/* * linux/mm/slab.c * Written by Mark Hemment, 1996/97. * (markhe@nextd.demon.co.uk) * * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli * * Major cleanup, different bufctl logic, per-cpu arrays * (c) 2000 Manfred Spraul * * Cleanup, make the head arrays unconditional, preparation for NUMA * (c) 2002 Manfred Spraul * * An implementation of the Slab Allocator as described in outline in; * UNIX Internals: The New Frontiers by Uresh Vahalia * Pub: Prentice Hall ISBN 0-13-101908-2 * or with a little more detail in; * The Slab Allocator: An Object-Caching Kernel Memory Allocator * Jeff Bonwick (Sun Microsystems). * Presented at: USENIX Summer 1994 Technical Conference * * The memory is organized in caches, one cache for each object type. * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct) * Each cache consists out of many slabs (they are small (usually one * page long) and always contiguous), and each slab contains multiple * initialized objects. * * This means, that your constructor is used only for newly allocated * slabs and you must pass objects with the same initializations to * kmem_cache_free. * * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM, * normal). If you need a special memory type, then must create a new * cache for that memory type. * * In order to reduce fragmentation, the slabs are sorted in 3 groups: * full slabs with 0 free objects * partial slabs * empty slabs with no allocated objects * * If partial slabs exist, then new allocations come from these slabs, * otherwise from empty slabs or new slabs are allocated. * * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache * during kmem_cache_destroy(). The caller must prevent concurrent allocs. * * Each cache has a short per-cpu head array, most allocs * and frees go into that array, and if that array overflows, then 1/2 * of the entries in the array are given back into the global cache. * The head array is strictly LIFO and should improve the cache hit rates. * On SMP, it additionally reduces the spinlock operations. * * The c_cpuarray may not be read with enabled local interrupts - * it's changed with a smp_call_function(). * * SMP synchronization: * constructors and destructors are called without any locking. * Several members in struct kmem_cache and struct slab never change, they * are accessed without any locking. * The per-cpu arrays are never accessed from the wrong cpu, no locking, * and local interrupts are disabled so slab code is preempt-safe. * The non-constant members are protected with a per-cache irq spinlock. * * Many thanks to Mark Hemment, who wrote another per-cpu slab patch * in 2000 - many ideas in the current implementation are derived from * his patch. * * Further notes from the original documentation: * * 11 April '97. Started multi-threading - markhe * The global cache-chain is protected by the mutex 'slab_mutex'. * The sem is only needed when accessing/extending the cache-chain, which * can never happen inside an interrupt (kmem_cache_create(), * kmem_cache_shrink() and kmem_cache_reap()). * * At present, each engine can be growing a cache. This should be blocked. * * 15 March 2005. NUMA slab allocator. * Shai Fultheim . * Shobhit Dayal * Alok N Kataria * Christoph Lameter * * Modified the slab allocator to be node aware on NUMA systems. * Each node has its own list of partial, free and full slabs. * All object allocations for a node occur from node specific slab lists. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" #include "slab.h" /* * 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. * 0 for faster, smaller code (especially in the critical paths). * * FORCED_DEBUG - 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible) */ #ifdef CONFIG_DEBUG_SLAB #define DEBUG 1 #define STATS 1 #define FORCED_DEBUG 1 #else #define DEBUG 0 #define STATS 0 #define FORCED_DEBUG 0 #endif /* Shouldn't this be in a header file somewhere? */ #define BYTES_PER_WORD sizeof(void *) #define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long)) #ifndef ARCH_KMALLOC_FLAGS #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN #endif /* * true if a page was allocated from pfmemalloc reserves for network-based * swap */ static bool pfmemalloc_active __read_mostly; /* * kmem_bufctl_t: * * Bufctl's are used for linking objs within a slab * linked offsets. * * This implementation relies on "struct page" for