diff options
Diffstat (limited to 'mm/slab.c')
-rw-r--r-- | mm/slab.c | 265 |
1 files changed, 110 insertions, 155 deletions
diff --git a/mm/slab.c b/mm/slab.c index ca3849fe0584..87c55b0e3e0e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -570,9 +570,9 @@ static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ -static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES]; -static struct kmem_cache cache_cache = { - .nodelists = cache_cache_nodelists, +static struct kmem_list3 *kmem_cache_nodelists[MAX_NUMNODES]; +static struct kmem_cache kmem_cache_boot = { + .nodelists = kmem_cache_nodelists, .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, @@ -795,6 +795,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, *left_over = slab_size - nr_objs*buffer_size - mgmt_size; } +#if DEBUG #define slab_error(cachep, msg) __slab_error(__func__, cachep, msg) static void __slab_error(const char *function, struct kmem_cache *cachep, @@ -805,6 +806,7 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, dump_stack(); add_taint(TAINT_BAD_PAGE); } +#endif /* * By default on NUMA we use alien caches to stage the freeing of @@ -969,7 +971,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, } /* The caller cannot use PFMEMALLOC objects, find another one */ - for (i = 1; i < ac->avail; i++) { + for (i = 0; i < ac->avail; i++) { /* If a !PFMEMALLOC object is found, swap them */ if (!is_obj_pfmemalloc(ac->entry[i])) { objp = ac->entry[i]; @@ -986,7 +988,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, l3 = cachep->nodelists[numa_mem_id()]; if (!list_empty(&l3->slabs_free) && force_refill) { struct slab *slabp = virt_to_slab(objp); - ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem)); + ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem)); clear_obj_pfmemalloc(&objp); recheck_pfmemalloc_active(cachep, ac); return objp; @@ -1018,7 +1020,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, { if (unlikely(pfmemalloc_active)) { /* Some pfmemalloc slabs exist, check if this is one */ - struct page *page = virt_to_page(objp); + struct page *page = virt_to_head_page(objp); if (PageSlabPfmemalloc(page)) set_obj_pfmemalloc(&objp); } @@ -1587,15 +1589,17 @@ void __init kmem_cache_init(void) int order; int node; + kmem_cache = &kmem_cache_boot; + if (num_possible_nodes() == 1) use_alien_caches = 0; for (i = 0; i < NUM_INIT_LISTS; i++) { kmem_list3_init(&initkmem_list3[i]); if (i < MAX_NUMNODES) - cache_cache.nodelists[i] = NULL; + kmem_cache->nodelists[i] = NULL; } - set_up_list3s(&cache_cache, CACHE_CACHE); + set_up_list3s(kmem_cache, CACHE_CACHE); /* * Fragmentation resistance on low memory - only use bigger @@ -1607,9 +1611,9 @@ void __init kmem_cache_init(void) /* Bootstrap is tricky, because several objects are allocated * from caches that do not exist yet: - * 1) initialize the cache_cache cache: it contains the struct - * kmem_cache structures of all caches, except cache_cache itself: - * cache_cache is statically allocated. + * 1) initialize the kmem_cache cache: it contains the struct + * kmem_cache structures of all caches, except kmem_cache itself: + * kmem_cache is statically allocated. * Initially an __init data area is used for the head array and the * kmem_list3 structures, it's replaced with a kmalloc allocated * array at the end of the bootstrap. @@ -1618,43 +1622,43 @@ void __init kmem_cache_init(void) * An __init data area is used for the head array. * 3) Create the remaining kmalloc caches, with minimally sized * head arrays. - * 4) Replace the __init data head arrays for cache_cache and the first + * 4) Replace the __init data head arrays for kmem_cache and the first * kmalloc cache with kmalloc allocated arrays. - * 5) Replace the __init data for kmem_list3 for cache_cache and + * 5) Replace the __init data for kmem_list3 for kmem_cache and * the other cache's with kmalloc allocated memory. * 6) Resize the head arrays of the kmalloc caches to their final sizes. */ node = numa_mem_id(); - /* 1) create the cache_cache */ + /* 1) create the kmem_cache */ INIT_LIST_HEAD(&slab_caches); - list_add(&cache_cache.list, &slab_caches); - cache_cache.colour_off = cache_line_size(); - cache_cache.array[smp_processor_id()] = &initarray_cache.cache; - cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; + list_add(&kmem_cache->list, &slab_caches); + kmem_cache->colour_off = cache_line_size(); + kmem_cache->array[smp_processor_id()] = &initarray_cache.cache; + kmem_cache->nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; /* * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + kmem_cache->size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + nr_node_ids * sizeof(struct kmem_list3 *); - cache_cache.object_size = cache_cache.size; - cache_cache.size = ALIGN(cache_cache.size, + kmem_cache->object_size = kmem_cache->size; + kmem_cache->size = ALIGN(kmem_cache->object_size, cache_line_size()); - cache_cache.reciprocal_buffer_size = - reciprocal_value(cache_cache.size); + kmem_cache->reciprocal_buffer_size = + reciprocal_value(kmem_cache->size); for (order = 0; order < MAX_ORDER; order++) { - cache_estimate(order, cache_cache.size, - cache_line_size(), 0, &left_over, &cache_cache.num); - if (cache_cache.num) + cache_estimate(order, kmem_cache->size, + cache_line_size(), 0, &left_over, &kmem_cache->num); + if (kmem_cache->num) break; } - BUG_ON(!cache_cache.num); - cache_cache.gfporder = order; - cache_cache.colour = left_over / cache_cache.colour_off; - cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) + + BUG_ON(!kmem_cache->num); + kmem_cache->gfporder = order; + kmem_cache->colour = left_over / kmem_cache->colour_off; + kmem_cache->slab_size = ALIGN(kmem_cache->num * sizeof(kmem_bufctl_t) + sizeof(struct slab), cache_line_size()); /* 2+3) create the kmalloc caches */ @@ -1667,19 +1671,22 @@ void __init kmem_cache_init(void) * bug. */ - sizes[INDEX_AC].cs_cachep = __kmem_cache_create(names[INDEX_AC].name, - sizes[INDEX_AC].cs_size, - ARCH_KMALLOC_MINALIGN, - ARCH_KMALLOC_FLAGS|SLAB_PANIC, - NULL); + sizes[INDEX_AC].cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + sizes[INDEX_AC].cs_cachep->name = names[INDEX_AC].name; + sizes[INDEX_AC].cs_cachep->size = sizes[INDEX_AC].cs_size; + sizes[INDEX_AC].cs_cachep->object_size = sizes[INDEX_AC].cs_size; + sizes[INDEX_AC].cs_cachep->align = ARCH_KMALLOC_MINALIGN; + __kmem_cache_create(sizes[INDEX_AC].cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC); + list_add(&sizes[INDEX_AC].cs_cachep->list, &slab_caches); if (INDEX_AC != INDEX_L3) { - sizes[INDEX_L3].cs_cachep = - __kmem_cache_create(names[INDEX_L3].name, - sizes[INDEX_L3].cs_size, - ARCH_KMALLOC_MINALIGN, - ARCH_KMALLOC_FLAGS|SLAB_PANIC, - NULL); + sizes[INDEX_L3].cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + sizes[INDEX_L3].cs_cachep->name = names[INDEX_L3].name; + sizes[INDEX_L3].cs_cachep->size = sizes[INDEX_L3].cs_size; + sizes[INDEX_L3].cs_cachep->object_size = sizes[INDEX_L3].cs_size; + sizes[INDEX_L3].cs_cachep->align = ARCH_KMALLOC_MINALIGN; + __kmem_cache_create(sizes[INDEX_L3].cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC); + list_add(&sizes[INDEX_L3].cs_cachep->list, &slab_caches); } slab_early_init = 0; @@ -1693,20 +1700,23 @@ void __init kmem_cache_init(void) * allow tighter packing of the smaller caches. */ if (!sizes->cs_cachep) { - sizes->cs_cachep = __kmem_cache_create(names->name, - sizes->cs_size, - ARCH_KMALLOC_MINALIGN, - ARCH_KMALLOC_FLAGS|SLAB_PANIC, - NULL); + sizes->cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + sizes->cs_cachep->name = names->name; + sizes->cs_cachep->size = sizes->cs_size; + sizes->cs_cachep->object_size = sizes->cs_size; + sizes->cs_cachep->align = ARCH_KMALLOC_MINALIGN; + __kmem_cache_create(sizes->cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC); + list_add(&sizes->cs_cachep->list, &slab_caches); } #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); + sizes->cs_dmacachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); + sizes->cs_dmacachep->name = names->name_dma; + sizes->cs_dmacachep->size = sizes->cs_size; + sizes->cs_dmacachep->object_size = sizes->cs_size; + sizes->cs_dmacachep->align = ARCH_KMALLOC_MINALIGN; + __kmem_cache_create(sizes->cs_dmacachep, + ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA| SLAB_PANIC); + list_add(&sizes->cs_dmacachep->list, &slab_caches); #endif sizes++; names++; @@ -1717,15 +1727,15 @@ void __init kmem_cache_init(void) ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT); - BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache); - memcpy(ptr, cpu_cache_get(&cache_cache), + BUG_ON(cpu_cache_get(kmem_cache) != &initarray_cache.cache); + memcpy(ptr, cpu_cache_get(kmem_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; + kmem_cache->array[smp_processor_id()] = ptr; ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT); @@ -1746,7 +1756,7 @@ void __init kmem_cache_init(void) int nid; for_each_online_node(nid) { - init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid); + init_list(kmem_cache, &initkmem_list3[CACHE_CACHE + nid], nid); init_list(malloc_sizes[INDEX_AC].cs_cachep, &initkmem_list3[SIZE_AC + nid], nid); @@ -2195,27 +2205,6 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) } } -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 @@ -2352,9 +2341,6 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) * Cannot be called within a int, but can be interrupted. * The @ctor is run when new pages are allocated by the cache. * - * @name must be valid until the cache is destroyed. This implies that - * the module calling this has to destroy the cache before getting unloaded. - * * The flags are * * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) @@ -2367,13 +2353,13 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ -struct kmem_cache * -__kmem_cache_create (const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *)) +int +__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { size_t left_over, slab_size, ralign; - struct kmem_cache *cachep = NULL; gfp_t gfp; + int err; + size_t size = cachep->size; #if DEBUG #if FORCED_DEBUG @@ -2445,8 +2431,8 @@ __kmem_cache_create (const char *name, size_t size, size_t align, ralign = ARCH_SLAB_MINALIGN; } /* 3) caller mandated alignment */ - if (ralign < align) { - ralign = align; + if (ralign < cachep->align) { + ralign = cachep->align; } /* disable debug if necessary */ if (ralign > __alignof__(unsigned long long)) @@ -2454,21 +2440,14 @@ __kmem_cache_create (const char *name, size_t size, size_t align, /* * 4) Store it. */ - align = ralign; + cachep->align = ralign; if (slab_is_available()) gfp = GFP_KERNEL; else gfp = GFP_NOWAIT; - /* Get cache's description obj. */ - cachep = kmem_cache_zalloc(&cache_cache, gfp); - if (!cachep) - return NULL; - cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; - cachep->object_size = size; - cachep->align = align; #if DEBUG /* @@ -2492,8 +2471,9 @@ __kmem_cache_create (const char *name, size_t size, size_t align, } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) if (size >= malloc_sizes[INDEX_L3 + 1].cs_size - && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { - cachep->obj_offset += PAGE_SIZE - ALIGN(size, align); + && cachep->object_size > cache_line_size() + && ALIGN(size, cachep->align) < PAGE_SIZE) { + cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align); size = PAGE_SIZE; } #endif @@ -2513,18 +2493,15 @@ __kmem_cache_create (const char *name, size_t size, size_t align, */ flags |= CFLGS_OFF_SLAB; - size = ALIGN(size, align); + size = ALIGN(size, cachep->align); - left_over = calculate_slab_order(cachep, size, align, flags); + left_over = calculate_slab_order(cachep, size, cachep->align, flags); + + if (!cachep->num) + return -E2BIG; - if (!cachep->num) { - printk(KERN_ERR - "kmem_cache_create: couldn't create cache %s.