpu/drm/sun4i/sun8i_csc.h @@ -12,7 +12,7 @@ struct sun8i_mixer; /* VI channel CSC units offsets */ #define CCSC00_OFFSET 0xAA050 -#define CCSC01_OFFSET 0xFA000 +#define CCSC01_OFFSET 0xFA050 #define CCSC10_OFFSET 0xA0000 #define CCSC11_OFFSET 0xF0000 diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index cc4fb916318f..c3304028e3dc 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -307,7 +307,7 @@ static struct regmap_config sun8i_mixer_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0xbfffc, /* guessed */ + .max_register = 0xffffc, /* guessed */ }; static int sun8i_mixer_of_get_id(struct device_node *node) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 15a11cd4de25..6339c6f0f571 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1117,6 +1117,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) card->num_links = 1; card->name = "vc4-hdmi"; card->dev = dev; + card->owner = THIS_MODULE; /* * Be careful, snd_soc_register_card() calls dev_set_drvdata() and diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 31268074c422..724bf30600d6 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -69,6 +69,7 @@ * These share bit definitions, so use the same values for the enable & * status bits. */ +#define ASPEED_I2CD_INTR_RECV_MASK 0xf000ffff #define ASPEED_I2CD_INTR_SDA_DL_TIMEOUT BIT(14) #define ASPEED_I2CD_INTR_BUS_RECOVER_DONE BIT(13) #define ASPEED_I2CD_INTR_SLAVE_MATCH BIT(7) @@ -604,6 +605,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id) writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE, bus->base + ASPEED_I2C_INTR_STS_REG); readl(bus->base + ASPEED_I2C_INTR_STS_REG); + irq_received &= ASPEED_I2CD_INTR_RECV_MASK; irq_remaining = irq_received; #if IS_ENABLED(CONFIG_I2C_SLAVE) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e32ef3f01fe8..ebb4c0b03057 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1709,6 +1709,16 @@ static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; } static inline void i801_acpi_remove(struct i801_priv *priv) { } #endif +static unsigned char i801_setup_hstcfg(struct i801_priv *priv) +{ + unsigned char hstcfg = priv->original_hstcfg; + + hstcfg &= ~SMBHSTCFG_I2C_EN; /* SMBus timing */ + hstcfg |= SMBHSTCFG_HST_EN; + pci_write_config_byte(priv->pci_dev, SMBHSTCFG, hstcfg); + return hstcfg; +} + static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) { unsigned char temp; @@ -1830,14 +1840,10 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) return err; } - pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &temp); - priv->original_hstcfg = temp; - temp &= ~SMBHSTCFG_I2C_EN; /* SMBus timing */ - if (!(temp & SMBHSTCFG_HST_EN)) { + pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &priv->original_hstcfg); + temp = i801_setup_hstcfg(priv); + if (!(priv->original_hstcfg & SMBHSTCFG_HST_EN)) dev_info(&dev->dev, "Enabling SMBus device\n"); - temp |= SMBHSTCFG_HST_EN; - } - pci_write_config_byte(priv->pci_dev, SMBHSTCFG, temp); if (temp & SMBHSTCFG_SMB_SMI_EN) { dev_dbg(&dev->dev, "SMBus using interrupt SMI#\n"); @@ -1952,10 +1958,9 @@ static void i801_shutdown(struct pci_dev *dev) #ifdef CONFIG_PM_SLEEP static int i801_suspend(struct device *dev) { - struct pci_dev *pci_dev = to_pci_dev(dev); - struct i801_priv *priv = pci_get_drvdata(pci_dev); + struct i801_priv *priv = dev_get_drvdata(dev); - pci_write_config_byte(pci_dev, SMBHSTCFG, priv->original_hstcfg); + pci_write_config_byte(priv->pci_dev, SMBHSTCFG, priv->original_hstcfg); return 0; } @@ -1963,6 +1968,7 @@ static int i801_resume(struct device *dev) { struct i801_priv *priv = dev_get_drvdata(dev); + i801_setup_hstcfg(priv); i801_enable_host_notify(&priv->adapter); return 0; diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index efc14041d45b..0cbdfbe605b5 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -681,8 +681,8 @@ static int mtk_i2c_calculate_speed(struct mtk_i2c *i2c, unsigned int clk_src, unsigned int cnt_mul; int ret = -EINVAL; - if (target_speed > I2C_MAX_FAST_MODE_PLUS_FREQ) - target_speed = I2C_MAX_FAST_MODE_PLUS_FREQ; + if (target_speed > I2C_MAX_HIGH_SPEED_MODE_FREQ) + target_speed = I2C_MAX_HIGH_SPEED_MODE_FREQ; max_step_cnt = mtk_i2c_max_step_cnt(target_speed); base_step_cnt = max_step_cnt; @@ -759,7 +759,7 @@ static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk) for (clk_div = 1; clk_div <= max_clk_div; clk_div++) { clk_src = parent_clk / clk_div; - if (target_speed > I2C_MAX_FAST_MODE_FREQ) { + if (target_speed > I2C_MAX_FAST_MODE_PLUS_FREQ) { /* Set master code speed register */ ret = mtk_i2c_calculate_speed(i2c, clk_src, I2C_MAX_FAST_MODE_FREQ, diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index 9587347447f0..c4b08a924461 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -25,6 +25,7 @@ #include <linux/of_device.h> #include <linux/dma-mapping.h> #include <linux/dmaengine.h> +#include <linux/dma/mxs-dma.h> #define DRIVER_NAME "mxs-i2c" @@ -200,7 +201,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap, dma_map_sg(i2c->dev, &i2c->sg_io[0], 1, DMA_TO_DEVICE); desc = dmaengine_prep_slave_sg(i2c->dmach, &i2c->sg_io[0], 1, DMA_MEM_TO_DEV, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + DMA_PREP_INTERRUPT | + MXS_DMA_CTRL_WAIT4END); if (!desc) { dev_err(i2c->dev, "Failed to get DMA data write descriptor.\n"); @@ -228,7 +230,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap, dma_map_sg(i2c->dev, &i2c->sg_io[1], 1, DMA_FROM_DEVICE); desc = dmaengine_prep_slave_sg(i2c->dmach, &i2c->sg_io[1], 1, DMA_DEV_TO_MEM, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + DMA_PREP_INTERRUPT | + MXS_DMA_CTRL_WAIT4END); if (!desc) { dev_err(i2c->dev, "Failed to get DMA data write descriptor.\n"); @@ -260,7 +263,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap, dma_map_sg(i2c->dev, i2c->sg_io, 2, DMA_TO_DEVICE); desc = dmaengine_prep_slave_sg(i2c->dmach, i2c->sg_io, 2, DMA_MEM_TO_DEV, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + DMA_PREP_INTERRUPT | + MXS_DMA_CTRL_WAIT4END); if (!desc) { dev_err(i2c->dev, "Failed to get DMA data write descriptor.\n"); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 5ec082e2039d..573b5da145d1 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1464,8 +1464,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) /* create pre-declared device nodes */ of_i2c_register_devices(adap); - i2c_acpi_register_devices(adap); i2c_acpi_install_space_handler(adap); + i2c_acpi_register_devices(adap); if (adap->nr < __i2c_first_dynamic_bus_num) i2c_scan_static_board_info(adap); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index c36b4d2b61e0..23ee65a9185f 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1285,6 +1285,8 @@ static void disable_device(struct ib_device *device) remove_client_context(device, cid); } + ib_cq_pool_destroy(device); + /* Pairs with refcount_set in enable_device */ ib_device_put(device); wait_for_completion(&device->unreg_completion); @@ -1328,6 +1330,8 @@ static int enable_device_and_get(struct ib_device *device) goto out; } + ib_cq_pool_init(device); + down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { ret = add_client_context(device, client); @@ -1400,7 +1404,6 @@ int ib_register_device(struct ib_device *device, const char *name) goto dev_cleanup; } - ib_cq_pool_init(device); ret = enable_device_and_get(device); dev_set_uevent_suppress(&device->dev, false); /* Mark for userspace that device is ready */ @@ -1455,7 +1458,6 @@ static void __ib_unregister_device(struct ib_device *ib_dev) goto out; disable_device(ib_dev); - ib_cq_pool_destroy(ib_dev); /* Expedite removing unregistered pointers from the hash table */ free_netdevs(ib_dev); diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c index 3eefee2ee2a1..854d5e758724 100644 --- a/drivers/input/mouse/trackpoint.c +++ b/drivers/input/mouse/trackpoint.c @@ -17,10 +17,12 @@ #include "trackpoint.h" static const char * const trackpoint_variants[] = { - [TP_VARIANT_IBM] = "IBM", - [TP_VARIANT_ALPS] = "ALPS", - [TP_VARIANT_ELAN] = "Elan", - [TP_VARIANT_NXP] = "NXP", + [TP_VARIANT_IBM] = "IBM", + [TP_VARIANT_ALPS] = "ALPS", + [TP_VARIANT_ELAN] = "Elan", + [TP_VARIANT_NXP] = "NXP", + [TP_VARIANT_JYT_SYNAPTICS] = "JYT_Synaptics", + [TP_VARIANT_SYNAPTICS] = "Synaptics", }; /* diff --git a/drivers/input/mouse/trackpoint.h b/drivers/input/mouse/trackpoint.h index 5cb93ed26085..eb5412904fe0 100644 --- a/drivers/input/mouse/trackpoint.h +++ b/drivers/input/mouse/trackpoint.h @@ -24,10 +24,12 @@ * 0x01 was the original IBM trackpoint, others implement very limited * subset of trackpoint features. */ -#define TP_VARIANT_IBM 0x01 -#define TP_VARIANT_ALPS 0x02 -#define TP_VARIANT_ELAN 0x03 -#define TP_VARIANT_NXP 0x04 +#define TP_VARIANT_IBM 0x01 +#define TP_VARIANT_ALPS 0x02 +#define TP_VARIANT_ELAN 0x03 +#define TP_VARIANT_NXP 0x04 +#define TP_VARIANT_JYT_SYNAPTICS 0x05 +#define TP_VARIANT_SYNAPTICS 0x06 /* * Commands diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 7d7f73702726..37fb9aa88f9c 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -548,6 +548,14 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), }, }, + { + /* Entroware Proteus */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), + DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), + }, + }, { } }; @@ -676,6 +684,14 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), }, }, + { + /* Entroware Proteus */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), + DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), + }, + }, { } }; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 07ae8b93887e..10e4200d3552 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3840,14 +3840,18 @@ int amd_iommu_activate_guest_mode(void *data) { struct amd_ir_data *ir_data = (struct amd_ir_data *)data; struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + u64 valid; if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry || entry->lo.fields_vapic.guest_mode) return 0; + valid = entry->lo.fields_vapic.valid; + entry->lo.val = 0; entry->hi.val = 0; + entry->lo.fields_vapic.valid = valid; entry->lo.fields_vapic.guest_mode = 1; entry->lo.fields_vapic.ga_log_intr = 1; entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr; @@ -3864,12 +3868,14 @@ int amd_iommu_deactivate_guest_mode(void *data) struct amd_ir_data *ir_data = (struct amd_ir_data *)data; struct irte_ga *entry = (struct irte_ga *) ir_data->entry; struct irq_cfg *cfg = ir_data->cfg; - u64 valid = entry->lo.fields_remap.valid; + u64 valid; if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry || !entry->lo.fields_vapic.guest_mode) return 0; + valid = entry->lo.fields_remap.valid; + entry->lo.val = 0; entry->hi.val = 0; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5edc3079e7c1..229f461e7def 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -860,10 +860,14 @@ EXPORT_SYMBOL_GPL(dm_table_set_type); int device_supports_dax(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - int blocksize = *(int *) data; + int blocksize = *(int *) data, id; + bool rc; - return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize, - start, len); + id = dax_read_lock(); + rc = dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len); + dax_read_unlock(id); + + return rc; } /* Check devices support synchronous DAX */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fb0255d25e4b..6ed05ca65a0f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1136,15 +1136,16 @@ static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bd { struct mapped_device *md = dax_get_private(dax_dev); struct dm_table *map; + bool ret = false; int srcu_idx; - bool ret; map = dm_get_live_table(md, &srcu_idx); if (!map) - return false; + goto out; ret = dm_table_supports_dax(map, device_supports_dax, &blocksize); +out: dm_put_live_table(md, srcu_idx); return ret; @@ -1723,23 +1724,6 @@ out: return ret; } -static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struct bio **bio) -{ - unsigned len, sector_count; - - sector_count = bio_sectors(*bio); - len = min_t(sector_t, max_io_len((*bio)->bi_iter.bi_sector, ti), sector_count); - - if (sector_count > len) { - struct bio *split = bio_split(*bio, len, GFP_NOIO, &md->queue->bio_split); - - bio_chain(split, *bio); - trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector); - submit_bio_noacct(*bio); - *bio = split; - } -} - static blk_qc_t dm_process_bio(struct mapped_device *md, struct dm_table *map, struct bio *bio) { @@ -1760,21 +1744,21 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, } /* - * If in ->queue_bio we need to use blk_queue_split(), otherwise + * If in ->submit_bio we need to use blk_queue_split(), otherwise * queue_limits for abnormal requests (e.g. discard, writesame, etc) * won't be imposed. + * If called from dm_wq_work() for deferred bio processing, bio + * was already handled by following code with previous ->submit_bio. */ if (current->bio_list) { if (is_abnormal_io(bio)) blk_queue_split(&bio); - else - dm_queue_split(md, ti, &bio); + /* regular IO is split by __split_and_process_bio */ } if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED) return __process_bio(md, map, bio, ti); - else - return __split_and_process_bio(md, map, bio); + return __split_and_process_bio(md, map, bio); } static blk_qc_t dm_submit_bio(struct bio *bio) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 4efe8014445e..926d65db6d3e 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1199,7 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap, /* Cancel the pending timeout work */ if (!cancel_delayed_work(&data->work)) { mutex_unlock(&adap->lock); - flush_scheduled_work(); + cancel_delayed_work_sync(&data->work); mutex_lock(&adap->lock); } /* diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index f544d3393e9d..4eab6d81cce1 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -721,39 +721,14 @@ int vb2_verify_memory_type(struct vb2_queue *q, } EXPORT_SYMBOL(vb2_verify_memory_type); -static void set_queue_consistency(struct vb2_queue *q, bool consistent_mem) -{ - q->dma_attrs &= ~DMA_ATTR_NON_CONSISTENT; - - if (!vb2_queue_allows_cache_hints(q)) - return; - if (!consistent_mem) - q->dma_attrs |= DMA_ATTR_NON_CONSISTENT; -} - -static bool verify_consistency_attr(struct vb2_queue *q, bool consistent_mem) -{ - bool queue_is_consistent = !(q->dma_attrs & DMA_ATTR_NON_CONSISTENT); - - if (consistent_mem != queue_is_consistent) { - dprintk(q, 1, "memory consistency model mismatch\n"); - return false; - } - return true; -} - int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count) + unsigned int *count) { unsigned int num_buffers, allocated_buffers, num_planes = 0; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool consistent_mem = true; unsigned int i; int ret; - if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT) - consistent_mem = false; - if (q->streaming) { dprintk(q, 1, "streaming active\n"); return -EBUSY; @@ -765,8 +740,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, } if (*count == 0 || q->num_buffers != 0 || - (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory) || - !verify_consistency_attr(q, consistent_mem)) { + (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory)) { /* * We already have buffers allocated, so first check if they * are not in use and can be freed. @@ -803,7 +777,6 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); q->memory = memory; - set_queue_consistency(q, consistent_mem); /* * Ask the driver how many buffers and planes per buffer it requires. @@ -888,18 +861,14 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, EXPORT_SYMBOL_GPL(vb2_core_reqbufs); int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count, + unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[]) { unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool consistent_mem = true; int ret; - if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT) - consistent_mem = false; - if (q->num_buffers == VB2_MAX_FRAME) { dprintk(q, 1, "maximum number of buffers already allocated\n"); return -ENOBUFS; @@ -912,15 +881,12 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); q->memory = memory; - set_queue_consistency(q, consistent_mem); q->waiting_for_buffers = !q->is_output; } else { if (q->memory != memory) { dprintk(q, 1, "memory model mismatch\n"); return -EINVAL; } - if (!verify_consistency_attr(q, consistent_mem)) - return -EINVAL; } num_buffers = min(*count, VB2_MAX_FRAME - q->num_buffers); @@ -2581,7 +2547,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read) fileio->memory = VB2_MEMORY_MMAP; fileio->type = q->type; q->fileio = fileio; - ret = vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + ret = vb2_core_reqbufs(q, fileio->memory, &fileio->count); if (ret) goto err_kfree; @@ -2638,7 +2604,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read) err_reqbufs: fileio->count = 0; - vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + vb2_core_reqbufs(q, fileio->memory, &fileio->count); err_kfree: q->fileio = NULL; @@ -2658,7 +2624,7 @@ static int __vb2_cleanup_fileio(struct vb2_queue *q) vb2_core_streamoff(q, q->type); q->fileio = NULL; fileio->count = 0; - vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + vb2_core_reqbufs(q, fileio->memory, &fileio->count); kfree(fileio); dprintk(q, 3, "file io emulator closed\n"); } diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index ec3446cc45b8..7b1b86ec942d 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -42,11 +42,6 @@ struct vb2_dc_buf { struct dma_buf_attachment *db_attach; }; -static inline bool vb2_dc_buffer_consistent(unsigned long attr) -{ - return !(attr & DMA_ATTR_NON_CONSISTENT); -} - /*********************************************/ /* scatterlist table functions */ /*********************************************/ @@ -341,13 +336,6 @@ static int vb2_dc_dmabuf_ops_begin_cpu_access(struct dma_buf *dbuf, enum dma_data_direction direction) { - struct vb2_dc_buf *buf = dbuf->priv; - struct sg_table *sgt = buf->dma_sgt; - - if (vb2_dc_buffer_consistent(buf->attrs)) - return 0; - - dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); return 0; } @@ -355,13 +343,6 @@ static int vb2_dc_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf, enum dma_data_direction direction) { - struct vb2_dc_buf *buf = dbuf->priv; - struct sg_table *sgt = buf->dma_sgt; - - if (vb2_dc_buffer_consistent(buf->attrs)) - return 0; - - dma_sync_sg_for_device(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); return 0; } diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 0a40e00f0d7e..a86fce5d8ea8 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -123,8 +123,7 @@ static void *vb2_dma_sg_alloc(struct device *dev, unsigned long dma_attrs, /* * NOTE: dma-sg allocates memory using the page allocator directly, so * there is no memory consistency guarantee, hence dma-sg ignores DMA - * attributes passed from the upper layer. That means that - * V4L2_FLAG_MEMORY_NON_CONSISTENT has no effect on dma-sg buffers. + * attributes passed from the upper layer. */ buf->pages = kvmalloc_array(buf->num_pages, sizeof(struct page *), GFP_KERNEL | __GFP_ZERO); diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 30caad27281e..cfe197df970d 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -722,22 +722,12 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) #endif } -static void clear_consistency_attr(struct vb2_queue *q, - int memory, - unsigned int *flags) -{ - if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) - *flags &= ~V4L2_FLAG_MEMORY_NON_CONSISTENT; -} - int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) { int ret = vb2_verify_memory_type(q, req->memory, req->type); fill_buf_caps(q, &req->capabilities); - clear_consistency_attr(q, req->memory, &req->flags); - return ret ? ret : vb2_core_reqbufs(q, req->memory, - req->flags, &req->count); + return ret ? ret : vb2_core_reqbufs(q, req->memory, &req->count); } EXPORT_SYMBOL_GPL(vb2_reqbufs); @@ -769,7 +759,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) unsigned i; fill_buf_caps(q, &create->capabilities); - clear_consistency_attr(q, create->memory, &create->flags); create->index = q->num_buffers; if (create->count == 0) return ret != -EBUSY ? ret : 0; @@ -813,7 +802,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) if (requested_sizes[i] == 0) return -EINVAL; return ret ? ret : vb2_core_create_bufs(q, create->memory, - create->flags, &create->count, requested_planes, requested_sizes); @@ -998,12 +986,11 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv, int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type); fill_buf_caps(vdev->queue, &p->capabilities); - clear_consistency_attr(vdev->queue, p->memory, &p->flags); if (res) return res; if (vb2_queue_is_busy(vdev, file)) return -EBUSY; - res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count); + res = vb2_core_reqbufs(vdev->queue, p->memory, &p->count); /* If count == 0, then the owner has released all buffers and he is no longer owner of the queue. Otherwise we have a new owner. */ if (res == 0) @@ -1021,7 +1008,6 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv, p->index = vdev->queue->num_buffers; fill_buf_caps(vdev->queue, &p->capabilities); - clear_consistency_attr(vdev->queue, p->memory, &p->flags); /* * If count == 0, then just check if memory and type are valid. * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0. diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c index 959d110407a4..6974f1731529 100644 --- a/drivers/media/dvb-core/dvb_vb2.c +++ b/drivers/media/dvb-core/dvb_vb2.c @@ -342,7 +342,7 @@ int dvb_vb2_reqbufs(struct dvb_vb2_ctx *ctx, struct dmx_requestbuffers *req) ctx->buf_siz = req->size; ctx->buf_cnt = req->count; - ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, 0, &req->count); + ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, &req->count); if (ret) { ctx->state = DVB_VB2_STATE_NONE; dprintk(1, "[%s] count=%d size=%d errno=%d\n", ctx->name, diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 593bcf6c3735..a99e82ec9ab6 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -246,9 +246,6 @@ struct v4l2_format32 { * @memory: buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. - * @flags: additional buffer management attributes (ignored unless the - * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and - * configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers32 { @@ -257,8 +254,7 @@ struct v4l2_create_buffers32 { __u32 memory; /* enum v4l2_memory */ struct v4l2_format32 format; __u32 capabilities; - __u32 flags; - __u32 reserved[6]; + __u32 reserved[7]; }; static int __bufsize_v4l2_format(struct v4l2_format32 __user *p32, u32 *size) @@ -359,8 +355,7 @@ static int get_v4l2_create32(struct v4l2_create_buffers __user *p64, { if (!access_ok(p32, sizeof(*p32)) || copy_in_user(p64, p32, - offsetof(struct v4l2_create_buffers32, format)) || - assign_in_user(&p64->flags, &p32->flags)) + offsetof(struct v4l2_create_buffers32, format))) return -EFAULT; return __get_v4l2_format32(&p64->format, &p32->format, aux_buf, aux_space); @@ -422,7 +417,6 @@ static int put_v4l2_create32(struct v4l2_create_buffers __user *p64, copy_in_user(p32, p64, offsetof(struct v4l2_create_buffers32, format)) || assign_in_user(&p32->capabilities, &p64->capabilities) || - assign_in_user(&p32->flags, &p64->flags) || copy_in_user(p32->reserved, p64->reserved, sizeof(p64->reserved))) return -EFAULT; return __put_v4l2_format32(&p64->format, &p32->format); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index f74b42280892..eeff398fbdcc 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2042,6 +2042,9 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; + + CLEAR_AFTER_FIELD(p, capabilities); + return ops->vidioc_reqbufs(file, fh, p); } @@ -2081,7 +2084,7 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(create, flags); + CLEAR_AFTER_FIELD(create, capabilities); v4l_sanitize_format(&create->format); diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 5055a7eb134a..18a850f37ddc 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1320,7 +1320,7 @@ static void mmc_spi_dma_free(struct mmc_spi_host *host) DMA_BIDIRECTIONAL); } #else -static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } +static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {} #endif diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 65eff4ce6ab1..0369d98b2d12 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -1907,16 +1907,15 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) } /** - * spi_nor_sr1_bit6_quad_enable() - Set/Unset the Quad Enable BIT(6) in the - * Status Register 1. + * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status + * Register 1. * @nor: pointer to a 'struct spi_nor' - * @enable: true to enable Quad mode, false to disable Quad mode. * * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories. * * Return: 0 on success, -errno otherwise. */ -int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable) +int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor) { int ret; @@ -1924,56 +1923,45 @@ int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable) if (ret) return ret; - if ((enable && (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)) || - (!enable && !(nor->bouncebuf[0] & SR1_QUAD_EN_BIT6))) + if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6) return 0; - if (enable) - nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6; - else - nor->bouncebuf[0] &= ~SR1_QUAD_EN_BIT6; + nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6; return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]); } /** - * spi_nor_sr2_bit1_quad_enable() - set/unset the Quad Enable BIT(1) in the - * Status Register 2. + * spi_nor_sr2_bit1_quad_enable() - set the Quad Enable BIT(1) in the Status + * Register 2. * @nor: pointer to a 'struct spi_nor'. - * @enable: true to enable Quad mode, false to disable Quad mode. * * Bit 1 of the Status Register 2 is the QE bit for Spansion like QSPI memories. * * Return: 0 on success, -errno otherwise. */ -int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable) +int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor) { int ret; if (nor->flags & SNOR_F_NO_READ_CR) - return spi_nor_write_16bit_cr_and_check(nor, - enable ? SR2_QUAD_EN_BIT1 : 0); + return spi_nor_write_16bit_cr_and_check(nor, SR2_QUAD_EN_BIT1); ret = spi_nor_read_cr(nor, nor->bouncebuf); if (ret) return ret; - if ((enable && (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)) || - (!enable && !(nor->bouncebuf[0] & SR2_QUAD_EN_BIT1))) + if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1) return 0; - if (enable) - nor->bouncebuf[0] |= SR2_QUAD_EN_BIT1; - else - nor->bouncebuf[0] &= ~SR2_QUAD_EN_BIT1; + nor->bouncebuf[0] |= SR2_QUAD_EN_BIT1; return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]); } /** - * spi_nor_sr2_bit7_quad_enable() - set/unset QE bit in Status Register 2. + * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2. * @nor: pointer to a 'struct spi_nor' - * @enable: true to enable Quad mode, false to disable Quad mode. * * Set the Quad Enable (QE) bit in the Status Register 2. * @@ -1983,7 +1971,7 @@ int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable) * * Return: 0 on success, -errno otherwise. */ -int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable) +int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor) { u8 *sr2 = nor->bouncebuf; int ret; @@ -1993,15 +1981,11 @@ int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable) ret = spi_nor_read_sr2(nor, sr2); if (ret) return ret; - if ((enable && (*sr2 & SR2_QUAD_EN_BIT7)) || - (!enable && !(*sr2 & SR2_QUAD_EN_BIT7))) + if (*sr2 & SR2_QUAD_EN_BIT7) return 0; /* Update the Quad Enable bit. */ - if (enable) - *sr2 |= SR2_QUAD_EN_BIT7; - else - *sr2 &= ~SR2_QUAD_EN_BIT7; + *sr2 |= SR2_QUAD_EN_BIT7; ret = spi_nor_write_sr2(nor, sr2); if (ret) @@ -2914,13 +2898,12 @@ static int spi_nor_init_params(struct spi_nor *nor) } /** - * spi_nor_quad_enable() - enable/disable Quad I/O if needed. + * spi_nor_quad_enable() - enable Quad I/O if needed. * @nor: pointer to a 'struct spi_nor' - * @enable: true to enable Quad mode. false to disable Quad mode. * * Return: 0 on success, -errno otherwise. */ -static int spi_nor_quad_enable(struct spi_nor *nor, bool enable) +static int spi_nor_quad_enable(struct spi_nor *nor) { if (!nor->params->quad_enable) return 0; @@ -2929,7 +2912,7 @@ static int spi_nor_quad_enable(struct spi_nor *nor, bool enable) spi_nor_get_protocol_width(nor->write_proto) == 4)) return 0; - return nor->params->quad_enable(nor, enable); + return nor->params->quad_enable(nor); } /** @@ -2953,7 +2936,7 @@ static int spi_nor_init(struct spi_nor *nor) { int err; - err = spi_nor_quad_enable(nor, true); + err = spi_nor_quad_enable(nor); if (err) { dev_dbg(nor->dev, "quad mode not supported\n"); return err; @@ -3000,8 +2983,6 @@ void spi_nor_restore(struct spi_nor *nor) if (nor->addr_width == 4 && !(nor->flags & SNOR_F_4B_OPCODES) && nor->flags & SNOR_F_BROKEN_RESET) nor->params->set_4byte_addr_mode(nor, false); - - spi_nor_quad_enable(nor, false); } EXPORT_SYMBOL_GPL(spi_nor_restore); diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index 95aa32f3ceb1..6f2f6b27173f 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -198,7 +198,7 @@ struct spi_nor_locking_ops { * higher index in the array, the higher priority. * @erase_map: the erase map parsed from the SFDP Sector Map Parameter * Table. - * @quad_enable: enables/disables SPI NOR Quad mode. + * @quad_enable: enables SPI NOR quad mode. * @set_4byte_addr_mode: puts the SPI NOR in 4 byte addressing mode. * @convert_addr: converts an absolute address into something the flash * will understand. Particularly useful when pagesize is @@ -219,7 +219,7 @@ struct spi_nor_flash_parameter { struct spi_nor_erase_map erase_map; - int (*quad_enable)(struct spi_nor *nor, bool enable); + int (*quad_enable)(struct spi_nor *nor); int (*set_4byte_addr_mode)(struct spi_nor *nor, bool enable); u32 (*convert_addr)(struct spi_nor *nor, u32 addr); int (*setup)(struct spi_nor *nor, const struct spi_nor_hwcaps *hwcaps); @@ -406,9 +406,9 @@ int spi_nor_write_ear(struct spi_nor *nor, u8 ear); int spi_nor_wait_till_ready(struct spi_nor *nor); int spi_nor_lock_and_prep(struct spi_nor *nor); void spi_nor_unlock_and_unprep(struct spi_nor *nor); -int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable); -int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable); -int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable); +int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor); +int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor); +int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor); int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr); ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 8f1d15ea15d9..f5779e152377 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -932,11 +932,19 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_ENABLE, true); if (cpu_port) { + if (!p->interface && dev->compat_interface) { + dev_warn(dev->dev, + "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. " + "Please update your device tree.\n", + port); + p->interface = dev->compat_interface; + } + /* Configure MII interface for proper network communication. */ ksz_read8(dev, REG_PORT_5_CTRL_6, &data8); data8 &= ~PORT_INTERFACE_TYPE; data8 &= ~PORT_GMII_1GPS_MODE; - switch (dev->interface) { + switch (p->interface) { case PHY_INTERFACE_MODE_MII: p->phydev.speed = SPEED_100; break; @@ -952,11 +960,11 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port) default: data8 &= ~PORT_RGMII_ID_IN_ENABLE; data8 &= ~PORT_RGMII_ID_OUT_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_RXID) data8 |= PORT_RGMII_ID_IN_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_TXID) data8 |= PORT_RGMII_ID_OUT_ENABLE; data8 |= PORT_GMII_1GPS_MODE; data8 |= PORT_INTERFACE_RGMII; @@ -1252,7 +1260,7 @@ static int ksz8795_switch_init(struct ksz_device *dev) } /* set the real number of ports */ - dev->ds->num_ports = dev->port_cnt; + dev->ds->num_ports = dev->port_cnt + 1; return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 3cb22d149813..2f5506ac7d19 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1208,7 +1208,7 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) /* configure MAC to 1G & RGMII mode */ ksz_pread8(dev, port, REG_PORT_XMII_CTRL_1, &data8); - switch (dev->interface) { + switch (p->interface) { case PHY_INTERFACE_MODE_MII: ksz9477_set_xmii(dev, 0, &data8); ksz9477_set_gbit(dev, false, &data8); @@ -1229,11 +1229,11 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz9477_set_gbit(dev, true, &data8); data8 &= ~PORT_RGMII_ID_IG_ENABLE; data8 &= ~PORT_RGMII_ID_EG_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_RXID) data8 |= PORT_RGMII_ID_IG_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_TXID) data8 |= PORT_RGMII_ID_EG_ENABLE; p->phydev.speed = SPEED_1000; break; @@ -1269,23 +1269,32 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) dev->cpu_port = i; dev->host_mask = (1 << dev->cpu_port); dev->port_mask |= dev->host_mask; + p = &dev->ports[i]; /* Read from XMII register to determine host port * interface. If set specifically in device tree * note the difference to help debugging. */ interface = ksz9477_get_interface(dev, i); - if (!dev->interface) - dev->interface = interface; - if (interface && interface != dev->interface) + if (!p->interface) { + if (dev->compat_interface) { + dev_warn(dev->dev, + "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. " + "Please update your device tree.\n", + i); + p->interface = dev->compat_interface; + } else { + p->interface = interface; + } + } + if (interface && interface != p->interface) dev_info(dev->dev, "use %s instead of %s\n", - phy_modes(dev->interface), + phy_modes(p->interface), phy_modes(interface)); /* enable cpu port */ ksz9477_port_setup(dev, i, true); - p = &dev->ports[dev->cpu_port]; p->vid_member = dev->port_mask; p->on = 1; } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8d53b12d40a8..8e755b50c9c1 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -388,6 +388,8 @@ int ksz_switch_register(struct ksz_device *dev, const struct ksz_dev_ops *ops) { phy_interface_t interface; + struct device_node *port; + unsigned int port_num; int ret; if (dev->pdata) @@ -421,10 +423,19 @@ int ksz_switch_register(struct ksz_device *dev, /* Host port interface will be self detected, or specifically set in * device tree. */ + for (port_num = 0; port_num < dev->port_cnt; ++port_num) + dev->ports[port_num].interface = PHY_INTERFACE_MODE_NA; if (dev->dev->of_node) { ret = of_get_phy_mode(dev->dev->of_node, &interface); if (ret == 0) - dev->interface = interface; + dev->compat_interface = interface; + for_each_available_child_of_node(dev->dev->of_node, port) { + if (of_property_read_u32(port, "reg", &port_num)) + continue; + if (port_num >= dev->port_cnt) + return -EINVAL; + of_get_phy_mode(port, &dev->ports[port_num].interface); + } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); } diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 206838160f49..cf866e48ff66 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -39,6 +39,7 @@ struct ksz_port { u32 freeze:1; /* MIB counter freeze is enabled */ struct ksz_port_mib mib; + phy_interface_t interface; }; struct ksz_device { @@ -72,7 +73,7 @@ struct ksz_device { int mib_cnt; int mib_port_cnt; int last_port; /* ports after that not used */ - phy_interface_t interface; + phy_interface_t compat_interface; u32 regs_size; bool phy_errata_9477; bool synclko_125; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 04bfa6e465ff..01427cd08448 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -585,7 +585,10 @@ static int felix_setup(struct dsa_switch *ds) if (err) return err; - ocelot_init(ocelot); + err = ocelot_init(ocelot); + if (err) + return err; + if (ocelot->ptp) { err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); if (err) { @@ -640,10 +643,13 @@ static void felix_teardown(struct dsa_switch *ds) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + int port; if (felix->info->mdio_bus_free) felix->info->mdio_bus_free(ocelot); + for (port = 0; port < ocelot->num_phys_ports; port++) + ocelot_deinit_port(ocelot, port); ocelot_deinit_timestamp(ocelot); /* stop workqueue thread */ ocelot_deinit(ocelot); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9b720c8ddfc3..6855c94256f8 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -645,17 +645,17 @@ static struct vcap_field vsc9959_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {118, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {119, 1}, - [VCAP_IS2_HK_L4_SPORT] = {120, 16}, - [VCAP_IS2_HK_L4_DPORT] = {136, 16}, + [VCAP_IS2_HK_L4_DPORT] = {120, 16}, + [VCAP_IS2_HK_L4_SPORT] = {136, 16}, [VCAP_IS2_HK_L4_RNG] = {152, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {160, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {161, 1}, - [VCAP_IS2_HK_L4_URG] = {162, 1}, - [VCAP_IS2_HK_L4_ACK] = {163, 1}, - [VCAP_IS2_HK_L4_PSH] = {164, 1}, - [VCAP_IS2_HK_L4_RST] = {165, 1}, - [VCAP_IS2_HK_L4_SYN] = {166, 1}, - [VCAP_IS2_HK_L4_FIN] = {167, 1}, + [VCAP_IS2_HK_L4_FIN] = {162, 1}, + [VCAP_IS2_HK_L4_SYN] = {163, 1}, + [VCAP_IS2_HK_L4_RST] = {164, 1}, + [VCAP_IS2_HK_L4_PSH] = {165, 1}, + [VCAP_IS2_HK_L4_ACK] = {166, 1}, + [VCAP_IS2_HK_L4_URG] = {167, 1}, [VCAP_IS2_HK_L4_1588_DOM] = {168, 8}, [VCAP_IS2_HK_L4_1588_VER] = {176, 4}, /* IP4_OTHER (TYPE=101) */ diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 625b1891d955..29df0797ecf5 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -659,17 +659,17 @@ static struct vcap_field vsc9953_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {122, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {123, 1}, - [VCAP_IS2_HK_L4_SPORT] = {124, 16}, - [VCAP_IS2_HK_L4_DPORT] = {140, 16}, + [VCAP_IS2_HK_L4_DPORT] = {124, 16}, + [VCAP_IS2_HK_L4_SPORT] = {140, 16}, [VCAP_IS2_HK_L4_RNG] = {156, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {164, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {165, 1}, - [VCAP_IS2_HK_L4_URG] = {166, 1}, - [VCAP_IS2_HK_L4_ACK] = {167, 1}, - [VCAP_IS2_HK_L4_PSH] = {168, 1}, - [VCAP_IS2_HK_L4_RST] = {169, 1}, - [VCAP_IS2_HK_L4_SYN] = {170, 1}, - [VCAP_IS2_HK_L4_FIN] = {171, 1}, + [VCAP_IS2_HK_L4_FIN] = {166, 1}, + [VCAP_IS2_HK_L4_SYN] = {167, 1}, + [VCAP_IS2_HK_L4_RST] = {168, 1}, + [VCAP_IS2_HK_L4_PSH] = {169, 1}, + [VCAP_IS2_HK_L4_ACK] = {170, 1}, + [VCAP_IS2_HK_L4_URG] = {171, 1}, /* IP4_OTHER (TYPE=101) */ [VCAP_IS2_HK_IP4_L3_PROTO] = {123, 8}, [VCAP_IS2_HK_L3_PAYLOAD] = {131, 56}, @@ -1008,7 +1008,7 @@ static const struct felix_info seville_info_vsc9953 = { .vcap_is2_keys = vsc9953_vcap_is2_keys, .vcap_is2_actions = vsc9953_vcap_is2_actions, .vcap = vsc9953_vcap_props, - .shared_queue_sz = 128 * 1024, + .shared_queue_sz = 2048 * 1024, .num_mact_rows = 2048, .num_ports = 10, .mdio_bus_alloc = vsc9953_mdio_bus_alloc, diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 8f40fbf70a82..a8c5a934c3d3 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -452,13 +452,19 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, return ret; if (vid == vlanmc.vid) { - /* clear VLAN member configurations */ - vlanmc.vid = 0; - vlanmc.priority = 0; - vlanmc.member = 0; - vlanmc.untag = 0; - vlanmc.fid = 0; - + /* Remove this port from the VLAN */ + vlanmc.member &= ~BIT(port); + vlanmc.untag &= ~BIT(port); + /* + * If no ports are members of this VLAN + * anymore then clear the whole member + * config so it can be reused. + */ + if (!vlanmc.member && vlanmc.untag) { + vlanmc.vid = 0; + vlanmc.priority = 0; + vlanmc.fid = 0; + } ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); if (ret) { dev_err(smi->dev, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b167066af450..7b7e8b7883c8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3782,6 +3782,7 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp, return -EOPNOTSUPP; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QSTATS_EXT, -1, -1); + req.fid = cpu_to_le16(0xffff); req.flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -3852,7 +3853,7 @@ static void bnxt_init_stats(struct bnxt *bp) tx_masks = stats->hw_masks; tx_count = sizeof(struct tx_port_stats_ext) / 8; - flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + flags = PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; rc = bnxt_hwrm_port_qstats_ext(bp, flags); if (rc) { mask = (1ULL << 40) - 1; @@ -4305,7 +4306,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return -EBUSY; if (msg_len > BNXT_HWRM_MAX_REQ_LEN) { @@ -5723,7 +5724,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); @@ -7817,7 +7818,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) if (set_tpa) tpa_flags = bp->flags & BNXT_FLAG_TPA; - else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + else if (BNXT_NO_FW_ACCESS(bp)) return 0; for (i = 0; i < bp->nr_vnics; i++) { rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); @@ -9311,18 +9312,16 @@ static ssize_t bnxt_show_temp(struct device *dev, struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); u32 len = 0; + int rc; resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - - if (len) - return len; - - return sprintf(buf, "unknown\n"); + return rc ?: len; } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); @@ -9342,7 +9341,16 @@ static void bnxt_hwmon_close(struct bnxt *bp) static void bnxt_hwmon_open(struct bnxt *bp) { + struct hwrm_temp_monitor_query_input req = {0}; struct pci_dev *pdev = bp->pdev; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); + rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc == -EACCES || rc == -EOPNOTSUPP) { + bnxt_hwmon_close(bp); + return; + } if (bp->hwmon_dev) return; @@ -11779,6 +11787,10 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bnxt_cancel_sp_work(bp); + bp->sp_event = 0; + bnxt_dl_fw_reporters_destroy(bp, true); if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); @@ -11786,9 +11798,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_cancel_sp_work(bp); - bp->sp_event = 0; bnxt_clear_int_mode(bp); bnxt_hwrm_func_drv_unrgtr(bp); @@ -12089,7 +12098,7 @@ static int bnxt_init_mac_addr(struct bnxt *bp) static void bnxt_vpd_read_info(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; - int i, len, pos, ro_size; + int i, len, pos, ro_size, size; ssize_t vpd_size; u8 *vpd_data; @@ -12124,7 +12133,8 @@ static void bnxt_vpd_read_info(struct bnxt *bp) if (len + pos > vpd_size) goto read_sn; - strlcpy(bp->board_partno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN)); + size = min(len, BNXT_VPD_FLD_LEN - 1); + memcpy(bp->board_partno, &vpd_data[pos], size); read_sn: pos = pci_vpd_find_info_keyword(vpd_data, i, ro_size, @@ -12137,7 +12147,8 @@ read_sn: if (len + pos > vpd_size) goto exit; - strlcpy(bp->board_serialno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN)); + size = min(len, BNXT_VPD_FLD_LEN - 1); + memcpy(bp->board_serialno, &vpd_data[pos], size); exit: kfree(vpd_data); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5a13eb66beda..0ef89dabfd61 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1737,6 +1737,10 @@ struct bnxt { #define BNXT_STATE_FW_FATAL_COND 6 #define BNXT_STATE_DRV_REGISTERED 7 +#define BNXT_NO_FW_ACCESS(bp) \ + (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ + pci_channel_offline((bp)->pdev)) + struct bnxt_irq *irq_tbl; int total_irqs; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d0928334bdc8..fecdfd875af1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1322,6 +1322,9 @@ static int bnxt_get_regs_len(struct net_device *dev) struct bnxt *bp = netdev_priv(dev); int reg_len; + if (!BNXT_PF(bp)) + return -EOPNOTSUPP; + reg_len = BNXT_PXP_REG_LEN; if (bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED) @@ -1788,9 +1791,12 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (!BNXT_PHY_CFG_ABLE(bp)) return -EOPNOTSUPP; + mutex_lock(&bp->link_lock); if (epause->autoneg) { - if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) - return -EINVAL; + if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { + rc = -EINVAL; + goto pause_exit; + } link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL; if (bp->hwrm_spec_code >= 0x10201) @@ -1811,11 +1817,11 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (epause->tx_pause) link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX; - if (netif_running(dev)) { - mutex_lock(&bp->link_lock); + if (netif_running(dev)) rc = bnxt_hwrm_set_pause(bp); - mutex_unlock(&bp->link_lock); - } + +pause_exit: + mutex_unlock(&bp->link_lock); return rc; } @@ -2552,8 +2558,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) struct bnxt *bp = netdev_priv(dev); struct ethtool_eee *eee = &bp->eee; struct bnxt_link_info *link_info = &bp->link_info; - u32 advertising = - _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0); + u32 advertising; int rc = 0; if (!BNXT_PHY_CFG_ABLE(bp)) @@ -2562,19 +2567,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) if (!