locating the cache & * slab an object belongs to. * This allows the bufctl structure to be small (one int), but limits * the number of objects a slab (not a cache) can contain when off-slab * bufctls are used. The limit is the size of the largest general cache * that does not use off-slab slabs. * For 32bit archs with 4 kB pages, is this 56. * This is not serious, as it is only for large objects, when it is unwise * to have too many per slab. * Note: This limit can be raised by introducing a general cache whose size * is less than 512 (PAGE_SIZE<<3), but greater than 256. */ typedef unsigned int kmem_bufctl_t; #define BUFCTL_END (((kmem_bufctl_t)(~0U))-0) #define BUFCTL_FREE (((kmem_bufctl_t)(~0U))-1) #define BUFCTL_ACTIVE (((kmem_bufctl_t)(~0U))-2) #define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3) /* * struct slab_rcu * * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to * arrange for kmem_freepages to be called via RCU. This is useful if * we need to approach a kernel structure obliquely, from its address * obtained without the usual locking. We can lock the structure to * stabilize it and check it's still at the given address, only if we * can be sure that the memory has not been meanwhile reused for some * other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. */ struct slab_rcu { struct rcu_head head; struct kmem_cache *cachep; void *addr; }; /* * struct slab * * Manages the objs in a slab. Placed either at the beginning of mem allocated * for a slab, or allocated from an general cache. * Slabs are chained into three list: fully used, partial, fully free slabs. */ struct slab { union { struct { struct list_head list; unsigned long colouroff; void *s_mem; /* including colour offset */ unsigned int inuse; /* num of objs active in slab */ kmem_bufctl_t free; unsigned short nodeid; }; struct slab_rcu __slab_cover_slab_rcu; }; }; /* * struct array_cache * * Purpose: * - LIFO ordering, to hand out cache-warm objects from _alloc * - reduce the number of linked list operations * - reduce spinlock operations * * The limit is stored in the per-cpu structure to reduce the data cache * footprint. * */ struct array_cache { unsigned int avail; unsigned int limit; unsigned int batchcount; unsigned int touched; spinlock_t lock; void *entry[]; /* * Must have this definition in here for the proper * alignment of array_cache. Also simplifies accessing * the entries. * * Entries should not be directly dereferenced as * entries belonging to slabs marked pfmemalloc will * have the lower bits set SLAB_OBJ_PFMEMALLOC */ }; #define SLAB_OBJ_PFMEMALLOC 1 static inline bool is_obj_pfmemalloc(void *objp) { return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC; } static inline void set_obj_pfmemalloc(void **objp) { *objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC); return; } static inline void clear_obj_pfmemalloc(void **objp) { *objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC); } /* * bootstrap: The caches do not work without cpuarrays anymore, but the * cpuarrays are allocated from the generic caches... */ #define BOOT_CPUCACHE_ENTRIES 1 struct arraycache_init { struct array_cache cache; void *entries[BOOT_CPUCACHE_ENTRIES]; }; /* * Need this for bootstrapping a per node allocator. */ #define NUM_INIT_LISTS (3 * MAX_NUMNODES) static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS]; #define CACHE_CACHE 0 #define SIZE_AC MAX_NUMNODES #define SIZE_NODE (2 * MAX_NUMNODES) static int drain_freelist(struct kmem_cache *cache, struct kmem_cache_node *n, int tofree); static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node); static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp); static void cache_reap(struct work_struct *unused); static int slab_early_init = 1; #define INDEX_AC kmalloc_index(sizeof(struct arraycache_init)) #define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node)) static void kmem_cache_node_init(struct kmem_cache_node *parent) { INIT_LIST_HEAD(&parent->slabs_full); INIT_LIST_HEAD(&parent->slabs_partial); INIT_LIST_HEAD(&parent->slabs_free); parent->shared = NULL; parent->alien = NULL; parent->colour_next = 0; spin_lock_init(&parent->list_lock); parent->free_objects = 0; parent->free_touched = 0; } #define MAKE_LIST(cachep, listp, slab, nodeid) \ do { \ INIT_LIST_HEAD(listp); \ list_splice(&(cachep->node[nodeid]->slab), listp); \ } while (0) #define MAKE_ALL_LISTS(cachep, ptr, nodeid) \ do { \ MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid); \ MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \ MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid); \ } while (0) #define CFLGS_OFF_SLAB (0x80000000UL) #define OFF_SLAB(x) ((x)->flags & CFLGS_OFF_SLAB) #define BATCHREFILL_LIMIT 16 /* * Optimization question: fewer reaps means less probability for unnessary * cpucache drain/refill cycles. * * OTOH the cpuarrays can contain lots of objects, * which could lock up otherwise freeable slabs. */ #define REAPTIMEOUT_CPUC (2*HZ) #define REAPTIMEOUT_LIST3 (4*HZ) #if STATS #define STATS_INC_ACTIVE(x) ((x)->num_active++) #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_ADD_REAPED(x,y) ((x)->reaped += (y)) #define STATS_SET_HIGH(x) \ do { \ if ((x)->num_active > (x)->high_mark) \ (x)->high_mark = (x)->num_active; \ } while (0) #define STATS_INC_ERR(x) ((x)->errors++) #define STATS_INC_NODEALLOCS(x) ((x)->node_allocs++) #define STATS_INC_NODEFREES(x) ((x)->node_frees++) #define STATS_INC_ACOVERFLOW(x) ((x)->node_overflow++) #define STATS_SET_FREEABLE(x, i) \ do { \ if ((x)->max_freeable < i) \ (x)->max_freeable = i; \ } while (0) #define STATS_INC_ALLOCHIT(x) atomic_inc(&(x)->allochit) #define STATS_INC_ALLOCMISS(x) atomic_inc(&(x)->allocmiss) #define STATS_INC_FREEHIT(x) atomic_inc(&(x)->freehit) #define STATS_INC_FREEMISS(x) atomic_inc(&(x)->freemiss) #else #define STATS_INC_ACTIVE(x) do { } while (0) #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_ADD_REAPED(x,y) do { (void)(y); } 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) #define STATS_INC_NODEFREES(x) do { } while (0) #define STATS_INC_ACOVERFLOW(x) do { } while (0) #define STATS_SET_FREEABLE(x, i) do { } while (0) #define STATS_INC_ALLOCHIT(x) do { } while (0) #define STATS_INC_ALLOCMISS(x) do { } while (0) #define STATS_INC_FREEHIT(x) do { } while (0) #define STATS_INC_FREEMISS(x) do { } while (0) #endif #if DEBUG /* * memory layout of objects: * 0 : objp * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that * the end of an object is aligned with the end of the real * allocation. Catches writes behind the end of the allocation. * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1: * redzone word. * cachep->obj_offset: The real object. * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] * cachep->size - 1* BYTES_PER_WORD: last caller address * [BYTES_PER_WORD long] */ static int obj_offset(struct kmem_cache *cachep) { return cachep->obj_offset; } static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); return (unsigned long long*) (objp + obj_offset(cachep) - sizeof(unsigned long long)); } 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 long *)(objp + cachep->size - sizeof(unsigned long long) - REDZONE_ALIGN); return (unsigned long long *) (objp + cachep->size - sizeof(unsigned long long)); } static void **dbg_userword(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_STORE_USER)); return (void **)(objp + cachep->size - BYTES_PER_WORD); } #else #define obj_offset(x) 0 #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 /* * Do not go above this order unless 0 objects fit into the slab or * overridden on the command line. */ #define SLAB_MAX_ORDER_HI 1 #define SLAB_MAX_ORDER_LO 0 static int slab_max_order = SLAB_MAX_ORDER_LO; static bool slab_max_order_set __initdata; static inline struct kmem_cache *virt_to_cache(const void *obj) { struct page *page = virt_to_head_page(obj); return page->slab_cache; } static inline struct slab *virt_to_slab(const void *obj) { struct page *page = virt_to_head_page(obj); VM_BUG_ON(!PageSlab(page)); return page->slab_page; } static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, unsigned int idx) { return slab->s_mem + cache->size * idx; } /* * We want to avoid an expensive divide : (offset / cache->size) * Using the fact that size is a constant for a particular cache, * we can replace (offset / cache->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) { u32 offset = (obj - slab->s_mem); return reciprocal_divide(offset, cache->reciprocal_buffer_size); } static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ static struct kmem_cache kmem_cache_boot = { .