diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/hugetlb.c | 2 | ||||
| -rw-r--r-- | mm/kmemleak.c | 7 | ||||
| -rw-r--r-- | mm/page_alloc.c | 60 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 2 | ||||
| -rw-r--r-- | mm/prio_tree.c | 1 | ||||
| -rw-r--r-- | mm/shmem.c | 148 | ||||
| -rw-r--r-- | mm/slab.c | 1 | ||||
| -rw-r--r-- | mm/slub.c | 165 | ||||
| -rw-r--r-- | mm/swap.c | 3 | ||||
| -rw-r--r-- | mm/vmscan.c | 3 |
10 files changed, 206 insertions, 186 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8ee3bd8ec5b5..bbb4a5bbb958 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -475,7 +475,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) - goto err;; + goto err; for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { diff --git a/mm/kmemleak.c b/mm/kmemleak.c index c1d5867543e4..aacee45616fc 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1414,9 +1414,12 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++(*pos); list_for_each_continue_rcu(n, &object_list) { - next_obj = list_entry(n, struct kmemleak_object, object_list); - if (get_object(next_obj)) + struct kmemleak_object *obj = + list_entry(n, struct kmemleak_object, object_list); + if (get_object(obj)) { + next_obj = obj; break; + } } put_object(prev_obj); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9f8a97b9a350..9d5498e2d0f5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include <trace/events/kmem.h> #include <linux/ftrace_event.h> #include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -2317,6 +2318,21 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); +static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +{ + if (addr) { + unsigned long alloc_end = addr + (PAGE_SIZE << order); + unsigned long used = addr + PAGE_ALIGN(size); + + split_page(virt_to_page((void *)addr), order); + while (used < alloc_end) { + free_page(used); + used += PAGE_SIZE; + } + } + return (void *)addr; +} + /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate @@ -2336,22 +2352,33 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned long addr; addr = __get_free_pages(gfp_mask, order); - if (addr) { - unsigned long alloc_end = addr + (PAGE_SIZE << order); - unsigned long used = addr + PAGE_ALIGN(size); - - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } - - return (void *)addr; + return make_alloc_exact(addr, order, size); } EXPORT_SYMBOL(alloc_pages_exact); /** + * alloc_pages_exact_nid - allocate an exact number of physically-contiguous + * pages on a node. + * @nid: the preferred node ID where memory should be allocated + * @size: the number of bytes to allocate + * @gfp_mask: GFP flags for the allocation + * + * Like alloc_pages_exact(), but try to allocate on node nid first before falling + * back. + * Note this is not alloc_pages_exact_node() which allocates on a specific node, + * but is not exact. + */ +void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +{ + unsigned order = get_order(size); + struct page *p = alloc_pages_node(nid, gfp_mask, order); + if (!p) + return NULL; + return make_alloc_exact((unsigned long)page_address(p), order, size); +} +EXPORT_SYMBOL(alloc_pages_exact_nid); + +/** * free_pages_exact - release memory allocated via alloc_pages_exact() * @virt: the value returned by alloc_pages_exact. * @size: size of allocation, same value as passed to alloc_pages_exact(). @@ -3514,7 +3541,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p, pcp->batch = PAGE_SHIFT * 8; } -static __meminit void setup_zone_pageset(struct zone *zone) +static void setup_zone_pageset(struct zone *zone) { int cpu; @@ -3564,7 +3591,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, alloc_size); + alloc_bootmem_node_nopanic(pgdat, alloc_size); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -4141,7 +4168,8 @@ static void __init setup_usemap(struct pglist_data *pgdat, unsigned long usemapsize = usemap_size(zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); + zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, + usemapsize); } #else static inline void setup_usemap(struct pglist_data *pgdat, @@ -4307,7 +4335,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node(pgdat, size); + map = alloc_bootmem_node_nopanic(pgdat, size); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 99055010cece..2daadc322ba6 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -134,7 +134,7 @@ static void *__init_refok alloc_page_cgroup(size_t size, int nid) { void *addr = NULL; - addr = alloc_pages_exact(size, GFP_KERNEL | __GFP_NOWARN); + addr = alloc_pages_exact_nid(nid, size, GFP_KERNEL | __GFP_NOWARN); if (addr) return addr; diff --git a/mm/prio_tree.c b/mm/prio_tree.c index 603ae98d9694..799dcfd7cd8c 100644 --- a/mm/prio_tree.c +++ b/mm/prio_tree.c @@ -13,6 +13,7 @@ #include <linux/mm.h> #include <linux/prio_tree.h> +#include <linux/prefetch.h> /* * See lib/prio_tree.c for details on the general radix priority search tree diff --git a/mm/shmem.c b/mm/shmem.c index 8fa27e4e582a..ba4ad28b7db6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -852,7 +852,7 @@ static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) { - struct inode *inode; + struct address_space *mapping; unsigned long idx; unsigned long size; unsigned long limit; @@ -875,8 +875,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) + if (offset >= 0) { + shmem_swp_balance_unmap(); goto found; + } if (!info->i_indirect) goto lost2; @@ -917,6 +919,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s shmem_swp_unmap(ptr); if (offset >= 0) { shmem_dir_unmap(dir); + ptr = shmem_swp_map(subdir); goto found; } } @@ -928,8 +931,7 @@ lost2: return 0; found: idx += offset; - inode = igrab(&info->vfs_inode); - spin_unlock(&info->lock); + ptr += offset; /* * Move _head_ to start search for next from here. @@ -940,37 +942,18 @@ found: */ if (shmem_swaplist.next != &info->swaplist) list_move_tail(&shmem_swaplist, &info->swaplist); - mutex_unlock(&shmem_swaplist_mutex); - error = 1; - if (!inode) - goto out; /* - * Charge page using GFP_KERNEL while we can wait. - * Charged back to the user(not to caller) when swap account is used. - * add_to_page_cache() will be called with GFP_NOWAIT. + * We rely on shmem_swaplist_mutex, not only to protect the swaplist, + * but also to hold up shmem_evict_inode(): so inode cannot be freed + * beneath us (pagelock doesn't help until the page is in pagecache). */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); - if (error) - goto out; - error = radix_tree_preload(GFP_KERNEL); - if (error) { - mem_cgroup_uncharge_cache_page(page); - goto out; - } - error = 1; - - spin_lock(&info->lock); - ptr = shmem_swp_entry(info, idx, NULL); - if (ptr && ptr->val == entry.val) { - error = add_to_page_cache_locked(page, inode->i_mapping, - idx, GFP_NOWAIT); - /* does mem_cgroup_uncharge_cache_page on error */ - } else /* we must compensate for our precharge above */ - mem_cgroup_uncharge_cache_page(page); + mapping = info->vfs_inode.i_mapping; + error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); + /* which does mem_cgroup_uncharge_cache_page on error */ if (error == -EEXIST) { - struct page *filepage = find_get_page(inode->i_mapping, idx); + struct page *filepage = find_get_page(mapping, idx); error = 1; if (filepage) { /* @@ -990,14 +973,8 @@ found: swap_free(entry); error = 1; /* not an error, but entry was found */ } - if (ptr) - shmem_swp_unmap(ptr); + shmem_swp_unmap(ptr); spin_unlock(&info->lock); - radix_tree_preload_end(); -out: - unlock_page(page); - page_cache_release(page); - iput(inode); /* allows for NULL */ return