From 1e76609cc1646c5222feefe86a3433a79be4fb73 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 7 Oct 2016 16:59:21 -0700 Subject: powerpc: implement arch_reserved_kernel_pages Currently significant amount of memory is reserved only in kernel booted to capture kernel dump using the fa_dump method. Kernels compiled with CONFIG_DEFERRED_STRUCT_PAGE_INIT will initialize only certain size memory per node. The certain size takes into account the dentry and inode cache sizes. Currently the cache sizes are calculated based on the total system memory including the reserved memory. However such a kernel when booting the same kernel as fadump kernel will not be able to allocate the required amount of memory to suffice for the dentry and inode caches. This results in crashes like Hence only implement arch_reserved_kernel_pages() for CONFIG_FA_DUMP configurations. The amount reserved will be reduced while calculating the large caches and will avoid crashes like the below on large systems such as 32 TB systems. Dentry cache hash table entries: 536870912 (order: 16, 4294967296 bytes) vmalloc: allocation failure, allocated 4097114112 of 17179934720 bytes swapper/0: page allocation failure: order:0, mode:0x2080020(GFP_ATOMIC) CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.6-master+ #3 Call Trace: dump_stack+0xb0/0xf0 (unreliable) warn_alloc_failed+0x114/0x160 __vmalloc_node_range+0x304/0x340 __vmalloc+0x6c/0x90 alloc_large_system_hash+0x1b8/0x2c0 inode_init+0x94/0xe4 vfs_caches_init+0x8c/0x13c start_kernel+0x50c/0x578 start_here_common+0x20/0xa8 Link: http://lkml.kernel.org/r/1472476010-4709-4-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Srikar Dronamraju Suggested-by: Mel Gorman Cc: Vlastimil Babka Cc: Michal Hocko Cc: Michael Ellerman Cc: Mahesh Salgaonkar Cc: Hari Bathini Cc: Dave Hansen Cc: Balbir Singh Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/mmzone.h | 3 +++ arch/powerpc/kernel/fadump.c | 5 +++++ 2 files changed, 8 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 7b589178be46..4d52ccfc2366 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -41,6 +41,9 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ +#ifdef CONFIG_FA_DUMP +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index b3a663333d36..eeb80de1f982 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -333,6 +333,11 @@ int __init fadump_reserve_mem(void) return 1; } +unsigned long __init arch_reserved_kernel_pages(void) +{ + return memblock_reserved_size() / PAGE_SIZE; +} + /* Look for fadump= cmdline option. */ static int __init early_fadump_param(char *p) { -- cgit v1.2.3 From 08ea8c07fb56d6eb8194d8ad408b469544bf2c29 Mon Sep 17 00:00:00 2001 From: Baoyou Xie Date: Fri, 7 Oct 2016 17:00:55 -0700 Subject: mm: move phys_mem_access_prot_allowed() declaration to pgtable.h We get 1 warning when building kernel with W=1: drivers/char/mem.c:220:12: warning: no previous prototype for 'phys_mem_access_prot_allowed' [-Wmissing-prototypes] int __weak phys_mem_access_prot_allowed(struct file *file, In fact, its declaration is spreading to several header files in different architecture, but need to be declare in common header file. So this patch moves phys_mem_access_prot_allowed() to pgtable.h. Link: http://lkml.kernel.org/r/1473751597-12139-1-git-send-email-baoyou.xie@linaro.org Signed-off-by: Baoyou Xie Acked-by: Thomas Gleixner Acked-by: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/pgtable.h | 2 -- arch/x86/include/asm/pgtable_types.h | 2 -- include/asm-generic/pgtable.h | 3 +++ 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 70128d3f770a..9e9e94415d08 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -673,8 +673,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); #endif /* diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f1218f512f62..8b4de22d6429 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -439,8 +439,6 @@ extern pgprot_t pgprot_writethrough(pgprot_t prot); struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); /* Install a pte for a particular vaddr in kernel space. */ void set_pte_vaddr(unsigned long vaddr, pte_t pte); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index d4458b6dbfb4..c4f8fd2fd384 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -800,6 +800,9 @@ static inline int pmd_clear_huge(pmd_t *pmd) #endif #endif +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range -- cgit v1.2.3 From 461a7184320a1b4d2c12ad538354062fef4ee0f1 Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Fri, 7 Oct 2016 17:01:46 -0700 Subject: mm/hugetlb: introduce ARCH_HAS_GIGANTIC_PAGE Avoid making ifdef get pretty unwieldy if many ARCHs support gigantic page. No functional change with this patch. Link: http://lkml.kernel.org/r/1475227569-63446-2-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie Suggested-by: Michal Hocko Acked-by: Michal Hocko Acked-by: Naoya Horiguchi Acked-by: Hillf Danton Cc: Hanjun Guo Cc: Will Deacon Cc: Dave Hansen Cc: Sudeep Holla Cc: Catalin Marinas Cc: Mark Rutland Cc: Rob Herring Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/Kconfig | 1 + arch/x86/Kconfig | 1 + fs/Kconfig | 3 +++ mm/hugetlb.c | 2 +- 4 files changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index deeadfa291ba..fb538031569a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -71,6 +71,7 @@ config S390 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN select ARCH_HAS_UBSAN_SANITIZE_ALL diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58bec8f9641a..827273c56ae9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,7 @@ config X86 select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE if X86_64 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_MMIO_FLUSH diff --git a/fs/Kconfig b/fs/Kconfig index 3ef62bad8f2b..4bd03a2b0518 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -200,6 +200,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config ARCH_HAS_GIGANTIC_PAGE + bool + source "fs/configfs/Kconfig" source "fs/efivarfs/Kconfig" diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 770d83eb3f48..e4a4500758f2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1022,7 +1022,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \ +#if defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) && \ ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_CMA)) static void destroy_compound_gigantic_page(struct page *page, -- cgit v1.2.3 From 14f099107aacea5ffa77d4fd3be52671e3925b93 Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Fri, 7 Oct 2016 17:01:49 -0700 Subject: arm64 Kconfig: select gigantic page Arm64 supports gigantic pages after commit 084bd29810a5 ("ARM64: mm: HugeTLB support.") however, it can only be allocated at boottime and can't be freed. This patch selects ARCH_HAS_GIGANTIC_PAGE to make gigantic pages can be allocated and freed at runtime for arch arm64. Link: http://lkml.kernel.org/r/1475227569-63446-3-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie Acked-by: Michal Hocko Acked-by: Catalin Marinas Acked-by: Hillf Danton Cc: Hanjun Guo Cc: Will Deacon Cc: Dave Hansen Cc: Sudeep Holla Cc: Mark Rutland Cc: Rob Herring Cc: Mike Kravetz Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 01600401a53e..c068aa689563 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -11,6 +11,7 @@ config ARM64 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST -- cgit v1.2.3 From 445ed0a0eac50d2a76441278a084554a4b9dcfda Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 7 Oct 2016 17:02:07 -0700 Subject: ia64: implement atomic64_dec_if_positive This is based on s390 version and needed to get rid of CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE Link: http://lkml.kernel.org/r/1473703083-8625-2-git-send-email-vgupta@synopsys.com Signed-off-by: Vineet Gupta Reported-by: kbuild test robot Cc: Tony Luck Cc: Fenghua Yu Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/atomic.