From 07fd5b6cdf3cc30bfde8fe0f644771688be04447 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 13 Jun 2022 12:19:50 -1000 Subject: cgroup: Use separate src/dst nodes when preloading css_sets for migration Each cset (css_set) is pinned by its tasks. When we're moving tasks around across csets for a migration, we need to hold the source and destination csets to ensure that they don't go away while we're moving tasks about. This is done by linking cset->mg_preload_node on either the mgctx->preloaded_src_csets or mgctx->preloaded_dst_csets list. Using the same cset->mg_preload_node for both the src and dst lists was deemed okay as a cset can't be both the source and destination at the same time. Unfortunately, this overloading becomes problematic when multiple tasks are involved in a migration and some of them are identity noop migrations while others are actually moving across cgroups. For example, this can happen with the following sequence on cgroup1: #1> mkdir -p /sys/fs/cgroup/misc/a/b #2> echo $$ > /sys/fs/cgroup/misc/a/cgroup.procs #3> RUN_A_COMMAND_WHICH_CREATES_MULTIPLE_THREADS & #4> PID=$! #5> echo $PID > /sys/fs/cgroup/misc/a/b/tasks #6> echo $PID > /sys/fs/cgroup/misc/a/cgroup.procs the process including the group leader back into a. In this final migration, non-leader threads would be doing identity migration while the group leader is doing an actual one. After #3, let's say the whole process was in cset A, and that after #4, the leader moves to cset B. Then, during #6, the following happens: 1. cgroup_migrate_add_src() is called on B for the leader. 2. cgroup_migrate_add_src() is called on A for the other threads. 3. cgroup_migrate_prepare_dst() is called. It scans the src list. 4. It notices that B wants to migrate to A, so it tries to A to the dst list but realizes that its ->mg_preload_node is already busy. 5. and then it notices A wants to migrate to A as it's an identity migration, it culls it by list_del_init()'ing its ->mg_preload_node and putting references accordingly. 6. The rest of migration takes place with B on the src list but nothing on the dst list. This means that A isn't held while migration is in progress. If all tasks leave A before the migration finishes and the incoming task pins it, the cset will be destroyed leading to use-after-free. This is caused by overloading cset->mg_preload_node for both src and dst preload lists. We wanted to exclude the cset from the src list but ended up inadvertently excluding it from the dst list too. This patch fixes the issue by separating out cset->mg_preload_node into ->mg_src_preload_node and ->mg_dst_preload_node, so that the src and dst preloadings don't interfere with each other. Signed-off-by: Tejun Heo Reported-by: Mukesh Ojha Reported-by: shisiyuan Link: http://lkml.kernel.org/r/1654187688-27411-1-git-send-email-shisiyuan@xiaomi.com Link: https://www.spinics.net/lists/cgroups/msg33313.html Fixes: f817de98513d ("cgroup: prepare migration path for unified hierarchy") Cc: stable@vger.kernel.org # v3.16+ --- include/linux/cgroup-defs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1bfcfb1af352..d4427d0a0e18 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -264,7 +264,8 @@ struct css_set { * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ - struct list_head mg_preload_node; + struct list_head mg_src_preload_node; + struct list_head mg_dst_preload_node; struct list_head mg_node; /* -- cgit v1.2.3 From f50974eee5c4a5de1e4f1a3d873099f170df25f8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 23 Jun 2022 13:02:31 -0700 Subject: memregion: Fix memregion_free() fallback definition In the CONFIG_MEMREGION=n case, memregion_free() is meant to be a static inline. 0day reports: In file included from drivers/cxl/core/port.c:4: include/linux/memregion.h:19:6: warning: no previous prototype for function 'memregion_free' [-Wmissing-prototypes] Mark memregion_free() static. Fixes: 33dd70752cd7 ("lib: Uplevel the pmem "region" ida to a global allocator") Reported-by: kernel test robot Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/165601455171.4042645.3350844271068713515.stgit@dwillia2-xfh Signed-off-by: Dan Williams --- include/linux/memregion.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memregion.h b/include/linux/memregion.h index e11595256cac..c04c4fd2e209 100644 --- a/include/linux/memregion.h +++ b/include/linux/memregion.h @@ -16,7 +16,7 @@ static inline int memregion_alloc(gfp_t gfp) { return -ENOMEM; } -void memregion_free(int id) +static inline void memregion_free(int id) { } #endif -- cgit v1.2.3 From 742ab6df974ae8384a2dd213db1a3a06cf6d8936 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 14 Jun 2022 23:15:32 +0200 Subject: x86/kvm/vmx: Make noinstr clean The recent mmio_stale_data fixes broke the noinstr constraints: vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x15b: call to wrmsrl.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x1bf: call to kvm_arch_has_assigned_device() leaves .noinstr.text section make it all happy again. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov --- arch/x86/kvm/vmx/vmx.c | 6 +++--- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3a919e49129b..009bbae9ad66 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -383,9 +383,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) if (!vmx->disable_fb_clear) return; - rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -396,7 +396,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1910e1e78b15..26d0cac32f73 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12631,9 +12631,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c20f2d55840c..83cf7fd842e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1513,7 +1513,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } -- cgit v1.2.3 From 6b80b59b3555706508008f1f127b5412c89c7fd8 Mon Sep 17 00:00:00 2001 From: Alexandre Chartre Date: Tue, 14 Jun 2022 23:15:49 +0200 Subject: x86/bugs: Report AMD retbleed vulnerability Report that AMD x86 CPUs are vulnerable to the RETBleed (Arbitrary Speculative Code Execution with Return Instructions) attack. [peterz: add hygon] [kim: invert parity; fam15h] Co-developed-by: Kim Phillips Signed-off-by: Kim Phillips Signed-off-by: Alexandre Chartre Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Josh Poimboeuf Signed-off-by: Borislav Petkov --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 13 +++++++++++++ arch/x86/kernel/cpu/common.c | 19 +++++++++++++++++++ drivers/base/cpu.c | 8 ++++++++ include/linux/cpu.h | 2 ++ 5 files changed, 43 insertions(+) (limited to 'include') diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index fa3d0db1470e..c16503ca3b75 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -453,5 +453,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 74c62cc47a5f..74fdd21e416b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1994,6 +1994,11 @@ static ssize_t srbds_show_state(char *buf) return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); } +static ssize_t retbleed_show_state(char *buf) +{ + return sprintf(buf, "Vulnerable\n"); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2039,6 +2044,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MMIO_STALE_DATA: return mmio_stale_data_show_state(buf); + case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -2095,4 +2103,9 @@ ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *at { return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } + +ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4730b0a58f24..4089c173c6ae 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1205,16 +1205,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; +#define VULNBL(vendor, family, model, blacklist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) + #define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, steppings, \ X86_FEATURE_ANY, issues) +#define VULNBL_AMD(family, blacklist) \ + VULNBL(AMD, family, X86_MODEL_ANY, blacklist) + +#define VULNBL_HYGON(family, blacklist) \ + VULNBL(HYGON, family, X86_MODEL_ANY, blacklist) + #define SRBDS BIT(0) /* CPU is affected by X86_BUG_MMIO_STALE_DATA */ #define MMIO BIT(1) /* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ #define MMIO_SBDS BIT(2) +/* CPU is affected by RETbleed, speculating where you would not expect it */ +#define RETBLEED BIT(3) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1247,6 +1258,11 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), + + VULNBL_AMD(0x15, RETBLEED), + VULNBL_AMD(0x16, RETBLEED), + VULNBL_AMD(0x17, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED), {} }; @@ -1348,6 +1364,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (cpu_matches(cpu_vuln_blacklist, RETBLEED)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a97776ea9d99..4c98849577d4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -570,6 +570,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -580,6 +586,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); +static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -592,6 +599,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, + &dev_attr_retbleed.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2c7477354744..314802f98b9d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From a09a6e2399ba0595c3042b3164f3ca68a3cff33e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 14 Jun 2022 23:16:03 +0200 Subject: objtool: Add entry UNRET validation Since entry asm is tricky, add a validation pass that ensures the retbleed mitigation has been done before the first actual RET instruction. Entry points are those that either have UNWIND_HINT_ENTRY, which acts as UNWIND_HINT_EMPTY but marks the instruction as an entry point, or those that have UWIND_HINT_IRET_REGS at +0. This is basically a variant of validate_branch() that is intra-function and it will simply follow all branches from marked entry points and ensures that all paths lead to ANNOTATE_UNRET_END. If a path hits RET or an indirection the path is a fail and will be reported. There are 3 ANNOTATE_UNRET_END instances: - UNTRAIN_RET itself - exception from-kernel; this path doesn't need UNTRAIN_RET - all early exceptions; these also don't need UNTRAIN_RET Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Josh Poimboeuf Signed-off-by: Borislav Petkov --- arch/x86/entry/entry_64.S | 3 +- arch/x86/entry/entry_64_compat.S | 6 +- arch/x86/include/asm/nospec-branch.h | 12 +++ arch/x86/include/asm/unwind_hints.h | 4 + arch/x86/kernel/head_64.S | 5 + arch/x86/xen/xen-asm.S | 10 +- include/linux/objtool.h | 3 + scripts/Makefile.vmlinux_o | 2 +- tools/include/linux/objtool.h | 3 + tools/objtool/builtin-check.c | 6 ++ tools/objtool/check.c | 177 ++++++++++++++++++++++++++++++-- tools/objtool/include/objtool/builtin.h | 1 + tools/objtool/include/objtool/check.h | 11 +- 13 files changed, 222 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0c88802e1155..65e3b8b7cbe5 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -85,7 +85,7 @@ */ SYM_CODE_START(entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR swapgs @@ -1095,6 +1095,7 @@ SYM_CODE_START_LOCAL(error_entry) .