From b69ec42b1b194cc88f04b3fbcda8d3f93182d6c3 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 8 Oct 2012 16:28:11 -0700 Subject: Kconfig: clean up the long arch list for the DEBUG_KMEMLEAK config option Introduce HAVE_DEBUG_KMEMLEAK config option and select it in corresponding architecture Kconfig files. DEBUG_KMEMLEAK now only depends on HAVE_DEBUG_KMEMLEAK. Signed-off-by: Catalin Marinas Cc: Russell King Cc: Michal Simek Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/tile/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/tile') diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index c9a3c1fe7297..9a0d77d3ba14 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -9,6 +9,7 @@ config TILE select GENERIC_FIND_FIRST_BIT select USE_GENERIC_SMP_HELPERS select CC_OPTIMIZE_FOR_SIZE + select HAVE_DEBUG_KMEMLEAK select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP -- cgit v1.2.3 From 9b2a60c484715e2d2f07d8192fd9f18435cbc77c Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 8 Oct 2012 16:28:13 -0700 Subject: Kconfig: clean up the long arch list for the DEBUG_BUGVERBOSE config option Introduce HAVE_DEBUG_BUGVERBOSE config option and select it in corresponding architecture Kconfig files. Architectures that already select GENERIC_BUG don't need to select HAVE_DEBUG_BUGVERBOSE. Signed-off-by: Catalin Marinas Acked-by: Geert Uytterhoeven Cc: David Howells Cc: Hirokazu Takata Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 1 + arch/frv/Kconfig | 1 + arch/m32r/Kconfig | 1 + arch/m68k/Kconfig | 1 + arch/sh/Kconfig | 1 + arch/sparc/Kconfig | 1 + arch/tile/Kconfig | 1 + lib/Kconfig.debug | 8 ++++---- 8 files changed, 11 insertions(+), 4 deletions(-) (limited to 'arch/tile') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5dc9273781d6..a30856058742 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -10,6 +10,7 @@ config ARM64 select GENERIC_TIME_VSYSCALL select HARDIRQS_SW_RESEND select HAVE_ARCH_TRACEHOOK + select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index cc5709d18350..9d262645f667 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -8,6 +8,7 @@ config FRV select HAVE_UID16 select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_SHOW + select HAVE_DEBUG_BUGVERBOSE select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_CPU_DEVICES select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 49498bbb9616..e875fc3ce9cb 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -8,6 +8,7 @@ config M32R select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA select ARCH_WANT_IPC_PARSE_VERSION + select HAVE_DEBUG_BUGVERBOSE select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 3e2b2f66db60..dae1e7e16a37 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -3,6 +3,7 @@ config M68K default y select HAVE_IDE select HAVE_AOUT if MMU + select HAVE_DEBUG_BUGVERBOSE select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_SHOW select GENERIC_ATOMIC64 diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index cfbf3e3c982b..3b3e27a3ff2c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -13,6 +13,7 @@ config SUPERH select HAVE_DMA_ATTRS select HAVE_IRQ_WORK select HAVE_PERF_EVENTS + select HAVE_DEBUG_BUGVERBOSE select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select PERF_USE_VMALLOC diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 274d6cf0ada2..700a01adec3a 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -32,6 +32,7 @@ config SPARC select GENERIC_PCI_IOMAP select HAVE_NMI_WATCHDOG if SPARC64 select HAVE_BPF_JIT + select HAVE_DEBUG_BUGVERBOSE select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE select GENERIC_CLOCKEVENTS diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 9a0d77d3ba14..df69d4296b4b 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -14,6 +14,7 @@ config TILE select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW + select HAVE_DEBUG_BUGVERBOSE select HAVE_SYSCALL_WRAPPERS if TILEGX select SYS_HYPERVISOR select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 736db3990506..b7281e4d1473 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -751,12 +751,12 @@ config DEBUG_HIGHMEM This options enables addition error checking for high memory systems. Disable for production systems. +config HAVE_DEBUG_BUGVERBOSE + bool + config DEBUG_BUGVERBOSE bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT - depends on BUG - depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \ - FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || \ - TILE || ARM64 + depends on BUG && (GENERIC_BUG || HAVE_DEBUG_BUGVERBOSE) default y help Say Y here to make BUG() panics output the file name and line number -- cgit v1.2.3 From 7ac57a89de958fbb5271dc504d0c25e34dbeec32 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 8 Oct 2012 16:28:16 -0700 Subject: Kconfig: clean up the "#if defined(arch)" list for