From d559db086ff5be9bcc259e5aa50bf3d881eaf1d1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 5 Mar 2010 13:41:39 -0800 Subject: mm: clean up mm_counter Presently, per-mm statistics counter is defined by macro in sched.h This patch modifies it to - defined in mm.h as inlinf functions - use array instead of macro's name creation. This patch is for reducing patch size in future patch to modify implementation of per-mm counter. Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Minchan Kim Cc: Christoph Lameter Cc: Lee Schermerhorn Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 104 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 90957f14195c..2124cdb2d1d0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -870,6 +870,110 @@ extern int mprotect_fixup(struct vm_area_struct *vma, */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +/* + * per-process(per-mm_struct) statistics. + */ +#if USE_SPLIT_PTLOCKS +/* + * The mm counters are not protected by its page_table_lock, + * so must be incremented atomically. + */ +static inline void set_mm_counter(struct mm_struct *mm, int member, long value) +{ + atomic_long_set(&mm->rss_stat.count[member], value); +} + +static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + return (unsigned long)atomic_long_read(&mm->rss_stat.count[member]); +} + +static inline void add_mm_counter(struct mm_struct *mm, int member, long value) +{ + atomic_long_add(value, &mm->rss_stat.count[member]); +} + +static inline void inc_mm_counter(struct mm_struct *mm, int member) +{ + atomic_long_inc(&mm->rss_stat.count[member]); +} + +static inline void dec_mm_counter(struct mm_struct *mm, int member) +{ + atomic_long_dec(&mm->rss_stat.count[member]); +} + +#else /* !USE_SPLIT_PTLOCKS */ +/* + * The mm counters are protected by its page_table_lock, + * so can be incremented directly. + */ +static inline void set_mm_counter(struct mm_struct *mm, int member, long value) +{ + mm->rss_stat.count[member] = value; +} + +static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + return mm->rss_stat.count[member]; +} + +static inline void add_mm_counter(struct mm_struct *mm, int member, long value) +{ + mm->rss_stat.count[member] += value; +} + +static inline void inc_mm_counter(struct mm_struct *mm, int member) +{ + mm->rss_stat.count[member]++; +} + +static inline void dec_mm_counter(struct mm_struct *mm, int member) +{ + mm->rss_stat.count[member]--; +} + +#endif /* !USE_SPLIT_PTLOCKS */ + +static inline unsigned long get_mm_rss(struct mm_struct *mm) +{ + return get_mm_counter(mm, MM_FILEPAGES) + + get_mm_counter(mm, MM_ANONPAGES); +} + +static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) +{ + return max(mm->hiwater_rss, get_mm_rss(mm)); +} + +static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) +{ + return max(mm->hiwater_vm, mm->total_vm); +} + +static inline void update_hiwater_rss(struct mm_struct *mm) +{ + unsigned long _rss = get_mm_rss(mm); + + if ((mm)->hiwater_rss < _rss) + (mm)->hiwater_rss = _rss; +} + +static inline void update_hiwater_vm(struct mm_struct *mm) +{ + if (mm->hiwater_vm < mm->total_vm) + mm->hiwater_vm = mm->total_vm; +} + +static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, + struct mm_struct *mm) +{ + unsigned long hiwater_rss = get_mm_hiwater_rss(mm); + + if (*maxrss < hiwater_rss) + *maxrss = hiwater_rss; +} + /* * A callback you can register to apply pressure to ageable caches. -- cgit v1.2.3 From 34e55232e59f7b19050267a05ff1226e5cd122a5 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 5 Mar 2010 13:41:40 -0800 Subject: mm: avoid false sharing of mm_counter Considering the nature of per mm stats, it's the shared object among threads and can be a cache-miss point in the page fault path. This patch adds per-thread cache for mm_counter. RSS value will be counted into a struct in task_struct and synchronized with mm's one at events. Now, in this patch, the event is the number of calls to handle_mm_fault. Per-thread value is added to mm at each 64 calls. rough estimation with small benchmark on parallel thread (2threads) shows [before] 4.5 cache-miss/faults [after] 4.0 cache-miss/faults Anyway, the most contended object is mmap_sem if the number of threads grows. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KAMEZAWA Hiroyuki Cc: Minchan Kim Cc: Christoph Lameter Cc: Lee Schermerhorn Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2124cdb2d1d0..8e580c07d171 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -873,7 +873,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, /* * per-process(per-mm_struct) statistics. */ -#if USE_SPLIT_PTLOCKS +#if defined(SPLIT_RSS_COUNTING) /* * The mm counters are not protected by its page_table_lock, * so must be incremented atomically. @@ -883,10 +883,7 @@ static inline void set_mm_counter(struct mm_struct *mm, int member, long value) atomic_long_set(&mm->rss_stat.count[member], value); } -static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) -{ - return (unsigned long)atomic_long_read(&mm->rss_stat.count[member]); -} +unsigned long get_mm_counter(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { @@ -974,6 +971,7 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } +void sync_mm_rss(struct task_struct *task, struct mm_struct *mm); /* * A callback you can register to apply pressure to ageable caches. -- cgit v1.2.3 From 5beb49305251e5669852ed541e8e2f2f7696c53e Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 5 Mar 2010 13:42:07 -0800 Subject: mm: change anon_vma linking to fix multi-process server scalability issue The old anon_vma code can lead to scalability issues with heavily forking workloads. Specifically, each anon_vma will be shared between the parent process and all its child processes. In a workload with 1000 child processes and a VMA with 1000 anonymous pages per process that get COWed, this leads to a system with a million anonymous pages in the same anon_vma, each of which is mapped in just one of the 1000 processes. However, the current rmap code needs to walk them all, leading to O(N) scanning complexity for each page. This can result in systems where one CPU is walking the page tables of 1000 processes in page_referenced_one, while all other CPUs are stuck on the anon_vma lock. This leads to