X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fslub.c;h=4996fc7195528ba931dda8c042da44b2501b083e;hb=1557aca7904ed6fadd22cdc3364754070bb3d3c3;hp=15960a09abb1422ed765c535585a85b602e34231;hpb=722f2a6c87f34ee0fd0130a8cf45f81e0705594a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/slub.c b/mm/slub.c index 15960a0..4996fc7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -142,6 +141,13 @@ SLAB_POISON | SLAB_STORE_USER) /* + * Debugging flags that require metadata to be stored in the slab. These get + * disabled when slub_debug=O is used and a cache's min order increases with + * metadata. + */ +#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) + +/* * Set of flags that will prevent slab merging */ #define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ @@ -179,12 +185,6 @@ static enum { SYSFS /* Sysfs up */ } slab_state = DOWN; -/* - * The slab allocator is initialized with interrupts disabled. Therefore, make - * sure early boot allocations don't accidentally enable interrupts. - */ -static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK; - /* A list of all slab caches on the system */ static DECLARE_RWSEM(slub_lock); static LIST_HEAD(slab_caches); @@ -332,6 +332,7 @@ static int slub_debug; #endif static char *slub_debug_slabs; +static int disable_higher_order_debug; /* * Object debugging @@ -653,7 +654,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); print_section("Padding", end - remainder, remainder); - restore_bytes(s, "slab padding", POISON_INUSE, start, end); + restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; } @@ -840,6 +841,11 @@ static inline unsigned long slabs_node(struct kmem_cache *s, int node) return atomic_long_read(&n->nr_slabs); } +static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) +{ + return atomic_long_read(&n->nr_slabs); +} + static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) { struct kmem_cache_node *n = get_node(s, node); @@ -978,6 +984,15 @@ static int __init setup_slub_debug(char *str) */ goto check_slabs; + if (tolower(*str) == 'o') { + /* + * Avoid enabling debugging on caches if its minimum order + * would increase as a result. + */ + disable_higher_order_debug = 1; + goto out; + } + slub_debug = 0; if (*str == '-') /* @@ -1028,8 +1043,8 @@ static unsigned long kmem_cache_flags(unsigned long objsize, * Enable debugging if selected on the kernel commandline. */ if (slub_debug && (!slub_debug_slabs || - strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)) == 0)) - flags |= slub_debug; + !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))) + flags |= slub_debug; return flags; } @@ -1056,8 +1071,12 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize, } #define slub_debug 0 +#define disable_higher_order_debug 0 + static inline unsigned long slabs_node(struct kmem_cache *s, int node) { return 0; } +static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) + { return 0; } static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) {} static inline void dec_slabs_node(struct kmem_cache *s, int node, @@ -1084,11 +1103,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; flags |= s->allocflags; - page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node, - oo); + /* + * Let the initial higher-order allocation fail under memory pressure + * so we fall-back to the minimum order allocation. + */ + alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; + + page = alloc_slab_page(alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; /* @@ -1103,8 +1128,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) } if (kmemcheck_enabled - && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) - { + && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); kmemcheck_alloc_shadow(page, oo_order(oo), flags, node); @@ -1514,6 +1538,69 @@ static inline int node_match(struct kmem_cache_cpu *c, int node) return 1; } +static int count_free(struct page *page) +{ + return page->objects - page->inuse; +} + +static unsigned long count_partial(struct kmem_cache_node *n, + int (*get_count)(struct page *)) +{ + unsigned long flags; + unsigned long x = 0; + struct page *page; + + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); + spin_unlock_irqrestore(&n->list_lock, flags); + return x; +} + +static inline unsigned long node_nr_objs(struct kmem_cache_node *n) +{ +#ifdef CONFIG_SLUB_DEBUG + return atomic_long_read(&n->total_objects); +#else + return 0; +#endif +} + +static noinline void +slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) +{ + int node; + + printk(KERN_WARNING + "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", + nid, gfpflags); + printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " + "default order: %d, min order: %d\n", s->name, s->objsize, + s->size, oo_order(s->oo), oo_order(s->min)); + + if (oo_order(s->min) > get_order(s->objsize)) + printk(KERN_WARNING " %s debugging increased min order, use " + "slub_debug=O to disable.