(bp->flags & BNXT_FLAG_EEE_CAP)) return -EOPNOTSUPP; + mutex_lock(&bp->link_lock); + advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0); if (!edata->eee_enabled) goto eee_ok; if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { netdev_warn(dev, "EEE requires autoneg\n"); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } if (edata->tx_lpi_enabled) { if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi || edata->tx_lpi_timer < bp->lpi_tmr_lo)) { netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n", bp->lpi_tmr_lo, bp->lpi_tmr_hi); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } else if (!bp->lpi_tmr_hi) { edata->tx_lpi_timer = eee->tx_lpi_timer; } @@ -2584,7 +2593,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) } else if (edata->advertised & ~advertising) { netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n", edata->advertised, advertising); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } eee->advertised = edata->advertised; @@ -2596,6 +2606,8 @@ eee_ok: if (netif_running(dev)) rc = bnxt_hwrm_set_link_setting(bp, false, true); +eee_exit: + mutex_unlock(&bp->link_lock); return rc; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6761f404b8aa..9179f7b0b900 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -647,8 +647,7 @@ static void macb_mac_link_up(struct phylink_config *config, ctrl |= GEM_BIT(GBE); } - /* We do not support MLO_PAUSE_RX yet */ - if (tx_pause) + if (rx_pause) ctrl |= MACB_BIT(PAE); macb_set_tx_clk(bp->tx_clk, speed, ndev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 650db92cb11c..481498585ead 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1911,13 +1911,16 @@ out: static int configure_filter_tcb(struct adapter *adap, unsigned int tid, struct filter_entry *f) { - if (f->fs.hitcnts) + if (f->fs.hitcnts) { set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W, - TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) | + TCB_TIMESTAMP_V(TCB_TIMESTAMP_M), + TCB_TIMESTAMP_V(0ULL), + 1); + set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W, TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M), - TCB_TIMESTAMP_V(0ULL) | TCB_RTT_TS_RECENT_AGE_V(0ULL), 1); + } if (f->fs.newdmac) set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c index b1a073eea60b..a020e8490681 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c @@ -229,7 +229,7 @@ void cxgb4_free_mps_ref_entries(struct adapter *adap) { struct mps_entries_ref *mps_entry, *tmp; - if (!list_empty(&adap->mps_ref)) + if (list_empty(&adap->mps_ref)) return; spin_lock(&adap->mps_ref_lock); diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index cb116b530f5e..2610efe4f873 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -85,7 +85,7 @@ MODULE_PARM_DESC (rx_copybreak, "de2104x Breakpoint at which Rx packets are copi #define DSL CONFIG_DE2104X_DSL #endif -#define DE_RX_RING_SIZE 64 +#define DE_RX_RING_SIZE 128 #define DE_TX_RING_SIZE 64 #define DE_RING_BYTES \ ((sizeof(struct de_desc) * DE_RX_RING_SIZE) + \ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h index 3ea51dd9374b..a24b20f76938 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h @@ -66,8 +66,8 @@ struct dpmac_cmd_get_counter { }; struct dpmac_rsp_get_counter { - u64 pad; - u64 counter; + __le64 pad; + __le64 counter; }; #endif /* _FSL_DPMAC_CMD_H */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 26d5981b798f..177334f0adb1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1053,7 +1053,6 @@ static int enetc_pf_probe(struct pci_dev *pdev, err_reg_netdev: enetc_teardown_serdes(priv); - enetc_mdio_remove(pf); enetc_free_msix(priv); err_alloc_msix: enetc_free_si_resources(priv); @@ -1061,6 +1060,7 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: + enetc_mdio_remove(pf); enetc_of_put_phy(pf); err_map_pf_space: enetc_pci_remove(pdev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index ed3829ae4ef1..a769273b36f7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -334,7 +334,7 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev, * bit6-11 for ppe0-5 * bit12-17 for roce0-5 * bit18-19 for com/dfx - * @enable: false - request reset , true - drop reset + * @dereset: false - request reset , true - drop reset */ static void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) @@ -357,7 +357,7 @@ hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) * bit6-11 for ppe0-5 * bit12-17 for roce0-5 * bit18-19 for com/dfx - * @enable: false - request reset , true - drop reset + * @dereset: false - request reset , true - drop reset */ static void hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 4eb50296f653..14e60c9e491d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -463,8 +463,8 @@ static int __lb_clean_rings(struct hns_nic_priv *priv, /** * nic_run_loopback_test - run loopback test - * @nic_dev: net device - * @loopback_type: loopback type + * @ndev: net device + * @loop_mode: loopback mode */ static int __lb_run_test(struct net_device *ndev, enum hnae_loop loop_mode) @@ -572,7 +572,7 @@ static int __lb_down(struct net_device *ndev, enum hnae_loop loop) /** * hns_nic_self_test - self test - * @dev: net device + * @ndev: net device * @eth_test: test cmd * @data: test result */ @@ -633,7 +633,7 @@ static void hns_nic_self_test(struct net_device *ndev, /** * hns_nic_get_drvinfo - get net driver info - * @dev: net device + * @net_dev: net device * @drvinfo: driver info */ static void hns_nic_get_drvinfo(struct net_device *net_dev, @@ -658,7 +658,7 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, /** * hns_get_ringparam - get ring parameter - * @dev: net device + * @net_dev: net device * @param: ethtool parameter */ static void hns_get_ringparam(struct net_device *net_dev, @@ -683,7 +683,7 @@ static void hns_get_ringparam(struct net_device *net_dev, /** * hns_get_pauseparam - get pause parameter - * @dev: net device + * @net_dev: net device * @param: pause parameter */ static void hns_get_pauseparam(struct net_device *net_dev, @@ -701,7 +701,7 @@ static void hns_get_pauseparam(struct net_device *net_dev, /** * hns_set_pauseparam - set pause parameter - * @dev: net device + * @net_dev: net device * @param: pause parameter * * Return 0 on success, negative on failure @@ -725,7 +725,7 @@ static int hns_set_pauseparam(struct net_device *net_dev, /** * hns_get_coalesce - get coalesce info. - * @dev: net device + * @net_dev: net device * @ec: coalesce info. * * Return 0 on success, negative on failure. @@ -769,7 +769,7 @@ static int hns_get_coalesce(struct net_device *net_dev, /** * hns_set_coalesce - set coalesce info. - * @dev: net device + * @net_dev: net device * @ec: coalesce info. * * Return 0 on success, negative on failure. @@ -808,7 +808,7 @@ static int hns_set_coalesce(struct net_device *net_dev, /** * hns_get_channels - get channel info. - * @dev: net device + * @net_dev: net device * @ch: channel info. */ static void @@ -825,7 +825,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) /** * get_ethtool_stats - get detail statistics. - * @dev: net device + * @netdev: net device * @stats: statistics info. * @data: statistics data. */ @@ -883,8 +883,8 @@ static void hns_get_ethtool_stats(struct net_device *netdev, /** * get_strings: Return a set of strings that describe the requested objects - * @dev: net device - * @stats: string set ID. + * @netdev: net device + * @stringset: string set ID. * @data: objects data. */ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) @@ -972,7 +972,7 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) /** * nic_get_sset_count - get string set count witch returned by nic_get_strings. - * @dev: net device + * @netdev: net device * @stringset: string set index, 0: self test string; 1: statistics string. * * Return string set count. @@ -1006,7 +1006,7 @@ static int hns_get_sset_count(struct net_device *netdev, int stringset) /** * hns_phy_led_set - set phy LED status. - * @dev: net device + * @netdev: net device * @value: LED state. * * Return 0 on success, negative on failure. @@ -1028,7 +1028,7 @@ static int hns_phy_led_set(struct net_device *netdev, int value) /** * nic_set_phys_id - set phy identify LED. - * @dev: net device + * @netdev: net device * @state: LED state. * * Return 0 on success, negative on failure. @@ -1104,9 +1104,9 @@ hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) /** * hns_get_regs - get net device register - * @dev: net device + * @net_dev: net device * @cmd: ethtool cmd - * @date: register data + * @data: register data */ static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, void *data) @@ -1126,7 +1126,7 @@ static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, /** * nic_get_regs_len - get total register len. - * @dev: net device + * @net_dev: net device * * Return total register len. */ @@ -1151,7 +1151,7 @@ static int hns_get_regs_len(struct net_device *net_dev) /** * hns_nic_nway_reset - nway reset - * @dev: net device + * @netdev: net device * * Return 0 on success, negative on failure */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 6bb65ade1d77..c340d9acba80 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1654,6 +1654,7 @@ static void hinic_diag_test(struct net_device *netdev, } netif_carrier_off(netdev); + netif_tx_disable(netdev); err = do_lp_test(nic_dev, eth_test->flags, LP_DEFAULT_TIME, &test_index); @@ -1662,9 +1663,12 @@ static void hinic_diag_test(struct net_device *netdev, data[test_index] = 1; } + netif_tx_wake_all_queues(netdev); + err = hinic_port_link_state(nic_dev, &link_state); if (!err && link_state == HINIC_LINK_STATE_UP) netif_carrier_on(netdev); + } static int hinic_set_phys_id(struct net_device *netdev, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index c6ce5966284c..2ebae6cb5db5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -47,8 +47,12 @@ #define MGMT_MSG_TIMEOUT 5000 +#define SET_FUNC_PORT_MBOX_TIMEOUT 30000 + #define SET_FUNC_PORT_MGMT_TIMEOUT 25000 +#define UPDATE_FW_MGMT_TIMEOUT 20000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) @@ -361,16 +365,22 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, return -EINVAL; } - if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) - timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + if (HINIC_IS_VF(hwif)) { + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MBOX_TIMEOUT; - if (HINIC_IS_VF(hwif)) return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in, - in_size, buf_out, out_size, 0); - else + in_size, buf_out, out_size, timeout); + } else { + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + else if (cmd == HINIC_PORT_CMD_UPDATE_FW) + timeout = UPDATE_FW_MGMT_TIMEOUT; + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, MSG_NOT_RESP, timeout); + } } static void recv_mgmt_msg_work_handler(struct work_struct *work) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 501056fd32ee..28581bd8ce07 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -174,6 +174,24 @@ err_init_txq: return err; } +static void enable_txqs_napi(struct hinic_dev *nic_dev) +{ + int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + int i; + + for (i = 0; i < num_txqs; i++) + napi_enable(&nic_dev->txqs[i].napi); +} + +static void disable_txqs_napi(struct hinic_dev *nic_dev) +{ + int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + int i; + + for (i = 0; i < num_txqs; i++) + napi_disable(&nic_dev->txqs[i].napi); +} + /** * free_txqs - Free the Logical Tx Queues of specific NIC device * @nic_dev: the specific NIC device @@ -400,6 +418,8 @@ int hinic_open(struct net_device *netdev) goto err_create_txqs; } + enable_txqs_napi(nic_dev); + err = create_rxqs(nic_dev); if (err) { netif_err(nic_dev, drv, netdev, @@ -484,6 +504,7 @@ err_port_state: } err_create_rxqs: + disable_txqs_napi(nic_dev); free_txqs(nic_dev); err_create_txqs: @@ -497,6 +518,9 @@ int hinic_close(struct net_device *netdev) struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; + /* Disable txq napi firstly to aviod rewaking txq in free_tx_poll */ + disable_txqs_napi(nic_dev); + down(&nic_dev->mgmt_lock); flags = nic_dev->flags; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 5bee951fe9d4..d0072f5e7efc 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -543,18 +543,25 @@ static int rx_request_irq(struct hinic_rxq *rxq) if (err) { netif_err(nic_dev, drv, rxq->netdev, "Failed to set RX interrupt coalescing attribute\n"); - rx_del_napi(rxq); - return err; + goto err_req_irq; } err = request_irq(rq->irq, rx_irq, 0, rxq->irq_name, rxq); - if (err) { - rx_del_napi(rxq); - return err; - } + if (err) + goto err_req_irq; cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask); - return irq_set_affinity_hint(rq->irq, &rq->affinity_mask); + err = irq_set_affinity_hint(rq->irq, &rq->affinity_mask); + if (err) + goto err_irq_affinity; + + return 0; + +err_irq_affinity: + free_irq(rq->irq, rxq); +err_req_irq: + rx_del_napi(rxq); + return err; } static void rx_free_irq(struct hinic_rxq *rxq) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index a97498ee6914..c1f81e9144a1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -717,8 +717,8 @@ static int free_tx_poll(struct napi_struct *napi, int budget) netdev_txq = netdev_get_tx_queue(txq->netdev, qp->q_id); __netif_tx_lock(netdev_txq, smp_processor_id()); - - netif_wake_subqueue(nic_dev->netdev, qp->q_id); + if (!netif_testing(nic_dev->netdev)) + netif_wake_subqueue(nic_dev->netdev, qp->q_id); __netif_tx_unlock(netdev_txq); @@ -745,18 +745,6 @@ static int free_tx_poll(struct napi_struct *napi, int budget) return budget; } -static void tx_napi_add(struct hinic_txq *txq, int weight) -{ - netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, weight); - napi_enable(&txq->napi); -} - -static void tx_napi_del(struct hinic_txq *txq) -{ - napi_disable(&txq->napi); - netif_napi_del(&txq->napi); -} - static irqreturn_t tx_irq(int irq, void *data) { struct hinic_txq *txq = data; @@ -790,7 +778,7 @@ static int tx_request_irq(struct hinic_txq *txq) qp = container_of(sq, struct hinic_qp, sq); - tx_napi_add(txq, nic_dev->tx_weight); + netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, nic_dev->tx_weight); hinic_hwdev_msix_set(nic_dev->hwdev, sq->msix_entry, TX_IRQ_NO_PENDING, TX_IRQ_NO_COALESC, @@ -807,14 +795,14 @@ static int tx_request_irq(struct hinic_txq *txq) if (err) { netif_err(nic_dev, drv, txq->netdev, "Failed to set TX interrupt coalescing attribute\n"); - tx_napi_del(txq); + netif_napi_del(&txq->napi); return err; } err = request_irq(sq->irq, tx_irq, 0, txq->irq_name, txq); if (err) { dev_err(&pdev->dev, "Failed to request Tx irq\n"); - tx_napi_del(txq); + netif_napi_del(&txq->napi); return err; } @@ -826,7 +814,7 @@ static void tx_free_irq(struct hinic_txq *txq) struct hinic_sq *sq = txq->sq; free_irq(sq->irq, txq); - tx_napi_del(txq); + netif_napi_del(&txq->napi); } /** diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d3a774331afc..1b702a43a5d0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2032,16 +2032,18 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); - if (rc) + if (rc) { netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", rc); goto out; + } rc = reset_rx_pools(adapter); - if (rc) + if (rc) { netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", rc); goto out; + } } ibmvnic_disable_irqs(adapter); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8e133d6545bd..47bfb2e95e2d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1115,7 +1115,7 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf) static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) { struct i40e_mac_filter *f; - int num_vlans = 0, bkt; + u16 num_vlans = 0, bkt; hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) @@ -1134,8 +1134,8 @@ static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) * * Called to get number of VLANs and VLAN list present in mac_filter_hash. **/ -static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, int *num_vlans, - s16 **vlan_list) +static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, u16 *num_vlans, + s16 **vlan_list) { struct i40e_mac_filter *f; int i = 0; @@ -1169,11 +1169,11 @@ err: **/ static i40e_status i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, - bool unicast_enable, s16 *vl, int num_vlans) + bool unicast_enable, s16 *vl, u16 num_vlans) { + i40e_status aq_ret, aq_tmp = 0; struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - i40e_status aq_ret; int i; /* No VLAN to set promisc on, set on VSI */ @@ -1222,6 +1222,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, vf->vf_id, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); + + if (!aq_tmp) + aq_tmp = aq_ret; } aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, seid, @@ -1235,8 +1238,15 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, vf->vf_id, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); + + if (!aq_tmp) + aq_tmp = aq_ret; } } + + if (aq_tmp) + aq_ret = aq_tmp; + return aq_ret; } @@ -1258,7 +1268,7 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, i40e_status aq_ret = I40E_SUCCESS; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi; - int num_vlans; + u16 num_vlans; s16 *vl; vsi = i40e_find_vsi_from_id(pf, vsi_id); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 3070dfdb7eb4..2d566f3c827b 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -299,18 +299,14 @@ extern char igc_driver_name[]; #define IGC_RX_HDR_LEN IGC_RXBUFFER_256 /* Transmit and receive latency (for PTP timestamps) */ -/* FIXME: These values were estimated using the ones that i225 has as - * basis, they seem to provide good numbers with ptp4l/phc2sys, but we - * need to confirm them. - */ -#define IGC_I225_TX_LATENCY_10 9542 -#define IGC_I225_TX_LATENCY_100 1024 -#define IGC_I225_TX_LATENCY_1000 178 -#define IGC_I225_TX_LATENCY_2500 64 -#define IGC_I225_RX_LATENCY_10 20662 -#define IGC_I225_RX_LATENCY_100 2213 -#define IGC_I225_RX_LATENCY_1000 448 -#define IGC_I225_RX_LATENCY_2500 160 +#define IGC_I225_TX_LATENCY_10 240 +#define IGC_I225_TX_LATENCY_100 58 +#define IGC_I225_TX_LATENCY_1000 80 +#define IGC_I225_TX_LATENCY_2500 1325 +#define IGC_I225_RX_LATENCY_10 6450 +#define IGC_I225_RX_LATENCY_100 185 +#define IGC_I225_RX_LATENCY_1000 300 +#define IGC_I225_RX_LATENCY_2500 1485 /* RX and TX descriptor control thresholds. * PTHRESH - MAC will consider prefetch if it has fewer than this number of diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 36c999250fcc..6a9b5102aa55 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -364,6 +364,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) struct sk_buff *skb = adapter->ptp_tx_skb; struct skb_shared_hwtstamps shhwtstamps; struct igc_hw *hw = &adapter->hw; + int adjust = 0; u64 regval; if (WARN_ON_ONCE(!skb)) @@ -373,6 +374,24 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval |= (u64)rd32(IGC_TXSTMPH) << 32; igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_TX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_TX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_TX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_TX_LATENCY_2500; + break; + } + + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); + /* Clear the lock early before calling skb_tstamp_tx so that * applications are not woken up before the lock bit is clear. We use * a copy of the skb pointer to ensure other threads can't change it diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 1645e4e7ebdb..635ff3a5dcfb 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget) } if (rx < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, rx)) + ltq_dma_enable_irq(&ch->dma); } return rx; @@ -268,9 +268,12 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) net_dev->stats.tx_bytes += bytes; netdev_completed_queue(ch->priv->net_dev, pkts, bytes); + if (netif_queue_stopped(net_dev)) + netif_wake_queue(net_dev); + if (pkts < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, pkts)) + ltq_dma_enable_irq(&ch->dma); } return pkts; @@ -342,10 +345,12 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) { struct xrx200_chan *ch = ptr; - ltq_dma_disable_irq(&ch->dma); - ltq_dma_ack_irq(&ch->dma); + if (napi_schedule_prep(&ch->napi)) { + __napi_schedule(&ch->napi); + ltq_dma_disable_irq(&ch->dma); + } - napi_schedule(&ch->napi); + ltq_dma_ack_irq(&ch->dma); return IRQ_HANDLED; } @@ -499,7 +504,7 @@ static int xrx200_probe(struct platform_device *pdev) /* setup NAPI */ netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32); - netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); + netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); platform_set_drvdata(pdev, priv); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index dfcb1767acbb..c4345e3d616f 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2029,11 +2029,11 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; - page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), - sync_len, napi); for (i = 0; i < sinfo->nr_frags; i++) page_pool_put_full_page(rxq->page_pool, skb_frag_page(&sinfo->frags[i]), napi); + page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), + sync_len, napi); } static int @@ -2383,8 +2383,12 @@ static int mvneta_rx_swbm(struct napi_struct *napi, mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf, &size, page, &ps); } else { - if (unlikely(!xdp_buf.data_hard_start)) + if (unlikely(!xdp_buf.data_hard_start)) { + rx_desc->buf_phys_addr = 0; + page_pool_put_full_page(rxq->page_pool, page, + true); continue; + } mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf, &size, page); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0cc2080fd847..90d5caabd6af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -600,7 +600,7 @@ struct mlx5e_rq { struct dim dim; /* Dynamic Interrupt Moderation */ /* XDP */ - struct bpf_prog *xdp_prog; + struct bpf_prog __rcu *xdp_prog; struct mlx5e_xdpsq *xdpsq; DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; @@ -1005,7 +1005,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); int mlx5e_open(struct net_device *netdev); -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); int mlx5e_bits_invert(unsigned long a, int size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 8fe8b4d6ad1c..254c84739046 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work) monitor_counters_work); mutex_lock(&priv->state_lock); - mlx5e_update_ndo_stats(priv); + mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); mlx5e_monitor_counter_arm(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 5de1cb9f5330..96608dbb9314 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy) int err; int i; - if (!MLX5_CAP_GEN(dev, pcam_reg)) - return -EOPNOTSUPP; - - if (!MLX5_CAP_PCAM_REG(dev, pplm)) - return -EOPNOTSUPP; + if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm)) + return false; MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c6bc9224c3b1..bc5f72ec3623 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -699,6 +699,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5e_mod_hdr_detach(ct_priv->esw->dev, &esw->offloads.mod_hdr, zone_rule->mh); + mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(spec); return err; @@ -958,12 +959,22 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, return 0; } +void mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) +{ + struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); + + if (!ct_priv || !ct_attr->ct_labels_id) + return; + + mapping_remove(ct_priv->labels_mapping, ct_attr->ct_labels_id); +} + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 3baef917a677..708c216325d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -87,12 +87,15 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv); void mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv); +void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr); + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack); +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack); int mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec); @@ -130,12 +133,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) { } +static inline void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {} + static inline int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 9334c9c3e208..24336c60123a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -20,6 +20,11 @@ enum mlx5e_icosq_wqe_type { }; /* General */ +static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb) +{ + return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST; +} + void mlx5e_trigger_irq(struct mlx5e_icosq *sq); void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 0e6946fc121f..b28df21981a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, u32 *len, struct xdp_buff *xdp) { - struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct bpf_prog *prog = rcu_dereference(rq->xdp_prog); u32 act; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a33a1f762c70..40db27bf790b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, { struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk; u32 cqe_bcnt32 = cqe_bcnt; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xsk_buff_dma_sync_for_cpu(xdp); prefetch(xdp->data); - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); - rcu_read_unlock(); - /* Possible flows: * - XDP_REDIRECT to XSKMAP: * The page is owned by the userspace from now. @@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, * allocated first from the Reuse Ring, so it has enough space. */ - if (likely(consumed)) { + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) { if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ @@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, u32 cqe_bcnt) { struct xdp_buff *xdp = wi->di->xsk; - bool consumed; /* wi->offset is not used in this function, because xdp->data and the * DMA address point directly to the necessary place. Furthermore, the @@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, return NULL; } - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp); - rcu_read_unlock(); - - if (likely(consumed)) + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp))) return NULL; /* page/packet was consumed by XDP */ /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dd9df519d383..55e65a438de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -106,8 +106,7 @@ err_free_cparam: void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - napi_synchronize(&c->napi); - synchronize_rcu(); /* Sync with the XSK wakeup. */ + synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */ mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index acf6d80a6bb7..6bbfcf18107d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx) /* Re-sync */ /* Runs in work context */ -static struct mlx5_wqe_ctrl_seg * +static int resync_post_get_progress_params(struct mlx5e_icosq *sq, struct mlx5e_ktls_offload_context_rx *priv_rx) { @@ -258,15 +258,19 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { err = -ENOMEM; - goto err_out; + goto err_free; } buf->priv_rx = priv_rx; BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); + + spin_lock(&sq->channel->async_icosq_lock); + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + spin_unlock(&sq->channel->async_icosq_lock); err = -ENOSPC; - goto err_out; + goto err_dma_unmap; } pi = mlx5e_icosq_get_next_pi(sq, 1); @@ -294,12 +298,18 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, }; icosq_fill_wi(sq, pi, &wi); sq->pc++; + mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); + spin_unlock(&sq->channel->async_icosq_lock); - return cseg; + return 0; +err_dma_unmap: + dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); +err_free: + kfree(buf); err_out: priv_rx->stats->tls_resync_req_skip++; - return ERR_PTR(err); + return err; } /* Function is called with elevated refcount. @@ -309,10 +319,8 @@ static void resync_handle_work(struct work_struct *work) { struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; - struct mlx5_wqe_ctrl_seg *cseg; struct mlx5e_channel *c; struct mlx5e_icosq *sq; - struct mlx5_wq_cyc *wq; resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work); priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync); @@ -324,18 +332,9 @@ static void resync_handle_work(struct work_struct *work) c = resync->priv->channels.c[priv_rx->rxq]; sq = &c->async_icosq; - wq = &sq->wq; - - spin_lock(&c->async_icosq_lock); - cseg = resync_post_get_progress_params(sq, priv_rx); - if (IS_ERR(cseg)) { + if (resync_post_get_progress_params(sq, priv_rx)) refcount_dec(&resync->refcnt); - goto unlock; - } - mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); -unlock: - spin_unlock(&c->async_icosq_lock); } static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync, @@ -386,16 +385,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; + struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; resync = &priv_rx->resync; - + dev = resync->priv->mdev->device; if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; - dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr, - PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, + DMA_FROM_DEVICE); ctx = buf->progress.ctx; tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state); @@ -411,6 +411,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, priv_rx->stats->tls_resync_req_end++; out: refcount_dec(&resync->refcnt); + dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); kfree(buf); } @@ -659,7 +660,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx); set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags); mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL); - napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi); + synchronize_rcu(); /* Sync with NAPI */ if (!cancel_work_sync(&priv_rx->rule.work)) /* completion is needed, as the priv_rx in the add flow * is maintained on the wqe info (wi), not on the socket. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c index 01468ec27446..b949b9a7538b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -35,7 +35,6 @@ #include <net/sock.h> #include "en.h" -#include "accel/tls.h" #include "fpga/sdk.h" #include "en_accel/tls.h" @@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) +static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +{ + return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); +} + int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; return NUM_TLS_SW_COUNTERS; @@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { unsigned int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) @@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aebcf73f8546..b3cda7b6e5e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work) mutex_unlock(&priv->state_lock); } -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv) -{ - int i; - - for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--) - if (mlx5e_nic_stats_grps[i]->update_stats_mask & - MLX5E_NDO_UPDATE_STATS) - mlx5e_nic_stats_grps[i]->update_stats(priv); -} - static void mlx5e_update_stats_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, @@ -399,7 +389,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (params->xdp_prog) bpf_prog_inc(params->xdp_prog); - rq->xdp_prog = params->xdp_prog; + RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog); rq_xdp_ix = rq->ix; if (xsk) @@ -408,7 +398,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (err < 0) goto err_rq_wq_destroy; - rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); pool_size = 1 << params->log_rq_mtu_frames; @@ -564,8 +554,8 @@ err_free: } err_rq_wq_destroy: - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); + if (params->xdp_prog) + bpf_prog_put(params->xdp_prog); xdp_rxq_info_unreg(&rq->xdp_rxq); page_pool_destroy(rq->page_pool); mlx5_wq_destroy(&rq->wq_ctrl); @@ -575,10 +565,16 @@ err_rq_wq_destroy: static void mlx5e_free_rq(struct mlx5e_rq *rq) { + struct mlx5e_channel *c = rq->channel; + struct bpf_prog *old_prog = NULL; int i; - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); + /* drop_rq has neither channel nor xdp_prog. */ + if (c) + old_prog = rcu_dereference_protected(rq->xdp_prog, + lockdep_is_held(&c->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: @@ -867,7 +863,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq) void mlx5e_deactivate_rq(struct mlx5e_rq *rq) { clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ + synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */ } void mlx5e_close_rq(struct mlx5e_rq *rq) @@ -1312,12 +1308,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { - struct mlx5e_channel *c = sq->channel; struct mlx5_wq_cyc *wq = &sq->wq; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */ mlx5e_tx_disable_queue(sq->txq); @@ -1392,10 +1386,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq) void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) { - struct mlx5e_channel *c = icosq->channel; - clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ } void mlx5e_close_icosq(struct mlx5e_icosq *sq) @@ -1474,7 +1466,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) struct mlx5e_channel *c = sq->channel; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ mlx5e_destroy_sq(c->mdev, sq->sqn); mlx5e_free_xdpsq_descs(sq); @@ -3567,6 +3559,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->rx_packets += rq_stats->packets + xskrq_stats->packets; s->rx_bytes += rq_stats->bytes + xskrq_stats->bytes; + s->multicast += rq_stats->mcast_packets + xskrq_stats->mcast_packets; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -3582,7 +3575,6 @@ void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; /* In switchdev mode, monitor counters doesn't monitor @@ -3617,12 +3609,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + stats->rx_frame_errors; stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; - - /* vport multicast also counts packets that are dropped due to steering - * or rx out of buffer - */ - stats->multicast = - VPORT_COUNTER_GET(vstats, received_eth_multicast.packets); } static void mlx5e_set_rx_mode(struct net_device *dev) @@ -4330,6 +4316,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) return 0; } +static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog) +{ + struct bpf_prog *old_prog; + + old_prog = rcu_replace_pointer(rq->xdp_prog, prog, + lockdep_is_held(&rq->channel->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); +} + static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4388,29 +4384,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) */ for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - napi_synchronize(&c->napi); - /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ - - old_prog = xchg(&c->rq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - - if (xsk_open) { - old_prog = xchg(&c->xskrq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - } - set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - /* napi_schedule in case we have missed anything */ - napi_schedule(&c->napi); + mlx5e_rq_replace_xdp_prog(&c->rq, prog); + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); } unlock: @@ -5200,7 +5177,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .enable = mlx5e_nic_enable, .disable = mlx5e_nic_disable, .update_rx = mlx5e_update_nic_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_nic, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e13e5d1b3eae..e979bff64c49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1171,7 +1171,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .cleanup_tx = mlx5e_cleanup_rep_tx, .enable = mlx5e_rep_enable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = 1, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), @@ -1189,7 +1189,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .enable = mlx5e_uplink_rep_enable, .disable = mlx5e_uplink_rep_disable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 65828af120b7..64c8ac5eabf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -53,6 +53,7 @@ #include "en/xsk/rx.h" #include "en/health.h" #include "en/params.h" +#include "en/txrx.h" static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, @@ -1080,6 +1081,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, mlx5e_enable_ecn(rq, skb); skb->protocol = eth_type_trans(skb, netdev); + + if (unlikely(mlx5e_skb_is_multicast(skb))) + stats->mcast_packets++; } static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, @@ -1132,7 +1136,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; - bool consumed; u32 frag_size; va = page_address(di->page) + wi->offset; @@ -1144,11 +1147,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp); - rcu_read_unlock(); - if (consumed) + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp)) return NULL; /* page/packet was consumed by XDP */ rx_headroom = xdp.data - xdp.data_hard_start; @@ -1438,7 +1438,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct sk_buff *skb; void *va, *data; u32 frag_size; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -1455,11 +1454,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp); - rcu_read_unlock(); - if (consumed) { + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e3b2f59408e6..f6383bc2bc3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -54,6 +54,18 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv) return total; } +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv) +{ + mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; + const unsigned int num_stats_grps = stats_grps_num(priv); + int i; + + for (i = num_stats_grps - 1; i >= 0; i--) + if (stats_grps[i]->update_stats && + stats_grps[i]->update_stats_mask & MLX5E_NDO_UPDATE_STATS) + stats_grps[i]->update_stats(priv); +} + void mlx5e_stats_update(struct mlx5e_priv *priv) { mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 2e1cca1923b9..562263d62141 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -103,6 +103,7 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv); void mlx5e_stats_update(struct mlx5e_priv *priv); void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx); void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data); +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv); /* Concrete NIC Stats */ @@ -119,6 +120,7 @@ struct mlx5e_sw_stats { u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_mcast_packets; u64 