From a1e78772d72b2616ed20e54896e68e0e7044854e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:23 -0700 Subject: hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index adefc1131f2..552c8d8e77a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -306,6 +307,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) spin_unlock(&file->f_mapping->i_mmap_lock); } + /* + * Clear hugetlb-related page reserves for children. This only + * affects MAP_PRIVATE mappings. Faults generated by the child + * are not guaranteed to succeed, even if read-only + */ + if (is_vm_hugetlb_page(tmp)) + reset_vma_resv_huge_pages(tmp); + /* * Link in the new vma and copy the page table entries. */ -- cgit v1.2.3-70-g09d2 From b69c49b78457f681ecfb3147bd968434ee6559c1 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 25 Jul 2008 01:45:40 -0700 Subject: clean up duplicated alloc/free_thread_info We duplicate alloc/free_thread_info defines on many platforms (the majority uses __get_free_pages/free_pages). This patch defines common defines and removes these duplicated defines. __HAVE_ARCH_THREAD_INFO_ALLOCATOR is introduced for platforms that do something different. Signed-off-by: FUJITA Tomonori Acked-by: Russell King Cc: Pekka Enberg Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-alpha/thread_info.h | 4 +--- include/asm-arm/thread_info.h | 13 ------------- include/asm-avr32/thread_info.h | 4 ---- include/asm-blackfin/thread_info.h | 5 +---- include/asm-cris/thread_info.h | 2 ++ include/asm-frv/thread_info.h | 2 ++ include/asm-h8300/thread_info.h | 5 +---- include/asm-ia64/thread_info.h | 2 ++ include/asm-m32r/thread_info.h | 2 ++ include/asm-m68k/thread_info.h | 8 +------- include/asm-m68knommu/thread_info.h | 4 ---- include/asm-mips/thread_info.h | 2 ++ include/asm-mn10300/thread_info.h | 2 ++ include/asm-parisc/thread_info.h | 10 +++------- include/asm-powerpc/thread_info.h | 14 +++----------- include/asm-s390/thread_info.h | 5 +---- include/asm-sh/thread_info.h | 2 ++ include/asm-sparc/thread_info_32.h | 2 ++ include/asm-sparc/thread_info_64.h | 2 ++ include/asm-um/thread_info.h | 16 +--------------- include/asm-x86/thread_info.h | 2 ++ include/asm-xtensa/thread_info.h | 5 +---- kernel/fork.c | 17 +++++++++++++++++ 23 files changed, 50 insertions(+), 80 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/asm-alpha/thread_info.h b/include/asm-alpha/thread_info.h index fb318519629..15fda434442 100644 --- a/include/asm-alpha/thread_info.h +++ b/include/asm-alpha/thread_info.h @@ -50,10 +50,8 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define current_thread_info() __current_thread_info /* Thread information allocation. */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (2*PAGE_SIZE) -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ diff --git a/include/asm-arm/thread_info.h b/include/asm-arm/thread_info.h index f5a66478631..d4be2d64616 100644 --- a/include/asm-arm/thread_info.h +++ b/include/asm-arm/thread_info.h @@ -97,19 +97,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)(sp & ~(THREAD_SIZE - 1)); } -/* thread information allocation */ -#ifdef CONFIG_DEBUG_STACK_USAGE -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, \ - THREAD_SIZE_ORDER)) -#else -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#endif - -#define free_thread_info(info) \ - free_pages((unsigned long)info, THREAD_SIZE_ORDER); - #define thread_saved_pc(tsk) \ ((unsigned long)(pc_pointer(task_thread_info(tsk)->cpu_context.pc))) #define thread_saved_fp(tsk) \ diff --git a/include/asm-avr32/thread_info.h b/include/asm-avr32/thread_info.h index df68631b7b2..294b25f9323 100644 --- a/include/asm-avr32/thread_info.h +++ b/include/asm-avr32/thread_info.h @@ -61,10 +61,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)addr; } -/* thread information allocation */ -#define alloc_thread_info(ti) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long)(ti), 1) #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/include/asm-blackfin/thread_info.h b/include/asm-blackfin/thread_info.h index bc2fe5accf2..642769329d1 100644 --- a/include/asm-blackfin/thread_info.h +++ b/include/asm-blackfin/thread_info.h @@ -42,6 +42,7 @@ /* * Size of kernel stack for each process. This must be a power of 2... */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE 8192 /* 2 pages */ #ifndef __ASSEMBLY__ @@ -94,10 +95,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)((long)ti & ~((long)THREAD_SIZE-1)); } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, 1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ /* diff --git a/include/asm-cris/thread_info.h b/include/asm-cris/thread_info.h index 784668ab0fa..7efe1000f99 100644 --- a/include/asm-cris/thread_info.h +++ b/include/asm-cris/thread_info.h @@ -11,6 +11,8 @@ #ifdef __KERNEL__ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifndef __ASSEMBLY__ #include #include diff --git a/include/asm-frv/thread_info.h b/include/asm-frv/thread_info.h index 348b8f1df17..b7ac6bf2844 100644 --- a/include/asm-frv/thread_info.h +++ b/include/asm-frv/thread_info.h @@ -82,6 +82,8 @@ register struct thread_info *__current_thread_info asm("gr15"); #define current_thread_info() ({ __current_thread_info; }) +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ diff --git a/include/asm-h8300/thread_info.h b/include/asm-h8300/thread_info.h index 27bb95e2944..aafd4d322ec 100644 --- a/include/asm-h8300/thread_info.h +++ b/include/asm-h8300/thread_info.h @@ -49,6 +49,7 @@ struct thread_info { /* * Size of kernel stack for each process. This must be a power of 2... */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE 8192 /* 2 pages */ @@ -65,10 +66,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, 1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ /* diff --git a/include/asm-ia64/thread_info.h b/include/asm-ia64/thread_info.h index 2422ac61658..7c60fcdd2ef 100644 --- a/include/asm-ia64/thread_info.h +++ b/include/asm-ia64/thread_info.h @@ -54,6 +54,8 @@ struct thread_info { }, \ } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifndef ASM_OFFSETS_C /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE)) diff --git a/include/asm-m32r/thread_info.h b/include/asm-m32r/thread_info.h index 1effcd0f5e6..8589d462df2 100644 --- a/include/asm-m32r/thread_info.h +++ b/include/asm-m32r/thread_info.h @@ -94,6 +94,8 @@ static inline struct thread_info *current_thread_info(void) return ti; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ diff --git a/include/asm-m68k/thread_info.h b/include/asm-m68k/thread_info.h index d635a375248..abc002798a2 100644 --- a/include/asm-m68k/thread_info.h +++ b/include/asm-m68k/thread_info.h @@ -25,13 +25,7 @@ struct thread_info { } /* THREAD_SIZE should be 8k, so handle differently for 4k and 8k machines */ -#if PAGE_SHIFT == 13 /* 8k machines */ -#define alloc_thread_info(tsk) ((struct thread_info *)__get_free_pages(GFP_KERNEL,0)) -#define free_thread_info(ti) free_pages((unsigned long)(ti),0) -#else /* otherwise assume 4k pages */ -#define alloc_thread_info(tsk) ((struct thread_info *)__get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long)(ti),1) -#endif /* PAGE_SHIFT == 13 */ +#define THREAD_SIZE_ORDER (13 - PAGE_SHIFT) #define init_thread_info (init_task.thread.info) #define init_stack (init_thread_union.stack) diff --git a/include/asm-m68knommu/thread_info.h b/include/asm-m68knommu/thread_info.h index 95996d978be..0c9bc095f3f 100644 --- a/include/asm-m68knommu/thread_info.h +++ b/include/asm-m68knommu/thread_info.h @@ -71,10 +71,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_SIZE_ORDER) #endif /* __ASSEMBLY__ */ #define PREEMPT_ACTIVE 0x4000000 diff --git a/include/asm-mips/thread_info.h b/include/asm-mips/thread_info.h index b2772df1a1b..bb3060699df 100644 --- a/include/asm-mips/thread_info.h +++ b/include/asm-mips/thread_info.h @@ -82,6 +82,8 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define THREAD_MASK (THREAD_SIZE - 1UL) +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ ({ \ diff --git a/include/asm-mn10300/thread_info.h b/include/asm-mn10300/thread_info.h index e397e719278..78a3881f3c1 100644 --- a/include/asm-mn10300/thread_info.h +++ b/include/asm-mn10300/thread_info.h @@ -112,6 +112,8 @@ static inline unsigned long current_stack_pointer(void) return sp; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) kzalloc(THREAD_SIZE, GFP_KERNEL) diff --git a/include/asm-parisc/thread_info.h b/include/asm-parisc/thread_info.h index 2d9c7500867..9f812741c35 100644 --- a/include/asm-parisc/thread_info.h +++ b/include/asm-parisc/thread_info.h @@ -34,15 +34,11 @@ struct thread_info { /* thread information allocation */ -#define THREAD_ORDER 2 +#define THREAD_SIZE_ORDER 2 /* Be sure to hunt all references to this down when you change the size of * the kernel stack */ -#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) -#define THREAD_SHIFT (PAGE_SHIFT + THREAD_ORDER) - -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, THREAD_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_ORDER) +#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER) /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *)mfctl(30)) diff --git a/include/asm-powerpc/thread_info.h b/include/asm-powerpc/thread_info.h index b705c2a7651..a9db562df69 100644 --- a/include/asm-powerpc/thread_info.h +++ b/include/asm-powerpc/thread_info.h @@ -66,20 +66,12 @@ struct thread_info { #if THREAD_SHIFT >= PAGE_SHIFT -#define THREAD_ORDER (THREAD_SHIFT - PAGE_SHIFT) - -#ifdef CONFIG_DEBUG_STACK_USAGE -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL | \ - __GFP_ZERO, THREAD_ORDER)) -#else -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL, THREAD_ORDER)) -#endif -#define free_thread_info(ti) free_pages((unsigned long)ti, THREAD_ORDER) +#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) #else /* THREAD_SHIFT < PAGE_SHIFT */ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + extern struct thread_info *alloc_thread_info(struct task_struct *tsk); extern void free_thread_info(struct thread_info *ti); diff --git a/include/asm-s390/thread_info.h b/include/asm-s390/thread_info.h index 99bbed99a3b..91a8f93ad35 100644 --- a/include/asm-s390/thread_info.h +++ b/include/asm-s390/thread_info.h @@ -78,10 +78,7 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)((*(unsigned long *) __LC_KERNEL_STACK)-THREAD_SIZE); } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL,THREAD_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti),THREAD_ORDER) +#define THREAD_SIZE_ORDER THREAD_ORDER #endif diff --git a/include/asm-sh/thread_info.h b/include/asm-sh/thread_info.h index c50e5d35fe8..5131e390752 100644 --- a/include/asm-sh/thread_info.h +++ b/include/asm-sh/thread_info.h @@ -92,6 +92,8 @@ static inline struct thread_info *current_thread_info(void) return ti; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(ti) kzalloc(THREAD_SIZE, GFP_KERNEL) diff --git a/include/asm-sparc/thread_info_32.h b/include/asm-sparc/thread_info_32.h index 91b9f5888c8..2cf9db04405 100644 --- a/include/asm-sparc/thread_info_32.h +++ b/include/asm-sparc/thread_info_32.h @@ -86,6 +86,8 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define THREAD_INFO_ORDER 1 #endif +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + BTFIXUPDEF_CALL(struct thread_info *, alloc_thread_info, void) #define alloc_thread_info(tsk) BTFIXUP_CALL(alloc_thread_info)() diff --git a/include/asm-sparc/thread_info_64.h b/include/asm-sparc/thread_info_64.h index c6d2e6c7f84..960969d5ad0 100644 --- a/include/asm-sparc/thread_info_64.h +++ b/include/asm-sparc/thread_info_64.h @@ -155,6 +155,8 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define __THREAD_INFO_ORDER 0 #endif /* PAGE_SHIFT == 13 */ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ ({ \ diff --git a/include/asm-um/thread_info.h b/include/asm-um/thread_info.h index 356b83e2c22..e07e72846c7 100644 --- a/include/asm-um/thread_info.h +++ b/include/asm-um/thread_info.h @@ -53,21 +53,7 @@ static inline struct thread_info *current_thread_info(void) return ti; } -#ifdef CONFIG_DEBUG_STACK_USAGE - -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, \ - CONFIG_KERNEL_STACK_ORDER)) -#else - -/* thread information allocation */ -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL, \ - CONFIG_KERNEL_STACK_ORDER)) -#endif - -#define free_thread_info(ti) \ - free_pages((unsigned long)(ti),CONFIG_KERNEL_STACK_ORDER) +#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER #endif diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h index 3f2de105098..da0a675adf9 100644 --- a/include/asm-x86/thread_info.h +++ b/include/asm-x86/thread_info.h @@ -152,6 +152,8 @@ struct thread_info { #define THREAD_FLAGS GFP_KERNEL #endif +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #define alloc_thread_info(tsk) \ ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER)) diff --git a/include/asm-xtensa/thread_info.h b/include/asm-xtensa/thread_info.h index a2c640682ed..7e4131dd546 100644 --- a/include/asm-xtensa/thread_info.h +++ b/include/asm-xtensa/thread_info.h @@ -111,10 +111,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) __get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) - #else /* !__ASSEMBLY__ */ /* how to get the thread information struct from ASM */ @@ -160,6 +156,7 @@ static inline struct thread_info *current_thread_info(void) #define TS_USEDFPU 0x0001 /* FPU was used by this task this quantum (SMP) */ #define THREAD_SIZE 8192 //(2*PAGE_SIZE) +#define THREAD_SIZE_ORDER 1 #endif /* __KERNEL__ */ #endif /* _XTENSA_THREAD_INFO */ diff --git a/kernel/fork.c b/kernel/fork.c index 552c8d8e77a..5a5d6fef341 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -93,6 +93,23 @@ int nr_processes(void) static struct kmem_cache *task_struct_cachep; #endif +#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR +static inline struct thread_info *alloc_thread_info(struct task_struct *tsk) +{ +#ifdef CONFIG_DEBUG_STACK_USAGE + gfp_t mask = GFP_KERNEL | __GFP_ZERO; +#else + gfp_t mask = GFP_KERNEL; +#endif + return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER); +} + +static inline void free_thread_info(struct thread_info *ti) +{ + free_pages((unsigned long)ti, THREAD_SIZE_ORDER); +} +#endif + /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; -- cgit v1.2.3-70-g09d2 From e885dcde75685e09f23cffae1f6d5169c105b8a0 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Fri, 25 Jul 2008 01:47:06 -0700 Subject: cgroup_clone: use pid of newly created task for new cgroup cgroup_clone creates a new cgroup with the pid of the task. This works correctly for unshare, but for clone cgroup_clone is called from copy_namespaces inside copy_process, which happens before the new pid is created. As a result, the new cgroup was created with current's pid. This patch: 1. Moves the call inside copy_process to after the new pid is created 2. Passes the struct pid into ns_cgroup_clone (as it is not yet attached to the task) 3. Passes a name from ns_cgroup_clone() into cgroup_clone() so as to keep cgroup_clone() itself simpler 4. Uses pid_vnr() to get the process id value, so that the pid used to name the new cgroup is always the pid as it would be known to the task which did the cloning or unsharing. I think that is the most intuitive thing to do. This way, task t1 does clone(CLONE_NEWPID) to get t2, which does clone(CLONE_NEWPID) to get t3, then the cgroup for t3 will be named for the pid by which t2 knows t3. (Thanks to Dan Smith for finding the main bug) Changelog: June 11: Incorporate Paul Menage's feedback: don't pass NULL to ns_cgroup_clone from unshare, and reduce patch size by using 'nodename' in cgroup_clone. June 10: Original version [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Serge Hallyn Acked-by: Paul Menage Tested-by: Dan Smith Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 3 ++- include/linux/nsproxy.h | 7 +++++-- kernel/cgroup.c | 7 +++---- kernel/fork.c | 6 ++++++ kernel/ns_cgroup.c | 8 ++++++-- kernel/nsproxy.c | 8 +------- 6 files changed, 23 insertions(+), 16 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cc59d3a21d8..c98dd7cb707 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -364,7 +364,8 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss); +int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss, + char *nodename); /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 0e66b57631f..c8a768e5964 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -82,9 +82,12 @@ static inline void get_nsproxy(struct nsproxy *ns) } #ifdef CONFIG_CGROUP_NS -int ns_cgroup_clone(struct task_struct *tsk); +int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid); #else -static inline int ns_cgroup_clone(struct task_struct *tsk) { return 0; } +static inline int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid) +{ + return 0; +} #endif #endif diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 86b71e714e1..66ec9fd21e0 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2848,16 +2848,17 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) * cgroup_clone - clone the cgroup the given subsystem is attached to * @tsk: the task to be moved * @subsys: the given subsystem + * @nodename: the name for the new cgroup * * Duplicate the current cgroup in the hierarchy that the given * subsystem is attached to, and move this task into the new * child. */ -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys) +int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, + char *nodename) { struct dentry *dentry; int ret = 0; - char nodename[MAX_CGROUP_TYPE_NAMELEN]; struct cgroup *parent, *child; struct inode *inode; struct css_set *cg; @@ -2882,8 +2883,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys) cg = tsk->cgroups; parent = task_cgroup(tsk, subsys->subsys_id); - snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid); - /* Pin the hierarchy */ atomic_inc(&parent->root->sb->s_active); diff --git a/kernel/fork.c b/kernel/fork.c index 5a5d6fef341..228f80c9155 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1107,6 +1107,12 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; + if (current->nsproxy != p->nsproxy) { + retval = ns_cgroup_clone(p, pid); + if (retval) + goto bad_fork_free_pid; + } + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 48d7ed6fc3a..43c2111cd54 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -24,9 +25,12 @@ static inline struct ns_cgroup *cgroup_to_ns( struct ns_cgroup, css); } -int ns_cgroup_clone(struct task_struct *task) +int ns_cgroup_clone(struct task_struct *task, struct pid *pid) { - return cgroup_clone(task, &ns_subsys); + char name[PROC_NUMBUF]; + + snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid)); + return cgroup_clone(task, &ns_subsys, name); } /* diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index adc785146a1..21575fc46d0 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -157,12 +157,6 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) goto out; } - err = ns_cgroup_clone(tsk); - if (err) { - put_nsproxy(new_ns); - goto out; - } - tsk->nsproxy = new_ns; out: @@ -209,7 +203,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, goto out; } - err = ns_cgroup_clone(current); + err = ns_cgroup_clone(current, task_pid(current)); if (err) put_nsproxy(*new_nsp); -- cgit v1.2.3-70-g09d2 From 246bb0b1deb29726990620d8b5e55ca29f331362 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:38 -0700 Subject: kill PF_BORROWED_MM in favour of PF_KTHREAD Kill PF_BORROWED_MM. Change use_mm/unuse_mm to not play with ->flags, and do s/PF_BORROWED_MM/PF_KTHREAD/ for a couple of other users. No functional changes yet. But this allows us to do further fixes/cleanups. oom_kill/ptrace/etc often check "p->mm != NULL" to filter out the kthreads, this is wrong because of use_mm(). The problem with PF_BORROWED_MM is that we need task_lock() to avoid races. With this patch we can check PF_KTHREAD directly, or use a simple lockless helper: /* The result must not be dereferenced !!! */ struct mm_struct *__get_task_mm(struct task_struct *tsk) { if (tsk->flags & PF_KTHREAD) return NULL; return tsk->mm; } Note also ecard_task(). It runs with ->mm != NULL, but it's the kernel thread without PF_BORROWED_MM. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/aio.c | 2 -- include/linux/sched.h | 3 +-- kernel/fork.c | 4 ++-- 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/aio.c b/fs/aio.c index 0fb3117ddd9..0051fd94b44 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -586,7 +586,6 @@ static void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); - tsk->flags |= PF_BORROWED_MM; active_mm = tsk->active_mm; atomic_inc(&mm->mm_count); tsk->mm = mm; @@ -610,7 +609,6 @@ static void unuse_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); - tsk->flags &= ~PF_BORROWED_MM; tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); diff --git a/include/linux/sched.h b/include/linux/sched.h index eec64a4adb9..0560999eb1d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1483,7 +1483,6 @@ static inline void put_task_struct(struct task_struct *t) #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ -#define PF_KTHREAD 0x00000020 /* I am a kernel thread */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ @@ -1497,7 +1496,7 @@ static inline void put_task_struct(struct task_struct *t) #define PF_KSWAPD 0x00040000 /* I am kswapd */ #define PF_SWAPOFF 0x00080000 /* I am in swapoff */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ -#define PF_BORROWED_MM 0x00200000 /* I am a kthread doing use_mm */ +#define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ diff --git a/kernel/fork.c b/kernel/fork.c index 228f80c9155..eeaec6893b0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(mmput); /** * get_task_mm - acquire a reference to the task's mm * - * Returns %NULL if the task has no mm. Checks PF_BORROWED_MM (meaning + * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() @@ -487,7 +487,7 @@ struct mm_struct *get_task_mm(struct task_struct *task) task_lock(task); mm = task->mm; if (mm) { - if (task->flags & PF_BORROWED_MM) + if (task->flags & PF_KTHREAD) mm = NULL; else atomic_inc(&mm->mm_users); -- cgit v1.2.3-70-g09d2 From 999d9fc1670bc082928b93b11d1f2e0e417d973c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 25 Jul 2008 01:47:41 -0700 Subject: coredump: move mm->core_waiters into struct core_state Move mm->core_waiters into "struct core_state" allocated on stack. This shrinks mm_struct a little bit and allows further changes. This patch mostly does s/core_waiters/core_state. The only essential change is that coredump_wait() must clear mm->core_state before return. The coredump_wait()'s path is uglified and .text grows by 30 bytes, this is fixed by the next patch. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 21 +++++++++++---------- include/linux/mm_types.h | 2 +- kernel/exit.c | 8 ++++---- kernel/fork.c | 2 +- kernel/signal.c | 4 ++-- 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/exec.c b/fs/exec.c index 71734568f01..50de3aaff4d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -722,12 +722,10 @@ static int exec_mmap(struct mm_struct *mm) * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going * through with the exec. We must hold mmap_sem around - * checking core_waiters and changing tsk->mm. The - * core-inducing thread will increment core_waiters for - * each thread whose ->mm == old_mm. + * checking core_state and changing tsk->mm. */ down_read(&old_mm->mmap_sem); - if (unlikely(old_mm->core_waiters)) { + if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); return -EINTR; } @@ -1514,7 +1512,7 @@ static void zap_process(struct task_struct *start) t = start; do { if (t != current && t->mm) { - t->mm->core_waiters++; + t->mm->core_state->nr_threads++; sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } @@ -1538,11 +1536,11 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (err) return err; - if (atomic_read(&mm->mm_users) == mm->core_waiters + 1) + if (atomic_read(&mm->mm_users) == mm->core_state->nr_threads + 1) goto done; /* * We should find and kill all tasks which use this mm, and we should - * count them correctly into mm->core_waiters. We don't take tasklist + * count them correctly into ->nr_threads. We don't take tasklist * lock, but this is safe wrt: * * fork: @@ -1590,7 +1588,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, } rcu_read_unlock(); done: - return mm->core_waiters; + return mm->core_state->nr_threads; } static int coredump_wait(int exit_code) @@ -1603,9 +1601,12 @@ static int coredump_wait(int exit_code) init_completion(&mm->core_done); init_completion(&core_state.startup); + core_state.nr_threads = 0; mm->core_state = &core_state; core_waiters = zap_threads(tsk, mm, exit_code); + if (core_waiters < 0) + mm->core_state = NULL; up_write(&mm->mmap_sem); if (unlikely(core_waiters < 0)) @@ -1623,8 +1624,8 @@ static int coredump_wait(int exit_code) if (core_waiters) wait_for_completion(&core_state.startup); + mm->core_state = NULL; fail: - BUG_ON(mm->core_waiters); return core_waiters; } @@ -1702,7 +1703,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) /* * If another thread got here first, or we are not dumpable, bail out. */ - if (mm->core_waiters || !get_dumpable(mm)) { + if (mm->core_state || !get_dumpable(mm)) { up_write(&mm->mmap_sem); goto fail; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 97819efd233..c0b1747b61a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -160,6 +160,7 @@ struct vm_area_struct { }; struct core_state { + int nr_threads; struct completion startup; }; @@ -179,7 +180,6 @@ struct mm_struct { atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ int map_count; /* number of VMAs */ - int core_waiters; struct rw_semaphore mmap_sem; spinlock_t page_table_lock; /* Protects page tables and some counters */ diff --git a/kernel/exit.c b/kernel/exit.c index f7fa21dbced..988e232254e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -670,16 +670,16 @@ static void exit_mm(struct task_struct * tsk) return; /* * Serialize with any possible pending coredump. - * We must hold mmap_sem around checking core_waiters + * We must hold mmap_sem around checking core_state * and clearing tsk->mm. The core-inducing thread - * will increment core_waiters for each thread in the + * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ down_read(&mm->mmap_sem); - if (mm->core_waiters) { + if (mm->core_state) { up_read(&mm->mmap_sem); down_write(&mm->mmap_sem); - if (!--mm->core_waiters) + if (!--mm->core_state->nr_threads) complete(&mm->core_state->startup); up_write(&mm->mmap_sem); diff --git a/kernel/fork.c b/kernel/fork.c index eeaec6893b0..813d5c89b9d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -400,7 +400,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) INIT_LIST_HEAD(&mm->mmlist); mm->flags = (current->mm) ? current->mm->flags : MMF_DUMP_FILTER_DEFAULT; - mm->core_waiters = 0; + mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); set_mm_counter(mm, anon_rss, 0); diff --git a/kernel/signal.c b/kernel/signal.c index 39c1706edf0..5c7b7eaa0dc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1480,10 +1480,10 @@ static inline int may_ptrace_stop(void) * is a deadlock situation, and pointless because our tracer * is dead so don't allow us to stop. * If SIGKILL was already sent before the caller unlocked - * ->siglock we must see ->core_waiters != 0. Otherwise it + * ->siglock we must see ->core_state != NULL. Otherwise it * is safe to enter schedule(). */ - if (unlikely(current->mm->core_waiters) && + if (unlikely(current->mm->core_state) && unlikely(current->mm == current->parent->mm)) return 0; -- cgit v1.2.3-70-g09d2 From 297c5d92634c809cef23d73e7b2556f2528ff7e2 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Fri, 25 Jul 2008 01:48:49 -0700 Subject: task IO accounting: provide distinct tgid/tid I/O statistics Report per-thread I/O statistics in /proc/pid/task/tid/io and aggregate parent I/O statistics in /proc/pid/io. This approach follows the same model used to account per-process and per-thread CPU times. As a practial application, this allows for example to quickly find the top I/O consumer when a process spawns many child threads that perform the actual I/O work, because the aggregated I/O statistics can always be found in /proc/pid/io. [ Oleg Nesterov points out that we should check that the task is still alive before we iterate over the threads, but also says that we can do that fixup on top of this later. - Linus ] Acked-by: Balbir Singh Signed-off-by: Andrea Righi Cc: Matt Heaton Cc: Shailabh Nagar Acked-by-with-comments: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 86 ++++++++++++++++++++++++++++++++++++++++++--------- include/linux/sched.h | 4 +++ kernel/exit.c | 27 ++++++++++++++++ kernel/fork.c | 6 ++++ 4 files changed, 108 insertions(+), 15 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index 58c3e6a8e15..a891fe4cb43 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2376,29 +2376,82 @@ static int proc_base_fill_cache(struct file *filp, void *dirent, } #ifdef CONFIG_TASK_IO_ACCOUNTING -static int proc_pid_io_accounting(struct task_struct *task, char *buffer) -{ +static int do_io_accounting(struct task_struct *task, char *buffer, int whole) +{ + u64 rchar, wchar, syscr, syscw; + struct task_io_accounting ioac; + + if (!whole) { + rchar = task->rchar; + wchar = task->wchar; + syscr = task->syscr; + syscw = task->syscw; + memcpy(&ioac, &task->ioac, sizeof(ioac)); + } else { + unsigned long flags; + struct task_struct *t = task; + rchar = wchar = syscr = syscw = 0; + memset(&ioac, 0, sizeof(ioac)); + + rcu_read_lock(); + do { + rchar += t->rchar; + wchar += t->wchar; + syscr += t->syscr; + syscw += t->syscw; + + ioac.read_bytes += t->ioac.read_bytes; + ioac.write_bytes += t->ioac.write_bytes; + ioac.cancelled_write_bytes += + t->ioac.cancelled_write_bytes; + t = next_thread(t); + } while (t != task); + rcu_read_unlock(); + + if (lock_task_sighand(task, &flags)) { + struct signal_struct *sig = task->signal; + + rchar += sig->rchar; + wchar += sig->wchar; + syscr += sig->syscr; + syscw += sig->syscw; + + ioac.read_bytes += sig->ioac.read_bytes; + ioac.write_bytes += sig->ioac.write_bytes; + ioac.cancelled_write_bytes += + sig->ioac.cancelled_write_bytes; + + unlock_task_sighand(task, &flags); + } + } + return sprintf(buffer, -#ifdef CONFIG_TASK_XACCT "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" "syscw: %llu\n" -#endif "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", -#ifdef CONFIG_TASK_XACCT - (unsigned long long)task->rchar, - (unsigned long long)task->wchar, - (unsigned long long)task->syscr, - (unsigned long long)task->syscw, -#endif - (unsigned long long)task->ioac.read_bytes, - (unsigned long long)task->ioac.write_bytes, - (unsigned long long)task->ioac.cancelled_write_bytes); + (unsigned long long)rchar, + (unsigned long long)wchar, + (unsigned long long)syscr, + (unsigned long long)syscw, + (unsigned long long)ioac.read_bytes, + (unsigned long long)ioac.write_bytes, + (unsigned long long)ioac.cancelled_write_bytes); +} + +static int proc_tid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 0); } -#endif + +static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 1); +} +#endif /* CONFIG_TASK_IO_ACCOUNTING */ /* * Thread groups @@ -2470,7 +2523,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING - INF("io", S_IRUGO, pid_io_accounting), + INF("io", S_IRUGO, tgid_io_accounting), #endif }; @@ -2797,6 +2850,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), #endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUGO, tid_io_accounting), +#endif }; static int proc_tid_base_readdir(struct file * filp, diff --git a/include/linux/sched.h b/include/linux/sched.h index af780f299c7..d22ffe06d0e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -506,6 +506,10 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; +#ifdef CONFIG_TASK_XACCT + u64 rchar, wchar, syscr, syscw; +#endif + struct task_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the diff --git a/kernel/exit.c b/kernel/exit.c index 8a4d4d12e29..ad933bb29ec 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -120,6 +120,18 @@ static void __exit_signal(struct task_struct *tsk) sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); +#ifdef CONFIG_TASK_XACCT + sig->rchar += tsk->rchar; + sig->wchar += tsk->wchar; + sig->syscr += tsk->syscr; + sig->syscw += tsk->syscw; +#endif /* CONFIG_TASK_XACCT */ +#ifdef CONFIG_TASK_IO_ACCOUNTING + sig->ioac.read_bytes += tsk->ioac.read_bytes; + sig->ioac.write_bytes += tsk->ioac.write_bytes; + sig->ioac.cancelled_write_bytes += + tsk->ioac.cancelled_write_bytes; +#endif /* CONFIG_TASK_IO_ACCOUNTING */ sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1366,6 +1378,21 @@ static int wait_task_zombie(struct task_struct *p, int options, psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; +#ifdef CONFIG_TASK_XACCT + psig->rchar += p->rchar + sig->rchar; + psig->wchar += p->wchar + sig->wchar; + psig->syscr += p->syscr + sig->syscr; + psig->syscw += p->syscw + sig->syscw; +#endif /* CONFIG_TASK_XACCT */ +#ifdef CONFIG_TASK_IO_ACCOUNTING + psig->ioac.read_bytes += + p->ioac.read_bytes + sig->ioac.read_bytes; + psig->ioac.write_bytes += + p->ioac.write_bytes + sig->ioac.write_bytes; + psig->ioac.cancelled_write_bytes += + p->ioac.cancelled_write_bytes + + sig->ioac.cancelled_write_bytes; +#endif /* CONFIG_TASK_IO_ACCOUNTING */ spin_unlock_irq(&p->parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index 813d5c89b9d..b99d73e971a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -812,6 +812,12 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; +#ifdef CONFIG_TASK_XACCT + sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0; +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + memset(&sig->ioac, 0, sizeof(sig->ioac)); +#endif sig->sum_sched_runtime = 0; INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); -- cgit v1.2.3-70-g09d2 From 51cc50685a4275c6a02653670af9f108a64e01cf Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jul 2008 19:45:34 -0700 Subject: SL*B: drop kmem cache argument from constructor Kmem cache passed to constructor is only needed for constructors that are themselves multiplexeres. Nobody uses this "feature", nor does anybody uses passed kmem cache in non-trivial way, so pass only pointer to object. Non-trivial places are: arch/powerpc/mm/init_64.c arch/powerpc/mm/hugetlbpage.c This is flag day, yes. Signed-off-by: Alexey Dobriyan Acked-by: Pekka Enberg Acked-by: Christoph Lameter Cc: Jon Tollefson Cc: Nick Piggin Cc: Matt Mackall [akpm@linux-foundation.org: fix arch/powerpc/mm/hugetlbpage.c] [akpm@linux-foundation.org: fix mm/slab.c] [akpm@linux-foundation.org: fix ubifs] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/plat-s3c24xx/dma.c | 2 +- arch/powerpc/kernel/rtas_flash.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 9 ++------- arch/powerpc/mm/init_64.c | 24 +++++++++--------------- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- arch/sh/mm/pmb.c | 2 +- arch/xtensa/mm/init.c | 2 +- drivers/usb/mon/mon_text.c | 4 ++-- fs/adfs/super.c | 2 +- fs/affs/super.c | 2 +- fs/afs/super.c | 4 ++-- fs/befs/linuxvfs.c | 2 +- fs/bfs/inode.c | 2 +- fs/block_dev.c | 2 +- fs/buffer.c | 2 +- fs/cifs/cifsfs.c | 2 +- fs/coda/inode.c | 2 +- fs/ecryptfs/main.c | 4 ++-- fs/efs/super.c | 2 +- fs/ext2/super.c | 2 +- fs/ext3/super.c | 2 +- fs/ext4/super.c | 2 +- fs/fat/cache.c | 2 +- fs/fat/inode.c | 2 +- fs/fuse/inode.c | 2 +- fs/gfs2/main.c | 4 ++-- fs/hfs/super.c | 2 +- fs/hfsplus/super.c | 2 +- fs/hpfs/super.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/inode.c | 2 +- fs/isofs/inode.c | 2 +- fs/jffs2/super.c | 2 +- fs/jfs/jfs_metapage.c | 2 +- fs/jfs/super.c | 2 +- fs/locks.c | 2 +- fs/minix/inode.c | 2 +- fs/ncpfs/inode.c | 2 +- fs/nfs/inode.c | 2 +- fs/ntfs/super.c | 2 +- fs/ocfs2/dlm/dlmfs.c | 3 +-- fs/ocfs2/super.c | 2 +- fs/openpromfs/inode.c | 2 +- fs/proc/inode.c | 2 +- fs/qnx4/inode.c | 2 +- fs/reiserfs/super.c | 2 +- fs/romfs/inode.c | 2 +- fs/smbfs/inode.c | 2 +- fs/sysv/inode.c | 2 +- fs/ubifs/super.c | 2 +- fs/udf/super.c | 2 +- fs/ufs/super.c | 2 +- fs/xfs/linux-2.6/kmem.h | 2 +- fs/xfs/linux-2.6/xfs_super.c | 1 - include/linux/slab.h | 2 +- include/linux/slub_def.h | 2 +- ipc/mqueue.c | 2 +- kernel/fork.c | 2 +- lib/idr.c | 2 +- lib/radix-tree.c | 2 +- mm/rmap.c | 2 +- mm/shmem.c | 2 +- mm/slab.c | 11 +++++------ mm/slob.c | 7 +++---- mm/slub.c | 13 ++++++------- net/socket.c | 2 +- net/sunrpc/rpc_pipe.c | 2 +- 67 files changed, 90 insertions(+), 106 deletions(-) (limited to 'kernel/fork.c') diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c index 60f162dc4fa..8c5e656d5d8 100644 --- a/arch/arm/plat-s3c24xx/dma.c +++ b/arch/arm/plat-s3c24xx/dma.c @@ -1304,7 +1304,7 @@ struct sysdev_class dma_sysclass = { /* kmem cache implementation */ -static void s3c2410_dma_cache_ctor(struct kmem_cache *c, void *p) +static void s3c2410_dma_cache_ctor(void *p) { memset(p, 0, sizeof(struct s3c2410_dma_buf)); } diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 09ded5c424a..149cb112cd1 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -286,7 +286,7 @@ static ssize_t rtas_flash_read(struct file *file, char __user *buf, } /* constructor for flash_block_cache */ -void rtas_block_ctor(struct kmem_cache *cache, void *ptr) +void rtas_block_ctor(void *ptr) { memset(ptr, 0, RTAS_BLK_SIZE); } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index fb42c4dd321..ed0aab0208a 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -113,7 +113,7 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, unsigned long address, unsigned int psize) { - pte_t *new = kmem_cache_alloc(huge_pgtable_cache(psize), + pte_t *new = kmem_cache_zalloc(huge_pgtable_cache(psize), GFP_KERNEL|__GFP_REPEAT); if (! new) @@ -730,11 +730,6 @@ static int __init hugepage_setup_sz(char *str) } __setup("hugepagesz=", hugepage_setup_sz); -static void zero_ctor(struct kmem_cache *cache, void *addr) -{ - memset(addr, 0, kmem_cache_size(cache)); -} - static int __init hugetlbpage_init(void) { unsigned int psize; @@ -756,7 +751,7 @@ static int __init hugetlbpage_init(void) HUGEPTE_TABLE_SIZE(psize), HUGEPTE_TABLE_SIZE(psize), 0, - zero_ctor); + NULL); if (!huge_pgtable_cache(psize)) panic("hugetlbpage_init(): could not create %s"\ "\n", HUGEPTE_CACHE_NAME(psize)); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index a41bc5aa204..4f7df85129d 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -136,9 +136,14 @@ static int __init setup_kcore(void) module_init(setup_kcore); #endif -static void zero_ctor(struct kmem_cache *cache, void *addr) +static void pgd_ctor(void *addr) { - memset(addr, 0, kmem_cache_size(cache)); + memset(addr, 0, PGD_TABLE_SIZE); +} + +static void pmd_ctor(void *addr) +{ + memset(addr, 0, PMD_TABLE_SIZE); } static const unsigned int pgtable_cache_size[2] = { @@ -163,19 +168,8 @@ struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)]; void pgtable_cache_init(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(pgtable_cache_size); i++) { - int size = pgtable_cache_size[i]; - const char *name = pgtable_cache_name[i]; - - pr_debug("Allocating page table cache %s (#%d) " - "for size: %08x...\n", name, i, size); - pgtable_cache[i] = kmem_cache_create(name, - size, size, - SLAB_PANIC, - zero_ctor); - } + pgtable_cache[0] = kmem_cache_create(pgtable_cache_name[0], PGD_TABLE_SIZE, PGD_TABLE_SIZE, SLAB_PANIC, pgd_ctor); + pgtable_cache[1] = kmem_cache_create(pgtable_cache_name[1], PMD_TABLE_SIZE, PMD_TABLE_SIZE, SLAB_PANIC, pmd_ctor); } #ifdef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 7123472801d..690ca7b0dcf 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -78,7 +78,7 @@ spufs_destroy_inode(struct inode *inode) } static void -spufs_init_once(struct kmem_cache *cachep, void *p) +spufs_init_once(void *p) { struct spufs_inode_info *ei = p; diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index 0b0ec6e0475..46911bcbf17 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -293,7 +293,7 @@ void pmb_unmap(unsigned long addr) } while (pmbe); } -static void pmb_cache_ctor(struct kmem_cache *cachep, void *pmb) +static void pmb_cache_ctor(void *pmb) { struct pmb_entry *pmbe = pmb; diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 81d0560eaea..ee261005b36 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -309,7 +309,7 @@ void show_mem(void) struct kmem_cache *pgtable_cache __read_mostly; -static void pgd_ctor(struct kmem_cache *cache, void* addr) +static void pgd_ctor(void* addr) { pte_t* ptep = (pte_t*)addr; int i; diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c index 5e3e4e9b6c7..1f715436d6d 100644 --- a/drivers/usb/mon/mon_text.c +++ b/drivers/usb/mon/mon_text.c @@ -87,7 +87,7 @@ struct mon_reader_text { static struct dentry *mon_dir; /* Usually /sys/kernel/debug/usbmon */ -static void mon_text_ctor(struct kmem_cache *, void *); +static void mon_text_ctor(void *); struct mon_text_ptr { int cnt, limit; @@ -720,7 +720,7 @@ void mon_text_del(struct mon_bus *mbus) /* * Slab interface: constructor. */ -static void mon_text_ctor(struct kmem_cache *slab, void *mem) +static void mon_text_ctor(void *mem) { /* * Nothing to initialize. No, really! diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 9e421eeb672..26f3b43726b 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -249,7 +249,7 @@ static void adfs_destroy_inode(struct inode *inode) kmem_cache_free(adfs_inode_cachep, ADFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct adfs_inode_info *ei = (struct adfs_inode_info *) foo; diff --git a/fs/affs/super.c b/fs/affs/super.c index 4e030956640..3a89094f93d 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -90,7 +90,7 @@ static void affs_destroy_inode(struct inode *inode) kmem_cache_free(affs_inode_cachep, AFFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct affs_inode_info *ei = (struct affs_inode_info *) foo; diff --git a/fs/afs/super.c b/fs/afs/super.c index 7e3faeef681..250d8c4d66e 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -27,7 +27,7 @@ #define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */ -static void afs_i_init_once(struct kmem_cache *cachep, void *foo); +static void afs_i_init_once(void *foo); static int afs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt); @@ -449,7 +449,7 @@ static void afs_put_super(struct super_block *sb) /* * initialise an inode cache slab element prior to any use */ -static void afs_i_init_once(struct kmem_cache *cachep, void *_vnode) +static void afs_i_init_once(void *_vnode) { struct afs_vnode *vnode = _vnode; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index e8717de3bab..02c6e62b72f 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -289,7 +289,7 @@ befs_destroy_inode(struct inode *inode) kmem_cache_free(befs_inode_cachep, BEFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct befs_inode_info *bi = (struct befs_inode_info *) foo; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 053e690ec9e..0ed57b5ee01 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -264,7 +264,7 @@ static void bfs_destroy_inode(struct inode *inode) kmem_cache_free(bfs_inode_cachep, BFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct bfs_inode_info *bi = foo; diff --git a/fs/block_dev.c b/fs/block_dev.c index 10d8a0aa871..dcf37cada36 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -271,7 +271,7 @@ static void bdev_destroy_inode(struct inode *inode) kmem_cache_free(bdev_cachep, bdi); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct bdev_inode *ei = (struct bdev_inode *) foo; struct block_device *bdev = &ei->bdev; diff --git a/fs/buffer.c b/fs/buffer.c index 109b261192d..5fd497cdd6f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3272,7 +3272,7 @@ int bh_submit_read(struct buffer_head *bh) EXPORT_SYMBOL(bh_submit_read); static void -init_buffer_head(struct kmem_cache *cachep, void *data) +init_buffer_head(void *data) { struct buffer_head *bh = data; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 22857c639df..fe5f6809cba 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -766,7 +766,7 @@ const struct file_operations cifs_dir_ops = { }; static void -cifs_init_once(struct kmem_cache *cachep, void *inode) +cifs_init_once(void *inode) { struct cifsInodeInfo *cifsi = inode; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 2f58dfc7008..830f51abb97 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -58,7 +58,7 @@ static void coda_destroy_inode(struct inode *inode) kmem_cache_free(coda_inode_cachep, ITOC(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct coda_inode_info *ei = (struct coda_inode_info *) foo; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 6f403cfba14..448dfd597b5 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -578,7 +578,7 @@ static struct file_system_type ecryptfs_fs_type = { * Initializes the ecryptfs_inode_info_cache when it is created */ static void -inode_info_init_once(struct kmem_cache *cachep, void *vptr) +inode_info_init_once(void *vptr) { struct ecryptfs_inode_info *ei = (struct ecryptfs_inode_info *)vptr; @@ -589,7 +589,7 @@ static struct ecryptfs_cache_info { struct kmem_cache **cache; const char *name; size_t size; - void (*ctor)(struct kmem_cache *cache, void *obj); + void (*ctor)(void *obj); } ecryptfs_cache_infos[] = { { .cache = &ecryptfs_auth_tok_list_item_cache, diff --git a/fs/efs/super.c b/fs/efs/super.c index d733531b55e..567b134fa1f 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -70,7 +70,7 @@ static void efs_destroy_inode(struct inode *inode) kmem_cache_free(efs_inode_cachep, INODE_INFO(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct efs_inode_info *ei = (struct efs_inode_info *) foo; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 31308a3b0b8..fd88c7b43e6 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -159,7 +159,7 @@ static void ext2_destroy_inode(struct inode *inode) kmem_cache_free(ext2_inode_cachep, EXT2_I(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct ext2_inode_info *ei = (struct ext2_inode_info *) foo; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 615788c6843..8ddced38467 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -472,7 +472,7 @@ static void ext3_destroy_inode(struct inode *inode) kmem_cache_free(ext3_inode_cachep, EXT3_I(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct ext3_inode_info *ei = (struct ext3_inode_info *) foo; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1cb371dcd60..b5479b1dff1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -595,7 +595,7 @@ static void ext4_destroy_inode(struct inode *inode) kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 3a9ecac8d61..3222f51c41c 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -36,7 +36,7 @@ static inline int fat_max_cache(struct inode *inode) static struct kmem_cache *fat_cache_cachep; -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct fat_cache *cache = (struct fat_cache *)foo; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 23676f9d79c..6d266d793e2 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -498,7 +498,7 @@ static void fat_destroy_inode(struct inode *inode) kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 7d2f7d6e22e..d2249f174e2 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -956,7 +956,7 @@ static inline void unregister_fuseblk(void) } #endif -static void fuse_inode_init_once(struct kmem_cache *cachep, void *foo) +static void fuse_inode_init_once(void *foo) { struct inode * inode = foo; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index bcc668d0fad..bb2cc303ac2 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -24,7 +24,7 @@ #include "util.h" #include "glock.h" -static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo) +static void gfs2_init_inode_once(void *foo) { struct gfs2_inode *ip = foo; @@ -33,7 +33,7 @@ static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo) ip->i_alloc = NULL; } -static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo) +static void gfs2_init_glock_once(void *foo) { struct gfs2_glock *gl = foo; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index ac2ec5ef66e..4abb1047c68 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -432,7 +432,7 @@ static struct file_system_type hfs_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; -static void hfs_init_once(struct kmem_cache *cachep, void *p) +static void hfs_init_once(void *p) { struct hfs_inode_info *i = p; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 3859118531c..e834e578c93 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -485,7 +485,7 @@ static struct file_system_type hfsplus_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; -static void hfsplus_init_once(struct kmem_cache *cachep, void *p) +static void hfsplus_init_once(void *p) { struct hfsplus_inode_info *i = p; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index f63a699ec65..b8ae9c90ada 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -173,7 +173,7 @@ static void hpfs_destroy_inode(struct inode *inode) kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index dbd01d262ca..3f58923fb39 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -705,7 +705,7 @@ static const struct address_space_operations hugetlbfs_aops = { }; -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo; diff --git a/fs/inode.c b/fs/inode.c index 35b6414522e..b6726f64453 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -224,7 +224,7 @@ void inode_init_once(struct inode *inode) EXPORT_SYMBOL(inode_init_once); -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct inode * inode = (struct inode *) foo; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 044a254d526..26948a6033b 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -73,7 +73,7 @@ static void isofs_destroy_inode(struct inode *inode) kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct iso_inode_info *ei = foo; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 7da69eae49e..efd401257ed 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -44,7 +44,7 @@ static void jffs2_destroy_inode(struct inode *inode) kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); } -static void jffs2_i_init_once(struct kmem_cache *cachep, void *foo) +static void jffs2_i_init_once(void *foo) { struct jffs2_inode_info *f = foo; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 854ff0ec574..c350057087d 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -182,7 +182,7 @@ static inline void remove_metapage(struct page *page, struct metapage *mp) #endif -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct metapage *mp = (struct metapage *)foo; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 359c091d896..3630718be39 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -760,7 +760,7 @@ static struct file_system_type jfs_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct jfs_inode_info *jfs_ip = (struct jfs_inode_info *) foo; diff --git a/fs/locks.c b/fs/locks.c index 01490300f7c..5eb259e3cd3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -201,7 +201,7 @@ EXPORT_SYMBOL(locks_init_lock); * Initialises the fields of the file lock which are invariant for * free file_locks. */ -static void init_once(struct kmem_cache *cache, void *foo) +static void init_once(void *foo) { struct file_lock *lock = (struct file_lock *) foo; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 523d7371341..d1d1eb84679 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -68,7 +68,7 @@ static void minix_destroy_inode(struct inode *inode) kmem_cache_free(minix_inode_cachep, minix_i(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct minix_inode_info *ei = (struct minix_inode_info *) foo; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 2e5ab1204de..d642f0e5b36 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -64,7 +64,7 @@ static void ncp_destroy_inode(struct inode *inode) kmem_cache_free(ncp_inode_cachep, NCP_FINFO(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct ncp_inode_info *ei = (struct ncp_inode_info *) foo; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index df23f987da6..52daefa2f52 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1242,7 +1242,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) #endif } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct nfs_inode *nfsi = (struct nfs_inode *) foo; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 3e76f3b216b..4a46743b507 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -3080,7 +3080,7 @@ struct kmem_cache *ntfs_inode_cache; struct kmem_cache *ntfs_big_inode_cache; /* Init once constructor for the inode slab cache. */ -static void ntfs_big_inode_init_once(struct kmem_cache *cachep, void *foo) +static void ntfs_big_inode_init_once(void *foo) { ntfs_inode *ni = (ntfs_inode *)foo; diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index e48aba698b7..533a789c3ef 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -267,8 +267,7 @@ static ssize_t dlmfs_file_write(struct file *filp, return writelen; } -static void dlmfs_init_once(struct kmem_cache *cachep, - void *foo) +static void dlmfs_init_once(void *foo) { struct dlmfs_inode_private *ip = (struct dlmfs_inode_private *) foo; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ccecfe5094f..2560b33889a 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1118,7 +1118,7 @@ bail: return status; } -static void ocfs2_inode_init_once(struct kmem_cache *cachep, void *data) +static void ocfs2_inode_init_once(void *data) { struct ocfs2_inode_info *oi = data; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index d17b4fd204e..9f5b054f06b 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -430,7 +430,7 @@ static struct file_system_type openprom_fs_type = { .kill_sb = kill_anon_super, }; -static void op_inode_init_once(struct kmem_cache * cachep, void *data) +static void op_inode_init_once(void *data) { struct op_inode_info *oi = (struct op_inode_info *) data; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 02eca2ed9dd..b37f25dc45a 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -94,7 +94,7 @@ static void proc_destroy_inode(struct inode *inode) kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct proc_inode *ei = (struct proc_inode *) foo; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index b31ab78052b..2aad1044b84 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -553,7 +553,7 @@ static void qnx4_destroy_inode(struct inode *inode) kmem_cache_free(qnx4_inode_cachep, qnx4_i(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 2ec748ba0bd..879e54d35c2 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -521,7 +521,7 @@ static void reiserfs_destroy_inode(struct inode *inode) kmem_cache_free(reiserfs_inode_cachep, REISERFS_I(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct reiserfs_inode_info *ei = (struct reiserfs_inode_info *)foo; diff --git a/fs/romfs/inode.c b/fs/romfs/inode.c index 3f13d491c7c..8e51a2aaa97 100644 --- a/fs/romfs/inode.c +++ b/fs/romfs/inode.c @@ -577,7 +577,7 @@ static void romfs_destroy_inode(struct inode *inode) kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct romfs_inode_info *ei = foo; diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 376ef3ee6ed..3528f40ffb0 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -67,7 +67,7 @@ static void smb_destroy_inode(struct inode *inode) kmem_cache_free(smb_inode_cachep, SMB_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct smb_inode_info *ei = (struct smb_inode_info *) foo; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index c5d60de0658..df0d435baa4 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -326,7 +326,7 @@ static void sysv_destroy_inode(struct inode *inode) kmem_cache_free(sysv_inode_cachep, SYSV_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *p) +static void init_once(void *p) { struct sysv_inode_info *si = (struct sysv_inode_info *)p; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 00eb9c68ad0..ca1e2d4e03c 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1841,7 +1841,7 @@ static struct file_system_type ubifs_fs_type = { /* * Inode slab cache constructor. */ -static void inode_slab_ctor(struct kmem_cache *cachep, void *obj) +static void inode_slab_ctor(void *obj) { struct ubifs_inode *ui = obj; inode_init_once(&ui->vfs_inode); diff --git a/fs/udf/super.c b/fs/udf/super.c index 44cc702f96c..5698bbf83bb 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -148,7 +148,7 @@ static void udf_destroy_inode(struct inode *inode) kmem_cache_free(udf_inode_cachep, UDF_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct udf_inode_info *ei = (struct udf_inode_info *)foo; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 227c9d70004..3e30e40aa24 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1302,7 +1302,7 @@ static void ufs_destroy_inode(struct inode *inode) kmem_cache_free(ufs_inode_cachep, UFS_I(inode)); } -static void init_once(struct kmem_cache * cachep, void *foo) +static void init_once(void *foo) { struct ufs_inode_info *ei = (struct ufs_inode_info *) foo; diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h index 5e956490297..a20683cf74d 100644 --- a/fs/xfs/linux-2.6/kmem.h +++ b/fs/xfs/linux-2.6/kmem.h @@ -79,7 +79,7 @@ kmem_zone_init(int size, char *zone_name) static inline kmem_zone_t * kmem_zone_init_flags(int size, char *zone_name, unsigned long flags, - void (*construct)(kmem_zone_t *, void *)) + void (*construct)(void *)) { return kmem_cache_create(zone_name, size, 0, flags, construct); } diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 742b2c7852c..943381284e2 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -843,7 +843,6 @@ xfs_fs_destroy_inode( STATIC void xfs_fs_inode_init_once( - kmem_zone_t *zonep, void *vnode) { inode_init_once(vn_to_inode((bhv_vnode_t *)vnode)); diff --git a/include/linux/slab.h b/include/linux/slab.h index 41103910f8a..9ff8e849940 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,7 +58,7 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, - void (*)(struct kmem_cache *, void *)); + void (*)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d117ea2825a..5bad61a93f6 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -85,7 +85,7 @@ struct kmem_cache { struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ - void (*ctor)(struct kmem_cache *, void *); + void (*ctor)(void *); int inuse; /* Offset to metadata */ int align; /* Alignment */ const char *name; /* Name (only for display!) */ diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 1fdc2eb2f6d..474984f9e03 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -207,7 +207,7 @@ static int mqueue_get_sb(struct file_system_type *fs_type, return get_sb_single(fs_type, flags, data, mqueue_fill_super, mnt); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo; diff --git a/kernel/fork.c b/kernel/fork.c index b99d73e971a..80e83e459b1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1442,7 +1442,7 @@ long do_fork(unsigned long clone_flags, #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif -static void sighand_ctor(struct kmem_cache *cachep, void *data) +static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; diff --git a/lib/idr.c b/lib/idr.c index 3476f8203e9..e728c7fccc4 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -607,7 +607,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id) } EXPORT_SYMBOL(idr_replace); -static void idr_cache_ctor(struct kmem_cache *idr_layer_cache, void *idr_layer) +static void idr_cache_ctor(void *idr_layer) { memset(idr_layer, 0, sizeof(struct idr_layer)); } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 9c4f1ffa286..be86b32bc87 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1183,7 +1183,7 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag) EXPORT_SYMBOL(radix_tree_tagged); static void -radix_tree_node_ctor(struct kmem_cache *cachep, void *node) +radix_tree_node_ctor(void *node) { memset(node, 0, sizeof(struct radix_tree_node)); } diff --git a/mm/rmap.c b/mm/rmap.c index abbd29f7c43..39ae5a9bf38 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -138,7 +138,7 @@ void anon_vma_unlink(struct vm_area_struct *vma) anon_vma_free(anon_vma); } -static void anon_vma_ctor(struct kmem_cache *cachep, void *data) +static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; diff --git a/mm/shmem.c b/mm/shmem.c index 1089092aeca..952d361774b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2352,7 +2352,7 @@ static void shmem_destroy_inode(struct inode *inode) kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct shmem_inode_info *p = (struct shmem_inode_info *) foo; diff --git a/mm/slab.c b/mm/slab.c index 052e7d64537..918f04f7fef 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -406,7 +406,7 @@ struct kmem_cache { unsigned int dflags; /* dynamic flags */ /* constructor func */ - void (*ctor)(struct kmem_cache *, void *); + void (*ctor)(void *obj); /* 5) cache creation/removal */ const char *name; @@ -2137,8 +2137,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep) */ struct kmem_cache * kmem_cache_create (const char *name, size_t size, size_t align, - unsigned long flags, - void (*ctor)(struct kmem_cache *, void *)) + unsigned long flags, void (*ctor)(void *)) { size_t left_over, slab_size, ralign; struct kmem_cache *cachep = NULL, *pc; @@ -2653,7 +2652,7 @@ static void cache_init_objs(struct kmem_cache *cachep, * They must also be threaded. */ if (cachep->ctor && !