X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fslab.c;h=944b20581f8c421369828fb2090381ad53aa3969;hb=03b9ae4b80dd5b20d7bf7e15902592d50c66780d;hp=a94cf0fea8a2deffab0eabe95ad051e3d9b5b306;hpb=4776874ff096cd410382c0eca5d75f69c9dfa58f;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/slab.c b/mm/slab.c index a94cf0f..944b205 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -86,9 +86,9 @@ * All object allocations for a node occur from node specific slab lists. */ -#include #include #include +#include #include #include #include @@ -103,18 +103,20 @@ #include #include #include +#include #include #include #include +#include +#include +#include -#include #include #include #include /* - * DEBUG - 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL, - * SLAB_RED_ZONE & SLAB_POISON. + * DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON. * 0 for faster, smaller code (especially in the critical paths). * * STATS - 1 to collect stats for /proc/slabinfo. @@ -146,10 +148,11 @@ * Usually, the kmalloc caches are cache_line_size() aligned, except when * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that. - * Note that this flag disables some debug features. + * alignment larger than the alignment of a 64-bit integer. + * ARCH_KMALLOC_MINALIGN allows that. + * Note that increasing this value may disable some debug features. */ -#define ARCH_KMALLOC_MINALIGN 0 +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif #ifndef ARCH_SLAB_MINALIGN @@ -169,15 +172,15 @@ /* Legal flag mask for kmem_cache_create(). */ #if DEBUG -# define CREATE_MASK (SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \ +# define CREATE_MASK (SLAB_RED_ZONE | \ SLAB_POISON | SLAB_HWCACHE_ALIGN | \ SLAB_CACHE_DMA | \ - SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \ + SLAB_STORE_USER | \ SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \ SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD) #else # define CREATE_MASK (SLAB_HWCACHE_ALIGN | \ - SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \ + SLAB_CACHE_DMA | \ SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \ SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD) #endif @@ -307,6 +310,13 @@ struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS]; #define SIZE_AC 1 #define SIZE_L3 (1 + MAX_NUMNODES) +static int drain_freelist(struct kmem_cache *cache, + struct kmem_list3 *l3, int tofree); +static void free_block(struct kmem_cache *cachep, void **objpp, int len, + int node); +static int enable_cpucache(struct kmem_cache *cachep); +static void cache_reap(struct work_struct *unused); + /* * This function must be completely optimized away if a constant is passed to * it. Mostly the same as what is in linux/slab.h except it returns an index. @@ -331,6 +341,8 @@ static __always_inline int index_of(const size_t size) return 0; } +static int slab_early_init = 1; + #define INDEX_AC index_of(sizeof(struct arraycache_init)) #define INDEX_L3 index_of(sizeof(struct kmem_list3)) @@ -375,8 +387,8 @@ struct kmem_cache { unsigned int shared; unsigned int buffer_size; + u32 reciprocal_buffer_size; /* 3) touched by every alloc & free from the backend */ - struct kmem_list3 *nodelists[MAX_NUMNODES]; unsigned int flags; /* constant flags */ unsigned int num; /* # of objs per slab */ @@ -431,6 +443,17 @@ struct kmem_cache { int obj_offset; int obj_size; #endif + /* + * We put nodelists[] at the end of kmem_cache, because we want to size + * this array to nr_node_ids slots instead of MAX_NUMNODES + * (see kmem_cache_init()) + * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache + * is statically defined, so we reserve the max number of nodes. + */ + struct kmem_list3 *nodelists[MAX_NUMNODES]; + /* + * Do not add fields after nodelists[] + */ }; #define CFLGS_OFF_SLAB (0x80000000UL) @@ -452,7 +475,7 @@ struct kmem_cache { #define STATS_DEC_ACTIVE(x) ((x)->num_active--) #define STATS_INC_ALLOCED(x) ((x)->num_allocations++) #define STATS_INC_GROWN(x) ((x)->grown++) -#define STATS_INC_REAPED(x) ((x)->reaped++) +#define STATS_ADD_REAPED(x,y) ((x)->reaped += (y)) #define STATS_SET_HIGH(x) \ do { \ if ((x)->num_active > (x)->high_mark) \ @@ -476,7 +499,7 @@ struct kmem_cache { #define STATS_DEC_ACTIVE(x) do { } while (0) #define STATS_INC_ALLOCED(x) do { } while (0) #define STATS_INC_GROWN(x) do { } while (0) -#define STATS_INC_REAPED(x) do { } while (0) +#define STATS_ADD_REAPED(x,y) do { } while (0) #define STATS_SET_HIGH(x) do { } while (0) #define STATS_INC_ERR(x) do { } while (0) #define STATS_INC_NODEALLOCS(x) do { } while (0) @@ -490,17 +513,6 @@ struct kmem_cache { #endif #if DEBUG -/* - * Magic nums for obj red zoning. - * Placed in the first word before and the first word after an obj. - */ -#define RED_INACTIVE 0x5A2CF071UL /* when obj is inactive */ -#define RED_ACTIVE 0x170FC2A5UL /* when obj is active */ - -/* ...and for poisoning */ -#define POISON_INUSE 0x5a /* for use-uninitialised poisoning */ -#define POISON_FREE 0x6b /* for use-after-free poisoning */ -#define POISON_END 0xa5 /* end-byte of poisoning */ /* * memory layout of objects: @@ -525,19 +537,22 @@ static int obj_size(struct kmem_cache *cachep) return cachep->obj_size; } -static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp) +static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); - return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD); + return (unsigned long long*) (objp + obj_offset(cachep) - + sizeof(unsigned long long)); } -static unsigned long *dbg_redzone2(struct kmem_cache *cachep, void *objp) +static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); if (cachep->flags & SLAB_STORE_USER) - return (unsigned long *)(objp + cachep->buffer_size - - 2 * BYTES_PER_WORD); - return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD); + return (unsigned long long *)(objp + cachep->buffer_size - + sizeof(unsigned long long) - + BYTES_PER_WORD); + return (unsigned long long *) (objp + cachep->buffer_size - + sizeof(unsigned long long)); } static void **dbg_userword(struct kmem_cache *cachep, void *objp) @@ -550,8 +565,8 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #define obj_offset(x) 0 #define obj_size(cachep) (cachep->buffer_size) -#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long *)NULL;}) -#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long *)NULL;}) +#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) +#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) #define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;}) #endif @@ -590,8 +605,8 @@ static inline void page_set_cache(struct page *page, struct kmem_cache *cache) static inline struct kmem_cache *page_get_cache(struct page *page) { - if (unlikely(PageCompound(page))) - page = (struct page *)page_private(page); + page = compound_head(page); + BUG_ON(!PageSlab(page)); return (struct kmem_cache *)page->lru.next; } @@ -602,20 +617,19 @@ static inline void page_set_slab(struct page *page, struct slab *slab) static inline struct slab *page_get_slab(struct page *page) { - if (unlikely(PageCompound(page))) - page = (struct page *)page_private(page); + BUG_ON(!PageSlab(page)); return (struct slab *)page->lru.prev; } static inline struct kmem_cache *virt_to_cache(const void *obj) { - struct page *page = virt_to_page(obj); + struct page *page = virt_to_head_page(obj); return page_get_cache(page); } static inline struct slab *virt_to_slab(const void *obj) { - struct page *page = virt_to_page(obj); + struct page *page = virt_to_head_page(obj); return page_get_slab(page); } @@ -625,10 +639,17 @@ static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, return slab->s_mem + cache->buffer_size * idx; } -static inline unsigned int obj_to_index(struct kmem_cache *cache, - struct slab *slab, void *obj) +/* + * We want to avoid an expensive divide : (offset / cache->buffer_size) + * Using the fact that buffer_size is a constant for a particular cache, + * we can replace (offset / cache->buffer_size) by + * reciprocal_divide(offset, cache->reciprocal_buffer_size) + */ +static inline unsigned int obj_to_index(const struct kmem_cache *cache, + const struct slab *slab, void *obj) { - return (unsigned)(obj - slab->s_mem) / cache->buffer_size; + u32 offset = (obj - slab->s_mem); + return reciprocal_divide(offset, cache->reciprocal_buffer_size); } /* @@ -667,22 +688,71 @@ static struct kmem_cache cache_cache = { .shared = 1, .buffer_size = sizeof(struct kmem_cache), .name = "kmem_cache", -#if DEBUG - .obj_size = sizeof(struct kmem_cache), -#endif }; -/* Guard access to the cache-chain. */ -static DEFINE_MUTEX(cache_chain_mutex); -static struct list_head cache_chain; +#define BAD_ALIEN_MAGIC 0x01020304ul + +#ifdef CONFIG_LOCKDEP /* - * vm_enough_memory() looks at this to determine how many slab-allocated pages - * are possibly freeable under pressure + * Slab sometimes uses the kmalloc slabs to store the slab headers + * for other slabs "off slab". + * The locking for this is tricky in that it nests within the locks + * of all other slabs in a few places; to deal with this special + * locking we put on-slab caches into