\n", name); - kmem_cache_free(&cache_cache, cachep); - return NULL; - } slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) - + sizeof(struct slab), align); + + sizeof(struct slab), cachep->align); /* * If the slab has been placed off-slab, and we have enough space then @@ -2552,8 +2529,8 @@ __kmem_cache_create (const char *name, size_t size, size_t align, cachep->colour_off = cache_line_size(); /* Offset must be a multiple of the alignment. */ - if (cachep->colour_off < align) - cachep->colour_off = align; + if (cachep->colour_off < cachep->align) + cachep->colour_off = cachep->align; cachep->colour = left_over / cachep->colour_off; cachep->slab_size = slab_size; cachep->flags = flags; @@ -2574,12 +2551,11 @@ __kmem_cache_create (const char *name, size_t size, size_t align, */ BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache)); } - cachep->ctor = ctor; - cachep->name = name; - if (setup_cpu_cache(cachep, gfp)) { - __kmem_cache_destroy(cachep); - return NULL; + err = setup_cpu_cache(cachep, gfp); + if (err) { + __kmem_cache_shutdown(cachep); + return err; } if (flags & SLAB_DEBUG_OBJECTS) { @@ -2592,9 +2568,7 @@ __kmem_cache_create (const char *name, size_t size, size_t align, slab_set_debugobj_lock_classes(cachep); } - /* cache setup completed, link it into the list */ - list_add(&cachep->list, &slab_caches); - return cachep; + return 0; } #if DEBUG @@ -2753,49 +2727,29 @@ int kmem_cache_shrink(struct kmem_cache *cachep) } 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. - * - * 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 - * cache being allocated each time a module is loaded and unloaded, if the - * module doesn't have persistent in-kernel storage across loads and unloads. - * - * The cache must be empty before calling this function. - * - * The caller must guarantee that no one will allocate memory from the cache - * during the kmem_cache_destroy(). - */ -void kmem_cache_destroy(struct kmem_cache *cachep) +int __kmem_cache_shutdown(struct kmem_cache *cachep) { - BUG_ON(!cachep || in_interrupt()); + int i; + struct kmem_list3 *l3; + int rc = __cache_shrink(cachep); - /* Find the cache in the chain of caches. */ - get_online_cpus(); - mutex_lock(&slab_mutex); - /* - * the chain is never empty, cache_cache is never destroyed - */ - list_del(&cachep->list); - if (__cache_shrink(cachep)) { - slab_error(cachep, "Can't free all objects"); - list_add(&cachep->list, &slab_caches); - mutex_unlock(&slab_mutex); - put_online_cpus(); - return; - } + if (rc) + return rc; - if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) - rcu_barrier(); + for_each_online_cpu(i) + kfree(cachep->array[i]); - __kmem_cache_destroy(cachep); - mutex_unlock(&slab_mutex); - put_online_cpus(); + /* 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); + } + } + return 0; } -EXPORT_SYMBOL(kmem_cache_destroy); /* * Get the memory for a slab management obj. @@ -3246,6 +3200,7 @@ force_grow: /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); + node = numa_mem_id(); /* no objects in sight? abort */ if (!x && (ac->avail == 0 || force_refill)) @@ -3328,7 +3283,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags) { - if (cachep == &cache_cache) + if (cachep == kmem_cache) return false; return should_failslab(cachep->object_size, flags, cachep->flags); |