rx_ecn_mark; u64 rx_removed_vlan_packets; u64 rx_csum_unnecessary; @@ -298,6 +300,7 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 mcast_packets; u64 ecn_mark; u64 removed_vlan_packets; u64 xdp_drop; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fd53d101d8fd..1c93f92d9210 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1290,11 +1290,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) { + if (flow_flag_test(flow, NOT_READY)) remove_unready_flow(flow); - kvfree(attr->parse_attr); - return; - } if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) @@ -1315,6 +1312,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, } kvfree(attr->parse_attr); + mlx5_tc_ct_match_del(priv, &flow->esw_attr->ct_attr); + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); @@ -2625,6 +2624,22 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; +static unsigned long mask_to_le(unsigned long mask, int size) +{ + __be32 mask_be32; + __be16 mask_be16; + + if (size == 32) { + mask_be32 = (__force __be32)(mask); + mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); + } else if (size == 16) { + mask_be32 = (__force __be32)(mask); + mask_be16 = *(__be16 *)&mask_be32; + mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + } + + return mask; +} static int offload_pedit_fields(struct mlx5e_priv *priv, int namespace, struct pedit_headers_action *hdrs, @@ -2638,9 +2653,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; struct mlx5_fields *f; - unsigned long mask; - __be32 mask_be32; - __be16 mask_be16; + unsigned long mask, field_mask; int err; u8 cmd; @@ -2706,14 +2719,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (skip) continue; - if (f->field_bsize == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (f->field_bsize == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); - } + mask = mask_to_le(mask, f->field_bsize); first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); @@ -2744,9 +2750,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (cmd == MLX5_ACTION_TYPE_SET) { int start; + field_mask = mask_to_le(f->field_mask, f->field_bsize); + /* if field is bit sized it can start not from first bit */ - start = find_first_bit((unsigned long *)&f->field_mask, - f->field_bsize); + start = find_first_bit(&field_mask, f->field_bsize); MLX5_SET(set_action_in, action, offset, first - start); /* length is num of bits to be written, zero means length of 32 */ @@ -4402,8 +4409,8 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, goto err_free; /* actions validation depends on parsing the ct matches first */ - err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, - &flow->esw_attr->ct_attr, extack); + err = mlx5_tc_ct_match_add(priv, &parse_attr->spec, f, + &flow->esw_attr->ct_attr, extack); if (err) goto err_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index de10b06bade5..d5868670f8a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) struct mlx5e_xdpsq *xsksq = &c->xsksq; struct mlx5e_rq *xskrq = &c->xskrq; struct mlx5e_rq *rq = &c->rq; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); bool aff_change = false; bool busy_xsk = false; bool busy = false; int work_done = 0; + bool xsk_open; int i; + rcu_read_lock(); + + xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + ch_stats->poll++; for (i = 0; i < c->num_tc; i++) @@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) busy |= busy_xsk; if (busy) { - if (likely(mlx5e_channel_no_affinity_change(c))) - return budget; + if (likely(mlx5e_channel_no_affinity_change(c))) { + work_done = budget; + goto out; + } ch_stats->aff_change++; aff_change = true; if (budget && work_done == budget) @@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; ch_stats->arm++; @@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) ch_stats->force_irq++; } +out: + rcu_read_unlock(); + return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d2516922d867..1bcf2609dca8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1219,35 +1219,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.send_to_vport_grp = g; - /* create peer esw miss group */ - memset(flow_group_in, 0, inlen); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + /* create peer esw miss group */ + memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); + esw_set_flow_group_source_port(esw, flow_group_in); - if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { - match_criteria = MLX5_ADDR_OF(create_flow_group_in, - flow_group_in, - match_criteria); + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { + match_criteria = MLX5_ADDR_OF(create_flow_group_in, + flow_group_in, + match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - misc_parameters.source_eswitch_owner_vhca_id); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_eswitch_owner_vhca_id); - MLX5_SET(create_flow_group_in, flow_group_in, - source_eswitch_owner_vhca_id_valid, 1); - } + MLX5_SET(create_flow_group_in, flow_group_in, + source_eswitch_owner_vhca_id_valid, 1); + } - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, - ix + esw->total_vports - 1); - ix += esw->total_vports; + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + esw->total_vports - 1); + ix += esw->total_vports; - g = mlx5_create_flow_group(fdb, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); - goto peer_miss_err; + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); + goto peer_miss_err; + } + esw->fdb_table.offloads.peer_miss_grp = g; } - esw->fdb_table.offloads.peer_miss_grp = g; /* create miss group */ memset(flow_group_in, 0, inlen); @@ -1281,7 +1283,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) miss_rule_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); miss_err: - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); peer_miss_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); send_vport_err: @@ -1305,7 +1308,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi); mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni); mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); mlx5_esw_chains_destroy(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9ccec5f8b92a..75fa44eee434 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -654,7 +654,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, fte->action = *flow_act; fte->flow_context = spec->flow_context; - tree_init_node(&fte->node, NULL, del_sw_fte); + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); return fte; } @@ -1792,7 +1792,6 @@ skip_search: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); return rule; } rule = ERR_PTR(-ENOENT); @@ -1891,7 +1890,6 @@ search_again_locked: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); tree_put_node(&g->node, false); return rule; @@ -2001,7 +1999,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) up_write_ref_node(&fte->node, false); } else { del_hw_fte(&fte->node); - up_write(&fte->node.lock); + /* Avoid double call to del_hw_fte */ + fte->node.del_hw_func = NULL; + up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); } kfree(handle); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 5abb7d2b0a9e..8518e1d60da4 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -421,10 +421,15 @@ int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port, if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP && ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { + spin_lock(&ocelot_port->ts_id_lock); + shinfo->tx_flags |= SKBTX_IN_PROGRESS; /* Store timestamp ID in cb[0] of sk_buff */ - skb->cb[0] = ocelot_port->ts_id % 4; + skb->cb[0] = ocelot_port->ts_id; + ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4; skb_queue_tail(&ocelot_port->tx_skbs, skb); + + spin_unlock(&ocelot_port->ts_id_lock); return 0; } return -ENODATA; @@ -1300,6 +1305,7 @@ void ocelot_init_port(struct ocelot *ocelot, int port) struct ocelot_port *ocelot_port = ocelot->ports[port]; skb_queue_head_init(&ocelot_port->tx_skbs); + spin_lock_init(&ocelot_port->ts_id_lock); /* Basic L2 initialization */ @@ -1544,18 +1550,18 @@ EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { - struct ocelot_port *port; - int i; - cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); - - for (i = 0; i < ocelot->num_phys_ports; i++) { - port = ocelot->ports[i]; - skb_queue_purge(&port->tx_skbs); - } } EXPORT_SYMBOL(ocelot_deinit); +void ocelot_deinit_port(struct ocelot *ocelot, int port) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + skb_queue_purge(&ocelot_port->tx_skbs); +} +EXPORT_SYMBOL(ocelot_deinit_port); + MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 0668d23cdbfa..8490e42e9e2d 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -330,6 +330,7 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) u8 grp = 0; /* Send everything on CPU group 0 */ unsigned int i, count, last; int port = priv->chip_port; + bool do_tstamp; val = ocelot_read(ocelot, QS_INJ_STATUS); if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))) || @@ -344,10 +345,12 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) info.vid = skb_vlan_tag_get(skb); /* Check if timestamping is needed */ + do_tstamp = (ocelot_port_add_txtstamp_skb(ocelot_port, skb) == 0); + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) { info.rew_op = ocelot_port->ptp_cmd; if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) - info.rew_op |= (ocelot_port->ts_id % 4) << 3; + info.rew_op |= skb->cb[0] << 3; } ocelot_gen_ifh(ifh, &info); @@ -380,12 +383,9 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - if (!ocelot_port_add_txtstamp_skb(ocelot_port, skb)) { - ocelot_port->ts_id++; - return NETDEV_TX_OK; - } + if (!do_tstamp) + dev_kfree_skb_any(skb); - dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 65408bc994c4..dfb1535f26f2 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -806,17 +806,17 @@ static const struct vcap_field vsc7514_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {123, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {124, 1}, - [VCAP_IS2_HK_L4_SPORT] = {125, 16}, - [VCAP_IS2_HK_L4_DPORT] = {141, 16}, + [VCAP_IS2_HK_L4_DPORT] = {125, 16}, + [VCAP_IS2_HK_L4_SPORT] = {141, 16}, [VCAP_IS2_HK_L4_RNG] = {157, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {165, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {166, 1}, - [VCAP_IS2_HK_L4_URG] = {167, 1}, - [VCAP_IS2_HK_L4_ACK] = {168, 1}, - [VCAP_IS2_HK_L4_PSH] = {169, 1}, - [VCAP_IS2_HK_L4_RST] = {170, 1}, - [VCAP_IS2_HK_L4_SYN] = {171, 1}, - [VCAP_IS2_HK_L4_FIN] = {172, 1}, + [VCAP_IS2_HK_L4_FIN] = {167, 1}, + [VCAP_IS2_HK_L4_SYN] = {168, 1}, + [VCAP_IS2_HK_L4_RST] = {169, 1}, + [VCAP_IS2_HK_L4_PSH] = {170, 1}, + [VCAP_IS2_HK_L4_ACK] = {171, 1}, + [VCAP_IS2_HK_L4_URG] = {172, 1}, [VCAP_IS2_HK_L4_1588_DOM] = {173, 8}, [VCAP_IS2_HK_L4_1588_VER] = {181, 4}, /* IP4_OTHER (TYPE=101) */ @@ -896,11 +896,137 @@ static struct ptp_clock_info ocelot_ptp_clock_info = { .enable = ocelot_ptp_enable, }; +static void mscc_ocelot_release_ports(struct ocelot *ocelot) +{ + int port; + + for (port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port_private *priv; + struct ocelot_port *ocelot_port; + + ocelot_port = ocelot->ports[port]; + if (!ocelot_port) + continue; + + ocelot_deinit_port(ocelot, port); + + priv = container_of(ocelot_port, struct ocelot_port_private, + port); + + unregister_netdev(priv->dev); + free_netdev(priv->dev); + } +} + +static int mscc_ocelot_init_ports(struct platform_device *pdev, + struct device_node *ports) +{ + struct ocelot *ocelot = platform_get_drvdata(pdev); + struct device_node *portnp; + int err; + + ocelot->ports = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, + sizeof(struct ocelot_port *), GFP_KERNEL); + if (!ocelot->ports) + return -ENOMEM; + + /* No NPI port */ + ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE, + OCELOT_TAG_PREFIX_NONE); + + for_each_available_child_of_node(ports, portnp) { + struct ocelot_port_private *priv; + struct ocelot_port *ocelot_port; + struct device_node *phy_node; + phy_interface_t phy_mode; + struct phy_device *phy; + struct regmap *target; + struct resource *res; + struct phy *serdes; + char res_name[8]; + u32 port; + + if (of_property_read_u32(portnp, "reg", &port)) + continue; + + snprintf(res_name, sizeof(res_name), "port%d", port); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + res_name); + target = ocelot_regmap_init(ocelot, res); + if (IS_ERR(target)) + continue; + + phy_node = of_parse_phandle(portnp, "phy-handle", 0); + if (!phy_node) + continue; + + phy = of_phy_find_device(phy_node); + of_node_put(phy_node); + if (!phy) + continue; + + err = ocelot_probe_port(ocelot, port, target, phy); + if (err) { + of_node_put(portnp); + return err; + } + + ocelot_port = ocelot->ports[port]; + priv = container_of(ocelot_port, struct ocelot_port_private, + port); + + of_get_phy_mode(portnp, &phy_mode); + + ocelot_port->phy_mode = phy_mode; + + switch (ocelot_port->phy_mode) { + case PHY_INTERFACE_MODE_NA: + continue; + case PHY_INTERFACE_MODE_SGMII: + break; + case PHY_INTERFACE_MODE_QSGMII: + /* Ensure clock signals and speed is set on all + * QSGMII links + */ + ocelot_port_writel(ocelot_port, + DEV_CLOCK_CFG_LINK_SPEED + (OCELOT_SPEED_1000), + DEV_CLOCK_CFG); + break; + default: + dev_err(ocelot->dev, + "invalid phy mode for port%d, (Q)SGMII only\n", + port); + of_node_put(portnp); + return -EINVAL; + } + + serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = PTR_ERR(serdes); + if (err == -EPROBE_DEFER) + dev_dbg(ocelot->dev, "deferring probe\n"); + else + dev_err(ocelot->dev, + "missing SerDes phys for port%d\n", + port); + + of_node_put(portnp); + return err; + } + + priv->serdes = serdes; + } + + return 0; +} + static int mscc_ocelot_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct device_node *ports, *portnp; int err, irq_xtr, irq_ptp_rdy; + struct device_node *ports; struct ocelot *ocelot; struct regmap *hsio; unsigned int i; @@ -985,20 +1111,24 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ports = of_get_child_by_name(np, "ethernet-ports"); if (!ports) { - dev_err(&pdev->dev, "no ethernet-ports child node found\n"); + dev_err(ocelot->dev, "no ethernet-ports child node found\n"); return -ENODEV; } ocelot->num_phys_ports = of_get_child_count(ports); - ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports, - sizeof(struct ocelot_port *), GFP_KERNEL); - ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys; ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions; ocelot->vcap = vsc7514_vcap_props; - ocelot_init(ocelot); + err = ocelot_init(ocelot); + if (err) + goto out_put_ports; + + err = mscc_ocelot_init_ports(pdev, ports); + if (err) + goto out_put_ports; + if (ocelot->ptp) { err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); if (err) { @@ -1008,96 +1138,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) } } - /* No NPI port */ - ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE, - OCELOT_TAG_PREFIX_NONE); - - for_each_available_child_of_node(ports, portnp) { - struct ocelot_port_private *priv; - struct ocelot_port *ocelot_port; - struct device_node *phy_node; - phy_interface_t phy_mode; - struct phy_device *phy; - struct regmap *target; - struct resource *res; - struct phy *serdes; - char res_name[8]; - u32 port; - - if (of_property_read_u32(portnp, "reg", &port)) - continue; - - snprintf(res_name, sizeof(res_name), "port%d", port); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - res_name); - target = ocelot_regmap_init(ocelot, res); - if (IS_ERR(target)) - continue; - - phy_node = of_parse_phandle(portnp, "phy-handle", 0); - if (!phy_node) - continue; - - phy = of_phy_find_device(phy_node); - of_node_put(phy_node); - if (!phy) - continue; - - err = ocelot_probe_port(ocelot, port, target, phy); - if (err) { - of_node_put(portnp); - goto out_put_ports; - } - - ocelot_port = ocelot->ports[port]; - priv = container_of(ocelot_port, struct ocelot_port_private, - port); - - of_get_phy_mode(portnp, &phy_mode); - - ocelot_port->phy_mode = phy_mode; - - switch (ocelot_port->phy_mode) { - case PHY_INTERFACE_MODE_NA: - continue; - case PHY_INTERFACE_MODE_SGMII: - break; - case PHY_INTERFACE_MODE_QSGMII: - /* Ensure clock signals and speed is set on all - * QSGMII links - */ - ocelot_port_writel(ocelot_port, - DEV_CLOCK_CFG_LINK_SPEED - (OCELOT_SPEED_1000), - DEV_CLOCK_CFG); - break; - default: - dev_err(ocelot->dev, - "invalid phy mode for port%d, (Q)SGMII only\n", - port); - of_node_put(portnp); - err = -EINVAL; - goto out_put_ports; - } - - serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); - if (IS_ERR(serdes)) { - err = PTR_ERR(serdes); - if (err == -EPROBE_DEFER) - dev_dbg(ocelot->dev, "deferring probe\n"); - else - dev_err(ocelot->dev, - "missing SerDes phys for port%d\n", - port); - - of_node_put(portnp); - goto out_put_ports; - } - - priv->serdes = serdes; - } - register_netdevice_notifier(&ocelot_netdevice_nb); register_switchdev_notifier(&ocelot_switchdev_nb); register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); @@ -1114,6 +1154,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev) struct ocelot *ocelot = platform_get_drvdata(pdev); ocelot_deinit_timestamp(ocelot); + mscc_ocelot_release_ports(ocelot); ocelot_deinit(ocelot); unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); unregister_switchdev_notifier(&ocelot_switchdev_nb); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 6eb9fb9a1814..9c9ae33d84ce 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -829,8 +829,8 @@ nfp_port_get_fecparam(struct net_device *netdev, struct nfp_eth_table_port *eth_port; struct nfp_port *port; - param->active_fec = ETHTOOL_FEC_NONE_BIT; - param->fec = ETHTOOL_FEC_NONE_BIT; + param->active_fec = ETHTOOL_FEC_NONE; + param->fec = ETHTOOL_FEC_NONE; port = nfp_port_from_netdev(netdev); eth_port = nfp_port_get_eth_port(port); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index b8f076e4e6b8..3db181f3617a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -4253,7 +4253,8 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | BIT(QED_MF_LLH_PROTO_CLSS) | BIT(QED_MF_LL2_NON_UNICAST) | - BIT(QED_MF_INTER_PF_SWITCH); + BIT(QED_MF_INTER_PF_SWITCH) | + BIT(QED_MF_DISABLE_ARFS); break; case NVM_CFG1_GLOB_MF_MODE_DEFAULT: cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | @@ -4266,6 +4267,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", cdev->mf_bits); + + /* In CMT the PF is unknown when the GFS block processes the + * packet. Therefore cannot use searcher as it has a per PF + * database, and thus ARFS must be disabled. + * + */ + if (QED_IS_CMT(cdev)) + cdev->mf_bits |= BIT(QED_MF_DISABLE_ARFS); } DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 4c6ac8862744..07824bf9d68d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1980,6 +1980,9 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_arfs_config_params *p_cfg_params) { + if (test_bit(QED_MF_DISABLE_ARFS, &p_hwfn->cdev->mf_bits)) + return; + if (p_cfg_params->mode != QED_FILTER_CONFIG_MODE_DISABLE) { qed_gft_config(p_hwfn, p_ptt, p_hwfn->rel_pf_id, p_cfg_params->tcp, diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index f39f629242a1..50e5eb22e60a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -444,6 +444,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->fw_eng = FW_ENGINEERING_VERSION; dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH, &cdev->mf_bits); + if (!test_bit(QED_MF_DISABLE_ARFS, &cdev->mf_bits)) + dev_info->b_arfs_capable = true; dev_info->tx_switching = true; if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f1f75b6d0421..b8dc5c4591ef 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -71,6 +71,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) p_ramrod->personality = PERSONALITY_ETH; break; case QED_PCI_ETH_ROCE: + case QED_PCI_ETH_IWARP: p_ramrod->personality = PERSONALITY_RDMA_AND_ETH; break; default: diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index f961f65d9372..c59b72c90293 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -311,6 +311,9 @@ int qede_alloc_arfs(struct qede_dev *edev) { int i; + if (!edev->dev_info.common.b_arfs_capable) + return -EINVAL; + edev->arfs = vzalloc(sizeof(*edev->arfs)); if (!edev->arfs) return -ENOMEM; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 140a392a81bb..9e1f41ba766c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -804,7 +804,7 @@ static void qede_init_ndev(struct qede_dev *edev) NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) + if (edev->dev_info.common.b_arfs_capable) hw_features |= NETIF_F_NTUPLE; if (edev->dev_info.common.vxlan_enable || @@ -2274,7 +2274,7 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { + if (edev->dev_info.common.b_arfs_capable) { qede_poll_for_freeing_arfs_filters(edev); qede_free_arfs(edev); } @@ -2341,10 +2341,9 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, if (rc) goto err2; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { - rc = qede_alloc_arfs(edev); - if (rc) - DP_NOTICE(edev, "aRFS memory allocation failed\n"); + if (qede_alloc_arfs(edev)) { + edev->ndev->features &= ~NETIF_F_NTUPLE; + edev->dev_info.common.b_arfs_capable = false; } qede_napi_add_enable(edev); diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c index c54b7f8243f3..ffdb36715a49 100644 --- a/drivers/net/ethernet/sfc/ef100.c +++ b/drivers/net/ethernet/sfc/ef100.c @@ -490,6 +490,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev, if (fcw.offset > pci_resource_len(efx->pci_dev, fcw.bar) - ESE_GZ_FCW_LEN) { netif_err(efx, probe, efx->net_dev, "Func control window overruns BAR\n"); + rc = -EIO; goto fail; } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 8ed78577cded..15672d0a4de6 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -17,6 +17,7 @@ #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/gpio/consumer.h> #include <linux/of.h> @@ -2070,9 +2071,61 @@ static int cpsw_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused cpsw_suspend(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_stop(ndev); + } + + rtnl_unlock(); + + /* Select sleep pin state */ + pinctrl_pm_select_sleep_state(dev); + + return 0; +} + +static int __maybe_unused cpsw_resume(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + /* Select default pin state */ + pinctrl_pm_select_default_state(dev); + + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_open(ndev); + } + + rtnl_unlock(); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(cpsw_pm_ops, cpsw_suspend, cpsw_resume); + static struct platform_driver cpsw_driver = { .driver = { .name = "cpsw-switch", + .pm = &cpsw_pm_ops, .of_match_table = cpsw_of_mtable, }, .probe = cpsw_probe, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c71f994fbc73..974a244f45ba 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -777,7 +777,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, struct net_device *dev, struct geneve_sock *gs4, struct flowi4 *fl4, - const struct ip_tunnel_info *info) + const struct ip_tunnel_info *info, + __be16 dport, __be16 sport) { bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); @@ -793,6 +794,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, fl4->flowi4_proto = IPPROTO_UDP; fl4->daddr = info->key.u.ipv4.dst; fl4->saddr = info->key.u.ipv4.src; + fl4->fl4_dport = dport; + fl4->fl4_sport = sport; tos = info->key.tos; if ((tos == 1) && !geneve->cfg.collect_md) { @@ -827,7 +830,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, struct net_device *dev, struct geneve_sock *gs6, struct flowi6 *fl6, - const struct ip_tunnel_info *info) + const struct ip_tunnel_info *info, + __be16 dport, __be16 sport) { bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); @@ -843,6 +847,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, fl6->flowi6_proto = IPPROTO_UDP; fl6->daddr = info->key.u.ipv6.dst; fl6->saddr = info->key.u.ipv6.src; + fl6->fl6_dport = dport; + fl6->fl6_sport = sport; + prio = info->key.tos; if ((prio == 1) && !geneve->cfg.collect_md) { prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb); @@ -889,7 +896,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info); + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -919,7 +928,6 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; } - sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->cfg.collect_md) { tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; @@ -974,7 +982,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info); + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -1003,7 +1013,6 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; } - sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->cfg.collect_md) { prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; @@ -1085,13 +1094,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); + __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct flowi4 fl4; + struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); + sport = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); - rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info); + rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -1101,9 +1115,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct flowi6 fl6; + struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); + sport = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info); + dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -1114,8 +1132,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return -EINVAL; } - info->key.tp_src = udp_flow_src_port(geneve->net, skb, - 1, USHRT_MAX, true); + info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 2181d4538ab7..a0f338cf1424 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -847,6 +847,10 @@ struct nvsp_message { #define NETVSC_XDP_HDRM 256 +#define NETVSC_XFER_HEADER_SIZE(rng_cnt) \ + (offsetof(struct vmtransfer_page_packet_header, ranges) + \ + (rng_cnt) * sizeof(struct vmtransfer_page_range)) + struct multi_send_data { struct sk_buff *skb; /* skb containing the pkt */ struct hv_netvsc_packet *pkt; /* netvsc pkt pending */ @@ -974,6 +978,9 @@ struct net_device_context { /* Serial number of the VF to team with */ u32 vf_serial; + /* Is the current data path through the VF NIC? */ + bool data_path_is_vf; + /* Used to temporarily save the config info across hibernation */ struct netvsc_device_info *saved_netvsc_dev_info; }; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 41f5cf0bb997..5a57d1985bae 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -388,6 +388,15 @@ static int netvsc_init_buf(struct hv_device *device, net_device->recv_section_size = resp->sections[0].sub_alloc_size; net_device->recv_section_cnt = resp->sections[0].num_sub_allocs; + /* Ensure buffer will not overflow */ + if (net_device->recv_section_size < NETVSC_MTU_MIN || (u64)net_device->recv_section_size * + (u64)net_device->recv_section_cnt > (u64)buf_size) { + netdev_err(ndev, "invalid recv_section_size %u\n", + net_device->recv_section_size); + ret = -EINVAL; + goto cleanup; + } + /* Setup receive completion ring. * Add 1 to the recv_section_cnt because at least one entry in a * ring buffer has to be empty. @@ -460,6 +469,12 @@ static int netvsc_init_buf(struct hv_device *device, /* Parse the response */ net_device->send_section_size = init_packet->msg. v1_msg.send_send_buf_complete.section_size; + if (net_device->send_section_size < NETVSC_MTU_MIN) { + netdev_err(ndev, "invalid send_section_size %u\n", + net_device->send_section_size); + ret = -EINVAL; + goto cleanup; + } /* Section count is simply the size divided by the section size. */ net_device->send_section_cnt = buf_size / net_device->send_section_size; @@ -731,12 +746,49 @@ static void netvsc_send_completion(struct net_device *ndev, int budget) { const struct nvsp_message *nvsp_packet = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); + + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netdev_err(ndev, "nvsp_message length too small: %u\n", msglen); + return; + } switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_message_init_complete)) { + netdev_err(ndev, "nvsp_msg length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_1_message_send_receive_buffer_complete)) { + netdev_err(ndev, "nvsp_msg1 length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_1_message_send_send_buffer_complete)) { + netdev_err(ndev, "nvsp_msg1 length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG5_TYPE_SUBCHANNEL: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_5_subchannel_complete)) { + netdev_err(ndev, "nvsp_msg5 length too small: %u\n", + msglen); + return; + } /* Copy the response back */ memcpy(&net_device->channel_init_pkt, nvsp_packet, sizeof(struct nvsp_message)); @@ -1117,19 +1169,28 @@ static void enq_receive_complete(struct net_device *ndev, static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, struct netvsc_channel *nvchan, - const struct vmpacket_descriptor *desc, - const struct nvsp_message *nvsp) + const struct vmpacket_descriptor *desc) { struct net_device_context *net_device_ctx = netdev_priv(ndev); struct vmbus_channel *channel = nvchan->channel; const struct vmtransfer_page_packet_header *vmxferpage_packet = container_of(desc, const struct vmtransfer_page_packet_header, d); + const struct nvsp_message *nvsp = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); u16 q_idx = channel->offermsg.offer.sub_channel_index; char *recv_buf = net_device->recv_buf; u32 status = NVSP_STAT_SUCCESS; int i; int count = 0; + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netif_err(net_device_ctx, rx_err, ndev, + "invalid nvsp header, length too small: %u\n", + msglen); + return 0; + } + /* Make sure this is a valid nvsp packet */ if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) { netif_err(net_device_ctx, rx_err, ndev, @@ -1138,6 +1199,14 @@ static int netvsc_receive(struct net_device *ndev, return 0; } + /* Validate xfer page pkt header */ + if ((desc->offset8 << 3) < sizeof(struct vmtransfer_page_packet_header)) { + netif_err(net_device_ctx, rx_err, ndev, + "Invalid xfer page pkt, offset too small: %u\n", + desc->offset8 << 3); + return 0; + } + if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) { netif_err(net_device_ctx, rx_err, ndev, "Invalid xfer page set id - expecting %x got %x\n", @@ -1148,6 +1217,14 @@ static int netvsc_receive(struct net_device *ndev, count = vmxferpage_packet->range_cnt; + /* Check count for a valid value */ + if (NETVSC_XFER_HEADER_SIZE(count) > desc->offset8 << 3) { + netif_err(net_device_ctx, rx_err, ndev, + "Range count is not valid: %d\n", + count); + return 0; + } + /* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */ for (i = 0; i < count; i++) { u32 offset = vmxferpage_packet->ranges[i].byte_offset; @@ -1155,7 +1232,8 @@ static int netvsc_receive(struct net_device *ndev, void *data; int ret; - if (unlikely(offset + buflen > net_device->recv_buf_size)) { + if (unlikely(offset > net_device->recv_buf_size || + buflen > net_device->recv_buf_size - offset)) { nvchan->rsc.cnt = 0; status = NVSP_STAT_FAIL; netif_err(net_device_ctx, rx_err, ndev, @@ -1194,6 +1272,13 @@ static void netvsc_send_table(struct net_device *ndev, u32 count, offset, *tab; int i; + /* Ensure packet is big enough to read send_table fields */ + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_5_send_indirect_table)) { + netdev_err(ndev, "nvsp_v5_msg length too small: %u\n", msglen); + return; + } + count = nvmsg->msg.v5_msg.send_table.count; offset = nvmsg->msg.v5_msg.send_table.offset; @@ -1225,10 +1310,18 @@ static void netvsc_send_table(struct net_device *ndev, } static void netvsc_send_vf(struct net_device *ndev, - const struct nvsp_message *nvmsg) + const struct nvsp_message *nvmsg, + u32 msglen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); + /* Ensure packet is big enough to read its fields */ + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_4_send_vf_association)) { + netdev_err(ndev, "nvsp_v4_msg length too small: %u\n", msglen); + return; + } + net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; netdev_info(ndev, "VF slot %u %s\n", @@ -1238,16 +1331,24 @@ static void netvsc_send_vf(struct net_device *ndev, static void netvsc_receive_inband(struct net_device *ndev, struct netvsc_device *nvscdev, - const struct nvsp_message *nvmsg, - u32 msglen) + const struct vmpacket_descriptor *desc) { + const struct nvsp_message *nvmsg = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); + + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netdev_err(ndev, "inband nvsp_message length too small: %u\n", msglen); + return; + } + switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: netvsc_send_table(ndev, nvscdev, nvmsg, msglen); break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: - netvsc_send_vf(ndev, nvmsg); + netvsc_send_vf(ndev, nvmsg, msglen); break; } } @@ -1261,23 +1362,20 @@ static int netvsc_process_raw_pkt(struct hv_device *device, { struct vmbus_channel *channel = nvchan->channel; const struct nvsp_message *nvmsg = hv_pkt_data(desc); - u32 msglen = hv_pkt_datalen(desc); trace_nvsp_recv(ndev, channel, nvmsg); switch (desc->type) { case VM_PKT_COMP: - netvsc_send_completion(ndev, net_device, channel, - desc, budget); + netvsc_send_completion(ndev, net_device, channel, desc, budget); break; case VM_PKT_DATA_USING_XFER_PAGES: - return netvsc_receive(ndev, net_device, nvchan, - desc, nvmsg); + return netvsc_receive(ndev, net_device, nvchan, desc); break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(ndev, net_device, nvmsg, msglen); + netvsc_receive_inband(ndev, net_device, desc); break; default: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 64b0a74c1523..9869e390875e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -748,6 +748,13 @@ void netvsc_linkstatus_callback(struct net_device *net, struct netvsc_reconfig *event; unsigned long flags; + /* Ensure the packet is big enough to access its fields */ + if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) { + netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n", + resp->msg_len); + return; + } + /* Update the physical link speed when changing to another vSwitch */ if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) { u32 speed; @@ -2366,7 +2373,16 @@ static int netvsc_register_vf(struct net_device *vf_netdev) return NOTIFY_OK; } -/* VF up/down change detected, schedule to change data path */ +/* Change the data path when VF UP/DOWN/CHANGE are detected. + * + * Typically a UP or DOWN event is followed by a CHANGE event, so + * net_device_ctx->data_path_is_vf is used to cache the current data path + * to avoid the duplicate call of netvsc_switch_datapath() and the duplicate + * message. + * + * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network + * interface, there is only the CHANGE event and no UP or DOWN event. + */ static int netvsc_vf_changed(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2383,6 +2399,10 @@ static int netvsc_vf_changed(struct net_device *vf_netdev) if (!netvsc_dev) return NOTIFY_DONE; + if (net_device_ctx->data_path_is_vf == vf_is_up) + return NOTIFY_OK; + net_device_ctx->data_path_is_vf = vf_is_up; + netvsc_switch_datapath(ndev, vf_is_up); netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); @@ -2587,8 +2607,8 @@ static int netvsc_remove(struct hv_device *dev) static int netvsc_suspend(struct hv_device *dev) { struct net_device_context *ndev_ctx; - struct net_device *vf_netdev, *net; struct netvsc_device *nvdev; + struct net_device *net; int ret; net = hv_get_drvdata(dev); @@ -2604,10 +2624,6 @@ static int netvsc_suspend(struct hv_device *dev) goto out; } - vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); - if (vf_netdev) - netvsc_unregister_vf(vf_netdev); - /* Save the current config info */ ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev); @@ -2628,6 +2644,12 @@ static int netvsc_resume(struct hv_device *dev) rtnl_lock(); net_device_ctx = netdev_priv(net); + + /* Reset the data path to the netvsc NIC before re-opening the vmbus + * channel. Later netvsc_netdev_event() will switch the data path to + * the VF upon the UP or CHANGE event. + */ + net_device_ctx->data_path_is_vf = false; device_info = net_device_ctx->saved_netvsc_dev_info; ret = netvsc_attach(net, device_info); @@ -2695,6 +2717,7 @@ static int netvsc_netdev_event(struct notifier_block *this, return netvsc_unregister_vf(event_dev); case NETDEV_UP: case NETDEV_DOWN: + case NETDEV_CHANGE: return netvsc_vf_changed(event_dev); default: return NOTIFY_DONE; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index b81ceba38218..12ad471ac5e1 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -275,6 +275,16 @@ static void rndis_filter_receive_response(struct net_device *ndev, return; } + /* Ensure the packet is big enough to read req_id. Req_id is the 1st + * field in any request/response message, so the payload should have at + * least sizeof(u32) bytes + */ + if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(u32)) { + netdev_err(ndev, "rndis msg_len too small: %u\n", + resp->msg_len); + return; + } + spin_lock_irqsave(&dev->request_lock, flags); list_for_each_entry(request, &dev->req_list, list_ent) { /* @@ -331,8 +341,9 @@ static void rndis_filter_receive_response(struct net_device *ndev, * Get the Per-Packet-Info with the specified type * return NULL if not found. */ -static inline void *rndis_get_ppi(struct rndis_packet *rpkt, - u32 type, u8 internal) +static inline void *rndis_get_ppi(struct net_device *ndev, + struct rndis_packet *rpkt, + u32 rpkt_len, u32 type, u8 internal) { struct rndis_per_packet_info *ppi; int len; @@ -340,11 +351,36 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, if (rpkt->per_pkt_info_offset == 0) return NULL; + /* Validate info_offset and info_len */ + if (rpkt->per_pkt_info_offset < sizeof(struct rndis_packet) || + rpkt->per_pkt_info_offset > rpkt_len) { + netdev_err(ndev, "Invalid per_pkt_info_offset: %u\n", + rpkt->per_pkt_info_offset); + return NULL; + } + + if (rpkt->per_pkt_info_len > rpkt_len - rpkt->per_pkt_info_offset) { + netdev_err(ndev, "Invalid per_pkt_info_len: %u\n", + rpkt->per_pkt_info_len); + return NULL; + } + ppi = (struct rndis_per_packet_info *)((ulong)rpkt + rpkt->per_pkt_info_offset); len = rpkt->per_pkt_info_len; while (len > 0) { + /* Validate ppi_offset and ppi_size */ + if (ppi->size > len) { + netdev_err(ndev, "Invalid ppi size: %u\n", ppi->size); + continue; + } + + if (ppi->ppi_offset >= ppi->size) { + netdev_err(ndev, "Invalid ppi_offset: %u\n", ppi->ppi_offset); + continue; + } + if (ppi->type == type && ppi->internal == internal) return (void *)((ulong)ppi + ppi->ppi_offset); len -= ppi->size; @@ -388,14 +424,29 @@ static int rndis_filter_receive_data(struct net_device *ndev, const struct ndis_pkt_8021q_info *vlan; const struct rndis_pktinfo_id *pktinfo_id; const u32 *hash_info; - u32 data_offset; + u32 data_offset, rpkt_len; void *data; bool rsc_more = false; int ret; + /* Ensure data_buflen is big enough to read header fields */ + if (data_buflen < RNDIS_HEADER_SIZE + sizeof(struct rndis_packet)) { + netdev_err(ndev, "invalid rndis pkt, data_buflen too small: %u\n", + data_buflen); + return NVSP_STAT_FAIL; + } + + /* Validate rndis_pkt offset */ + if (rndis_pkt->data_offset >= data_buflen - RNDIS_HEADER_SIZE) { + netdev_err(ndev, "invalid rndis packet offset: %u\n", + rndis_pkt->data_offset); + return NVSP_STAT_FAIL; + } + /* Remove the rndis header and pass it back up the stack */ data_offset = RNDIS_HEADER_SIZE + rndis_pkt->data_offset; + rpkt_len = data_buflen - RNDIS_HEADER_SIZE; data_buflen -= data_offset; /* @@ -410,13 +461,13 @@ static int rndis_filter_receive_data(struct net_device *ndev, return NVSP_STAT_FAIL; } - vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO, 0); + vlan = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, IEEE_8021Q_INFO, 0); - csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO, 0); + csum_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, TCPIP_CHKSUM_PKTINFO, 0); - hash_info = rndis_get_ppi(rndis_pkt, NBL_HASH_VALUE, 0); + hash_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, NBL_HASH_VALUE, 0); - pktinfo_id = rndis_get_ppi(rndis_pkt, RNDIS_PKTINFO_ID, 1); + pktinfo_id = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, RNDIS_PKTINFO_ID, 1); data = (void *)msg + data_offset; @@ -474,6 +525,14 @@ int rndis_filter_receive(struct net_device *ndev, if (netif_msg_rx_status(net_device_ctx)) dump_rndis_message(ndev, rndis_msg); + /* Validate incoming rndis_message packet */ + if (buflen < RNDIS_HEADER_SIZE || rndis_msg->msg_len < RNDIS_HEADER_SIZE || + buflen < rndis_msg->msg_len) { + netdev_err(ndev, "Invalid rndis_msg (buflen: %u, msg_len: %u)\n", + buflen, rndis_msg->msg_len); + return NVSP_STAT_FAIL; + } + switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: return rndis_filter_receive_data(ndev, net_dev, nvchan, diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index c11f32f644db..7db9cbd0f5de 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -882,7 +882,9 @@ static int adf7242_rx(struct adf7242_local *lp) int ret; u8 lqi, len_u8, *data; - adf7242_read_reg(lp, 0, &len_u8); + ret = adf7242_read_reg(lp, 0, &len_u8); + if (ret) + return ret; len = len_u8; diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e04c3b60cae7..4eb64709d44c 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2925,6 +2925,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv) ); if (!priv->irq_workqueue) { dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n"); + destroy_workqueue(priv->mlme_workqueue); return -ENOMEM; } diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2098ca2f2c90..b3790aa952a1 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -521,7 +521,7 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint) val = ioread32(endpoint->ipa->reg_virt + offset); /* Zero all filter-related fields, preserving the rest */ - u32_replace_bits(val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL); + u32p_replace_bits(&val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL); iowrite32(val, endpoint->ipa->reg_virt + offset); } @@ -573,7 +573,7 @@ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id) val = ioread32(ipa->reg_virt + offset); /* Zero all route-related fields, preserving the rest */ - u32_replace_bits(val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL); + u32p_replace_bits(&val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL); iowrite32(val, ipa->reg_virt + offset); } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 735a806045ac..8947d58f2a25 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -996,7 +996,7 @@ void phy_stop(struct phy_device *phydev) { struct net_device *dev = phydev->attached_dev; - if (!phy_is_started(phydev)) { + if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); return; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8adfbad0a1e8..5dab6be6fc38 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1143,10 +1143,6 @@ int phy_init_hw(struct phy_device *phydev) if (ret < 0) return ret; - ret = phy_disable_interrupts(phydev); - if (ret) - return ret; - if (phydev->drv->config_init) ret = phydev->drv->config_init(phydev); @@ -1423,6 +1419,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (err) goto error; + err = phy_disable_interrupts(phydev); + if (err) + return err; + phy_resume(phydev); phy_led_triggers_register(phydev); @@ -1682,7 +1682,8 @@ void phy_detach(struct phy_device *phydev) phy_led_triggers_unregister(phydev); - module_put(phydev->mdio.dev.driver->owner); + if (phydev->mdio.dev.driver) + module_put(phydev->mdio.dev.driver->owner); /* If the device had no specific driver before (i.e. - it * was using the generic driver), we unbind the device diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index bd9c07888ebb..6fa7a009a24a 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -201,7 +201,7 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) dev_dbg(&info->control->dev, "rndis response error, code %d\n", retval); } - msleep(20); + msleep(40); } dev_dbg(&info->control->dev, "rndis response timeout\n"); return -ETIMEDOUT; diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 444130655d8e..cb5898f7d68c 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -118,6 +118,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type, skb_put(skb, sizeof(struct cisco_packet)); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); dev_queue_xmit(skb); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 9acad651ea1f..d6cfd51613ed 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -433,6 +433,8 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (pvc->state.fecn) /* TX Congestion counter */ dev->stats.tx_compressed++; skb->dev = pvc->frad; + skb->protocol = htons(ETH_P_HDLC); + skb_reset_network_header(skb); dev_queue_xmit(skb); return NETDEV_TX_OK; } @@ -555,6 +557,7 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) skb_put(skb, i); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); dev_queue_xmit(skb); @@ -1041,7 +1044,7 @@ static void pvc_setup(struct net_device *dev) { dev->type = ARPHRD_DLCI; dev->flags = IFF_POINTOPOINT; - dev->hard_header_len = 10; + dev->hard_header_len = 0; dev->addr_len = 2; netif_keep_dst(dev); } @@ -1093,6 +1096,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) dev->mtu = HDLC_MAX_MTU; dev->min_mtu = 68; dev->max_mtu = HDLC_MAX_MTU; + dev->needed_headroom = 10; dev->priv_flags |= IFF_NO_QUEUE; dev->ml_priv = pvc; diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 48ced3912576..64f855651336 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -251,6 +251,7 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code, skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); skb_queue_tail(&tx_queue, skb); } @@ -383,11 +384,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, } for (opt = data; len; len -= opt[1], opt += opt[1]) { - if (len < 2 || len < opt[1]) { - dev->stats.rx_errors++; - kfree(out); - return; /* bad packet, drop silently */ - } + if (len < 2 || opt[1] < 2 || len < opt[1]) + goto err_out; if (pid == PID_LCP) switch (opt[0]) { @@ -395,6 +393,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, continue; /* MRU always OK and > 1500 bytes? */ case LCP_OPTION_ACCM: /* async control character map */ + if (opt[1] < sizeof(valid_accm)) + goto err_out; if (!memcmp(opt, valid_accm, sizeof(valid_accm))) continue; @@ -406,6 +406,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, } break; case LCP_OPTION_MAGIC: + if (len < 6) + goto err_out; if (opt[1] != 6 || (!opt[2] && !opt[3] && !opt[4] && !opt[5])) break; /* reject invalid magic number */ @@ -424,6 +426,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data); kfree(out); + return; + +err_out: + dev->stats.rx_errors++; + kfree(out); } static int ppp_rx(struct sk_buff *skb) diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 732a6c1851f5..b6be2454b8bd 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -198,8 +198,6 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) struct net_device *dev; int size = skb->len; - skb->protocol = htons(ETH_P_X25); - ptr = skb_push(skb, 2); *ptr++ = size % 256; @@ -210,6 +208,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) skb->dev = dev = lapbeth->ethdev; + skb->protocol = htons(ETH_P_DEC); + skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c index 3dd3b76790d0..c0cfd9b36c0b 100644 --- a/drivers/net/wireguard/noise.c +++ b/drivers/net/wireguard/noise.c @@ -87,15 +87,12 @@ static void handshake_zero(struct noise_handshake *handshake) void wg_noise_handshake_clear(struct noise_handshake *handshake) { + down_write(&handshake->lock); wg_index_hashtable_remove( handshake->entry.peer->device->index_hashtable, &handshake->entry); - down_write(&handshake->lock); handshake_zero(handshake); up_write(&handshake->lock); - wg_index_hashtable_remove( - handshake->entry.peer->device->index_hashtable, - &handshake->entry); } static struct noise_keypair *keypair_create(struct wg_peer *peer) diff --git a/drivers/net/wireguard/peerlookup.c b/drivers/net/wireguard/peerlookup.c index e4deb331476b..f2783aa7a88f 100644 --- a/drivers/net/wireguard/peerlookup.c +++ b/drivers/net/wireguard/peerlookup.c @@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct index_hashtable *table, struct index_hashtable_entry *old, struct index_hashtable_entry *new) { - if (unlikely(hlist_unhashed(&old->index_hash))) - return false; + bool ret; + spin_lock_bh(&table->lock); + ret = !hlist_unhashed(&old->index_hash); + if (unlikely(!ret)) + goto out; + new->index = old->index; hlist_replace_rcu(&old->index_hash, &new->index_hash); @@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct index_hashtable *table, * simply gets dropped, which isn't terrible. */ INIT_HLIST_NODE(&old->index_hash); +out: spin_unlock_bh(&table->lock); - return true; + return ret; } void wg_index_hashtable_remove(struct index_hashtable *table, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index e8712ad3ac45..3c07d1bbe1c6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -664,9 +664,15 @@ static void pkt_align(struct sk_buff *p, int len, int align) /* To check if there's window offered */ static bool data_ok(struct brcmf_sdio *bus) { - /* Reserve TXCTL_CREDITS credits for txctl */ - return (bus->tx_max - bus->tx_seq) > TXCTL_CREDITS && - ((bus->tx_max - bus->tx_seq) & 0x80) == 0; + u8 tx_rsv = 0; + + /* Reserve TXCTL_CREDITS credits for txctl when it is ready to send */ + if (bus->ctrl_frame_stat) + tx_rsv = TXCTL_CREDITS; + + return (bus->tx_max - bus->tx_seq - tx_rsv) != 0 && + ((bus->tx_max - bus->tx_seq - tx_rsv) & 0x80) == 0; + } /* To check if there's window offered */ diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 8047e307892e..d9f8bdbc817b 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -954,7 +954,7 @@ struct mwifiex_tkip_param { struct mwifiex_aes_param { u8 pn[WPA_PN_SIZE]; __le16 key_len; - u8 key[WLAN_KEY_LEN_CCMP]; + u8 key[WLAN_KEY_LEN_CCMP_256]; } __packed; struct mwifiex_wapi_param { diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 962d8bfe6f10..119ccacd1fcc 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -619,7 +619,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, key_v2 = &resp->params.key_material_v2; len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len); - if (len > WLAN_KEY_LEN_CCMP) + if (len > sizeof(key_v2->key_param_set.key_params.aes.key)) return -EINVAL; if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) { @@ -635,7 +635,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, return 0; memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0, - WLAN_KEY_LEN_CCMP); + sizeof(key_v2->key_param_set.key_params.aes.key)); priv->aes_key_v2.key_param_set.key_params.aes.key_len = cpu_to_le16(len); memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index d0cbb283982f..bd316dbd9041 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -2128,7 +2128,8 @@ static int mt7615_load_n9(struct mt7615_dev *dev, const char *name) sizeof(dev->mt76.hw->wiphy->fw_version), "%.10s-%.15s", hdr->fw_ver, hdr->build_date); - if (!strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) { + if (!is_mt7615(&dev->mt76) && + !strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) { dev->fw_ver = MT7615_FIRMWARE_V2; dev->mcu_ops = &sta_update_ops; } else { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index e90d0087e377..8d6ceb3b67b4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -699,8 +699,12 @@ void mt7915_unregister_device(struct mt7915_dev *dev) spin_lock_bh(&dev->token_lock); idr_for_each_entry(&dev->token, txwi, id) { mt7915_txp_skb_unmap(&dev->mt76, txwi); - if (txwi->skb) - dev_kfree_skb_any(txwi->skb); + if (txwi->skb) { + struct ieee80211_hw *hw; + + hw = mt76_tx_status_get_hw(&dev->mt76, txwi->skb); + ieee80211_free_txskb(hw, txwi->skb); + } mt76_put_txwi(&dev->mt76, txwi); } spin_unlock_bh(&dev->token_lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 6825afca1efb..036207f828f3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -841,7 +841,7 @@ mt7915_tx_complete_status(struct mt76_dev *mdev, struct sk_buff *skb, if (sta || !(info->flags & IEEE80211_TX_CTL_NO_ACK)) mt7915_tx_status(sta, hw, info, NULL); - dev_kfree_skb(skb); + ieee80211_free_txskb(hw, skb); } void mt7915_txp_skb_unmap(struct mt76_dev *dev, diff --git a/drivers/net/wireless/ti/wlcore/cmd.h b/drivers/net/wireless/ti/wlcore/cmd.h index 9acd8a41ea61..f2609d5b6bf7 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.h +++ b/drivers/net/wireless/ti/wlcore/cmd.h @@ -458,7 +458,6 @@ enum wl1271_cmd_key_type { KEY_TKIP = 2, KEY_AES = 3, KEY_GEM = 4, - KEY_IGTK = 5, }; struct wl1271_cmd_set_keys { diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 821ad1acd505..d2bbd5108f7e 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -3559,9 +3559,6 @@ int wlcore_set_key(struct wl1271 *wl, enum set_key_cmd cmd, case WL1271_CIPHER_SUITE_GEM: key_type = KEY_GEM; break; - case WLAN_CIPHER_SUITE_AES_CMAC: - key_type = KEY_IGTK; - break; default: wl1271_error("Unknown key algo 0x%x", key_conf->cipher); @@ -6231,7 +6228,6 @@ static int wl1271_init_ieee80211(struct wl1271 *wl) WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, WL1271_CIPHER_SUITE_GEM, - WLAN_CIPHER_SUITE_AES_CMAC, }; /* The tx descriptor buffer */ diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 3ed9786b88d8..a44d49d63968 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -73,6 +73,7 @@ config NVME_TCP depends on INET depends on BLK_DEV_NVME select NVME_FABRICS + select CRYPTO select CRYPTO_CRC32C help This provides support for the NVMe over Fabrics protocol using diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f3a61a24d45f..8f9d61e0729f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3041,7 +3041,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, if (!cel) return -ENOMEM; - ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi, + ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, &cel->log, sizeof(cel->log), 0); if (ret) { kfree(cel); @@ -3236,8 +3236,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret < 0) return ret; - if (!ctrl->identified) - nvme_hwmon_init(ctrl); + if (!ctrl->identified) { + ret = nvme_hwmon_init(ctrl); + if (ret < 0) + return ret; + } ctrl->identified = true; @@ -3261,10 +3264,24 @@ static int nvme_dev_open(struct inode *inode, struct file *file) return -EWOULDBLOCK; } + nvme_get_ctrl(ctrl); + if (!try_module_get(ctrl->ops->module)) + return -EINVAL; + file->private_data = ctrl; return 0; } +static int nvme_dev_release(struct inode *inode, struct file *file) +{ + struct nvme_ctrl *ctrl = + container_of(inode->i_cdev, struct nvme_ctrl, cdev); + + module_put(ctrl->ops->module); + nvme_put_ctrl(ctrl); + return 0; +} + static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) { struct nvme_ns *ns; @@ -3327,6 +3344,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, static const struct file_operations nvme_dev_fops = { .owner = THIS_MODULE, .open = nvme_dev_open, + .release = nvme_dev_release, .unlocked_ioctl = nvme_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e8ef42b9d50c..e2e09e25c056 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3671,12 +3671,14 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts) spin_lock_irqsave(&nvme_fc_lock, flags); list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { if (lport->localport.node_name != laddr.nn || - lport->localport.port_name != laddr.pn) + lport->localport.port_name != laddr.pn || + lport->localport.port_state != FC_OBJSTATE_ONLINE) continue; list_for_each_entry(rport, &lport->endp_list, endp_list) { if (rport->remoteport.node_name != raddr.nn || - rport->remoteport.port_name != raddr.pn) + rport->remoteport.port_name != raddr.pn || + rport->remoteport.port_state != FC_OBJSTATE_ONLINE) continue; /* if fail to get reference fall through. Will error */ diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 412a6c97c0d8..552dbc04567b 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -59,12 +59,8 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { - int ret; - - ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, + return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, NVME_CSI_NVM, &data->log, sizeof(data->log), 0); - - return ret <= 0 ? ret : -EIO; } static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, @@ -225,7 +221,7 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = { .info = nvme_hwmon_info, }; -void nvme_hwmon_init(struct nvme_ctrl *ctrl) +int nvme_hwmon_init(struct nvme_ctrl *ctrl) { struct device *dev = ctrl->dev; struct nvme_hwmon_data *data; @@ -234,7 +230,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) - return; + return 0; data->ctrl = ctrl; mutex_init(&data->read_lock); @@ -244,7 +240,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) dev_warn(ctrl->device, "Failed to read smart log (error %d)\n", err); devm_kfree(dev, data); - return; + return err; } hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, @@ -254,4 +250,6 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) dev_warn(dev, "Failed to instantiate hwmon device\n"); devm_kfree(dev, data); } + + return 0; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9fd45ff656da..2aaedfa43ed8 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -827,9 +827,12 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) } #ifdef CONFIG_NVME_HWMON -void nvme_hwmon_init(struct nvme_ctrl *ctrl); +int nvme_hwmon_init(struct nvme_ctrl *ctrl); #else -static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { } +static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) +{ + return 0; +} #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 899d2f4d7ab6..8984796db0c8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -940,13 +940,6 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) struct nvme_completion *cqe = &nvmeq->cqes[idx]; struct request *req; - if (unlikely(cqe->command_id >= nvmeq->q_depth)) { - dev_warn(nvmeq->dev->ctrl.device, - "invalid id %d completed on queue %d\n", - cqe->command_id, le16_to_cpu(cqe->sq_id)); - return; - } - /* * AEN requests are special as they don't time out and can * survive any kind of queue freeze and often don't respond to @@ -960,6 +953,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) } req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id); + if (unlikely(!req)) { + dev_warn(nvmeq->dev->ctrl.device, + "invalid id %d completed on queue %d\n", + cqe->command_id, le16_to_cpu(cqe->sq_id)); + return; + } + trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail); if (!nvme_try_complete_req(req, cqe->status, cqe->result)) nvme_pci_complete_rq(req); @@ -3153,7 +3153,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_MEDIUM_PRIO_SQ | - NVME_QUIRK_NO_TEMP_THRESH_CHANGE }, + NVME_QUIRK_NO_TEMP_THRESH_CHANGE | + NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a6), /* Intel 760p/Pro 7600p */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 8bd7f656e240..dacfa7435d0b 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -517,6 +517,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys) subsys->ver = NVME_VS(1, 2, 1); } + __module_get(subsys->passthru_ctrl->ops->module); mutex_unlock(&subsys->lock); return 0; @@ -531,6 +532,7 @@ static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys) { if (subsys->passthru_ctrl) { xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid); + module_put(subsys->passthru_ctrl->ops->module); nvme_put_ctrl(subsys->passthru_ctrl); } subsys->passthru_ctrl = NULL; diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 25c764905f9b..983d75bd5bd1 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1039,6 +1039,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), + X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &rapl_defaults_byt), X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &rapl_defaults_cht), diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 1bacb37e8a99..cd1224182ad7 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -42,8 +42,9 @@ #define AXP20X_DCDC2_V_OUT_MASK GENMASK(5, 0) #define AXP20X_DCDC3_V_OUT_MASK GENMASK(7, 0) -#define AXP20X_LDO24_V_OUT_MASK GENMASK(7, 4) +#define AXP20X_LDO2_V_OUT_MASK GENMASK(7, 4) #define AXP20X_LDO3_V_OUT_MASK GENMASK(6, 0) +#define AXP20X_LDO4_V_OUT_MASK GENMASK(3, 0) #define AXP20X_LDO5_V_OUT_MASK GENMASK(7, 4) #define AXP20X_PWR_OUT_EXTEN_MASK BIT_MASK(0) @@ -542,14 +543,14 @@ static const struct regulator_desc axp20x_regulators[] = { AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_DCDC3_MASK), AXP_DESC_FIXED(AXP20X, LDO1, "ldo1", "acin", 1300), AXP_DESC(AXP20X, LDO2, "ldo2", "ldo24in", 1800, 3300, 100, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO2_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO2_MASK), AXP_DESC(AXP20X, LDO3, "ldo3", "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, AXP20X_LDO3_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO3_MASK), AXP_DESC_RANGES(AXP20X, LDO4, "ldo4", "ldo24in", axp20x_ldo4_ranges, AXP20X_LDO4_V_OUT_NUM_VOLTAGES, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO4_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO4_MASK), AXP_DESC_IO(AXP20X, LDO5, "ldo5", "ldo5in", 1800, 3300, 100, AXP20X_LDO5_V_OUT, AXP20X_LDO5_V_OUT_MASK, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index cbb770824226..1a44e321b54e 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -40,6 +40,7 @@ MODULE_LICENSE("GPL"); static struct dasd_discipline dasd_fba_discipline; +static void *dasd_fba_zero_page; struct dasd_fba_private { struct dasd_fba_characteristics rdc_data; @@ -270,7 +271,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count) ccw->cmd_code = DASD_FBA_CCW_WRITE; ccw->flags |= CCW_FLAG_SLI; ccw->count = count; - ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0)); + ccw->cda = (__u32) (addr_t) dasd_fba_zero_page; } /* @@ -830,6 +831,11 @@ dasd_fba_init(void) int ret; ASCEBC(dasd_fba_discipline.ebcname, 4); + + dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!dasd_fba_zero_page) + return -ENOMEM; + ret = ccw_driver_register(&dasd_fba_driver); if (!ret) wait_for_device_probe(); @@ -841,6 +847,7 @@ static void __exit dasd_fba_cleanup(void) { ccw_driver_unregister(&dasd_fba_driver); + free_page((unsigned long)dasd_fba_zero_page); } module_init(dasd_fba_init); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 4dbbfd88262c..f314936b5462 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1449,7 +1449,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); - if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) + if (copy_to_user((int __user *) arg, reqcnt, + sizeof(u32) * AP_DEVICES)) rc = -EFAULT; kfree(reqcnt); return rc; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 3f5b61351cde..c793dcabd551 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1692,9 +1692,9 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, *nr_apqns = 0; /* fetch status of all crypto cards */ - device_status = kmalloc_array(MAX_ZDEV_ENTRIES_EXT, - sizeof(struct zcrypt_device_status_ext), - GFP_KERNEL); + device_status = kvmalloc_array(MAX_ZDEV_ENTRIES_EXT, + sizeof(struct zcrypt_device_status_ext), + GFP_KERNEL); if (!device_status) return -ENOMEM; zcrypt_device_status_mask_ext(device_status); @@ -1762,7 +1762,7 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, verify = 0; } - kfree(device_status); + kvfree(device_status); return rc; } EXPORT_SYMBOL(cca_findcard2); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 3a94f6cad167..6384f7adba66 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -284,11 +284,11 @@ static void qeth_l2_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_clear_ipacmd_list(card); - qeth_drain_output_queues(card); card->state = CARD_STATE_DOWN; } qeth_qdio_clear_card(card, 0); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); flush_workqueue(card->event_wq); qeth_flush_local_addrs(card); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 4d461960370d..09ef518ca1ea 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1168,11 +1168,11 @@ static void qeth_l3_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_l3_clear_ip_htable(card, 1); qeth_clear_ipacmd_list(card); - qeth_drain_output_queues(card); card->state = CARD_STATE_DOWN; } qeth_qdio_clear_card(card, 0); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); flush_workqueue(card->event_wq); qeth_flush_local_addrs(card); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index d32c7e7ab09d..bb02fd8bc2dd 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -71,6 +71,7 @@ static void lpfc_disc_timeout_handler(struct lpfc_vport *); static void lpfc_disc_flush_list(struct lpfc_vport *vport); static void lpfc_unregister_fcfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *); static int lpfc_fcf_inuse(struct lpfc_hba *); +static void lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_terminate_rport_io(struct fc_rport *rport) @@ -1138,11 +1139,13 @@ out: return; } - void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) { struct lpfc_vport *vport = pmb->vport; + LPFC_MBOXQ_t *sparam_mb; + struct lpfc_dmabuf *sparam_mp; + int rc; if (pmb->u.mb.mbxStatus) goto out; @@ -1167,12 +1170,42 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } /* Start discovery by sending a FLOGI. port_state is identically - * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending - * the FLOGI is being deferred till after MBX_READ_SPARAM completes. + * LPFC_FLOGI while waiting for FLOGI cmpl. */ if (vport->port_state != LPFC_FLOGI) { - if (!(phba->hba_flag & HBA_DEFER_FLOGI)) + /* Issue MBX_READ_SPARAM to update CSPs before FLOGI if + * bb-credit recovery is in place. + */ + if (phba->bbcredit_support && phba->cfg_enable_bbcr && + !(phba->link_flag & LS_LOOPBACK_MODE)) { + sparam_mb = mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!sparam_mb) + goto sparam_out; + + rc = lpfc_read_sparam(phba, sparam_mb, 0); + if (rc) { + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + sparam_mb->vport = vport; + sparam_mb->mbox_cmpl = lpfc_mbx_cmpl_read_sparam; + rc = lpfc_sli_issue_mbox(phba, sparam_mb, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + sparam_mp = (struct lpfc_dmabuf *) + sparam_mb->ctx_buf; + lpfc_mbuf_free(phba, sparam_mp->virt, + sparam_mp->phys); + kfree(sparam_mp); + sparam_mb->ctx_buf = NULL; + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + + phba->hba_flag |= HBA_DEFER_FLOGI; + } else { lpfc_initial_flogi(vport); + } } else { if (vport->fc_flag & FC_PT2PT) lpfc_disc_start(vport); @@ -1184,6 +1217,7 @@ out: "0306 CONFIG_LINK mbxStatus error x%x " "HBA state x%x\n", pmb->u.mb.mbxStatus, vport->port_state); +sparam_out: mempool_free(pmb, phba->mbox_mem_pool); lpfc_linkdown(phba); @@ -3239,21 +3273,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) lpfc_linkup(phba); sparam_mbox = NULL; - if (!(phba->hba_flag & HBA_FCOE_MODE)) { - cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!cfglink_mbox) - goto out; - vport->port_state = LPFC_LOCAL_CFG_LINK; - lpfc_config_link(phba, cfglink_mbox); - cfglink_mbox->vport = vport; - cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; - rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(cfglink_mbox, phba->mbox_mem_pool); - goto out; - } - } - sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!sparam_mbox) goto out; @@ -3274,7 +3293,20 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) goto out; } - if (phba->hba_flag & HBA_FCOE_MODE) { + if (!(phba->hba_flag & HBA_FCOE_MODE)) { + cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!cfglink_mbox) + goto out; + vport->port_state = LPFC_LOCAL_CFG_LINK; + lpfc_config_link(phba, cfglink_mbox); + cfglink_mbox->vport = vport; + cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; + rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + mempool_free(cfglink_mbox, phba->mbox_mem_pool); + goto out; + } + } else { vport->port_state = LPFC_VPORT_UNKNOWN; /* * Add the driver's default FCF record at FCF index 0 now. This @@ -3331,10 +3363,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) } /* Reset FCF roundrobin bmask for new discovery */ lpfc_sli4_clear_fcf_rr_bmask(phba); - } else { - if (phba->bbcredit_support && phba->cfg_enable_bbcr && - !(phba->link_flag & LS_LOOPBACK_MODE)) - phba->hba_flag |= HBA_DEFER_FLOGI; } /* Prepare for LINK up registrations */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 95018e650f2d..16503e22691e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2964,26 +2964,32 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (sdkp->device->type == TYPE_ZBC) { /* Host-managed */ - q->limits.zoned = BLK_ZONED_HM; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM); } else { sdkp->zoned = (buffer[8] >> 4) & 3; - if (sdkp->zoned == 1 && !disk_has_partitions(sdkp->disk)) { + if (sdkp->zoned == 1) { /* Host-aware */ - q->limits.zoned = BLK_ZONED_HA; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA); } else { - /* - * Treat drive-managed devices and host-aware devices - * with partitions as regular block devices. - */ - q->limits.zoned = BLK_ZONED_NONE; - if (sdkp->zoned == 2 && sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "Drive-managed SMR disk\n"); + /* Regular disk or drive managed disk */ + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE); } } - if (blk_queue_is_zoned(q) && sdkp->first_scan) + + if (!sdkp->first_scan) + goto out; + + if (blk_queue_is_zoned(q)) { sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware"); + } else { + if (sdkp->zoned == 1) + sd_printk(KERN_NOTICE, sdkp, + "Host-aware SMR disk used as regular disk\n"); + else if (sdkp->zoned == 2) + sd_printk(KERN_NOTICE, sdkp, + "Drive-managed SMR disk\n"); + } out: kfree(buffer); @@ -3404,10 +3410,6 @@ static int sd_probe(struct device *dev) sdkp->first_scan = 1; sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS; - error = sd_zbc_init_disk(sdkp); - if (error) - goto out_free_index; - sd_revalidate_disk(gd); gd->flags = GENHD_FL_EXT_DEVT; diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 4933e7daf17d..a3aad608bc38 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -215,7 +215,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) #ifdef CONFIG_BLK_DEV_ZONED -int sd_zbc_init_disk(struct scsi_disk *sdkp); void sd_zbc_release_disk(struct scsi_disk *sdkp); int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); @@ -231,11 +230,6 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, #else /* CONFIG_BLK_DEV_ZONED */ -static inline int sd_zbc_init_disk(struct scsi_disk *sdkp) -{ - return 0; -} - static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {} static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, @@ -259,7 +253,7 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { - return 0; + return good_bytes; } static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 0e94ff056bff..cf07b7f93579 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -651,6 +651,28 @@ static void sd_zbc_print_zones(struct scsi_disk *sdkp) sdkp->zone_blocks); } +static int sd_zbc_init_disk(struct scsi_disk *sdkp) +{ + sdkp->zones_wp_offset = NULL; + spin_lock_init(&sdkp->zones_wp_offset_lock); + sdkp->rev_wp_offset = NULL; + mutex_init(&sdkp->rev_mutex); + INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn); + sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL); + if (!sdkp->zone_wp_update_buf) + return -ENOMEM; + + return 0; +} + +void sd_zbc_release_disk(struct scsi_disk *sdkp) +{ + kvfree(sdkp->zones_wp_offset); + sdkp->zones_wp_offset = NULL; + kfree(sdkp->zone_wp_update_buf); + sdkp->zone_wp_update_buf = NULL; +} + static void sd_zbc_revalidate_zones_cb(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); @@ -667,7 +689,24 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) u32 max_append; int ret = 0; - if (!sd_is_zoned(sdkp)) + /* + * For all zoned disks, initialize zone append emulation data if not + * already done. This is necessary also for host-aware disks used as + * regular disks due to the presence of partitions as these partitions + * may be deleted and the disk zoned model changed back from + * BLK_ZONED_NONE to BLK_ZONED_HA. + */ + if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) { + ret = sd_zbc_init_disk(sdkp); + if (ret) + return ret; + } + + /* + * There is nothing to do for regular disks, including host-aware disks + * that have partitions. + */ + if (!blk_queue_is_zoned(q)) return 0; /* @@ -764,28 +803,3 @@ err: return ret; } - -int sd_zbc_init_disk(struct scsi_disk *sdkp) -{ - if (!sd_is_zoned(sdkp)) - return 0; - - sdkp->zones_wp_offset = NULL; - spin_lock_init(&sdkp->zones_wp_offset_lock); - sdkp->rev_wp_offset = NULL; - mutex_init(&sdkp->rev_mutex); - INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn); - sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL); - if (!sdkp->zone_wp_update_buf) - return -ENOMEM; - - return 0; -} - -void sd_zbc_release_disk(struct scsi_disk *sdkp) -{ - kvfree(sdkp->zones_wp_offset); - sdkp->zones_wp_offset = NULL; - kfree(sdkp->zone_wp_update_buf); - sdkp->zone_wp_update_buf = NULL; -} diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 681d09085175..9cfa15ec8b08 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1295,7 +1295,7 @@ static const struct of_device_id bcm_qspi_of_match[] = { }, { .compatible = "brcm,spi-bcm-qspi", - .data = &bcm_qspi_rev_data, + .data = &bcm_qspi_no_rev_data, }, { .compatible = "brcm,spi-bcm7216-qspi", diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index c45d76c848c8..41986ac0fbfb 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -75,7 +75,7 @@ #define DRV_NAME "spi-bcm2835" /* define polling limits */ -unsigned int polling_limit_us = 30; +static unsigned int polling_limit_us = 30; module_param(polling_limit_us, uint, 0664); MODULE_PARM_DESC(polling_limit_us, "time in us to run a transfer in polling mode\n"); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 91c6affe139c..127323a4b27c 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -174,17 +174,17 @@ static const struct fsl_dspi_devtype_data devtype_data[] = { .fifo_size = 16, }, [LS2080A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, [LS2085A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, [LX2160A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, @@ -1273,11 +1273,14 @@ static int dspi_probe(struct platform_device *pdev) void __iomem *base; bool big_endian; - ctlr = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi)); + dspi = devm_kzalloc(&pdev->dev, sizeof(*dspi), GFP_KERNEL); + if (!dspi) + return -ENOMEM; + + ctlr = spi_alloc_master(&pdev->dev, 0); if (!ctlr) return -ENOMEM; - dspi = spi_controller_get_devdata(ctlr); dspi->pdev = pdev; dspi->ctlr = ctlr; @@ -1414,7 +1417,7 @@ poll_mode: if (dspi->devtype_data->trans_mode != DSPI_DMA_MODE) ctlr->ptp_sts_supported = true; - platform_set_drvdata(pdev, ctlr); + platform_set_drvdata(pdev, dspi); ret = spi_register_controller(ctlr); if (ret != 0) { @@ -1437,8 +1440,7 @@ out_ctlr_put: static int dspi_remove(struct platform_device *pdev) { - struct spi_controller *ctlr = platform_get_drvdata(pdev); - struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); + struct fsl_dspi *dspi = platform_get_drvdata(pdev); /* Disconnect from the SPI framework */ spi_unregister_controller(dspi->ctlr); diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c index e60581283a24..6d148ab70b93 100644 --- a/drivers/spi/spi-fsl-espi.c +++ b/drivers/spi/spi-fsl-espi.c @@ -564,13 +564,14 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events) static irqreturn_t fsl_espi_irq(s32 irq, void *context_data) { struct fsl_espi *espi = context_data; - u32 events; + u32 events, mask; spin_lock(&espi->lock); /* Get interrupt events(tx/rx) */ events = fsl_espi_read_reg(espi, ESPI_SPIE); - if (!events) { + mask = fsl_espi_read_reg(espi, ESPI_SPIM); + if (!(events & mask)) { spin_unlock(&espi->lock); return IRQ_NONE; } diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index 3ebca44ab3fa..0c8471be3e32 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -7,6 +7,7 @@ */ #include <linux/crc32.h> +#include <linux/delay.h> #include <linux/property.h> #include <linux/slab.h> #include "tb.h" @@ -389,8 +390,8 @@ static int tb_drom_parse_entries(struct tb_switch *sw) struct tb_drom_entry_header *entry = (void *) (sw->drom + pos); if (pos + 1 == drom_size || pos + entry->len > drom_size || !entry->len) { - tb_sw_warn(sw, "drom buffer overrun, aborting\n"); - return -EIO; + tb_sw_warn(sw, "DROM buffer overrun\n"); + return -EILSEQ; } switch (entry->type) { @@ -526,7 +527,8 @@ int tb_drom_read(struct tb_switch *sw) u16 size; u32 crc; struct tb_drom_header *header; - int res; + int res, retries = 1; + if (sw->drom) return 0; @@ -612,7 +614,17 @@ parse: tb_sw_warn(sw, "drom device_rom_revision %#x unknown\n", header->device_rom_revision); - return tb_drom_parse_entries(sw); + res = tb_drom_parse_entries(sw); + /* If the DROM parsing fails, wait a moment and retry once */ + if (res == -EILSEQ && retries--) { + tb_sw_warn(sw, "parsing DROM failed, retrying\n"); + msleep(100); + res = tb_drom_read_n(sw, 0, sw->drom, size); + if (!res) + goto parse; + } + + return res; err: kfree(sw->drom); sw->drom = NULL; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 3eb2d485eaeb..55bb7b897d97 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -5566,6 +5566,17 @@ static const struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, + /* + * Realtek RealManage + */ + { PCI_VENDOR_ID_REALTEK, 0x816a, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_b0_1_115200 }, + + { PCI_VENDOR_ID_REALTEK, 0x816b, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_b0_1_115200 }, + /* Fintek PCI serial cards */ { PCI_DEVICE(0x1c29, 0x1104), .driver_data = pbn_fintek_4 }, { PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 }, diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index f797c971cd82..124524ecfe26 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1916,24 +1916,12 @@ static inline bool uart_console_enabled(struct uart_port *port) return uart_console(port) && (port->cons->flags & CON_ENABLED); } -static void __uart_port_spin_lock_init(struct uart_port *port) +static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); lockdep_set_class(&port->lock, &port_lock_key); } -/* - * Ensure that the serial console lock is initialised early. - * If this port is a console, then the spinlock is already initialised. - */ -static inline void uart_port_spin_lock_init(struct uart_port *port) -{ - if (uart_console(port)) - return; - - __uart_port_spin_lock_init(port); -} - #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL) /** * uart_console_write - write a console message to a serial port @@ -2086,7 +2074,15 @@ uart_set_options(struct uart_port *port, struct console *co, struct ktermios termios; static struct ktermios dummy; - uart_port_spin_lock_init(port); + /* + * Ensure that the serial-console lock is initialised early. + * + * Note that the console-enabled check is needed because of kgdboc, + * which can end up calling uart_set_options() for an already enabled + * console via tty_find_polling_driver() and uart_poll_init(). + */ + if (!uart_console_enabled(port) && !port->console_reinit) + uart_port_spin_lock_init(port); memset(&termios, 0, sizeof(struct ktermios)); @@ -2379,13 +2375,6 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_change_pm(state, UART_PM_STATE_ON); /* - * If this driver supports console, and it hasn't been - * successfully registered yet, initialise spin lock for it. - */ - if (port->cons && !