From db1466b3e1bd1727375cdbfcbea4bcce2f860f61 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Mar 2010 07:46:56 -0800 Subject: rcu: Use wrapper function instead of exporting tasklist_lock Lockdep-RCU commit d11c563d exported tasklist_lock, which is not a good thing. This patch instead exports a function that uses lockdep to check whether tasklist_lock is held. Suggested-by: Christoph Hellwig Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: Christoph Hellwig LKML-Reference: <1267631219-8713-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/fork.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 17bbf093356d..8691c540a470 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -86,7 +86,14 @@ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ -EXPORT_SYMBOL_GPL(tasklist_lock); + +#ifdef CONFIG_PROVE_RCU +int lockdep_tasklist_lock_is_held(void) +{ + return lockdep_is_held(&tasklist_lock); +} +EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); +#endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { -- cgit v1.2.3 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 --- fs/proc/task_mmu.c | 4 +- include/linux/mm.h | 104 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 33 ++++++++++----- include/linux/sched.h | 54 ------------------------ kernel/fork.c | 3 +- kernel/tsacct.c | 1 + mm/filemap_xip.c | 2 +- mm/fremap.c | 2 +- mm/memory.c | 56 +++++++++++++++---------- mm/oom_kill.c | 4 +- mm/rmap.c | 10 ++--- mm/swapfile.c | 2 +- 12 files changed, 174 insertions(+), 101 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f277c4a111cb..375581276011 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -65,11 +65,11 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - *shared = get_mm_counter(mm, file_rss); + *shared = get_mm_counter(mm, MM_FILEPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; - *resident = *shared + get_mm_counter(mm, anon_rss); + *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); return mm->total_vm; } 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. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 36f96271306c..e1ca64be6678 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -24,12 +24,6 @@ struct address_space; #define USE_SPLIT_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#if USE_SPLIT_PTLOCKS -typedef atomic_long_t mm_counter_t; -#else /* !USE_SPLIT_PTLOCKS */ -typedef unsigned long mm_counter_t; -#endif /* !USE_SPLIT_PTLOCKS */ - /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -201,6 +195,22 @@ struct core_state { struct completion startup; }; +enum { + MM_FILEPAGES, + MM_ANONPAGES, + NR_MM_COUNTERS +}; + +#if USE_SPLIT_PTLOCKS +struct mm_rss_stat { + atomic_long_t count[NR_MM_COUNTERS]; +}; +#else /* !USE_SPLIT_PTLOCKS */ +struct mm_rss_stat { + unsigned long count[NR_MM_COUNTERS]; +}; +#endif /* !USE_SPLIT_PTLOCKS */ + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -227,11 +237,6 @@ struct mm_struct { * by mmlist_lock */ - /* Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - mm_counter_t _file_rss; - mm_counter_t _anon_rss; unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ @@ -244,6 +249,12 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + /* + * Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + struct mm_rss_stat rss_stat; + struct linux_binfmt *binfmt; cpumask_t cpu_vm_mask; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4b1753f7e48e..cbeafa49a53b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -396,60 +396,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} #endif -#if USE_SPLIT_PTLOCKS -/* - * The mm counters are not protected by its page_table_lock, - * so must be incremented atomically. - */ -#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value) -#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member)) -#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member) -#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member) -#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member) - -#else /* !USE_SPLIT_PTLOCKS */ -/* - * The mm counters are protected by its page_table_lock, - * so can be incremented directly. - */ -#define set_mm_counter(mm, member, value) (mm)->_##member = (value) -#define get_mm_counter(mm, member) ((mm)->_##member) -#define add_mm_counter(mm, member, value) (mm)->_##member += (value) -#define inc_mm_counter(mm, member) (mm)->_##member++ -#define dec_mm_counter(mm, member) (mm)->_##member-- - -#endif /* !USE_SPLIT_PTLOCKS */ - -#define get_mm_rss(mm) \ - (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss)) -#define update_hiwater_rss(mm) do { \ - unsigned long _rss = get_mm_rss(mm); \ - if ((mm)->hiwater_rss < _rss) \ - (mm)->hiwater_rss = _rss; \ -} while (0) -#define update_hiwater_vm(mm) do { \ - if ((mm)->hiwater_vm < (mm)->total_vm) \ - (mm)->hiwater_vm = (mm)->total_vm; \ -} while (0) - -static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) -{ - return max(mm->hiwater_rss, get_mm_rss(mm)); -} - -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; -} - -static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) -{ - return max(mm->hiwater_vm, mm->total_vm); -} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); diff --git a/kernel/fork.c b/kernel/fork.c index 17bbf093356d..7616bcf107b9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -455,8 +455,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; mm->nr_ptes = 0; - set_mm_counter(mm, file_rss, 0); - set_mm_counter(mm, anon_rss, 0); + memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 00d59d048edf..0a67e041edf8 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -21,6 +21,7 @@ #include #include #include +#include /* * fill in basic accounting fields diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 1888b2d71bb8..78b94f0b6d5d 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -194,7 +194,7 @@ retry: flush_cache_page(vma, address, pte_pfn(*pte)); pteval = ptep_clear_flush_notify(vma, address, pte); page_remove_rmap(page); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); BUG_ON(pte_dirty(pteval)); pte_unmap_unlock(pte, ptl); page_cache_release(page); diff --git a/mm/fremap.c b/mm/fremap.c index b6ec85abbb39..46f5dacf90a2 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -40,7 +40,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, page_remove_rmap(page); page_cache_release(page); update_hiwater_rss(mm); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); } } else { if (!pte_file(pte)) diff --git a/mm/memory.c b/mm/memory.c index 72fb5f39bccc..c57678478801 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -121,6 +121,7 @@ static int __init init_zero_pfn(void) } core_initcall(init_zero_pfn); + /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but @@ -376,12 +377,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) return 0; } -static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +static inline void init_rss_vec(int *rss) { - if (file_rss) - add_mm_counter(mm, file_rss, file_rss); - if (anon_rss) - add_mm_counter(mm, anon_rss, anon_rss); + memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); +} + +static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) + if (rss[i]) + add_mm_counter(mm, i, rss[i]); } /* @@ -632,7 +639,10 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (page) { get_page(page); page_dup_rmap(page); - rss[PageAnon(page)]++; + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; } out_set_pte: @@ -648,11 +658,12 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress = 0; - int rss[2]; + int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; again: - rss[1] = rss[0] = 0; + init_rss_vec(rss); + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; @@ -688,7 +699,7 @@ again: arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap_nested(orig_src_pte); - add_mm_rss(dst_mm, rss[0], rss[1]); + add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); @@ -816,8 +827,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, struct mm_struct *mm = tlb->mm; pte_t *pte; spinlock_t *ptl; - int file_rss = 0; - int anon_rss = 0; + int rss[NR_MM_COUNTERS]; + + init_rss_vec(rss); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); @@ -863,14 +875,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, set_pte_at(mm, addr, pte, pgoff_to_pte(page->index)); if (PageAnon(page)) - anon_rss--; + rss[MM_ANONPAGES]--; else { if (pte_dirty(ptent)) set_page_dirty(page); if (pte_young(ptent) && likely(!VM_SequentialReadHint(vma))) mark_page_accessed(page); - file_rss--; + rss[MM_FILEPAGES]--; } page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) @@ -893,7 +905,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); - add_mm_rss(mm, file_rss, anon_rss); + add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); @@ -1527,7 +1539,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter(mm, file_rss); + inc_mm_counter(mm, MM_FILEPAGES); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -2163,11 +2175,11 @@ gotten: if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter(mm, file_rss); - inc_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_FILEPAGES); + inc_mm_counter(mm, MM_ANONPAGES); } } else - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2604,7 +2616,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * discarded at swap_free(). */ - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); pte = mk_pte(page, vma->vm_page_prot); if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); @@ -2688,7 +2700,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_none(*page_table)) goto release; - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); setpte: set_pte_at(mm, address, page_table, entry); @@ -2842,10 +2854,10 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_WRITE) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (anon) { - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter(mm, file_rss); + inc_mm_counter(mm, MM_FILEPAGES); page_add_file_rmap(page); if (flags & FAULT_FLAG_WRITE) { dirty_page = page; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 237050478f28..35755a4156d6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -401,8 +401,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose) "vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(p), p->comm, K(p->mm->total_vm), - K(get_mm_counter(p->mm, anon_rss)), - K(get_mm_counter(p->mm, file_rss))); + K(get_mm_counter(p->mm, MM_ANONPAGES)), + K(get_mm_counter(p->mm, MM_FILEPAGES))); task_unlock(p); /* diff --git a/mm/rmap.c b/mm/rmap.c index 278cd277bdec..73d0472884c2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -815,9 +815,9 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { if (PageAnon(page)) - dec_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_ANONPAGES); else - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); } else if (PageAnon(page)) { @@ -839,7 +839,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } - dec_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_ANONPAGES); } else if (PAGE_MIGRATION) { /* * Store the pfn of the page in a special migration @@ -857,7 +857,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, entry = make_migration_entry(page, pte_write(pteval)); set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); } else - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); page_remove_rmap(page); page_cache_release(page); @@ -996,7 +996,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, page_remove_rmap(page); page_cache_release(page); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); (*mapcount)--; } pte_unmap_unlock(pte - 1, ptl); diff --git a/mm/swapfile.c b/mm/swapfile.c index 6c0585b16418..893984946a2c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -840,7 +840,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, goto out; } - inc_mm_counter(vma->vm_mm, anon_rss); + inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); -- 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 --- arch/ia64/kernel/perfmon.c | 1 + arch/ia64/mm/init.c | 2 + fs/exec.c | 6 +- include/linux/mm.h | 6 +- include/linux/mm_types.h | 3 +- include/linux/rmap.h | 35 ++++++++-- kernel/fork.c | 6 +- mm/ksm.c | 12 +++- mm/memory-failure.c | 5 +- mm/memory.c | 4 +- mm/mmap.c | 138 +++++++++++++++++++++++++++------------ mm/mremap.c | 7 +- mm/nommu.c | 2 +- mm/rmap.c | 156 +++++++++++++++++++++++++++++++++++++-------- 14 files changed, 298 insertions(+), 85 deletions(-) (limited to 'kernel/fork.c') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index b81e46b1629b..703062c44fb9 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2315,6 +2315,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("Cannot allocate vma\n")); goto error_kmem; } + INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index ca3335ea56cc..ed41759efcac 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -117,6 +117,7 @@ ia64_init_addr_space (void) */ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (vma) { + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; @@ -135,6 +136,7 @@ ia64_init_addr_space (void) if (!(current->personality & MMAP_PAGE_ZERO)) { vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (vma) { + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); diff --git a/fs/exec.c b/fs/exec.c index ea7861727efd..591030735591 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -246,6 +246,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) goto err; @@ -516,7 +517,8 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * cover the whole range: [new_start, old_end) */ - vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL); + if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) + return -ENOMEM; /* * move the page tables downwards, on failure we rely on @@ -547,7 +549,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) tlb_finish_mmu(tlb, new_end, old_end); /* - * shrink the vma to just the new range. + * Shrink the vma to just the new range. Always succeeds. */ vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); 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, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 19549d7275ab..048b46270aa5 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -163,7 +163,8 @@ struct vm_area_struct { * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ - struct list_head anon_vma_node; /* Serialized by anon_vma->lock */ + struct list_head anon_vma_chain; /* Serialized by mmap_sem & + * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b019ae64e2ab..62da2001d55c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -37,7 +37,27 @@ struct anon_vma { * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ - struct list_head head; /* List of private "related" vmas */ + struct list_head head; /* Chain of private "related" vmas */ +}; + +/* + * The copy-on-write semantics of fork mean that an anon_vma + * can become associated with multiple processes. Furthermore, + * each child process will have its own anon_vma, where new + * pages for that process are instantiated. + * + * This structure allows us to find the anon_vmas associated + * with a VMA, or the VMAs associated with an anon_vma. + * The "same_vma" list contains the anon_vma_chains linking + * all the anon_vmas associated with this VMA. + * The "same_anon_vma" list contains the anon_vma_chains + * which link all the VMAs associated with this anon_vma. + */ +struct anon_vma_chain { + struct vm_area_struct *vma; + struct anon_vma *anon_vma; + struct list_head same_vma; /* locked by mmap_sem & page_table_lock */ + struct list_head same_anon_vma; /* locked by anon_vma->lock */ }; #ifdef CONFIG_MMU @@ -89,12 +109,19 @@ static inline void anon_vma_unlock(struct vm_area_struct *vma) */ void anon_vma_init(void); /* create anon_vma_cachep */ int anon_vma_prepare(struct vm_area_struct *); -void __anon_vma_merge(struct vm_area_struct *, struct vm_area_struct *); -void anon_vma_unlink(struct vm_area_struct *); -void anon_vma_link(struct vm_area_struct *); +void unlink_anon_vmas(struct vm_area_struct *); +int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); +int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); void __anon_vma_link(struct vm_area_struct *); void anon_vma_free(struct anon_vma *); +static inline void anon_vma_merge(struct vm_area_struct *vma, + struct vm_area_struct *next) +{ + VM_BUG_ON(vma->anon_vma != next->anon_vma); + unlink_anon_vmas(next); +} + /* * rmap interfaces called when adding or removing pte of page */ diff --git a/kernel/fork.c b/kernel/fork.c index 7616bcf107b9..bab7b254ad39 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -329,15 +329,17 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (!tmp) goto fail_nomem; *tmp = *mpnt; + INIT_LIST_HEAD(&tmp->anon_vma_chain); pol = mpol_dup(vma_policy(mpnt)); retval = PTR_ERR(pol); if (IS_ERR(pol)) goto fail_nomem_policy; vma_set_policy(tmp, pol); + if (anon_vma_fork(tmp, mpnt)) + goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; tmp->vm_next = NULL; - anon_vma_link(tmp); file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; @@ -392,6 +394,8 @@ out: flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); return retval; +fail_nomem_anon_vma_fork: + mpol_put(pol); fail_nomem_policy: kmem_cache_free(vm_area_cachep, tmp); fail_nomem: diff --git a/mm/ksm.c b/mm/ksm.c index 56a0da1f9979..a93f1b7f508c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1563,10 +1563,12 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; @@ -1614,10 +1616,12 @@ int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; @@ -1664,10 +1668,12 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 17299fd4577c..d1f335162976 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -383,9 +383,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (av == NULL) /* Not actually mapped anymore */ goto out; for_each_process (tsk) { + struct anon_vma_chain *vmac; + if (!task_early_kill(tsk)) continue; - list_for_each_entry (vma, &av->head, anon_vma_node) { + list_for_each_entry(vmac, &av->head, same_anon_vma) { + vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == tsk->mm) diff --git a/mm/memory.c b/mm/memory.c index 77d9f840936b..dc785b438d70 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -374,7 +374,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { @@ -388,7 +388,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, diff --git a/mm/mmap.c b/mm/mmap.c index 31656147128e..6a0c15db7f60 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -437,7 +437,6 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); - __anon_vma_link(vma); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, @@ -499,7 +498,7 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -void vma_adjust(struct vm_area_struct *vma, unsigned long start, +int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { struct mm_struct *mm = vma->vm_mm; @@ -542,6 +541,28 @@ again: remove_next = 1 + (end > next->vm_end); } } + /* + * When changing only vma->vm_end, we don't really need anon_vma lock. + */ + if (vma->anon_vma && (insert || importer || start != vma->vm_start)) + anon_vma = vma->anon_vma; + if (anon_vma) { + /* + * Easily overlooked: when mprotect shifts the boundary, + * make sure the expanding vma has anon_vma set if the + * shrinking vma had, to cover any anon pages imported. + */ + if (importer && !importer->anon_vma) { + /* Block reverse map lookups until things are set up. */ + importer->vm_flags |= VM_LOCK_RMAP; + if (anon_vma_clone(importer, vma)) { + importer->vm_flags &= ~VM_LOCK_RMAP; + return -ENOMEM; + } + importer->anon_vma = anon_vma; + } + } + if (file) { mapping = file->f_mapping; if (!(vma->vm_flags & VM_NONLINEAR)) @@ -567,25 +588,6 @@ again: remove_next = 1 + (end > next->vm_end); } } - /* - * When changing only vma->vm_end, we don't really need - * anon_vma lock. - */ - if (vma->anon_vma && (insert || importer || start != vma->vm_start)) - anon_vma = vma->anon_vma; - if (anon_vma) { - spin_lock(&anon_vma->lock); - /* - * Easily overlooked: when mprotect shifts the boundary, - * make sure the expanding vma has anon_vma set if the - * shrinking vma had, to cover any anon pages imported. - */ - if (importer && !importer->anon_vma) { - importer->anon_vma = anon_vma; - __anon_vma_link(importer); - } - } - if (root) { flush_dcache_mmap_lock(mapping); vma_prio_tree_remove(vma, root); @@ -616,8 +618,11 @@ again: remove_next = 1 + (end > next->vm_end); __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); - if (next->anon_vma) - __anon_vma_merge(vma, next); + /* + * This VMA is now dead, no need for rmap to follow it. + * Call anon_vma_merge below, outside of i_mmap_lock. + */ + next->vm_flags |= VM_LOCK_RMAP; } else if (insert) { /* * split_vma has split insert from vma, and needs @@ -627,17 +632,25 @@ again: remove_next = 