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch') diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index f565ad376142..65d4bb2b6685 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -269,6 +269,22 @@ static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +static __inline__ long atomic64_dec_if_positive(atomic64_t *v) +{ + long c, old, dec; + c = atomic64_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic64_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + /* * Atomically add I to V and return TRUE if the resulting value is * negative. -- cgit v1.2.3 From 51a021244b9d579be6b4f8c15c493a76deb2a79e Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 7 Oct 2016 17:02:10 -0700 Subject: atomic64: no need for CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE This came to light when implementing native 64-bit atomics for ARCv2. The atomic64 self-test code uses CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE to check whether atomic64_dec_if_positive() is available. It seems it was needed when not every arch defined it. However as of current code the Kconfig option seems needless - for CONFIG_GENERIC_ATOMIC64 it is auto-enabled in lib/Kconfig and a generic definition of API is present lib/atomic64.c - arches with native 64-bit atomics select it in arch/*/Kconfig and define the API in their headers So I see no point in keeping the Kconfig option Compile tested for: - blackfin (CONFIG_GENERIC_ATOMIC64) - x86 (!CONFIG_GENERIC_ATOMIC64) - ia64 Link: http://lkml.kernel.org/r/1473703083-8625-3-git-send-email-vgupta@synopsys.com Signed-off-by: Vineet Gupta Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Vineet Gupta Cc: Zhaoxiu Zeng Cc: Linus Walleij Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Herbert Xu Cc: Ming Lin Cc: Arnd Bergmann Cc: Geert Uytterhoeven Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Andi Kleen Cc: Boqun Feng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/tile/Kconfig | 1 - arch/x86/Kconfig | 1 - lib/Kconfig | 3 --- lib/atomic64_test.c | 4 ---- 12 files changed, 17 deletions(-) (limited to 'arch') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 7f312d80b43b..0e49d39ea74a 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -15,7 +15,6 @@ config ALPHA select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select ARCH_HAVE_NMI_SAFE_CMPXCHG - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select AUDIT_ARCH select GENERIC_CLOCKEVENTS select GENERIC_SMP_IDLE_THREAD diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3cd9042fbb62..c297bc5e341c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2,7 +2,6 @@ config ARM bool default y select ARCH_CLOCKSOURCE_DATA - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c068aa689563..30398dbc940a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -8,7 +8,6 @@ config ARM64 select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 212ff92920d2..1a322c807f22 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -30,7 +30,6 @@ config MIPS select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select RTC_LIB if !MACH_LOONGSON64 select GENERIC_ATOMIC64 if !64BIT - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_DMA_CONTIGUOUS select HAVE_DMA_API_DEBUG select GENERIC_IRQ_PROBE diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index af12c2db9bb8..8a96bdcc3807 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -14,7 +14,6 @@ config PARISC select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select BROKEN_RODATA select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 927d2ab2ce08..18d1b42cf545 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -113,7 +113,6 @@ config PPC select HAVE_DEBUG_KMEMLEAK select ARCH_HAS_SG_CHAIN select GENERIC_ATOMIC64 if PPC32 - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index fb538031569a..426481d4cc86 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -67,7 +67,6 @@ config DEBUG_RODATA config S390 def_bool y - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index f5d60f14a0bc..b23c76b42d6e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -22,7 +22,6 @@ config SPARC select HAVE_ARCH_TRACEHOOK select HAVE_EXIT_THREAD select SYSCTL_EXCEPTION_TRACE - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select RTC_CLASS select RTC_DRV_M48T59 select RTC_SYSTOHC diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 78da75b670bc..4583c0320059 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -3,7 +3,6 @@ config TILE def_bool y - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 827273c56ae9..bada636d1065 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,7 +23,6 @@ config X86 select ARCH_CLOCKSOURCE_DATA select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER diff --git a/lib/Kconfig b/lib/Kconfig index d79909dc01ec..0e74df3c5441 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -457,9 +457,6 @@ config NLATTR config GENERIC_ATOMIC64 bool -config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - def_bool y if GENERIC_ATOMIC64 - config LRU_CACHE tristate diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index dbb369145dda..46042901130f 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -213,7 +213,6 @@ static __init void test_atomic64(void) r += one; BUG_ON(v.counter != r); -#ifdef CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE INIT(onestwos); BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1)); r -= one; @@ -226,9 +225,6 @@ static __init void test_atomic64(void) INIT(-one); BUG_ON(atomic64_dec_if_positive(&v) != (-one - one)); BUG_ON(v.counter != r); -#else -#warning Please implement atomic64_dec_if_positive for your architecture and select the above Kconfig symbol -#endif INIT(onestwos); BUG_ON(!atomic64_inc_not_zero(&v)); -- cgit v1.2.3 From 9a01c3ed5cdb35d9004eb92510ee6ea11b4a5f16 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:45 -0700 Subject: nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Tested-by: Daniel Thompson [arm] Reviewed-by: Aaron Tomlin Reviewed-by: Petr Mladek Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Ralf Baechle Cc: David Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/irq.h | 5 +++-- arch/arm/kernel/smp.c | 4 ++-- arch/mips/include/asm/irq.h | 5 +++-- arch/mips/kernel/process.c | 11 +++++++++-- arch/sparc/include/asm/irq_64.h | 5 +++-- arch/sparc/kernel/process_64.c | 10 +++++----- arch/x86/include/asm/irq.h | 5 +++-- arch/x86/kernel/apic/hw_nmi.c | 18 +++++++++--------- include/linux/nmi.h | 31 ++++++++++++++++++++++++++----- lib/nmi_backtrace.c | 17 +++++++++-------- 10 files changed, 72 insertions(+), 39 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 1bd9510de1b9..e53638c8ed8a 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -36,8 +36,9 @@ extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); #endif #ifdef CONFIG_SMP -extern void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x) +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif static inline int nr_legacy_irqs(void) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 937c8920d741..5abc5697e4e5 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -760,7 +760,7 @@ static void raise_nmi(cpumask_t *mask) smp_cross_call(mask, IPI_CPU_BACKTRACE); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, raise_nmi); + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_nmi); } diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 