error; } @@ -1009,6 +986,26 @@ int shmem_unuse(swp_entry_t entry, struct page *page) struct list_head *p, *next; struct shmem_inode_info *info; int found = 0; + int error; + + /* + * Charge page using GFP_KERNEL while we can wait, before taking + * the shmem_swaplist_mutex which might hold up shmem_writepage(). + * Charged back to the user (not to caller) when swap account is used. + * add_to_page_cache() will be called with GFP_NOWAIT. + */ + error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + if (error) + goto out; + /* + * Try to preload while we can wait, to not make a habit of + * draining atomic reserves; but don't latch on to this cpu, + * it's okay if sometimes we get rescheduled after this. + */ + error = radix_tree_preload(GFP_KERNEL); + if (error) + goto uncharge; + radix_tree_preload_end(); mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(p, next, &shmem_swaplist) { @@ -1016,17 +1013,19 @@ int shmem_unuse(swp_entry_t entry, struct page *page) found = shmem_unuse_inode(info, entry, page); cond_resched(); if (found) - goto out; + break; } mutex_unlock(&shmem_swaplist_mutex); - /* - * Can some race bring us here? We've been holding page lock, - * so I think not; but would rather try again later than BUG() - */ + +uncharge: + if (!found) + mem_cgroup_uncharge_cache_page(page); + if (found < 0) + error = found; +out: unlock_page(page); page_cache_release(page); -out: - return (found < 0) ? found : 0; + return error; } /* @@ -1064,7 +1063,25 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) else swap.val = 0; + /* + * Add inode to shmem_unuse()'s list of swapped-out inodes, + * if it's not already there. Do it now because we cannot take + * mutex while holding spinlock, and must do so before the page + * is moved to swap cache, when its pagelock no longer protects + * the inode from eviction. But don't unlock the mutex until + * we've taken the spinlock, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under both locks. + */ + if (swap.val) { + mutex_lock(&shmem_swaplist_mutex); + if (list_empty(&info->swaplist)) + list_add_tail(&info->swaplist, &shmem_swaplist); + } + spin_lock(&info->lock); + if (swap.val) + mutex_unlock(&shmem_swaplist_mutex); + if (index >= info->next_index) { BUG_ON(!(info->flags & SHMEM_TRUNCATE)); goto unlock; @@ -1084,21 +1101,10 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) delete_from_page_cache(page); shmem_swp_set(info, entry, swap.val); shmem_swp_unmap(entry); - if (list_empty(&info->swaplist)) - inode = igrab(inode); - else - inode = NULL; spin_unlock(&info->lock); swap_shmem_alloc(swap); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); - if (inode) { - mutex_lock(&shmem_swaplist_mutex); - /* move instead of add in case we're racing */ - list_move_tail(&info->swaplist, &shmem_swaplist); - mutex_unlock(&shmem_swaplist_mutex); - iput(inode); - } return 0; } @@ -1400,20 +1406,14 @@ repeat: if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks) >= 0 || - shmem_acct_block(info->flags)) { - spin_unlock(&info->lock); - error = -ENOSPC; - goto failed; - } + shmem_acct_block(info->flags)) + goto nospace; percpu_counter_inc(&sbinfo->used_blocks); spin_lock(&inode->i_lock); inode->i_blocks += BLOCKS_PER_PAGE; spin_unlock(&inode->i_lock); - } else if (shmem_acct_block(info->flags)) { - spin_unlock(&info->lock); - error = -ENOSPC; - goto failed; - } + } else if (shmem_acct_block(info->flags)) + goto nospace; if (!filepage) { int ret; @@ -1493,6 +1493,24 @@ done: error = 0; goto out; +nospace: + /* + * Perhaps the page was brought in from swap between find_lock_page + * and taking info->lock? We allow for that at add_to_page_cache_lru, + * but must also avoid reporting a spurious ENOSPC while working on a + * full tmpfs. (When filepage has been passed in to