exception-trace sysctl entry Introduce SYSCTL_EXCEPTION_TRACE config option and selec it in the architectures requiring support for the "exception-trace" debug_table entry in kernel/sysctl.c. Signed-off-by: Catalin Marinas Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 1 + arch/powerpc/Kconfig | 1 + arch/s390/Kconfig | 1 + arch/sparc/Kconfig | 1 + arch/tile/Kconfig | 1 + arch/x86/Kconfig | 1 + init/Kconfig | 5 +++++ kernel/sysctl.c | 3 +-- 8 files changed, 12 insertions(+), 2 deletions(-) (limited to 'arch/tile') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a30856058742..7ff68c946073 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -28,6 +28,7 @@ config ARM64 select PERF_USE_VMALLOC select RTC_LIB select SPARSE_IRQ + select SYSCTL_EXCEPTION_TRACE help ARM 64-bit (AArch64) Linux support. diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6a798a70a6d1..df7edb887a04 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -99,6 +99,7 @@ config PPC select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER + select SYSCTL_EXCEPTION_TRACE select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_IDE select HAVE_IOREMAP_PROT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8c6d7986f6d2..ceff7aef2477 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,6 +68,7 @@ config S390 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_C_RECORDMCOUNT select HAVE_SYSCALL_TRACEPOINTS + select SYSCTL_EXCEPTION_TRACE select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_GRAPH_TRACER select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 700a01adec3a..e184075877d7 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -18,6 +18,7 @@ config SPARC select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK + select SYSCTL_EXCEPTION_TRACE select ARCH_WANT_OPTIONAL_GPIOLIB select RTC_CLASS select RTC_DRV_M48T59 diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index df69d4296b4b..dc46490adca0 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -7,6 +7,7 @@ config TILE select HAVE_DMA_API_DEBUG select HAVE_KVM if !TILEGX select GENERIC_FIND_FIRST_BIT + select SYSCTL_EXCEPTION_TRACE select USE_GENERIC_SMP_HELPERS select CC_OPTIMIZE_FOR_SIZE select HAVE_DEBUG_KMEMLEAK diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3fea1848d955..6119d6c7002e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -47,6 +47,7 @@ config X86 select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_SYSCALL_TRACEPOINTS + select SYSCTL_EXCEPTION_TRACE select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK diff --git a/init/Kconfig b/init/Kconfig index 38bab420bd9b..4c93533da42c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1152,6 +1152,11 @@ config SYSCTL_SYSCALL If unsure say N here. +config SYSCTL_EXCEPTION_TRACE + bool + help + Enable support for /proc/sys/debug/exception-trace. + config KALLSYMS bool "Load all symbols for debugging/ksymoops" if EXPERT default y diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c2a2f8084bad..26f65eaa01f9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1549,8 +1549,7 @@ static struct ctl_table fs_table[] = { }; static struct ctl_table debug_table[] = { -#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \ - defined(CONFIG_S390) || defined(CONFIG_TILE) || defined(CONFIG_ARM64) +#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", .data = &show_unhandled_signals, -- cgit v1.2.3 From 2dd8ad81e31d0d36a5d448329c646ab43eb17788 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:51 -0700 Subject: mm: use mm->exe_file instead of first VM_EXECUTABLE vma->vm_file Some security modules and oprofile still uses VM_EXECUTABLE for retrieving a task's executable file. After this patch they will use mm->exe_file directly. mm->exe_file is protected with mm->mmap_sem, so locking stays the same. Signed-off-by: Konstantin Khlebnikov Acked-by: Chris Metcalf [arch/tile] Acked-by: Tetsuo Handa [tomoyo] Cc: Alexander Viro Cc: Carsten Otte Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Acked-by: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/oprofile/cell/spu_task_sync.c | 15 ++++----------- arch/tile/mm/elf.c | 19 +++++++------------ drivers/oprofile/buffer_sync.c | 17 +++-------------- kernel/auditsc.c | 13 ++----------- kernel/fork.c | 3 +-- security/tomoyo/util.c | 9 ++------- 6 files changed, 19 insertions(+), 57 deletions(-) (limited to 'arch/tile') diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index 642fca137ccb..28f1af2db1f5 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -304,7 +304,7 @@ static inline unsigned long fast_get_dcookie(struct path *path) return cookie; } -/* Look up the dcookie for the task's first VM_EXECUTABLE mapping, +/* Look up the dcookie for the task's mm->exe_file, * which corresponds loosely to "application name". Also, determine * the offset for the SPU ELF object. If computed offset is * non-zero, it implies an embedded SPU object; otherwise, it's a @@ -321,7 +321,6 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, { unsigned long app_cookie = 0; unsigned int my_offset = 0; - struct file *app = NULL; struct vm_area_struct *vma; struct mm_struct *mm = spu->mm; @@ -330,16 +329,10 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (!vma->vm_file) - continue; - if (!