a separate lock-class. * - * SLAB_RECLAIM_ACCOUNT turns this on per-slab + * We set lock class for alien array caches which are up during init. + * The lock annotation will be lost if all cpus of a node goes down and + * then comes back up during hotplug + */ +static struct lock_class_key on_slab_l3_key; +static struct lock_class_key on_slab_alc_key; + +static inline void init_lock_keys(void) + +{ + int q; + struct cache_sizes *s = malloc_sizes; + + while (s->cs_size != ULONG_MAX) { + for_each_node(q) { + struct array_cache **alc; + int r; + struct kmem_list3 *l3 = s->cs_cachep->nodelists[q]; + if (!l3 || OFF_SLAB(s->cs_cachep)) + continue; + lockdep_set_class(&l3->list_lock, &on_slab_l3_key); + alc = l3->alien; + /* + * FIXME: This check for BAD_ALIEN_MAGIC + * should go away when common slab code is taught to + * work even without alien caches. + * Currently, non NUMA code returns BAD_ALIEN_MAGIC + * for alloc_alien_cache, + */ + if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC) + continue; + for_each_node(r) { + if (alc[r]) + lockdep_set_class(&alc[r]->lock, + &on_slab_alc_key); + } + } + s++; + } +} +#else +static inline void init_lock_keys(void) +{ +} +#endif + +/* + * 1. Guard access to the cache-chain. + * 2. Protect sanity of cpu_online_map against cpu hotplug events */ -atomic_t slab_reclaim_pages; +static DEFINE_MUTEX(cache_chain_mutex); +static struct list_head cache_chain; /* * chicken and egg problem: delay the per-cpu array allocation @@ -703,13 +773,7 @@ int slab_is_available(void) return g_cpucache_up == FULL; } -static DEFINE_PER_CPU(struct work_struct, reap_work); - -static void free_block(struct kmem_cache *cachep, void **objpp, int len, - int node); -static void enable_cpucache(struct kmem_cache *cachep); -static void cache_reap(void *unused); -static int __node_shrink(struct kmem_cache *cachep, int node); +static DEFINE_PER_CPU(struct delayed_work, reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { @@ -736,16 +800,17 @@ static inline struct kmem_cache *__find_general_cachep(size_t size, * has cs_{dma,}cachep==NULL. Thus no special case * for large kmalloc calls required. */ +#ifdef CONFIG_ZONE_DMA if (unlikely(gfpflags & GFP_DMA)) return csizep->cs_dmacachep; +#endif return csizep->cs_cachep; } -struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags) +static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags) { return __find_general_cachep(size, gfpflags); } -EXPORT_SYMBOL(kmem_find_general_cachep); static size_t slab_mgmt_size(size_t nr_objs, size_t align) { @@ -823,6 +888,22 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, dump_stack(); } +/* + * By default on NUMA we use alien caches to stage the freeing of + * objects allocated from other nodes. This causes massive memory + * inefficiencies when using fake NUMA setup to split memory into a + * large number of small nodes, so it can be disabled on the command + * line + */ + +static int use_alien_caches __read_mostly = 1; +static int __init noaliencache_setup(char *s) +{ + use_alien_caches = 0; + return 1; +} +__setup("noaliencache", noaliencache_setup); + #ifdef CONFIG_NUMA /* * Special reaping functions for NUMA systems called from cache_reap(). @@ -840,19 +921,13 @@ static void init_reap_node(int cpu) if (node == MAX_NUMNODES) node = first_node(node_online_map); - __get_cpu_var(reap_node) = node; + per_cpu(reap_node, cpu) = node; } static void next_reap_node(void) { int node = __get_cpu_var(reap_node); - /* - * Also drain per cpu pages on remote zones - */ - if (node != numa_node_id()) - drain_node_pages(node); - node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); @@ -873,17 +948,18 @@ static void next_reap_node(void) */ static void __devinit start_cpu_timer(int cpu) { - struct work_struct *reap_work = &per_cpu(reap_work, cpu); + struct delayed_work *reap_work = &per_cpu(reap_work, cpu); /* * When this gets called from do_initcalls via cpucache_init(), * init_workqueues() has already run, so keventd will be setup * at that time. */ - if (keventd_up() && reap_work->func == NULL) { + if (keventd_up() && reap_work->work.func == NULL) { init_reap_node(cpu); - INIT_WORK(reap_work, cache_reap, NULL); - schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu); + INIT_DELAYED_WORK(reap_work, cache_reap); + schedule_delayed_work_on(cpu, reap_work, + __round_jiffies_relative(HZ, cpu)); } } @@ -928,14 +1004,46 @@ static int transfer_objects(struct array_cache *to, return nr; } -#ifdef CONFIG_NUMA -static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int); +#ifndef CONFIG_NUMA + +#define drain_alien_cache(cachep, alien) do { } while (0) +#define reap_alien(cachep, l3) do { } while (0) + +static inline struct array_cache **alloc_alien_cache(int node, int limit) +{ + return (struct array_cache **)BAD_ALIEN_MAGIC; +} + +static inline void free_alien_cache(struct array_cache **ac_ptr) +{ +} + +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +{ + return 0; +} + +static inline void *alternate_node_alloc(struct kmem_cache *cachep, + gfp_t flags) +{ + return NULL; +} + +static inline void *____cache_alloc_node(struct kmem_cache *cachep, + gfp_t flags, int nodeid) +{ + return NULL; +} + +#else /* CONFIG_NUMA */ + +static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); static void *alternate_node_alloc(struct kmem_cache *, gfp_t); static struct array_cache **alloc_alien_cache(int node, int limit) { struct array_cache **ac_ptr; - int memsize = sizeof(void *) * MAX_NUMNODES; + int memsize = sizeof(void *) * nr_node_ids; int i; if (limit > 1) @@ -1031,15 +1139,18 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) int nodeid = slabp->nodeid; struct kmem_list3 *l3; struct array_cache *alien = NULL; + int node; + + node = numa_node_id(); /* * Make sure we are not freeing a object from another node to the array * cache on this cpu. */ - if (likely(slabp->nodeid == numa_node_id())) + if (likely(slabp->nodeid == node)) return 0; - l3 = cachep->nodelists[numa_node_id()]; + l3 = cachep->nodelists[node]; STATS_INC_NODEFREES(cachep); if (l3->alien && l3->alien[nodeid]) { alien = l3->alien[nodeid]; @@ -1057,29 +1168,9 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) } return 1; } - -#else - -#define drain_alien_cache(cachep, alien) do { } while (0) -#define reap_alien(cachep, l3) do { } while (0) - -static inline struct array_cache **alloc_alien_cache(int node, int limit) -{ - return (struct array_cache **) 0x01020304ul; -} - -static inline void free_alien_cache(struct array_cache **ac_ptr) -{ -} - -static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) -{ - return 0; -} - #endif -static int cpuup_callback(struct notifier_block *nfb, +static int __cpuinit cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { long cpu = (long)hcpu; @@ -1089,8 +1180,11 @@ static int cpuup_callback(struct notifier_block *nfb, int memsize = sizeof(struct kmem_list3); switch (action) { - case CPU_UP_PREPARE: + case CPU_LOCK_ACQUIRE: mutex_lock(&cache_chain_mutex); + break; + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: /* * We need to do this right in the beginning since * alloc_arraycache's are going to use this list. @@ -1133,22 +1227,25 @@ static int cpuup_callback(struct notifier_block *nfb, */ list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; - struct array_cache *shared; - struct array_cache **alien; + struct array_cache *shared = NULL; + struct array_cache **alien = NULL; nc = alloc_arraycache(node, cachep->limit, cachep->batchcount); if (!nc) goto bad; - shared = alloc_arraycache(node, + if (cachep->shared) { + shared = alloc_arraycache(node, cachep->shared * cachep->batchcount, 0xbaadf00d); - if (!shared) - goto bad; - - alien = alloc_alien_cache(node, cachep->limit); - if (!alien) - goto bad; + if (!shared) + goto bad; + } + if (use_alien_caches) { + alien = alloc_alien_cache(node, cachep->limit); + if (!alien) + goto bad; + } cachep->array[cpu] = nc; l3 = cachep->nodelists[node]; BUG_ON(!l3); @@ -1172,13 +1269,30 @@ static int cpuup_callback(struct notifier_block *nfb, kfree(shared); free_alien_cache(alien); } - mutex_unlock(&cache_chain_mutex); break; case CPU_ONLINE: + case CPU_ONLINE_FROZEN: start_cpu_timer(cpu); break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + /* + * Shutdown cache reaper. Note that the cache_chain_mutex is + * held so that if cache_reap() is invoked it cannot do + * anything expensive but will only modify reap_work + * and reschedule the timer. + */ + cancel_rearming_delayed_work(&per_cpu(reap_work, cpu)); + /* Now the cache_reaper is guaranteed to be not running. */ + per_cpu(reap_work, cpu).work.func = NULL; + break; + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + start_cpu_timer(cpu); + break; case CPU_DEAD: + case CPU_DEAD_FROZEN: /* * Even if all the cpus of a node are down, we don't free the * kmem_list3 of any cache. This to avoid a race between @@ -1188,8 +1302,9 @@ static int cpuup_callback(struct notifier_block *nfb, * gets destroyed at kmem_cache_destroy(). */ /* fall thru */ +#endif case CPU_UP_CANCELED: - mutex_lock(&cache_chain_mutex); + case CPU_UP_CANCELED_FROZEN: list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; struct array_cache *shared; @@ -1219,8 +1334,8 @@ static int cpuup_callback(struct notifier_block *nfb, shared = l3->shared; if (shared) { - free_block(cachep, l3->shared->entry, - l3->shared->avail, node); + free_block(cachep, shared->entry, + shared->avail, node); l3->shared = NULL; } @@ -1246,22 +1361,21 @@ free_array_cache: l3 = cachep->nodelists[node]; if (!l3) continue; - spin_lock_irq(&l3->list_lock); - /* free slabs belonging to this node */ - __node_shrink(cachep, node); - spin_unlock_irq(&l3->list_lock); + drain_freelist(cachep, l3, l3->free_objects); } + break; + case CPU_LOCK_RELEASE: mutex_unlock(&cache_chain_mutex); break; -#endif } return NOTIFY_OK; bad: - mutex_unlock(&cache_chain_mutex); return NOTIFY_BAD; } -static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 }; +static struct notifier_block __cpuinitdata cpucache_notifier = { + &cpuup_callback, NULL, 0 +}; /* * swap the static kmem_list3 with kmalloced memory @@ -1271,12 +1385,16 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, { struct kmem_list3 *ptr; - BUG_ON(cachep->nodelists[nodeid] != list); ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid); BUG_ON(!ptr); local_irq_disable(); memcpy(ptr, list, sizeof(struct kmem_list3)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->list_lock); + MAKE_ALL_LISTS(cachep, ptr, nodeid); cachep->nodelists[nodeid] = ptr; local_irq_enable(); @@ -1293,6 +1411,10 @@ void __init kmem_cache_init(void) struct cache_names *names; int i; int order; + int node; + + if (num_possible_nodes() == 1) + use_alien_caches = 0; for (i = 0; i < NUM_INIT_LISTS; i++) { kmem_list3_init(&initkmem_list3[i]); @@ -1327,15 +1449,28 @@ void __init kmem_cache_init(void) * 6) Resize the head arrays of the kmalloc caches to their final sizes. */ + node = numa_node_id(); + /* 1) create the cache_cache */ INIT_LIST_HEAD(&cache_chain); list_add(&cache_cache.next, &cache_chain); cache_cache.colour_off = cache_line_size(); cache_cache.array[smp_processor_id()] = &initarray_cache.cache; - cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE]; + cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE]; + /* + * struct kmem_cache size depends on nr_node_ids, which + * can be less than MAX_NUMNODES. + */ + cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) + + nr_node_ids * sizeof(struct kmem_list3 *); +#if DEBUG + cache_cache.obj_size = cache_cache.buffer_size; +#endif cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size()); + cache_cache.reciprocal_buffer_size = + reciprocal_value(cache_cache.buffer_size); for (order = 0; order < MAX_ORDER; order++) { cache_estimate(order, cache_cache.buffer_size, @@ -1374,6 +1509,8 @@ void __init kmem_cache_init(void) NULL, NULL); } + slab_early_init = 0; + while (sizes->cs_size != ULONG_MAX) { /* * For performance, all the general caches are L1 aligned. @@ -1389,19 +1526,21 @@ void __init kmem_cache_init(void) ARCH_KMALLOC_FLAGS|SLAB_PANIC, NULL, NULL); } - - sizes->cs_dmacachep = kmem_cache_create(names->name_dma, +#ifdef CONFIG_ZONE_DMA + sizes->cs_dmacachep = kmem_cache_create( + names->name_dma, sizes->cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA| SLAB_PANIC, NULL, NULL); +#endif sizes++; names++; } /* 4) Replace the bootstrap head arrays */ { - void *ptr; + struct array_cache *ptr; ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); @@ -1409,6 +1548,11 @@ void __init kmem_cache_init(void) BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache); memcpy(ptr, cpu_cache_get(&cache_cache), sizeof(struct arraycache_init)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->lock); + cache_cache.array[smp_processor_id()] = ptr; local_irq_enable(); @@ -1419,25 +1563,29 @@ void __init kmem_cache_init(void) != &initarray_generic.cache); memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep), sizeof(struct arraycache_init)); + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ + spin_lock_init(&ptr->lock); + malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] = ptr; local_irq_enable(); } /* 5) Replace the bootstrap kmem_list3's */ { - int node; + int nid; + /* Replace the static kmem_list3 structures for the boot cpu */ - init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], - numa_node_id()); + init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], node); - for_each_online_node(node) { + for_each_online_node(nid) { init_list(malloc_sizes[INDEX_AC].cs_cachep, - &initkmem_list3[SIZE_AC + node], node); + &initkmem_list3[SIZE_AC + nid], nid); if (INDEX_AC != INDEX_L3) { init_list(malloc_sizes[INDEX_L3].cs_cachep, - &initkmem_list3[SIZE_L3 + node], - node); + &initkmem_list3[SIZE_L3 + nid], nid); } } } @@ -1447,10 +1595,15 @@ void __init kmem_cache_init(void) struct kmem_cache *cachep; mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) - enable_cpucache(cachep); + if (enable_cpucache(cachep)) + BUG(); mutex_unlock(&cache_chain_mutex); } + /* Annotate slab for lockdep -- annotate the malloc caches */ + init_lock_keys(); + + /* Done! */ g_cpucache_up = FULL; @@ -1489,31 +1642,33 @@ __initcall(cpucache_init); static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct page *page; - void *addr; + int nr_pages; int i; - flags |= cachep->gfpflags; #ifndef CONFIG_MMU - /* nommu uses slab's for process anonymous memory allocations, so - * requires __GFP_COMP to properly refcount higher order allocations" + /* + * Nommu uses slab's for process anonymous memory allocations, and thus + * requires __GFP_COMP to properly refcount higher order allocations */ - page = alloc_pages_node(nodeid, (flags | __GFP_COMP), cachep->gfporder); -#else - page = alloc_pages_node(nodeid, flags, cachep->gfporder); + flags |= __GFP_COMP; #endif + + flags |= cachep->gfpflags; + + page = alloc_pages_node(nodeid, flags, cachep->gfporder); if (!page) return NULL; - addr = page_address(page); - i = (1 << cachep->gfporder); + nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_add(i, &slab_reclaim_pages); - add_page_state(nr_slab, i); - while (i--) { - __SetPageSlab(page); - page++; - } - return addr; + add_zone_page_state(page_zone(page), + NR_SLAB_RECLAIMABLE, nr_pages); + else + add_zone_page_state(page_zone(page), + NR_SLAB_UNRECLAIMABLE, nr_pages); + for (i = 0; i < nr_pages; i++) + __SetPageSlab(page + i); + return page_address(page); } /* @@ -1525,17 +1680,20 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) struct page *page = virt_to_page(addr); const unsigned long nr_freed = i; + if (cachep->flags & SLAB_RECLAIM_ACCOUNT) + sub_zone_page_state(page_zone(page), + NR_SLAB_RECLAIMABLE, nr_freed); + else + sub_zone_page_state(page_zone(page), + NR_SLAB_UNRECLAIMABLE, nr_freed); while (i--) { BUG_ON(!PageSlab(page)); __ClearPageSlab(page); page++; } - sub_page_state(nr_slab, nr_freed); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; free_pages((unsigned long)addr, cachep->gfporder); - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_sub(1 << cachep->gfporder, &slab_reclaim_pages); } static void kmem_rcu_free(struct rcu_head *head) @@ -1596,10 +1754,32 @@ static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) static void dump_line(char *data, int offset, int limit) { int i; + unsigned char error = 0; + int bad_count = 0; + printk(KERN_ERR "%03x:", offset); - for (i = 0; i < limit; i++) + for (i = 0; i < limit; i++) { + if (data[offset + i] != POISON_FREE) { + error = data[offset + i]; + bad_count++; + } printk(" %02x", (unsigned char)data[offset + i]); + } printk("\n"); + + if (bad_count == 1) { + error ^= POISON_FREE; + if (!(error & (error - 1))) { + printk(KERN_ERR "Single bit error detected. Probably " + "bad RAM.\n"); +#ifdef CONFIG_X86 + printk(KERN_ERR "Run memtest86+ or a similar memory " + "test tool.\n"); +#else + printk(KERN_ERR "Run a memory test tool.