shmem_getpage, it + * is already in page cache, which prevents this race from occurring.) + */ + if (!filepage) { + struct page *page = find_get_page(mapping, idx); + if (page) { + spin_unlock(&info->lock); + page_cache_release(page); + goto repeat; + } + } + spin_unlock(&info->lock); + error = -ENOSPC; failed: if (*pagep != filepage) { unlock_page(filepage); diff --git a/mm/slab.c b/mm/slab.c index 46a9c163a92f..bcfa4987c8ae 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -115,6 +115,7 @@ #include <linux/debugobjects.h> #include <linux/kmemcheck.h> #include <linux/memory.h> +#include <linux/prefetch.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> diff --git a/mm/slub.c b/mm/slub.c index 9d2e5e46bf09..4ea7f1a22a94 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -261,6 +261,18 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object) return *(void **)(object + s->offset); } +static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) +{ + void *p; + +#ifdef CONFIG_DEBUG_PAGEALLOC + probe_kernel_read(&p, (void **)(object + s->offset), sizeof(p)); +#else + p = get_freepointer(s, object); +#endif + return p; +} + static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) { *(void **)(object + s->offset) = fp; @@ -271,10 +283,6 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\ __p += (__s)->size) -/* Scan freelist */ -#define for_each_free_object(__p, __s, __free) \ - for (__p = (__free); __p; __p = get_freepointer((__s), __p)) - /* Determine object index from a given position */ static inline int slab_index(void *p, struct kmem_cache *s, void *addr) { @@ -332,6 +340,21 @@ static inline int oo_objects(struct kmem_cache_order_objects x) #ifdef CONFIG_SLUB_DEBUG /* + * Determine a map of object in use on a page. + * + * Slab lock or node listlock must be held to guarantee that the page does + * not vanish from under us. + */ +static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map) +{ + void *p; + void *addr = page_address(page); + + for (p = page->freelist; p; p = get_freepointer(s, p)) + set_bit(slab_index(p, s, addr), map); +} + +/* * Debug settings: */ #ifdef CONFIG_SLUB_DEBUG_ON @@ -1487,7 +1510,7 @@ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; page = get_partial_node(get_node(s, searchnode)); - if (page || node != -1) + if (page || node != NUMA_NO_NODE) return page; return get_any_partial(s, flags); @@ -1540,7 +1563,6 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) } } -#ifdef CONFIG_CMPXCHG_LOCAL #ifdef CONFIG_PREEMPT /* * Calculate the next globally unique transaction for disambiguiation @@ -1600,17 +1622,12 @@ static inline void note_cmpxchg_failure(const char *n, stat(s, CMPXCHG_DOUBLE_CPU_FAIL); } -#endif - void init_kmem_cache_cpus(struct kmem_cache *s) { -#ifdef CONFIG_CMPXCHG_LOCAL int cpu; for_each_possible_cpu(cpu) per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); -#endif - } /* * Remove the cpu slab @@ -1643,9 +1660,7 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) page->inuse--; } c->page = NULL; -#ifdef CONFIG_CMPXCHG_LOCAL c->tid = next_tid(c->tid); -#endif unfreeze_slab(s, page, tail); } @@ -1779,8 +1794,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void **object; - struct page *new; -#ifdef CONFIG_CMPXCHG_LOCAL + struct page *page; unsigned long flags; local_irq_save(flags); @@ -1792,37 +1806,35 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, */ c = this_cpu_ptr(s->cpu_slab); #endif -#endif /* We handle __GFP_ZERO in the caller */ gfpflags &= ~__GFP_ZERO; - if (!c->page) + page = c->page; + if (!page) goto new_slab; - slab_lock(c->page); + slab_lock(page); if (unlikely(!node_match(c, node))) goto another_slab; stat(s, ALLOC_REFILL); load_freelist: - object = c->page->freelist; + object = page->freelist; if (unlikely(!object)) goto