(cachep->flags & SLAB_POISON)) - cachep->ctor(cachep, objp + obj_offset(cachep)); + cachep->ctor(objp + obj_offset(cachep)); if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) @@ -2669,7 +2668,7 @@ static void cache_init_objs(struct kmem_cache *cachep, cachep->buffer_size / PAGE_SIZE, 0); #else if (cachep->ctor) - cachep->ctor(cachep, objp); + cachep->ctor(objp); #endif slab_bufctl(slabp)[i] = i + 1; } @@ -3093,7 +3092,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, #endif objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) - cachep->ctor(cachep, objp); + cachep->ctor(objp); #if ARCH_SLAB_MINALIGN if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", diff --git a/mm/slob.c b/mm/slob.c index de268eb7ac7..d8fbd4d1bfa 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -525,12 +525,11 @@ struct kmem_cache { unsigned int size, align; unsigned long flags; const char *name; - void (*ctor)(struct kmem_cache *, void *); + void (*ctor)(void *); }; struct kmem_cache *kmem_cache_create(const char *name, size_t size, - size_t align, unsigned long flags, - void (*ctor)(struct kmem_cache *, void *)) + size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *c; @@ -575,7 +574,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) b = slob_new_page(flags, get_order(c->size), node); if (c->ctor) - c->ctor(c, b); + c->ctor(b); return b; } diff --git a/mm/slub.c b/mm/slub.c index 77c21cf53ff..b7e2cd5d82d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1012,7 +1012,7 @@ __setup("slub_debug", setup_slub_debug); static unsigned long kmem_cache_flags(unsigned long objsize, unsigned long flags, const char *name, - void (*ctor)(struct kmem_cache *, void *)) + void (*ctor)(void *)) { /* * Enable debugging if selected on the kernel commandline. @@ -1040,7 +1040,7 @@ static inline int check_object(struct kmem_cache *s, struct page *page, static inline void add_full(struct kmem_cache_node *n, struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long objsize, unsigned long flags, const char *name, - void (*ctor)(struct kmem_cache *, void *)) + void (*ctor)(void *)) { return flags; } @@ -1103,7 +1103,7 @@ static void setup_object(struct kmem_cache *s, struct page *page, { setup_object_debug(s, page, object); if (unlikely(s->ctor)) - s->ctor(s, object); + s->ctor(object); } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -2286,7 +2286,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, const char *name, size_t size, size_t align, unsigned long flags, - void (*ctor)(struct kmem_cache *, void *)) + void (*ctor)(void *)) { memset(s, 0, kmem_size); s->name = name; @@ -3042,7 +3042,7 @@ static int slab_unmergeable(struct kmem_cache *s) static struct kmem_cache *find_mergeable(size_t size, size_t align, unsigned long flags, const char *name, - void (*ctor)(struct kmem_cache *, void *)) + void (*ctor)(void *)) { struct kmem_cache *s; @@ -3082,8 +3082,7 @@ static struct kmem_cache *find_mergeable(size_t size, } struct kmem_cache *kmem_cache_create(const char *name, size_t size, - size_t align, unsigned long flags, - void (*ctor)(struct kmem_cache *, void *)) + size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; diff --git a/net/socket.c b/net/socket.c index 1310a82cbba..8ef8ba81b9e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -265,7 +265,7 @@ static void sock_destroy_inode(struct inode *inode) container_of(inode, struct socket_alloc, vfs_inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 5a9b0e7828c..23a2b8f6dc4 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -897,7 +897,7 @@ static struct file_system_type rpc_pipe_fs_type = { }; static void -init_once(struct kmem_cache * cachep, void *foo) +init_once(void *foo) { struct rpc_inode *rpci = (struct rpc_inode *) foo; -- cgit v1.2.3-70-g09d2 From 09a05394fe2448a4139b014936330af23fa7ec83 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: clone This moves all the ptrace initialization and tracing logic for task creation into tracehook.h and ptrace.h inlines. It reorganizes the code slightly, but should not change any behavior. There are four tracehook entry points, at each important stage of task creation. This keeps the interface from the core fork.c code fairly clean, while supporting the complex setup required for ptrace or something like it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 22 ++++++++++ include/linux/tracehook.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 69 +++++++++++++------------------- 3 files changed, 150 insertions(+), 41 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c74abfc4c7e..dae6d85520f 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -154,6 +154,28 @@ static inline int ptrace_event(int mask, int event, unsigned long message) return 1; } +/** + * ptrace_init_task - initialize ptrace state for a new child + * @child: new child task + * @ptrace: true if child should be ptrace'd by parent's tracer + * + * This is called immediately after adding @child to its parent's children + * list. @ptrace is false in the normal case, and true to ptrace @child. + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void ptrace_init_task(struct task_struct *child, bool ptrace) +{ + INIT_LIST_HEAD(&child->ptrace_entry); + INIT_LIST_HEAD(&child->ptraced); + child->parent = child->real_parent; + child->ptrace = 0; + if (unlikely(ptrace)) { + child->ptrace = current->ptrace; + __ptrace_link(child, current->parent); + } +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 967ab473afb..3ebc58b5976 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -110,4 +110,104 @@ static inline void tracehook_report_exit(long *exit_code) ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); } +/** + * tracehook_prepare_clone - prepare for new child to be cloned + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * + * This is called before a new user task is to be cloned. + * Its return value will be passed to tracehook_finish_clone(). + * + * Called with no locks held. + */ +static inline int tracehook_prepare_clone(unsigned clone_flags) +{ + if (clone_flags & CLONE_UNTRACED) + return 0; + + if (clone_flags & CLONE_VFORK) { + if (current->ptrace & PT_TRACE_VFORK) + return PTRACE_EVENT_VFORK; + } else if ((clone_flags & CSIGNAL) != SIGCHLD) { + if (current->ptrace & PT_TRACE_CLONE) + return PTRACE_EVENT_CLONE; + } else if (current->ptrace & PT_TRACE_FORK) + return PTRACE_EVENT_FORK; + + return 0; +} + +/** + * tracehook_finish_clone - new child created and being attached + * @child: new child task + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * @trace: return value from tracehook_clone_prepare() + * + * This is called immediately after adding @child to its parent's children list. + * The @trace value is that returned by tracehook_prepare_clone(). + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_clone(struct task_struct *child, + unsigned long clone_flags, int trace) +{ + ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); +} + +/** + * tracehook_report_clone - in parent, new child is about to start running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: new child task + * + * Called after a child is set up, but before it has been started running. + * The @trace value is that returned by tracehook_clone_prepare(). + * This is not a good place to block, because the child has not started yet. + * Suspend the child here if desired, and block in tracehook_clone_complete(). + * This must prevent the child from self-reaping if tracehook_clone_complete() + * uses the @child pointer; otherwise it might have died and been released by + * the time tracehook_report_clone_complete() is called. + * + * Called with no locks held, but the child cannot run until this returns. + */ +static inline void tracehook_report_clone(int trace, struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, struct task_struct *child) +{ + if (unlikely(trace)) { + /* + * The child starts up with an immediate SIGSTOP. + */ + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); + } +} + +/** + * tracehook_report_clone_complete - new child is running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: child task, already running + * + * This is called just after the child has started running. This is + * just before the clone/fork syscall returns, or blocks for vfork + * child completion if @clone_flags has the %CLONE_VFORK bit set. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_clone_complete(int trace, + struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, + struct task_struct *child) +{ + if (unlikely(trace)) + ptrace_event(0, trace, pid); +} + #endif /* */ diff --git a/kernel/fork.c b/kernel/fork.c index 80e83e459b1..b42f8ed2361 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -865,8 +866,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags &= ~PF_SUPERPRIV; new_flags |= PF_FORKNOEXEC; - if (!(clone_flags & CLONE_PTRACE)) - p->ptrace = 0; + new_flags |= PF_STARTING; p->flags = new_flags; clear_freeze_flag(p); } @@ -907,7 +907,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, struct pt_regs *regs, unsigned long stack_size, int __user *child_tidptr, - struct pid *pid) + struct pid *pid, + int trace) { int retval; struct task_struct *p; @@ -1163,8 +1164,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_LIST_HEAD(&p->ptrace_entry); - INIT_LIST_HEAD(&p->ptraced); /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible @@ -1195,7 +1194,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_parent = current->real_parent; else p->real_parent = current; - p->parent = p->real_parent; spin_lock(¤t->sighand->siglock); @@ -1237,8 +1235,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (likely(p->pid)) { list_add_tail(&p->sibling, &p->real_parent->children); - if (unlikely(p->ptrace & PT_PTRACED)) - __ptrace_link(p, current->parent); + tracehook_finish_clone(p, clone_flags, trace); if (thread_group_leader(p)) { if (clone_flags & CLONE_NEWPID) @@ -1323,29 +1320,13 @@ struct task_struct * __cpuinit fork_idle(int cpu) struct pt_regs regs; task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, - &init_struct_pid); + &init_struct_pid, 0); if (!IS_ERR(task)) init_idle(task, cpu); return task; } -static int fork_traceflag(unsigned clone_flags) -{ - if (clone_flags & CLONE_UNTRACED) - return 0; - else if (clone_flags & CLONE_VFORK) { - if (current->ptrace & PT_TRACE_VFORK) - return PTRACE_EVENT_VFORK; - } else if ((clone_flags & CSIGNAL) != SIGCHLD) { - if (current->ptrace & PT_TRACE_CLONE) - return PTRACE_EVENT_CLONE; - } else if (current->ptrace & PT_TRACE_FORK) - return PTRACE_EVENT_FORK; - - return 0; -} - /* * Ok, this is the main fork-routine. * @@ -1380,14 +1361,14 @@ long do_fork(unsigned long clone_flags, } } - if (unlikely(current->ptrace)) { - trace = fork_traceflag (clone_flags); - if (trace) - clone_flags |= CLONE_PTRACE; - } + /* + * When called from kernel_thread, don't do user tracing stuff. + */ + if (likely(user_mode(regs))) + trace = tracehook_prepare_clone(clone_flags); p = copy_process(clone_flags, stack_start, regs, stack_size, - child_tidptr, NULL); + child_tidptr, NULL, trace); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1405,24 +1386,30 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { + tracehook_report_clone(trace, regs, clone_flags, nr, p); + + /* + * We set PF_STARTING at creation in case tracing wants to + * use this to distinguish a fully live task from one that + * hasn't gotten to tracehook_report_clone() yet. Now we + * clear it and set the child going. + */ + p->flags &= ~PF_STARTING; + + if (unlikely(clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); - } - - if (!(clone_flags & CLONE_STOPPED)) - wake_up_new_task(p, clone_flags); - else __set_task_state(p, TASK_STOPPED); - - if (unlikely (trace)) { - current->ptrace_message = nr; - ptrace_notify ((trace << 8) | SIGTRAP); + } else { + wake_up_new_task(p, clone_flags); } + tracehook_report_clone_complete(trace, regs, + clone_flags, nr, p); + if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); wait_for_completion(&vfork); -- cgit v1.2.3-70-g09d2 From daded34be96b1975ff8539ff62ad8b158ce7d842 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: vfork-done This moves the PTRACE_EVENT_VFORK_DONE tracing into a tracehook.h inline, tracehook_report_vfork_done(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ kernel/fork.c | 5 +---- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3ebc58b5976..830e6e16097 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -210,4 +210,22 @@ static inline void tracehook_report_clone_complete(int trace, ptrace_event(0, trace, pid); } +/** + * tracehook_report_vfork_done - vfork parent's child has exited or exec'd + * @child: child task, already running + * @pid: new child's PID in the parent's namespace + * + * Called after a %CLONE_VFORK parent has waited for the child to complete. + * The clone/vfork system call will return immediately after this. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_vfork_done(struct task_struct *child, + pid_t pid) +{ + ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); +} + #endif /* */ diff --git a/kernel/fork.c b/kernel/fork.c index b42f8ed2361..abb3ed6298f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1414,10 +1414,7 @@ long do_fork(unsigned long clone_flags, freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) { - current->ptrace_message = nr; - ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); - } + tracehook_report_vfork_done(p, nr); } } else { nr = PTR_ERR(p); -- cgit v1.2.3-70-g09d2 From 7f2da1e7d0330395e5e9e350b879b98a1ea495df Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 10 May 2008 20:44:54 -0400 Subject: [PATCH] kill altroot long overdue... Signed-off-by: Al Viro --- fs/namei.c | 89 +------------------------------------------ fs/namespace.c | 8 +--- fs/open.c | 3 +- include/asm-alpha/namei.h | 17 --------- include/asm-arm/namei.h | 25 ------------ include/asm-avr32/namei.h | 7 ---- include/asm-blackfin/namei.h | 19 --------- include/asm-cris/namei.h | 17 --------- include/asm-frv/namei.h | 18 --------- include/asm-h8300/namei.h | 17 --------- include/asm-ia64/namei.h | 25 ------------ include/asm-m32r/namei.h | 17 --------- include/asm-m68k/namei.h | 17 --------- include/asm-m68knommu/namei.h | 1 - include/asm-mips/namei.h | 11 ------ include/asm-mn10300/namei.h | 22 ----------- include/asm-parisc/namei.h | 17 --------- include/asm-powerpc/namei.h | 20 ---------- include/asm-s390/namei.h | 21 ---------- include/asm-sh/namei.h | 17 --------- include/asm-sparc/namei.h | 8 ---- include/asm-sparc64/namei.h | 1 - include/asm-um/namei.h | 6 --- include/asm-v850/namei.h | 17 --------- include/asm-x86/namei.h | 11 ------ include/asm-xtensa/namei.h | 26 ------------- include/linux/fs_struct.h | 3 +- include/linux/namei.h | 1 - kernel/exec_domain.c | 1 - kernel/exit.c | 2 - kernel/fork.c | 7 ---- 31 files changed, 5 insertions(+), 466 deletions(-) delete mode 100644 include/asm-alpha/namei.h delete mode 100644 include/asm-arm/namei.h delete mode 100644 include/asm-avr32/namei.h delete mode 100644 include/asm-blackfin/namei.h delete mode 100644 include/asm-cris/namei.h delete mode 100644 include/asm-frv/namei.h delete mode 100644 include/asm-h8300/namei.h delete mode 100644 include/asm-ia64/namei.h delete mode 100644 include/asm-m32r/namei.h delete mode 100644 include/asm-m68k/namei.h delete mode 100644 include/asm-m68knommu/namei.h delete mode 100644 include/asm-mips/namei.h delete mode 100644 include/asm-mn10300/namei.h delete mode 100644 include/asm-parisc/namei.h delete mode 100644 include/asm-powerpc/namei.h delete mode 100644 include/asm-s390/namei.h delete mode 100644 include/asm-sh/namei.h delete mode 100644 include/asm-sparc/namei.h delete mode 100644 include/asm-sparc64/namei.h delete mode 100644 include/asm-um/namei.h delete mode 100644 include/asm-v850/namei.h delete mode 100644 include/asm-x86/namei.h delete mode 100644 include/asm-xtensa/namei.h (limited to 'kernel/fork.c') diff --git a/fs/namei.c b/fs/namei.c index 6c76e1ee9c4..095818089ac 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE]) @@ -562,27 +561,16 @@ out_unlock: return result; } -static int __emul_lookup_dentry(const char *, struct nameidata *); - /* SMP-safe */ -static __always_inline int +static __always_inline void walk_init_root(const char *name, struct nameidata *nd) { struct fs_struct *fs = current->fs; read_lock(&fs->lock); - if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { - nd->path = fs->altroot; - path_get(&fs->altroot); - read_unlock(&fs->lock); - if (__emul_lookup_dentry(name,nd)) - return 0; - read_lock(&fs->lock); - } nd->path = fs->root; path_get(&fs->root); read_unlock(&fs->lock); - return 1; } /* @@ -623,12 +611,9 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l if (*link == '/') { path_put(&nd->path); - if (!walk_init_root(link, nd)) - /* weird __emul_prefix() stuff did it */ - goto out; + walk_init_root(link, nd); } res = link_path_walk(link, nd); -out: if (nd->depth || res || nd->last_type!