\n"); +#endif + } + } } #endif @@ -1611,7 +1791,7 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) char *realobj; if (cachep->flags & SLAB_RED_ZONE) { - printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n", + printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n", *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } @@ -1653,8 +1833,8 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) /* Print header */ if (lines == 0) { printk(KERN_ERR - "Slab corruption: start=%p, len=%d\n", - realobj, size); + "Slab corruption: %s start=%p, len=%d\n", + cachep->name, realobj, size); print_objinfo(cachep, objp, 0); } /* Hexdump the affected line */ @@ -1780,7 +1960,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) * For setting up all the kmem_list3s for cache whose buffer_size is same as * size of kmem_list3. */ -static void set_up_list3s(struct kmem_cache *cachep, int index) +static void __init set_up_list3s(struct kmem_cache *cachep, int index) { int node; @@ -1792,6 +1972,27 @@ static void set_up_list3s(struct kmem_cache *cachep, int index) } } +static void __kmem_cache_destroy(struct kmem_cache *cachep) +{ + int i; + struct kmem_list3 *l3; + + for_each_online_cpu(i) + kfree(cachep->array[i]); + + /* NUMA: free the list3 structures */ + for_each_online_node(i) { + l3 = cachep->nodelists[i]; + if (l3) { + kfree(l3->shared); + free_alien_cache(l3->alien); + kfree(l3); + } + } + kmem_cache_free(&cache_cache, cachep); +} + + /** * calculate_slab_order - calculate size (page order) of slabs * @cachep: pointer to the cache that is being created @@ -1862,12 +2063,11 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, return left_over; } -static void setup_cpu_cache(struct kmem_cache *cachep) +static int setup_cpu_cache(struct kmem_cache *cachep) { - if (g_cpucache_up == FULL) { - enable_cpucache(cachep); - return; - } + if (g_cpucache_up == FULL) + return enable_cpucache(cachep); + if (g_cpucache_up == NONE) { /* * Note: the first kmem_cache_create must create the cache @@ -1914,6 +2114,7 @@ static void setup_cpu_cache(struct kmem_cache *cachep) cpu_cache_get(cachep)->touched = 0; cachep->batchcount = 1; cachep->limit = BOOT_CPUCACHE_ENTRIES; + return 0; } /** @@ -1952,8 +2153,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, void (*dtor)(void*, struct kmem_cache *, unsigned long)) { size_t left_over, slab_size, ralign; - struct kmem_cache *cachep = NULL; - struct list_head *p; + struct kmem_cache *cachep = NULL, *pc; /* * Sanity checks... these are all serious usage bugs. @@ -1966,16 +2166,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, } /* - * Prevent CPUs from coming and going. - * lock_cpu_hotplug() nests outside cache_chain_mutex + * We use cache_chain_mutex to ensure a consistent view of + * cpu_online_map as well. Please see cpuup_callback */ - lock_cpu_hotplug(); - mutex_lock(&cache_chain_mutex); - list_for_each(p, &cache_chain) { - struct kmem_cache *pc = list_entry(p, struct kmem_cache, next); - mm_segment_t old_fs = get_fs(); + list_for_each_entry(pc, &cache_chain, next) { char tmp; int res; @@ -1984,17 +2180,17 @@ kmem_cache_create (const char *name, size_t size, size_t align, * destroy its slab cache and no-one else reuses the vmalloc * area of the module. Print a warning. */ - set_fs(KERNEL_DS); - res = __get_user(tmp, pc->name); - set_fs(old_fs); + res = probe_kernel_address(pc->name, tmp); if (res) { - printk("SLAB: cache with size %d has lost its name\n", + printk(KERN_ERR + "SLAB: cache with size %d has lost its name\n", pc->buffer_size); continue; } if (!strcmp(pc->name, name)) { - printk("kmem_cache_create: duplicate cache %s\n", name); + printk(KERN_ERR + "kmem_cache_create: duplicate cache %s\n", name); dump_stack(); goto oops; } @@ -2002,12 +2198,6 @@ kmem_cache_create (const char *name, size_t size, size_t align, #if DEBUG WARN_ON(strchr(name, ' ')); /* It confuses parsers */ - if ((flags & SLAB_DEBUG_INITIAL) && !ctor) { - /* No constructor, but inital state check requested */ - printk(KERN_ERR "%s: No con, but init state check " - "requested - %s\n", __FUNCTION__, name); - flags &= ~SLAB_DEBUG_INITIAL; - } #if FORCED_DEBUG /* * Enable redzoning and last user accounting, except for caches with @@ -2057,46 +2247,52 @@ kmem_cache_create (const char *name, size_t size, size_t align, } else { ralign = BYTES_PER_WORD; } - /* 2) arch mandated alignment: disables debug if necessary */ + + /* + * Redzoning and user store require word alignment. Note this will be + * overridden by architecture or caller mandated alignment if either + * is greater than BYTES_PER_WORD. + */ + if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER) + ralign = __alignof__(unsigned long long); + + /* 2) arch mandated alignment */ if (ralign < ARCH_SLAB_MINALIGN) { ralign = ARCH_SLAB_MINALIGN; - if (ralign > BYTES_PER_WORD) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); } - /* 3) caller mandated alignment: disables debug if necessary */ + /* 3) caller mandated alignment */ if (ralign < align) { ralign = align; - if (ralign > BYTES_PER_WORD) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); } + /* disable debug if necessary */ + if (ralign > __alignof__(unsigned long long)) + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); /* - * 4) Store it. Note that the debug code below can reduce - * the alignment to BYTES_PER_WORD. + * 4) Store it. */ align = ralign; /* Get cache's description obj. */ - cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL); + cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL); if (!cachep) goto oops; #if DEBUG cachep->obj_size = size; + /* + * Both debugging options require word-alignment which is calculated + * into align above. + */ if (flags & SLAB_RED_ZONE) { - /* redzoning only works with word aligned caches */ - align = BYTES_PER_WORD; - /* add space for red zone words */ - cachep->obj_offset += BYTES_PER_WORD; - size += 2 * BYTES_PER_WORD; + cachep->obj_offset += sizeof(unsigned long long); + size += 2 * sizeof(unsigned long long); } if (flags & SLAB_STORE_USER) { - /* user store requires word alignment and - * one word storage behind the end of the real - * object. + /* user store requires one word storage behind the end of + * the real object. */ - align = BYTES_PER_WORD; size += BYTES_PER_WORD; } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) @@ -2108,8 +2304,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, #endif #endif - /* Determine if the slab management is 'on' or 'off' slab. */ - if (size >= (PAGE_SIZE >> 3)) + /* + * Determine if the slab management is 'on' or 'off' slab. + * (bootstrapping cannot cope with offslab caches so don't do + * it too early on.) + */ + if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init) /* * Size is large, assume best to place the slab management obj * off-slab (should allow better packing of objs). @@ -2121,7 +2321,8 @@ kmem_cache_create (const char *name, size_t size, size_t align, left_over = calculate_slab_order(cachep, size, align, flags); if (!cachep->num) { - printk("kmem_cache_create: couldn't create cache %s.\n", name); + printk(KERN_ERR + "kmem_cache_create: couldn't create cache %s.\n", name); kmem_cache_free(&cache_cache, cachep); cachep = NULL; goto oops; @@ -2152,18 +2353,31 @@ kmem_cache_create (const char *name, size_t size, size_t align, cachep->slab_size = slab_size; cachep->flags = flags; cachep->gfpflags = 0; - if (flags & SLAB_CACHE_DMA) + if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) cachep->gfpflags |= GFP_DMA; cachep->buffer_size = size; + cachep->reciprocal_buffer_size = reciprocal_value(size); - if (flags & CFLGS_OFF_SLAB) + if (flags & CFLGS_OFF_SLAB) { cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u); + /* + * This is a possibility for one of the malloc_sizes caches. + * But since we go off slab only for object size greater than + * PAGE_SIZE/8, and malloc_sizes gets created in ascending order, + * this should not happen at all. + * But leave a BUG_ON for some lucky dude. + */ + BUG_ON(!cachep->slabp_cache); + } cachep->ctor = ctor; cachep->dtor = dtor; cachep->name = name; - - setup_cpu_cache(cachep); + if (setup_cpu_cache(cachep)) { + __kmem_cache_destroy(cachep); + cachep = NULL; + goto oops; + } /* cache setup completed, link it into the list */ list_add(&cachep->next, &cache_chain); @@ -2172,7 +2386,6 @@ oops: panic("kmem_cache_create(): failed to create slab `%s'\n", name); mutex_unlock(&cache_chain_mutex); - unlock_cpu_hotplug(); return cachep; } EXPORT_SYMBOL(kmem_cache_create); @@ -2249,34 +2462,48 @@ static void drain_cpu_caches(struct kmem_cache *cachep) } } -static int __node_shrink(struct kmem_cache *cachep, int node) +/* + * Remove slabs from the list of free slabs. + * Specify the number of slabs to drain in tofree. + * + * Returns the actual number of slabs released. + */ +static int drain_freelist(struct kmem_cache *cache, + struct kmem_list3 *l3, int tofree) { + struct list_head *p; + int nr_freed; struct slab *slabp; - struct kmem_list3 *l3 = cachep->nodelists[node]; - int ret; - for (;;) { - struct list_head *p; + nr_freed = 0; + while (nr_freed < tofree && !list_empty(&l3->slabs_free)) { + spin_lock_irq(&l3->list_lock); p = l3->slabs_free.prev; - if (p == &l3->slabs_free) - break; + if (p == &l3->slabs_free) { + spin_unlock_irq(&l3->list_lock); + goto out; + } - slabp = list_entry(l3->slabs_free.prev, struct slab, list); + slabp = list_entry(p, struct slab, list); #if DEBUG BUG_ON(slabp->inuse); #endif list_del(&slabp->list); - - l3->free_objects -= cachep->num; + /* + * Safe to drop the lock. The slab is no longer linked + * to the cache. + */ + l3->free_objects -= cache->num; spin_unlock_irq(&l3->list_lock); - slab_destroy(cachep, slabp); - spin_lock_irq(&l3->list_lock); + slab_destroy(cache, slabp); + nr_freed++; } - ret = !list_empty(&l3->slabs_full) || !list_empty(&l3->slabs_partial); - return ret; +out: + return nr_freed; } +/* Called with cache_chain_mutex held to protect against cpu hotplug */ static int __cache_shrink(struct kmem_cache *cachep) { int ret = 0, i = 0; @@ -2287,11 +2514,13 @@ static int __cache_shrink(struct kmem_cache *cachep) check_irq_on(); for_each_online_node(i) { l3 = cachep->nodelists[i]; - if (l3) { - spin_lock_irq(&l3->list_lock); - ret += __node_shrink(cachep, i); - spin_unlock_irq(&l3->list_lock); - } + if (!l3) + continue; + + drain_freelist(cachep, l3, l3->free_objects); + + ret += !list_empty(&l3->slabs_full) || + !list_empty(&l3->slabs_partial); } return (ret ? 