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, .size = sizeof(struct kmem_cache), .name = "kmem_cache", }; #define BAD_ALIEN_MAGIC 0x01020304ul #ifdef CONFIG_LOCKDEP /* * 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. * * 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 struct lock_class_key debugobj_l3_key; static struct lock_class_key debugobj_alc_key; static void slab_set_lock_classes(struct kmem_cache *cachep, struct lock_class_key *l3_key, struct lock_class_key *alc_key, int q) { struct array_cache **alc; struct kmem_cache_node *n; int r; n = cachep->node[q]; if (!n) return; lockdep_set_class(&n->list_lock, l3_key); alc = n->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) return; for_each_node(r) { if (alc[r]) lockdep_set_class(&alc[r]->lock, alc_key); } } static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node) { slab_set_lock_classes(cachep, &debugobj_l3_key, &debugobj_alc_key, node); } static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) { int node; for_each_online_node(node) slab_set_debugobj_lock_classes_node(cachep, node); } static void init_node_lock_keys(int q) { int i; if (slab_state < UP) return; for (i = 1; i < PAGE_SHIFT + MAX_ORDER; i++) { struct kmem_cache_node *n; struct kmem_cache *cache = kmalloc_caches[i]; if (!cache) continue; n = cache->node[q]; if (!n || OFF_SLAB(cache)) continue; slab_set_lock_classes(cache, &on_slab_l3_key, &on_slab_alc_key, q); } } static void on_slab_lock_classes_node(struct kmem_cache *cachep, int q) { if (!cachep->node[q]) return; slab_set_lock_classes(cachep, &on_slab_l3_key, &on_slab_alc_key, q); } static inline void on_slab_lock_classes(struct kmem_cache *cachep) { int node; VM_BUG_ON(OFF_SLAB(cachep)); for_each_node(node) on_slab_lock_classes_node(cachep, node); } static inline void init_lock_keys(void) { int node; for_each_node(node) init_node_lock_keys(node); } #else static void init_node_lock_keys(int q) { } static inline void init_lock_keys(void) { } static inline void on_slab_lock_classes(struct kmem_cache *cachep) { } static inline void on_slab_lock_classes_node(struct kmem_cache *cachep, int node) { } static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node) { } static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) { } #endif static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { return cachep->array[smp_processor_id()]; } static size_t slab_mgmt_size(size_t nr_objs, size_t align) { return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align); } /* * Calculate the number of objects and left-over bytes for a given buffer size. */ static void cache_estimate(unsigned long gfporder, size_t buffer_size, size_t align, int flags, size_t *left_over, unsigned int *num) { int nr_objs; size_t mgmt_size; size_t slab_size = PAGE_SIZE << gfporder; /* * The slab management structure can be either off the slab or * on it. For the latter case, the memory allocated for a * slab is used for: * * - The struct slab * - One kmem_bufctl_t for each object * - Padding to respect alignment of @align * - @buffer_size bytes for each object * * If the slab management structure is off the slab, then the * alignment will already be calculated into the size. Because * the slabs are all pages aligned, the objects will be at the * correct alignment when allocated. */ if (flags & CFLGS_OFF_SLAB) { mgmt_size = 0; nr_objs = slab_size / buffer_size; if (nr_objs > SLAB_LIMIT) nr_objs = SLAB_LIMIT; } else { /* * Ignore padding for the initial guess. The padding * is at most @align-1 bytes, and @buffer_size is at * least @align. In the worst case, this result will * be one greater than the number of objects that fit * into the memory allocation when taking the padding * into account. */ nr_objs = (slab_size - sizeof(struct slab)) / (buffer_size + sizeof(kmem_bufctl_t)); /* * This calculated number will be either the right * amount, or one greater than what we want. */ if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size > slab_size) nr_objs--; if (nr_objs > SLAB_LIMIT) nr_objs = SLAB_LIMIT; mgmt_size = slab_mgmt_size(nr_objs, align); } *num = nr_objs; *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, char *msg) { printk(KERN_ERR "slab error in %s(): cache `%s': %s\n", function, cachep->name, msg); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } #endif /* * 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); static int __init slab_max_order_setup(char *str) { get_option(&str, &slab_max_order); slab_max_order = slab_max_order < 0 ? 