=LAST_NORM) return res; /* @@ -1077,67 +1062,6 @@ static int path_walk(const char *name, struct nameidata *nd) return link_path_walk(name, nd); } -/* - * SMP-safe: Returns 1 and nd will have valid dentry and mnt, if - * everything is done. Returns 0 and drops input nd, if lookup failed; - */ -static int __emul_lookup_dentry(const char *name, struct nameidata *nd) -{ - if (path_walk(name, nd)) - return 0; /* something went wrong... */ - - if (!nd->path.dentry->d_inode || - S_ISDIR(nd->path.dentry->d_inode->i_mode)) { - struct path old_path = nd->path; - struct qstr last = nd->last; - int last_type = nd->last_type; - struct fs_struct *fs = current->fs; - - /* - * NAME was not found in alternate root or it's a directory. - * Try to find it in the normal root: - */ - nd->last_type = LAST_ROOT; - read_lock(&fs->lock); - nd->path = fs->root; - path_get(&fs->root); - read_unlock(&fs->lock); - if (path_walk(name, nd) == 0) { - if (nd->path.dentry->d_inode) { - path_put(&old_path); - return 1; - } - path_put(&nd->path); - } - nd->path = old_path; - nd->last = last; - nd->last_type = last_type; - } - return 1; -} - -void set_fs_altroot(void) -{ - char *emul = __emul_prefix(); - struct nameidata nd; - struct path path = {}, old_path; - int err; - struct fs_struct *fs = current->fs; - - if (!emul) - goto set_it; - err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd); - if (!err) - path = nd.path; -set_it: - write_lock(&fs->lock); - old_path = fs->altroot; - fs->altroot = path; - write_unlock(&fs->lock); - if (old_path.dentry) - path_put(&old_path); -} - /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int do_path_lookup(int dfd, const char *name, unsigned int flags, struct nameidata *nd) @@ -1153,14 +1077,6 @@ static int do_path_lookup(int dfd, const char *name, if (*name=='/') { read_lock(&fs->lock); - if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { - nd->path = fs->altroot; - path_get(&fs->altroot); - read_unlock(&fs->lock); - if (__emul_lookup_dentry(name,nd)) - goto out; /* found in altroot */ - read_lock(&fs->lock); - } nd->path = fs->root; path_get(&fs->root); read_unlock(&fs->lock); @@ -1194,7 +1110,6 @@ static int do_path_lookup(int dfd, const char *name, } retval = path_walk(name, nd); -out: if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && nd->path.dentry->d_inode)) audit_inode(name, nd->path.dentry); diff --git a/fs/namespace.c b/fs/namespace.c index f30b11e2240..c4fcf48acef 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1972,7 +1972,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, struct fs_struct *fs) { struct mnt_namespace *new_ns; - struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL; + struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct vfsmount *p, *q; new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL); @@ -2015,10 +2015,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, pwdmnt = p; fs->pwd.mnt = mntget(q); } - if (p == fs->altroot.mnt) { - altrootmnt = p; - fs->altroot.mnt = mntget(q); - } } p = next_mnt(p, mnt_ns->root); q = next_mnt(q, new_ns->root); @@ -2029,8 +2025,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); - if (altrootmnt) - mntput(altrootmnt); return new_ns; } diff --git a/fs/open.c b/fs/open.c index 8e02d42bfe4..d3a2a00f52d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -548,7 +548,7 @@ asmlinkage long sys_chroot(const char __user * filename) struct nameidata nd; int error; - error = __user_walk(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY | LOOKUP_NOALT, &nd); + error = __user_walk(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &nd); if (error) goto out; @@ -561,7 +561,6 @@ asmlinkage long sys_chroot(const char __user * filename) goto dput_and_out; set_fs_root(current->fs, &nd.path); - set_fs_altroot(); error = 0; dput_and_out: path_put(&nd.path); diff --git a/include/asm-alpha/namei.h b/include/asm-alpha/namei.h deleted file mode 100644 index 5cc9bb39499..00000000000 --- a/include/asm-alpha/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $ - * linux/include/asm-alpha/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ALPHA_NAMEI_H -#define __ALPHA_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __ALPHA_NAMEI_H */ diff --git a/include/asm-arm/namei.h b/include/asm-arm/namei.h deleted file mode 100644 index a402d3b9d0f..00000000000 --- a/include/asm-arm/namei.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * linux/include/asm-arm/namei.h - * - * Routines to handle famous /usr/gnemul - * Derived from the Sparc version of this file - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASMARM_NAMEI_H -#define __ASMARM_NAMEI_H - -#define ARM_BSD_EMUL "usr/gnemul/bsd/" - -static inline char *__emul_prefix(void) -{ - switch (current->personality) { - case PER_BSD: - return ARM_BSD_EMUL; - default: - return NULL; - } -} - -#endif /* __ASMARM_NAMEI_H */ diff --git a/include/asm-avr32/namei.h b/include/asm-avr32/namei.h deleted file mode 100644 index f0a26de06ca..00000000000 --- a/include/asm-avr32/namei.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __ASM_AVR32_NAMEI_H -#define __ASM_AVR32_NAMEI_H - -/* This dummy routine may be changed to something useful */ -#define __emul_prefix() NULL - -#endif /* __ASM_AVR32_NAMEI_H */ diff --git a/include/asm-blackfin/namei.h b/include/asm-blackfin/namei.h deleted file mode 100644 index 8b89a2d65cb..00000000000 --- a/include/asm-blackfin/namei.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * linux/include/asm/namei.h - * - * Included from linux/fs/namei.c - * - * Changes made by Lineo Inc. May 2001 - */ - -#ifndef __BFIN_NAMEI_H -#define __BFIN_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-cris/namei.h b/include/asm-cris/namei.h deleted file mode 100644 index 8a3be7a6d9f..00000000000 --- a/include/asm-cris/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 2000/07/10 16:32:31 bjornw Exp $ - * linux/include/asm-cris/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __CRIS_NAMEI_H -#define __CRIS_NAMEI_H - -/* used to find file-system prefixes for doing emulations - * see for example asm-sparc/namei.h - * we don't use it... - */ - -#define __emul_prefix() NULL - -#endif /* __CRIS_NAMEI_H */ diff --git a/include/asm-frv/namei.h b/include/asm-frv/namei.h deleted file mode 100644 index 4ea57171d95..00000000000 --- a/include/asm-frv/namei.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-frv/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASM_NAMEI_H -#define __ASM_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif - diff --git a/include/asm-h8300/namei.h b/include/asm-h8300/namei.h deleted file mode 100644 index ab6f196db6e..00000000000 --- a/include/asm-h8300/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-h8300/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __H8300_NAMEI_H -#define __H8300_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-ia64/namei.h b/include/asm-ia64/namei.h deleted file mode 100644 index 78e76807908..00000000000 --- a/include/asm-ia64/namei.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _ASM_IA64_NAMEI_H -#define _ASM_IA64_NAMEI_H - -/* - * Modified 1998, 1999, 2001 - * David Mosberger-Tang , Hewlett-Packard Co - */ - -#include -#include - -#define EMUL_PREFIX_LINUX_IA32 "/emul/ia32-linux/" - -static inline char * -__emul_prefix (void) -{ - switch (current->personality) { - case PER_LINUX32: - return EMUL_PREFIX_LINUX_IA32; - default: - return NULL; - } -} - -#endif /* _ASM_IA64_NAMEI_H */ diff --git a/include/asm-m32r/namei.h b/include/asm-m32r/namei.h deleted file mode 100644 index 210f8056b80..00000000000 --- a/include/asm-m32r/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _ASM_M32R_NAMEI_H -#define _ASM_M32R_NAMEI_H - -/* - * linux/include/asm-m32r/namei.h - * - * Included from linux/fs/namei.c - */ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_M32R_NAMEI_H */ diff --git a/include/asm-m68k/namei.h b/include/asm-m68k/namei.h deleted file mode 100644 index f33f243b644..00000000000 --- a/include/asm-m68k/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-m68k/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __M68K_NAMEI_H -#define __M68K_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif diff --git a/include/asm-m68knommu/namei.h b/include/asm-m68knommu/namei.h deleted file mode 100644 index 31a85d27b93..00000000000 --- a/include/asm-m68knommu/namei.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mips/namei.h b/include/asm-mips/namei.h deleted file mode 100644 index a6605a75246..00000000000 --- a/include/asm-mips/namei.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_NAMEI_H -#define _ASM_NAMEI_H - -/* - * This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_NAMEI_H */ diff --git a/include/asm-mn10300/namei.h b/include/asm-mn10300/namei.h deleted file mode 100644 index bd9ce94aeb6..00000000000 --- a/include/asm-mn10300/namei.h +++ /dev/null @@ -1,22 +0,0 @@ -/* Emulation stuff - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#ifndef _ASM_NAMEI_H -#define _ASM_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_NAMEI_H */ diff --git a/include/asm-parisc/namei.h b/include/asm-parisc/namei.h deleted file mode 100644 index 8d29b3d9fb3..00000000000 --- a/include/asm-parisc/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $ - * linux/include/asm-parisc/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __PARISC_NAMEI_H -#define __PARISC_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __PARISC_NAMEI_H */ diff --git a/include/asm-powerpc/namei.h b/include/asm-powerpc/namei.h deleted file mode 100644 index 657443474a6..00000000000 --- a/include/asm-powerpc/namei.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _ASM_POWERPC_NAMEI_H -#define _ASM_POWERPC_NAMEI_H - -#ifdef __KERNEL__ - -/* - * Adapted from include/asm-alpha/namei.h - * - * Included from fs/namei.c - */ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NAMEI_H */ diff --git a/include/asm-s390/namei.h b/include/asm-s390/namei.h deleted file mode 100644 index 3e286bdde4b..00000000000 --- a/include/asm-s390/namei.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * include/asm-s390/namei.h - * - * S390 version - * - * Derived from "include/asm-i386/namei.h" - * - * Included from linux/fs/namei.c - */ - -#ifndef __S390_NAMEI_H -#define __S390_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __S390_NAMEI_H */ diff --git a/include/asm-sh/namei.h b/include/asm-sh/namei.h deleted file mode 100644 index 338a5d94714..00000000000 --- a/include/asm-sh/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* $Id: namei.h,v 1.3 2000/07/04 06:24:49 gniibe Exp $ - * linux/include/asm-sh/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __ASM_SH_NAMEI_H -#define __ASM_SH_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __ASM_SH_NAMEI_H */ diff --git a/include/asm-sparc/namei.h b/include/asm-sparc/namei.h deleted file mode 100644 index eff944b8e32..00000000000 --- a/include/asm-sparc/namei.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef ___ASM_SPARC_NAMEI_H -#define ___ASM_SPARC_NAMEI_H -#if defined(__sparc__) && defined(__arch64__) -#include -#else -#include -#endif -#endif diff --git a/include/asm-sparc64/namei.h b/include/asm-sparc64/namei.h deleted file mode 100644 index 1344a910ba2..00000000000 --- a/include/asm-sparc64/namei.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-um/namei.h b/include/asm-um/namei.h deleted file mode 100644 index 002984d5bc8..00000000000 --- a/include/asm-um/namei.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __UM_NAMEI_H -#define __UM_NAMEI_H - -#include "asm/arch/namei.h" - -#endif diff --git a/include/asm-v850/namei.h b/include/asm-v850/namei.h deleted file mode 100644 index ee8339b2384..00000000000 --- a/include/asm-v850/namei.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * linux/include/asm-v850/namei.h - * - * Included from linux/fs/namei.c - */ - -#ifndef __V850_NAMEI_H__ -#define __V850_NAMEI_H__ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __V850_NAMEI_H__ */ diff --git a/include/asm-x86/namei.h b/include/asm-x86/namei.h deleted file mode 100644 index 415ef5d9550..00000000000 --- a/include/asm-x86/namei.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_NAMEI_H -#define _ASM_X86_NAMEI_H - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* _ASM_X86_NAMEI_H */ diff --git a/include/asm-xtensa/namei.h b/include/asm-xtensa/namei.h deleted file mode 100644 index 3fdff039d27..00000000000 --- a/include/asm-xtensa/namei.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * include/asm-xtensa/namei.h - * - * Included from linux/fs/namei.c - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - -#ifndef _XTENSA_NAMEI_H -#define _XTENSA_NAMEI_H - -#ifdef __KERNEL__ - -/* This dummy routine maybe changed to something useful - * for /usr/gnemul/ emulation stuff. - * Look at asm-sparc/namei.h for details. - */ - -#define __emul_prefix() NULL - -#endif /* __KERNEL__ */ -#endif /* _XTENSA_NAMEI_H */ diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 282f5421912..9e5a06e78d0 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -7,7 +7,7 @@ struct fs_struct { atomic_t count; rwlock_t lock; int umask; - struct path root, pwd, altroot; + struct path root, pwd; }; #define INIT_FS { \ @@ -19,7 +19,6 @@ struct fs_struct { extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); -extern void set_fs_altroot(void); extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); diff --git a/include/linux/namei.h b/include/linux/namei.h index 3cf62d26d49..768773d5785 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -47,7 +47,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_DIRECTORY 2 #define LOOKUP_CONTINUE 4 #define LOOKUP_PARENT 16 -#define LOOKUP_NOALT 32 #define LOOKUP_REVAL 64 /* * Intent data diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index c1ef192aa65..0d407e88673 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -168,7 +168,6 @@ __set_personality(u_long personality) current->personality = personality; oep = current_thread_info()->exec_domain; current_thread_info()->exec_domain = ep; - set_fs_altroot(); module_put(oep->module); return 0; diff --git a/kernel/exit.c b/kernel/exit.c index 6cdf60712bd..0caf590548a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -565,8 +565,6 @@ void put_fs_struct(struct fs_struct *fs) if (atomic_dec_and_test(&fs->count)) { path_put(&fs->root); path_put(&fs->pwd); - if (fs->altroot.dentry) - path_put(&fs->altroot); kmem_cache_free(fs_cachep, fs); } } diff --git a/kernel/fork.c b/kernel/fork.c index abb3ed6298f..5e050c1317c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -657,13 +657,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old) path_get(&old->root); fs->pwd = old->pwd; path_get(&old->pwd); - if (old->altroot.dentry) { - fs->altroot = old->altroot; - path_get(&old->altroot); - } else { - fs->altroot.mnt = NULL; - fs->altroot.dentry = NULL; - } read_unlock(&old->lock); } return fs; -- cgit v1.2.3-70-g09d2 From 5995477ab7f3522c497c9c4a1c55373e9d655574 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sun, 27 Jul 2008 17:29:15 +0200 Subject: task IO accounting: improve code readability Put all i/o statistics in struct proc_io_accounting and use inline functions to initialize and increment statistics, removing a lot of single variable assignments. This also reduces the kernel size as following (with CONFIG_TASK_XACCT=y and CONFIG_TASK_IO_ACCOUNTING=y). text data bss dec hex filename 11651 0 0 11651 2d83 kernel/exit.o.before 11619 0 0 11619 2d63 kernel/exit.o.after 10886 132 136 11154 2b92 kernel/fork.o.before 10758 132 136 11026 2b12 kernel/fork.o.after 3082029 807968 4818600 8708597 84e1f5 vmlinux.o.before 3081869 807968 4818600 8708437 84e155 vmlinux.o.after Signed-off-by: Andrea Righi Acked-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/proc/base.c | 57 ++++++++++------------------------ include/linux/sched.h | 19 ++++-------- include/linux/task_io_accounting.h | 27 ++++++++++++++-- include/linux/task_io_accounting_ops.h | 56 +++++++++++++++++++++++++++------ kernel/exit.c | 30 ++---------------- kernel/fork.c | 15 ++------- kernel/tsacct.c | 14 ++++----- 7 files changed, 104 insertions(+), 114 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index e74308bdabd..3d94906c7aa 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -2402,44 +2403,17 @@ static int proc_base_fill_cache(struct file *filp, void *dirent, #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, char *buffer, int whole) { - u64 rchar, wchar, syscr, syscw; - struct task_io_accounting ioac; - - rchar = task->rchar; - wchar = task->wchar; - syscr = task->syscr; - syscw = task->syscw; - memcpy(&ioac, &task->ioac, sizeof(ioac)); - - if (whole) { - unsigned long flags; - - if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - struct task_struct *t = task; - - rchar += sig->rchar; - wchar += sig->wchar; - syscr += sig->syscr; - syscw += sig->syscw; - - ioac.read_bytes += sig->ioac.read_bytes; - ioac.write_bytes += sig->ioac.write_bytes; - ioac.cancelled_write_bytes += - sig->ioac.cancelled_write_bytes; - while_each_thread(task, t) { - rchar += t->rchar; - wchar += t->wchar; - syscr += t->syscr; - syscw += t->syscw; - - ioac.read_bytes += t->ioac.read_bytes; - ioac.write_bytes += t->ioac.write_bytes; - ioac.cancelled_write_bytes += - t->ioac.cancelled_write_bytes; - } - unlock_task_sighand(task, &flags); - } + struct proc_io_accounting acct = task->ioac; + unsigned long flags; + + if (whole && lock_task_sighand(task, &flags)) { + struct task_struct *t = task; + + task_io_accounting_add(&acct, &task->signal->ioac); + while_each_thread(task, t) + task_io_accounting_add(&acct, &t->ioac); + + unlock_task_sighand(task, &flags); } return sprintf(buffer, "rchar: %llu\n" @@ -2449,9 +2423,10 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole) "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", - rchar, wchar, syscr, syscw, - ioac.read_bytes, ioac.write_bytes, - ioac.cancelled_write_bytes); + acct.chr.rchar, acct.chr.wchar, + acct.chr.syscr, acct.chr.syscw, + acct.blk.read_bytes, acct.blk.write_bytes, + acct.blk.cancelled_write_bytes); } static int proc_tid_io_accounting(struct task_struct *task, char *buffer) diff --git a/include/linux/sched.h b/include/linux/sched.h index f59318a0099..034c1ca6b33 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -505,10 +505,7 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; -#ifdef CONFIG_TASK_XACCT - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the @@ -1256,11 +1253,7 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ -#ifdef CONFIG_TASK_XACCT -/* i/o counters(bytes read/written, #syscalls */ - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ @@ -2190,22 +2183,22 @@ extern long sched_group_rt_period(struct task_group *tg); #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { - tsk->rchar += amt; + tsk->ioac.chr.rchar += amt; } static inline void add_wchar(struct task_struct *tsk, ssize_t amt) { - tsk->wchar += amt; + tsk->ioac.chr.wchar += amt; } static inline void inc_syscr(struct task_struct *tsk) { - tsk->syscr++; + tsk->ioac.chr.syscr++; } static inline void inc_syscw(struct task_struct *tsk) { - tsk->syscw++; + tsk->ioac.chr.syscw++; } #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index 44d00e9ccee..165390f8b93 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -1,5 +1,5 @@ /* - * task_io_accounting: a structure which is used for recording a single task's + * proc_io_accounting: a structure which is used for recording a single task's * IO statistics. * * Don't include this header file directly - it is designed to be dragged in via @@ -8,6 +8,22 @@ * Blame akpm@osdl.org for all this. */ +#ifdef CONFIG_TASK_XACCT +struct task_chr_io_accounting { + /* bytes read */ + u64 rchar; + /* bytes written */ + u64 wchar; + /* # of read syscalls */ + u64 syscr; + /* # of write syscalls */ + u64 syscw; +}; +#else /* CONFIG_TASK_XACCT */ +struct task_chr_io_accounting { +}; +#endif /* CONFIG_TASK_XACCT */ + #ifdef CONFIG_TASK_IO_ACCOUNTING struct task_io_accounting { /* @@ -31,7 +47,12 @@ struct task_io_accounting { */ u64 cancelled_write_bytes; }; -#else +#else /* CONFIG_TASK_IO_ACCOUNTING */ struct task_io_accounting { }; -#endif +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +struct proc_io_accounting { + struct task_chr_io_accounting chr; + struct task_io_accounting blk; +}; diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index ff46c6fad79..e6f958ebe97 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -9,7 +9,7 @@ #ifdef CONFIG_TASK_IO_ACCOUNTING static inline void task_io_account_read(size_t bytes) { - current->ioac.read_bytes += bytes; + current->ioac.blk.read_bytes += bytes; } /* @@ -18,12 +18,12 @@ static inline void task_io_account_read(size_t bytes) */ static inline unsigned long task_io_get_inblock(const struct task_struct *p) { - return p->ioac.read_bytes >> 9; + return p->ioac.blk.read_bytes >> 9; } static inline void task_io_account_write(size_t bytes) { - current->ioac.write_bytes += bytes; + current->ioac.blk.write_bytes += bytes; } /* @@ -32,17 +32,25 @@ static inline void task_io_account_write(size_t bytes) */ static inline unsigned long task_io_get_oublock(const struct task_struct *p) { - return p->ioac.write_bytes >> 9; + return p->ioac.blk.write_bytes >> 9; } static inline void task_io_account_cancelled_write(size_t bytes) { - current->ioac.cancelled_write_bytes += bytes; + current->ioac.blk.cancelled_write_bytes += bytes; } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) { - memset(&tsk->ioac, 0, sizeof(tsk->ioac)); + memset(ioac, 0, sizeof(*ioac)); +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->blk.read_bytes += src->blk.read_bytes; + dst->blk.write_bytes += src->blk.write_bytes; + dst->blk.cancelled_write_bytes += src->blk.cancelled_write_bytes; } #else @@ -69,9 +77,37 @@ static inline void task_io_account_cancelled_write(size_t bytes) { } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) +{ +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) { } -#endif /* CONFIG_TASK_IO_ACCOUNTING */ -#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +#ifdef CONFIG_TASK_XACCT +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->chr.rchar += src->chr.rchar; + dst->chr.wchar += src->chr.wchar; + dst->chr.syscr += src->chr.syscr; + dst->chr.syscw += src->chr.syscw; +} +#else +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ +} +#endif /* CONFIG_TASK_XACCT */ + +static inline void task_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + task_chr_io_accounting_add(dst, src); + task_blk_io_accounting_add(dst, src); +} +#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ diff --git a/kernel/exit.c b/kernel/exit.c index 0caf590548a..eb4d6470d1d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -121,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk) sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); -#ifdef CONFIG_TASK_XACCT - sig->rchar += tsk->rchar; - sig->wchar += tsk->wchar; - sig->syscr += tsk->syscr; - sig->syscw += tsk->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - sig->ioac.read_bytes += tsk->ioac.read_bytes; - sig->ioac.write_bytes += tsk->ioac.write_bytes; - sig->ioac.cancelled_write_bytes += - tsk->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1363,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options, psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; -#ifdef CONFIG_TASK_XACCT - psig->rchar += p->rchar + sig->rchar; - psig->wchar += p->wchar + sig->wchar; - psig->syscr += p->syscr + sig->syscr; - psig->syscw += p->syscw + sig->syscw; -#endif /* CONFIG_TASK_XACCT */ -#ifdef CONFIG_TASK_IO_ACCOUNTING - psig->ioac.read_bytes += - p->ioac.read_bytes + sig->ioac.read_bytes; - psig->ioac.write_bytes += - p->ioac.write_bytes + sig->ioac.write_bytes; - psig->ioac.cancelled_write_bytes += - p->ioac.cancelled_write_bytes + - sig->ioac.cancelled_write_bytes; -#endif /* CONFIG_TASK_IO_ACCOUNTING */ + task_io_accounting_add(&psig->ioac, &p->ioac); + task_io_accounting_add(&psig->ioac, &sig->ioac); spin_unlock_irq(&p->parent->sighand->siglock); } diff --git a/kernel/fork.c b/kernel/fork.c index 5e050c1317c..8214ba7c8bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -806,12 +806,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; -#ifdef CONFIG_TASK_XACCT - sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0; -#endif -#ifdef CONFIG_TASK_IO_ACCOUNTING - memset(&sig->ioac, 0, sizeof(sig->ioac)); -#endif + task_io_accounting_init(&sig->ioac); sig->sum_sched_runtime = 0; INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); @@ -994,13 +989,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->last_switch_timestamp = 0; #endif -#ifdef CONFIG_TASK_XACCT - p->rchar = 0; /* I/O counter: bytes read */ - p->wchar = 0; /* I/O counter: bytes written */ - p->syscr = 0; /* I/O counter: read syscalls */ - p->syscw = 0; /* I/O counter: write syscalls */ -#endif - task_io_accounting_init(p); + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); p->it_virt_expires = cputime_zero; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 3da47ccdc5e..f9cd2561689 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -94,14 +94,14 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) stats->hiwater_vm = mm->hiwater_vm * PAGE_SIZE / KB; mmput(mm); } - stats->read_char = p->rchar; - stats->write_char = p->wchar; - stats->read_syscalls = p->syscr; - stats->write_syscalls = p->syscw; + stats->read_char = p->ioac.chr.rchar; + stats->write_char = p->ioac.chr.wchar; + stats->read_syscalls = p->ioac.chr.syscr; + stats->write_syscalls = p->ioac.chr.syscw; #ifdef CONFIG_TASK_IO_ACCOUNTING - stats->read_bytes = p->ioac.read_bytes; - stats->write_bytes = p->ioac.write_bytes; - stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes; + stats->read_bytes = p->ioac.blk.read_bytes; + stats->write_bytes = p->ioac.blk.write_bytes; + stats->cancelled_write_bytes = p->ioac.blk.cancelled_write_bytes; #else stats->read_bytes = 0; stats->write_bytes = 0; -- cgit v1.2.3-70-g09d2 From cddb8a5c14aa89810b40495d94d3d2a0faee6619 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:29 -0700 Subject: mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli Signed-off-by: Nick Piggin Signed-off-by: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kvm/Kconfig | 1 + include/linux/mm_types.h | 4 + include/linux/mmu_notifier.h | 279 +++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 3 + mm/Kconfig | 3 + mm/Makefile | 1 + mm/filemap_xip.c | 3 +- mm/fremap.c | 3 + mm/hugetlb.c | 3 + mm/memory.c | 35 +++++- mm/mmap.c | 2 + mm/mmu_notifier.c | 277 ++++++++++++++++++++++++++++++++++++++++++ mm/mprotect.c | 3 + mm/mremap.c | 6 + mm/rmap.c | 13 +- 15 files changed, 623 insertions(+), 13 deletions(-) create mode 100644 include/linux/mmu_notifier.h create mode 100644 mm/mmu_notifier.c (limited to 'kernel/fork.c') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8d45fabc5f3..ce3251ce550 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM select PREEMPT_NOTIFIERS + select MMU_NOTIFIER select ANON_INODES ---help--- Support hosting fully virtualized guest machines using hardware diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 746f975b58e..386edbe2cb4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -253,6 +254,9 @@ struct mm_struct { struct file *exe_file; unsigned long num_exe_file_vmas; #endif +#ifdef CONFIG_MMU_NOTIFIER + struct mmu_notifier_mm *mmu_notifier_mm; +#endif }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h new file mode 100644 index 00000000000..b77486d152c --- /dev/null +++ b/include/linux/mmu_notifier.h @@ -0,0 +1,279 @@ +#ifndef _LINUX_MMU_NOTIFIER_H +#define _LINUX_MMU_NOTIFIER_H + +#include +#include +#include + +struct mmu_notifier; +struct mmu_notifier_ops; + +#ifdef CONFIG_MMU_NOTIFIER + +/* + * The mmu notifier_mm structure is allocated and installed in + * mm->mmu_notifier_mm inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_mm { + /* all mmu notifiers registerd in this mm are queued in this list */ + struct hlist_head list; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; +}; + +struct mmu_notifier_ops { + /* + * Called either by mmu_notifier_unregister or when the mm is + * being destroyed by exit_mmap, always before all pages are + * freed. This can run concurrently with other mmu notifier + * methods (the ones invoked outside the mm context) and it + * should tear down all secondary mmu mappings and freeze the + * secondary mmu. If this method isn't implemented you've to + * be sure that nothing could possibly write to the pages + * through the secondary mmu by the time the last thread with + * tsk->mm == mm exits. + * + * As side note: the pages freed after ->release returns could + * be immediately reallocated by the gart at an alias physical + * address with a different cache model, so if ->release isn't + * implemented because all _software_ driven memory accesses + * through the secondary mmu are terminated by the time the + * last thread of this mm quits, you've also to be sure that + * speculative _hardware_ operations can't allocate dirty + * cachelines in the cpu that could not be snooped and made + * coherent with the other read and write operations happening + * through the gart alias address, so leading to memory + * corruption. + */ + void (*release)(struct mmu_notifier *mn, + struct mm_struct *mm); + + /* + * clear_flush_young is called after the VM is + * test-and-clearing the young/accessed bitflag in the + * pte. This way the VM will provide proper aging to the + * accesses to the page through the secondary MMUs and not + * only to the ones through the Linux pte. + */ + int (*clear_flush_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * Before this is invoked any secondary MMU is still ok to + * read/write to the page previously pointed to by the Linux + * pte because the page hasn't been freed yet and it won't be + * freed until this returns. If required set_page_dirty has to + * be called internally to this method. + */ + void (*invalidate_page)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * invalidate_range_start() and invalidate_range_end() must be + * paired and are called only when the mmap_sem and/or the + * locks protecting the reverse maps are held. The subsystem + * must guarantee that no additional references are taken to + * the pages in the range established between the call to + * invalidate_range_start() and the matching call to + * invalidate_range_end(). + * + * Invalidation of multiple concurrent ranges may be + * optionally permitted by the driver. Either way the + * establishment of sptes is forbidden in the range passed to + * invalidate_range_begin/end for the whole duration of the + * invalidate_range_begin/end critical section. + * + * invalidate_range_start() is called when all pages in the + * range are still mapped and have at least a refcount of one. + * + * invalidate_range_end() is called when all pages in the + * range have been unmapped and the pages have been freed by + * the VM. + * + * The VM will remove the page table entries and potentially + * the page between invalidate_range_start() and + * invalidate_range_end(). If the page must not be freed + * because of pending I/O or other circumstances then the + * invalidate_range_start() callback (or the initial mapping + * by the driver) must make sure that the refcount is kept + * elevated. + * + * If the driver increases the refcount when the pages are + * initially mapped into an address space then either + * invalidate_range_start() or invalidate_range_end() may + * decrease the refcount. If the refcount is decreased on + * invalidate_range_start() then the VM can free pages as page + * table entries are removed. If the refcount is only + * droppped on invalidate_range_end() then the driver itself + * will drop the last refcount but it must take care to flush + * any secondary tlb before doing the final free on the + * page. Pages will no longer be referenced by the linux + * address space but may still be referenced by sptes until + * the last refcount is dropped. + */ + void (*invalidate_range_start)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); + void (*invalidate_range_end)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); +}; + +/* + * The notifier chains are protected by mmap_sem and/or the reverse map + * semaphores. Notifier chains are only changed when all reverse maps and + * the mmap_sem locks