1 : 0); } @@ -2305,9 +2534,13 @@ static int __cache_shrink(struct kmem_cache *cachep) */ int kmem_cache_shrink(struct kmem_cache *cachep) { + int ret; BUG_ON(!cachep || in_interrupt()); - return __cache_shrink(cachep); + mutex_lock(&cache_chain_mutex); + ret = __cache_shrink(cachep); + mutex_unlock(&cache_chain_mutex); + return ret; } EXPORT_SYMBOL(kmem_cache_shrink); @@ -2315,8 +2548,7 @@ EXPORT_SYMBOL(kmem_cache_shrink); * kmem_cache_destroy - delete a cache * @cachep: the cache to destroy * - * Remove a struct kmem_cache object from the slab cache. - * Returns 0 on success. + * Remove a &struct kmem_cache object from the slab cache. * * It is expected this function will be called by a module when it is * unloaded. This will remove the cache completely, and avoid a duplicate @@ -2328,55 +2560,42 @@ EXPORT_SYMBOL(kmem_cache_shrink); * The caller must guarantee that noone will allocate memory from the cache * during the kmem_cache_destroy(). */ -int kmem_cache_destroy(struct kmem_cache *cachep) +void kmem_cache_destroy(struct kmem_cache *cachep) { - int i; - struct kmem_list3 *l3; - BUG_ON(!cachep || in_interrupt()); - /* Don't let CPUs to come and go */ - lock_cpu_hotplug(); - /* Find the cache in the chain of caches. */ mutex_lock(&cache_chain_mutex); /* * the chain is never empty, cache_cache is never destroyed */ list_del(&cachep->next); - mutex_unlock(&cache_chain_mutex); - if (__cache_shrink(cachep)) { slab_error(cachep, "Can't free all objects"); - mutex_lock(&cache_chain_mutex); list_add(&cachep->next, &cache_chain); mutex_unlock(&cache_chain_mutex); - unlock_cpu_hotplug(); - return 1; + return; } if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) synchronize_rcu(); - for_each_online_cpu(i) - kfree(cachep->array[i]); - - /* NUMA: free the list3 structures */ - for_each_online_node(i) { - l3 = cachep->nodelists[i]; - if (l3) { - kfree(l3->shared); - free_alien_cache(l3->alien); - kfree(l3); - } - } - kmem_cache_free(&cache_cache, cachep); - unlock_cpu_hotplug(); - return 0; + __kmem_cache_destroy(cachep); + mutex_unlock(&cache_chain_mutex); } EXPORT_SYMBOL(kmem_cache_destroy); -/* Get the memory for a slab management obj. */ +/* + * Get the memory for a slab management obj. + * For a slab cache when the slab descriptor is off-slab, slab descriptors + * always come from malloc_sizes caches. The slab descriptor cannot + * come from the same cache which is getting created because, + * when we are searching for an appropriate cache for these + * descriptors in kmem_cache_create, we search through the malloc_sizes array. + * If we are creating a malloc_sizes cache here it would not be visible to + * kmem_find_general_cachep till the initialization is complete. + * Hence we cannot have slabp_cache same as the original cache. + */ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, int colour_off, gfp_t local_flags, int nodeid) @@ -2386,7 +2605,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ slabp = kmem_cache_alloc_node(cachep->slabp_cache, - local_flags, nodeid); + local_flags & ~GFP_THISNODE, nodeid); if (!slabp) return NULL; } else { @@ -2456,10 +2675,12 @@ static void cache_init_objs(struct kmem_cache *cachep, static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) { - if (flags & SLAB_DMA) - BUG_ON(!(cachep->gfpflags & GFP_DMA)); - else - BUG_ON(cachep->gfpflags & GFP_DMA); + if (CONFIG_ZONE_DMA_FLAG) { + if (flags & GFP_DMA) + BUG_ON(!(cachep->gfpflags & GFP_DMA)); + else + BUG_ON(cachep->gfpflags & GFP_DMA); + } } static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, @@ -2527,10 +2748,10 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, * Grow (by 1) the number of slabs within a cache. This is called by * kmem_cache_alloc() when there are no active objs left in a cache. */ -static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) +static int cache_grow(struct kmem_cache *cachep, + gfp_t flags, int nodeid, void *objp) { struct slab *slabp; - void *objp; size_t offset; gfp_t local_flags; unsigned long ctor_flags; @@ -2540,19 +2761,10 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) * Be lazy and only check for valid flags here, keeping it out of the * critical path in kmem_cache_alloc(). */ - BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW)); - if (flags & SLAB_NO_GROW) - return 0; + BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK)); ctor_flags = SLAB_CTOR_CONSTRUCTOR; - local_flags = (flags & SLAB_LEVEL_MASK); - if (!(local_flags & __GFP_WAIT)) - /* - * Not allowed to sleep. Need to tell a constructor about - * this - it might need to know... - */ - ctor_flags |= SLAB_CTOR_ATOMIC; - + local_flags = (flags & GFP_LEVEL_MASK); /* Take the l3 list lock to change the colour_next on this node */ check_irq_off(); l3 = cachep->nodelists[nodeid]; @@ -2582,12 +2794,14 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) * Get mem for the objs. Attempt to allocate a physical page from * 'nodeid'. */ - objp = kmem_getpages(cachep, flags, nodeid); + if (!objp) + objp = kmem_getpages(cachep, flags, nodeid); if (!objp) goto failed; /* Get slab management. */ - slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid); + slabp = alloc_slabmgmt(cachep, objp, offset, + local_flags & ~GFP_THISNODE, nodeid); if (!slabp) goto opps1; @@ -2625,19 +2839,33 @@ failed: */ static void kfree_debugcheck(const void *objp) { - struct page *page; - if (!virt_addr_valid(objp)) { printk(KERN_ERR "kfree_debugcheck: out of range ptr %lxh.\n", (unsigned long)objp); BUG(); } - page = virt_to_page(objp); - if (!PageSlab(page)) { - printk(KERN_ERR "kfree_debugcheck: bad ptr %lxh.\n", - (unsigned long)objp); - BUG(); - } +} + +static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) +{ + unsigned long long redzone1, redzone2; + + redzone1 = *dbg_redzone1(cache, obj); + redzone2 = *dbg_redzone2(cache, obj); + + /* + * Redzone is ok. + */ + if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE) + return; + + if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE) + slab_error(cache, "double free detected"); + else + slab_error(cache, "memory outside object was overwritten"); + + printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n", + obj, redzone1, redzone2); } static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, @@ -2649,29 +2877,12 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, objp -= obj_offset(cachep); kfree_debugcheck(objp); - page = virt_to_page(objp); - - if (page_get_cache(page) != cachep) { - printk(KERN_ERR "mismatch in kmem_cache_free: expected " - "cache %p, got %p\n", - page_get_cache(page), cachep); - printk(KERN_ERR "%p is %s.\n", cachep, cachep->name); - printk(KERN_ERR "%p is %s.\n", page_get_cache(page), - page_get_cache(page)->name); - WARN_ON(1); - } + page = virt_to_head_page(objp); + slabp = page_get_slab(page); if (cachep->flags & SLAB_RED_ZONE) { - if (*dbg_redzone1(cachep, objp) != RED_ACTIVE || - *dbg_redzone2(cachep, objp) != RED_ACTIVE) { - slab_error(cachep, "double free, or memory outside" - " object was overwritten"); - printk(KERN_ERR "%p: redzone 1:0x%lx, " - "redzone 2:0x%lx.\n", - objp, *dbg_redzone1(cachep, objp), - *dbg_redzone2(cachep, objp)); - } + verify_redzone_free(cachep, objp); *dbg_redzone1(cachep, objp) = RED_INACTIVE; *dbg_redzone2(cachep, objp) = RED_INACTIVE; } @@ -2683,15 +2894,6 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, BUG_ON(objnr >= cachep->num); BUG_ON(objp != index_to_obj(cachep, slabp, objnr)); - if (cachep->flags & SLAB_DEBUG_INITIAL) { - /* - * Need to call the slab's constructor so the caller can - * perform a verify of its state (debugging). Called without - * the cache-lock held. - */ - cachep->ctor(objp + obj_offset(cachep), - cachep, SLAB_CTOR_CONSTRUCTOR | SLAB_CTOR_VERIFY); - } if (cachep->flags & SLAB_POISON && cachep->dtor) { /* we want to cache poison the object, * call the destruction callback @@ -2755,6 +2957,9 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) int batchcount; struct kmem_list3 *l3; struct array_cache *ac; + int node; + + node = numa_node_id(); check_irq_off(); ac = cpu_cache_get(cachep); @@ -2768,7 +2973,7 @@ retry: */ batchcount = BATCHREFILL_LIMIT; } - l3 = cachep->nodelists[numa_node_id()]; + l3 = cachep->nodelists[node]; BUG_ON(ac->avail > 0 || !l3); spin_lock(&l3->list_lock); @@ -2792,13 +2997,21 @@ retry: slabp = list_entry(entry, struct slab, list); check_slabp(cachep, slabp); check_spinlock_acquired(cachep); + + /* + * The slab was either on partial or free list so + * there must be at least one object available for + * allocation. + */ + BUG_ON(slabp->inuse < 0 || slabp->inuse >= cachep->num); + while (slabp->inuse < cachep->num && batchcount--) { STATS_INC_ALLOCED(cachep); STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); ac->entry[ac->avail++] = slab_get_obj(cachep, slabp, - numa_node_id()); + node); } check_slabp(cachep, slabp); @@ -2817,7 +3030,7 @@ alloc_done: if (unlikely(!ac->avail)) { int x; - x = cache_grow(cachep, flags, numa_node_id()); + x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL); /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); @@ -2867,7 +3080,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, slab_error(cachep, "double free, or memory outside" " object was overwritten"); printk(KERN_ERR - "%p: redzone 1:0x%lx, redzone 2:0x%lx\n", + "%p: redzone 1:0x%llx, redzone 2:0x%llx\n", objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } @@ -2879,40 +3092,106 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, struct slab *slabp; unsigned objnr; - slabp = page_get_slab(virt_to_page(objp)); + slabp = page_get_slab(virt_to_head_page(objp)); objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size; slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE; } #endif objp += obj_offset(cachep); - if (cachep->ctor && cachep->flags & SLAB_POISON) { - unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR; - - if (!