15e0fecbc300..6bf10e796553 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -51,7 +51,8 @@ extern int cp0_fdc_irq; extern int get_c0_fdc_int(void); -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif /* _ASM_IRQ_H */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index d2d061520a23..9514e5f2209f 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -569,9 +569,16 @@ static void arch_dump_stack(void *info) dump_stack(); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - smp_call_function(arch_dump_stack, NULL, 1); + long this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) + dump_stack(); + + smp_call_function_many(mask, arch_dump_stack, NULL, 1); + + put_cpu(); } int mips_get_process_fp_mode(struct task_struct *task) diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 3f70f900e834..1d51a11fb261 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -86,8 +86,9 @@ static inline unsigned long get_softint(void) return retval; } -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace extern void *hardirq_stack[NR_CPUS]; extern void *softirq_stack[NR_CPUS]; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index fa14402b33f9..47ff5588e521 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) } } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { struct thread_info *tp = current_thread_info(); struct pt_regs *regs = get_irq_regs(); @@ -255,15 +255,15 @@ void arch_trigger_all_cpu_backtrace(bool include_self) memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); - if (include_self) + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) __global_reg_self(tp, regs, this_cpu); smp_fetch_global_regs(); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, mask) { struct global_reg_snapshot *gp; - if (!include_self && cpu == this_cpu) + if (exclude_self && cpu == this_cpu) continue; gp = &global_cpu_snapshot[cpu].reg; @@ -300,7 +300,7 @@ void arch_trigger_all_cpu_backtrace(bool include_self) static void sysrq_handle_globreg(int key) { - arch_trigger_all_cpu_backtrace(true); + trigger_all_cpu_backtrace(); } static struct sysrq_key_op sparc_globalreg_op = { diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index e7de5c9a4fbd..16d3fa211962 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -50,8 +50,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index f29501e1a5c1..c73c9fb281e1 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -26,32 +26,32 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) } #endif -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static void nmi_raise_cpu_backtrace(cpumask_t *mask) { apic->send_IPI_mask(mask, NMI_VECTOR); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); + nmi_trigger_cpumask_backtrace(mask, exclude_self, + nmi_raise_cpu_backtrace); } -static int -arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) +static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { if (nmi_cpu_backtrace(regs)) return NMI_HANDLED; return NMI_DONE; } -NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); +NOKPROBE_SYMBOL(nmi_cpu_backtrace_handler); -static int __init register_trigger_all_cpu_backtrace(void) +static int __init register_nmi_cpu_backtrace_handler(void) { - register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler, + register_nmi_handler(NMI_LOCAL, nmi_cpu_backtrace_handler, 0, "arch_bt"); return 0; } -early_initcall(register_trigger_all_cpu_backtrace); +early_initcall(register_nmi_cpu_backtrace_handler); #endif diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..a78c35cff1ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {} * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(true); - + arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } + static inline bool trigger_allbutself_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(false); + arch_trigger_cpumask_backtrace(cpu_online_mask, true); + return true; +} + +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + arch_trigger_cpumask_backtrace(mask, false); + return true; +} + +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); @@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + return false; +} +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 26caf51cc238..df347e355267 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -17,20 +17,21 @@ #include #include -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; -/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +/* "in progress" flag of arch_trigger_cpumask_backtrace */ static unsigned long backtrace_flag; /* - * When raise() is called it will be is passed a pointer to the + * When raise() is called it will be passed a pointer to the * backtrace_mask. Architectures that call nmi_cpu_backtrace() * directly from their raise() functions may rely on the mask * they are passed being updated as a side effect of this call. */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)) { int i, this_cpu = get_cpu(); @@ -44,13 +45,13 @@ void nmi_trigger_all_cpu_backtrace(bool include_self, return; } - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - if (!include_self) + cpumask_copy(to_cpumask(backtrace_mask), mask); + if (exclude_self) cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); if (!cpumask_empty(to_cpumask(backtrace_mask))) { - pr_info("Sending NMI to %s CPUs:\n", - (include_self ? "all" : "other")); + pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", + this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); raise(to_cpumask(backtrace_mask)); } -- cgit v1.2.3 From 677664895278267a80bda0e3b26821d60cdbebf5 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:49 -0700 Subject: nmi_backtrace: do a local dump_stack() instead of a self-NMI Currently on arm there is code that checks whether it should call dump_stack() explicitly, to avoid trying to raise an NMI when the current context is not preemptible by the backtrace IPI. Similarly, the forthcoming arch/tile support uses an IPI mechanism that does not support generating an NMI to self. Accordingly, move the code that guards this case into the generic mechanism, and invoke it unconditionally whenever we want a backtrace of the current cpu. It seems plausible that in all cases, dump_stack() will generate better information than generating a stack from the NMI handler. The register state will be missing, but that state is likely not particularly helpful in any case. Or, if we think it is helpful, we should be capturing and emitting the current register state in all cases when regs == NULL is passed to nmi_cpu_backtrace(). Link: http://lkml.kernel.org/r/1472487169-14923-3-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Tested-by: Daniel Thompson [arm] Reviewed-by: Petr Mladek Acked-by: Aaron Tomlin Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/smp.c | 9 --------- lib/nmi_backtrace.c | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 5abc5697e4e5..7dd14e8395e6 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -748,15 +748,6 @@ core_initcall(register_cpufreq_notifier); static void raise_nmi(cpumask_t *mask) { - /* - * Generate the backtrace directly if we are running in a calling - * context that is not preemptible by the backtrace IPI. Note - * that nmi_cpu_backtrace() automatically removes the current cpu - * from mask. - */ - if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled()) - nmi_cpu_backtrace(NULL); - smp_cross_call(mask, IPI_CPU_BACKTRACE); } diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index df347e355267..393a3cca1f47 