(vma->vm_flags & VM_EXECUTABLE)) - continue; - app_cookie = fast_get_dcookie(&vma->vm_file->f_path); + if (mm->exe_file) { + app_cookie = fast_get_dcookie(&mm->exe_file->f_path); pr_debug("got dcookie for %s\n", - vma->vm_file->f_dentry->d_name.name); - app = vma->vm_file; - break; + mm->exe_file->f_dentry->d_name.name); } for (vma = mm->mmap; vma; vma = vma->vm_next) { diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c index 758b6038c2b7..3cfa98bf9125 100644 --- a/arch/tile/mm/elf.c +++ b/arch/tile/mm/elf.c @@ -36,19 +36,14 @@ static void sim_notify_exec(const char *binary_name) } while (c); } -static int notify_exec(void) +static int notify_exec(struct mm_struct *mm) { int retval = 0; /* failure */ - struct vm_area_struct *vma = current->mm->mmap; - while (vma) { - if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file) - break; - vma = vma->vm_next; - } - if (vma) { + + if (mm->exe_file) { char *buf = (char *) __get_free_page(GFP_KERNEL); if (buf) { - char *path = d_path(&vma->vm_file->f_path, + char *path = d_path(&mm->exe_file->f_path, buf, PAGE_SIZE); if (!IS_ERR(path)) { sim_notify_exec(path); @@ -106,16 +101,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, unsigned long vdso_base; int retval = 0; + down_write(&mm->mmap_sem); + /* * Notify the simulator that an exec just occurred. * If we can't find the filename of the mapping, just use * whatever was passed as the linux_binprm filename. */ - if (!notify_exec()) + if (!notify_exec(mm)) sim_notify_exec(bprm->filename); - down_write(&mm->mmap_sem); - /* * MAYWRITE to allow gdb to COW and set breakpoints */ diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index f34b5b29fb95..d93b2b6b1f7a 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -216,7 +216,7 @@ static inline unsigned long fast_get_dcookie(struct path *path) } -/* Look up the dcookie for the task's first VM_EXECUTABLE mapping, +/* Look up the dcookie for the task's mm->exe_file, * which corresponds loosely to "application name". This is * not strictly necessary but allows oprofile to associate * shared-library samples with particular applications @@ -224,21 +224,10 @@ static inline unsigned long fast_get_dcookie(struct path *path) static unsigned long get_exec_dcookie(struct mm_struct *mm) { unsigned long cookie = NO_COOKIE; - struct vm_area_struct *vma; - - if (!mm) - goto out; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (!vma->vm_file) - continue; - if (!(vma->vm_flags & VM_EXECUTABLE)) - continue; - cookie = fast_get_dcookie(&vma->vm_file->f_path); - break; - } + if (mm && mm->exe_file) + cookie = fast_get_dcookie(&mm->exe_file->f_path); -out: return cookie; } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 29e090cc0e46..f4a7756f999c 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1151,7 +1151,6 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) const struct cred *cred; char name[sizeof(tsk->comm)]; struct mm_struct *mm = tsk->mm; - struct vm_area_struct *vma; char *tty; if (!ab) @@ -1191,16 +1190,8 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) if (mm) { down_read(&mm->mmap_sem); - vma = mm->mmap; - while (vma) { - if ((vma->vm_flags & VM_EXECUTABLE) && - vma->vm_file) { - audit_log_d_path(ab, " exe=", - &vma->vm_file->f_path); - break; - } - vma = vma->vm_next; - } + if (mm->exe_file) + audit_log_d_path(ab, " exe=", &mm->exe_file->f_path); up_read(&mm->mmap_sem); } audit_log_task_context(ab); diff --git a/kernel/fork.c b/kernel/fork.c index a2b1efc20928..a57a993681ed 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -656,8 +656,7 @@ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; - /* We need mmap_sem to protect against races with removal of - * VM_EXECUTABLE vmas */ + /* We need mmap_sem to protect against races with removal of exe_file */ down_read(&mm->mmap_sem); exe_file = mm->exe_file; if (exe_file) diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index 867558c98334..2952ba576fb9 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -949,18 +949,13 @@ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const char *tomoyo_get_exe(void) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; const char *cp = NULL; if (!mm) return NULL; down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file) { - cp = tomoyo_realpath_from_path(&vma->vm_file->f_path); - break; - } - } + if (mm->exe_file) + cp = tomoyo_realpath_from_path(&mm->exe_file->f_path); up_read(&mm->mmap_sem); return cp; } -- cgit v1.2.3 From 