1 + (end > next->vm_end); __insert_vm_struct(mm, insert); } - if (anon_vma) - spin_unlock(&anon_vma->lock); if (mapping) spin_unlock(&mapping->i_mmap_lock); + /* + * The current VMA has been set up. It is now safe for the + * rmap code to get from the pages to the ptes. + */ + if (anon_vma && importer) + importer->vm_flags &= ~VM_LOCK_RMAP; + if (remove_next) { if (file) { fput(file); if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } + /* Protected by mmap_sem and VM_LOCK_RMAP. */ + if (next->anon_vma) + anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); kmem_cache_free(vm_area_cachep, next); @@ -653,6 +666,8 @@ again: remove_next = 1 + (end > next->vm_end); } validate_mm(mm); + + return 0; } /* @@ -759,6 +774,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; + int err; /* * We later require that vma->vm_flags == vm_flags, @@ -792,11 +808,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma)) { /* cases 1, 6 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL); + if (err) + return NULL; return prev; } @@ -808,11 +826,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen)) { if (prev && addr < prev->vm_end) /* case 4 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ - vma_adjust(area, addr, next->vm_end, + err = vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL); + if (err) + return NULL; return area; } @@ -1205,6 +1225,7 @@ munmap_back: vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; + INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { error = -EINVAL; @@ -1865,6 +1886,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, { struct mempolicy *pol; struct vm_area_struct *new; + int err = -ENOMEM; if (is_vm_hugetlb_page(vma) && (addr & ~(huge_page_mask(hstate_vma(vma))))) @@ -1872,11 +1894,13 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) - return -ENOMEM; + goto out_err; /* most fields are the same, copy all, and then fixup */ *new = *vma; + INIT_LIST_HEAD(&new->anon_vma_chain); + if (new_below) new->vm_end = addr; else { @@ -1886,11 +1910,14 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, pol = mpol_dup(vma_policy(vma)); if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new); - return PTR_ERR(pol); + err = PTR_ERR(pol); + goto out_free_vma; } vma_set_policy(new, pol); + if (anon_vma_clone(new, vma)) + goto out_free_mpol; + if (new->vm_file) { get_file(new->vm_file); if (vma->vm_flags & VM_EXECUTABLE) @@ -1901,12 +1928,28 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_ops->open(new); if (new_below) - vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + + err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else - vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); + err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); - return 0; + /* Success. */ + if (!err) + return 0; + + /* Clean everything up if vma_adjust failed. */ + new->vm_ops->close(new); + if (new->vm_file) { + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + fput(new->vm_file); + } + out_free_mpol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new); + out_err: + return err; } /* @@ -2116,6 +2159,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) return -ENOMEM; } + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2252,10 +2296,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma) { *new_vma = *vma; pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new_vma); - return NULL; - } + if (IS_ERR(pol)) + goto out_free_vma; + INIT_LIST_HEAD(&new_vma->anon_vma_chain); + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; @@ -2271,6 +2316,12 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } } return new_vma; + + out_free_mempol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new_vma); + return NULL; } /* @@ -2348,6 +2399,7 @@ int install_special_mapping(struct mm_struct *mm, if (unlikely(vma == NULL)) return -ENOMEM; + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2448,6 +2500,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = -EINTR; BUG_ON(down_read_trylock(&mm->mmap_sem)); @@ -2465,7 +2518,8 @@ int mm_take_all_locks(struct mm_struct *mm) if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) - vm_lock_anon_vma(mm, vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); } ret = 0; @@ -2520,13 +2574,15 @@ static void vm_unlock_mapping(struct address_space *mapping) void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; BUG_ON(down_read_trylock(&mm->mmap_sem)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) - vm_unlock_anon_vma(vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } diff --git a/mm/mremap.c b/mm/mremap.c index 4c4c803453f3..e9c75efce609 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -460,8 +460,11 @@ unsigned long do_mremap(unsigned long addr, if (vma_expandable(vma, new_len - old_len)) { int pages = (new_len - old_len) >> PAGE_SHIFT; - vma_adjust(vma, vma->vm_start, - addr + new_len, vma->vm_pgoff, NULL); + if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + ret = -ENOMEM; + goto out; + } mm->total_vm += pages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); diff --git a/mm/nommu.c b/mm/nommu.c index 48a2ecfaf059..55727a74af98 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1209,7 +1209,7 @@ unsigned long do_mmap_pgoff(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_node); + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; diff --git a/mm/rmap.c b/mm/rmap.c index 5cb47111f79e..be34094e4595 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -62,6 +62,7 @@ #include "internal.h" static struct kmem_cache *anon_vma_cachep; +static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { @@ -73,6 +74,16 @@ void anon_vma_free(struct anon_vma *anon_vma) kmem_cache_free(anon_vma_cachep, anon_vma); } +static inline struct anon_vma_chain *anon_vma_chain_alloc(void) +{ + return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL); +} + +void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) +{ + kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); +} + /** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question @@ -103,18 +114,23 @@ void anon_vma_free(struct anon_vma *anon_vma) int anon_vma_prepare(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; might_sleep(); if (unlikely(!anon_vma)) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *allocated; + avc = anon_vma_chain_alloc(); + if (!avc) + goto out_enomem; + anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) - return -ENOMEM; + goto out_enomem_free_avc; allocated = anon_vma; } spin_lock(&anon_vma->lock); @@ -123,53 +139,113 @@ int anon_vma_prepare(struct vm_area_struct *vma) spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; - list_add_tail(&vma->anon_vma_node, &anon_vma->head); + avc->anon_vma = anon_vma; + avc->vma = vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + list_add(&avc->same_anon_vma, &anon_vma->head); allocated = NULL; } spin_unlock(&mm->page_table_lock); spin_unlock(&anon_vma->lock); - if (unlikely(allocated)) + if (unlikely(allocated)) { anon_vma_free(allocated); + anon_vma_chain_free(avc); + } } return 0; + + out_enomem_free_avc: + anon_vma_chain_free(avc); + out_enomem: + return -ENOMEM; } -void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) +static void anon_vma_chain_link(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) { - BUG_ON(vma->anon_vma != next->anon_vma); - list_del(&next->anon_vma_node); + avc->vma = vma; + avc->anon_vma = anon_vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + + spin_lock(&anon_vma->lock); + list_add_tail(&avc->same_anon_vma, &anon_vma->head); + spin_unlock(&anon_vma->lock); } -void __anon_vma_link(struct vm_area_struct *vma) +/* + * Attach the anon_vmas from src to dst. + * Returns 0 on success, -ENOMEM on failure. + */ +int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc, *pavc; + + list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { + avc = anon_vma_chain_alloc(); + if (!avc) + goto enomem_failure; + anon_vma_chain_link(dst, avc, pavc->anon_vma); + } + return 0; - if (anon_vma) - list_add_tail(&vma->anon_vma_node, &anon_vma->head); + enomem_failure: + unlink_anon_vmas(dst); + return -ENOMEM; } -void anon_vma_link(struct vm_area_struct *vma) +/* + * Attach vma to its own anon_vma, as well as to the anon_vmas that + * the corresponding VMA in the parent process is attached to. + * Returns 0 on success, non-zero on failure. + */ +int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; + struct anon_vma *anon_vma; - if (anon_vma) { - spin_lock(&anon_vma->lock); - list_add_tail(&vma->anon_vma_node, &anon_vma->head); - spin_unlock(&anon_vma->lock); - } + /* Don't bother if the parent process has no anon_vma here. */ + if (!pvma->anon_vma) + return 0; + + /* + * First, attach the new VMA to the parent VMA's anon_vmas, + * so rmap can find non-COWed pages in child processes. + */ + if (anon_vma_clone(vma, pvma)) + return -ENOMEM; + + /* Then add our own anon_vma. */ + anon_vma = anon_vma_alloc(); + if (!anon_vma) + goto out_error; + avc = anon_vma_chain_alloc(); + if (!avc) + goto out_error_free_anon_vma; + anon_vma_chain_link(vma, avc, anon_vma); + /* Mark this anon_vma as the one where our new (COWed) pages go. */ + vma->anon_vma = anon_vma; + + return 0; + + out_error_free_anon_vma: + anon_vma_free(anon_vma); + out_error: + return -ENOMEM; } -void anon_vma_unlink(struct vm_area_struct *vma) +static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma *anon_vma = anon_vma_chain->anon_vma; int empty; + /* If anon_vma_fork fails, we can get an empty anon_vma_chain. */ if (!anon_vma) return; spin_lock(&anon_vma->lock); - list_del(&vma->anon_vma_node); + list_del(&anon_vma_chain->same_anon_vma); /* We must garbage collect the anon_vma if it's empty */ empty = list_empty(&anon_vma->head) && !ksm_refcount(anon_vma); @@ -179,6 +255,18 @@ void anon_vma_unlink(struct vm_area_struct *vma) anon_vma_free(anon_vma); } +void unlink_anon_vmas(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc, *next; + + /* Unlink each anon_vma chained to the VMA. */ + list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { + anon_vma_unlink(avc); + list_del(&avc->same_vma); + anon_vma_chain_free(avc); + } +} + static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; @@ -192,6 +280,7 @@ void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor); + anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); } /* @@ -240,6 +329,18 