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -49,6 +49,15 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, if (exclude_self) cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); + /* + * Don't try to send an NMI to this cpu; it may work on some + * architectures, but on others it may not, and we'll get + * information at least as useful just by doing a dump_stack() here. + * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit. + */ + if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask))) + nmi_cpu_backtrace(NULL); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); -- cgit v1.2.3 From 511f8389454e55ece5115dc3bc84a0947788ff4f Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:52 -0700 Subject: arch/tile: adopt the new nmi_backtrace framework Previously tile was rolling its own method of capturing backtrace data in the NMI handlers, but it was relying on running printk() from the NMI handler, which is not always safe. So adopt the nmi_backtrace model (with the new cpumask extension) instead. So we can call the nmi_backtrace code directly from the nmi handler, move the nmi_enter()/exit() into the top-level tile NMI handler. The semantics of the routine change slightly since it is now synchronous with the remote cores completing the backtraces. Previously it was asynchronous, but with protection to avoid starting a new remote backtrace if the old one was still in progress. Link: http://lkml.kernel.org/r/1472487169-14923-4-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Cc: Daniel Thompson [arm] Cc: Petr Mladek Cc: Aaron Tomlin Cc: Peter Zijlstra (Intel) Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/tile/include/asm/irq.h | 5 ++-- arch/tile/kernel/pmc.c | 3 -- arch/tile/kernel/process.c | 73 +++++++++++---------------------------------- arch/tile/kernel/traps.c | 9 ++++-- 4 files changed, 27 insertions(+), 63 deletions(-) (limited to 'arch') diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h index 84a924034bdb..1fa1f2544ff9 100644 --- a/arch/tile/include/asm/irq.h +++ b/arch/tile/include/asm/irq.h @@ -79,8 +79,9 @@ void tile_irq_activate(unsigned int irq, int tile_irq_type); void setup_irq_regs(void); #ifdef __tilegx__ -void arch_trigger_all_cpu_backtrace(bool self); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif #endif /* _ASM_TILE_IRQ_H */ diff --git a/arch/tile/kernel/pmc.c b/arch/tile/kernel/pmc.c index db62cc34b955..81cf8743a3f3 100644 --- a/arch/tile/kernel/pmc.c +++ b/arch/tile/kernel/pmc.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -29,9 +28,7 @@ int handle_perf_interrupt(struct pt_regs *regs, int fault) if (!perf_irq) panic("Unexpected PERF_COUNT interrupt %d\n", fault); - nmi_enter(); retval = perf_irq(regs, fault); - nmi_exit(); return retval; } diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index a465d8372edd..9f37106ef93a 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include @@ -594,66 +594,18 @@ void show_regs(struct pt_regs *regs) tile_show_stack(&kbt); } -/* To ensure stack dump on tiles occurs one by one. */ -static DEFINE_SPINLOCK(backtrace_lock); -/* To ensure no backtrace occurs before all of the stack dump are done. */ -static atomic_t backtrace_cpus; -/* The cpu mask to avoid reentrance. */ -static struct cpumask backtrace_mask; - -void do_nmi_dump_stack(struct pt_regs *regs) -{ - int is_idle = is_idle_task(current) && !in_interrupt(); - int cpu; - - nmi_enter(); - cpu = smp_processor_id(); - if (WARN_ON_ONCE(!cpumask_test_and_clear_cpu(cpu, &backtrace_mask))) - goto done; - - spin_lock(&backtrace_lock); - if (is_idle) - pr_info("CPU: %d idle\n", cpu); - else - show_regs(regs); - spin_unlock(&backtrace_lock); - atomic_dec(&backtrace_cpus); -done: - nmi_exit(); -} - #ifdef __tilegx__ -void arch_trigger_all_cpu_backtrace(bool self) +void nmi_raise_cpu_backtrace(struct cpumask *in_mask) { struct cpumask mask; HV_Coord tile; unsigned int timeout; int cpu; - int ongoing; HV_NMI_Info info[NR_CPUS]; - ongoing = atomic_cmpxchg(&backtrace_cpus, 0, num_online_cpus() - 1); - if (ongoing != 0) { - pr_err("Trying to do all-cpu backtrace.\n"); - pr_err("But another all-cpu backtrace is ongoing (%d cpus left)\n", - ongoing); - if (self) { - pr_err("Reporting the stack on this cpu only.\n"); - dump_stack(); - } - return; - } - - cpumask_copy(&mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &mask); - cpumask_copy(&backtrace_mask, &mask); - - /* Backtrace for myself first. */ - if (self) - dump_stack(); - /* Tentatively dump stack on remote tiles via NMI. */ timeout = 100; + cpumask_copy(&mask, in_mask); while (!cpumask_empty(&mask) && timeout) { for_each_cpu(cpu, &mask) { tile.x = cpu_x(cpu); @@ -664,12 +616,17 @@ void arch_trigger_all_cpu_backtrace(bool self) } mdelay(10); + touch_softlockup_watchdog(); timeout--; } - /* Warn about cpus stuck in ICS and decrement their counts here. */ + /* Warn about cpus stuck in ICS. */ if (!cpumask_empty(&mask)) { for_each_cpu(cpu, &mask) { + + /* Clear the bit as if nmi_cpu_backtrace() ran. */ + cpumask_clear_cpu(cpu, in_mask); + switch (info[cpu].result) { case HV_NMI_RESULT_FAIL_ICS: pr_warn("Skipping stack dump of cpu %d in ICS at pc %#llx\n", @@ -680,16 +637,20 @@ void arch_trigger_all_cpu_backtrace(bool self) cpu); break; case HV_ENOSYS: - pr_warn("Hypervisor too old to allow remote stack dumps.\n"); - goto skip_for_each; + WARN_ONCE(1, "Hypervisor too old to allow remote stack dumps.\n"); + break; default: /* should not happen */ pr_warn("Skipping stack dump of cpu %d [%d,%#llx]\n", cpu, info[cpu].result, info[cpu].pc); break; } } -skip_for_each: - atomic_sub(cpumask_weight(&mask), &backtrace_cpus); } } + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, + nmi_raise_cpu_backtrace); +} #endif /* __tilegx_ */ diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c index 4d9651c5b1ad..39f427bb0de2 100644 --- a/arch/tile/kernel/traps.c +++ b/arch/tile/kernel/traps.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include #include @@ -392,14 +394,17 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num, void do_nmi(struct pt_regs *regs, int fault_num, unsigned long reason) { + nmi_enter(); switch (reason) { +#ifdef arch_trigger_cpumask_backtrace case TILE_NMI_DUMP_STACK: - do_nmi_dump_stack(regs); + nmi_cpu_backtrace(regs); break; +#endif default: panic("Unexpected do_nmi type %ld", reason); - return; } + nmi_exit(); } /* Deprecated function currently only used here. */ -- cgit v1.2.3 From 6727ad9e206cc08b80d8000a4d67f8417e53539d Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:55 -0700 Subject: nmi_backtrace: generate one-line reports for idle cpus When doing an nmi backtrace of many cores, most of which are idle, the output is a little overwhelming and very uninformative. Suppress messages for cpus that are idling when they are interrupted and just emit one line, "NMI backtrace for N skipped: idling at pc 0xNNN". We do this by grouping all the cpuidle code together into a new .cpuidle.text section, and then checking the address of the interrupted PC to see if it lies within that section. This commit suitably tags x86 and tile idle routines, and only adds in the minimal framework for other architectures. Link: http://lkml.kernel.org/r/1472487169-14923-5-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Acked-by: Peter Zijlstra (Intel) Tested-by: Peter Zijlstra (Intel) Tested-by: Daniel Thompson [arm] Tested-by: Petr Mladek Cc: Aaron Tomlin Cc: Peter Zijlstra (Intel) Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/vmlinux.lds.S | 1 + arch/arc/kernel/vmlinux.lds.S | 1 + arch/arm/kernel/vmlinux-xip.lds.S | 1 + arch/arm/kernel/vmlinux.lds.S | 1 + arch/arm64/kernel/vmlinux.lds.S | 1 + arch/avr32/kernel/vmlinux.lds.S | 1 + arch/blackfin/kernel/vmlinux.lds.S | 1 + arch/c6x/kernel/vmlinux.lds.S | 1 + arch/cris/kernel/vmlinux.lds.S | 1 + arch/frv/kernel/vmlinux.lds.S | 1 + arch/h8300/kernel/vmlinux.lds.S | 1 + arch/hexagon/kernel/vmlinux.lds.S | 1 + arch/ia64/kernel/vmlinux.lds.S | 1 + arch/m32r/kernel/vmlinux.lds.S | 1 + arch/m68k/kernel/vmlinux-nommu.lds | 1 + arch/m68k/kernel/vmlinux-std.lds | 1 + arch/m68k/kernel/vmlinux-sun3.lds | 1 + arch/metag/kernel/vmlinux.lds.S | 1 + arch/microblaze/kernel/vmlinux.lds.S | 1 + arch/mips/kernel/vmlinux.lds.S | 1 + arch/mn10300/kernel/vmlinux.lds.S | 1 + arch/nios2/kernel/vmlinux.lds.S | 1 + arch/openrisc/kernel/vmlinux.lds.S | 1 + arch/parisc/kernel/vmlinux.lds.S | 1 + arch/powerpc/kernel/vmlinux.lds.S | 1 + arch/s390/kernel/vmlinux.lds.S | 1 + arch/score/kernel/vmlinux.lds.S | 1 + arch/sh/kernel/vmlinux.lds.S | 1 + arch/sparc/kernel/vmlinux.lds.S | 1 + arch/tile/kernel/entry.S | 2 +- arch/tile/kernel/vmlinux.lds.S | 1 + arch/um/kernel/dyn.lds.S | 1 + arch/um/kernel/uml.lds.S | 1 + arch/unicore32/kernel/vmlinux.lds.S | 1 + arch/x86/include/asm/irqflags.h | 12 ++++++++---- arch/x86/kernel/acpi/cstate.c | 2 +- arch/x86/kernel/process.c | 4 ++-- arch/x86/kernel/vmlinux.lds.S | 1 + arch/xtensa/kernel/vmlinux.lds.S | 3 +++ drivers/acpi/processor_idle.c | 5 +++-- drivers/cpuidle/driver.c | 5 +++-- drivers/idle/intel_idle.c | 4 ++-- include/asm-generic/vmlinux.lds.h | 6 ++++++ include/linux/cpu.h | 5 +++++ kernel/sched/idle.c | 13 +++++++++++-- lib/nmi_backtrace.c | 16 +++++++++++----- scripts/mod/modpost.c | 2 +- scripts/recordmcount.c | 1 + scripts/recordmcount.pl | 1 + 49 files changed, 93 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 647b84c15382..cebecfb76fbf 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -22,6 +22,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 36611072305f..f35ed578e007 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -89,6 +89,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index cba1ec899a69..7fa487ef7e2f 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -98,6 +98,7 @@ SECTIONS IRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.warning) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index d24e5dd2aa7a..f7f55df0bf7b 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -111,6 +111,7 @@ SECTIONS SOFTIRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT HYPERVISOR_TEXT KPROBES_TEXT diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 5ce9b2929e0d..1105aab1e6d6 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -122,6 +122,7 @@ SECTIONS ENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT HYPERVISOR_TEXT diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S index a4589176bed5..17f2730eb497 100644 --- a/arch/avr32/kernel/vmlinux.lds.S +++ b/arch/avr32/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS KPROBES_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S index d920b959ff3a..68069a120055 100644 --- a/arch/blackfin/kernel/vmlinux.lds.S +++ b/arch/blackfin/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS #ifndef CONFIG_SCHEDULE_L1 SCHED_TEXT #endif + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S index 50bc10f97bcb..a1a5c166bc9b 100644 --- a/arch/c6x/kernel/vmlinux.lds.S +++ b/arch/c6x/kernel/vmlinux.lds.S @@ -70,6 +70,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index 7552c2557506..979586261520 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -43,6 +43,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.text.__*) diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S index 7e958d829ec9..aa6e573d57da 100644 --- a/arch/frv/kernel/vmlinux.lds.S +++ b/arch/frv/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS *(.text..tlbmiss) TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #ifdef CONFIG_DEBUG_INFO INIT_TEXT diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S index cb5dfb02c88d..7f11da1b895e 100644 --- a/arch/h8300/kernel/vmlinux.lds.S +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -29,6 +29,7 @@ SECTIONS _stext = . ; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #if defined(CONFIG_ROMKERNEL) *(.int_redirect) diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 5f268c1071b3..ec87e67feb19 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index dc506b05ffbd..f89d20c97412 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ SECTIONS { __end_ivt_text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.linkonce.t*) diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 018e4a711d79..ad1fe56455aa 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -31,6 +31,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 06a763f49fd3..d2c8abf1c8c4 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -45,6 +45,7 @@ SECTIONS { HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) . = ALIGN(16); diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index d0993594f558..5b5ce1e4d1ed 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 8080469ee6c1..fe5ea1974b16 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S index 150ace92c7ad..e6c700eaf207 100644 --- a/arch/metag/kernel/vmlinux.lds.S +++ b/arch/metag/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index 0a47f0410554..289d0e7f3e3a 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS { EXIT_TEXT EXIT_CALL SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a82c178d0bb9..d5de67591735 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -55,6 +55,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S index 13c4814c29f8..2d5f1c3f1afb 100644 --- a/arch/mn10300/kernel/vmlinux.lds.S +++ b/arch/mn10300/kernel/vmlinux.lds.S @@ -30,6 +30,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index e23e89539967..6a8045bb1a77 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index d936de4c07ca..d68b9ede8423 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -47,6 +47,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index f3ead0b6ce46..9ec8ec075dae 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -69,6 +69,7 @@ SECTIONS .text ALIGN(PAGE_SIZE) : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b5fba689fca6..7ed59f0d947f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 429bfd111961..000e6e91f6a0 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -35,6 +35,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S index 7274b5c4287e..4117890b1db1 100644 --- a/arch/score/kernel/vmlinux.lds.S +++ b/arch/score/kernel/vmlinux.lds.S @@ -40,6 +40,7 @@ SECTIONS _text = .; /* Text and read-only data */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.text.*) diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 235a4101999f..5b9a3cc90c58 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -36,6 +36,7 @@ SECTIONS TEXT_TEXT EXTRA_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index d79b3b734245..572db686f845 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -49,6 +49,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S index 670a3569450f..101de132e363 100644 --- a/arch/tile/kernel/entry.S +++ b/arch/tile/kernel/entry.S @@ -50,7 +50,7 @@ STD_ENTRY(smp_nap) * When interrupted at _cpu_idle_nap, we bump the PC forward 8, and * as a result return to the function that called _cpu_idle(). */ -STD_ENTRY(_cpu_idle) +STD_ENTRY_SECTION(_cpu_idle, .cpuidle.text) movei r1, 1 IRQ_ENABLE_LOAD(r2, r3) mtspr INTERRUPT_CRITICAL_SECTION, r1 diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 9d449caf8910..e1baf094fba4 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -42,6 +42,7 @@ SECTIONS .text : AT (ADDR(.text) - LOAD_OFFSET) { HEAD_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index adde088aeeff..4fdbcf958cd5 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -68,6 +68,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.stub .text.