another_slab; if (kmem_cache_debug(s)) goto debug; c->freelist = get_freepointer(s, object); - c->page->inuse = c->page->objects; - c->page->freelist = NULL; - c->node = page_to_nid(c->page); + page->inuse = page->objects; + page->freelist = NULL; + unlock_out: - slab_unlock(c->page); -#ifdef CONFIG_CMPXCHG_LOCAL + slab_unlock(page); c->tid = next_tid(c->tid); local_irq_restore(flags); -#endif stat(s, ALLOC_SLOWPATH); return object; @@ -1830,10 +1842,11 @@ another_slab: deactivate_slab(s, c); new_slab: - new = get_partial(s, gfpflags, node); - if (new) { - c->page = new; + page = get_partial(s, gfpflags, node); + if (page) { stat(s, ALLOC_FROM_PARTIAL); + c->node = page_to_nid(page); + c->page = page; goto load_freelist; } @@ -1841,33 +1854,35 @@ new_slab: if (gfpflags & __GFP_WAIT) local_irq_enable(); - new = new_slab(s, gfpflags, node); + page = new_slab(s, gfpflags, node); if (gfpflags & __GFP_WAIT) local_irq_disable(); - if (new) { + if (page) { c = __this_cpu_ptr(s->cpu_slab); stat(s, ALLOC_SLAB); if (c->page) flush_slab(s, c); - slab_lock(new); - __SetPageSlubFrozen(new); - c->page = new; + + slab_lock(page); + __SetPageSlubFrozen(page); + c->node = page_to_nid(page); + c->page = page; goto load_freelist; } if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) slab_out_of_memory(s, gfpflags, node); -#ifdef CONFIG_CMPXCHG_LOCAL local_irq_restore(flags); -#endif return NULL; debug: - if (!alloc_debug_processing(s, c->page, object, addr)) + if (!alloc_debug_processing(s, page, object, addr)) goto another_slab; - c->page->inuse++; - c->page->freelist = get_freepointer(s, object); + page->inuse++; + page->freelist = get_freepointer(s, object); + deactivate_slab(s, c); + c->page = NULL; c->node = NUMA_NO_NODE; goto unlock_out; } @@ -1887,20 +1902,12 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, { void **object; struct kmem_cache_cpu *c; -#ifdef CONFIG_CMPXCHG_LOCAL unsigned long tid; -#else - unsigned long flags; -#endif if (slab_pre_alloc_hook(s, gfpflags)) return NULL; -#ifndef CONFIG_CMPXCHG_LOCAL - local_irq_save(flags); -#else redo: -#endif /* * Must read kmem_cache cpu data via this cpu ptr. Preemption is @@ -1910,7 +1917,6 @@ redo: */ c = __this_cpu_ptr(s->cpu_slab); -#ifdef CONFIG_CMPXCHG_LOCAL /* * The transaction ids are globally unique per cpu and per operation on * a per cpu queue. Thus they can be guarantee that the cmpxchg_double @@ -1919,7 +1925,6 @@ redo: */ tid = c->tid; barrier(); -#endif object = c->freelist; if (unlikely(!object || !node_match(c, node))) @@ -1927,7 +1932,6 @@ redo: object = __slab_alloc(s, gfpflags, node, addr, c); else { -#ifdef CONFIG_CMPXCHG_LOCAL /* * The cmpxchg will only match if there was no additional * operation and if we are on the right processor. @@ -1943,21 +1947,14 @@ redo: if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, object, tid, - get_freepointer(s, object), next_tid(tid)))) { + get_freepointer_safe(s, object), next_tid(tid)))) { note_cmpxchg_failure("slab_alloc", s, tid); goto redo; } -#else - c->freelist = get_freepointer(s, object); -#endif stat(s, ALLOC_FASTPATH); } -#ifndef CONFIG_CMPXCHG_LOCAL - local_irq_restore(flags); -#endif - if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, s->objsize); @@ -2034,18 +2031,15 @@ static void __slab_free(struct kmem_cache *s, struct page *page, { void *prior; void **object = (void *)x; -#ifdef CONFIG_CMPXCHG_LOCAL unsigned long flags; local_irq_save(flags); -#endif slab_lock(page); stat(s, FREE_SLOWPATH); - if (kmem_cache_debug(s)) - goto debug; + if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr)) + goto out_unlock; -checks_ok: prior = page->freelist; set_freepointer(s, object, prior); page->freelist = object; @@ -2070,9 +2064,7 @@ checks_ok: out_unlock: slab_unlock(page); -#ifdef CONFIG_CMPXCHG_LOCAL