catastrophic failure for a benchmark like AIM7, where the total number of processes can reach in the tens of thousands. Real workloads are still a factor 10 less process intensive than AIM7, but they are catching up. This patch changes the way anon_vmas and VMAs are linked, which allows us to associate multiple anon_vmas with a VMA. At fork time, each child process gets its own anon_vmas, in which its COWed pages will be instantiated. The parents' anon_vma is also linked to the VMA, because non-COWed pages could be present in any of the children. This reduces rmap scanning complexity to O(1) for the pages of the 1000 child processes, with O(N) complexity for at most 1/N pages in the system. This reduces the average scanning cost in heavily forking workloads from O(N) to 2. The only real complexity in this patch stems from the fact that linking a VMA to anon_vmas now involves memory allocations. This means vma_adjust can fail, if it needs to attach a VMA to anon_vma structures. This in turn means error handling needs to be added to the calling functions. A second source of complexity is that, because there can be multiple anon_vmas, the anon_vma linking in vma_adjust can no longer be done under "the" anon_vma lock. To prevent the rmap code from walking up an incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h to make sure it is impossible to compile a kernel that needs both symbolic values for the same bitflag. Some test results: Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test box with 16GB RAM and not quite enough IO), the system ends up running >99% in system time, with every CPU on the same anon_vma lock in the pageout code. With these changes, AIM7 hits the cross-over point around 29.7k users. This happens with ~99% IO wait time, there never seems to be any spike in system time. The anon_vma lock contention appears to be resolved. [akpm@linux-foundation.org: cleanups] Signed-off-by: Rik van Riel Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Lee Schermerhorn Cc: Minchan Kim Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e580c07d171..8e2841a2f441 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,7 +97,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ +#ifdef CONFIG_MMU +#define VM_LOCK_RMAP 0x01000000 /* Do not follow this rmap (mmu mmap) */ +#else #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ @@ -1216,7 +1220,7 @@ static inline void vma_nonlinear_insert(struct vm_area_struct *vma, /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern void vma_adjust(struct vm_area_struct *vma, unsigned long start, +extern int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, -- cgit v1.2.3 From fc148a5f7e0532750c312385c7ee9fa3e9311f34 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 5 Mar 2010 13:42:10 -0800 Subject: mm: remove VM_LOCK_RMAP code When a VMA is in an inconsistent state during setup or teardown, the worst that can happen is that the rmap code will not be able to find the page. The mapping is in the process of being torn down (PTEs just got invalidated by munmap), or set up (no PTEs have been instantiated yet). It is also impossible for the rmap code to follow a pointer to an already freed VMA, because the rmap code holds the anon_vma->lock, which the VMA teardown code needs to take before the VMA is removed from the anon_vma chain. Hence, we should not need the VM_LOCK_RMAP locking at all. Signed-off-by: Rik van Riel Cc: Nick Piggin Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Lee Schermerhorn Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e2841a2f441..3899395a03de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,11 +97,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ -#ifdef CONFIG_MMU -#define VM_LOCK_RMAP 0x01000000 /* Do not follow this rmap (mmu mmap) */ -#else #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ -- cgit v1.2.3 From 53bddb4e9f3f53df02a783751984ddeade71b085 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 10 Mar 2010 15:20:38 -0800 Subject: nommu: fix build breakage Commit 34e55232e59f7b19050267a05ff1226e5cd122a5 ("mm: avoid false sharing of mm_counter") added sync_mm_rss() for syncing loosely accounted rss counters. It's for CONFIG_MMU but sync_mm_rss is called even in NOMMU enviroment (kerne/exit.c, fs/exec.c). Above commit doesn't handle it well. This patch changes SPLIT_RSS_COUNTING depends on SPLIT_PTLOCKS && CONFIG_MMU And for avoid unnecessary function calls, sync_mm_rss changed to be inlined noop function in header file. Reported-by: David Howells Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Mike Frysinger Signed-off-by: Michal Simek Signed-off-by: David Howells Cc: Greg Ungerer Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3899395a03de..7f693b272c4a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -971,7 +971,13 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } +#if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct task_struct *task, struct mm_struct *mm); +#else +static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) +{ +} +#endif /* * A callback you can register to apply pressure to ageable caches. -- cgit v1.2.3 From 718a38211bf4375c0a1efad3afbc5dbaef5d33f9 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 10 Mar 2010 15:20:43 -0800 Subject: mm: introduce dump_page() and print symbolic flag names - introduce dump_page() to print the page info for debugging some error condition. - convert three mm users: bad_page(), print_bad_pte() and memory offline failure. - print an extra field: the symbolic names of page->flags Example dump_page() output: [ 157.521694] page:ffffea0000a7cba8 count:2 mapcount:1 mapping:ffff88001c901791 index:0x147 [ 157.525570] page flags: 0x100000000100068(uptodate|lru|active|swapbacked) Signed-off-by: Wu Fengguang Cc: Ingo Molnar Cc: Alex Chiang Cc: Rik van Riel Cc: Andi Kleen Cc: Mel Gorman Cc: Christoph Lameter Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7f693b272c4a..e70f21beb4b4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1465,5 +1465,7 @@ extern void shake_page(struct page *p, int access); extern atomic_long_t mce_bad_pages; extern int soft_offline_page(struct page *page, int flags); +extern void dump_page(struct page *page); + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3