(port->cons->flags & CON_ENABLED)) - __uart_port_spin_lock_init(port); - - /* * Ensure that the modem control lines are de-activated. * keep the DTR setting that is set in uart_set_options() * We probably don't need a spinlock around this, but @@ -2801,10 +2790,12 @@ static ssize_t console_store(struct device *dev, if (oldconsole && !newconsole) { ret = unregister_console(uport->cons); } else if (!oldconsole && newconsole) { - if (uart_console(uport)) + if (uart_console(uport)) { + uport->console_reinit = 1; register_console(uport->cons); - else + } else { ret = -ENOENT; + } } } else { ret = -ENXIO; @@ -2900,7 +2891,12 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) goto out; } - uart_port_spin_lock_init(uport); + /* + * If this port is in use as a console then the spinlock is already + * initialised. + */ + if (!uart_console_enabled(uport)) + uart_port_spin_lock_init(uport); if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 084c48c5848f..67cbd42421be 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -827,6 +827,11 @@ static ssize_t usblp_read(struct file *file, char __user *buffer, size_t len, lo if (rv < 0) return rv; + if (!usblp->present) { + count = -ENODEV; + goto done; + } + if ((avail = usblp->rstatus) < 0) { printk(KERN_ERR "usblp%d: error %d reading from printer\n", usblp->minor, (int)avail); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f232914de5fd..10574fa3f927 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -397,6 +397,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Generic RTL8153 based ethernet adapters */ { USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM }, + /* SONiX USB DEVICE Touchpad */ + { USB_DEVICE(0x0c45, 0x7056), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 6257be4110ca..3575b7201881 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -22,6 +22,7 @@ #include <linux/interrupt.h> #include <linux/usb.h> #include <linux/usb/hcd.h> +#include <linux/usb/otg.h> #include <linux/moduleparam.h> #include <linux/dma-mapping.h> #include <linux/debugfs.h> diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index ce0eaf7d7c12..087402aec5cb 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -14,7 +14,6 @@ */ /*-------------------------------------------------------------------------*/ -#include <linux/usb/otg.h> #define PORT_WAKE_BITS (PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E) diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 08f9296431e9..8183504e3abb 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -662,8 +662,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, if (devinfo->resetting) { cmnd->result = DID_ERROR << 16; cmnd->scsi_done(cmnd); - spin_unlock_irqrestore(&devinfo->lock, flags); - return 0; + goto zombie; } /* Find a free uas-tag */ @@ -699,6 +698,16 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, cmdinfo->state &= ~(SUBMIT_DATA_IN_URB | SUBMIT_DATA_OUT_URB); err = uas_submit_urbs(cmnd, devinfo); + /* + * in case of fatal errors the SCSI layer is peculiar + * a command that has finished is a success for the purpose + * of queueing, no matter how fatal the error + */ + if (err == -ENODEV) { + cmnd->result = DID_ERROR << 16; + cmnd->scsi_done(cmnd); + goto zombie; + } if (err) { /* If we did nothing, give up now */ if (cmdinfo->state & SUBMIT_STATUS_URB) { @@ -709,6 +718,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, } devinfo->cmnd[idx] = cmnd; +zombie: spin_unlock_irqrestore(&devinfo->lock, flags); return 0; } diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index ec7da0fa3cf8..676b525c2a66 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -125,13 +125,19 @@ static int hsl_orientation(struct pmc_usb_port *port) static int pmc_usb_command(struct pmc_usb_port *port, u8 *msg, u32 len) { u8 response[4]; + int ret; /* * Error bit will always be 0 with the USBC command. - * Status can be checked from the response message. + * Status can be checked from the response message if the + * function intel_scu_ipc_dev_command succeeds. */ - intel_scu_ipc_dev_command(port->pmc->ipc, PMC_USBC_CMD, 0, msg, len, - response, sizeof(response)); + ret = intel_scu_ipc_dev_command(port->pmc->ipc, PMC_USBC_CMD, 0, msg, + len, response, sizeof(response)); + + if (ret) + return ret; + if (response[2] & PMC_USB_RESP_STATUS_FAILURE) { if (response[2] & PMC_USB_RESP_STATUS_FATAL) return -EIO; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e680fcfdee60..758b988ac518 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -216,14 +216,18 @@ void ucsi_altmode_update_active(struct ucsi_connector *con) con->partner_altmode[i] == altmode); } -static u8 ucsi_altmode_next_mode(struct typec_altmode **alt, u16 svid) +static int ucsi_altmode_next_mode(struct typec_altmode **alt, u16 svid) { u8 mode = 1; int i; - for (i = 0; alt[i]; i++) + for (i = 0; alt[i]; i++) { + if (i > MODE_DISCOVERY_MAX) + return -ERANGE; + if (alt[i]->svid == svid) mode++; + } return mode; } @@ -258,8 +262,11 @@ static int ucsi_register_altmode(struct ucsi_connector *con, goto err; } - desc->mode = ucsi_altmode_next_mode(con->port_altmode, - desc->svid); + ret = ucsi_altmode_next_mode(con->port_altmode, desc->svid); + if (ret < 0) + return ret; + + desc->mode = ret; switch (desc->svid) { case USB_TYPEC_DP_SID: @@ -292,8 +299,11 @@ static int ucsi_register_altmode(struct ucsi_connector *con, goto err; } - desc->mode = ucsi_altmode_next_mode(con->partner_altmode, - desc->svid); + ret = ucsi_altmode_next_mode(con->partner_altmode, desc->svid); + if (ret < 0) + return ret; + + desc->mode = ret; alt = typec_partner_register_altmode(con->partner, desc); if (IS_ERR(alt)) { diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index c0aca2f0f23f..fbfe8f5933af 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -78,7 +78,7 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, if (ret) goto out_clear_bit; - if (!wait_for_completion_timeout(&ua->complete, msecs_to_jiffies(5000))) + if (!wait_for_completion_timeout(&ua->complete, 60 * HZ)) ret = -ETIMEDOUT; out_clear_bit: diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 0b49b0f44edf..41f3fa3db6d4 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2018,7 +2018,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, struct fb_var_screeninfo var = info->var; int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh; - if (ops->p && ops->p->userfont && FNTSIZE(vc->vc_font.data)) { + if (p->userfont && FNTSIZE(vc->vc_font.data)) { int size; int pitch = PITCH(vc->vc_font.width); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index abf86b202b43..9f72b092bc22 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -636,16 +636,15 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, csum_tree_block(eb, result); if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); + u8 val[BTRFS_CSUM_SIZE] = { 0 }; read_extent_buffer(eb, &val, 0, csum_size); btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %x found %x level %d", + "%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d", fs_info->sb->s_id, eb->start, - val, found, btrfs_header_level(eb)); + CSUM_FMT_VALUE(csum_size, val), + CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb)); ret = -EUCLEAN; goto err; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index c8df2edafd85..5be30066563c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1170,10 +1170,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices, disk_kobj->name); } - kobject_del(&one_device->devid_kobj); - kobject_put(&one_device->devid_kobj); + if (one_device->devid_kobj.state_initialized) { + kobject_del(&one_device->devid_kobj); + kobject_put(&one_device->devid_kobj); - wait_for_completion(&one_device->kobj_unregister); + wait_for_completion(&one_device->kobj_unregister); + } return 0; } @@ -1186,10 +1188,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices, sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name); } - kobject_del(&one_device->devid_kobj); - kobject_put(&one_device->devid_kobj); + if (one_device->devid_kobj.state_initialized) { + kobject_del(&one_device->devid_kobj); + kobject_put(&one_device->devid_kobj); - wait_for_completion(&one_device->kobj_unregister); + wait_for_completion(&one_device->kobj_unregister); + } } return 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 149227160ff0..58b27e4070a3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2184,7 +2184,7 @@ static int __init start_dirtytime_writeback(void) __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 6611ef3269a8..43c165e796da 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3091,11 +3091,10 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; - bool async_dio = ff->fc->async_dio; loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_iter_count(iter); + size_t count = iov_iter_count(iter), shortened = 0; loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; @@ -3103,17 +3102,9 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) inode = file->f_mapping->host; i_size = i_size_read(inode); - if ((iov_iter_rw(iter) == READ) && (offset > i_size)) + if ((iov_iter_rw(iter) == READ) && (offset >= i_size)) return 0; - /* optimization for short read */ - if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) { - if (offset >= i_size) - return 0; - iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); - count = iov_iter_count(iter); - } - io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); if (!io) return -ENOMEM; @@ -3129,15 +3120,22 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. */ - io->async = async_dio; + io->async = ff->fc->async_dio; io->iocb = iocb; io->blocking = is_sync_kiocb(iocb); + /* optimization for short read */ + if (io->async && !io->write && offset + count > i_size) { + iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); + shortened = count - iov_iter_count(iter); + count -= shortened; + } + /* * We cannot asynchronously extend the size of a file. * In such case the aio will behave exactly like sync io. */ - if ((offset + count > i_size) && iov_iter_rw(iter) == WRITE) + if ((offset + count > i_size) && io->write) io->blocking = true; if (io->async && io->blocking) { @@ -3155,6 +3153,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } else { ret = __fuse_direct_read(io, iter, &pos); } + iov_iter_reexpand(iter, iov_iter_count(iter) + shortened); if (io->async) { bool blocking = io->blocking; diff --git a/fs/io_uring.c b/fs/io_uring.c index 3790c7fe9fee..eed0d068904c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1753,6 +1753,9 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb, struct io_ring_ctx *ctx = req->ctx; int ret, notify; + if (tsk->flags & PF_EXITING) + return -ESRCH; + /* * SQPOLL kernel thread doesn't need notification, just a wakeup. For * all other cases, use TWA_SIGNAL unconditionally to ensure we're @@ -1787,8 +1790,10 @@ static void __io_req_task_cancel(struct io_kiocb *req, int error) static void io_req_task_cancel(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + struct io_ring_ctx *ctx = req->ctx; __io_req_task_cancel(req, -ECANCELED); + percpu_ref_put(&ctx->refs); } static void __io_req_task_submit(struct io_kiocb *req) @@ -2010,6 +2015,12 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { + /* + * Not safe to run on exiting task, and the task_work handling will + * not add work to such a task. + */ + if (unlikely(current->flags & PF_EXITING)) + return false; if (current->task_works) { __set_current_state(TASK_RUNNING); task_work_run(); @@ -2283,13 +2294,17 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) goto end_req; } - ret = io_import_iovec(rw, req, &iovec, &iter, false); - if (ret < 0) - goto end_req; - ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); - if (!ret) + if (!req->io) { + ret = io_import_iovec(rw, req, &iovec, &iter, false); + if (ret < 0) + goto end_req; + ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); + if (!ret) + return true; + kfree(iovec); + } else { return true; - kfree(iovec); + } end_req: req_set_fail_links(req); io_req_complete(req, ret); @@ -3115,6 +3130,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, struct iov_iter __iter, *iter = &__iter; ssize_t io_size, ret, ret2; size_t iov_count; + bool no_async; if (req->io) iter = &req->io->rw.iter; @@ -3132,7 +3148,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, kiocb->ki_flags &= ~IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_async(req->file, READ)) + no_async = force_nonblock && !io_file_supports_async(req->file, READ); + if (no_async) goto copy_iov; ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count); @@ -3155,10 +3172,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, goto done; /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, iov_count - iov_iter_count(iter)); - ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); - if (ret) - goto out_free; - return -EAGAIN; + ret = 0; + goto copy_iov; } else if (ret < 0) { /* make sure -ERESTARTSYS -> -EINTR is done */ goto done; @@ -3176,6 +3191,8 @@ copy_iov: ret = ret2; goto out_free; } + if (no_async) + return -EAGAIN; /* it's copied and will be cleaned with ->io */ iovec = NULL; /* now use our persistent iterator, if we aren't already */ @@ -3508,8 +3525,6 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; if (unlikely(sqe->ioprio || sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) @@ -3536,6 +3551,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { u64 flags, mode; + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; if (req->flags & REQ_F_NEED_CLEANUP) return 0; mode = READ_ONCE(sqe->len); @@ -3550,6 +3567,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) size_t len; int ret; + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; if (req->flags & REQ_F_NEED_CLEANUP) return 0; how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); @@ -3767,7 +3786,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -3882,7 +3901,7 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock) static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->buf_index) return -EINVAL; @@ -5399,6 +5418,8 @@ static int io_async_cancel(struct io_kiocb *req) static int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) + return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->rw_flags) @@ -5449,6 +5470,8 @@ static int io_req_defer_prep(struct io_kiocb *req, if (unlikely(ret)) return ret; + io_prep_async_work(req); + switch (req->opcode) { case IORING_OP_NOP: break; @@ -5646,6 +5669,11 @@ static void __io_clean_op(struct io_kiocb *req) io_put_file(req, req->splice.file_in, (req->splice.flags & SPLICE_F_FD_IN_FIXED)); break; + case IORING_OP_OPENAT: + case IORING_OP_OPENAT2: + if (req->open.filename) + putname(req->open.filename); + break; } req->flags &= ~REQ_F_NEED_CLEANUP; } @@ -6323,9 +6351,6 @@ static void io_submit_state_start(struct io_submit_state *state, struct io_ring_ctx *ctx, unsigned int max_ios) { blk_start_plug(&state->plug); -#ifdef CONFIG_BLOCK - state->plug.nowait = true; -#endif state->comp.nr = 0; INIT_LIST_HEAD(&state->comp.list); state->comp.ctx = ctx; @@ -8180,6 +8205,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, /* cancel this request, or head link requests */ io_attempt_cancel(ctx, cancel_req); io_put_req(cancel_req); + /* cancellations _may_ trigger task work */ + io_run_task_work(); schedule(); finish_wait(&ctx->inflight_wait, &wait); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e732580fe47b..cb52db9a0cfb 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -579,6 +579,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); do { + if (entry->label) + entry->label->len = NFS4_MAXLABELLEN; + status = xdr_decode(desc, entry, &stream); if (status != 0) { if (status == -EAGAIN) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index ff8965d1a4d4..a163533446fa 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task, } static void -ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx) +ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx) } static void -ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx) +ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx) static struct nfs4_pnfs_ds * ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx, + u32 start_idx, u32 *best_idx, bool check_device) { struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; bool fail_return = false; - int idx; + u32 idx; /* mirrors are initially sorted by efficiency */ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { @@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, static struct nfs4_pnfs_ds * ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false); } static struct nfs4_pnfs_ds * ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true); } static struct nfs4_pnfs_ds * ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { struct nfs4_pnfs_ds *ds; @@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, } static struct nfs4_pnfs_ds * -ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx) +ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, + u32 *best_idx) { struct pnfs_layout_segment *lseg = pgio->pg_lseg; struct nfs4_pnfs_ds *ds; @@ -837,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_pgio_mirror *pgm; struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; - int ds_idx; + u32 ds_idx, i; retry: ff_layout_pg_check_layout(pgio, req); @@ -863,14 +864,14 @@ retry: goto retry; } - mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + for (i = 0; i < pgio->pg_mirror_count; i++) { + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); + pgm = &pgio->pg_mirrors[i]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + } pgio->pg_mirror_idx = ds_idx; - /* read always uses only one mirror - idx 0 for pgio layer */ - pgm = &pgio->pg_mirrors[0]; - pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; - if (NFS_SERVER(pgio->pg_inode)->flags & (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans; @@ -894,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs4_ff_layout_mirror *mirror; struct nfs_pgio_mirror *pgm; struct nfs4_pnfs_ds *ds; - int i; + u32 i; retry: ff_layout_pg_check_layout(pgio, req); @@ -1038,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; - int new_idx = 0; + u32 new_idx = 0; if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx)) ff_layout_send_layouterror(hdr->lseg); @@ -1075,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; @@ -1149,7 +1150,7 @@ reset: /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ static int ff_layout_async_handle_error_v3(struct rpc_task *task, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -1184,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { int vers = clp->cl_nfs_mod->rpc_vers->number; @@ -1211,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task, } static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, - int idx, u64 offset, u64 length, + u32 idx, u64 offset, u64 length, u32 *op_status, int opnum, int error) { struct nfs4_ff_layout_mirror *mirror; @@ -1809,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) loff_t offset = hdr->args.offset; int vers; struct nfs_fh *fh; - int idx = hdr->pgio_mirror_idx; + u32 idx = hdr->pgio_mirror_idx; mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 142225f0af59..2b2211d1234e 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -356,7 +356,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, truncate_pagecache_range(dst_inode, pos_dst, pos_dst + res->write_res.count); - + spin_lock(&dst_inode->i_lock); + NFS_I(dst_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE | + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_SIZE | + NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA); + spin_unlock(&dst_inode->i_lock); + spin_lock(&src_inode->i_lock); + NFS_I(src_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE | + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_ATIME); + spin_unlock(&src_inode->i_lock); status = res->write_res.count; out: if (args->sync) diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 8fe03b4a0d2b..25aade344192 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -384,7 +384,7 @@ fail_nomem: static int vboxsf_parse_monolithic(struct fs_context *fc, void *data) { - char *options = data; + unsigned char *options = data; if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 && options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 && diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..b3fc5d3dd8ea 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -497,13 +497,12 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; + return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..868e11face00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -352,6 +352,8 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); + #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3215023d4852..bf9181cef444 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -142,7 +142,6 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, - CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 75895e6363b8..6175c77bf25e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -82,6 +82,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ #define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ #define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ +#define CPUIDLE_FLAG_RCU_IDLE BIT(6) /* idle-state takes care of RCU */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..43b39ab9de1a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -58,6 +58,8 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ @@ -104,6 +106,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { @@ -189,14 +197,23 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +#if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); +#else +static inline int dax_read_lock(void) +{ + return 0; +} + +static inline void dax_read_unlock(int id) +{ +} +#endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2eab6d5f6736..aab0ffc6bac6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16)) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..8aab327b5539 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; diff --git a/include/linux/mm.h b/include/linux/mm.h index ca6e6a81576b..16b799a0522c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,8 @@ struct writeback_control; struct bdi_writeback; struct pt_regs; +extern int sysctl_page_lock_unfairness; + void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ @@ -1644,7 +1646,7 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma); + struct vm_area_struct *vma, struct vm_area_struct *new); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); @@ -2414,7 +2416,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum memmap_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 496c3ff97cce..ed028af3cb19 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -436,6 +436,16 @@ struct mm_struct { */ atomic_t mm_count; + /** + * @has_pinned: Whether this mm has pinned any pages. This can + * be either replaced in the future by @pinned_vm when it + * becomes stable, or grow into a counter on its own. We're + * aggresive on this bit now - even if the pinned pages were + * unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm just for simplicity. + */ + atomic_t has_pinned; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8379432f4f2f..0f7a4ff4b059 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -824,10 +824,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; + extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2cc3cf80b49a..0b17c4322b09 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) -/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..7bd4fcdd0738 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1784,6 +1784,7 @@ enum netdev_priv_flags { * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * + * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one @@ -1848,6 +1849,7 @@ enum netdev_priv_flags { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @xdp_state: stores info on attached XDP BPF programs * * FIXME: cleanup struct net_device such that network protocol info * moves out. diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9408f3252c8e..69cb46f7b8d2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1611,8 +1611,8 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_idx; /* ds index if ds_clp is set */ - int pgio_mirror_idx;/* mirror index in pgio layer */ + u32 ds_commit_idx; /* ds index if ds_clp is set */ + u32 pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { diff --git a/include/linux/node.h b/include/linux/node.h index 4866f32a02d8..014ba3ab2efd 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,11 +99,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn); +int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn) + unsigned long end_pfn, + enum meminit_context context) { return 0; } @@ -128,7 +130,8 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn); + error = link_mem_sections(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5e033fe1ff4e..5fda40f97fe9 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* @@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); @@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked @@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8cbc2e795d5..90654cb63e9e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,16 @@ typedef unsigned int pgtbl_mod_mask; #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif +#ifndef p4d_offset_lockless +#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) +#endif +#ifndef pud_offset_lockless +#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) +#endif +#ifndef pmd_offset_lockless +#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) +#endif + /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..cdd73afc4c46 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -623,6 +623,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 01fc4d9c9c54..8a99279a579b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -248,6 +248,7 @@ struct uart_port { unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; + unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed9bea924dc3..04a18e01b362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3223,8 +3223,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ -static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, - bool free_on_error) +static inline int __must_check __skb_put_padto(struct sk_buff *skb, + unsigned int len, + bool free_on_error) { unsigned int size = skb->len; @@ -3247,7 +3248,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 3d5c3271a9a8..a59db2f08e76 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -25,7 +25,7 @@ static inline void stackleak_task_init(struct task_struct *t) #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE int stack_erasing_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 898c890fc153..27fb99cfeb02 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -21,6 +21,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 +#define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 52ef92049073..bbb3f26fbde9 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -744,8 +744,6 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * vb2_core_reqbufs() - Initiate streaming. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. Currently, the only - * used flag is %V4L2_FLAG_MEMORY_NON_CONSISTENT. * @count: requested buffer count. * * Videobuf2 core helper to implement VIDIOC_REQBUF() operation. It is called @@ -770,13 +768,12 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * Return: returns zero on success; an error code otherwise. */ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count); + unsigned int *count); /** * vb2_core_create_bufs() - Allocate buffers and any required auxiliary structs * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. * @count: requested buffer count. * @requested_planes: number of planes requested. * @requested_sizes: array with the size of the planes. @@ -794,7 +791,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, * Return: returns zero on success; an error code otherwise. */ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count, + unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[]); diff --git a/include/net/flow.h b/include/net/flow.h index 929d3ca614d0..b2531df3f65f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = sport; + fl4->flowi4_multipath_hash = 0; } /* Reset some input parameters after previous lookup */ diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..8e0eb2c9c528 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -726,7 +726,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected - * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() @@ -824,7 +823,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index a1a8d45adb42..6c0806bd8d1e 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -8,6 +8,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; struct list_head module_list; + struct list_head notify_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index b33f1aefad09..0bdff38eb4bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -226,12 +226,14 @@ struct sctp_sock { data_ready_signalled:1; atomic_t pd_mode; + + /* Fields after this point will be skipped on copies, like on accept + * and peeloff operations + */ + /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; - /* These must be the last fields, as they will skipped on copies, - * like on accept and peeloff operations - */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index da369b12005f..0ac4e7fba086 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -566,6 +566,7 @@ struct ocelot_port { u8 ptp_cmd; struct sk_buff_head tx_skbs; u8 ts_id; + spinlock_t ts_id_lock; phy_interface_t phy_mode; @@ -677,6 +678,7 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi, int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); +void ocelot_deinit_port(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_port_enable(struct ocelot *ocelot, int port, diff --git a/include/sound/soc.h b/include/sound/soc.h index 5e3919ffb00c..fc4fcac72cf7 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1193,6 +1193,8 @@ struct snd_soc_pcm_runtime { ((i) < (rtd)->num_cpus + (rtd)->num_codecs) && \ ((dai) = (rtd)->dais[i]); \ (i)++) +#define for_each_rtd_dais_rollback(rtd, i, dai) \ + for (; (--(i) >= 0) && ((dai) = (rtd)->dais[i]);) void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd); @@ -1361,6 +1363,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai); struct snd_soc_dai *snd_soc_find_dai( const struct snd_soc_dai_link_component *dlc); +struct snd_soc_dai *snd_soc_find_dai_with_mutex( + const struct snd_soc_dai_link_component *dlc); #include <sound/soc-dai.h> diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5dcd24cb33ea..72ba36be9655 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -79,6 +79,7 @@ enum { ETHTOOL_MSG_TSINFO_GET_REPLY, ETHTOOL_MSG_CABLE_TEST_NTF, ETHTOOL_MSG_CABLE_TEST_TDR_NTF, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c7b70ff53bc1..235db7754606 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -191,8 +191,6 @@ enum v4l2_memory { V4L2_MEMORY_DMABUF = 4, }; -#define V4L2_FLAG_MEMORY_NON_CONSISTENT (1 << 0) - /* see also http://vektor.theorem.ca/graphics/ycbcr/ */ enum v4l2_colorspace { /* @@ -949,10 +947,7 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - union { - __u32 flags; - __u32 reserved[1]; - }; + __u32 reserved[1]; }; /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ @@ -2456,9 +2451,6 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. - * @flags: additional buffer management attributes (ignored unless the - * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability - * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2467,8 +2459,7 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 flags; - __u32 reserved[6]; + __u32 reserved[7]; }; /* diff --git a/init/main.c b/init/main.c index ae78fb68d231..e880b4ecb314 100644 --- a/init/main.c +++ b/init/main.c @@ -33,6 +33,7 @@ #include <linux/nmi.h> #include <linux/percpu.h> #include <linux/kmod.h> +#include <linux/kprobes.h> #include <linux/vmalloc.h> #include <linux/kernel_stat.h> #include <linux/start_kernel.h> @@ -303,7 +304,7 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) #ifdef CONFIG_BOOT_CONFIG -char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; +static char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; #define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0) @@ -1402,6 +1403,7 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + kprobe_free_init_mem(); ftrace_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 78dfff6a501b..7df28a45c66b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info { struct bpf_map *map; struct bpf_htab *htab; void *percpu_value_buf; // non-zero means percpu hash - unsigned long flags; u32 bucket_id; u32 skip_elems; }; @@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, struct htab_elem *prev_elem) { const struct bpf_htab *htab = info->htab; - unsigned long flags = info->flags; u32 skip_elems = info->skip_elems; u32 bucket_id = info->bucket_id; struct hlist_nulls_head *head; @@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, /* not found, unlock and go to the next bucket */ b = &htab->buckets[bucket_id++]; - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } for (i = bucket_id; i < htab->n_buckets; i++) { b = &htab->buckets[i]; - flags = htab_lock_bucket(htab, b); + rcu_read_lock(); count = 0; head = &b->head; hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { if (count >= skip_elems) { - info->flags = flags; info->bucket_id = i; info->skip_elems = count; return elem; @@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, count++; } - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } @@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v) static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v) { - struct bpf_iter_seq_hash_map_info *info = seq->private; - if (!v) (void)__bpf_hash_map_seq_show(seq, NULL); else - htab_unlock_bucket(info->htab, - &info->htab->buckets[info->bucket_id], - info->flags); + rcu_read_unlock(); } static int bpf_iter_init_hash_map(void *priv_data, diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index fb878ba3f22f..18f4969552ac 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) else prev_key = key; + rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; - return NULL; + key = NULL; } + rcu_read_unlock(); return key; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 18683598edbc..6fdb6105e6d6 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -60,13 +60,15 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, return ret; } + /* Either of the above might have changed the syscall number */ + syscall = syscall_get_nr(current, regs); + if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall); syscall_enter_audit(regs, syscall); - /* The above might have changed the syscall number */ - return ret ? : syscall_get_nr(current, regs); + return ret ? : syscall; } static __always_inline long diff --git a/kernel/fork.c b/kernel/fork.c index 49677d668de4..da8d360fb032 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) - retval = copy_page_range(mm, oldmm, mpnt); + retval = copy_page_range(mm, oldmm, mpnt, tmp); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); @@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; + atomic_set(&mm->has_pinned, 0); atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 287b263c9cb9..e995541d277d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2140,6 +2140,9 @@ static void kill_kprobe(struct kprobe *p) lockdep_assert_held(&kprobe_mutex); + if (WARN_ON_ONCE(kprobe_gone(p))) + return; + p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* @@ -2159,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p) /* * The module is going away. We should disarm the kprobe which - * is using ftrace. + * is using ftrace, because ftrace framework is still available at + * MODULE_STATE_GOING notification. */ - if (kprobe_ftrace(p)) + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } @@ -2419,7 +2423,10 @@ static int kprobes_module_callback(struct notifier_block *nb, mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry(p, head, hlist) + hlist_for_each_entry(p, head, hlist) { + if (kprobe_gone(p)) + continue; + if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { @@ -2436,6 +2443,7 @@ static int kprobes_module_callback(struct notifier_block *nb, */ kill_kprobe(p); } + } } if (val == MODULE_STATE_GOING) remove_module_kprobe_blacklist(mod); @@ -2452,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = { extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; +void kprobe_free_init_mem(void) +{ + void *start = (void *)(&__init_begin); + void *end = (void *)(&__init_end); + struct hlist_head *head; + struct kprobe *p; + int i; + + mutex_lock(&kprobe_mutex); + + /* Kill all kprobes on initmem */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry(p, head, hlist) { + if (start <= (void *)p->addr && (void *)p->addr < end) + kill_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); +} + static int __init init_kprobes(void) { int i, err = 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 54b74fabf40c..2facbbd146ec 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr, static int mark_lock(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit) { - unsigned int new_mask = 1 << new_bit, ret = 1; + unsigned int old_mask, new_mask, ret = 1; if (new_bit >= LOCK_USAGE_STATES) { DEBUG_LOCKS_WARN_ON(1); return 0; } + if (new_bit == LOCK_USED && this->read) + new_bit = LOCK_USED_READ; + + new_mask = 1 << new_bit; + /* * If already set then do not dirty the cacheline, * nor do any checks: @@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, /* * Make sure we didn't race: */ - if (unlikely(hlock_class(this)->usage_mask & new_mask)) { - graph_unlock(); - return 1; - } + if (unlikely(hlock_class(this)->usage_mask & new_mask)) + goto unlock; + old_mask = hlock_class(this)->usage_mask; hlock_class(this)->usage_mask |= new_mask; + /* + * Save one usage_traces[] entry and map both LOCK_USED and + * LOCK_USED_READ onto the same entry. + */ + if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) { + if (old_mask & (LOCKF_USED | LOCKF_USED_READ)) + goto unlock; + new_bit = LOCK_USED; + } + if (!(hlock_class(this)->usage_traces[new_bit] = save_trace())) return 0; @@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return 0; } +unlock: graph_unlock(); /* @@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock { #ifdef CONFIG_PROVE_LOCKING struct lock_class *class = look_up_lock_class(lock, subclass); + unsigned long mask = LOCKF_USED; /* if it doesn't have a class (yet), it certainly hasn't been used yet */ if (!class) return; - if (!(class->usage_mask & LOCK_USED)) + /* + * READ locks only conflict with USED, such that if we only ever use + * READ locks, there is no deadlock possible -- RCU. + */ + if (!hlock->read) + mask |= LOCKF_USED_READ; + + if (!(class->usage_mask & mask)) return; hlock->class_idx = class - lock_classes; diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index baca699b94e9..b0be1560ed17 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -19,6 +19,7 @@ enum lock_usage_bit { #include "lockdep_states.h" #undef LOCKDEP_STATE LOCK_USED, + LOCK_USED_READ, LOCK_USAGE_STATES }; @@ -40,6 +41,7 @@ enum { #include "lockdep_states.h" #undef LOCKDEP_STATE __LOCKF(USED) + __LOCKF(USED_READ) }; #define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE | diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 8bbafe3e5203..70a32a576f3f 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem); static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); /* * Due to having preemption disabled the decrement happens on @@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem) if (likely(!atomic_read_acquire(&sem->block))) return true; - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); /* Prod writer to re-evaluate readers_active_check() */ rcuwait_wake_up(&sem->writer); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 835e2df8590a..05d3e1375e4c 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -590,7 +590,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu) } #else /* #ifdef CONFIG_TASKS_RCU */ -static void show_rcu_tasks_classic_gp_kthread(void) { } +static inline void show_rcu_tasks_classic_gp_kthread(void) { } void exit_tasks_rcu_start(void) { } void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); } #endif /* #else #ifdef CONFIG_TASKS_RCU */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8ce77d9ac716..f78ee759af9c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -673,6 +673,7 @@ void rcu_idle_enter(void) lockdep_assert_irqs_disabled(); rcu_eqs_enter(false); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); #ifdef CONFIG_NO_HZ_FULL /** @@ -886,6 +887,7 @@ void rcu_idle_exit(void) rcu_eqs_exit(false); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); #ifdef CONFIG_NO_HZ_FULL /** diff --git a/kernel/stackleak.c b/kernel/stackleak.c index a8fc9ae1d03d..ce161a8e8d97 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -20,7 +20,7 @@ static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); int stack_erasing_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; int state = !static_branch_unlikely(&stack_erasing_bypass); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09e70ee2332e..afad085960b8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2912,6 +2912,14 @@ static struct ctl_table vm_table[] = { .proc_handler = percpu_pagelist_fraction_sysctl_handler, .extra1 = SYSCTL_ZERO, }, + { + .procname = "page_lock_unfairness", + .data = &sysctl_page_lock_unfairness, + .maxlen = sizeof(sysctl_page_lock_unfairness), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, #ifdef CONFIG_MMU { .procname = "max_map_count", diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 275441254bb5..603255f5f085 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops) { lockdep_assert_held(&ftrace_lock); list_del_rcu(&ops->list); + synchronize_rcu(); } /* @@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command) __unregister_ftrace_function(ops); ftrace_start_up--; ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + ftrace_trampoline_free(ops); return ret; } @@ -7531,8 +7534,7 @@ static bool is_permanent_ops_registered(void) int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret = -ENODEV; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f40d850ebabc..2a7c26345e83 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3782,14 +3782,14 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _------=> CPU# \n" + "# / _-----=> irqs-off \n" + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" + "# |||| / delay \n" + "# cmd pid ||||| time | caller \n" + "# \\ / ||||| \\ | / \n"); } static void print_event_info(struct array_buffer *buf, struct seq_file *m) @@ -3810,26 +3810,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, print_event_info(buf, m); - seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; - const char *space = " "; - int prec = tgid ? 10 : 2; + const char *space = " "; + int prec = tgid ? 12 : 2; print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); - seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); - seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); - seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); - seq_printf(m, "# %.*s||| / delay\n", prec, space); - seq_printf(m, "# TASK-PID %.*sCPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); - seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); + seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); + seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); + seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); + seq_printf(m, "# %.*s||| / delay\n", prec, space); + seq_printf(m, "# TASK-PID %.