0 : min(slab_max_order, MAX_ORDER - 1); slab_max_order_set = true; return 1; } __setup("slab_max_order=", slab_max_order_setup); #ifdef CONFIG_NUMA /* * Special reaping functions for NUMA systems called from cache_reap(). * These take care of doing round robin flushing of alien caches (containing * objects freed on different nodes from which they were allocated) and the * flushing of remote pcps by calling drain_node_pages. */ static DEFINE_PER_CPU(unsigned long, slab_reap_node); static void init_reap_node(int cpu) { int node; node = next_node(cpu_to_mem(cpu), node_online_map); if (node == MAX_NUMNODES) node = first_node(node_online_map); per_cpu(slab_reap_node, cpu) = node; } static void next_reap_node(void) { int node = __this_cpu_read(slab_reap_node); node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); __this_cpu_write(slab_reap_node, node); } #else #define init_reap_node(cpu) do { } while (0) #define next_reap_node(void) do { } while (0) #endif /* * Initiate the reap timer running on the target CPU. We run at around 1 to 2Hz * via the workqueue/eventd. * Add the CPU number into the expiration time to minimize the possibility of * the CPUs getting into lockstep and contending for the global cache chain * lock. */ static void __cpuinit start_cpu_timer(int cpu) { struct delayed_work *reap_work = &per_cpu(slab_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->work.func == NULL) { init_reap_node(cpu); INIT_DEFERRABLE_WORK(reap_work, cache_reap); schedule_delayed_work_on(cpu, reap_work, __round_jiffies_relative(HZ, cpu)); } } static struct array_cache *alloc_arraycache(int node, int entries, int batchcount, gfp_t gfp) { int memsize = sizeof(void *) * entries + sizeof(struct array_cache); struct array_cache *nc = NULL; nc = kmalloc_node(memsize, gfp, node); /* * The array_cache structures contain pointers to free object. * However, when such objects are allocated or transferred to another * cache the pointers are not cleared and they could be counted as * valid references during a kmemleak scan. Therefore, kmemleak must * not scan such objects. */ kmemleak_no_scan(nc); if (nc) { nc->avail = 0; nc->limit = entries; nc->batchcount = batchcount; nc->touched = 0; spin_lock_init(&nc->lock); } return nc; } static inline bool is_slab_pfmemalloc(struct slab *slabp) { struct page *page = virt_to_page(slabp->s_mem); return PageSlabPfmemalloc(page); } /* Clears pfmemalloc_active if no slabs have pfmalloc set */ static void recheck_pfmemalloc_active(struct kmem_cache *cachep, struct array_cache *ac) { struct kmem_cache_node *n = cachep->node[numa_mem_id()]; struct slab *slabp; unsigned long flags; if (!pfmemalloc_active) return; spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(slabp, &n->slabs_full, list) if (is_slab_pfmemalloc(slabp)) goto out; list_for_each_entry(slabp, &n->slabs_partial, list) if (is_slab_pfmemalloc(slabp)) goto out; list_for_each_entry(slabp, &n->slabs_free, list) if (is_slab_pfmemalloc(slabp)) goto out; pfmemalloc_active = false; out: spin_unlock_irqrestore(&n->list_lock, flags); } static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, gfp_t flags, bool force_refill) { int i; void *objp = ac->entry[--ac->avail]; /* Ensure the caller is allowed to use objects from PFMEMALLOC slab */ if (unlikely(is_obj_pfmemalloc(objp))) { struct kmem_cache_node *n; if (gfp_pfmemalloc_allowed(flags)) { clear_obj_pfmemalloc(&objp); return objp; } /* The caller cannot use PFMEMALLOC objects, find another one */ 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]; ac->entry[i] = ac->entry[ac->avail]; ac->entry[ac->avail] = objp; return objp; } } /* * If there are empty slabs on the slabs_free list and we are * being forced to refill the cache, mark this one !pfmemalloc. */ n = cachep->node[numa_mem_id()]; if (!list_empty(&n->slabs_free) && force_refill) { struct slab *slabp = virt_to_slab(objp); ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem)); clear_obj_pfmemalloc(&objp); recheck_pfmemalloc_active(cachep, ac); return objp; } /* No !PFMEMALLOC objects available */ ac->avail++; objp = NULL; } return objp; } static inline void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, gfp_t flags, bool force_refill) { void *objp; if (unlikely(sk_memalloc_socks())) objp = __ac_get_obj(cachep, ac, flags, force_refill); else objp = ac->entry[--ac->avail]; return objp; } static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, void *objp) { if (unlikely(pfmemalloc_active)) { /* Some pfmemalloc slabs exist, check if this is one */ struct page *page = virt_to_head_page(objp); if (PageSlabPfmemalloc(page)) set_obj_pfmemalloc(&objp); } return objp; } static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, void *objp) { if (unlikely(sk_memalloc_socks())) objp = __ac_put_obj(cachep, ac, objp); ac->entry[ac->avail++] = objp; } /* * Transfer objects in one arraycache to another. * Locking must be handled by the caller. * * Return the number of entries transferred. */ static int transfer_objects(struct array_cache *to, struct array_cache *from, unsigned int max) { /* Figure out how many entries to transfer */ int nr = min3(from->avail, max, to->limit - to->avail); if (!nr) return 0; memcpy(to->entry + to->avail, from->entry + from->avail -nr, sizeof(void *) *nr); from->avail -= nr; to->avail += nr; return nr; } #ifndef CONFIG_NUMA #define drain_alien_cache(cachep, alien) do { } while (0) #define reap_alien(cachep, n) do { } while (0) static inline struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp) { 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, gfp_t gfp) { struct array_cache **ac_ptr; int memsize = sizeof(void *) * nr_node_ids; int i; if (limit > 1) limit = 12; ac_ptr = kzalloc_node(memsize, gfp, node); if (ac_ptr) { for_each_node(i) { if (i == node || !node_online(i)) continue; ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d, gfp); if (!ac_ptr[i]) { for (i--; i >= 0; i--) kfree(ac_ptr[i]); kfree(ac_ptr); return NULL; } } } return ac_ptr; } static void free_alien_cache(struct array_cache **ac_ptr) { int i; if (!ac_ptr) return; for_each_node(i) kfree(ac_ptr[i]); kfree(ac_ptr); } static void __drain_alien_cache(struct kmem_cache *cachep, struct array_cache *ac, int node) { struct kmem_cache_node *n = cachep->node[node]; if (ac->avail) { spin_lock(&n->list_lock); /* * Stuff objects into the remote nodes shared array first. * That way we could avoid the overhead of putting the objects * into the free lists and getting them back later. */ if (n->shared) transfer_objects(n->shared, ac, ac->limit); free_block(cachep, ac->entry, ac->avail, node); ac->avail = 0; spin_unlock(&n->list_lock); } } /* * Called from cache_reap() to regularly drain alien caches round robin. */ static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n) { int node = __this_cpu_read(slab_reap_node); if (n->alien) { struct array_cache *ac = n->alien[node]; if (ac && ac->avail && spin_trylock_irq(&ac->lock)) { __drain_alien_cache(cachep, ac, node); spin_unlock_irq(&ac->lock); } } } static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien) { int i = 0; struct array_cache *ac; unsigned long flags; for_each_online_node(i) { ac = alien[i]; if (ac) { spin_lock_irqsave(&ac->lock, flags); __drain_alien_cache(cachep, ac, i); spin_unlock_irqrestore(&ac->lock, flags); } } } static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) { struct slab *slabp = virt_to_slab(objp); int nodeid = slabp->nodeid; struct kmem_cache_node *n; struct array_cache *alien = NULL; int node; node = numa_mem_id(); /* * Make sure we are not freeing a object from another node to the array * cache on this cpu. */ if (likely(slabp->nodeid == node)) return 0; n = cachep->node[node]; STATS_INC_NODEFREES(cachep); if (n->alien && n->alien[nodeid]) { alien = n->alien[nodeid]; spin_lock(&alien->lock); if (unlikely(alien->avail == alien->limit)) { STATS_INC_ACOVERFLOW(cachep); __drain_alien_cache(cachep, alien, nodeid); } ac_put_obj(cachep, alien, objp); spin_unlock(&alien->lock); } else { spin_lock(&(cachep->node[nodeid])->list_lock); free_block(cachep, &objp, 1, nodeid); spin_unlock(&(cachep->node[nodeid])->list_lock); } return 1; } #endif /* * Allocates and initializes node for a node on each slab cache, used for * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node * will be allocated off-node since memory is not yet online for the new node. * When hotplugging memory or a cpu, existing node are not replaced if * already in use. * * Must hold slab_mutex. */ static int init_cache_node_node(int node) { struct kmem_cache *cachep; struct kmem_cache_node *n; const int memsize = sizeof(struct kmem_cache_node); list_for_each_entry(cachep, &slab_caches, list) { /* * Set up the size64 kmemlist for cpu before we can * begin anything. Make sure some other cpu