* .gnu.linkonce.t.*) diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 6899195602b7..1840f55ed042 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -28,6 +28,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) /* .gnu.warning sections are handled specially by elf32.em. */ diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S index 77e407e49a63..56e788e8ee83 100644 --- a/arch/unicore32/kernel/vmlinux.lds.S +++ b/arch/unicore32/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { /* Real text segment */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index b77f5edb03b0..ac7692dcfa2e 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -4,6 +4,10 @@ #include #ifndef __ASSEMBLY__ + +/* Provide __cpuidle; we can't safely include */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + /* * Interrupt control: */ @@ -44,12 +48,12 @@ static inline void native_irq_enable(void) asm volatile("sti": : :"memory"); } -static inline void native_safe_halt(void) +static inline __cpuidle void native_safe_halt(void) { asm volatile("sti; hlt": : :"memory"); } -static inline void native_halt(void) +static inline __cpuidle void native_halt(void) { asm volatile("hlt": : :"memory"); } @@ -86,7 +90,7 @@ static inline notrace void arch_local_irq_enable(void) * Used in the idle loop; sti takes one instruction cycle * to complete: */ -static inline void arch_safe_halt(void) +static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } @@ -95,7 +99,7 @@ static inline void arch_safe_halt(void) * Used when interrupts are already enabled or to * shutdown the processor: */ -static inline void halt(void) +static inline __cpuidle void halt(void) { native_halt(); } diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index bdfad642123f..af15f4444330 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -152,7 +152,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) +void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); struct cstate_entry *percpu_entry; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4002b475171c..28cea7802ecb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -302,7 +302,7 @@ void arch_cpu_idle(void) /* * We use this if we don't have any better idle routine.. */ -void default_idle(void) +void __cpuidle default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); @@ -417,7 +417,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with interrupts enabled and no flags, which is backwards compatible with the * original MWAIT implementation. */ -static void mwait_idle(void) +static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9297a002d8e5..dbf67f64d5ec 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -97,6 +97,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT ENTRY_TEXT diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index 72cfe3587dd8..31411fc82662 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -89,6 +89,9 @@ SECTIONS VMLINUX_SYMBOL(__sched_text_start) = .; *(.sched.literal .sched.text) VMLINUX_SYMBOL(__sched_text_end) = .; + VMLINUX_SYMBOL(__cpuidle_text_start) = .; + *(.cpuidle.literal .cpuidle.text) + VMLINUX_SYMBOL(__cpuidle_text_end) = .; VMLINUX_SYMBOL(__lock_text_start) = .; *(.spinlock.literal .spinlock.text) VMLINUX_SYMBOL(__lock_text_end) = .; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index cea52528aa18..2237d3f24f0e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -31,6 +31,7 @@ #include /* need_resched() */ #include #include +#include #include /* @@ -115,7 +116,7 @@ static const struct dmi_system_id processor_power_dmi_table[] = { * Callers should disable interrupts before the call and enable * interrupts after return. */ -static void acpi_safe_halt(void) +static void __cpuidle acpi_safe_halt(void) { if (!tif_need_resched()) { safe_halt(); @@ -645,7 +646,7 @@ static int acpi_idle_bm_check(void) * * Caller disables interrupt before call and enables interrupt after return. */ -static void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 389ade4572be..ab264d393233 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -178,8 +179,8 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) } #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static int __cpuidle poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { local_irq_enable(); if (!current_set_polling_and_test()) { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 67ec58f9ef99..4466a2f969d7 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -863,8 +863,8 @@ static struct cpuidle_state dnv_cstates[] = { * * Must be called under local_irq_disable(). */ -static int intel_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __cpuidle int intel_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { unsigned long ecx = 1; /* break on interrupt flag */ struct cpuidle_state *state = &drv->states[index]; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 24563970ff7b..3e42bcdd014b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -454,6 +454,12 @@ *(.spinlock.text) \ VMLINUX_SYMBOL(__lock_text_end) = .; +#define CPUIDLE_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__cpuidle_text_start) = .; \ + *(.cpuidle.text) \ + VMLINUX_SYMBOL(__cpuidle_text_end) = .; + #define KPROBES_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__kprobes_text_start) = .; \ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7572d9e9dced..b886dc17f2f3 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -231,6 +231,11 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); +/* Attach to any functions which should be considered cpuidle. */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + +bool cpu_in_idle(unsigned long pc); + void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 9fb873cfc75c..1d8718d5300d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -16,6 +16,9 @@ #include "sched.h" +/* Linker adds these: start and end of __cpuidle functions */ +extern char __cpuidle_text_start[], __cpuidle_text_end[]; + /** * sched_idle_set_state - Record idle state for the current CPU. * @idle_state: State to record. @@ -53,7 +56,7 @@ static int __init cpu_idle_nopoll_setup(char *__unused) __setup("hlt", cpu_idle_nopoll_setup); #endif -static inline int cpu_idle_poll(void) +static noinline int __cpuidle cpu_idle_poll(void) { rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); @@ -84,7 +87,7 @@ void __weak arch_cpu_idle(void) * * To use when the cpuidle framework cannot be used. */ -void default_idle_call(void) +void __cpuidle default_idle_call(void) { if (current_clr_polling_and_test()) { local_irq_enable(); @@ -271,6 +274,12 @@ static void cpu_idle_loop(void) } } +bool cpu_in_idle(unsigned long pc) +{ + return pc >= (unsigned long)__cpuidle_text_start && + pc < (unsigned long)__cpuidle_text_end; +} + void cpu_startup_entry(enum cpuhp_state state) { /* diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 393a3cca1f47..75554754eadf 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef arch_trigger_cpumask_backtrace /* For reliability, we're prepared to waste bits here. */ @@ -87,11 +88,16 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) int cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - pr_warn("NMI backtrace for cpu %d\n", cpu); - if (regs) - show_regs(regs); - else - dump_stack(); + if (regs && cpu_in_idle(instruction_pointer(regs))) { + pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n", + cpu, instruction_pointer(regs)); + } else { + pr_warn("NMI backtrace for cpu %d\n", cpu); + if (regs) + show_regs(regs); + else + dump_stack(); + } cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 48958d3cec9e..bd8349759095 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -888,7 +888,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text" + ".kprobes.text", ".cpuidle.text" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", ".text.