*s CPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); + seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); } void diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0b933546142e..1b2ef6490229 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { - kfree(hist_data->attrs->var_defs.name[n_vars]); ret = -ENOMEM; goto free; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 4d1893564912..000e9dc224c6 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%8.8s-%-5d %3d", + trace_seq_printf(s, "%8.8s-%-7d %3d", comm, entry->pid, cpu); return trace_print_lat_fmt(s, entry); @@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid); if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { unsigned int tgid = trace_find_tgid(entry->pid); if (!tgid) - trace_seq_printf(s, "(-----) "); + trace_seq_printf(s, "(-------) "); else - trace_seq_printf(s, "(%5d) ", tgid); + trace_seq_printf(s, "(%7d) ", tgid); } trace_seq_printf(s, "[%03d] ", iter->cpu); @@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); trace_seq_printf( - s, "%16s %5d %3d %d %08x %08lx ", + s, "%16s %7d %3d %d %08x %08lx ", comm, entry->pid, iter->cpu, entry->flags, entry->preempt_count, iter->idx); } else { @@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, S = task_index_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, - " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n", field->prev_pid, field->prev_prio, S, delim, diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index f10073e62603..f4938040c228 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { + lockdep_hardirqs_off(CALLER_ADDR0); + if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } - - lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e068c3c7189a..0c781f912f9f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -520,8 +520,8 @@ config DEBUG_FS_ALLOW_NONE endchoice source "lib/Kconfig.kgdb" - source "lib/Kconfig.ubsan" +source "lib/Kconfig.kcsan" endmenu @@ -1620,8 +1620,6 @@ config PROVIDE_OHCI1394_DMA_INIT source "samples/Kconfig" -source "lib/Kconfig.kcsan" - config ARCH_HAS_DEVMEM_IS_ALLOWED bool diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 2c905a91d4eb..649ed44f199c 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -31,6 +31,8 @@ static size_t xbc_data_size __initdata; static struct xbc_node *last_parent __initdata; static const char *xbc_err_msg __initdata; static int xbc_err_pos __initdata; +static int open_brace[XBC_DEPTH_MAX] __initdata; +static int brace_index __initdata; static int __init xbc_parse_error(const char *msg, const char *p) { @@ -431,27 +433,27 @@ static char *skip_spaces_until_newline(char *p) return p; } -static int __init __xbc_open_brace(void) +static int __init __xbc_open_brace(char *p) { - /* Mark the last key as open brace */ - last_parent->next = XBC_NODE_MAX; + /* Push the last key as open brace */ + open_brace[brace_index++] = xbc_node_index(last_parent); + if (brace_index >= XBC_DEPTH_MAX) + return xbc_parse_error("Exceed max depth of braces", p); return 0; } static int __init __xbc_close_brace(char *p) { - struct xbc_node *node; - - if (!last_parent || last_parent->next != XBC_NODE_MAX) + brace_index--; + if (!last_parent || brace_index < 0 || + (open_brace[brace_index] != xbc_node_index(last_parent))) return xbc_parse_error("Unexpected closing brace", p); - node = last_parent; - node->next = 0; - do { - node = xbc_node_get_parent(node); - } while (node && node->next != XBC_NODE_MAX); - last_parent = node; + if (brace_index == 0) + last_parent = NULL; + else + last_parent = &xbc_nodes[open_brace[brace_index - 1]]; return 0; } @@ -492,8 +494,8 @@ static int __init __xbc_parse_value(char **__v, char **__n) break; } if (strchr(",;\n#}", c)) { - v = strim(v); *p++ = '\0'; + v = strim(v); break; } } @@ -661,7 +663,7 @@ static int __init xbc_open_brace(char **k, char *n) return ret; *k = n; - return __xbc_open_brace(); + return __xbc_open_brace(n - 1); } static int __init xbc_close_brace(char **k, char *n) @@ -681,6 +683,13 @@ static int __init xbc_verify_tree(void) int i, depth, len, wlen; struct xbc_node *n, *m; + /* Brace closing */ + if (brace_index) { + n = &xbc_nodes[open_brace[brace_index]]; + return xbc_parse_error("Brace is not closed", + xbc_node_get_data(n)); + } + /* Empty tree */ if (xbc_node_num == 0) { xbc_parse_error("Empty config", xbc_data); @@ -745,6 +754,7 @@ void __init xbc_destroy_all(void) xbc_node_num = 0; memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; + brace_index = 0; } /** diff --git a/lib/memregion.c b/lib/memregion.c index 77c85b5251da..be5cfa5a3b57 100644 --- a/lib/memregion.c +++ b/lib/memregion.c @@ -2,6 +2,7 @@ /* identifiers for device / performance-differentiated memory regions */ #include <linux/idr.h> #include <linux/types.h> +#include <linux/memregion.h> static DEFINE_IDA(memregion_ids); diff --git a/lib/string.c b/lib/string.c index 6012c385fb31..4288e0158d47 100644 --- a/lib/string.c +++ b/lib/string.c @@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const char *src, size_t count) } EXPORT_SYMBOL(strscpy_pad); +/** + * stpcpy - copy a string from src to dest returning a pointer to the new end + * of dest, including src's %NUL-terminator. May overrun dest. + * @dest: pointer to end of string being copied into. Must be large enough + * to receive copy. + * @src: pointer to the beginning of string being copied from. Must not overlap + * dest. + * + * stpcpy differs from strcpy in a key way: the return value is a pointer + * to the new %NUL-terminating character in @dest. (For strcpy, the return + * value is a pointer to the start of @dest). This interface is considered + * unsafe as it doesn't perform bounds checking of the inputs. As such it's + * not recommended for usage. Instead, its definition is provided in case + * the compiler lowers other libcalls to stpcpy. + */ +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src); +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src) +{ + while ((*dest++ = *src++) != '\0') + /* nothing */; + return --dest; +} +EXPORT_SYMBOL(stpcpy); + #ifndef __HAVE_ARCH_STRCAT /** * strcat - Append one %NUL-terminated string to another diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index c5a6fef7b45d..76c607ee6db5 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -434,7 +434,7 @@ static int __init test_rhltable(unsigned int entries) } else { if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d", err, -ENOENT)) - continue; + continue; } } diff --git a/mm/filemap.c b/mm/filemap.c index 1aaea26556cc..5202e38ab79e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -988,9 +988,43 @@ void __init pagecache_init(void) page_writeback_init(); } +/* + * The page wait code treats the "wait->flags" somewhat unusually, because + * we have multiple different kinds of waits, not just the usual "exclusive" + * one. + * + * We have: + * + * (a) no special bits set: + * + * We're just waiting for the bit to be released, and when a waker + * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, + * and remove it from the wait queue. + * + * Simple and straightforward. + * + * (b) WQ_FLAG_EXCLUSIVE: + * + * The waiter is waiting to get the lock, and only one waiter should + * be woken up to avoid any thundering herd behavior. We'll set the + * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. + * + * This is the traditional exclusive wait. + * + * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: + * + * The waiter is waiting to get the bit, and additionally wants the + * lock to be transferred to it for fair lock behavior. If the lock + * cannot be taken, we stop walking the wait queue without waking + * the waiter. + * + * This is the "fair lock handoff" case, and in addition to setting + * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see + * that it now has the lock. + */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { - int ret; + unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); @@ -999,35 +1033,44 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, return 0; /* - * If it's an exclusive wait, we get the bit for it, and - * stop walking if we can't. - * - * If it's a non-exclusive wait, then the fact that this - * wake function was called means that the bit already - * was cleared, and we don't care if somebody then - * re-took it. + * If it's a lock handoff wait, we get the bit for it, and + * stop walking (and do not wake it up) if we can't. */ - ret = 0; - if (wait->flags & WQ_FLAG_EXCLUSIVE) { - if (test_and_set_bit(key->bit_nr, &key->page->flags)) + flags = wait->flags; + if (flags & WQ_FLAG_EXCLUSIVE) { + if (test_bit(key->bit_nr, &key->page->flags)) return -1; - ret = 1; + if (flags & WQ_FLAG_CUSTOM) { + if (test_and_set_bit(key->bit_nr, &key->page->flags)) + return -1; + flags |= WQ_FLAG_DONE; + } } - wait->flags |= WQ_FLAG_WOKEN; + /* + * We are holding the wait-queue lock, but the waiter that + * is waiting for this will be checking the flags without + * any locking. + * + * So update the flags atomically, and wake up the waiter + * afterwards to avoid any races. This store-release pairs + * with the load-acquire in wait_on_page_bit_common(). + */ + smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * - * Note that this has to be the absolute last thing we do, - * since after list_del_init(&wait->entry) the wait entry + * Note that this pairs with the "finish_wait()" in the + * waiter, and has to be the absolute last thing we do. + * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); - return ret; + return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void wake_up_page_bit(struct page *page, int bit_nr) @@ -1107,8 +1150,8 @@ enum behavior { }; /* - * Attempt to check (or get) the page bit, and mark the - * waiter woken if successful. + * Attempt to check (or get) the page bit, and mark us done + * if successful. */ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, struct wait_queue_entry *wait) @@ -1119,13 +1162,17 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, } else if (test_bit(bit_nr, &page->flags)) return false; - wait->flags |= WQ_FLAG_WOKEN; + wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } +/* How many times do we accept lock stealing from under a waiter? */ +int sysctl_page_lock_unfairness = 5; + static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { + int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; @@ -1143,11 +1190,18 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, } init_wait(wait); - wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; +repeat: + wait->flags = 0; + if (behavior == EXCLUSIVE) { + wait->flags = WQ_FLAG_EXCLUSIVE; + if (--unfairness < 0) + wait->flags |= WQ_FLAG_CUSTOM; + } + /* * Do one last check whether we can get the * page bit synchronously. @@ -1170,27 +1224,63 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, /* * From now on, all the logic will be based on - * the WQ_FLAG_WOKEN flag, and the and the page - * bit testing (and setting) will be - or has - * already been - done by the wake function. + * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to + * see whether the page bit testing has already + * been done by the wake function. * * We can drop our reference to the page. */ if (behavior == DROP) put_page(page); + /* + * Note that until the "finish_wait()", or until + * we see the WQ_FLAG_WOKEN flag, we need to + * be very careful with the 'wait->flags', because + * we may race with a waker that sets them. + */ for (;;) { + unsigned int flags; + set_current_state(state); - if (signal_pending_state(state, current)) + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(state, current)) + break; + + io_schedule(); + continue; + } + + /* If we were non-exclusive, we're done */ + if (behavior != EXCLUSIVE) break; - if (wait->flags & WQ_FLAG_WOKEN) + /* If the waker got the lock for us, we're done */ + if (flags & WQ_FLAG_DONE) break; - io_schedule(); + /* + * Otherwise, if we're getting the lock, we need to + * try to get it ourselves. + * + * And if that fails, we'll have to retry this all. + */ + if (unlikely(test_and_set_bit(bit_nr, &page->flags))) + goto repeat; + + wait->flags |= WQ_FLAG_DONE; + break; } + /* + * If a signal happened, this 'finish_wait()' may remove the last + * waiter from the wait-queues, but the PageWaiters bit will remain + * set. That's ok. The next wakeup will take care of it, and trying + * to do it here would be difficult and prone to races. + */ finish_wait(q, wait); if (thrashing) { @@ -1200,12 +1290,20 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, } /* - * A signal could leave PageWaiters set. Clearing it here if - * !waitqueue_active would be possible (by open-coding finish_wait), - * but still fail to catch it in the case of wait hash collision. We - * already can fail to clear wait hash collision cases, so don't - * bother with signals either. + * NOTE! The wait->flags weren't stable until we've done the + * 'finish_wait()', and we could have exited the loop above due + * to a signal, and had a wakeup event happen after the signal + * test but before the 'finish_wait()'. + * + * So only after the finish_wait() can we reliably determine + * if we got woken up or not, so we can now figure out the final + * return value based on that state without races. + * + * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive + * waiter, but an exclusive one requires WQ_FLAG_DONE. */ + if (behavior == EXCLUSIVE) + return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } @@ -1255,6 +1255,9 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, BUG_ON(*locked != 1); } + if (flags & FOLL_PIN) + atomic_set(&mm->has_pinned, 1); + /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has @@ -2485,13 +2488,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, +static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; - pmdp = pmd_offset(&pud, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = READ_ONCE(*pmdp); @@ -2528,13 +2531,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&p4d, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -2549,20 +2552,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr)) + } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; - p4dp = p4d_offset(&pgd, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); @@ -2574,7 +2577,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr)) + } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); @@ -2602,7 +2605,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr)) return; - } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr)) + } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } @@ -2660,6 +2663,9 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, FOLL_FAST_ONLY))) return -EINVAL; + if (gup_flags & FOLL_PIN) + atomic_set(¤t->mm->has_pinned, 1); + if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7ff29cc3d55c..da397779a6d4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1074,6 +1074,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + + /* + * If this page is a potentially pinned page, split and retry the fault + * with smaller page size. Normally this should not happen because the + * userspace should use MADV_DONTFORK upon pinned regions. This is a + * best effort that the pinned pages won't be replaced by another + * random page during the coming copy-on-write. + */ + if (unlikely(is_cow_mapping(vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(src_page))) { + pte_free(dst_mm, pgtable); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pmd(vma, src_pmd, addr, false, NULL); + return -EAGAIN; + } + get_page(src_page); page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -1177,6 +1195,16 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* No huge zero pud yet */ } + /* Please refer to comments in copy_huge_pmd() */ + if (unlikely(is_cow_mapping(vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(pud_page(pud)))) { + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pud(vma, src_pud, addr); + return -EAGAIN; + } + pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); @@ -2022,7 +2050,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, put_page(page); add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (is_huge_zero_pmd(*pmd)) { + } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2116,30 +2144,34 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, entry); - atomic_inc(&page[i]._mapcount); - pte_unmap(pte); - } - - /* - * Set PG_double_map before dropping compound_mapcount to avoid - * false-negative page_mapped(). - */ - if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { - for (i = 0; i < HPAGE_PMD_NR; i++) + if (!pmd_migration) atomic_inc(&page[i]._mapcount); + pte_unmap(pte); } - lock_page_memcg(page); - if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { - /* Last compound_mapcount is gone. */ - __dec_lruvec_page_state(page, NR_ANON_THPS); - if (TestClearPageDoubleMap(page)) { - /* No need in mapcount reference anymore */ + if (!pmd_migration) { + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && + !TestSetPageDoubleMap(page)) { for (i = 0; i < HPAGE_PMD_NR; i++) - atomic_dec(&page[i]._mapcount); + atomic_inc(&page[i]._mapcount); + } + + lock_page_memcg(page); + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_lruvec_page_state(page, NR_ANON_THPS); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } } + unlock_page_memcg(page); } - unlock_page_memcg(page); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); @@ -2586,6 +2586,10 @@ struct page *ksm_might_need_to_copy(struct page *page, return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) { + put_page(new_page); + new_page = NULL; + } if (new_page) { copy_user_highpage(new_page, page, address, vma); diff --git a/mm/madvise.c b/mm/madvise.c index d4aa5f776543..0e0d61003fc6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -381,9 +381,9 @@ huge_unlock: return 0; } +regular_page: if (pmd_trans_unstable(pmd)) return 0; -regular_page: #endif tlb_change_page_size(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cfa6cbad21d5..6877c765b8d0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1538,9 +1538,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg) memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON)); seq_buf_printf(&s, "workingset_activate_file %lu\n", memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE)); - seq_buf_printf(&s, "workingset_restore %lu\n", + seq_buf_printf(&s, "workingset_restore_anon %lu\n", memcg_page_state(memcg, WORKINGSET_RESTORE_ANON)); - seq_buf_printf(&s, "workingset_restore %lu\n", + seq_buf_printf(&s, "workingset_restore_file %lu\n", memcg_page_state(memcg, WORKINGSET_RESTORE_FILE)); seq_buf_printf(&s, "workingset_nodereclaim %lu\n", memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); diff --git a/mm/memory.c b/mm/memory.c index 469af373ae76..fcfc4ca36eba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -695,84 +695,218 @@ out: * covered by this vma. */ -static inline unsigned long -copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static unsigned long +copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr, int *rss) { unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); - /* pte contains position in swap or file, so copy. */ - if (unlikely(!pte_present(pte))) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - rss[mm_counter(page)]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } - } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + rss[mm_counter(page)]++; + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { /* - * Update rss count even for unaddressable pages, as - * they should treated just like normal pages in this - * respect. - * - * We will likely want to have some new rss counters - * for unaddressable pages, at some point. But for now - * keep things as they are. + * COW mappings require pages in both + * parent and child to be set to read. */ - get_page(page); - rss[mm_counter(page)]++; - page_dup_rmap(page, false); + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); - /* - * We do not preserve soft-dirty information, because so - * far, checkpoint/restore is the only feature that - * requires that. And checkpoint/restore does not work - * when a device driver is involved (you cannot easily - * save and restore device driver state). - */ - if (is_write_device_private_entry(entry) && - is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + page_dup_rmap(page, false); + + /* + * We do not preserve soft-dirty information, because so + * far, checkpoint/restore is the only feature that + * requires that. And checkpoint/restore does not work + * when a device driver is involved (you cannot easily + * save and restore device driver state). + */ + if (is_write_device_private_entry(entry) && + is_cow_mapping(vm_flags)) { + make_device_private_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); } - goto out_set_pte; + } + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy a present and normal page if necessary. + * + * NOTE! The usual case is that this doesn't need to do + * anything, and can just return a positive value. That + * will let the caller know that it can just increase + * the page refcount and re-use the pte the traditional + * way. + * + * But _if_ we need to copy it because it needs to be + * pinned in the parent (and the child should get its own + * copy rather than just a reference to the same page), + * we'll do that here and return zero to let the caller + * know we're done. + * + * And if we need a pre-allocated page but don't yet have + * one, return a negative error to let the preallocation + * code know so that it can do so outside the page table + * lock. + */ +static inline int +copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, + struct vm_area_struct *vma, struct vm_area_struct *new, + unsigned long addr, int *rss, struct page **prealloc, + pte_t pte, struct page *page) +{ + struct page *new_page; + + if (!is_cow_mapping(vma->vm_flags)) + return 1; + + /* + * The trick starts. + * + * What we want to do is to check whether this page may + * have been pinned by the parent process. If so, + * instead of wrprotect the pte on both sides, we copy + * the page immediately so that we'll always guarantee + * the pinned page won't be randomly replaced in the + * future. + * + * To achieve this, we do the following: + * + * 1. Write-protect the pte if it's writable. This is + * to protect concurrent write fast-gup with + * FOLL_PIN, so that we'll fail the fast-gup with + * the write bit removed. + * + * 2. Check page_maybe_dma_pinned() to see whether this + * page may have been pinned. + * + * The order of these steps is important to serialize + * against the fast-gup code (gup_pte_range()) on the + * pte check and try_grab_compound_head(), so that + * we'll make sure either we'll capture that fast-gup + * so we'll copy the pinned page here, or we'll fail + * that fast-gup. + * + * NOTE! Even if we don't end up copying the page, + * we won't undo this wrprotect(), because the normal + * reference copy will need it anyway. + */ + if (pte_write(pte)) + ptep_set_wrprotect(src_mm, addr, src_pte); + + /* + * These are the "normally we can just copy by reference" + * checks. + */ + if (likely(!atomic_read(&src_mm->has_pinned))) + return 1; + if (likely(!page_maybe_dma_pinned(page))) + return 1; + + /* + * Uhhuh. It looks like the page might be a pinned page, + * and we actually need to copy it. Now we can set the + * source pte back to being writable. + */ + if (pte_write(pte)) + set_pte_at(src_mm, addr, src_pte, pte); + + new_page = *prealloc; + if (!new_page) + return -EAGAIN; + + /* + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. + */ + *prealloc = NULL; + copy_user_highpage(new_page, page, addr, vma); + __SetPageUptodate(new_page); + page_add_new_anon_rmap(new_page, new, addr, false); + lru_cache_add_inactive_or_unevictable(new_page, new); + rss[mm_counter(new_page)]++; + + /* All done, just insert the new page copy in the child */ + pte = mk_pte(new_page, new->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), new); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page + * is required to copy this pte. + */ +static inline int +copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, + struct vm_area_struct *new, + unsigned long addr, int *rss, struct page **prealloc) +{ + unsigned long vm_flags = vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + page = vm_normal_page(vma, addr, pte); + if (page) { + int retval; + + retval = copy_present_page(dst_mm, src_mm, + dst_pte, src_pte, + vma, new, + addr, rss, prealloc, + pte, page); + if (retval <= 0) + return retval; + + get_page(page); + page_dup_rmap(page, false); + rss[mm_counter(page)]++; } /* @@ -800,35 +934,51 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!(vm_flags & VM_UFFD_WP)) pte = pte_clear_uffd_wp(pte); - page = vm_normal_page(vma, addr, pte); - if (page) { - get_page(page); - page_dup_rmap(page, false); - rss[mm_counter(page)]++; - } - -out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } +static inline struct page * +page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *new_page; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); + if (!new_page) + return NULL; + + if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + put_page(new_page); + return NULL; + } + cgroup_throttle_swaprate(new_page, GFP_KERNEL); + + return new_page; +} + static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; - int progress = 0; + int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; + struct page *prealloc = NULL; again: + progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); - if (!dst_pte) - return -ENOMEM; + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -851,10 +1001,34 @@ again: progress++; continue; } - entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, + if (unlikely(!pte_present(*src_pte))) { + entry.val = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, vma, addr, rss); - if (entry.val) + if (entry.val) + break; + progress += 8; + continue; + } + /* copy_present_pte() will clear `*prealloc' if consumed */ + ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte, + vma, new, addr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + */ + if (unlikely(ret == -EAGAIN)) break; + if (unlikely(prealloc)) { + /* + * pre-alloc page cannot be reused by next time so as + * to strictly follow mempolicy (e.g., alloc_page_vma() + * will allocate page according to address). This + * could only happen if one pinned pte changed. + */ + put_page(prealloc); + prealloc = NULL; + } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); @@ -866,17 +1040,30 @@ again: cond_resched(); if (entry.val) { - if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { + ret = -ENOMEM; + goto out; + } + entry.val = 0; + } else if (ret) { + WARN_ON_ONCE(ret != -EAGAIN); + prealloc = page_copy_prealloc(src_mm, vma, addr); + if (!prealloc) return -ENOMEM; - progress = 0; + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; } if (addr != end) goto again; - return 0; +out: + if (unlikely(prealloc)) + put_page(prealloc); + return ret; } static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pmd_t *src_pmd, *dst_pmd; @@ -903,7 +1090,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; @@ -911,6 +1098,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; @@ -937,7 +1125,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; @@ -945,6 +1133,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { p4d_t *src_p4d, *dst_p4d; @@ -959,14 +1148,14 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma) + struct vm_area_struct *vma, struct vm_area_struct *new) { pgd_t *src_pgd, *dst_pgd; unsigned long next; @@ -1021,7 +1210,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next))) { + vma, new, addr, next))) { ret = -ENOMEM; break; } @@ -2955,8 +3144,8 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ - wp_page_reuse(vmf); unlock_page(page); + wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e9d5ab5d3ca0..ce3e73e3a5c1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -729,7 +729,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * are reserved so nobody should be touching them so we should be safe */ memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, - MEMMAP_HOTPLUG, altmap); + MEMINIT_HOTPLUG, altmap); set_zone_contiguous(zone); } @@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res) } /* link memory sections under this node.*/ - ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1)); + ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); BUG_ON(ret); /* create new memmap entry */ @@ -1575,6 +1576,20 @@ static int __ref __offline_pages(unsigned long start_pfn, /* check again */ ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL, check_pages_isolated_cb); + /* + * per-cpu pages are drained in start_isolate_page_range, but if + * there are still pages that are not free, make sure that we + * drain again, because when we isolated range we might + * have raced with another thread that was adding pages to pcp + * list. + * + * Forward progress should be still guaranteed because + * pages on the pcp list can only belong to MOVABLE_ZONE + * because has_unmovable_pages explicitly checks for + * PageBuddy on freed pages on other zones. + */ + if (ret) + drain_all_pages(zone); } while (ret); /* Ok, all of our target is isolated. diff --git a/mm/migrate.c b/mm/migrate.c index 941b89383cf3..04a98bb2f568 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -668,7 +668,8 @@ void migrate_page_states(struct page *newpage, struct page *page) copy_page_owner(page, newpage); - mem_cgroup_migrate(page, newpage); + if (!PageHuge(page)) + mem_cgroup_migrate(page, newpage); } EXPORT_SYMBOL(migrate_page_states); @@ -1445,7 +1446,7 @@ retry: * Capture required information that might get lost * during migration. */ - is_thp = PageTransHuge(page); + is_thp = PageTransHuge(page) && !PageHuge(page); nr_subpages = thp_nr_pages(page); cond_resched(); @@ -1471,7 +1472,7 @@ retry: * we encounter them after the rest of the list * is processed. */ - if (PageTransHuge(page) && !PageHuge(page)) { + if (is_thp) { lock_page(page); rc = split_huge_page_to_list(page, from); unlock_page(page); @@ -1480,8 +1481,7 @@ retry: nr_thp_split++; goto retry; } - } - if (is_thp) { + nr_thp_failed++; nr_failed += nr_subpages; goto out; diff --git a/mm/mlock.c b/mm/mlock.c index 93ca2bf30b4f..884b1216da6a 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -58,11 +58,14 @@ EXPORT_SYMBOL(can_do_mlock); */ void clear_page_mlock(struct page *page) { + int nr_pages; + if (!TestClearPageMlocked(page)) return; - mod_zone_page_state(page_zone(page), NR_MLOCK, -thp_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGCLEARED); + nr_pages = thp_nr_pages(page); + mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); /* * The previous TestClearPageMlocked() corresponds to the smp_mb() * in __pagevec_lru_add_fn(). @@ -76,7 +79,7 @@ void clear_page_mlock(struct page *page) * We lost the race. the page already moved to evictable list. */ if (PageUnevictable(page)) - count_vm_event(UNEVICTABLE_PGSTRANDED); + count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } } @@ -93,9 +96,10 @@ void mlock_vma_page(struct page *page) VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); if (!TestSetPageMlocked(page)) { - mod_zone_page_state(page_zone(page), NR_MLOCK, - thp_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGMLOCKED); + int nr_pages = thp_nr_pages(page); + + mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); + count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); if (!isolate_lru_page(page)) putback_lru_page(page); } @@ -138,7 +142,7 @@ static void __munlock_isolated_page(struct page *page) /* Did try_to_unlock() succeed or punt? */ if (!PageMlocked(page)) - count_vm_event(UNEVICTABLE_PGMUNLOCKED); + count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page)); putback_lru_page(page); } @@ -154,10 +158,12 @@ static void __munlock_isolated_page(struct page *page) */ static void __munlock_isolation_failed(struct page *page) { + int nr_pages = thp_nr_pages(page); + if (PageUnevictable(page)) - __count_vm_event(UNEVICTABLE_PGSTRANDED); + __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); else - __count_vm_event(UNEVICTABLE_PGMUNLOCKED); + __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); } /** diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fab5e97dc9ca..5661fa164f13 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5975,7 +5975,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context, + unsigned long start_pfn, enum meminit_context context, struct vmem_altmap *altmap) { unsigned long pfn, end_pfn = start_pfn + size; @@ -6007,7 +6007,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context == MEMMAP_EARLY) { + if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; if (defer_init(nid, pfn, end_pfn)) @@ -6016,7 +6016,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMMAP_HOTPLUG) + if (context == MEMINIT_HOTPLUG) __SetPageReserved(page); /* @@ -6099,7 +6099,7 @@ void __ref memmap_init_zone_device(struct zone *zone, * check here not to call set_pageblock_migratetype() against * pfn out of zone. * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap * because this is done early in section_activate() */ if (!(pfn & (pageblock_nr_pages - 1))) { @@ -6137,7 +6137,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid, if (end_pfn > start_pfn) { size = end_pfn - start_pfn; memmap_init_zone(size, nid, zone, start_pfn, - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); } } } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 242c03121d73..63a3db10a8c0 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -170,6 +170,14 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * pageblocks we may have modified and return -EBUSY to caller. This * prevents two threads from simultaneously working on overlapping ranges. * + * Please note that there is no strong synchronization with the page allocator + * either. Pages might be freed while their page blocks are marked ISOLATED. + * In some cases pages might still end up on pcp lists and that would allow + * for their allocation even when they are in fact isolated already. Depending + * on how strong of a guarantee the caller needs drain_all_pages might be needed + * (e.g. __offline_pages will need to call it after check for isolated range for + * a next retry). + * * Return: the number of isolated pageblocks on success and -EBUSY if any part * of range cannot be isolated. */ diff --git a/mm/percpu.c b/mm/percpu.c index f4709629e6de..1ed1a349eab8 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1316,7 +1316,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, /* allocate chunk */ alloc_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT); + BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, diff --git a/mm/shmem.c b/mm/shmem.c index 271548ca20f3..8e2b35ba93ad 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -279,11 +279,13 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) if (!(sb->s_flags & SB_KERNMOUNT)) { spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return -ENOSPC; + if (sbinfo->max_inodes) { + if (!sbinfo->free_inodes) { + spin_unlock(&sbinfo->stat_lock); + return -ENOSPC; + } + sbinfo->free_inodes--; } - sbinfo->free_inodes--; if (inop) { ino = sbinfo->next_ino++; if (unlikely(is_zero_ino(ino))) diff --git a/mm/slab.c b/mm/slab.c index 3160dff6fd76..f658e86ec8ce 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1632,6 +1632,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page) kmem_cache_free(cachep->freelist_cache, freelist); } +/* + * Update the size of the caches before calling slabs_destroy as it may + * recursively call kfree. + */ static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list) { struct page *page, *n; @@ -2153,8 +2157,8 @@ static void do_drain(void *arg) spin_lock(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); spin_unlock(&n->list_lock); - slabs_destroy(cachep, &list); ac->avail = 0; + slabs_destroy(cachep, &list); } static void drain_cpu_caches(struct kmem_cache *cachep) @@ -3402,9 +3406,9 @@ free_done: } #endif spin_unlock(&n->list_lock); - slabs_destroy(cachep, &list); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); + slabs_destroy(cachep, &list); } /* diff --git a/mm/swap.c b/mm/swap.c index d16d65d9b4e0..e7bdf094f76a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -494,14 +494,14 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { + int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ - __mod_zone_page_state(page_zone(page), NR_MLOCK, - thp_nr_pages(page)); - count_vm_event(UNEVICTABLE_PGMLOCKED); + __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); + count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 12f59e641b5e..debc94155f74 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1078,7 +1078,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FS)) + if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, diff --git a/mm/vmscan.c b/mm/vmscan.c index 9727dd8e2581..466fc3144fff 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4268,8 +4268,14 @@ void check_move_unevictable_pages(struct pagevec *pvec) for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); + int nr_pages; + + if (PageTransTail(page)) + continue; + + nr_pages = thp_nr_pages(page); + pgscanned += nr_pages; - pgscanned++; if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irq(&pgdat->lru_lock); @@ -4288,7 +4294,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); - pgrescued++; + pgrescued += nr_pages; } } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 8500f56cbd10..c350ab63cd54 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -25,6 +25,7 @@ #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> +#include <linux/preempt.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -83,11 +84,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size) */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { - const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; + const struct batadv_bla_backbone_gw *gw; u32 hash = 0; - hash = jhash(&claim->addr, sizeof(claim->addr), hash); - hash = jhash(&claim->vid, sizeof(claim->vid), hash); + gw = (struct batadv_bla_backbone_gw *)data; + hash = jhash(&gw->orig, sizeof(gw->orig), hash); + hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } @@ -1579,13 +1581,16 @@ int batadv_bla_init(struct batadv_priv *bat_priv) } /** - * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information - * @skb: contains the bcast_packet to be checked + * @skb: contains the multicast packet to be checked + * @payload_ptr: pointer to position inside the head buffer of the skb + * marking the start of the data to be CRC'ed + * @orig: originator mac address, NULL if unknown * - * check if it is on our broadcast list. Another gateway might - * have sent the same packet because it is connected to the same backbone, - * so we have to remove this duplicate. + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore @@ -1594,19 +1599,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv) * * Return: true if a packet is in the duplicate list, false otherwise. */ -bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct sk_buff *skb) +static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb, u8 *payload_ptr, + const u8 *orig) { - int i, curr; - __be32 crc; - struct batadv_bcast_packet *bcast_packet; struct batadv_bcast_duplist_entry *entry; bool ret = false; - - bcast_packet = (struct batadv_bcast_packet *)skb->data; + int i, curr; + __be32 crc; /* calculate the crc ... */ - crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1)); + crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1625,8 +1628,21 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, if (entry->crc != crc) continue; - if (batadv_compare_eth(entry->orig, bcast_packet->orig)) - continue; + /* are the originators both known and not anonymous? */ + if (orig && !is_zero_ether_addr(orig) && + !is_zero_ether_addr(entry->orig)) { + /* If known, check if the new frame came from + * the same originator: + * We are safe to take identical frames from the + * same orig, if known, as multiplications in + * the mesh are detected via the (orig, seqno) pair. + * So we can be a bit more liberal here and allow + * identical frames from the same orig which the source + * host might have sent multiple times on purpose. + */ + if (batadv_compare_eth(entry->orig, orig)) + continue; + } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. @@ -1642,7 +1658,14 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; - ether_addr_copy(entry->orig, bcast_packet->orig); + + /* known originator */ + if (orig) + ether_addr_copy(entry->orig, orig); + /* anonymous originator */ + else + eth_zero_addr(entry->orig); + bat_priv->bla.bcast_duplist_curr = curr; out: @@ -1652,6 +1675,48 @@ out: } /** + * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the multicast packet to be checked, decapsulated from a + * unicast_packet + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); +} + +/** + * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the bcast_packet to be checked + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct batadv_bcast_packet *bcast_packet; + u8 *payload_ptr; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + payload_ptr = (u8 *)(bcast_packet + 1); + + return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, + bcast_packet->orig); +} + +/** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. * @bat_priv: the bat priv with all the soft interface information @@ -1812,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame - * @is_bcast: the packet came in a broadcast packet type. + * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim @@ -1824,7 +1889,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast) + unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; @@ -1846,9 +1911,32 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) - /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) - goto handled; + /* don't allow multicast packets while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + /* Both broadcast flooding or multicast-via-unicasts + * delivery might send to multiple backbone gateways + * sharing the same LAN and therefore need to coordinate + * which backbone gateway forwards into the LAN, + * by claiming the payload source address. + * + * Broadcast flooding and multicast-via-unicasts + * delivery use the following two batman packet types. + * Note: explicitly exclude BATADV_UNICAST_4ADDR, + * as the DHCP gateway feature will send explicitly + * to only one BLA gateway, so the claiming process + * should be avoided there. + */ + if (packet_type == BATADV_BCAST || + packet_type == BATADV_UNICAST) + goto handled; + + /* potential duplicates from foreign BLA backbone gateways via + * multicast-in-unicast packets + */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + packet_type == BATADV_UNICAST && + batadv_bla_check_ucast_duplist(bat_priv, skb)) + goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; @@ -1883,13 +1971,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; } - /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* if it is a multicast ... */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * - * We need to check is_bcast because with the gateway + * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent - * using a unicast packet type. + * using a unicast 4 address packet type. See comment above. */ goto handled; } else { diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 41edb2c4a327..a81c41b636f9 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -35,7 +35,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac) #ifdef CONFIG_BATMAN_ADV_BLA bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast); + unsigned short vid, int packet_type); bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); bool batadv_bla_is_backbone_gw(struct sk_buff *skb, @@ -66,7 +66,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, static inline bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, - bool is_bcast) + int packet_type) { return false; } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index bdc4a1fba1c6..ca24a2e522b7 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -51,6 +51,7 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> +#include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" @@ -1435,6 +1436,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } /** + * batadv_mcast_forw_send_orig() - send a multicast packet to an originator + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * @vid: the vlan identifier + * @orig_node: the originator to send the packet to + * + * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. + */ +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + /* Avoid sending multicast-in-unicast packets to other BLA + * gateways - they already got the frame from the LAN side + * we share with them. + * TODO: Refactor to take BLA into account earlier, to avoid + * reducing the mcast_fanout count. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { + dev_kfree_skb(skb); + return NET_XMIT_SUCCESS; + } + + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, + orig_node, vid); +} + +/** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit @@ -1471,8 +1501,8 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_entry->orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, + orig_entry->orig_node); } rcu_read_unlock(); @@ -1513,8 +1543,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1551,8 +1580,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1618,8 +1646,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1656,8 +1683,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index ebf825991ecd..3e114bc5ca3b 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -46,6 +46,11 @@ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **mcast_single_orig); +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node); + int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -72,6 +77,16 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } static inline int +batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + +static inline int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 27cdf5e4349a..9e5c71e406ff 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -826,6 +826,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, vid = batadv_get_vid(skb, hdr_len); ethhdr = (struct ethhdr *)(skb->data + hdr_len); + /* do not reroute multicast frames in a unicast header */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + return true; + /* check if the destination client was served by this node and it is now * roaming. In this case, it means that the node has got a ROAM_ADV * message and that it knows the new destination in the mesh to re-route diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 23833a0ba5e6..cdde943c1b83 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -364,9 +364,8 @@ send: goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); } else if (mcast_single_orig) { - ret = batadv_send_skb_unicast(bat_priv, skb, - BATADV_UNICAST, 0, - mcast_single_orig, vid); + ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, + mcast_single_orig); } else if (forw_mode == BATADV_FORW_SOME) { ret = batadv_mcast_forw_send(bat_priv, skb, vid); } else { @@ -425,10 +424,10 @@ void batadv_interface_rx(struct net_device *soft_iface, struct vlan_ethhdr *vhdr; struct ethhdr *ethhdr; unsigned short vid; - bool is_bcast; + int packet_type; batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data; - is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST); + packet_type = batadv_bcast_packet->packet_type; skb_pull_rcsum(skb, hdr_size); skb_reset_mac_header(skb); @@ -471,7 +470,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + if (batadv_bla_rx(bat_priv, skb, vid, packet_type)) goto out; if (orig_node) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index f9092c71225f..61c94cefa843 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1288,11 +1288,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, } } -static int __br_vlan_get_pvid(const struct net_device *dev, - struct net_bridge_port *p, u16 *p_pvid) +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) @@ -1303,18 +1305,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev, *p_pvid = br_get_pvid(vg); return 0; } - -int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) -{ - ASSERT_RTNL(); - - return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid); -} EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { - return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid); + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); diff --git a/net/core/dev.c b/net/core/dev.c index 4086d335978c..266073e300b5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8647,7 +8647,7 @@ int dev_get_port_parent_id(struct net_device *dev, if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) - return -ENODATA; + return -EOPNOTSUPP; } return err; diff --git a/net/core/dst.c b/net/core/dst.c index d6b6ced0d451..0c01bd8d9d81 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -144,7 +144,7 @@ static void dst_destroy_rcu(struct rcu_head *head) /* Operations to mark dst as DEAD and clean up the net device referenced * by dst: - * 1. put the dst under loopback interface and discard all tx/rx packets + * 1. put the dst under blackhole interface and discard all tx/rx packets * on this route. * 2. release the net_device * This function should be called when removing routes from the fib tree diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 51678a528f85..7bcfb16854cb 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -16,7 +16,7 @@ #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> -#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) diff --git a/net/core/filter.c b/net/core/filter.c index 1f647ab986b6..21eaf3b182f2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4838,6 +4838,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; + fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; @@ -7065,8 +7066,6 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; - /* We're guaranteed here that CTX is in R6. */ - *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { @@ -7074,6 +7073,8 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: @@ -9522,7 +9523,7 @@ BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; @@ -9540,7 +9541,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; @@ -9558,12 +9559,12 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { #ifdef CONFIG_INET - if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) + if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) - if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) + if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif @@ -9582,12 +9583,12 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET - if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) - if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif @@ -9609,7 +9610,7 @@ BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dcd61aca343e..944ab214e5ae 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -251,10 +251,10 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return id; } @@ -264,12 +264,12 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) @@ -534,20 +534,20 @@ static void unhash_nsid(struct net *net, struct net *last) for_each_net(tmp) { int id; - spin_lock(&tmp->nsid_lock); + spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock(&tmp->nsid_lock); + spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); @@ -760,9 +760,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(peer); } - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -771,7 +771,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, } err = alloc_netid(net, peer, nsid); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 84dde5a2066e..16014ad19406 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int prio; int err; if (!ops) @@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, struct dcbnl_buffer *buffer = nla_data(ieee[DCB_ATTR_DCB_BUFFER]); + for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { + if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { + err = -EINVAL; + goto err; + } + } + err = ops->dcbnl_setbuffer(netdev, buffer); if (err) goto err; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 9af1a2d0cec4..16e5f98d4882 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1799,15 +1799,27 @@ int dsa_slave_create(struct dsa_port *port) dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); - ret = register_netdev(slave_dev); + rtnl_lock(); + + ret = register_netdevice(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); + rtnl_unlock(); goto out_phy; } + ret = netdev_upper_dev_link(master, slave_dev, NULL); + + rtnl_unlock(); + + if (ret) + goto out_unregister; + return 0; +out_unregister: + unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1824,16 +1836,18 @@ out_free: void dsa_slave_destroy(struct net_device *slave_dev) { + struct net_device *master = dsa_slave_to_master(slave_dev); struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); netif_carrier_off(slave_dev); rtnl_lock(); + netdev_upper_dev_unlink(master, slave_dev); + unregister_netdevice(slave_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); - unregister_netdev(slave_dev); phylink_destroy(dp->pl); gro_cells_destroy(&p->gcells); free_percpu(p->stats64); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 42f327c06dca..b4fc05cafaa6 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -160,11 +160,14 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; + rew_op = ocelot_port->ptp_cmd; - if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { - rew_op |= (ocelot_port->ts_id % 4) << 3; - ocelot_port->ts_id++; - } + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); } diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 84f23289475b..d93bf2da0f34 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -200,7 +200,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info) reply_len = ret + ethnl_reply_header_size(); rskb = ethnl_reply_init(reply_len, req_info.dev, - ETHTOOL_MSG_TUNNEL_INFO_GET, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, ETHTOOL_A_TUNNEL_INFO_HEADER, info, &reply_payload); if (!rskb) { @@ -273,7 +273,7 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb) goto cont; ehdr = ethnl_dump_put(skb, cb, - ETHTOOL_MSG_TUNNEL_INFO_GET); + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY); if (!ehdr) { ret = -EMSGSIZE; goto out; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 06c3cd988760..0e4681cf71db 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -76,7 +76,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]); if (proto >= HSR_PROTOCOL_MAX) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol\n"); + NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol"); return -EINVAL; } @@ -84,14 +84,14 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, proto_version = HSR_V0; } else { if (proto == HSR_PROTOCOL_PRP) { - NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported\n"); + NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported"); return -EINVAL; } proto_version = nla_get_u8(data[IFLA_HSR_VERSION]); if (proto_version > HSR_V1) { NL_SET_ERR_MSG_MOD(extack, - "Only HSR version 0/1 supported\n"); + "Only HSR version 0/1 supported"); return -EINVAL; } } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 41079490a118..86a23e4a6a50 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -362,6 +362,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 4a98dd736270..f1bd95f243b3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -186,8 +186,8 @@ errout: } EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill); -static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, - struct nlattr **req_nlas) +static int inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr **req_nlas) { struct nlattr *nla; int remaining; @@ -195,9 +195,13 @@ static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) { int type = nla_type(nla); + if (type == INET_DIAG_REQ_PROTOCOL && nla_len(nla) != sizeof(u32)) + return -EINVAL; + if (type < __INET_DIAG_REQ_MAX) req_nlas[type] = nla; } + return 0; } static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req, @@ -574,7 +578,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, int err, protocol; memset(&dump_data, 0, sizeof(dump_data)); - inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); + err = inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); + if (err) + return err; + protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); @@ -1180,8 +1187,11 @@ static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) if (!cb_data) return -ENOMEM; - inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); - + err = inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); + if (err) { + kfree(cb_data); + return err; + } nla = cb_data->inet_diag_nla_bc; if (nla) { err = inet_diag_bc_audit(nla, skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 61f802d5350c..e6f2ada9e7d5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -74,6 +74,7 @@ #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> +#include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> @@ -1703,7 +1704,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, if (IS_ERR(rt)) return; - inet_sk(sk)->tos = arg->tos; + inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 75c6013ff9a4..b2ea1a8c5fd6 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -554,6 +554,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); + md->gbp &= VXLAN_GBP_MASK; info->key.tun_flags |= TUNNEL_VXLAN_OPT; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8ca6bcab7b03..58642b29a499 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -786,8 +786,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, skb); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); @@ -1013,6 +1015,7 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + struct net *net = dev_net(dst->dev); u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; @@ -1033,9 +1036,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) return; rcu_read_lock(); - if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + if (fib_lookup(net, fl4, &res, 0) == 0) { + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, NULL); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } @@ -2147,6 +2152,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; @@ -2667,8 +2673,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); - fl4->flowi4_oif = dev_out->ifindex; - make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 76bff79d6fed..747f56e0c636 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -303,6 +303,7 @@ config IPV6_SEG6_LWTUNNEL config IPV6_SEG6_HMAC bool "IPv6: Segment Routing HMAC support" depends on IPV6 + select CRYPTO select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_SHA256 diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 25a90f3f705c..4a664ad4f4d4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1993,14 +1993,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { - struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, - lockdep_is_held(&rt->fib6_table->tb6_lock)); - struct fib6_table *table = rt->fib6_table; struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; + struct fib6_table *table; + struct fib6_node *fn; + + if (rt == net->ipv6.fib6_null_entry) + return -ENOENT; - if (!fn || rt == net->ipv6.fib6_null_entry) + table = rt->fib6_table; + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5e7e25e2523a..fb075d9545b9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4202,7 +4202,7 @@ static struct fib6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; - cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO, + cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 314973033d03..26d2f8ba7029 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -560,7 +560,9 @@ static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, if (rate->idx < 0 || !rate->count) return -1; - if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) + if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) + stat->bw = RATE_INFO_BW_160; + else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) stat->bw = RATE_INFO_BW_40; @@ -668,20 +670,26 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, * This will not be very accurate, but much better than simply * assuming un-aggregated tx in all cases. */ - if (duration > 400) /* <= VHT20 MCS2 1S */ + if (duration > 400 * 1024) /* <= VHT20 MCS2 1S */ agg_shift = 1; - else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + else if (duration > 250 * 1024) /* <= VHT20 MCS3 1S or MCS1 2S */ agg_shift = 2; - else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + else if (duration > 150 * 1024) /* <= VHT20 MCS5 1S or MCS2 2S */ agg_shift = 3; - else + else if (duration > 70 * 1024) /* <= VHT20 MCS5 2S */ agg_shift = 4; + else if (stat.encoding != RX_ENC_HE || + duration > 20 * 1024) /* <= HE40 MCS6 2S */ + agg_shift = 5; + else + agg_shift = 6; duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; + duration += (overhead >> agg_shift); - return duration + (overhead >> agg_shift); + return max_t(u32, duration, 4); } if (!conf) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ac870309b911..2e400b0ff696 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4861,6 +4861,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; + bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; struct ieee80211_bss *bss = (void *)cbss->priv; int ret; u32 i; @@ -4879,7 +4880,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } - if (!sband->vht_cap.vht_supported && !is_6ghz) { + if (!sband->vht_cap.vht_supported && is_5ghz) { ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 836cde516a18..a959ebf56852 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -451,7 +451,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (status->bw == RATE_INFO_BW_5) channel_flags |= IEEE80211_CHAN_QUARTER; - if (status->band == NL80211_BAND_5GHZ) + if (status->band == NL80211_BAND_5GHZ || + status->band == NL80211_BAND_6GHZ) channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ; else if (status->encoding != RX_ENC_LEGACY) channel_flags |= IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c8504ffc71a1..8d3bfc0fe176 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3353,9 +3353,10 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, he_chandef.center_freq1 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs0, NL80211_BAND_6GHZ); - he_chandef.center_freq2 = - ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, - NL80211_BAND_6GHZ); + if (support_80_80 || support_160) + he_chandef.center_freq2 = + ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, + NL80211_BAND_6GHZ); } if (!cfg80211_chandef_valid(&he_chandef)) { diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 9c6045f9c24d..d1b64d0751f2 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -168,10 +168,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, /* take some capabilities as-is */ cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info); vht_cap->cap = cap_info; - vht_cap->cap &= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | - IEEE80211_VHT_CAP_RXLDPC | + vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_VHT_TXOP_PS | IEEE80211_VHT_CAP_HTC_VHT | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | @@ -180,6 +177,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN | IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN; + vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK, + own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK); + /* and some based on our own capabilities */ switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index ab52811523e9..c829e4a75325 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,11 +34,11 @@ void ieee802154_xmit_worker(struct work_struct *work) if (res) goto err_tx; - ieee802154_xmit_complete(&local->hw, skb, false); - dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + ieee802154_xmit_complete(&local->hw, skb, false); + return; err_tx: @@ -78,6 +78,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) /* async is priority, otherwise sync is fallback */ if (local->ops->xmit_async) { + unsigned int len = skb->len; + ret = drv_xmit_async(local, skb); if (ret) { ieee802154_wake_queue(&local->hw); @@ -85,7 +87,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += len; } else { local->tx_skb = skb; queue_work(local->workqueue, &local->tx_work); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c8820c4156e6..770da3627848 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -66,6 +66,16 @@ static bool addresses_equal(const struct mptcp_addr_info *a, return a->port == b->port; } +static bool address_zero(const struct mptcp_addr_info *addr) +{ + struct mptcp_addr_info zero; + + memset(&zero, 0, sizeof(zero)); + zero.family = addr->family; + + return addresses_equal(addr, &zero, false); +} + static void local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { @@ -171,9 +181,9 @@ static void check_work_pending(struct mptcp_sock *msk) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { + struct mptcp_addr_info remote = { 0 }; struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *local; - struct mptcp_addr_info remote; struct pm_nl_pernet *pernet; pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); @@ -323,10 +333,13 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) * addr */ local_address((struct sock_common *)msk, &msk_local); - local_address((struct sock_common *)msk, &skc_local); + local_address((struct sock_common *)skc, &skc_local); if (addresses_equal(&msk_local, &skc_local, false)) return 0; + if (address_zero(&skc_local)) + return 0; + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); rcu_read_lock(); @@ -341,7 +354,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return ret; /* address not found, add to local list */ - entry = kmalloc(sizeof(*entry), GFP_KERNEL); + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return -ENOMEM; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e8cac2655c82..9ead43f79023 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1063,6 +1063,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct sockaddr_storage addr; + int remote_id = remote->id; int local_id = loc->id; struct socket *sf; struct sock *ssk; @@ -1107,10 +1108,11 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, goto failed; mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u local_id=%d", msk, remote_token, - local_id); + pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, + remote_token, local_id, remote_id); subflow->remote_token = remote_token; subflow->local_id = local_id; + subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = 1; mptcp_info2sockaddr(remote, &addr); @@ -1347,6 +1349,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; new_ctx->local_id = subflow_req->local_id; + new_ctx->remote_id = subflow_req->remote_id; new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 832eabecfbdd..c3a4214dc958 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -851,7 +851,6 @@ static int ctnetlink_done(struct netlink_callback *cb) } struct ctnetlink_filter { - u_int32_t cta_flags; u8 family; u_int32_t orig_flags; @@ -906,10 +905,6 @@ static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_zone *zone, u_int32_t flags); -/* applied on filters */ -#define CTA_FILTER_F_CTA_MARK (1 << 0) -#define CTA_FILTER_F_CTA_MARK_MASK (1 << 1) - static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { @@ -930,14 +925,10 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK); - - if (cda[CTA_MARK_MASK]) { + if (cda[CTA_MARK_MASK]) filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); - filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK); - } else { + else filter->mark.mask = 0xffffffff; - } } else if (cda[CTA_MARK_MASK]) { err = -EINVAL; goto err_filter; @@ -1117,11 +1108,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) && - (ct->mark & filter->mark.mask) != filter->mark.val) - goto ignore_entry; - else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) && - ct->mark != filter->mark.val) + if ((ct->mark & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif @@ -1404,7 +1391,8 @@ ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], if (err < 0) return err; - + if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) + return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 95f79980348c..47e9319d2cf3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net) int err; err = nf_ct_netns_do_get(net, NFPROTO_IPV4); +#if IS_ENABLED(CONFIG_IPV6) if (err < 0) goto err1; err = nf_ct_netns_do_get(net, NFPROTO_IPV6); @@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net) err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: +#endif return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b7dc1cbf40ea..4603b667973a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -684,6 +684,18 @@ nla_put_failure: return -1; } +struct nftnl_skb_parms { + bool report; +}; +#define NFT_CB(skb) (*(struct nftnl_skb_parms*)&((skb)->cb)) + +static void nft_notify_enqueue(struct sk_buff *skb, bool report, + struct list_head *notify_list) +{ + NFT_CB(skb).report = report; + list_add_tail(&skb->list, notify_list); +} + static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct sk_buff *skb; @@ -715,8 +727,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1468,8 +1479,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2807,8 +2817,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3837,8 +3846,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report, - gfp_flags); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -4959,8 +4967,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report, - GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6275,7 +6282,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp); + nft_notify_enqueue(skb, report, &net->nft.notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7085,8 +7092,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7695,6 +7701,41 @@ static void nf_tables_commit_release(struct net *net) mutex_unlock(&net->nft.commit_mutex); } +static void nft_commit_notify(struct net *net, u32 portid) +{ + struct sk_buff *batch_skb = NULL, *nskb, *skb; + unsigned char *data; + int len; + + list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) { + if (!batch_skb) { +new_batch: + batch_skb = skb; + len = NLMSG_GOODSIZE - skb->len; + list_del(&skb->list); + continue; + } + len -= skb->len; + if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) { + data = skb_put(batch_skb, skb->len); + memcpy(data, skb->data, skb->len); + list_del(&skb->list); + kfree_skb(skb); + continue; + } + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + goto new_batch; + } + + if (batch_skb) { + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + } + + WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nft_trans *trans, *next; @@ -7897,6 +7938,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } } + nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_release(net); @@ -8721,6 +8763,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); INIT_LIST_HEAD(&net->nft.module_list); + INIT_LIST_HEAD(&net->nft.notify_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -8737,6 +8780,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); + WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); } static struct pernet_operations nf_tables_net_ops = { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 7bc6537f3ccb..b37bd02448d8 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -147,11 +147,11 @@ nft_meta_get_eval_skugid(enum nft_meta_keys key, switch (key) { case NFT_META_SKUID: - *dest = from_kuid_munged(&init_user_ns, + *dest = from_kuid_munged(sock_net(sk)->user_ns, sock->file->f_cred->fsuid); break; case NFT_META_SKGID: - *dest = from_kgid_munged(&init_user_ns, + *dest = from_kgid_munged(sock_net(sk)->user_ns, sock->file->f_cred->fsgid); break; default: diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 90c558f89d46..957aa9263ba4 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -332,8 +332,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, { struct qrtr_hdr_v1 *hdr; size_t len = skb->len; - int rc = -ENODEV; - int confirm_rx; + int rc, confirm_rx; confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { @@ -357,15 +356,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->size = cpu_to_le32(len); hdr->confirm_rx = !!confirm_rx; - skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); - - mutex_lock(&node->ep_lock); - if (node->ep) - rc = node->ep->xmit(node->ep, skb); - else - kfree_skb(skb); - mutex_unlock(&node->ep_lock); + rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); + if (!rc) { + mutex_lock(&node->ep_lock); + rc = -ENODEV; + if (node->ep) + rc = node->ep->xmit(node->ep, skb); + else + kfree_skb(skb); + mutex_unlock(&node->ep_lock); + } /* Need to ensure that a subsequent message carries the otherwise lost * confirm_rx flag if we dropped this one */ if (rc && confirm_rx) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index c1fcd85719d6..5c568757643b 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } +static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; +} + static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(i, val, len, rtnl_held); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, rtnl_held); + if (err) { + kfree(p); + return err; + } + } + index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { @@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, - tb[TCA_IFE_METALST], NULL, - NULL); - if (err) - goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 536c4bc31be6..37f1e10f35e0 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -156,6 +156,7 @@ tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, struct vxlan_metadata *md = dst; md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; } return sizeof(struct vxlan_metadata); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index a4f7ef1de7e7..fed18fd2c50b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1175,8 +1175,10 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, return -EINVAL; } - if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } return sizeof(*md); } @@ -1221,6 +1223,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, } if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + memset(&md->u, 0x00, sizeof(md->u)); md->u.index = nla_get_be32(nla); } } else if (md->version == 2) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 265a61d011df..54c417244642 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { - bool nolock = qdisc->flags & TCQ_F_NOLOCK; - if (qdisc->flags & TCQ_F_BUILTIN) return; - if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state)) - return; - - if (nolock) - spin_lock_bh(&qdisc->seqlock); - spin_lock_bh(qdisc_lock(qdisc)); set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); - - qdisc_reset(qdisc); - - spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) - spin_unlock_bh(&qdisc->seqlock); } static void dev_deactivate_queue(struct net_device *dev, @@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev, } } +static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; + + qdisc = dev_queue->qdisc_sleeping; + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); +} + static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head) dev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. + /* Wait for outstanding qdisc-less dev_queue_xmit calls or + * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); + list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index fe53c1e38c7d..b0ad7687ee2c 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; -static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, +static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, + struct sched_entry *entry, struct netlink_ext_ack *extack) { + int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) @@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); - if (interval == 0) { + /* The interval should allow at least the minimum ethernet + * frame to go out. + */ + if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } @@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, return 0; } -static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, - int index, struct netlink_ext_ack *extack) +static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, + struct sched_entry *entry, int index, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; @@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, entry->index = index; - return fill_sched_entry(tb, entry, extack); + return fill_sched_entry(q, tb, entry, extack); } -static int parse_sched_list(struct nlattr *list, +static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { @@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list, return -ENOMEM; } - err = parse_sched_entry(n, entry, i, extack); + err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; @@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list, return i; } -static int parse_taprio_schedule(struct nlattr **tb, +static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { @@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb, new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) - err = parse_sched_list( - tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); + err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], + new, extack); if (err < 0) return err; @@ -1473,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - err = parse_taprio_schedule(tb, new_admin, extack); + err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 836615f71a7d..53d0a4161df3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9220,13 +9220,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, static inline void sctp_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { - int ancestor_size = sizeof(struct inet_sock) + - sizeof(struct sctp_sock) - - offsetof(struct sctp_sock, pd_lobby); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); + size_t ancestor_size = sizeof(struct inet_sock); + ancestor_size += sk_from->sk_prot->obj_size; + ancestor_size -= offsetof(struct sctp_sock, pd_lobby); __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index d5805fa1d066..c2752e2b9ce3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -228,7 +228,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek) { struct bvec_iter bi = { - .bi_size = size, + .bi_size = size + seek, }; struct bio_vec bv; diff --git a/net/tipc/group.c b/net/tipc/group.c index 588c2d2b0c69..b1fcd2ad5ecf 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, return NULL; } -static void tipc_group_add_to_tree(struct tipc_group *grp, - struct tipc_member *m) +static int tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; @@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp, else if (key > nkey) n = &(*n)->rb_right; else - return; + return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); + return 0; } static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, @@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, u32 instance, int state) { struct tipc_member *m; + int ret; m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) @@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; + ret = tipc_group_add_to_tree(grp, m); + if (ret < 0) { + kfree(m); + return NULL; + } grp->member_cnt++; - tipc_group_add_to_tree(grp, m); tipc_nlist_add(&grp->dests, m->node); m->state = state; return m; diff --git a/net/tipc/link.c b/net/tipc/link.c index b7362556da95..cef38a910107 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -532,7 +532,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, * tipc_link_bc_create - create new link to be used for broadcast * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers - * @window: send window to be used + * @min_win: minimal send window to be used by link + * @max_win: maximal send window to be used by link * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 848fae674532..52e93ba4d8e2 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -150,7 +150,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - if (unlikely(skb_unclone(frag, GFP_ATOMIC))) + frag = skb_unshare(frag, GFP_ATOMIC); + if (unlikely(!frag)) goto err; head = *headbuf = frag; *buf = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ebd280e767bd..11b27ddc75ba 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2771,10 +2771,7 @@ static int tipc_shutdown(struct socket *sock, int how) trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " "); __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN); - if (tipc_sk_type_connectionless(sk)) - sk->sk_shutdown = SHUTDOWN_MASK; - else - sk->sk_shutdown = SEND_SHUTDOWN; + sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == TIPC_DISCONNECTING) { /* Discard any unreceived messages */ diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index faf74850a1b5..27026f587fa6 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO select CRYPTO_AES select CRYPTO_CCM diff --git a/net/wireless/util.c b/net/wireless/util.c index 4a9ff9ef513f..6fa99df52f86 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -95,7 +95,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) /* see 802.11ax D6.1 27.3.23.2 */ if (chan == 2) return MHZ_TO_KHZ(5935); - if (chan <= 253) + if (chan <= 233) return MHZ_TO_KHZ(5950 + chan * 5); break; case NL80211_BAND_60GHZ: diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index e97db37354e4..b010bfde0149 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -303,10 +303,10 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { + u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom; bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; - u32 chunk_size = mr->chunk_size, headroom = mr->headroom; u64 npgs, addr = mr->addr, size = mr->len; - unsigned int chunks, chunks_per_page; + unsigned int chunks, chunks_rem; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -336,19 +336,18 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if ((addr + size) < addr) return -EINVAL; - npgs = size >> PAGE_SHIFT; + npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem); + if (npgs_rem) + npgs++; if (npgs > U32_MAX) return -EINVAL; - chunks = (unsigned int)div_u64(size, chunk_size); + chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem); if (chunks == 0) return -EINVAL; - if (!unaligned_chunks) { - chunks_per_page = PAGE_SIZE / chunk_size; - if (chunks < chunks_per_page || chunks % chunks_per_page) - return -EINVAL; - } + if (!unaligned_chunks && chunks_rem) + return -EINVAL; if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 0096cd965332..7ecd2ccba531 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -82,6 +82,7 @@ static char *sym_name(const struct sym_entry *s) static bool is_ignored_symbol(const char *name, char type) { + /* Symbol names that exactly match to the following are ignored.*/ static const char * const ignored_symbols[] = { /* * Symbols which vary between passes. Passes 1 and 2 must have @@ -104,6 +105,7 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that begin with the following are ignored.*/ static const char * const ignored_prefixes[] = { "$", /* local symbols for ARM, MIPS, etc. */ ".LASANPC", /* s390 kasan local symbols */ @@ -113,6 +115,7 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that end with the following are ignored.*/ static const char * const ignored_suffixes[] = { "_from_arm", /* arm */ "_from_thumb", /* arm */ @@ -120,9 +123,15 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that contain the following are ignored.*/ + static const char * const ignored_matches[] = { + ".long_branch.", /* ppc stub */ + ".plt_branch.", /* ppc stub */ + NULL + }; + const char * const *p; - /* Exclude symbols which vary between passes. */ for (p = ignored_symbols; *p; p++) if (!strcmp(name, *p)) return true; @@ -138,6 +147,11 @@ static bool is_ignored_symbol(const char *name, char type) return true; } + for (p = ignored_matches; *p; p++) { + if (strstr(name, *p)) + return true; + } + if (type == 'U' || type == 'u') return true; /* exclude debugging symbols */ diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index d4ca8297364f..8454649b17bd 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -66,23 +66,6 @@ static inline void xfwrite(const void *str, size_t len, size_t count, FILE *out) fprintf(stderr, "Error in writing or end of file.