are taken. + * + * Therefore notifier chains can only be traversed when either + * + * 1. mmap_sem is held. + * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock). + * 3. No other concurrent thread can access the list (release) + */ +struct mmu_notifier { + struct hlist_node hlist; + const struct mmu_notifier_ops *ops; +}; + +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return unlikely(mm->mmu_notifier_mm); +} + +extern int mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern int __mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void mmu_notifier_unregister(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); +extern void __mmu_notifier_release(struct mm_struct *mm); +extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end); + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_release(mm); +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_flush_young(mm, address); + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_page(mm, address); +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_start(mm, start, end); +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_end(mm, start, end); +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ + mm->mmu_notifier_mm = NULL; +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_mm_destroy(mm); +} + +/* + * These two macros will sometime replace ptep_clear_flush. + * ptep_clear_flush is impleemnted as macro itself, so this also is + * implemented as a macro until ptep_clear_flush will converted to an + * inline function, to diminish the risk of compilation failure. The + * invalidate_page method over time can be moved outside the PT lock + * and these two macros can be later removed. + */ +#define ptep_clear_flush_notify(__vma, __address, __ptep) \ +({ \ + pte_t __pte; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __pte = ptep_clear_flush(___vma, ___address, __ptep); \ + mmu_notifier_invalidate_page(___vma->vm_mm, ___address); \ + __pte; \ +}) + +#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + +#else /* CONFIG_MMU_NOTIFIER */ + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ +} + +#define ptep_clear_flush_young_notify ptep_clear_flush_young +#define ptep_clear_flush_notify ptep_clear_flush + +#endif /* CONFIG_MMU_NOTIFIER */ + +#endif /* _LINUX_MMU_NOTIFIER_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 8214ba7c8bb..7ce2ebe8479 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -414,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; + mmu_notifier_mm_init(mm); return mm; } @@ -446,6 +448,7 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); + mmu_notifier_mm_destroy(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); diff --git a/mm/Kconfig b/mm/Kconfig index efee5d379df..446c6588c75 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -208,3 +208,6 @@ config NR_QUICK config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS + +config MMU_NOTIFIER + bool diff --git a/mm/Makefile b/mm/Makefile index 06ca2381fef..da4ccf015ae 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o +obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 98a3f31ccd6..380ab402d71 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -188,7 +189,7 @@ __xip_unmap (struct address_space * mapping, if (pte) { /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); page_remove_rmap(page, vma); dec_mm_counter(mm, file_rss); BUG_ON(pte_dirty(pteval)); diff --git a/mm/fremap.c b/mm/fremap.c index 07a9c82ce1a..7881638e4a1 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -214,7 +215,9 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, spin_unlock(&mapping->i_mmap_lock); } + mmu_notifier_invalidate_range_start(mm, start, start + size); err = populate_range(mm, vma, start, size, pgoff); + mmu_notifier_invalidate_range_end(mm, start, start + size); if (!err && !(flags & MAP_NONBLOCK)) { if (unlikely(has_write_lock)) { downgrade_write(&mm->mmap_sem); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3be79dc18c5..80eb0d31d0d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1672,6 +1673,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); + mmu_notifier_invalidate_range_start(mm, start, end); spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); @@ -1713,6 +1715,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { list_del(&page->lru); put_page(page); diff --git a/mm/memory.c b/mm/memory.c index a8ca04faaea..67f0ab9077d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -652,6 +653,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long next; unsigned long addr = vma->vm_start; unsigned long end = vma->vm_end; + int ret; /* * Don't copy ptes where a page fault will fill them correctly. @@ -667,17 +669,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_start(src_mm, addr, end); + + ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next)) - return -ENOMEM; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - return 0; + + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_end(src_mm, + vma->vm_start, end); + return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -881,7 +899,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; int fullmm = (*tlbp)->fullmm; + struct mm_struct *mm = vma->vm_mm; + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { unsigned long end; @@ -946,6 +966,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } } out: + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); return start; /* which is now the end (or restart) address */ } @@ -1616,10 +1637,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, { pgd_t *pgd; unsigned long next; - unsigned long end = addr + size; + unsigned long start = addr, end = addr + size; int err; BUG_ON(addr >= end); + mmu_notifier_invalidate_range_start(mm, start, end); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); @@ -1627,6 +1649,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + mmu_notifier_invalidate_range_end(mm, start, end); return err; } EXPORT_SYMBOL_GPL(apply_to_page_range); @@ -1839,7 +1862,7 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush(vma, address, page_table); + ptep_clear_flush_notify(vma, address, page_table); set_pte_at(mm, address, page_table, entry); update_mmu_cache(vma, address, entry); lru_cache_add_active(new_page); diff --git a/mm/mmap.c b/mm/mmap.c index e5f9cb83d6d..245c3d69067 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -2061,6 +2062,7 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ arch_exit_mmap(mm); + mmu_notifier_release(mm); lru_add_drain(); flush_cache_mm(mm); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c new file mode 100644 index 00000000000..5f4ef0250be --- /dev/null +++ b/mm/mmu_notifier.c @@ -0,0 +1,277 @@ +/* + * linux/mm/mmu_notifier.c + * + * Copyright (C) 2008 Qumranet, Inc. + * Copyright (C) 2008 SGI + * Christoph Lameter + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * This function can't run concurrently against mmu_notifier_register + * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap + * runs with mm_users == 0. Other tasks may still invoke mmu notifiers + * in parallel despite there being no task using this mm any more, + * through the vmas outside of the exit_mmap context, such as with + * vmtruncate. This serializes against mmu_notifier_unregister with + * the mmu_notifier_mm->lock in addition to RCU and it serializes + * against the other mmu notifiers with RCU. struct mmu_notifier_mm + * can't go away from under us as exit_mmap holds an mm_count pin + * itself. + */ +void __mmu_notifier_release(struct mm_struct *mm) +{ + struct mmu_notifier *mn; + + spin_lock(&mm->mmu_notifier_mm->lock); + while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { + mn = hlist_entry(mm->mmu_notifier_mm->list.first, + struct mmu_notifier, + hlist); + /* + * We arrived before mmu_notifier_unregister so + * mmu_notifier_unregister will do nothing other than + * to wait ->release to finish and + * mmu_notifier_unregister to return. + */ + hlist_del_init_rcu(&mn->hlist); + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + spin_lock(&mm->mmu_notifier_mm->lock); + } + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * synchronize_rcu here prevents mmu_notifier_release to + * return to exit_mmap (which would proceed freeing all pages + * in the mm) until the ->release method returns, if it was + * invoked by mmu_notifier_unregister. + * + * The mmu_notifier_mm can't go away from under us because one + * mm_count is hold by exit_mmap. + */ + synchronize_rcu(); +} + +/* + * If no young bitflag is supported by the hardware, ->clear_flush_young can + * unmap the address and return 1 or 0 depending if the mapping previously + * existed or not. + */ +int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + int young = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->clear_flush_young) + young |= mn->ops->clear_flush_young(mn, mm, address); + } + rcu_read_unlock(); + + return young; +} + +void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_page) + mn->ops->invalidate_page(mn, mm, address); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_start) + mn->ops->invalidate_range_start(mn, mm, start, end); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_end) + mn->ops->invalidate_range_end(mn, mm, start, end); + } + rcu_read_unlock(); +} + +static int do_mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm, + int take_mmap_sem) +{ + struct mmu_notifier_mm *mmu_notifier_mm; + int ret; + + BUG_ON(atomic_read(&mm->mm_users) <= 0); + + ret = -ENOMEM; + mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); + if (unlikely(!mmu_notifier_mm)) + goto out; + + if (take_mmap_sem) + down_write(&mm->mmap_sem); + ret = mm_take_all_locks(mm); + if (unlikely(ret)) + goto out_cleanup; + + if (!mm_has_notifiers(mm)) { + INIT_HLIST_HEAD(&mmu_notifier_mm->list); + spin_lock_init(&mmu_notifier_mm->lock); + mm->mmu_notifier_mm = mmu_notifier_mm; + mmu_notifier_mm = NULL; + } + atomic_inc(&mm->mm_count); + + /* + * Serialize the update against mmu_notifier_unregister. A + * side note: mmu_notifier_release can't run concurrently with + * us because we hold the mm_users pin (either implicitly as + * current->mm or explicitly with get_task_mm() or similar). + * We can't race against any other mmu notifier method either + * thanks to mm_take_all_locks(). + */ + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list); + spin_unlock(&mm->mmu_notifier_mm->lock); + + mm_drop_all_locks(mm); +out_cleanup: + if (take_mmap_sem) + up_write(&mm->mmap_sem); + /* kfree() does nothing if mmu_notifier_mm is NULL */ + kfree(mmu_notifier_mm); +out: + BUG_ON(atomic_read(&mm->mm_users) <= 0); + return ret; +} + +/* + * Must not hold mmap_sem nor any other VM related lock when calling + * this registration function. Must also ensure mm_users can't go down + * to zero while this runs to avoid races with mmu_notifier_release, + * so mm has to be current->mm or the mm should be pinned safely such + * as with get_task_mm(). If the mm is not current->mm, the mm_users + * pin should be released by calling mmput after mmu_notifier_register + * returns. mmu_notifier_unregister must be always called to + * unregister the notifier. mm_count is automatically pinned to allow + * mmu_notifier_unregister to safely run at any time later, before or + * after exit_mmap. ->release will always be called before exit_mmap + * frees the pages. + */ +int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 1); +} +EXPORT_SYMBOL_GPL(mmu_notifier_register); + +/* + * Same as mmu_notifier_register but here the caller must hold the + * mmap_sem in write mode. + */ +int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 0); +} +EXPORT_SYMBOL_GPL(__mmu_notifier_register); + +/* this is called after the last mmu_notifier_unregister() returned */ +void __mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list)); + kfree(mm->mmu_notifier_mm); + mm->mmu_notifier_mm = LIST_POISON1; /* debug */ +} + +/* + * This releases the mm_count pin automatically and frees the mm + * structure if it was the last user of it. It serializes against + * running mmu notifiers with RCU and against mmu_notifier_unregister + * with the unregister lock + RCU. All sptes must be dropped before + * calling mmu_notifier_unregister. ->release or any other notifier + * method may be invoked concurrently with mmu_notifier_unregister, + * and only after mmu_notifier_unregister returned we're guaranteed + * that ->release or any other method can't run anymore. + */ +void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) +{ + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + spin_lock(&mm->mmu_notifier_mm->lock); + if (!hlist_unhashed(&mn->hlist)) { + hlist_del_rcu(&mn->hlist); + + /* + * RCU here will force exit_mmap to wait ->release to finish + * before freeing the pages. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * exit_mmap will block in mmu_notifier_release to + * guarantee ->release is called before freeing the + * pages. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + } else + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * Wait any running method to finish, of course including + * ->release if it was run by mmu_notifier_relase instead of us. + */ + synchronize_rcu(); + + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_notifier_unregister); diff --git a/mm/mprotect.c b/mm/mprotect.c index abd645a3b0a..fded06f923f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -203,10 +204,12 @@ success: dirty_accountable = 1; } + mmu_notifier_invalidate_range_start(mm, start, end); if (is_vm_hugetlb_page(vma)) hugetlb_change_protection(vma, start, end, vma->vm_page_prot); else change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable); + mmu_notifier_invalidate_range_end(mm, start, end); vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); vm_stat_account(mm, newflags, vma->vm_file, nrpages); return 0; diff --git a/mm/mremap.c b/mm/mremap.c index 08e3c7f2bd1..1a7743923c8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -74,7 +75,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; + unsigned long old_start; + old_start = old_addr; + mmu_notifier_invalidate_range_start(vma->vm_mm, + old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -116,6 +121,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); + mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) diff --git a/mm/rmap.c b/mm/rmap.c index 39ae5a9bf38..99bc3f9cd79 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -287,7 +288,7 @@ static int page_referenced_one(struct page *page, if (vma->vm_flags & VM_LOCKED) { referenced++; *mapcount = 1; /* break early from loop */ - } else if (ptep_clear_flush_young(vma, address, pte)) + } else if (ptep_clear_flush_young_notify(vma, address, pte)) referenced++; /* Pretend the page is referenced if the task has the @@ -457,7 +458,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma) pte_t entry; flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, address, pte); + entry = ptep_clear_flush_notify(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(mm, address, pte, entry); @@ -705,14 +706,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * skipped over this mm) then we should reactivate it. */ if (!migration && ((vma->vm_flags & VM_LOCKED) || - (ptep_clear_flush_young(vma, address, pte)))) { + (ptep_clear_flush_young_notify(vma, address, pte)))) { ret = SWAP_FAIL; goto out_unmap; } /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -837,12 +838,12 @@ static void try_to_unmap_cluster(unsigned long cursor, page = vm_normal_page(vma, address, *pte); BUG_ON(!page || PageAnon(page)); - if (ptep_clear_flush_young(vma, address, pte)) + if (ptep_clear_flush_young_notify(vma, address, pte)) continue; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ if (page->index != linear_page_index(vma, address)) -- cgit v1.2.3-70-g09d2