*", \ ".coldtext" diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index a68f03133df9..5423a58d1b06 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -365,6 +365,7 @@ is_mcounted_section_name(char const *const txtname) strcmp(".irqentry.text", txtname) == 0 || strcmp(".softirqentry.text", txtname) == 0 || strcmp(".kprobes.text", txtname) == 0 || + strcmp(".cpuidle.text", txtname) == 0 || strcmp(".text.unlikely", txtname) == 0; } diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 2d48011bc362..faac4b10d8ea 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -136,6 +136,7 @@ my %text_sections = ( ".irqentry.text" => 1, ".softirqentry.text" => 1, ".kprobes.text" => 1, + ".cpuidle.text" => 1, ".text.unlikely" => 1, ); -- cgit v1.2.3 From ea036230f7c604e3c90fbf57f4643bd733034af9 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Fri, 7 Oct 2016 17:03:01 -0700 Subject: uprobes: remove function declarations from arch/{mips,s390} The declarations of arch-specific functions have been moved to a common header in commit 3820b4d2789f ('uprobes: Move function declarations out of arch'), but MIPS and S390 has added them to their own trees later. Remove the unnecessary duplicates. Link: http://lkml.kernel.org/r/1472804384-17830-1-git-send-email-marcin.nowakowski@imgtec.com Signed-off-by: Marcin Nowakowski Acked-by: Heiko Carstens Cc: Martin Schwidefsky Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/uprobes.h | 12 ------------ arch/s390/include/asm/uprobes.h | 10 ---------- 2 files changed, 22 deletions(-) (limited to 'arch') diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h index 70a4a2f173ff..b86d1ae07125 100644 --- a/arch/mips/include/asm/uprobes.h +++ b/arch/mips/include/asm/uprobes.h @@ -42,16 +42,4 @@ struct arch_uprobe_task { unsigned long saved_trap_nr; }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, - struct mm_struct *mm, unsigned long addr); -extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); -extern int arch_uprobe_exception_notify(struct notifier_block *self, - unsigned long val, void *data); -extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, - struct pt_regs *regs); -extern unsigned long arch_uretprobe_hijack_return_addr( - unsigned long trampoline_vaddr, struct pt_regs *regs); - #endif /* __ASM_UPROBES_H */ diff --git a/arch/s390/include/asm/uprobes.h b/arch/s390/include/asm/uprobes.h index 1411dff7fea7..658393c65d7e 100644 --- a/arch/s390/include/asm/uprobes.h +++ b/arch/s390/include/asm/uprobes.h @@ -29,14 +29,4 @@ struct arch_uprobe { struct arch_uprobe_task { }; -int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, - unsigned long addr); -int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); -int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); -bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); -int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, - void *data); -void arch_uprobe_abort_xol(struct arch_uprobe *ap, struct pt_regs *regs); -unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline, - struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ -- cgit v1.2.3 From 81243eacfa400f5f7b89f4c2323d0de9982bb0fb Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 7 Oct 2016 17:03:12 -0700 Subject: cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan Cc: Vasily Kulikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/kernel/compat_linux.c | 4 +- drivers/staging/lustre/lustre/ptlrpc/sec.c | 2 +- fs/nfsd/auth.c | 6 +-- fs/nfsd/nfs4state.c | 2 +- fs/proc/array.c | 2 +- include/linux/cred.h | 11 +---- kernel/groups.c | 67 ++++++++++-------------------- kernel/uid16.c | 4 +- net/ipv4/ping.c | 15 +++---- net/sunrpc/auth_generic.c | 4 +- net/sunrpc/auth_gss/gss_rpc_xdr.c | 2 +- net/sunrpc/auth_gss/svcauth_gss.c | 2 +- net/sunrpc/auth_unix.c | 4 +- net/sunrpc/svcauth_unix.c | 6 +-- 14 files changed, 46 insertions(+), 85 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 437e61159279..0f9cd90c11af 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -189,7 +189,7 @@ static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - kgid = GROUP_AT(group_info, i); + kgid = group_info->gid[i]; group = (u16)from_kgid_munged(user_ns, kgid); if (put_user(group, grouplist+i)) return -EFAULT; @@ -213,7 +213,7 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec.c b/drivers/staging/lustre/lustre/ptlrpc/sec.c index 5d3995d5c69a..a7416cd9ac71 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/sec.c +++ b/drivers/staging/lustre/lustre/ptlrpc/sec.c @@ -2220,7 +2220,7 @@ int sptlrpc_pack_user_desc(struct lustre_msg *msg, int offset) task_lock(current); if (pud->pud_ngroups > current_ngroups) pud->pud_ngroups = current_ngroups; - memcpy(pud->pud_groups, current_cred()->group_info->blocks[0], + memcpy(pud->pud_groups, current_cred()->group_info->gid, pud->pud_ngroups * sizeof(__u32)); task_unlock(current); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 9d46a0bdd9f9..62469c60be23 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -55,10 +55,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) goto oom; for (i = 0; i < rqgi->ngroups; i++) { - if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i))) - GROUP_AT(gi, i) = exp->ex_anon_gid; + if (gid_eq(GLOBAL_ROOT_GID, rqgi->gid[i])) + gi->gid[i] = exp->ex_anon_gid; else - GROUP_AT(gi, i) = GROUP_AT(rqgi, i); + gi->gid[i] = rqgi->gid[i]; } } else { gi = get_group_info(rqgi); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a204d7e109d4..39bfaba9c99c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1903,7 +1903,7 @@ static bool groups_equal(struct group_info *g1, struct group_info *g2) if (g1->ngroups != g2->ngroups) return false; for (i=0; ingroups; i++) - if (!gid_eq(GROUP_AT(g1, i), GROUP_AT(g2, i))) + if (!gid_eq(g1->gid[i], g2->gid[i])) return false; return true; } diff --git a/fs/proc/array.c b/fs/proc/array.c index d25b44601b30..89600fd5963d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -207,7 +207,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, group_info = cred->group_info; for (g = 0; g < group_info->ngroups; g++) seq_put_decimal_ull(m, g ? " " : "", - from_kgid_munged(user_ns, GROUP_AT(group_info, g))); + from_kgid_munged(user_ns, group_info->gid[g])); put_cred(cred); /* Trailing space shouldn't have been added in the first place. */ seq_putc(m, ' '); diff --git a/include/linux/cred.h b/include/linux/cred.h index 257db64562e5..f0e70a1bb3ac 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -26,15 +26,10 @@ struct inode; /* * COW Supplementary groups list */ -#define NGROUPS_SMALL 32 -#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(kgid_t))) - struct group_info { atomic_t usage; int ngroups; - int nblocks; - kgid_t small_block[NGROUPS_SMALL]; - kgid_t *blocks[0]; + kgid_t gid[0]; }; /** @@ -88,10 +83,6 @@ extern void set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); extern bool may_setgroups(void); -/* access the groups "array" with this macro */ -#define GROUP_AT(gi, i) \ - ((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK]) - /* * The