\n"); } -/* menu.c */ -void _menu_init(void); -void menu_warn(struct menu *menu, const char *fmt, ...); -struct menu *menu_add_menu(void); -void menu_end_menu(void); -void menu_add_entry(struct symbol *sym); -void menu_add_dep(struct expr *dep); -void menu_add_visibility(struct expr *dep); -struct property *menu_add_prompt(enum prop_type type, char *prompt, struct expr *dep); -void menu_add_expr(enum prop_type type, struct expr *expr, struct expr *dep); -void menu_add_symbol(enum prop_type type, struct symbol *sym, struct expr *dep); -void menu_add_option_modules(void); -void menu_add_option_defconfig_list(void); -void menu_add_option_allnoconfig_y(void); -void menu_finalize(struct menu *parent); -void menu_set_type(int type); - /* util.c */ struct file *file_lookup(const char *name); void *xmalloc(size_t size); @@ -109,6 +92,36 @@ void str_append(struct gstr *gs, const char *s); void str_printf(struct gstr *gs, const char *fmt, ...); const char *str_get(struct gstr *gs); +/* menu.c */ +void _menu_init(void); +void menu_warn(struct menu *menu, const char *fmt, ...); +struct menu *menu_add_menu(void); +void menu_end_menu(void); +void menu_add_entry(struct symbol *sym); +void menu_add_dep(struct expr *dep); +void menu_add_visibility(struct expr *dep); +struct property *menu_add_prompt(enum prop_type type, char *prompt, struct expr *dep); +void menu_add_expr(enum prop_type type, struct expr *expr, struct expr *dep); +void menu_add_symbol(enum prop_type type, struct symbol *sym, struct expr *dep); +void menu_add_option_modules(void); +void menu_add_option_defconfig_list(void); +void menu_add_option_allnoconfig_y(void); +void menu_finalize(struct menu *parent); +void menu_set_type(int type); + +extern struct menu rootmenu; + +bool menu_is_empty(struct menu *menu); +bool menu_is_visible(struct menu *menu); +bool menu_has_prompt(struct menu *menu); +const char *menu_get_prompt(struct menu *menu); +struct menu *menu_get_root_menu(struct menu *menu); +struct menu *menu_get_parent_menu(struct menu *menu); +bool menu_has_help(struct menu *menu); +const char *menu_get_help(struct menu *menu); +struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head); +void menu_get_ext_help(struct menu *menu, struct gstr *help); + /* symbol.c */ void sym_clear_all_valid(void); struct symbol *sym_choice_default(struct symbol *sym); diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index f9ab98238aef..9e81be33c40f 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -12,20 +12,6 @@ bool conf_get_changed(void); void conf_set_changed_callback(void (*fn)(void)); void conf_set_message_callback(void (*fn)(const char *s)); -/* menu.c */ -extern struct menu rootmenu; - -bool menu_is_empty(struct menu *menu); -bool menu_is_visible(struct menu *menu); -bool menu_has_prompt(struct menu *menu); -const char * menu_get_prompt(struct menu *menu); -struct menu * menu_get_root_menu(struct menu *menu); -struct menu * menu_get_parent_menu(struct menu *menu); -bool menu_has_help(struct menu *menu); -const char * menu_get_help(struct menu *menu); -struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head); -void menu_get_ext_help(struct menu *menu, struct gstr *help); - /* symbol.c */ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 8638785328a7..8ce624a3b54b 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -1108,6 +1108,11 @@ void ConfigInfoView::menuInfo(void) if (showDebug()) stream << debug_info(sym); + struct gstr help_gstr = str_new(); + + menu_get_ext_help(_menu, &help_gstr); + stream << print_filter(str_get(&help_gstr)); + str_free(&help_gstr); } else if (_menu->prompt) { stream << "<big><b>"; stream << print_filter(_menu->prompt->text); @@ -1119,11 +1124,11 @@ void ConfigInfoView::menuInfo(void) expr_print_help, &stream, E_NONE); stream << "<br><br>"; } + + stream << "defined at " << _menu->file->name << ":" + << _menu->lineno << "<br><br>"; } } - if (showDebug()) - stream << "defined at " << _menu->file->name << ":" - << _menu->lineno << "<br><br>"; setText(info); } @@ -1276,7 +1281,7 @@ void ConfigInfoView::clicked(const QUrl &url) } free(result); - delete data; + delete[] data; } void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event) diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index 496dcde9715d..9790f5108a16 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -343,7 +343,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, struct hpi_message hm; struct hpi_response hr; struct hpi_adapter adapter; - struct hpi_pci pci; + struct hpi_pci pci = { 0 }; memset(&adapter, 0, sizeof(adapter)); @@ -499,7 +499,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, return 0; err: - for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) { + while (--idx >= 0) { if (pci.ap_mem_base[idx]) { iounmap(pci.ap_mem_base[idx]); pci.ap_mem_base[idx] = NULL; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c521a1f17096..d4f17b465892 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2475,7 +2475,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), - SND_PCI_QUIRK(0x1462, 0x9c37, "MSI X570-A PRO", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), @@ -3428,7 +3427,11 @@ static void alc256_shutup(struct hda_codec *codec) /* 3k pull low control for Headset jack. */ /* NOTE: call this before clearing the pin, otherwise codec stalls */ - alc_update_coef_idx(codec, 0x46, 0, 3 << 12); + /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly + * when booting with headset plugged. So skip setting it for the codec alc257 + */ + if (codec->core.vendor_id != 0x10ec0257) + alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, @@ -5993,6 +5996,40 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec, snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); } + +static void alc294_gx502_toggle_output(struct hda_codec *codec, + struct hda_jack_callback *cb) +{ + /* The Windows driver sets the codec up in a very different way where + * it appears to leave 0x10 = 0x8a20 set. For Linux we need to toggle it + */ + if (snd_hda_jack_detect_state(codec, 0x21) == HDA_JACK_PRESENT) + alc_write_coef_idx(codec, 0x10, 0x8a20); + else + alc_write_coef_idx(codec, 0x10, 0x0a20); +} + +static void alc294_fixup_gx502_hp(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + /* Pin 0x21: headphones/headset mic */ + if (!is_jack_detectable(codec, 0x21)) + return; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_jack_detect_enable_callback(codec, 0x21, + alc294_gx502_toggle_output); + break; + case HDA_FIXUP_ACT_INIT: + /* Make sure to start in a correct state, i.e. if + * headphones have been plugged in before powering up the system + */ + alc294_gx502_toggle_output(codec, NULL); + break; + } +} + static void alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -6017,6 +6054,7 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, #include "hp_x360_helper.c" enum { + ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, ALC275_FIXUP_SONY_VAIO_GPIO2, ALC269_FIXUP_DELL_M101Z, @@ -6173,6 +6211,9 @@ enum { ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, ALC294_FIXUP_ASUS_COEF_1B, + ALC294_FIXUP_ASUS_GX502_HP, + ALC294_FIXUP_ASUS_GX502_PINS, + ALC294_FIXUP_ASUS_GX502_VERBS, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED, @@ -6191,9 +6232,14 @@ enum { ALC269_FIXUP_LEMOTE_A1802, ALC269_FIXUP_LEMOTE_A190X, ALC256_FIXUP_INTEL_NUC8_RUGGED, + ALC255_FIXUP_XIAOMI_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { + [ALC269_FIXUP_GPIO2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_gpio2, + }, [ALC269_FIXUP_SONY_VAIO] = { .type = HDA_FIXUP_PINCTLS, .v.pins = (const struct hda_pintbl[]) { @@ -7013,6 +7059,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC233_FIXUP_LENOVO_MULTI_CODECS] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, + .chained = true, + .chain_id = ALC269_FIXUP_GPIO2 }, [ALC233_FIXUP_ACER_HEADSET_MIC] = { .type = HDA_FIXUP_VERBS, @@ -7338,6 +7386,33 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_GX502_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, /* front HP mic */ + { 0x1a, 0x01a11830 }, /* rear external mic */ + { 0x21, 0x03211020 }, /* front HP out */ + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_GX502_VERBS + }, + [ALC294_FIXUP_ASUS_GX502_VERBS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* set 0x15 to HP-OUT ctrl */ + { 0x15, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc0 }, + /* unmute the 0x15 amp */ + { 0x15, AC_VERB_SET_AMP_GAIN_MUTE, 0xb000 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_GX502_HP + }, + [ALC294_FIXUP_ASUS_GX502_HP] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc294_fixup_gx502_hp, + }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -7527,6 +7602,16 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE }, + [ALC255_FIXUP_XIAOMI_HEADSET_MIC] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 }, + { } + }, + .chained = true, + .chain_id = ALC289_FIXUP_ASUS_GA401 + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7711,6 +7796,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -7823,6 +7909,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI), SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101), SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ + SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), @@ -8000,6 +8087,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"}, {.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"}, {.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"}, + {.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c index 5fe724728e84..e4675cfff7b2 100644 --- a/sound/soc/codecs/max98373-sdw.c +++ b/sound/soc/codecs/max98373-sdw.c @@ -838,8 +838,8 @@ static int max98373_sdw_probe(struct sdw_slave *slave, /* Regmap Initialization */ regmap = devm_regmap_init_sdw(slave, &max98373_sdw_regmap); - if (!regmap) - return -EINVAL; + if (IS_ERR(regmap)) + return PTR_ERR(regmap); return max98373_init(slave, regmap); } diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c index 5e445fee4ef5..821e7395f90f 100644 --- a/sound/soc/codecs/pcm3168a.c +++ b/sound/soc/codecs/pcm3168a.c @@ -306,6 +306,13 @@ static int pcm3168a_set_dai_sysclk(struct snd_soc_dai *dai, struct pcm3168a_priv *pcm3168a = snd_soc_component_get_drvdata(dai->component); int ret; + /* + * Some sound card sets 0 Hz as reset, + * but it is impossible to set. Ignore it here + */ + if (freq == 0) + return 0; + if (freq > PCM3168A_MAX_SYSCLK) return -EINVAL; diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c index b0ba0d2acbdd..56e952a904a3 100644 --- a/sound/soc/codecs/rt1308-sdw.c +++ b/sound/soc/codecs/rt1308-sdw.c @@ -684,8 +684,8 @@ static int rt1308_sdw_probe(struct sdw_slave *slave, /* Regmap Initialization */ regmap = devm_regmap_init_sdw(slave, &rt1308_sdw_regmap); - if (!regmap) - return -EINVAL; + if (IS_ERR(regmap)) + return PTR_ERR(regmap); rt1308_sdw_init(&slave->dev, regmap, slave); diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c index 4d14048d1197..1d24bf040718 100644 --- a/sound/soc/codecs/rt700-sdw.c +++ b/sound/soc/codecs/rt700-sdw.c @@ -452,8 +452,8 @@ static int rt700_sdw_probe(struct sdw_slave *slave, /* Regmap Initialization */ sdw_regmap = devm_regmap_init_sdw(slave, &rt700_sdw_regmap); - if (!sdw_regmap) - return -EINVAL; + if (IS_ERR(sdw_regmap)) + return PTR_ERR(sdw_regmap); regmap = devm_regmap_init(&slave->dev, NULL, &slave->dev, &rt700_regmap); diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c index 45b928954b58..7efff130a638 100644 --- a/sound/soc/codecs/rt711-sdw.c +++ b/sound/soc/codecs/rt711-sdw.c @@ -452,8 +452,8 @@ static int rt711_sdw_probe(struct sdw_slave *slave, /* Regmap Initialization */ sdw_regmap = devm_regmap_init_sdw(slave, &rt711_sdw_regmap); - if (!sdw_regmap) - return -EINVAL; + if (IS_ERR(sdw_regmap)) + return PTR_ERR(sdw_regmap); regmap = devm_regmap_init(&slave->dev, NULL, &slave->dev, &rt711_regmap); diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index d11b23d6b240..68a36739f1b0 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -527,8 +527,8 @@ static int rt715_sdw_probe(struct sdw_slave *slave, /* Regmap Initialization */ sdw_regmap = devm_regmap_init_sdw(slave, &rt715_sdw_regmap); - if (!sdw_regmap) - return -EINVAL; + if (IS_ERR(sdw_regmap)) + return PTR_ERR(sdw_regmap); regmap = devm_regmap_init(&slave->dev, NULL, &slave->dev, &rt715_regmap); diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 5cd50d841177..8efe20605f9b 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -842,6 +842,18 @@ static int adcx140_codec_probe(struct snd_soc_component *component) if (ret) goto out; + if (adcx140->supply_areg == NULL) + sleep_cfg_val |= ADCX140_AREG_INTERNAL; + + ret = regmap_write(adcx140->regmap, ADCX140_SLEEP_CFG, sleep_cfg_val); + if (ret) { + dev_err(adcx140->dev, "setting sleep config failed %d\n", ret); + goto out; + } + + /* 8.4.3: Wait >= 1ms after entering active mode. */ + usleep_range(1000, 100000); + pdm_count = device_property_count_u32(adcx140->dev, "ti,pdm-edge-select"); if (pdm_count <= ADCX140_NUM_PDM_EDGES && pdm_count > 0) { @@ -889,18 +901,6 @@ static int adcx140_codec_probe(struct snd_soc_component *component) if (ret) goto out; - if (adcx140->supply_areg == NULL) - sleep_cfg_val |= ADCX140_AREG_INTERNAL; - - ret = regmap_write(adcx140->regmap, ADCX140_SLEEP_CFG, sleep_cfg_val); - if (ret) { - dev_err(adcx140->dev, "setting sleep config failed %d\n", ret); - goto out; - } - - /* 8.4.3: Wait >= 1ms after entering active mode. */ - usleep_range(1000, 100000); - ret = regmap_update_bits(adcx140->regmap, ADCX140_BIAS_CFG, ADCX140_MIC_BIAS_VAL_MSK | ADCX140_MIC_BIAS_VREF_MSK, bias_cfg); @@ -980,6 +980,8 @@ static int adcx140_i2c_probe(struct i2c_client *i2c, if (!adcx140) return -ENOMEM; + adcx140->dev = &i2c->dev; + adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(adcx140->gpio_reset)) @@ -1007,7 +1009,7 @@ static int adcx140_i2c_probe(struct i2c_client *i2c, ret); return ret; } - adcx140->dev = &i2c->dev; + i2c_set_clientdata(i2c, adcx140); return devm_snd_soc_register_component(&i2c->dev, diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 038be667c1a6..fc9ea198ac79 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -3514,6 +3514,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * return -EINVAL; } + pm_runtime_get_sync(component->dev); + switch (micbias) { case 1: micdet = &wm8994->micdet[0]; @@ -3561,6 +3563,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * snd_soc_dapm_sync(dapm); + pm_runtime_put(component->dev); + return 0; } EXPORT_SYMBOL_GPL(wm8994_mic_detect); @@ -3932,6 +3936,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * return -EINVAL; } + pm_runtime_get_sync(component->dev); + if (jack) { snd_soc_dapm_force_enable_pin(dapm, "CLK_SYS"); snd_soc_dapm_sync(dapm); @@ -4000,6 +4006,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * snd_soc_dapm_sync(dapm); } + pm_runtime_put(component->dev); + return 0; } EXPORT_SYMBOL_GPL(wm8958_mic_detect); @@ -4193,11 +4201,13 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994->hubs.dcs_readback_mode = 2; break; } + wm8994->hubs.micd_scthr = true; break; case WM8958: wm8994->hubs.dcs_readback_mode = 1; wm8994->hubs.hp_startup_mode = 1; + wm8994->hubs.micd_scthr = true; switch (control->revision) { case 0: diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c index 891effe220fe..0c881846f485 100644 --- a/sound/soc/codecs/wm_hubs.c +++ b/sound/soc/codecs/wm_hubs.c @@ -1223,6 +1223,9 @@ int wm_hubs_handle_analogue_pdata(struct snd_soc_component *component, snd_soc_component_update_bits(component, WM8993_ADDITIONAL_CONTROL, WM8993_LINEOUT2_FB, WM8993_LINEOUT2_FB); + if (!hubs->micd_scthr) + return 0; + snd_soc_component_update_bits(component, WM8993_MICBIAS, WM8993_JD_SCTHR_MASK | WM8993_JD_THR_MASK | WM8993_MICB1_LVL | WM8993_MICB2_LVL, diff --git a/sound/soc/codecs/wm_hubs.h b/sound/soc/codecs/wm_hubs.h index 4b8e5f0d6e32..988b29e63060 100644 --- a/sound/soc/codecs/wm_hubs.h +++ b/sound/soc/codecs/wm_hubs.h @@ -27,6 +27,7 @@ struct wm_hubs_data { int hp_startup_mode; int series_startup; int no_series_update; + bool micd_scthr; bool no_cache_dac_hp_direct; struct list_head dcs_cache; diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index b1cac7abdc0a..fba2c795ce0d 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -333,6 +333,17 @@ static int sst_media_open(struct snd_pcm_substream *substream, if (ret_val < 0) goto out_power_up; + /* + * Make sure the period to be multiple of 1ms to align the + * design of firmware. Apply same rule to buffer size to make + * sure alsa could always find a value for period size + * regardless the buffer size given by user space. + */ + snd_pcm_hw_constraint_step(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 48); + snd_pcm_hw_constraint_step(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_BUFFER_SIZE, 48); + /* Make sure, that the period size is always even */ snd_pcm_hw_constraint_step(substream->runtime, 0, SNDRV_PCM_HW_PARAM_PERIODS, 2); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 479992f4e97a..fc202747ba83 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -591,6 +591,16 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* MPMAN Converter 9, similar hw as the I.T.Works TW891 2-in-1 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"), + DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* MPMAN MPWIN895CL */ .matches = { diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c index ca4900036ead..bc50eda297ab 100644 --- a/sound/soc/intel/boards/skl_hda_dsp_generic.c +++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c @@ -181,7 +181,7 @@ static void skl_set_hda_codec_autosuspend_delay(struct snd_soc_card *card) struct snd_soc_dai *dai; for_each_card_rtds(card, rtd) { - if (!strstr(rtd->dai_link->codecs->name, "ehdaudio")) + if (!strstr(rtd->dai_link->codecs->name, "ehdaudio0D0")) continue; dai = asoc_rtd_to_codec(rtd, 0); hda_pvt = snd_soc_component_get_drvdata(dai->component); diff --git a/sound/soc/intel/boards/sof_maxim_common.c b/sound/soc/intel/boards/sof_maxim_common.c index 1a6961592029..b6e63ea13d64 100644 --- a/sound/soc/intel/boards/sof_maxim_common.c +++ b/sound/soc/intel/boards/sof_maxim_common.c @@ -66,6 +66,10 @@ int max98373_trigger(struct snd_pcm_substream *substream, int cmd) int j; int ret = 0; + /* set spk pin by playback only */ + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) + return 0; + for_each_rtd_codec_dais(rtd, j, codec_dai) { struct snd_soc_component *component = codec_dai->component; struct snd_soc_dapm_context *dapm = @@ -86,9 +90,6 @@ int max98373_trigger(struct snd_pcm_substream *substream, int cmd) case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - /* Make sure no streams are active before disable pin */ - if (snd_soc_dai_active(codec_dai) != 1) - break; ret = snd_soc_dapm_disable_pin(dapm, pin_name); if (!ret) snd_soc_dapm_sync(dapm); diff --git a/sound/soc/intel/haswell/sst-haswell-dsp.c b/sound/soc/intel/haswell/sst-haswell-dsp.c index de80e19454c1..88c3f63bded9 100644 --- a/sound/soc/intel/haswell/sst-haswell-dsp.c +++ b/sound/soc/intel/haswell/sst-haswell-dsp.c @@ -243,92 +243,45 @@ static irqreturn_t hsw_irq(int irq, void *context) return ret; } -#define CSR_DEFAULT_VALUE 0x8480040E -#define ISC_DEFAULT_VALUE 0x0 -#define ISD_DEFAULT_VALUE 0x0 -#define IMC_DEFAULT_VALUE 0x7FFF0003 -#define IMD_DEFAULT_VALUE 0x7FFF0003 -#define IPCC_DEFAULT_VALUE 0x0 -#define IPCD_DEFAULT_VALUE 0x0 -#define CLKCTL_DEFAULT_VALUE 0x7FF -#define CSR2_DEFAULT_VALUE 0x0 -#define LTR_CTRL_DEFAULT_VALUE 0x0 -#define HMD_CTRL_DEFAULT_VALUE 0x0 - -static void hsw_set_shim_defaults(struct sst_dsp *sst) -{ - sst_dsp_shim_write_unlocked(sst, SST_CSR, CSR_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_ISRX, ISC_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_ISRD, ISD_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_IMRX, IMC_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_IMRD, IMD_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_IPCX, IPCC_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_IPCD, IPCD_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_CLKCTL, CLKCTL_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_CSR2, CSR2_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_LTRC, LTR_CTRL_DEFAULT_VALUE); - sst_dsp_shim_write_unlocked(sst, SST_HMDC, HMD_CTRL_DEFAULT_VALUE); -} - -/* all clock-gating minus DCLCGE and DTCGE */ -#define SST_VDRTCL2_CG_OTHER 0xB7D - static void hsw_set_dsp_D3(struct sst_dsp *sst) { + u32 val; u32 reg; - /* disable clock core gating */ + /* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */ reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg &= ~(SST_VDRTCL2_DCLCGE); + reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE); writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); - /* stall, reset and set 24MHz XOSC */ - sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, - SST_CSR_24MHZ_LPCS | SST_CSR_STALL | SST_CSR_RST, - SST_CSR_24MHZ_LPCS | SST_CSR_STALL | SST_CSR_RST); - - /* DRAM power gating all */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0); - reg |= SST_VDRTCL0_ISRAMPGE_MASK | - SST_VDRTCL0_DSRAMPGE_MASK; - reg &= ~(SST_VDRTCL0_D3SRAMPGD); - reg |= SST_VDRTCL0_D3PGD; - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0); - udelay(50); + /* enable power gating and switch off DRAM & IRAM blocks */ + val = readl(sst->addr.pci_cfg + SST_VDRTCTL0); + val |= SST_VDRTCL0_DSRAMPGE_MASK | + SST_VDRTCL0_ISRAMPGE_MASK; + val &= ~(SST_VDRTCL0_D3PGD | SST_VDRTCL0_D3SRAMPGD); + writel(val, sst->addr.pci_cfg + SST_VDRTCTL0); - /* PLL shutdown enable */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_APLLSE_MASK; - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); + /* switch off audio PLL */ + val = readl(sst->addr.pci_cfg + SST_VDRTCTL2); + val |= SST_VDRTCL2_APLLSE_MASK; + writel(val, sst->addr.pci_cfg + SST_VDRTCTL2); - /* disable MCLK */ + /* disable MCLK(clkctl.smos = 0) */ sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL, - SST_CLKCTL_MASK, 0); - - /* switch clock gating */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_CG_OTHER; - reg &= ~(SST_VDRTCL2_DTCGE); - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); - /* enable DTCGE separatelly */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_DTCGE; - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); + SST_CLKCTL_MASK, 0); - /* set shim defaults */ - hsw_set_shim_defaults(sst); - - /* set D3 */ - reg = readl(sst->addr.pci_cfg + SST_PMCS); - reg |= SST_PMCS_PS_MASK; - writel(reg, sst->addr.pci_cfg + SST_PMCS); + /* Set D3 state, delay 50 us */ + val = readl(sst->addr.pci_cfg + SST_PMCS); + val |= SST_PMCS_PS_MASK; + writel(val, sst->addr.pci_cfg + SST_PMCS); udelay(50); - /* enable clock core gating */ + /* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */ reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_DCLCGE; + reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE; writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); + udelay(50); + } static void hsw_reset(struct sst_dsp *sst) @@ -346,62 +299,75 @@ static void hsw_reset(struct sst_dsp *sst) SST_CSR_RST | SST_CSR_STALL, SST_CSR_STALL); } -/* recommended CSR state for power-up */ -#define SST_CSR_D0_MASK (0x18A09C0C | SST_CSR_DCS_MASK) - static int hsw_set_dsp_D0(struct sst_dsp *sst) { - u32 reg; + int tries = 10; + u32 reg, fw_dump_bit; - /* disable clock core gating */ + /* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */ reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg &= ~(SST_VDRTCL2_DCLCGE); + reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE); writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); - /* switch clock gating */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_CG_OTHER; - reg &= ~(SST_VDRTCL2_DTCGE); - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); + /* Disable D3PG (VDRTCTL0.D3PGD = 1) */ + reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0); + reg |= SST_VDRTCL0_D3PGD; + writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0); - /* set D0 */ + /* Set D0 state */ reg = readl(sst->addr.pci_cfg + SST_PMCS); - reg &= ~(SST_PMCS_PS_MASK); + reg &= ~SST_PMCS_PS_MASK; writel(reg, sst->addr.pci_cfg + SST_PMCS); - /* DRAM power gating none */ - reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0); - reg &= ~(SST_VDRTCL0_ISRAMPGE_MASK | - SST_VDRTCL0_DSRAMPGE_MASK); - reg |= SST_VDRTCL0_D3SRAMPGD; - reg |= SST_VDRTCL0_D3PGD; - writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0); - mdelay(10); + /* check that ADSP shim is enabled */ + while (tries--) { + reg = readl(sst->addr.pci_cfg + SST_PMCS) & SST_PMCS_PS_MASK; + if (reg == 0) + goto finish; + + msleep(1); + } + + return -ENODEV; - /* set shim defaults */ - hsw_set_shim_defaults(sst); +finish: + /* select SSP1 19.2MHz base clock, SSP clock 0, turn off Low Power Clock */ + sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, + SST_CSR_S1IOCS | SST_CSR_SBCS1 | SST_CSR_LPCS, 0x0); + + /* stall DSP core, set clk to 192/96Mhz */ + sst_dsp_shim_update_bits_unlocked(sst, + SST_CSR, SST_CSR_STALL | SST_CSR_DCS_MASK, + SST_CSR_STALL | SST_CSR_DCS(4)); - /* restore MCLK */ + /* Set 24MHz MCLK, prevent local clock gating, enable SSP0 clock */ sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL, - SST_CLKCTL_MASK, SST_CLKCTL_MASK); + SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0, + SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0); - /* PLL shutdown disable */ + /* Stall and reset core, set CSR */ + hsw_reset(sst); + + /* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */ reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg &= ~(SST_VDRTCL2_APLLSE_MASK); + reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE; writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); - sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, - SST_CSR_D0_MASK, SST_CSR_SBCS0 | SST_CSR_SBCS1 | - SST_CSR_STALL | SST_CSR_DCS(4)); udelay(50); - /* enable clock core gating */ + /* switch on audio PLL */ reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2); - reg |= SST_VDRTCL2_DCLCGE; + reg &= ~SST_VDRTCL2_APLLSE_MASK; writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2); - /* clear reset */ - sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, SST_CSR_RST, 0); + /* set default power gating control, enable power gating control for all blocks. that is, + can't be accessed, please enable each block before accessing. */ + reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0); + reg |= SST_VDRTCL0_DSRAMPGE_MASK | SST_VDRTCL0_ISRAMPGE_MASK; + /* for D0, always enable the block(DSRAM[0]) used for FW dump */ + fw_dump_bit = 1 << SST_VDRTCL0_DSRAMPGE_SHIFT; + writel(reg & ~fw_dump_bit, sst->addr.pci_cfg + SST_VDRTCTL0); + /* disable DMA finish function for SSP0 & SSP1 */ sst_dsp_shim_update_bits_unlocked(sst, SST_CSR2, SST_CSR2_SDFD_SSP1, @@ -418,6 +384,12 @@ static int hsw_set_dsp_D0(struct sst_dsp *sst) sst_dsp_shim_update_bits(sst, SST_IMRD, (SST_IMRD_DONE | SST_IMRD_BUSY | SST_IMRD_SSP0 | SST_IMRD_DMAC), 0x0); + /* clear IPC registers */ + sst_dsp_shim_write(sst, SST_IPCX, 0x0); + sst_dsp_shim_write(sst, SST_IPCD, 0x0); + sst_dsp_shim_write(sst, 0x80, 0x6); + sst_dsp_shim_write(sst, 0xe0, 0x300a); + return 0; } @@ -443,6 +415,11 @@ static void hsw_sleep(struct sst_dsp *sst) { dev_dbg(sst->dev, "HSW_PM dsp runtime suspend\n"); + /* put DSP into reset and stall */ + sst_dsp_shim_update_bits(sst, SST_CSR, + SST_CSR_24MHZ_LPCS | SST_CSR_RST | SST_CSR_STALL, + SST_CSR_RST | SST_CSR_STALL | SST_CSR_24MHZ_LPCS); + hsw_set_dsp_D3(sst); dev_dbg(sst->dev, "HSW_PM dsp runtime suspend exit\n"); } diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c index e711abcf8c12..d6adf7edea41 100644 --- a/sound/soc/meson/axg-toddr.c +++ b/sound/soc/meson/axg-toddr.c @@ -18,6 +18,7 @@ #define CTRL0_TODDR_SEL_RESAMPLE BIT(30) #define CTRL0_TODDR_EXT_SIGNED BIT(29) #define CTRL0_TODDR_PP_MODE BIT(28) +#define CTRL0_TODDR_SYNC_CH BIT(27) #define CTRL0_TODDR_TYPE_MASK GENMASK(15, 13) #define CTRL0_TODDR_TYPE(x) ((x) << 13) #define CTRL0_TODDR_MSB_POS_MASK GENMASK(12, 8) @@ -189,10 +190,31 @@ static const struct axg_fifo_match_data axg_toddr_match_data = { .dai_drv = &axg_toddr_dai_drv }; +static int g12a_toddr_dai_startup(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai); + int ret; + + ret = axg_toddr_dai_startup(substream, dai); + if (ret) + return ret; + + /* + * Make sure the first channel ends up in the at beginning of the output + * As weird as it looks, without this the first channel may be misplaced + * in memory, with a random shift of 2 channels. + */ + regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_SYNC_CH, + CTRL0_TODDR_SYNC_CH); + + return 0; +} + static const struct snd_soc_dai_ops g12a_toddr_ops = { .prepare = g12a_toddr_dai_prepare, .hw_params = axg_toddr_dai_hw_params, - .startup = axg_toddr_dai_startup, + .startup = g12a_toddr_dai_startup, .shutdown = axg_toddr_dai_shutdown, }; diff --git a/sound/soc/qcom/apq8016_sbc.c b/sound/soc/qcom/apq8016_sbc.c index 083413abc2f6..575e2aefefe3 100644 --- a/sound/soc/qcom/apq8016_sbc.c +++ b/sound/soc/qcom/apq8016_sbc.c @@ -143,6 +143,7 @@ static int apq8016_sbc_platform_probe(struct platform_device *pdev) card = &data->card; card->dev = dev; + card->owner = THIS_MODULE; card->dapm_widgets = apq8016_sbc_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(apq8016_sbc_dapm_widgets); diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c index 253549600c5a..1a69baefc5ce 100644 --- a/sound/soc/qcom/apq8096.c +++ b/sound/soc/qcom/apq8096.c @@ -114,6 +114,7 @@ static int apq8096_platform_probe(struct platform_device *pdev) return -ENOMEM; card->dev = dev; + card->owner = THIS_MODULE; dev_set_drvdata(dev, card); ret = qcom_snd_parse_of(card); if (ret) diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index 5194d90ddb96..fd69cf8b1f23 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -52,8 +52,10 @@ int qcom_snd_parse_of(struct snd_soc_card *card) for_each_child_of_node(dev->of_node, np) { dlc = devm_kzalloc(dev, 2 * sizeof(*dlc), GFP_KERNEL); - if (!dlc) - return -ENOMEM; + if (!dlc) { + ret = -ENOMEM; + goto err; + } link->cpus = &dlc[0]; link->platforms = &dlc[1]; diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index 0d10fba53945..ab1bf23c21a6 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -555,6 +555,7 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev) card->dapm_widgets = sdm845_snd_widgets; card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets); card->dev = dev; + card->owner = THIS_MODULE; dev_set_drvdata(dev, card); ret = qcom_snd_parse_of(card); if (ret) diff --git a/sound/soc/qcom/storm.c b/sound/soc/qcom/storm.c index c0c388d4db82..80c9cf2f254a 100644 --- a/sound/soc/qcom/storm.c +++ b/sound/soc/qcom/storm.c @@ -96,6 +96,7 @@ static int storm_platform_probe(struct platform_device *pdev) return -ENOMEM; card->dev = &pdev->dev; + card->owner = THIS_MODULE; ret = snd_soc_of_parse_card_name(card, "qcom,model"); if (ret) { diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 663e3839f251..054437660678 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -834,6 +834,19 @@ struct snd_soc_dai *snd_soc_find_dai( } EXPORT_SYMBOL_GPL(snd_soc_find_dai); +struct snd_soc_dai *snd_soc_find_dai_with_mutex( + const struct snd_soc_dai_link_component *dlc) +{ + struct snd_soc_dai *dai; + + mutex_lock(&client_mutex); + dai = snd_soc_find_dai(dlc); + mutex_unlock(&client_mutex); + + return dai; +} +EXPORT_SYMBOL_GPL(snd_soc_find_dai_with_mutex); + static int soc_dai_link_sanity_check(struct snd_soc_card *card, struct snd_soc_dai_link *link) { diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index 91a2551e4cef..0dbd312aad08 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -412,14 +412,14 @@ void snd_soc_dai_link_set_capabilities(struct snd_soc_dai_link *dai_link) supported_codec = false; for_each_link_cpus(dai_link, i, cpu) { - dai = snd_soc_find_dai(cpu); + dai = snd_soc_find_dai_with_mutex(cpu); if (dai && snd_soc_dai_stream_valid(dai, direction)) { supported_cpu = true; break; } } for_each_link_codecs(dai_link, i, codec) { - dai = snd_soc_find_dai(codec); + dai = snd_soc_find_dai_with_mutex(codec); if (dai && snd_soc_dai_stream_valid(dai, direction)) { supported_codec = true; break; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 00ac1cbf6f88..4c9d4cd8cf0b 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -812,7 +812,7 @@ dynamic: return 0; config_err: - for_each_rtd_dais(rtd, i, dai) + for_each_rtd_dais_rollback(rtd, i, dai) snd_soc_dai_shutdown(dai, substream); snd_soc_link_shutdown(substream); diff --git a/sound/soc/ti/ams-delta.c b/sound/soc/ti/ams-delta.c index 5c47de96c529..57feb473a579 100644 --- a/sound/soc/ti/ams-delta.c +++ b/sound/soc/ti/ams-delta.c @@ -446,12 +446,12 @@ static const struct snd_soc_dai_ops ams_delta_dai_ops = { /* Will be used if the codec ever has its own digital_mute function */ static int ams_delta_startup(struct snd_pcm_substream *substream) { - return ams_delta_digital_mute(NULL, 0, substream->stream); + return ams_delta_mute(NULL, 0, substream->stream); } static void ams_delta_shutdown(struct snd_pcm_substream *substream) { - ams_delta_digital_mute(NULL, 1, substream->stream); + ams_delta_mute(NULL, 1, substream->stream); } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 5b43e9e40e49..c369c81e74c4 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -371,7 +371,6 @@ static const struct usbmix_name_map asus_rog_map[] = { }; static const struct usbmix_name_map lenovo_p620_rear_map[] = { - { 19, NULL, 2 }, /* FU, Volume */ { 19, NULL, 12 }, /* FU, Input Gain Pad */ {} }; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 75bbdc691243..892296df131d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1678,12 +1678,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny - * delay here, otherwise requests like get/set frequency return as - * failed despite actually succeeding. + /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX + * needs a tiny delay here, otherwise requests like get/set + * frequency return as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || + chip->usb_id == USB_ID(0x046d, 0x0a56) || chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 56284b98d8f0..d295e406a756 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -137,6 +137,31 @@ $BOOTCONF $INITRD > $TEMPCONF cat $TEMPCONF xpass grep \'\"string\"\' $TEMPCONF +echo "Repeat same-key tree" +cat > $TEMPCONF << EOF +foo +bar +foo { buz } +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xpass grep -q "bar" $OUTFILE + + +echo "Remove/keep tailing spaces" +cat > $TEMPCONF << EOF +foo = val # comment +bar = "val2 " # comment +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xfail grep -q val[[:space:]] $OUTFILE +xpass grep -q val2[[:space:]] $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 0a6d09a3e91f..39bb322707b4 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean runqslower_clean +clean: bpftool_clean runqslower_clean resolve_btfids_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index a88cd4426398..fe8eb537688b 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -80,6 +80,7 @@ libbpf-clean: clean: libsubcmd-clean libbpf-clean fixdep-clean $(call msg,CLEAN,$(BINARY)) $(Q)$(RM) -f $(BINARY); \ + $(RM) -rf $(if $(OUTPUT),$(OUTPUT),.)/feature; \ find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) tags: diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c index 0f257139b003..7703f0118385 100644 --- a/tools/io_uring/io_uring-bench.c +++ b/tools/io_uring/io_uring-bench.c @@ -130,7 +130,7 @@ static int io_uring_register_files(struct submitter *s) s->nr_files); } -static int gettid(void) +static int lk_gettid(void) { return syscall(__NR_gettid); } @@ -281,7 +281,7 @@ static void *submitter_fn(void *data) struct io_sq_ring *ring = &s->sq_ring; int ret, prepped; - printf("submitter=%d\n", gettid()); + printf("submitter=%d\n", lk_gettid()); srand48_r(pthread_self(), &s->rand); diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index bf8ed134cb8a..9ae8f4ef0aac 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -59,7 +59,7 @@ FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray FEATURE_DISPLAY = libelf zlib bpf -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) check_feat := 1 @@ -152,6 +152,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -219,6 +220,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0ad0b0491e1f..7253b833576c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -5203,8 +5203,8 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; + struct bpf_map *map = NULL, *targ_map; const struct btf_member *member; - struct bpf_map *map, *targ_map; const char *name, *mname; Elf_Data *symbols; unsigned int moff; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e034a8f24f46..90a66891441a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -619,7 +619,7 @@ static int add_jump_destinations(struct objtool_file *file) if (!is_static_jump(insn)) continue; - if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) + if (insn->offset == FAKE_JUMP_OFFSET) continue; reloc = find_reloc_by_dest_range(file->elf, insn->sec, diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c index 07ddbfdbcab7..6dfce3fd68bc 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -47,7 +47,10 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) __u32 seq_num = ctx->meta->seq_num; struct bpf_map *map = ctx->map; struct key_t *key = ctx->key; + struct key_t tmp_key; __u64 *val = ctx->value; + __u64 tmp_val = 0; + int ret; if (in_test_mode) { /* test mode is used by selftests to @@ -61,6 +64,18 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) if (key == (void *)0 || val == (void *)0) return 0; + /* update the value and then delete the <key, value> pair. + * it should not impact the existing 'val' which is still + * accessible under rcu. + */ + __builtin_memcpy(&tmp_key, key, sizeof(struct key_t)); + ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0); + if (ret) + return 0; + ret = bpf_map_delete_elem(&hashmap1, &tmp_key); + if (ret) + return 0; + key_sum_a += key->a; key_sum_b += key->b; key_sum_c += key->c; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index b8d14f9db5f9..2fc6b3af81a1 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -73,7 +73,7 @@ int main(void) int i; /* Instruction lengths starting at ss_start */ int ss_size[4] = { - 3, /* xor */ + 2, /* xor */ 2, /* cpuid */ 5, /* mov */ 2, /* rdmsr */ diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 7c38a909f8b8..8a2fe6d64bf2 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -1175,6 +1175,51 @@ kci_test_neigh_get() echo "PASS: neigh get" } +kci_test_bridge_parent_id() +{ + local ret=0 + sysfsnet=/sys/bus/netdevsim/devices/netdevsim + probed=false + + if [ ! -w /sys/bus/netdevsim/new_device ] ; then + modprobe -q netdevsim + check_err $? + if [ $ret -ne 0 ]; then + echo "SKIP: bridge_parent_id can't load netdevsim" + return $ksft_skip + fi + probed=true + fi + + echo "10 1" > /sys/bus/netdevsim/new_device + while [ ! -d ${sysfsnet}10 ] ; do :; done + echo "20 1" > /sys/bus/netdevsim/new_device + while [ ! -d ${sysfsnet}20 ] ; do :; done + udevadm settle + dev10=`ls ${sysfsnet}10/net/` + dev20=`ls ${sysfsnet}20/net/` + + ip link add name test-bond0 type bond mode 802.3ad + ip link set dev $dev10 master test-bond0 + ip link set dev $dev20 master test-bond0 + ip link add name test-br0 type bridge + ip link set dev test-bond0 master test-br0 + check_err $? + + # clean up any leftovers + ip link del dev test-br0 + ip link del dev test-bond0 + echo 20 > /sys/bus/netdevsim/del_device + echo 10 > /sys/bus/netdevsim/del_device + $probed && rmmod netdevsim + + if [ $ret -ne 0 ]; then + echo "FAIL: bridge_parent_id" + return 1 + fi + echo "PASS: bridge_parent_id" +} + kci_test_rtnl() { local ret=0 @@ -1224,6 +1269,8 @@ kci_test_rtnl() check_err $? kci_test_neigh_get check_err $? + kci_test_bridge_parent_id + check_err $? kci_del_dummy return $ret diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c index e0cf8ebbf8cd..30b71b1d78d5 100644 --- a/tools/testing/selftests/powerpc/mm/prot_sao.c +++ b/tools/testing/selftests/powerpc/mm/prot_sao.c @@ -7,6 +7,7 @@ #include <stdlib.h> #include <string.h> #include <sys/mman.h> +#include <unistd.h> #include <asm/cputable.h> @@ -18,9 +19,13 @@ int test_prot_sao(void) { char *p; - /* SAO was introduced in 2.06 and removed in 3.1 */ + /* + * SAO was introduced in 2.06 and removed in 3.1. It's disabled in + * guests/LPARs by default, so also skip if we are running in a guest. + */ SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) || - have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + have_hwcap2(PPC_FEATURE2_ARCH_3_1) || + access("/proc/device-tree/rtas/ibm,hypertas-functions", F_OK) == 0); /* * Ensure we can ask for PROT_SAO. diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c index 6af951900aa3..312889edb84a 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/vm/map_hugetlb.c @@ -83,7 +83,7 @@ int main(int argc, char **argv) } if (shift) - printf("%u kB hugepages\n", 1 << shift); + printf("%u kB hugepages\n", 1 << (shift - 10)); else printf("Default size hugepages\n"); printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20); |