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY leaq 8(%rsp), %rax /* return pt_regs pointer */ + ANNOTATE_UNRET_END RET .Lbstep_iret: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index bcb89d23ac0e..682338e7e2a3 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -49,7 +49,7 @@ * 0(%ebp) arg6 */ SYM_CODE_START(entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -179,7 +179,7 @@ SYM_CODE_END(entry_SYSENTER_compat) * 0(%esp) arg6 */ SYM_CODE_START(entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* Interrupts are off on entry. */ swapgs @@ -305,7 +305,7 @@ SYM_CODE_END(entry_SYSCALL_compat) * ebp arg6 */ SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* * Interrupts are off on entry. diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 05dd75478d7b..bba42bd78edf 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -81,6 +81,17 @@ */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE +/* + * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should + * eventually turn into it's own annotation. + */ +.macro ANNOTATE_UNRET_END +#ifdef CONFIG_DEBUG_ENTRY + ANNOTATE_RETPOLINE_SAFE + nop +#endif +.endm + /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 @@ -131,6 +142,7 @@ */ .macro UNTRAIN_RET #ifdef CONFIG_RETPOLINE + ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ "call zen_untrain_ret", X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 8b33674288ea..6f70fe4c93f2 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -11,6 +11,10 @@ UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1 .endm +.macro UNWIND_HINT_ENTRY + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_ENTRY end=1 +.endm + .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 .if \base == %rsp .if \indirect diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 92c4afa2b729..d860d437631b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -389,6 +389,8 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS @@ -448,6 +450,7 @@ SYM_CODE_END(early_idt_handler_array) SYM_CODE_START_LOCAL(early_idt_handler_common) UNWIND_HINT_IRET_REGS offset=16 + ANNOTATE_UNRET_END /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -497,6 +500,8 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR + ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 6bf9d45b9178..6b4fdf6b9542 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -121,7 +121,7 @@ SYM_FUNC_END(xen_read_cr2_direct); .macro xen_pv_trap name SYM_CODE_START(xen_\name) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR pop %rcx pop %r11 @@ -235,7 +235,7 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) /* Normal 64-bit system call target */ SYM_CODE_START(xen_entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -255,7 +255,7 @@ SYM_CODE_END(xen_entry_SYSCALL_64) /* 32-bit compat syscall target */ SYM_CODE_START(xen_entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR popq %rcx popq %r11 @@ -273,7 +273,7 @@ SYM_CODE_END(xen_entry_SYSCALL_compat) /* 32-bit compat sysenter target */ SYM_CODE_START(xen_entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR /* * NB: Xen is polite and clears TF from EFLAGS for us. This means @@ -297,7 +297,7 @@ SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_START(xen_entry_SYSCALL_compat) SYM_CODE_START(xen_entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 15b940ec1eac..b026f1ae39c6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,11 +32,14 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 #ifdef CONFIG_OBJTOOL diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 3c97a1564947..bc67748044a6 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -44,7 +44,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) objtool_args := \ $(if $(delay-objtool),$(objtool_args)) \ - $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr) \ + $(if $(CONFIG_NOINSTR_VALIDATION), --noinstr $(if $(CONFIG_RETPOLINE), --unret)) \ $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ --link diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 15b940ec1eac..b026f1ae39c6 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -32,11 +32,14 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 #ifdef CONFIG_OBJTOOL diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index f4c3a5091737..c063e1ff96b2 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -68,6 +68,7 @@ const struct option check_options[] = { OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"), OPT_BOOLEAN('o', "orc", &opts.orc, "generate ORC metadata"), OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"), + OPT_BOOLEAN(0, "unret", &opts.unret, "validate entry unret placement"), OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"), OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"), OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"), @@ -163,6 +164,11 @@ static bool link_opts_valid(struct objtool_file *file) return false; } + if (opts.unret) { + ERROR("--unret requires --link"); + return false; + } + return true; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 7dc378156a63..822a490e6d87 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2032,16 +2032,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; - if (opts.ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { + if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); - if (sym && sym->bind == STB_GLOBAL && - insn->type != INSN_ENDBR && !insn->noendbr) { - WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", - insn->sec, insn->offset); + if (sym && sym->bind == STB_GLOBAL) { + if (opts.ibt && insn->type != INSN_ENDBR && !insn->noendbr) { + WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", + insn->sec, insn->offset); + } + + insn->entry = 1; } } + if (hint->type == UNWIND_HINT_TYPE_ENTRY) { + hint->type = UNWIND_HINT_TYPE_CALL; + insn->entry = 1; + } + if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -2116,8 +2124,9 @@ static int read_retpoline_hints(struct objtool_file *file) if (insn->type != INSN_JUMP_DYNAMIC && insn->type != INSN_CALL_DYNAMIC && - insn->type != INSN_RETURN) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret", + insn->type != INSN_RETURN && + insn->type != INSN_NOP) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", insn->sec, insn->offset); return -1; } @@ -3305,8 +3314,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } - visited = 1 << state.uaccess; - if (insn->visited) { + visited = VISITED_BRANCH << state.uaccess; + if (insn->visited & VISITED_BRANCH_MASK) { if (!insn->hint && !insn_cfi_match(insn, &state.cfi)) return 1; @@ -3520,6 +3529,145 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) return warnings; } +/* + * Validate rethunk entry constraint: must untrain RET before the first RET. + * + * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * before an actual RET instruction. + */ +static int validate_entry(struct objtool_file *file, struct instruction *insn) +{ + struct instruction *next, *dest; + int ret, warnings = 0; + + for (;;) { + next = next_insn_to_validate(file, insn); + + if (insn->visited & VISITED_ENTRY) + return 0; + + insn->visited |= VISITED_ENTRY; + + if (!insn->ignore_alts && !list_empty(&insn->alts)) { + struct alternative *alt; + bool skip_orig = false; + + list_for_each_entry(alt, &insn->alts, list) { + if (alt->skip_orig) + skip_orig = true; + + ret = validate_entry(file, alt->insn); + if (ret) { + if (opts.backtrace) + BT_FUNC("(alt)", insn); + return ret; + } + } + + if (skip_orig) + return 0; + } + + switch (insn->type) { + + case INSN_CALL_DYNAMIC: + case INSN_JUMP_DYNAMIC: + case INSN_JUMP_DYNAMIC_CONDITIONAL: + WARN_FUNC("early indirect call", insn->sec, insn->offset); + return 1; + + case INSN_JUMP_UNCONDITIONAL: + case INSN_JUMP_CONDITIONAL: + if (!is_sibling_call(insn)) { + if (!insn->jump_dest) { + WARN_FUNC("unresolved jump target after linking?!?", + insn->sec, insn->offset); + return -1; + } + ret = validate_entry(file, insn->jump_dest); + if (ret) { + if (opts.backtrace) { + BT_FUNC("(branch%s)", insn, + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); + } + return ret; + } + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + } + + /* fallthrough */ + case INSN_CALL: + dest = find_insn(file, insn->call_dest->sec, + insn->call_dest->offset); + if (!dest) { + WARN("Unresolved function after linking!?: %s", + insn->call_dest->name); + return -1; + } + + ret = validate_entry(file, dest); + if (ret) { + if (opts.backtrace) + BT_FUNC("(call)", insn); + return ret; + } + /* + * If a call returns without error, it must have seen UNTRAIN_RET. + * Therefore any non-error return is a success. + */ + return 0; + + case INSN_RETURN: + WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + return 1; + + case INSN_NOP: + if (insn->retpoline_safe) + return 0; + break; + + default: + break; + } + + if (!next) { + WARN_FUNC("teh end!", insn->sec, insn->offset); + return -1; + } + insn = next; + } + + return warnings; +} + +/* + * Validate that all branches starting at 'insn->entry' encounter UNRET_END + * before RET. + */ +static int validate_unret(struct objtool_file *file) +{ + struct instruction *insn; + int ret, warnings = 0; + + for_each_insn(file, insn) { + if (!insn->entry) + continue; + + ret = validate_entry(file, insn); + if (ret < 0) { + WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + return ret; + } + warnings += ret; + } + + return warnings; +} + static