\n", s->name); + + for_each_online_node(node) { + struct kmem_cache_node *n = get_node(s, node); + unsigned long nr_slabs; + unsigned long nr_objs; + unsigned long nr_free; + + if (!n) + continue; + + nr_free = count_partial(n, count_free); + nr_slabs = node_nr_slabs(n); + nr_objs = node_nr_objs(n); + + printk(KERN_WARNING + " node %d: slabs: %ld, objs: %ld, free: %ld\n", + node, nr_slabs, nr_objs, nr_free); + } +} + /* * Slow path. The lockless freelist is empty or we need to perform * debugging duties. @@ -1595,6 +1682,8 @@ new_slab: c->page = new; goto load_freelist; } + if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) + slab_out_of_memory(s, gfpflags, node); return NULL; debug: if (!alloc_debug_processing(s, c->page, object, addr)) @@ -1624,7 +1713,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, unsigned long flags; unsigned int objsize; - gfpflags &= slab_gfp_mask; + gfpflags &= gfp_allowed_mask; lockdep_trace_alloc(gfpflags); might_sleep_if(gfpflags & __GFP_WAIT); @@ -1934,7 +2023,7 @@ static inline int calculate_order(int size) return order; fraction /= 2; } - min_objects --; + min_objects--; } /* @@ -2024,8 +2113,8 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s) */ #define NR_KMEM_CACHE_CPU 100 -static DEFINE_PER_CPU(struct kmem_cache_cpu, - kmem_cache_cpu)[NR_KMEM_CACHE_CPU]; +static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU], + kmem_cache_cpu); static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free); static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS); @@ -2333,6 +2422,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * on bootup. */ align = calculate_alignment(flags, align, s->objsize); + s->align = align; /* * SLUB stores one object immediately after another beginning from @@ -2385,6 +2475,18 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, if (!calculate_sizes(s, -1)) goto error; + if (disable_higher_order_debug) { + /* + * Disable debugging flags that store metadata if the min slab + * order increased. + */ + if (get_order(s->size) > get_order(s->objsize)) { + s->flags &= ~DEBUG_METADATA_FLAGS; + s->offset = 0; + if (!calculate_sizes(s, -1)) + goto error; + } + } /* * The larger the object size is, the more pages we want on the partial @@ -2537,6 +2639,8 @@ void kmem_cache_destroy(struct kmem_cache *s) "still has objects.\n", s->name, __func__); dump_stack(); } + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); sysfs_slab_remove(s); } else up_write(&slub_lock); @@ -2636,6 +2740,7 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags) struct kmem_cache *s; char *text; size_t realsize; + unsigned long slabflags; s = kmalloc_caches_dma[index]; if (s) @@ -2657,10 +2762,18 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags) (unsigned int)realsize); s = kmalloc(kmem_size, flags & ~SLUB_DMA); + /* + * Must defer sysfs creation to a workqueue because we don't know + * what context we are called from. Before sysfs comes up, we don't + * need to do anything because our sysfs initcall will start by + * adding all existing slabs to sysfs. + */ + slabflags = SLAB_CACHE_DMA|SLAB_NOTRACK; + if (slab_state >= SYSFS) + slabflags |= __SYSFS_ADD_DEFERRED; + if (!s || !text || !kmem_cache_open(s, flags, text, - realsize, ARCH_KMALLOC_MINALIGN, - SLAB_CACHE_DMA|SLAB_NOTRACK|__SYSFS_ADD_DEFERRED, - NULL)) { + realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) { kfree(s); kfree(text); goto unlock_out; @@ -2669,7 +2782,8 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags) list_add(&s->list, &slab_caches); kmalloc_caches_dma[index] = s; - schedule_work(&sysfs_add_work); + if (slab_state >= SYSFS) + schedule_work(&sysfs_add_work); unlock_out: up_write(&slub_lock); @@ -2711,6 +2825,11 @@ static s8 size_index[24] = { 2 /* 192 */ }; +static inline int size_index_elem(size_t bytes) +{ + return (bytes - 1) / 8; +} + static struct kmem_cache *get_slab(size_t size, gfp_t flags) { int index; @@ -2719,7 +2838,7 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags) if (!size) return ZERO_SIZE_PTR; - index = size_index[(size - 1) / 8]; + index = size_index[size_index_elem(size)]; } else index = fls(size - 1); @@ -2755,13 +2874,15 @@ EXPORT_SYMBOL(__kmalloc); static void *kmalloc_large_node(size_t size, gfp_t flags, int node) { struct page *page; + void *ptr = NULL; flags |= __GFP_COMP | __GFP_NOTRACK; page = alloc_pages_node(node, flags, get_order(size)); if (page) - return page_address(page); - else - return NULL; + ptr = page_address(page); + + kmemleak_alloc(ptr, size, 1, flags); + return ptr; } #ifdef CONFIG_NUMA @@ -2846,6 +2967,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); + kmemleak_free(x); put_page(page); return; } @@ -3074,10 +3196,12 @@ void __init kmem_cache_init(void) slab_state = PARTIAL; /* Caches that are not of the two-to-the-power-of size */ - if (KMALLOC_MIN_SIZE <= 64) { + if (KMALLOC_MIN_SIZE <= 32) { create_kmalloc_cache(&kmalloc_caches[1], "kmalloc-96", 96, GFP_NOWAIT); caches++; + } + if (KMALLOC_MIN_SIZE <= 64) { create_kmalloc_cache(&kmalloc_caches[2], "kmalloc-192", 192, GFP_NOWAIT); caches++; @@ -3104,17 +3228,28 @@ void __init kmem_cache_init(void) BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); - for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) - size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW; + for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { + int elem = size_index_elem(i); + if (elem >= ARRAY_SIZE(size_index)) + break; + size_index[elem] = KMALLOC_SHIFT_LOW; + } - if (KMALLOC_MIN_SIZE == 128) { + if (KMALLOC_MIN_SIZE == 64) { + /* + * The 96 byte size cache is not used if the alignment + * is 64 byte. + */ + for (i = 64 + 8; i <= 96; i += 8) + size_index[size_index_elem(i)] = 7; + } else if (KMALLOC_MIN_SIZE == 128) { /* * The 192 byte sized cache is not used if the alignment * is 128 byte. Redirect kmalloc to use the 256 byte cache * instead. */ for (i = 128 + 8; i <= 192; i += 8) - size_index[(i - 1) / 8] = 8; + size_index[size_index_elem(i)] = 8; } slab_state = UP; @@ -3142,10 +3277,6 @@ void __init kmem_cache_init(void) void __init kmem_cache_init_late(void) { - /* - * Interrupts are enabled now so all GFP allocations are safe. - */ - slab_gfp_mask = __GFP_BITS_MASK; } /* @@ -3214,6 +3345,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, { struct kmem_cache *s; + if (WARN_ON(!name)) + return NULL; + down_write(&slub_lock); s = find_mergeable(size, align, flags, name, ctor); if (s) { @@ -3368,20 +3502,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, } #ifdef CONFIG_SLUB_DEBUG -static unsigned long count_partial(struct kmem_cache_node *n, - int (*get_count)(struct page *)) -{ - unsigned long flags; - unsigned long x = 0; - struct page *page; - - spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, lru) - x += get_count(page); - spin_unlock_irqrestore(&n->list_lock, flags); - return x; -} - static int count_inuse(struct page *page) { return page->inuse; @@ -3392,11 +3512,6 @@ static int count_total(struct page *page) return page->objects; } -static int count_free(struct page *page) -{ - return page->objects - page->inuse; -} - static int validate_slab(struct kmem_cache *s, struct page *page, unsigned long *map) { @@ -3765,7 +3880,7 @@ static int list_locations(struct kmem_cache *s, char *buf, to_cpumask(l->cpus)); } - if (num_online_nodes() > 1 && !nodes_empty(l->nodes) && + if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " nodes="); len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50, @@ -4484,8 +4599,11 @@ static int sysfs_slab_add(struct kmem_cache *s) } err = sysfs_create_group(&s->kobj, &slab_attr_group); - if (err) + if (err) { + kobject_del(&s->kobj); + kobject_put(&s->kobj); return err; + } kobject_uevent(&s->kobj, KOBJ_ADD); if (!unmergeable) { /* Setup first alias */ @@ -4667,7 +4785,7 @@ static const struct file_operations proc_slabinfo_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations); + proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations); return 0; } module_init(slab_proc_init);