5d3a551c28c6669dc43be40d8fafafbc2ec8f42b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 8 Oct 2012 16:29:32 -0700 Subject: mm: hugetlb: add arch hook for clearing page flags before entering pool The core page allocator ensures that page flags are zeroed when freeing pages via free_pages_check. A number of architectures (ARM, PPC, MIPS) rely on this property to treat new pages as dirty with respect to the data cache and perform the appropriate flushing before mapping the pages into userspace. This can lead to cache synchronisation problems when using hugepages, since the allocator keeps its own pool of pages above the usual page allocator and does not reset the page flags when freeing a page into the pool. This patch adds a new architecture hook, arch_clear_hugepage_flags, so that architectures which rely on the page flags being in a particular state for fresh allocations can adjust the flags accordingly when a page is freed into the pool. Signed-off-by: Will Deacon Cc: Michal Hocko Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/hugetlb.h | 4 ++++ arch/mips/include/asm/hugetlb.h | 4 ++++ arch/powerpc/include/asm/hugetlb.h | 4 ++++ arch/s390/include/asm/hugetlb.h | 1 + arch/sh/include/asm/hugetlb.h | 6 ++++++ arch/sparc/include/asm/hugetlb.h | 4 ++++ arch/tile/include/asm/hugetlb.h | 4 ++++ arch/x86/include/asm/hugetlb.h | 4 ++++ mm/hugetlb.c | 1 + 9 files changed, 32 insertions(+) (limited to 'arch/tile') diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index da55c63728e0..94eaa5bd5d0c 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -77,4 +77,8 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #endif /* _ASM_IA64_HUGETLB_H */ diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index 58d36889f09b..bd94946a18f3 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -112,4 +112,8 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index dfdb95bc59a5..62e11a32c4c2 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -151,6 +151,10 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #else /* ! CONFIG_HUGETLB_PAGE */ static inline void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 2d6e6e380564..fc322421b1cc 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -33,6 +33,7 @@ static inline int prepare_hugepage_range(struct file *file, } #define hugetlb_prefault_arch_hook(mm) do { } while (0) +#define arch_clear_hugepage_flags(page) do { } while (0) int arch_prepare_hugepage(struct page *page); void arch_release_hugepage(struct page *page); diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 967068fb79ac..b3808c7d67b2 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -1,6 +1,7 @@ #ifndef _ASM_SH_HUGETLB_H #define _ASM_SH_HUGETLB_H +#include #include @@ -89,4 +90,9 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ + clear_bit(PG_dcache_clean, &page->flags); +} + #endif /* _ASM_SH_HUGETLB_H */ diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 177061064ee6..e7927c9758a1 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -82,4 +82,8 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #endif /* _ASM_SPARC64_HUGETLB_H */ diff --git a/arch/tile/include/asm/hugetlb.h b/arch/tile/include/asm/hugetlb.h index b2042380a5aa..0f885af2b621 100644 --- a/arch/tile/include/asm/hugetlb.h +++ b/arch/tile/include/asm/hugetlb.h @@ -106,6 +106,10 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #ifdef CONFIG_HUGETLB_SUPER_PAGES static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 439a9acc132d..bdd35dbd0605 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -90,4 +90,8 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #endif /* _ASM_X86_HUGETLB_H */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bc727122dd44..f1bb534254f6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -637,6 +637,7 @@ static void free_huge_page(struct page *page) h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } else { + arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); -- cgit v1.2.3 From 45cac65b0fcd287ebb877b141d40ba9bbe8e5da7 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 8 Oct 2012 16:32:19 -0700 Subject: readahead: fault retry breaks mmap file read random detection .fault now can retry. The retry can break state machine of .fault. In filemap_fault, if page is miss, ra->mmap_miss is increased. In the second try, since the page is in page cache now, ra->mmap_miss is decreased. And these are done in one fault, so we can't detect random mmap file access. Add a new flag to indicate .fault is tried once. In the second try, skip ra->mmap_miss decreasing. The filemap_fault state machine is ok with it. I only tested x86, didn't test other archs, but looks the change for other archs is obvious, but who knows :) Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/fault.c | 1 + arch/avr32/mm/fault.c | 1 + arch/cris/mm/fault.c | 1 + arch/hexagon/mm/vm_fault.c | 1 + arch/ia64/mm/fault.c | 1 + arch/m68k/mm/fault.c | 1 + arch/microblaze/mm/fault.c | 1 + arch/mips/mm/fault.c | 1 + arch/openrisc/mm/fault.c | 1 + arch/powerpc/mm/fault.c | 1 + arch/s390/mm/fault.c | 1 + arch/sh/mm/fault.c | 1 + arch/sparc/mm/fault_32.c | 1 + arch/sparc/mm/fault_64.c | 1 + arch/tile/mm/fault.c | 1 + arch/um/kernel/trap.c | 1 + arch/x86/mm/fault.c | 1 + arch/xtensa/mm/fault.c | 1 + include/linux/mm.h | 1 + mm/filemap.c | 4 ++-- 20 files changed, 21 insertions(+), 2 deletions(-) (limited to 'arch/tile') diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c3bd83450227..5dbf13f954f6 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -336,6 +336,7 @@ retry: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index b92e60958617..b2f2d2d66849 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -152,6 +152,7 @@ good_area: tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would have diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 45fd542cf173..73312ab6c696 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -186,6 +186,7 @@ retry: tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 06695cc4fe58..513b74cb397e 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -113,6 +113,7 @@ good_area: current->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 8443daf4f515..6cf0341f978e 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -184,6 +184,7 @@ retry: current->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index aeebbb7b30f0..a563727806bf 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -170,6 +170,7 @@ good_area: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index eb365d6795fa..714b35a9c4f7 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -233,6 +233,7 @@ good_area: current->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index c14f6dfed995..9f513486af10 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -171,6 +171,7 @@ good_area: } if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 40f850e9766c..e2bfafce66c5 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -183,6 +183,7 @@ good_area: tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5495ebe983a2..0a6b28336eb0 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -451,6 +451,7 @@ good_area: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index ac9122ca1152..04ad4001a289 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -367,6 +367,7 @@ retry: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; down_read(&mm->mmap_sem); goto retry; } diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 3bdc1ad9a341..cbbdcad8fcb3 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -504,6 +504,7 @@ good_area: } if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 77ac917be152..e98bfda205a2 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -265,6 +265,7 @@ good_area: } if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 1fe0429b6314..413d29263304 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -452,6 +452,7 @@ good_area: } if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 84ce7abbf5af..fe811fa5f1b9 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -454,6 +454,7 @@ good_area: tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* * No need to up_read(&mm->mmap_sem) as we would diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 0353b98ae35a..0f00e9c82080 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -89,6 +89,7 @@ good_area: current->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a530b230e7d7..8e13ecb41bee 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1220,6 +1220,7 @@ good_area: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 5a74c53bc69c..2c2f710ed1dc 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -126,6 +126,7 @@ good_area: current->min_flt++; if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; /* No need to up_read(&mm->mmap_sem) as we would * have already released it in __lock_page_or_retry diff --git a/include/linux/mm.h b/include/linux/mm.h index b01e585ab4b5..bcaab4e6fe91 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -161,6 +161,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ #define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ +#define FAULT_FLAG_TRIED 0x40 /* second try */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's diff --git a/mm/filemap.c b/mm/filemap.c index a9827b42556e..83efee76a5c0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1607,13 +1607,13 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); - if (likely(page)) { + if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { /* * We found the page, so try async readahead before * waiting for the lock. */ do_async_mmap_readahead(vma, ra, file, page, offset); - } else { + } else if (!page) { /* No page in the page cache at all */ do_sync_mmap_readahead(vma, ra, file, offset); count_vm_event(PGMAJFAULT); -- cgit v1.2.3