security context of a task * diff --git a/kernel/groups.c b/kernel/groups.c index 74d431d25251..2fcadd66a8fd 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -7,55 +7,31 @@ #include #include #include +#include #include struct group_info *groups_alloc(int gidsetsize) { - struct group_info *group_info; - int nblocks; - int i; - - nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; - /* Make sure we always allocate at least one indirect block pointer */ - nblocks = nblocks ? : 1; - group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); - if (!group_info) + struct group_info *gi; + unsigned int len; + + len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; + gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); + if (!gi) + gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL); + if (!gi) return NULL; - group_info->ngroups = gidsetsize; - group_info->nblocks = nblocks; - atomic_set(&group_info->usage, 1); - - if (gidsetsize <= NGROUPS_SMALL) - group_info->blocks[0] = group_info->small_block; - else { - for (i = 0; i < nblocks; i++) { - kgid_t *b; - b = (void *)__get_free_page(GFP_USER); - if (!b) - goto out_undo_partial_alloc; - group_info->blocks[i] = b; - } - } - return group_info; -out_undo_partial_alloc: - while (--i >= 0) { - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); - return NULL; + atomic_set(&gi->usage, 1); + gi->ngroups = gidsetsize; + return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { - if (group_info->blocks[0] != group_info->small_block) { - int i; - for (i = 0; i < group_info->nblocks; i++) - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); + kvfree(group_info); } EXPORT_SYMBOL(groups_free); @@ -70,7 +46,7 @@ static int groups_to_user(gid_t __user *grouplist, for (i = 0; i < count; i++) { gid_t gid; - gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i)); + gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } @@ -95,7 +71,7 @@ static int groups_from_user(struct group_info *group_info, if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; } @@ -115,15 +91,14 @@ static void groups_sort(struct group_info *group_info) for (base = 0; base < max; base++) { int left = base; int right = left + stride; - kgid_t tmp = GROUP_AT(group_info, right); + kgid_t tmp = group_info->gid[right]; - while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) { - GROUP_AT(group_info, right) = - GROUP_AT(group_info, left); + while (left >= 0 && gid_gt(group_info->gid[left], tmp)) { + group_info->gid[right] = group_info->gid[left]; right = left; left -= stride; } - GROUP_AT(group_info, right) = tmp; + group_info->gid[right] = tmp; } stride /= 3; } @@ -141,9 +116,9 @@ int groups_search(const struct group_info *group_info, kgid_t grp) right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; - if (gid_gt(grp, GROUP_AT(group_info, mid))) + if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; - else if (gid_lt(grp, GROUP_AT(group_info, mid))) + else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; diff --git a/kernel/uid16.c b/kernel/uid16.c index d58cc4d8f0d1..cc40793464e3 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -117,7 +117,7 @@ static int groups16_to_user(old_gid_t __user *grouplist, kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { - kgid = GROUP_AT(group_info, i); + kgid = group_info->gid[i]; group = high2lowgid(from_kgid_munged(user_ns, kgid)); if (put_user(group, grouplist+i)) return -EFAULT; @@ -142,7 +142,7 @@ static int groups16_from_user(struct group_info *group_info, if (!gid_valid(kgid)) return -EINVAL; - GROUP_AT(group_info, i) = kgid; + group_info->gid[i] = kgid; } return 0; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 66ddcb60519a..7cf7d6e380c2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -258,7 +258,7 @@ int ping_init_sock(struct sock *sk) struct net *net = sock_net(sk); kgid_t group = current_egid(); struct group_info *group_info; - int i, j, count; + int i; kgid_t low, high; int ret = 0; @@ -270,16 +270,11 @@ int ping_init_sock(struct sock *sk) return 0; group_info = get_current_groups(); - count = group_info->ngroups; - for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); - for (j = 0; j < cp_count; j++) { - kgid_t gid = group_info->blocks[i][j]; - if (gid_lte(low, gid) && gid_lte(gid, high)) - goto out_release_group; - } + for (i = 0; i < group_info->ngroups; i++) { + kgid_t gid = group_info->gid[i]; - count -= cp_count; + if (gid_lte(low, gid) && gid_lte(gid, high)) + goto out_release_group; } ret = -EACCES; diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 168219535a34..83dffeadf20a 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -176,8 +176,8 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) if (gcred->acred.group_info->ngroups != acred->group_info->ngroups) goto out_nomatch; for (i = 0; i < gcred->acred.group_info->ngroups; i++) { - if (!gid_eq(GROUP_AT(gcred->acred.group_info, i), - GROUP_AT(acred->group_info, i))) + if (!gid_eq(gcred->acred.group_info->gid[i], + acred->group_info->gid[i])) goto out_nomatch; } out_match: diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index eeeba5adee6d..dc6fb79a361f 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -229,7 +229,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, kgid = make_kgid(&init_user_ns, tmp); if (!gid_valid(kgid)) goto out_free_groups; - GROUP_AT(creds->cr_group_info, i) = kgid; + creds->cr_group_info->gid[i] = kgid; } return 0; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index d8582028b346..d67f7e1bc82d 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -479,7 +479,7 @@ static int rsc_parse(struct cache_detail *cd, kgid = make_kgid(&init_user_ns, id); if (!gid_valid(kgid)) goto out; - GROUP_AT(rsci.cred.cr_group_info, i) = kgid; + rsci.cred.cr_group_info->gid[i] = kgid; } /* mech name */ diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index a99278c984e8..a1d768a973f5 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -79,7 +79,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t cred->uc_gid = acred->gid; for (i = 0; i < groups; i++) - cred->uc_gids[i] = GROUP_AT(acred->group_info, i); + cred->uc_gids[i] = acred->group_info->gid[i]; if (i < NFS_NGROUPS) cred->uc_gids[i] = INVALID_GID; @@ -127,7 +127,7 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) if (groups > NFS_NGROUPS) groups = NFS_NGROUPS; for (i = 0; i < groups ; i++) - if (!gid_eq(cred->uc_gids[i], GROUP_AT(acred->group_info, i))) + if (!gid_eq(cred->uc_gids[i], acred->group_info->gid[i])) return 0; if (groups < NFS_NGROUPS && gid_valid(cred->uc_gids[groups])) return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index dfacdc95b3f5..64af4f034de6 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -517,7 +517,7 @@ static int unix_gid_parse(struct cache_detail *cd, kgid = make_kgid(&init_user_ns, gid); if (!gid_valid(kgid)) goto out; - GROUP_AT(ug.gi, i) = kgid; + ug.gi->gid[i] = kgid; } ugp = unix_gid_lookup(cd, uid); @@ -564,7 +564,7 @@ static int unix_gid_show(struct seq_file *m, seq_printf(m, "%u %d:", from_kuid_munged(user_ns, ug->uid), glen); for (i = 0; i < glen; i++) - seq_printf(m, " %d", from_kgid_munged(user_ns, GROUP_AT(ug->gi, i))); + seq_printf(m, " %d", from_kgid_munged(user_ns, ug->gi->gid[i])); seq_printf(m, "\n"); return 0; } @@ -817,7 +817,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) return SVC_CLOSE; for (i = 0; i < slen; i++) { kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv)); - GROUP_AT(cred->cr_group_info, i) = kgid; + cred->cr_group_info->gid[i] = kgid; } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; -- cgit v1.2.3