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* page should be within @vma mapping range */ return -EFAULT; } + if (unlikely(vma->vm_flags & VM_LOCK_RMAP)) { + /* + * This VMA is being unlinked or is not yet linked into the + * VMA tree. Do not try to follow this rmap. This race + * condition can result in page_referenced() ignoring a + * reference or in try_to_unmap() failing to unmap a page. + * The VMA cannot be freed under us because we hold the + * anon_vma->lock, which the munmap code takes while + * unlinking the anon_vmas from the VMA. + */ + return -EFAULT; + } return address; } @@ -396,7 +497,7 @@ static int page_referenced_anon(struct page *page, { unsigned int mapcount; struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int referenced = 0; anon_vma = page_lock_anon_vma(page); @@ -404,7 +505,8 @@ static int page_referenced_anon(struct page *page, return referenced; mapcount = page_mapcount(page); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -1025,14 +1127,15 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) { struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = SWAP_AGAIN; anon_vma = page_lock_anon_vma(page); if (!anon_vma) return ret; - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -1223,7 +1326,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = SWAP_AGAIN; /* @@ -1238,7 +1341,8 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, if (!anon_vma) return ret; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; -- cgit v1.2.3 From 78d7d407b62a021e6d2e8dc24c0b90e390ab58a1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 5 Mar 2010 13:42:54 -0800 Subject: kernel core: use helpers for rlimits Make sure compiler won't do weird things with limits. E.g. fetching them twice may return 2 different values after writable limits are implemented. I.e. either use rlimit helpers added in commit 3e10e716abf3 ("resource: add helpers for fetching rlimits") or ACCESS_ONCE if not applicable. Signed-off-by: Jiri Slaby Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 ++++++---- kernel/perf_event.c | 2 +- kernel/posix-cpu-timers.c | 10 ++++++---- kernel/sched.c | 4 ++-- kernel/sched_rt.c | 5 +++-- kernel/signal.c | 2 +- kernel/sys.c | 3 +-- 7 files changed, 20 insertions(+), 16 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index bab7b254ad39..b0ec34abc0bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -828,6 +828,8 @@ void __cleanup_sighand(struct sighand_struct *sighand) */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { + unsigned long cpu_limit; + /* Thread group counters. */ thread_group_cputime_init(sig); @@ -842,9 +844,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) sig->cputime_expires.virt_exp = cputime_zero; sig->cputime_expires.sched_exp = 0; - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - sig->cputime_expires.prof_exp = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); + cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + if (cpu_limit != RLIM_INFINITY) { + sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); sig->cputimer.running = 1; } @@ -1037,7 +1039,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif retval = -EAGAIN; if (atomic_read(&p->real_cred->user->processes) >= - p->signal->rlim[RLIMIT_NPROC].rlim_cur) { + task_rlimit(p, RLIMIT_NPROC)) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->real_cred->user != INIT_USER) goto bad_fork_free; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a661e7991865..8e352c756ba7 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2610,7 +2610,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (user_locked > user_lock_limit) extra = user_locked - user_lock_limit; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = vma->vm_mm->locked_vm + extra; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index dbb16bf15c45..1a22dfd42df9 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1031,9 +1031,10 @@ static void check_thread_timers(struct task_struct *tsk, /* * Check for the special case thread timers. */ - soft = sig->rlim[RLIMIT_RTTIME].rlim_cur; + soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); if (soft != RLIM_INFINITY) { - unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max; + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); if (hard != RLIM_INFINITY && tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { @@ -1194,10 +1195,11 @@ static void check_process_timers(struct task_struct *tsk, SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, SIGVTALRM); - soft = sig->rlim[RLIMIT_CPU].rlim_cur; + soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (soft != RLIM_INFINITY) { unsigned long psecs = cputime_to_secs(ptime); - unsigned long hard = sig->rlim[RLIMIT_CPU].rlim_max; + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); cputime_t x; if (psecs >= hard) { /* diff --git a/kernel/sched.c b/kernel/sched.c index abb36b16b93b..b47ceeec1a91 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4353,7 +4353,7 @@ int can_nice(const struct task_struct *p, const int nice) /* convert nice value [19,-20] to rlimit style value [1,40] */ int nice_rlim = 20 - nice; - return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); } @@ -4530,7 +4530,7 @@ recheck: if (!lock_task_sighand(p, &flags)) return -ESRCH; - rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; + rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); unlock_task_sighand(p, &flags); /* can't set/change the rt policy */ diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index bf3e38fdbe6d..5a6ed1f0990a 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1662,8 +1662,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) if (!p->signal) return; - soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur; - hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max; + /* max may change after cur was read, this will be fixed next tick */ + soft = task_rlimit(p, RLIMIT_RTTIME); + hard = task_rlimit_max(p, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { unsigned long next; diff --git a/kernel/signal.c b/kernel/signal.c index 5bb9baffa4f1..dbd7fe073c55 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -245,7 +245,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi if (override_rlimit || atomic_read(&user->sigpending) <= - t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) { + task_rlimit(t, RLIMIT_SIGPENDING)) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); diff --git a/kernel/sys.c b/kernel/sys.c index 877fe4f8e05e..9814e43fb23b 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -571,8 +571,7 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; - if (atomic_read(&new_user->processes) >= - current->signal->rlim[RLIMIT_NPROC].rlim_cur && + if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && new_user != INIT_USER) { free_uid(new_user); return -EAGAIN; -- cgit v1.2.3 From a56704ef6b0c5796c9ff38cc78aa232dfb9644d7 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 10 Mar 2010 15:23:01 -0800 Subject: copy_signal() cleanup: use zalloc and remove initializations Use kmem_cache_zalloc() on signal creation and remove unneeded initialization lines in copy_signal(). Signed-off-by: Veaceslav Falico Acked-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index b0ec34abc0bb..ce2666f84d85 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -863,7 +863,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_THREAD) return 0; - sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); + sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; @@ -871,46 +871,21 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) atomic_set(&sig->count, 1); atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); - sig->flags = 0; if (clone_flags & CLONE_NEWPID) sig->flags |= SIGNAL_UNKILLABLE; - sig->group_exit_code = 0; - sig->group_exit_task = NULL; - sig->group_stop_count = 0; sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->leader = 0; /* session leadership doesn't inherit */ - sig->tty_old_pgrp = NULL; - sig->tty = NULL; - - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; - sig->gtime = cputime_zero; - sig->cgtime = cputime_zero; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - sig->prev_utime = sig->prev_stime = cputime_zero; -#endif - 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; - sig->maxrss = sig->cmaxrss = 0; - task_io_accounting_init(&sig->ioac); - sig->sum_sched_runtime = 0; - taskstats_tgid_init(sig); - task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); - acct_init_pacct(&sig->pacct); - tty_audit_fork(sig); sig->oom_adj = current->signal->oom_adj; -- cgit v1.2.3 From 93c59907c6f247d09239135caecf294a106a2ae0 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 10 Mar 2010 15:23:03 -0800 Subject: copy_signal() cleanup: clean thread_group_cputime_init() Remove unneeded initializations in thread_group_cputime_init() and in posix_cpu_timers_init_group(). They are useless after kmem_cache_zalloc() was used in copy_signal(). Signed-off-by: Veaceslav Falico Acked-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 -- kernel/fork.c | 11 ----------- 2 files changed, 13 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 46c6f8d5dc06..ca635c128482 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2391,9 +2391,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); static inline void thread_group_cputime_init(struct signal_struct *sig) { - sig->cputimer.cputime = INIT_CPUTIME; spin_lock_init(&sig->cputimer.lock); - sig->cputimer.running = 0; } static inline void thread_group_cputime_free(struct signal_struct *sig) diff --git a/kernel/fork.c b/kernel/fork.c index ce2666f84d85..1beb6c303c41 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -833,17 +833,6 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) /* Thread group counters. */ thread_group_cputime_init(sig); - /* Expiration times and increments. */ - sig->it[CPUCLOCK_PROF].expires = cputime_zero; - sig->it[CPUCLOCK_PROF].incr = cputime_zero; - sig->it[CPUCLOCK_VIRT].expires = cputime_zero; - sig->it[CPUCLOCK_VIRT].incr = cputime_zero; - - /* Cached expiration times. */ - sig->cputime_expires.prof_exp = cputime_zero; - sig->cputime_expires.virt_exp = cputime_zero; - sig->cputime_expires.sched_exp = 0; - cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (cpu_limit != RLIM_INFINITY) { sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); -- cgit v1.2.3