(flags & __GFP_WAIT)) - ctor_flags |= SLAB_CTOR_ATOMIC; - - cachep->ctor(objp, cachep, ctor_flags); + if (cachep->ctor && cachep->flags & SLAB_POISON) + cachep->ctor(objp, cachep, SLAB_CTOR_CONSTRUCTOR); +#if ARCH_SLAB_MINALIGN + if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { + printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", + objp, ARCH_SLAB_MINALIGN); } +#endif return objp; } #else #define cache_alloc_debugcheck_after(a,b,objp,d) (objp) #endif +#ifdef CONFIG_FAILSLAB + +static struct failslab_attr { + + struct fault_attr attr; + + u32 ignore_gfp_wait; +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + struct dentry *ignore_gfp_wait_file; +#endif + +} failslab = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, +}; + +static int __init setup_failslab(char *str) +{ + return setup_fault_attr(&failslab.attr, str); +} +__setup("failslab=", setup_failslab); + +static int should_failslab(struct kmem_cache *cachep, gfp_t flags) +{ + if (cachep == &cache_cache) + return 0; + if (flags & __GFP_NOFAIL) + return 0; + if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT)) + return 0; + + return should_fail(&failslab.attr, obj_size(cachep)); +} + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +static int __init failslab_debugfs(void) +{ + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + struct dentry *dir; + int err; + + err = init_fault_attr_dentries(&failslab.attr, "failslab"); + if (err) + return err; + dir = failslab.attr.dentries.dir; + + failslab.ignore_gfp_wait_file = + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &failslab.ignore_gfp_wait); + + if (!failslab.ignore_gfp_wait_file) { + err = -ENOMEM; + debugfs_remove(failslab.ignore_gfp_wait_file); + cleanup_fault_attr_dentries(&failslab.attr); + } + + return err; +} + +late_initcall(failslab_debugfs); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#else /* CONFIG_FAILSLAB */ + +static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags) +{ + return 0; +} + +#endif /* CONFIG_FAILSLAB */ + static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *objp; struct array_cache *ac; -#ifdef CONFIG_NUMA - if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { - objp = alternate_node_alloc(cachep, flags); - if (objp != NULL) - return objp; - } -#endif - check_irq_off(); + ac = cpu_cache_get(cachep); if (likely(ac->avail)) { STATS_INC_ALLOCHIT(cachep); @@ -2925,23 +3204,6 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) return objp; } -static __always_inline void *__cache_alloc(struct kmem_cache *cachep, - gfp_t flags, void *caller) -{ - unsigned long save_flags; - void *objp; - - cache_alloc_debugcheck_before(cachep, flags); - - local_irq_save(save_flags); - objp = ____cache_alloc(cachep, flags); - local_irq_restore(save_flags); - objp = cache_alloc_debugcheck_after(cachep, flags, objp, - caller); - prefetchw(objp); - return objp; -} - #ifdef CONFIG_NUMA /* * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY. @@ -2953,7 +3215,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) { int nid_alloc, nid_here; - if (in_interrupt()) + if (in_interrupt() || (flags & __GFP_THISNODE)) return NULL; nid_alloc = nid_here = numa_node_id(); if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) @@ -2961,14 +3223,89 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) else if (current->mempolicy) nid_alloc = slab_node(current->mempolicy); if (nid_alloc != nid_here) - return __cache_alloc_node(cachep, flags, nid_alloc); + return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; } /* + * Fallback function if there was no memory available and no objects on a + * certain node and fall back is permitted. First we scan all the + * available nodelists for available objects. If that fails then we + * perform an allocation without specifying a node. This allows the page + * allocator to do its reclaim / fallback magic. We then insert the + * slab into the proper nodelist and then allocate from it. + */ +static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) +{ + struct zonelist *zonelist; + gfp_t local_flags; + struct zone **z; + void *obj = NULL; + int nid; + + if (flags & __GFP_THISNODE) + return NULL; + + zonelist = &NODE_DATA(slab_node(current->mempolicy)) + ->node_zonelists[gfp_zone(flags)]; + local_flags = (flags & GFP_LEVEL_MASK); + +retry: + /* + * Look through allowed nodes for objects available + * from existing per node queues. + */ + for (z = zonelist->zones; *z && !obj; z++) { + nid = zone_to_nid(*z); + + if (cpuset_zone_allowed_hardwall(*z, flags) && + cache->nodelists[nid] && + cache->nodelists[nid]->free_objects) + obj = ____cache_alloc_node(cache, + flags | GFP_THISNODE, nid); + } + + if (!obj) { + /* + * This allocation will be performed within the constraints + * of the current cpuset / memory policy requirements. + * We may trigger various forms of reclaim on the allowed + * set and go into memory reserves if necessary. + */ + if (local_flags & __GFP_WAIT) + local_irq_enable(); + kmem_flagcheck(cache, flags); + obj = kmem_getpages(cache, flags, -1); + if (local_flags & __GFP_WAIT) + local_irq_disable(); + if (obj) { + /* + * Insert into the appropriate per node queues + */ + nid = page_to_nid(virt_to_page(obj)); + if (cache_grow(cache, flags, nid, obj)) { + obj = ____cache_alloc_node(cache, + flags | GFP_THISNODE, nid); + if (!obj) + /* + * Another processor may allocate the + * objects in the slab since we are + * not holding any locks. + */ + goto retry; + } else { + /* cache_grow already freed obj */ + obj = NULL; + } + } + } + return obj; +} + +/* * A interface to enable slab creation on nodeid */ -static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, +static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct list_head *entry; @@ -3017,16 +3354,120 @@ retry: must_grow: spin_unlock(&l3->list_lock); - x = cache_grow(cachep, flags, nodeid); + x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL); + if (x) + goto retry; - if (!x) - return NULL; + return fallback_alloc(cachep, flags); - goto retry; done: return obj; } -#endif + +/** + * kmem_cache_alloc_node - Allocate an object on the specified node + * @cachep: The cache to allocate from. + * @flags: See kmalloc(). + * @nodeid: node number of the target node. + * @caller: return address of caller, used for debug information + * + * Identical to kmem_cache_alloc but it will allocate memory on the given + * node, which can improve the performance for cpu bound structures. + * + * Fallback to other node is possible if __GFP_THISNODE is not set. + */ +static __always_inline void * +__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, + void *caller) +{ + unsigned long save_flags; + void *ptr; + + if (should_failslab(cachep, flags)) + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); + local_irq_save(save_flags); + + if (unlikely(nodeid == -1)) + nodeid = numa_node_id(); + + if (unlikely(!cachep->nodelists[nodeid])) { + /* Node not bootstrapped yet */ + ptr = fallback_alloc(cachep, flags); + goto out; + } + + if (nodeid == numa_node_id()) { + /* + * Use the locally cached objects if possible. + * However ____cache_alloc does not allow fallback + * to other nodes. It may fail while we still have + * objects on other nodes available. + */ + ptr = ____cache_alloc(cachep, flags); + if (ptr) + goto out; + } + /* ___cache_alloc_node can fall back to other nodes */ + ptr = ____cache_alloc_node(cachep, flags, nodeid); + out: + local_irq_restore(save_flags); + ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); + + return ptr; +} + +static __always_inline void * +__do_cache_alloc(struct kmem_cache *cache, gfp_t flags) +{ + void *objp; + + if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { + objp = alternate_node_alloc(cache, flags); + if (objp) + goto out; + } + objp = ____cache_alloc(cache, flags); + + /* + * We may just have run out of memory on the local node. + * ____cache_alloc_node() knows how to locate memory on other nodes + */ + if (!objp) + objp = ____cache_alloc_node(cache, flags, numa_node_id()); + + out: + return objp; +} +#else + +static __always_inline void * +__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + return ____cache_alloc(cachep, flags); +} + +#endif /* CONFIG_NUMA */ + +static __always_inline void * +__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) +{ + unsigned long save_flags; + void *objp; + + if (should_failslab(cachep, flags)) + return NULL; + + cache_alloc_debugcheck_before(cachep, flags); + local_irq_save(save_flags); + objp = __do_cache_alloc(cachep, flags); + local_irq_restore(save_flags); + objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); + prefetchw(objp); + + return objp; +} /* * Caller needs to acquire correct kmem_list's list_lock @@ -3055,6 +3496,12 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, if (slabp->inuse == 0) { if (l3->free_objects > l3->free_limit) { l3->free_objects -= cachep->num; + /* No need to drop any previously held + * lock here, even if we have a off-slab slab + * descriptor it is guaranteed to come from + * a different cache, refer to comments before + * alloc_slabmgmt. + */ slab_destroy(cachep, slabp); } else { list_add(&slabp->list, &l3->slabs_free); @@ -3131,7 +3578,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp) check_irq_off(); objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0)); - if (cache_free_alien(cachep, objp)) + if (use_alien_caches && cache_free_alien(cachep, objp)) return; if (likely(ac->avail < ac->limit)) { @@ -3160,7 +3607,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) EXPORT_SYMBOL(kmem_cache_alloc); /** - * kmem_cache_alloc - Allocate an object. The memory is set to zero. + * kmem_cache_zalloc - Allocate an object. The memory is set to zero. * @cache: The cache to allocate from. * @flags: See kmalloc(). * @@ -3190,7 +3637,7 @@ EXPORT_SYMBOL(kmem_cache_zalloc); * * Currently only used for dentry validation. */ -int fastcall kmem_ptr_validate(struct kmem_cache *cachep, void *ptr) +int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr) { unsigned long addr = (unsigned long)ptr; unsigned long min_addr = PAGE_OFFSET; @@ -3219,41 +3666,15 @@ out: } #ifdef CONFIG_NUMA -/** - * kmem_cache_alloc_node - Allocate an object on the specified node - * @cachep: The cache to allocate from. - * @flags: See kmalloc(). - * @nodeid: node number of the target node. - * - * Identical to kmem_cache_alloc, except that this function is slow - * and can sleep. And it will allocate memory on the given node, which - * can improve the performance for cpu bound structures. - * New and improved: it will now make sure that the object gets - * put on the correct node list so that there is no false sharing. - */ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - unsigned long save_flags; - void *ptr; - - cache_alloc_debugcheck_before(cachep, flags); - local_irq_save(save_flags); - - if (nodeid == -1 || nodeid == numa_node_id() || - !cachep->nodelists[nodeid]) - ptr = ____cache_alloc(cachep, flags); - else - ptr = __cache_alloc_node(cachep, flags, nodeid); - local_irq_restore(save_flags); - - ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, - __builtin_return_address(0)); - - return ptr; + return __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); } EXPORT_SYMBOL(kmem_cache_alloc_node); -void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline void * +__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; @@ -3262,30 +3683,35 @@ void *kmalloc_node(size_t size, gfp_t flags, int node) return NULL; return kmem_cache_alloc_node(cachep, flags, node); } -EXPORT_SYMBOL(kmalloc_node); -#endif + +#ifdef CONFIG_DEBUG_SLAB +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, + int node, void *caller) +{ + return __do_kmalloc_node(size, flags, node, caller); +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); +#else +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, NULL); +} +EXPORT_SYMBOL(__kmalloc_node); +#endif /* CONFIG_DEBUG_SLAB */ +#endif /* CONFIG_NUMA */ /** - * kmalloc - allocate memory + * __do_kmalloc - allocate memory * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate. + * @flags: the type of memory to allocate (see kmalloc). * @caller: function caller for debug tracking of the caller - * - * kmalloc is the normal method of allocating memory - * in the kernel. - * - * The @flags argument may be one of: - * - * %GFP_USER - Allocate memory on behalf of user. May sleep. - * - * %GFP_KERNEL - Allocate normal kernel ram. May sleep. - * - * %GFP_ATOMIC - Allocation will not sleep. Use inside interrupt handlers. - * - * Additionally, the %GFP_DMA flag may be set to indicate the memory - * must be suitable for DMA. This can mean different things on different - * platforms. For example, on i386, it means that the memory must come - * from the first 16MB. */ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, void *caller) @@ -3304,72 +3730,72 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, } +#ifdef CONFIG_DEBUG_SLAB void *__kmalloc(size_t size, gfp_t flags) { -#ifndef CONFIG_DEBUG_SLAB - return __do_kmalloc(size, flags, NULL); -#else return __do_kmalloc(size, flags, __builtin_return_address(0)); -#endif } EXPORT_SYMBOL(__kmalloc); -#ifdef CONFIG_DEBUG_SLAB void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller) { return __do_kmalloc(size, flags, caller); } EXPORT_SYMBOL(__kmalloc_track_caller); + +#else +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc(size, flags, NULL); +} +EXPORT_SYMBOL(__kmalloc); #endif -#ifdef CONFIG_SMP /** - * __alloc_percpu - allocate one copy of the object for every present - * cpu in the system, zeroing them. - * Objects should be dereferenced using the per_cpu_ptr macro only. + * krealloc - reallocate memory. The contents will remain unchanged. + * @p: object to reallocate memory for. + * @new_size: how many bytes of memory are required. + * @flags: the type of memory to allocate. * - * @size: how many bytes of memory are required. + * The contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. If @p is %NULL, krealloc() + * behaves exactly like kmalloc(). If @size is 0 and @p is not a + * %NULL pointer, the object pointed to is freed. */ -void *__alloc_percpu(size_t size) +void *krealloc(const void *p, size_t new_size, gfp_t flags) { - int i; - struct percpu_data *pdata = kmalloc(sizeof(*pdata), GFP_KERNEL); + struct kmem_cache *cache, *new_cache; + void *ret; - if (!pdata) - return NULL; + if (unlikely(!p)) + return kmalloc_track_caller(new_size, flags); - /* - * Cannot use for_each_online_cpu since a cpu may come online - * and we have no way of figuring out how to fix the array - * that we have allocated then.... - */ - for_each_possible_cpu(i) { - int node = cpu_to_node(i); - - if (node_online(node)) - pdata->ptrs[i] = kmalloc_node(size, GFP_KERNEL, node); - else - pdata->ptrs[i] = kmalloc(size, GFP_KERNEL); - - if (!pdata->ptrs[i]) - goto unwind_oom; - memset(pdata->ptrs[i], 0, size); + if (unlikely(!new_size)) { + kfree(p); + return NULL; } - /* Catch derefs w/o wrappers */ - return (void *)(~(unsigned long)pdata); + cache = virt_to_cache(p); + new_cache = __find_general_cachep(new_size, flags); -unwind_oom: - while (--i >= 0) { - if (!cpu_possible(i)) - continue; - kfree(pdata->ptrs[i]); + /* + * If new size fits in the current cache, bail out. + */ + if (likely(cache == new_cache)) + return (void *)p; + + /* + * We are on the slow-path here so do not use __cache_alloc + * because it bloats kernel text. + */ + ret = kmalloc_track_caller(new_size, flags); + if (ret) { + memcpy(ret, p, min(new_size, ksize(p))); + kfree(p); } - kfree(pdata); - return NULL; + return ret; } -EXPORT_SYMBOL(__alloc_percpu); -#endif +EXPORT_SYMBOL(krealloc); /** * kmem_cache_free - Deallocate an object @@ -3383,7 +3809,10 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) { unsigned long flags; + BUG_ON(virt_to_cache(objp) != cachep); + local_irq_save(flags); + debug_check_no_locks_freed(objp, obj_size(cachep)); __cache_free(cachep, objp); local_irq_restore(flags); } @@ -3408,35 +3837,12 @@ void kfree(const void *objp) local_irq_save(flags); kfree_debugcheck(objp); c = virt_to_cache(objp); - mutex_debug_check_no_locks_freed(objp, obj_size(c)); + debug_check_no_locks_freed(objp, obj_size(c)); __cache_free(c, (void *)objp); local_irq_restore(flags); } EXPORT_SYMBOL(kfree); -#ifdef CONFIG_SMP -/** - * free_percpu - free previously allocated percpu memory - * @objp: pointer returned by alloc_percpu. - * - * Don't free memory not originally allocated by alloc_percpu() - * The complemented objp is to check for that. - */ -void free_percpu(const void *objp) -{ - int i; - struct percpu_data *p = (struct percpu_data *)(~(unsigned long)objp); - - /* - * We allocate for all cpus so we cannot use for online cpu here. - */ - for_each_possible_cpu(i) - kfree(p->ptrs[i]); - kfree(p); -} -EXPORT_SYMBOL(free_percpu); -#endif - unsigned int kmem_cache_size(struct kmem_cache *cachep) { return obj_size(cachep); @@ -3457,20 +3863,25 @@ static int alloc_kmemlist(struct kmem_cache *cachep) int node; struct kmem_list3 *l3; struct array_cache *new_shared; - struct array_cache **new_alien; + struct array_cache **new_alien = NULL; for_each_online_node(node) { - new_alien = alloc_alien_cache(node, cachep->limit); - if (!new_alien) - goto fail; + if (use_alien_caches) { + new_alien = alloc_alien_cache(node, cachep->limit); + if (!new_alien) + goto fail; + } - new_shared = alloc_arraycache(node, + new_shared = NULL; + if (cachep->shared) { + new_shared = alloc_arraycache(node, cachep->shared*cachep->batchcount, 0xbaadf00d); - if (!new_shared) { - free_alien_cache(new_alien); - goto fail; + if (!new_shared) { + free_alien_cache(new_alien); + goto fail; + } } l3 = cachep->nodelists[node]; @@ -3553,22 +3964,26 @@ static void do_ccupdate_local(void *info) static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount, int shared) { - struct ccupdate_struct new; - int i, err; + struct ccupdate_struct *new; + int i; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return -ENOMEM; - memset(&new.new, 0, sizeof(new.new)); for_each_online_cpu(i) { - new.new[i] = alloc_arraycache(cpu_to_node(i), limit, + new->new[i] = alloc_arraycache(cpu_to_node(i), limit, batchcount); - if (!new.new[i]) { + if (!new->new[i]) { for (i--; i >= 0; i--) - kfree(new.new[i]); + kfree(new->new[i]); + kfree(new); return -ENOMEM; } } - new.cachep = cachep; + new->cachep = cachep; - on_each_cpu(do_ccupdate_local, (void *)&new, 1, 1); + on_each_cpu(do_ccupdate_local, (void *)new, 1, 1); check_irq_on(); cachep->batchcount = batchcount; @@ -3576,7 +3991,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, cachep->shared = shared; for_each_online_cpu(i) { - struct array_cache *ccold = new.new[i]; + struct array_cache *ccold = new->new[i]; if (!ccold) continue; spin_lock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock); @@ -3584,18 +3999,12 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, spin_unlock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock); kfree(ccold); } - - err = alloc_kmemlist(cachep); - if (err) { - printk(KERN_ERR "alloc_kmemlist failed for %s, error %d.\n", - cachep->name, -err); - BUG(); - } - return 0; + kfree(new); + return alloc_kmemlist(cachep); } /* Called with cache_chain_mutex held always */ -static void enable_cpucache(struct kmem_cache *cachep) +static int enable_cpucache(struct kmem_cache *cachep) { int err; int limit, shared; @@ -3630,10 +4039,8 @@ static void enable_cpucache(struct kmem_cache *cachep) * to a larger limit. Thus disabled by default. */ shared = 0; -#ifdef CONFIG_SMP - if (cachep->buffer_size <= PAGE_SIZE) + if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1) shared = 8; -#endif #if DEBUG /* @@ -3647,6 +4054,7 @@ static void enable_cpucache(struct kmem_cache *cachep) if (err) printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n", cachep->name, -err); + return err; } /* @@ -3680,7 +4088,7 @@ void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, /** * cache_reap - Reclaim memory from caches. - * @unused: unused parameter + * @w: work descriptor * * Called from workqueue/eventd every few seconds. * Purpose: @@ -3690,26 +4098,19 @@ void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, * If we cannot acquire the cache chain mutex then just give up - we'll try * again on the next iteration. */ -static void cache_reap(void *unused) +static void cache_reap(struct work_struct *w) { - struct list_head *walk; + struct kmem_cache *searchp; struct kmem_list3 *l3; int node = numa_node_id(); + struct delayed_work *work = + container_of(w, struct delayed_work, work); - if (!mutex_trylock(&cache_chain_mutex)) { + if (!mutex_trylock(&cache_chain_mutex)) /* Give up. Setup the next iteration. */ - schedule_delayed_work(&__get_cpu_var(reap_work), - REAPTIMEOUT_CPUC); - return; - } - - list_for_each(walk, &cache_chain) { - struct kmem_cache *searchp; - struct list_head *p; - int tofree; - struct slab *slabp; + goto out; - searchp = list_entry(walk, struct kmem_cache, next); + list_for_each_entry(searchp, &cache_chain, next) { check_irq_on(); /* @@ -3734,49 +4135,24 @@ static void cache_reap(void *unused) drain_array(searchp, l3, l3->shared, 0, node); - if (l3->free_touched) { + if (l3->free_touched) l3->free_touched = 0; - goto next; - } - - tofree = (l3->free_limit + 5 * searchp->num - 1) / - (5 * searchp->num); - do { - /* - * Do not lock if there are no free blocks. - */ - if (list_empty(&l3->slabs_free)) - break; + else { + int freed; - spin_lock_irq(&l3->list_lock); - p = l3->slabs_free.next; - if (p == &(l3->slabs_free)) { - spin_unlock_irq(&l3->list_lock); - break; - } - - slabp = list_entry(p, struct slab, list); - BUG_ON(slabp->inuse); - list_del(&slabp->list); - STATS_INC_REAPED(searchp); - - /* - * Safe to drop the lock. The slab is no longer linked - * to the cache. searchp cannot disappear, we hold - * cache_chain_lock - */ - l3->free_objects -= searchp->num; - spin_unlock_irq(&l3->list_lock); - slab_destroy(searchp, slabp); - } while (--tofree > 0); + freed = drain_freelist(searchp, l3, (l3->free_limit + + 5 * searchp->num - 1) / (5 * searchp->num)); + STATS_ADD_REAPED(searchp, freed); + } next: cond_resched(); } check_irq_on(); mutex_unlock(&cache_chain_mutex); next_reap_node(); +out: /* Set up the next iteration */ - schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC); + schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC)); } #ifdef CONFIG_PROC_FS @@ -3837,7 +4213,6 @@ static void s_stop(struct seq_file *m, void *p) static int s_show(struct seq_file *m, void *p) { struct kmem_cache *cachep = p; - struct list_head *q; struct slab *slabp; unsigned long active_objs; unsigned long num_objs; @@ -3858,15 +4233,13 @@ static int s_show(struct seq_file *m, void *p) check_irq_on(); spin_lock_irq(&l3->list_lock); - list_for_each(q, &l3->slabs_full) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_full, list) { if (slabp->inuse != cachep->num && !error) error = "slabs_full accounting error"; active_objs += cachep->num; active_slabs++; } - list_for_each(q, &l3->slabs_partial) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_partial, list) { if (slabp->inuse == cachep->num && !error) error = "slabs_partial inuse accounting error"; if (!slabp->inuse && !error) @@ -3874,8 +4247,7 @@ static int s_show(struct seq_file *m, void *p) active_objs += slabp->inuse; active_slabs++; } - list_for_each(q, &l3->slabs_free) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_free, list) { if (slabp->inuse && !error) error = "slabs_free/inuse accounting error"; num_slabs++; @@ -3948,7 +4320,7 @@ static int s_show(struct seq_file *m, void *p) * + further values on SMP and with statistics enabled */ -struct seq_operations slabinfo_op = { +const struct seq_operations slabinfo_op = { .start = s_start, .next = s_next, .stop = s_stop, @@ -3968,7 +4340,7 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer, { char kbuf[MAX_SLABINFO_WRITE + 1], *tmp; int limit, batchcount, shared, res; - struct list_head *p; + struct kmem_cache *cachep; if (count > MAX_SLABINFO_WRITE) return -EINVAL; @@ -3987,10 +4359,7 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer, /* Find the cache in the chain of caches. */ mutex_lock(&cache_chain_mutex); res = -EINVAL; - list_for_each(p, &cache_chain) { - struct kmem_cache *cachep; - - cachep = list_entry(p, struct kmem_cache, next); + list_for_each_entry(cachep, &cache_chain, next) { if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || batchcount > limit || shared < 0) { @@ -4072,16 +4441,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s) static void show_symbol(struct seq_file *m, unsigned long address) { #ifdef CONFIG_KALLSYMS - char *modname; - const char *name; unsigned long offset, size; - char namebuf[KSYM_NAME_LEN+1]; - - name = kallsyms_lookup(address, &size, &offset, &modname, namebuf); + char modname[MODULE_NAME_LEN + 1], name[KSYM_NAME_LEN + 1]; - if (name) { + if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) { seq_printf(m, "%s+%#lx/%#lx", name, offset, size); - if (modname) + if (modname[0]) seq_printf(m, " [%s]", modname); return; } @@ -4092,7 +4457,6 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { struct kmem_cache *cachep = p; - struct list_head *q; struct slab *slabp; struct kmem_list3 *l3; const char *name; @@ -4117,14 +4481,10 @@ static int leaks_show(struct seq_file *m, void *p) check_irq_on(); spin_lock_irq(&l3->list_lock); - list_for_each(q, &l3->slabs_full) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_full, list) handle_slab(n, cachep, slabp); - } - list_for_each(q, &l3->slabs_partial) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_partial, list) handle_slab(n, cachep, slabp); - } spin_unlock_irq(&l3->list_lock); } name = cachep->name; @@ -4150,10 +4510,11 @@ static int leaks_show(struct seq_file *m, void *p) show_symbol(m, n[2*i+2]); seq_putc(m, '\n'); } + return 0; } -struct seq_operations slabstats_op = { +const struct seq_operations slabstats_op = { .start = leaks_start, .next = s_next, .stop = s_stop, @@ -4174,7 +4535,7 @@ struct seq_operations slabstats_op = { * allocated with either kmalloc() or kmem_cache_alloc(). The object * must not be freed during the duration of the call. */ -unsigned int ksize(const void *objp) +size_t ksize(const void *objp) { if (unlikely(objp == NULL)) return 0;