local_irq_restore(flags); -#endif return; slab_empty: @@ -2084,17 +2076,9 @@ slab_empty: stat(s, FREE_REMOVE_PARTIAL); } slab_unlock(page); -#ifdef CONFIG_CMPXCHG_LOCAL local_irq_restore(flags); -#endif stat(s, FREE_SLAB); discard_slab(s, page); - return; - -debug: - if (!free_debug_processing(s, page, x, addr)) - goto out_unlock; - goto checks_ok; } /* @@ -2113,20 +2097,11 @@ static __always_inline void slab_free(struct kmem_cache *s, { void **object = (void *)x; struct kmem_cache_cpu *c; -#ifdef CONFIG_CMPXCHG_LOCAL unsigned long tid; -#else - unsigned long flags; -#endif slab_free_hook(s, x); -#ifndef CONFIG_CMPXCHG_LOCAL - local_irq_save(flags); - -#else redo: -#endif /* * Determine the currently cpus per cpu slab. @@ -2136,15 +2111,12 @@ redo: */ c = __this_cpu_ptr(s->cpu_slab); -#ifdef CONFIG_CMPXCHG_LOCAL tid = c->tid; barrier(); -#endif - if (likely(page == c->page && c->node != NUMA_NO_NODE)) { + if (likely(page == c->page)) { set_freepointer(s, object, c->freelist); -#ifdef CONFIG_CMPXCHG_LOCAL if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, c->freelist, tid, @@ -2153,16 +2125,10 @@ redo: note_cmpxchg_failure("slab_free", s, tid); goto redo; } -#else - c->freelist = object; -#endif stat(s, FREE_FASTPATH); } else __slab_free(s, page, x, addr); -#ifndef CONFIG_CMPXCHG_LOCAL - local_irq_restore(flags); -#endif } void kmem_cache_free(struct kmem_cache *s, void *x) @@ -2673,9 +2639,8 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, return; slab_err(s, page, "%s", text); slab_lock(page); - for_each_free_object(p, s, page->freelist) - set_bit(slab_index(p, s, addr), map); + get_map(s, page, map); for_each_object(p, s, addr, page->objects) { if (!test_bit(slab_index(p, s, addr), map)) { @@ -3203,7 +3168,7 @@ static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s) list_for_each_entry(p, &n->partial, lru) p->slab = s; -#ifdef CONFIG_SLAB_DEBUG +#ifdef CONFIG_SLUB_DEBUG list_for_each_entry(p, &n->full, lru) p->slab = s; #endif @@ -3610,10 +3575,11 @@ static int validate_slab(struct kmem_cache *s, struct page *page, /* Now we know that a valid freelist exists */ bitmap_zero(map, page->objects); - for_each_free_object(p, s, page->freelist) { - set_bit(slab_index(p, s, addr), map); - if (!check_object(s, page, p, SLUB_RED_INACTIVE)) - return 0; + get_map(s, page, map); + for_each_object(p, s, addr, page->objects) { + if (test_bit(slab_index(p, s, addr), map)) + if (!check_object(s, page, p, SLUB_RED_INACTIVE)) + return 0; } for_each_object(p, s, addr, page->objects) @@ -3821,8 +3787,7 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s, void *p; bitmap_zero(map, page->objects); - for_each_free_object(p, s, page->freelist) - set_bit(slab_index(p, s, addr), map); + get_map(s, page, map); for_each_object(p, s, addr, page->objects) if (!test_bit(slab_index(p, s, addr), map)) diff --git a/mm/swap.c b/mm/swap.c index a448db377cb0..5602f1a1b1e7 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -396,6 +396,9 @@ static void lru_deactivate_fn(struct page *page, void *arg) if (!PageLRU(page)) return; + if (PageUnevictable(page)) + return; + /* Some processes are using the page */ if (page_mapped(page)) return; diff --git a/mm/vmscan.c b/mm/vmscan.c index f6b435c80079..c9177202c8ce 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -42,6 +42,7 @@ #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/oom.h> +#include <linux/prefetch.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -937,7 +938,7 @@ keep_lumpy: * back off and wait for congestion to clear because further reclaim * will encounter the same problem */ - if (nr_dirty == nr_congested && nr_dirty != 0) + if (nr_dirty && nr_dirty == nr_congested && scanning_global_lru(sc)) zone_set_flag(zone, ZONE_CONGESTED); free_page_list(&free_pages); |