int validate_retpoline(struct objtool_file *file) { struct instruction *insn; @@ -4039,6 +4187,17 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.unret) { + /* + * Must be after validate_branch() and friends, it plays + * further games with insn->visited. + */ + ret = validate_unret(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (opts.ibt) { ret = validate_ibt(file); if (ret < 0) diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 280ea18b7f2b..0c476b0b40a3 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -19,6 +19,7 @@ struct opts { bool noinstr; bool orc; bool retpoline; + bool unret; bool sls; bool stackval; bool static_call; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index f10d7374f388..0eeedeacbefb 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -51,8 +51,10 @@ struct instruction { ignore_alts : 1, hint : 1, retpoline_safe : 1, - noendbr : 1; - /* 2 bit hole */ + noendbr : 1, + entry : 1; + /* 1 bit hole */ + s8 instr; u8 visited; /* u8 hole */ @@ -69,6 +71,11 @@ struct instruction { struct cfi_state *cfi; }; +#define VISITED_BRANCH 0x01 +#define VISITED_BRANCH_UACCESS 0x02 +#define VISITED_BRANCH_MASK 0x03 +#define VISITED_ENTRY 0x04 + static inline bool is_static_jump(struct instruction *insn) { return insn->type == INSN_JUMP_CONDITIONAL || -- cgit v1.2.3 From 8faea26e611189e933ea2281975ff4dc7c1106b6 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 24 Jun 2022 12:52:40 +0200 Subject: objtool: Re-add UNWIND_HINT_{SAVE_RESTORE} Commit c536ed2fffd5 ("objtool: Remove SAVE/RESTORE hints") removed the save/restore unwind hints because they were no longer needed. Now they're going to be needed again so re-add them. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov --- arch/x86/include/asm/unwind_hints.h | 12 +++++++++-- include/linux/objtool.h | 6 ++++-- tools/include/linux/objtool.h | 6 ++++-- tools/objtool/check.c | 40 +++++++++++++++++++++++++++++++++++ tools/objtool/include/objtool/check.h | 19 +++++++++-------- 5 files changed, 68 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 6f70fe4c93f2..f66fbe6537dd 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -8,11 +8,11 @@ #ifdef __ASSEMBLY__ .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1 + UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1 .endm .macro UNWIND_HINT_ENTRY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_ENTRY end=1 + UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 @@ -56,6 +56,14 @@ UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm +.macro UNWIND_HINT_SAVE + UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE +.endm + +.macro UNWIND_HINT_RESTORE + UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE +.endm + #else #define UNWIND_HINT_FUNC \ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index b026f1ae39c6..10bc88cc3bf6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 #define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -127,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -180,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index b026f1ae39c6..10bc88cc3bf6 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 #define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -127,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -180,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 822a490e6d87..ddfdd138cc2a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2032,6 +2032,17 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; + if (hint->type == UNWIND_HINT_TYPE_SAVE) { + insn->hint = false; + insn->save = true; + continue; + } + + if (hint->type == UNWIND_HINT_TYPE_RESTORE) { + insn->restore = true; + continue; + } + if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); @@ -3329,6 +3340,35 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, state.instr += insn->instr; if (insn->hint) { + if (insn->restore) { + struct instruction *save_insn, *i; + + i = insn; + save_insn = NULL; + + sym_for_each_insn_continue_reverse(file, func, i) { + if (i->save) { + save_insn = i; + break; + } + } + + if (!save_insn) { + WARN_FUNC("no corresponding CFI save for CFI restore", + sec, insn->offset); + return 1; + } + + if (!save_insn->visited) { + WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", + sec, insn->offset); + return 1; + } + + insn->cfi = save_insn->cfi; + nr_cfi_reused++; + } + state.cfi = *insn->cfi; } else { /* XXX track if we actually changed state.cfi */ diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 0eeedeacbefb..036129cebeee 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -46,18 +46,19 @@ struct instruction { enum insn_type type; unsigned long immediate; - u8 dead_end : 1, - ignore : 1, - ignore_alts : 1, - hint : 1, - retpoline_safe : 1, - noendbr : 1, - entry : 1; - /* 1 bit hole */ + u16 dead_end : 1, + ignore : 1, + ignore_alts : 1, + hint : 1, + save : 1, + restore : 1, + retpoline_safe : 1, + noendbr : 1, + entry : 1; + /* 7 bit hole */ s8 instr; u8 visited; - /* u8 hole */ struct alt_group *alt_group; struct symbol *call_dest; -- cgit v1.2.3 From 03895c8414d748747900ede2cb603d0ed3eeae1c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Jun 2022 00:42:12 +0200 Subject: wifi: mac80211: add gfp_t parameter to ieeee80211_obss_color_collision_notify Introduce the capability to specify gfp_t parameter to ieeee80211_obss_color_collision_notify routine since it runs in interrupt context in ieee80211_rx_check_bss_color_collision(). Fixes: 6d945a33f2b0a ("mac80211: introduce BSS color collision detection") Co-developed-by: Ryder Lee Signed-off-by: Ryder Lee Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/02c990fb3fbd929c8548a656477d20d6c0427a13.1655419135.git.lorenzo@kernel.org Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath11k/wmi.c | 3 ++- include/net/cfg80211.h | 5 +++-- include/net/mac80211.h | 3 ++- net/mac80211/cfg.c | 4 ++-- net/mac80211/rx.c | 3 ++- 5 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 84d1c7054013..7b1dc19c565e 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -3822,7 +3822,8 @@ ath11k_wmi_obss_color_collision_event(struct ath11k_base *ab, struct sk_buff *sk switch (ev->evt_type) { case WMI_BSS_COLOR_COLLISION_DETECTION: - ieeee80211_obss_color_collision_notify(arvif->vif, ev->obss_color_bitmap); + ieeee80211_obss_color_collision_notify(arvif->vif, ev->obss_color_bitmap, + GFP_KERNEL); ath11k_dbg(ab, ATH11K_DBG_WMI, "OBSS color collision detected vdev:%d, event:%d, bitmap:%08llx\n", ev->vdev_id, ev->evt_type, ev->obss_color_bitmap); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6d02e12e4702..80f41446b1f0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8462,11 +8462,12 @@ int cfg80211_bss_color_notify(struct net_device *dev, gfp_t gfp, * cfg80211_obss_color_collision_notify - notify about bss color collision * @dev: network device * @color_bitmap: representations of the colors that the local BSS is aware of + * @gfp: allocation flags */ static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, - u64 color_bitmap) + u64 color_bitmap, gfp_t gfp) { - return cfg80211_bss_color_notify(dev, GFP_KERNEL, + return cfg80211_bss_color_notify(dev, gfp, NL80211_CMD_OBSS_COLOR_COLLISION, 0, color_bitmap); } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ebadb2103968..47642b020706 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6960,10 +6960,11 @@ ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is * aware of. + * @gfp: allocation flags */ void ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap); + u64 color_bitmap, gfp_t gfp); /** * ieee80211_is_tx_data - check if frame is a data frame diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f7896f257e1b..4ddf297f40f2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4468,14 +4468,14 @@ EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap) + u64 color_bitmap, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (sdata->vif.color_change_active || sdata->vif.csa_active) return; - cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap); + cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap, gfp); } EXPORT_SYMBOL_GPL(ieeee80211_obss_color_collision_notify); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c08ae04ddbc..1675f8cb87f1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3217,7 +3217,8 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) IEEE80211_HE_OPERATION_BSS_COLOR_MASK); if (color == bss_conf->he_bss_color.color) ieeee80211_obss_color_collision_notify(&rx->sdata->vif, - BIT_ULL(color)); + BIT_ULL(color), + GFP_ATOMIC); } } -- cgit v1.2.3 From eb7f8e28420372787933eec079735c35034bda7d Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 30 Jun 2022 20:32:55 -0600 Subject: misc: rtsx_usb: fix use of dma mapped buffer for usb bulk transfer rtsx_usb driver allocates coherent dma buffer for urb transfers. This buffer is passed to usb_bulk_msg() and usb core tries to map already mapped buffer running into a dma mapping error. xhci_hcd 0000:01:00.0: rejecting DMA map of vmalloc memory WARNING: CPU: 1 PID: 279 at include/linux/dma-mapping.h:326 usb_ hcd_map_urb_for_dma+0x7d6/0x820 ... xhci_map_urb_for_dma+0x291/0x4e0 usb_hcd_submit_urb+0x199/0x12b0 ... usb_submit_urb+0x3b8/0x9e0 usb_start_wait_urb+0xe3/0x2d0 usb_bulk_msg+0x115/0x240 rtsx_usb_transfer_data+0x185/0x1a8 [rtsx_usb] rtsx_usb_send_cmd+0xbb/0x123 [rtsx_usb] rtsx_usb_write_register+0x12c/0x143 [rtsx_usb] rtsx_usb_probe+0x226/0x4b2 [rtsx_usb] Fix it to use kmalloc() to get DMA-able memory region instead. Signed-off-by: Shuah Khan Cc: stable Link: https://lore.kernel.org/r/667d627d502e1ba9ff4f9b94966df3299d2d3c0d.1656642167.git.skhan@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/rtsx_usb.c | 13 +++++++------ include/linux/rtsx_usb.h | 1 - 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c index 1ef9b61077c4..e147cc8ab0fd 100644 --- a/drivers/misc/cardreader/rtsx_usb.c +++ b/drivers/misc/cardreader/rtsx_usb.c @@ -631,8 +631,7 @@ static int rtsx_usb_probe(struct usb_interface *intf, ucr->pusb_dev = usb_dev; - ucr->iobuf = usb_alloc_coherent(ucr->pusb_dev, IOBUF_SIZE, - GFP_KERNEL, &ucr->iobuf_dma); + ucr->iobuf = kmalloc(IOBUF_SIZE, GFP_KERNEL); if (!ucr->iobuf) return -ENOMEM; @@ -668,8 +667,9 @@ static int rtsx_usb_probe(struct usb_interface *intf, out_init_fail: usb_set_intfdata(ucr->pusb_intf, NULL); - usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf, - ucr->iobuf_dma); + kfree(ucr->iobuf); + ucr->iobuf = NULL; + ucr->cmd_buf = ucr->rsp_buf = NULL; return ret; } @@ -682,8 +682,9 @@ static void rtsx_usb_disconnect(struct usb_interface *intf) mfd_remove_devices(&intf->dev); usb_set_intfdata(ucr->pusb_intf, NULL); - usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf, - ucr->iobuf_dma); + kfree(ucr->iobuf); + ucr->iobuf = NULL; + ucr->cmd_buf = ucr->rsp_buf = NULL; } #ifdef CONFIG_PM diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h index 159729cffd8e..a07f7341ebc2 100644 --- a/include/linux/rtsx_usb.h +++ b/include/linux/rtsx_usb.h @@ -55,7 +55,6 @@ struct rtsx_ucr { struct usb_interface *pusb_intf; struct usb_sg_request current_sg; unsigned char *iobuf; - dma_addr_t iobuf_dma; struct timer_list sg_timer; struct mutex dev_mutex; -- cgit v1.2.3 From 3776c78559853fd151be7c41e369fd076fb679d5 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 30 Jun 2022 20:32:56 -0600 Subject: misc: rtsx_usb: use separate command and response buffers rtsx_usb uses same buffer for command and response. There could be a potential conflict using the same buffer for both especially if retries and timeouts are involved. Use separate command and response buffers to avoid conflicts. Signed-off-by: Shuah Khan Cc: stable Link: https://lore.kernel.org/r/07e3721804ff07aaab9ef5b39a5691d0718b9ade.1656642167.git.skhan@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/rtsx_usb.c | 26 +++++++++++++++++--------- include/linux/rtsx_usb.h | 1 - 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c index e147cc8ab0fd..4e2108052509 100644 --- a/drivers/misc/cardreader/rtsx_usb.c +++ b/drivers/misc/cardreader/rtsx_usb.c @@ -631,15 +631,18 @@ static int rtsx_usb_probe(struct usb_interface *intf, ucr->pusb_dev = usb_dev; - ucr->iobuf = kmalloc(IOBUF_SIZE, GFP_KERNEL); - if (!ucr->iobuf) + ucr->cmd_buf = kmalloc(IOBUF_SIZE, GFP_KERNEL); + if (!ucr->cmd_buf) return -ENOMEM; + ucr->rsp_buf = kmalloc(IOBUF_SIZE, GFP_KERNEL); + if (!ucr->rsp_buf) + goto out_free_cmd_buf; + usb_set_intfdata(intf, ucr); ucr->vendor_id = id->idVendor; ucr->product_id = id->idProduct; - ucr->cmd_buf = ucr->rsp_buf = ucr->iobuf; mutex_init(&ucr->dev_mutex); @@ -667,9 +670,11 @@ static int rtsx_usb_probe(struct usb_interface *intf, out_init_fail: usb_set_intfdata(ucr->pusb_intf, NULL); - kfree(ucr->iobuf); - ucr->iobuf = NULL; - ucr->cmd_buf = ucr->rsp_buf = NULL; + kfree(ucr->rsp_buf); + ucr->rsp_buf = NULL; +out_free_cmd_buf: + kfree(ucr->cmd_buf); + ucr->cmd_buf = NULL; return ret; } @@ -682,9 +687,12 @@ static void rtsx_usb_disconnect(struct usb_interface *intf) mfd_remove_devices(&intf->dev); usb_set_intfdata(ucr->pusb_intf, NULL); - kfree(ucr->iobuf); - ucr->iobuf = NULL; - ucr->cmd_buf = ucr->rsp_buf = NULL; + + kfree(ucr->cmd_buf); + ucr->cmd_buf = NULL; + + kfree(ucr->rsp_buf); + ucr->rsp_buf = NULL; } #ifdef CONFIG_PM diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h index a07f7341ebc2..3247ed8e9ff0 100644 --- a/include/linux/rtsx_usb.h +++ b/include/linux/rtsx_usb.h @@ -54,7 +54,6 @@ struct rtsx_ucr { struct usb_device *pusb_dev; struct usb_interface *pusb_intf; struct usb_sg_request current_sg; - unsigned char *iobuf; struct timer_list sg_timer; struct mutex dev_mutex; -- cgit v1.2.3 From 07358194badf73e267289b40b761f5dc56928eab Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 27 Jun 2022 20:42:18 +0200 Subject: PM: runtime: Redefine pm_runtime_release_supplier() Instead of passing an extra bool argument to pm_runtime_release_supplier(), make its callers take care of triggering a runtime-suspend of the supplier device as needed. No expected functional impact. Suggested-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki Reviewed-by: Greg Kroah-Hartman Cc: 5.1+ # 5.1+ --- drivers/base/core.c | 3 ++- drivers/base/power/runtime.c | 20 +++++++++----------- include/linux/pm_runtime.h | 5 ++--- 3 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 7cd789c4985d..58aa49527d3a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -486,7 +486,8 @@ static void device_link_release_fn(struct work_struct *work) /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); - pm_runtime_release_supplier(link, true); + pm_runtime_release_supplier(link); + pm_request_idle(link->supplier); put_device(link->consumer); put_device(link->supplier); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 676dc72d912d..23cc4c377d77 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -308,13 +308,10 @@ static int rpm_get_suppliers(struct device *dev) /** * pm_runtime_release_supplier - Drop references to device link's supplier. * @link: Target device link. - * @check_idle: Whether or not to check if the supplier device is idle. * - * Drop all runtime PM references associated with @link to its supplier device - * and if @check_idle is set, check if that device is idle (and so it can be - * suspended). + * Drop all runtime PM references associated with @link to its supplier device. */ -void pm_runtime_release_supplier(struct device_link *link, bool check_idle) +void pm_runtime_release_supplier(struct device_link *link) { struct device *supplier = link->supplier; @@ -327,9 +324,6 @@ void pm_runtime_release_supplier(struct device_link *link, bool check_idle) while (refcount_dec_not_one(&link->rpm_active) && atomic_read(&supplier->power.usage_count) > 0) pm_runtime_put_noidle(supplier); - - if (check_idle) - pm_request_idle(supplier); } static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) @@ -337,8 +331,11 @@ static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, - device_links_read_lock_held()) - pm_runtime_release_supplier(link, try_to_suspend); + device_links_read_lock_held()) { + pm_runtime_release_supplier(link); + if (try_to_suspend) + pm_request_idle(link->supplier); + } } static void rpm_put_suppliers(struct device *dev) @@ -1838,7 +1835,8 @@ void pm_runtime_drop_link(struct device_link *link) return; pm_runtime_drop_link_count(link->consumer); - pm_runtime_release_supplier(link, true); + pm_runtime_release_supplier(link); + pm_request_idle(link->supplier); } static bool pm_runtime_need_not_resume(struct device *dev) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 9e4d056967c6..0a41b2dcccad 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -88,7 +88,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); -extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle); +extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); @@ -314,8 +314,7 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} -static inline void pm_runtime_release_supplier(struct device_link *link, - bool check_idle) {} +static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ -- cgit v1.2.3 From cffe57bee62b155c08d71218fc0e9e84a0a90bbb Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Wed, 22 Jun 2022 15:45:46 +0700 Subject: Documentation: highmem: use literal block for code example in highmem.h comment When building htmldocs on Linus's tree, there are inline emphasis warnings on include/linux/highmem.h: Documentation/vm/highmem:166: ./include/linux/highmem.h:154: WARNING: Inline emphasis start-string without end-string. Documentation/vm/highmem:166: ./include/linux/highmem.h:157: WARNING: Inline emphasis start-string without end-string. These warnings above are due to comments in code example at the mentioned lines above are enclosed by double dash (--), which confuses Sphinx as inline markup delimiters instead. Fix these warnings by indenting the code example with literal block indentation and making the comments C comments. Link: https://lkml.kernel.org/r/20220622084546.17745-1-bagasdotme@gmail.com Fixes: 85a85e7601263f ("Documentation/vm: move "Using kmap-atomic" to highmem.h") Signed-off-by: Bagas Sanjaya Reviewed-by: Ira Weiny Tested-by: Ira Weiny Cc: "Matthew Wilcox (Oracle)" Cc: "Fabio M. De Francesco" Cc: Sebastian Andrzej Siewior Signed-off-by: Andrew Morton --- include/linux/highmem.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 3af34de54330..56d6a0196534 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they - * can be used in a manner similar to the following: + * can be used in a manner similar to the following:: * - * -- Find the page of interest. -- - * struct page *page = find_get_page(mapping, offset); + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * -- Gain access to the contents of that page. -- - * void *vaddr = kmap_atomic(page); + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); * - * -- Do something to the contents of that page. -- - * memset(vaddr, 0, PAGE_SIZE); + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); * - * -- Unmap that page. -- - * kunmap_atomic(vaddr); + * // Unmap that page. + * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. -- cgit v1.2.3 From 85e4ea1049c70fb99de5c6057e835d151fb647da Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Apr 2022 14:27:17 +0100 Subject: fscache: Fix invalidation/lookup race If an NFS file is opened for writing and closed, fscache_invalidate() will be asked to invalidate the file - however, if the cookie is in the LOOKING_UP state (or the CREATING state), then request to invalidate doesn't get recorded for fscache_cookie_state_machine() to do something with. Fix this by making __fscache_invalidate() set a flag if it sees the cookie is in the LOOKING_UP state to indicate that we need to go to invalidation. Note that this requires a count on the n_accesses counter for the state machine, which that will release when it's done. fscache_cookie_state_machine() then shifts to the INVALIDATING state if it sees the flag. Without this, an nfs file can get corrupted if it gets modified locally and then read locally as the cache contents may not get updated. Fixes: d24af13e2e23 ("fscache: Implement cookie invalidation") Reported-by: Max Kellermann Signed-off-by: David Howells Tested-by: Max Kellermann Link: https://lore.kernel.org/r/YlWWbpW5Foynjllo@rabbit.intern.cm-ag [1] --- fs/fscache/cookie.c | 15 ++++++++++++++- include/linux/fscache.h | 1 + 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 575a5ba07c0d..74920826d8f6 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -522,7 +522,14 @@ static void fscache_perform_lookup(struct fscache_cookie *cookie) } fscache_see_cookie(cookie, fscache_cookie_see_active); - fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); + spin_lock(&cookie->lock); + if (test_and_clear_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags)) + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_INVALIDATING); + else + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); trace = fscache_access_lookup_cookie_end; out: @@ -757,6 +764,9 @@ again_locked: spin_lock(&cookie->lock); } + if (test_and_clear_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags)) + fscache_end_cookie_access(cookie, fscache_access_invalidate_cookie_end); + switch (state) { case FSCACHE_COOKIE_STATE_RELINQUISHING: fscache_see_cookie(cookie, fscache_cookie_see_relinquish); @@ -1053,6 +1063,9 @@ void __fscache_invalidate(struct fscache_cookie *cookie, return; case FSCACHE_COOKIE_STATE_LOOKING_UP: + __fscache_begin_cookie_access(cookie, fscache_access_invalidate_cookie); + set_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags); + fallthrough; case FSCACHE_COOKIE_STATE_CREATING: spin_unlock(&cookie->lock); _leave(" [look %x]", cookie->inval_counter); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 72585c9729a2..b86265664879 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -130,6 +130,7 @@ struct fscache_cookie { #define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ #define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ #define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ +#define FSCACHE_COOKIE_DO_INVALIDATE 15 /* T if cookie needs invalidation */ enum fscache_cookie_state state; u8 advice; /* FSCACHE_ADV_* */ -- cgit v1.2.3 From 7feec7430edddb87c24b0a86b08a03d0b496a755 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 5 Jul 2022 13:29:14 -0500 Subject: ACPI: CPPC: Only probe for _CPC if CPPC v2 is acked Previously the kernel used to ignore whether the firmware masked CPPC or CPPCv2 and would just pretend that it worked. When support for the USB4 bit in _OSC was introduced from commit 9e1f561afb ("ACPI: Execute platform _OSC also with query bit clear") the kernel began to look at the return when the query bit was clear. This caused regressions that were misdiagnosed and attempted to be solved as part of commit 2ca8e6285250 ("Revert "ACPI: Pass the same capabilities to the _OSC regardless of the query flag""). This caused a different regression where non-Intel systems weren't able to negotiate _OSC properly. This was reverted in commit 2ca8e6285250 ("Revert "ACPI: Pass the same capabilities to the _OSC regardless of the query flag"") and attempted to be fixed by commit c42fa24b4475 ("ACPI: bus: Avoid using CPPC if not supported by firmware") but the regression still returned. These systems with the regression only load support for CPPC from an SSDT dynamically when _OSC reports CPPC v2. Avoid the problem by not letting CPPC satisfy the requirement in `acpi_cppc_processor_probe`. Reported-by: CUI Hao Reported-by: maxim.novozhilov@gmail.com Reported-by: lethe.tree@protonmail.com Reported-by: garystephenwright@gmail.com Reported-by: galaxyking0419@gmail.com Fixes: c42fa24b4475 ("ACPI: bus: Avoid using CPPC if not supported by firmware") Fixes: 2ca8e6285250 ("Revert "ACPI Pass the same capabilities to the _OSC regardless of the query flag"") Link: https://bugzilla.kernel.org/show_bug.cgi?id=213023 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2075387 Reviewed-by: Mika Westerberg Tested-by: CUI Hao Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki --- drivers/acpi/bus.c | 11 +++++------ drivers/acpi/cppc_acpi.c | 4 +++- include/linux/acpi.h | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 86fa61a21826..e2db1bdd9dd2 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -298,7 +298,7 @@ EXPORT_SYMBOL_GPL(osc_cpc_flexible_adr_space_confirmed); bool osc_sb_native_usb4_support_confirmed; EXPORT_SYMBOL_GPL(osc_sb_native_usb4_support_confirmed); -bool osc_sb_cppc_not_supported; +bool osc_sb_cppc2_support_acked; static u8 sb_uuid_str[] = "0811B06E-4A27-44F9-8D60-3CBBC22E7B48"; static void acpi_bus_osc_negotiate_platform_control(void) @@ -358,11 +358,6 @@ static void acpi_bus_osc_negotiate_platform_control(void) return; } -#ifdef CONFIG_ACPI_CPPC_LIB - osc_sb_cppc_not_supported = !(capbuf_ret[OSC_SUPPORT_DWORD] & - (OSC_SB_CPC_SUPPORT | OSC_SB_CPCV2_SUPPORT)); -#endif - /* * Now run _OSC again with query flag clear and with the caps * supported by both the OS and the platform. @@ -376,6 +371,10 @@ static void acpi_bus_osc_negotiate_platform_control(void) capbuf_ret = context.ret.pointer; if (context.ret.length > OSC_SUPPORT_DWORD) { +#ifdef CONFIG_ACPI_CPPC_LIB + osc_sb_cppc2_support_acked = capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_CPCV2_SUPPORT; +#endif + osc_sb_apei_support_acked = capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_APEI_SUPPORT; osc_pc_lpi_support_confirmed = diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 903528f7e187..d64facbda0fb 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -684,8 +684,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) acpi_status status; int ret = -ENODATA; - if (osc_sb_cppc_not_supported) + if (!osc_sb_cppc2_support_acked) { + pr_debug("CPPC v2 _OSC not acked\n"); return -ENODEV; + } /* Parse the ACPI _CPC table for this CPU. */ status = acpi_evaluate_object_typed(handle, "_CPC", NULL, &output, diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4f82a5bc6d98..44975c1bbe12 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -584,7 +584,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; -extern bool osc_sb_cppc_not_supported; +extern bool osc_sb_cppc2_support_acked; extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ -- cgit v1.2.3 From 8b356e536e69f3a4d6778ae9f0858a1beadabb1f Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 5 Jul 2022 13:29:15 -0500 Subject: ACPI: CPPC: Don't require _OSC if X86_FEATURE_CPPC is supported commit 72f2ecb7ece7 ("ACPI: bus: Set CPPC _OSC bits for all and when CPPC_LIB is supported") added support for claiming to support CPPC in _OSC on non-Intel platforms. This unfortunately caused a regression on a vartiety of AMD platforms in the field because a number of AMD platforms don't set the `_OSC` bit 5 or 6 to indicate CPPC or CPPC v2 support. As these AMD platforms already claim CPPC support via a dedicated MSR from `X86_FEATURE_CPPC`, use this enable this feature rather than requiring the `_OSC` on platforms with a dedicated MSR. If there is additional breakage on the shared memory designs also missing this _OSC, additional follow up changes may be needed. Fixes: 72f2ecb7ece7 ("Set CPPC _OSC bits for all and when CPPC_LIB is supported") Reported-by: Perry Yuan Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/acpi/cppc.c | 10 ++++++++++ drivers/acpi/cppc_acpi.c | 16 +++++++++++++++- include/acpi/cppc_acpi.h | 1 + 3 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8b8cbf22461a..734b96454896 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -11,6 +11,16 @@ /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ +bool cpc_supported_by_cpu(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + return boot_cpu_has(X86_FEATURE_CPPC); + } + return false; +} + bool cpc_ffh_supported(void) { return true; diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index d64facbda0fb..6ff1901d7d43 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -577,6 +577,19 @@ bool __weak cpc_ffh_supported(void) return false; } +/** + * cpc_supported_by_cpu() - check if CPPC is supported by CPU + * + * Check if the architectural support for CPPC is present even + * if the _OSC hasn't prescribed it + * + * Return: true for supported, false for not supported + */ +bool __weak cpc_supported_by_cpu(void) +{ + return false; +} + /** * pcc_data_alloc() - Allocate the pcc_data memory for pcc subspace * @@ -686,7 +699,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) if (!osc_sb_cppc2_support_acked) { pr_debug("CPPC v2 _OSC not acked\n"); - return -ENODEV; + if (!cpc_supported_by_cpu()) + return -ENODEV; } /* Parse the ACPI _CPC table for this CPU. */ diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index c6108581d97d..d389bab54241 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -145,6 +145,7 @@ extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); extern unsigned int cppc_get_transition_latency(int cpu); extern bool cpc_ffh_supported(void); +extern bool cpc_supported_by_cpu(void); extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val); extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val); #else /* !CONFIG_ACPI_CPPC_LIB */ -- cgit v1.2.3 From 4140d77a022101376bbfa3ec3e3da5063455c60e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 25 Jun 2022 21:34:30 +0800 Subject: iommu/vt-d: Fix RID2PASID setup/teardown failure The IOMMU driver shares the pasid table for PCI alias devices. When the RID2PASID entry of the shared pasid table has been filled by the first device, the subsequent device will encounter the "DMAR: Setup RID2PASID failed" failure as the pasid entry has already been marked as present. As the result, the IOMMU probing process will be aborted. On the contrary, when any alias device is hot-removed from the system, for example, by writing to /sys/bus/pci/devices/.../remove, the shared RID2PASID will be cleared without any notifications to other devices. As the result, any DMAs from those rest devices are blocked. Sharing pasid table among PCI alias devices could save two memory pages for devices underneath the PCIe-to-PCI bridges. Anyway, considering that those devices are rare on modern platforms that support VT-d in scalable mode and the saved memory is negligible, it's reasonable to remove this part of immature code to make the driver feasible and stable. Fixes: ef848b7e5a6a0 ("iommu/vt-d: Setup pasid entry for RID2PASID support") Reported-by: Chenyi Qiang Reported-by: Ethan Zhao Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Ethan Zhao Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220623065720.727849-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220625133430.2200315-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 24 ---------------- drivers/iommu/intel/pasid.c | 69 ++------------------------------------------- drivers/iommu/intel/pasid.h | 1 - include/linux/intel-iommu.h | 3 -- 4 files changed, 3 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 44016594831d..5c0dce78586a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -320,30 +320,6 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); -/* - * Iterate over elements in device_domain_list and call the specified - * callback @fn against each element. - */ -int for_each_device_domain(int (*fn)(struct device_domain_info *info, - void *data), void *data) -{ - int ret = 0; - unsigned long flags; - struct device_domain_info *info; - - spin_lock_irqsave(&device_domain_lock, flags); - list_for_each_entry(info, &device_domain_list, global) { - ret = fn(info, data); - if (ret) { - spin_unlock_irqrestore(&device_domain_lock, flags); - return ret; - } - } - spin_unlock_irqrestore(&device_domain_lock, flags); - - return 0; -} - const struct iommu_ops intel_iommu_ops; static bool translation_pre_enabled(struct intel_iommu *iommu) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index cb4c1d0cf25c..17cad7c1f62d 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -86,54 +86,6 @@ void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid) /* * Per device pasid table management: */ -static inline void -device_attach_pasid_table(struct device_domain_info *info, - struct pasid_table *pasid_table) -{ - info->pasid_table = pasid_table; - list_add(&info->table, &pasid_table->dev); -} - -static inline void -device_detach_pasid_table(struct device_domain_info *info, - struct pasid_table *pasid_table) -{ - info->pasid_table = NULL; - list_del(&info->table); -} - -struct pasid_table_opaque { - struct pasid_table **pasid_table; - int segment; - int bus; - int devfn; -}; - -static int search_pasid_table(struct device_domain_info *info, void *opaque) -{ - struct pasid_table_opaque *data = opaque; - - if (info->iommu->segment == data->segment && - info->bus == data->bus && - info->devfn == data->devfn && - info->pasid_table) { - *data->pasid_table = info->pasid_table; - return 1; - } - - return 0; -} - -static int get_alias_pasid_table(struct pci_dev *pdev, u16 alias, void *opaque) -{ - struct pasid_table_opaque *data = opaque; - - data->segment = pci_domain_nr(pdev->bus); - data->bus = PCI_BUS_NUM(alias); - data->devfn = alias & 0xff; - - return for_each_device_domain(&search_pasid_table, data); -} /* * Allocate a pasid table for @dev. It should be called in a @@ -143,28 +95,18 @@ int intel_pasid_alloc_table(struct device *dev) { struct device_domain_info *info; struct pasid_table *pasid_table; - struct pasid_table_opaque data; struct page *pages; u32 max_pasid = 0; - int ret, order; - int size; + int order, size; might_sleep(); info = dev_iommu_priv_get(dev); if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table)) return -EINVAL; - /* DMA alias device already has a pasid table, use it: */ - data.pasid_table = &pasid_table; - ret = pci_for_each_dma_alias(to_pci_dev(dev), - &get_alias_pasid_table, &data); - if (ret) - goto attach_out; - pasid_table = kzalloc(sizeof(*pasid_table), GFP_KERNEL); if (!pasid_table) return -ENOMEM; - INIT_LIST_HEAD(&pasid_table->dev); if (info->pasid_supported) max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)), @@ -182,9 +124,7 @@ int intel_pasid_alloc_table(struct device *dev) pasid_table->table = page_address(pages); pasid_table->order = order; pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3); - -attach_out: - device_attach_pasid_table(info, pasid_table); + info->pasid_table = pasid_table; return 0; } @@ -202,10 +142,7 @@ void intel_pasid_free_table(struct device *dev) return; pasid_table = info->pasid_table; - device_detach_pasid_table(info, pasid_table); - - if (!list_empty(&pasid_table->dev)) - return; + info->pasid_table = NULL; /* Free scalable mode PASID directory tables: */ dir = pasid_table->table; diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 583ea67fc783..bf5b937848b4 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -74,7 +74,6 @@ struct pasid_table { void *table; /* pasid table pointer */ int order; /* page order of pasid table */ u32 max_pasid; /* max pasid */ - struct list_head dev; /* device list */ }; /* Get PRESENT bit of a PASID directory entry. */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4f29139bbfc3..5fcf89faa31a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -612,7 +612,6 @@ struct intel_iommu { struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ - struct list_head table; /* link to pasid table */ u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ @@ -729,8 +728,6 @@ extern int dmar_ir_support(void); void *alloc_pgtable_page(int node); void free_pgtable_page(void *vaddr); struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); -int for_each_device_domain(int (*fn)(struct device_domain_info *info, - void *data), void *data); void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); -- cgit v1.2.3 From 3663a2fb325b8782524f3edb0ae32d6faa615109 Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Fri, 1 Jul 2022 01:33:29 +0800 Subject: video: of_display_timing.h: include errno.h If CONFIG_OF is not enabled, default of_get_display_timing() returns an errno, so include the header. Fixes: 422b67e0b31a ("videomode: provide dummy inline functions for !CONFIG_OF") Suggested-by: Stephen Boyd Signed-off-by: Hsin-Yi Wang Reviewed-by: Stephen Boyd Signed-off-by: Helge Deller --- include/video/of_display_timing.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/video/of_display_timing.h b/include/video/of_display_timing.h index e1126a74882a..eff166fdd81b 100644 --- a/include/video/of_display_timing.h +++ b/include/video/of_display_timing.h @@ -8,6 +8,8 @@ #ifndef __LINUX_OF_DISPLAY_TIMING_H #define __LINUX_OF_DISPLAY_TIMING_H +#include + struct device_node; struct display_timing; struct display_timings; -- cgit v1.2.3 From 5c629dc9609dc43492a7bc8060cc6120875bf096 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 6 Jul 2022 10:05:05 -0700 Subject: nvme: use struct group for generic command dwords This will allow the trace event to know the full size of the data intended to be copied and silence read overflow checks. Reported-by: John Garry Suggested-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/trace.h | 2 +- include/linux/nvme.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index b5f85259461a..37c7f4c89f92 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -69,7 +69,7 @@ TRACE_EVENT(nvme_setup_cmd, __entry->metadata = !!blk_integrity_rq(req); __entry->fctype = cmd->fabrics.fctype; __assign_disk_name(__entry->disk, req->q->disk); - memcpy(__entry->cdw10, &cmd->common.cdw10, + memcpy(__entry->cdw10, &cmd->common.cdws, sizeof(__entry->cdw10)); ), TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)", diff --git a/include/linux/nvme.h b/include/linux/nvme.h index e3934003f239..07cfc922f8e4 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -906,12 +906,14 @@ struct nvme_common_command { __le32 cdw2[2]; __le64 metadata; union nvme_data_ptr dptr; + struct_group(cdws, __le32 cdw10; __le32 cdw11; __le32 cdw12; __le32 cdw13; __le32 cdw14; __le32 cdw15; + ); }; struct nvme_rw_command { -- cgit v1.2.3 From e64242caef18b4a5840b0e7a9bff37abd4f4f933 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 25 Jun 2022 13:00:34 +0200 Subject: fbcon: Prevent that screen size is smaller than font size We need to prevent that users configure a screen size which is smaller than the currently selected font size. Otherwise rendering chars on the screen will access memory outside the graphics memory region. This patch adds a new function fbcon_modechange_possible() which implements this check and which later may be extended with other checks if necessary. The new function is called from the FBIOPUT_VSCREENINFO ioctl handler in fbmem.c, which will return -EINVAL if userspace asked for a too small screen size. Signed-off-by: Helge Deller Reviewed-by: Geert Uytterhoeven Cc: stable@vger.kernel.org # v5.4+ --- drivers/video/fbdev/core/fbcon.c | 28 ++++++++++++++++++++++++++++ drivers/video/fbdev/core/fbmem.c | 4 +++- include/linux/fbcon.h | 4 ++++ 3 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index a33532564393..5632870a9aeb 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2736,6 +2736,34 @@ void fbcon_update_vcs(struct fb_info *info, bool all) } EXPORT_SYMBOL(fbcon_update_vcs); +/* let fbcon check if it supports a new screen resolution */ +int fbcon_modechange_possible(struct fb_info *info, struct fb_var_screeninfo *var) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct vc_data *vc; + unsigned int i; + + WARN_CONSOLE_UNLOCKED(); + + if (!ops) + return 0; + + /* prevent setting a screen size which is smaller than font size */ + for (i = first_fb_vc; i <= last_fb_vc; i++) { + vc = vc_cons[i].d; + if (!vc || vc->vc_mode != KD_TEXT || + registered_fb[con2fb_map[i]] != info) + continue; + + if (vc->vc_font.width > FBCON_SWAP(var->rotate, var->xres, var->yres) || + vc->vc_font.height > FBCON_SWAP(var->rotate, var->yres, var->xres)) + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL_GPL(fbcon_modechange_possible); + int fbcon_mode_deleted(struct fb_info *info, struct fb_videomode *mode) { diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index ee63b5b47290..7dc6848a96bb 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1107,7 +1107,9 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, return -EFAULT; console_lock(); lock_fb_info(info); - ret = fb_set_var(info, &var); + ret = fbcon_modechange_possible(info, &var); + if (!ret) + ret = fb_set_var(info, &var); if (!ret) fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL); unlock_fb_info(info); diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h index ff5596dd30f8..2382dec6d6ab 100644 --- a/include/linux/fbcon.h +++ b/include/linux/fbcon.h @@ -15,6 +15,8 @@ void fbcon_new_modelist(struct fb_info *info); void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps); void fbcon_fb_blanked(struct fb_info *info, int blank); +int fbcon_modechange_possible(struct fb_info *info, + struct fb_var_screeninfo *var); void fbcon_update_vcs(struct fb_info *info, bool all); void fbcon_remap_all(struct fb_info *info); int fbcon_set_con2fb_map_ioctl(void __user *argp); @@ -33,6 +35,8 @@ static inline void fbcon_new_modelist(struct fb_info *info) {} static inline void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps) {} static inline void fbcon_fb_blanked(struct fb_info *info, int blank) {} +static inline int fbcon_modechange_possible(struct fb_info *info, + struct fb_var_screeninfo *var) { return 0; } static inline void fbcon_update_vcs(struct fb_info *info, bool all) {} static inline void fbcon_remap_all(struct fb_info *info) {} static inline int fbcon_set_con2fb_map_ioctl(void __user *argp) { return 0; } -- cgit v1.2.3 From bdb2c48e4b38e6dbe82533b437468999ba3ae498 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 7 Jul 2022 15:00:38 +0100 Subject: io_uring: explicit sqe padding for ioctl commands 32 bit sqe->cmd_op is an union with 64 bit values. It's always a good idea to do padding explicitly. Also zero check it in prep, so it can be used in the future if needed without compatibility concerns. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e6b95a05e970af79000435166185e85b196b2ba2.1657202417.git.asml.silence@gmail.com [axboe: turn bitwise OR into logical variant] Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- include/uapi/linux/io_uring.h | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 0d491ad15b66..cddc0e8490af 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5066,7 +5066,7 @@ static int io_uring_cmd_prep(struct io_kiocb *req, { struct io_uring_cmd *ioucmd = &req->uring_cmd; - if (sqe->rw_flags) + if (sqe->rw_flags || sqe->__pad1) return -EINVAL; ioucmd->cmd = sqe->cmd; ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f10b59d6693e..0ad3da28d2fc 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,7 +22,10 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; - __u32 cmd_op; + struct { + __u32 cmd_op; + __u32 __pad1; + }; }; union { __u64 addr; /* pointer to buffer or iovecs */ -- cgit v1.2.3 From f8d3da4ef8faf027261e06b7864583930dd7c7b9 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 6 Jul 2022 16:25:47 -0700 Subject: bpf: Add flags arg to bpf_dynptr_read and bpf_dynptr_write APIs Commit 13bbbfbea759 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write") added the bpf_dynptr_write() and bpf_dynptr_read() APIs. However, it will be needed for some dynptr types to pass in flags as well (e.g. when writing to a skb, the user may like to invalidate the hash or recompute the checksum). This patch adds a "u64 flags" arg to the bpf_dynptr_read() and bpf_dynptr_write() APIs before their UAPI signature freezes where we then cannot change them anymore with a 5.19.x released kernel. Fixes: 13bbbfbea759 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20220706232547.4016651-1-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 11 +++++++---- kernel/bpf/helpers.c | 12 ++++++++---- tools/include/uapi/linux/bpf.h | 11 +++++++---- tools/testing/selftests/bpf/progs/dynptr_fail.c | 10 +++++----- tools/testing/selftests/bpf/progs/dynptr_success.c | 4 ++-- 5 files changed, 29 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 225806a02efb..bb1254f07667 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1497,11 +1497,12 @@ const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) { int err; - if (!src->data) + if (!src->data || flags) return -EINVAL; err = bpf_dynptr_check_off_len(src, offset, len); @@ -1521,13 +1522,15 @@ const struct bpf_func_proto bpf_dynptr_read_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_DYNPTR, .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) { int err; - if (!dst->data || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); @@ -1547,6 +1550,7 @@ const struct bpf_func_proto bpf_dynptr_write_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..ef78e0e1a754 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5222,22 +5222,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index d811cff73597..0a26c243e6e9 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -140,12 +140,12 @@ int use_after_invalid(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(read_data), 0, &ptr); - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); return 0; } @@ -338,7 +338,7 @@ int invalid_helper2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0); return 0; } @@ -377,7 +377,7 @@ int invalid_write2(void *ctx) memcpy((void *)&ptr + 8, &x, sizeof(x)); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); bpf_ringbuf_submit_dynptr(&ptr, 0); @@ -473,7 +473,7 @@ int invalid_read2(void *ctx) get_map_val_dynptr(&ptr); /* this should fail */ - bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0); + bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 1, 0, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index d67be48df4b2..a3a6103c8569 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -43,10 +43,10 @@ int test_read_write(void *ctx) bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(write_data), 0, &ptr); /* Write data into the dynptr */ - err = err ?: bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data)); + err = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0); /* Read the data that was written into the dynptr */ - err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0); + err = err ?: bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); /* Ensure the data we read matches the data we wrote */ for (i = 0; i < sizeof(read_data); i++) { -- cgit v1.2.3 From 820b8963adaea34a87abbecb906d1f54c0aabfb7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Jul 2022 10:50:40 -0400 Subject: net: sock: tracing: Fix sock_exceed_buf_limit not to dereference stale pointer The trace event sock_exceed_buf_limit saves the prot->sysctl_mem pointer and then dereferences it in the TP_printk() portion. This is unsafe as the TP_printk() portion is executed at the time the buffer is read. That is, it can be seconds, minutes, days, months, even years later. If the proto is freed, then this dereference will can also lead to a kernel crash. Instead, save the sysctl_mem array into the ring buffer and have the TP_printk() reference that instead. This is the proper and safe way to read pointers in trace events. Link: https://lore.kernel.org/all/20220706052130.16368-12-kuniyu@amazon.com/ Cc: stable@vger.kernel.org Fixes: 3847ce32aea9f ("core: add tracepoints for queueing skb to rcvbuf") Signed-off-by: Steven Rostedt (Google) Acked-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/trace/events/sock.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index 12c315782766..777ee6cbe933 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -98,7 +98,7 @@ TRACE_EVENT(sock_exceed_buf_limit, TP_STRUCT__entry( __array(char, name, 32) - __field(long *, sysctl_mem) + __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) @@ -110,7 +110,9 @@ TRACE_EVENT(sock_exceed_buf_limit, TP_fast_assign( strncpy(__entry->name, prot->name, 32); - __entry->sysctl_mem = prot->sysctl_mem; + __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); + __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); + __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); -- cgit v1.2.3 From 310731e2f1611d1d13aae237abcf8e66d33345d5 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 6 Jul 2022 16:40:00 -0700 Subject: net: Fix data-races around sysctl_mem. While reading .sysctl_mem, it can be changed concurrently. So, we need to add READ_ONCE() to avoid data-races. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..9fa54762e077 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1529,7 +1529,7 @@ void __sk_mem_reclaim(struct sock *sk, int amount); /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = sk->sk_prot->sysctl_mem[index]; + long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); #if PAGE_SIZE > SK_MEM_QUANTUM val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -- cgit v1.2.3 From c39ba4de6b0a843bec5d46c2b6f2064428dada5e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 5 Jul 2022 11:41:59 +0200 Subject: netfilter: nf_tables: replace BUG_ON by element length check BUG_ON can be triggered from userspace with an element with a large userdata area. Replace it by length check and return EINVAL instead. Over time extensions have been growing in size. Pick a sufficiently old Fixes: tag to propagate this fix. Fixes: 7d7402642eaf ("netfilter: nf_tables: variable sized set element keys / data") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 14 +++++--- net/netfilter/nf_tables_api.c | 72 +++++++++++++++++++++++++++------------ 2 files changed, 60 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5c4e5a96a984..64cf655c818c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -657,18 +657,22 @@ static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) tmpl->len = sizeof(struct nft_set_ext); } -static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, - unsigned int len) +static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, + unsigned int len) { tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); - BUG_ON(tmpl->len > U8_MAX); + if (tmpl->len > U8_MAX) + return -EINVAL; + tmpl->offset[id] = tmpl->len; tmpl->len += nft_set_ext_types[id].len + len; + + return 0; } -static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) +static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) { - nft_set_ext_add_length(tmpl, id, 0); + return nft_set_ext_add_length(tmpl, id, 0); } static inline void nft_set_ext_init(struct nft_set_ext *ext, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d6b59beab3a9..646d5fd53604 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5833,8 +5833,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && @@ -5943,7 +5946,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_set_elem_expr; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto err_parse_key; } if (nla[NFTA_SET_ELEM_KEY_END]) { @@ -5952,22 +5957,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_parse_key; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto err_parse_key_end; } if (timeout > 0) { - nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); - if (timeout != set->timeout) - nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (err < 0) + goto err_parse_key_end; + + if (timeout != set->timeout) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + if (err < 0) + goto err_parse_key_end; + } } if (num_exprs) { for (i = 0; i < num_exprs; i++) size += expr_array[i]->ops->size; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, - sizeof(struct nft_set_elem_expr) + - size); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, + sizeof(struct nft_set_elem_expr) + size); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { @@ -5982,7 +5996,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = PTR_ERR(obj); goto err_parse_key_end; } - nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { @@ -6016,7 +6032,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + if (err < 0) + goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum @@ -6026,9 +6044,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); - if (ulen > 0) - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, - ulen); + if (ulen > 0) { + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, + ulen); + if (err < 0) + goto err_parse_data; + } } err = -ENOMEM; @@ -6256,8 +6277,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_prepare(&tmpl); - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, @@ -6265,16 +6289,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto fail_elem; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) - return err; + goto fail_elem; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto fail_elem_key_end; } err = -ENOMEM; @@ -6282,7 +6310,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, elem.key_end.val.data, NULL, 0, 0, GFP_KERNEL_ACCOUNT); if (elem.priv == NULL) - goto fail_elem; + goto fail_elem_key_end; ext = nft_set_elem_ext(set, elem.priv); if (flags) @@ -6306,6 +6334,8 @@ fail_ops: kfree(trans); fail_trans: kfree(elem.priv); +fail_elem_key_end: + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; -- cgit v1.2.3 From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 11 Jul 2022 18:16:25 +0200 Subject: fix race between exit_itimers() and /proc/pid/timers As Chris explains, the comment above exit_itimers() is not correct, we can race with proc_timers_seq_ops. Change exit_itimers() to clear signal->posix_timers with ->siglock held. Cc: Reported-by: chris@accessvector.net Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- include/linux/sched/task.h | 2 +- kernel/exit.c | 2 +- kernel/time/posix-timers.c | 19 ++++++++++++++----- 4 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/exec.c b/fs/exec.c index 0989fb8472a1..778123259e42 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm) bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS - exit_itimers(me->signal); + exit_itimers(me); flush_itimer_signals(); #endif diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 505aaf9fe477..81cab4b01edc 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk) extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); diff --git a/kernel/exit.c b/kernel/exit.c index f072959fcab7..64c938ce36fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); - exit_itimers(tsk->signal); + exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cd10b102c51..5dead89308b7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1051,15 +1051,24 @@ retry_delete: } /* - * This is called by do_exit or de_thread, only when there are no more - * references to the shared signal_struct. + * This is called by do_exit or de_thread, only when nobody else can + * modify the signal->posix_timers list. Yet we need sighand->siglock + * to prevent the race with /proc/pid/timers. */ -void exit_itimers(struct signal_struct *sig) +void exit_itimers(struct task_struct *tsk) { + struct list_head timers; struct k_itimer *tmr; - while (!list_empty(&sig->posix_timers)) { - tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + if (list_empty(&tsk->signal->posix_timers)) + return; + + spin_lock_irq(&tsk->sighand->siglock); + list_replace_init(&tsk->signal->posix_timers, &timers); + spin_unlock_irq(&tsk->sighand->siglock); + + while (!list_empty(&timers)) { + tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); } } -- cgit v1.2.3 From 0bb7e14c8e15ad78b7300e7d89a615ea8b8c89a9 Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Wed, 29 Jun 2022 11:00:13 +0800 Subject: blk-iocost: tracing: atomic64_read(&ioc->vtime_rate) is assigned an extra semicolon Remove extra semicolon. Link: https://lkml.kernel.org/r/20220629030013.10362-1-kunyu@nfschina.com Cc: Tejun Heo Cc: Jens Axboe Signed-off-by: Li kunyu Signed-off-by: Steven Rostedt (Google) --- include/trace/events/iocost.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index e282ce02fa2d..6d1626e7a4ce 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -160,7 +160,7 @@ TRACE_EVENT(iocost_ioc_vrate_adj, TP_fast_assign( __assign_str(devname, ioc_name(ioc)); - __entry->old_vrate = atomic64_read(&ioc->vtime_rate);; + __entry->old_vrate = atomic64_read(&ioc->vtime_rate); __entry->new_vrate = new_vrate; __entry->busy_level = ioc->busy_level; __entry->read_missed_ppm = missed_ppm[READ]; -- cgit v1.2.3 From 1dace014928e6e385363032d359a04dee9158af0 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Jul 2022 17:15:29 -0700 Subject: raw: Fix a data-race around sysctl_raw_l3mdev_accept. While reading sysctl_raw_l3mdev_accept, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 6897445fb194 ("net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/raw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/raw.h b/include/net/raw.h index 8ad8df594853..c51a635671a7 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -75,7 +75,7 @@ static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, + return inet_bound_dev_eq(READ_ONCE(net->ipv4.sysctl_raw_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); -- cgit v1.2.3 From af16df54b89dee72df253abc5e7b5e8a6d16c11c Mon Sep 17 00:00:00 2001 From: Coiby Xu Date: Wed, 13 Jul 2022 15:21:11 +0800 Subject: ima: force signature verification when CONFIG_KEXEC_SIG is configured Currently, an unsigned kernel could be kexec'ed when IMA arch specific policy is configured unless lockdown is enabled. Enforce kernel signature verification check in the kexec_file_load syscall when IMA arch specific policy is configured. Fixes: 99d5cadfde2b ("kexec_file: split KEXEC_VERIFY_SIG into KEXEC_SIG and KEXEC_SIG_FORCE") Reported-and-suggested-by: Mimi Zohar Signed-off-by: Coiby Xu Signed-off-by: Mimi Zohar --- include/linux/kexec.h | 6 ++++++ kernel/kexec_file.c | 11 ++++++++++- security/integrity/ima/ima_efi.c | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ce6536f1d269..475683cd67f1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -452,6 +452,12 @@ static inline int kexec_crash_loaded(void) { return 0; } #define kexec_in_progress false #endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_KEXEC_SIG +void set_kexec_sig_enforced(void); +#else +static inline void set_kexec_sig_enforced(void) {} +#endif + #endif /* !defined(__ASSEBMLY__) */ #endif /* LINUX_KEXEC_H */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 145321a5e798..f9261c07b048 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -29,6 +29,15 @@ #include #include "kexec_internal.h" +#ifdef CONFIG_KEXEC_SIG +static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE); + +void set_kexec_sig_enforced(void) +{ + sig_enforce = true; +} +#endif + static int kexec_calculate_store_digests(struct kimage *image); /* @@ -159,7 +168,7 @@ kimage_validate_signature(struct kimage *image) image->kernel_buf_len); if (ret) { - if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { + if (sig_enforce) { pr_notice("Enforced kernel signature verification failed (%d).\n", ret); return ret; } diff --git a/security/integrity/ima/ima_efi.c b/security/integrity/ima/ima_efi.c index 71786d01946f..9db66fe310d4 100644 --- a/security/integrity/ima/ima_efi.c +++ b/security/integrity/ima/ima_efi.c @@ -67,6 +67,8 @@ const char * const *arch_get_ima_policy(void) if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) { if (IS_ENABLED(CONFIG_MODULE_SIG)) set_module_sig_enforced(); + if (IS_ENABLED(CONFIG_KEXEC_SIG)) + set_kexec_sig_enforced(); return sb_arch_rules; } return NULL; -- cgit v1.2.3 From 3d8c51b25a235e283e37750943bbf356ef187230 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 14 Jul 2022 10:07:54 +0300 Subject: net/tls: Check for errors in tls_device_init Add missing error checks in tls_device_init. Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Reported-by: Jakub Kicinski Reviewed-by: Maxim Mikityanskiy Signed-off-by: Tariq Toukan Link: https://lore.kernel.org/r/20220714070754.1428-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/tls.h | 4 ++-- net/tls/tls_device.c | 4 ++-- net/tls/tls_main.c | 7 ++++++- 3 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 8017f1703447..8bd938f98bdd 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -704,7 +704,7 @@ int tls_sw_fallback_init(struct sock *sk, struct tls_crypto_info *crypto_info); #ifdef CONFIG_TLS_DEVICE -void tls_device_init(void); +int tls_device_init(void); void tls_device_cleanup(void); void tls_device_sk_destruct(struct sock *sk); int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); @@ -724,7 +724,7 @@ static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) return tls_get_ctx(sk)->rx_conf == TLS_HW; } #else -static inline void tls_device_init(void) {} +static inline int tls_device_init(void) { return 0; } static inline void tls_device_cleanup(void) {} static inline int diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index ec6f4b699a2b..ce827e79c66a 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1419,9 +1419,9 @@ static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; -void __init tls_device_init(void) +int __init tls_device_init(void) { - register_netdevice_notifier(&tls_dev_notifier); + return register_netdevice_notifier(&tls_dev_notifier); } void __exit tls_device_cleanup(void) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 2ffede463e4a..d80ab3d1764e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1048,7 +1048,12 @@ static int __init tls_register(void) if (err) return err; - tls_device_init(); + err = tls_device_init(); + if (err) { + unregister_pernet_subsys(&tls_proc_ops); + return err; + } + tcp_register_ulp(&tcp_tls_ulp_ops); return 0; -- cgit v1.2.3