on this * node has not already allocated this */ if (!cachep->node[node]) { n = kmalloc_node(memsize, GFP_KERNEL, node); if (!n) return -ENOMEM; kmem_cache_node_init(n); n->next_reap = jiffies + REAPTIMEOUT_LIST3 + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; /* * The l3s don't come and go as CPUs come and * go. slab_mutex is sufficient * protection here. */ cachep->node[node] = n; } spin_lock_irq(&cachep->node[node]->list_lock); cachep->node[node]->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; spin_unlock_irq(&cachep->node[node]->list_lock); } return 0; } static void __cpuinit cpuup_canceled(long cpu) { struct kmem_cache *cachep; struct kmem_cache_node *n = NULL; int node = cpu_to_mem(cpu); const struct cpumask *mask = cpumask_of_node(node); list_for_each_entry(cachep, &slab_caches, list) { struct array_cache *nc; struct array_cache *shared; struct array_cache **alien; /* cpu is dead; no one can alloc from it. */ nc = cachep->array[cpu]; cachep->array[cpu] = NULL; n = cachep->node[node]; if (!n) goto free_array_cache; spin_lock_irq(&n->list_lock); /* Free limit for this kmem_cache_node */ n->free_limit -= cachep->batchcount; if (nc) free_block(cachep, nc->entry, nc->avail, node); if (!cpumask_empty(mask)) { spin_unlock_irq(&n->list_lock); goto free_array_cache; } shared = n->shared; if (shared) { free_block(cachep, shared->entry, shared->avail, node); n->shared = NULL; } alien = n->alien; n->alien = NULL; spin_unlock_irq(&n->list_lock); kfree(shared); if (alien) { drain_alien_cache(cachep, alien); free_alien_cache(alien); } free_array_cache: kfree(nc); } /* * In the previous loop, all the objects were freed to * the respective cache's slabs, now we can go ahead and * shrink each nodelist to its limit. */ list_for_each_entry(cachep, &slab_caches, list) { n = cachep->node[node]; if (!n) continue; drain_freelist(cachep, n, n->free_objects); } } static int __cpuinit cpuup_prepare(long cpu) { struct kmem_cache *cachep; struct kmem_cache_node *n = NULL; int node = cpu_to_mem(cpu); int err; /* * We need to do this right in the beginning since * alloc_arraycache's are going to use this list. * kmalloc_node allows us to add the slab to the right * kmem_cache_node and not this cpu's kmem_cache_node */ err = init_cache_node_node(node); if (err < 0) goto bad; /* * Now we can go ahead with allocating the shared arrays and * array caches */ list_for_each_entry(cachep, &slab_caches, list) { struct array_cache *nc; struct array_cache *shared = NULL; struct array_cache **alien = NULL; nc = alloc_arraycache(node, cachep->limit, cachep->batchcount, GFP_KERNEL); if (!nc) goto bad; if (cachep->shared) { shared = alloc_arraycache(node, cachep->shared * cachep->batchcount, 0xbaadf00d, GFP_KERNEL); if (!shared) { kfree(nc); goto bad; } } if (use_alien_caches) { alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL); if (!alien) { kfree(shared); kfree(nc); goto bad; } } cachep->array[cpu] = nc; n = cachep->node[node]; BUG_ON(!n); spin_lock_irq(&n->list_lock); if (!n->shared) { /* * We are serialised from CPU_DEAD or * CPU_UP_CANCELLED by the cpucontrol lock */ n->shared = shared; shared = NULL; } #ifdef CONFIG_NUMA if (!n->alien) { n->alien = alien; alien = NULL; } #endif spin_unlock_irq(&n->list_lock); kfree(shared); free_alien_cache(alien); if (cachep->flags & SLAB_DEBUG_OBJECTS) slab_set_debugobj_lock_classes_node(cachep, node); else if (!OFF_SLAB(cachep) && !(cachep->flags & SLAB_DESTROY_BY_RCU)) on_slab_lock_classes_node(cachep, node); } init_node_lock_keys(node); return 0; bad: cpuup_canceled(cpu); return -ENOMEM; } static int __cpuinit cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { long cpu = (long)hcpu; int err = 0; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: mutex_lock(&slab_mutex); err = cpuup_prepare(cpu); mutex_unlock(&slab_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 slab_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_delayed_work_sync(&per_cpu(slab_reap_work, cpu)); /* Now the cache_reaper is guaranteed to be not running. */ per_cpu(slab_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_cache_node of any cache. This to avoid a race between * cpu_down, and a kmalloc allocation from another cpu for * memory from the node of the cpu going down. The node * structure is usually allocated from kmem_cache_create() and * gets destroyed at kmem_cache_destroy(). */ /* fall through */ #endif case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: mutex_lock(&slab_mutex); cpuup_canceled(cpu); mutex_unlock(&slab_mutex); break; } return notifier_from_errno(err); } static struct notifier_block __cpuinitdata cpucache_notifier = { &cpuup_callback, NULL, 0 }; #if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG) /* * Drains freelist for a node on each slab cache, used for memory hot-remove. * Returns -EBUSY if all objects cannot be drained so that the node is not * removed. * * Must hold slab_mutex. */ static int __meminit drain_cache_node_node(int node) { struct kmem_cache *cachep; int ret = 0; list_for_each_entry(cachep, &slab_caches, list) { struct kmem_cache_node *n; n = cachep->node[node]; if (!n) continue; drain_freelist(cachep, n, n->free_objects); if (!list_empty(&n->slabs_full) || !list_empty(&n->slabs_partial)) { ret = -EBUSY; break; } } return ret; } static int __meminit slab_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mnb = arg; int ret = 0; int nid; nid = mnb->status_change_nid; if (nid < 0) goto out; switch (action) { case MEM_GOING_ONLINE: mutex_lock(&slab_mutex); ret = init_cache_node_node(nid); mutex_unlock(&slab_mutex); break; case MEM_GOING_OFFLINE: mutex_lock(&slab_mutex); ret = drain_cache_node_node(nid); mutex_unlock(&slab_mutex); break; case MEM_ONLINE: case MEM_OFFLINE: case MEM_CANCEL_ONLINE: case MEM_CANCEL_OFFLINE: break; } out: return notifier_from_errno(ret); } #endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */ /* * swap the static kmem_cache_node with kmalloced memory */ static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list, int nodeid) { struct kmem_cache_node *ptr; ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid); BUG_ON(!ptr); memcpy(ptr, list, sizeof(struct kmem_cache_node)); /* * Do not assume that spinlocks can be initialized via memcpy: */ spin_lock_init(&ptr->list_lock); MAKE_ALL_LISTS(cachep, ptr, nodeid); cachep->node[nodeid] = ptr; } /* * For setting up all the kmem_cache_node for cache whose buffer_size is same as * size of kmem_cache_node. */ static void __init set_up_node(struct kmem_cache *cachep, int index) { int node; for_each_online_node(node) { cachep->node[node] = &init_kmem_cache_node[index + node]; cachep->node[node]->next_reap = jiffies + REAPTIMEOUT_LIST3 + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; } } /* * The memory after the last cpu cache pointer is used for the * the node pointer. */ static void setup_node_pointer(struct kmem_cache *cachep) { cachep->node = (struct kmem_cache_node **)&cachep->array[nr_cpu_ids]; } /* * Initialisation. Called after the page allocator have been initialised and * before smp_init(). */ void __init kmem_cache_init(void) { int i; kmem_cache = &kmem_cache_boot; setup_node_pointer(kmem_cache); if (num_possible_nodes() == 1) use_alien_caches = 0; for (i = 0; i < NUM_INIT_LISTS; i++) kmem_cache_node_init(&init_kmem_cache_node[i]); set_up_node(kmem_cache, CACHE_CACHE); /* * Fragmentation resistance on low memory - only use bigger * page orders on machines with more than 32MB of memory if * not overridden on the command line. */ if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT) slab_max_order = SLAB_MAX_ORDER_HI; /* Bootstrap is tricky, because several objects are allocated * from caches that do not exist yet: * 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_cache_node structures, it's replaced with a kmalloc allocated * array at the end of the bootstrap. * 2) Create the first kmalloc cache. * The struct kmem_cache for the new cache is allocated normally. * 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 kmem_cache and the first * kmalloc cache with kmalloc allocated arrays. * 5) Replace the __init data for kmem_cache_node 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. */ /* 1) create the kmem_cache */ /* * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ create_boot_cache(kmem_cache, "kmem_cache", offsetof(struct kmem_cache, array[nr_cpu_ids]) + nr_node_ids * sizeof(struct kmem_cache_node *), SLAB_HWCACHE_ALIGN); list_add(&kmem_cache->list, &slab_caches); /* 2+3) create the kmalloc caches */ /* * Initialize the caches that provide memory for the array cache and the * kmem_cache_node structures first. Without this, further allocations will * bug. */ kmalloc_caches[INDEX_AC] = create_kmalloc_cache("kmalloc-ac", kmalloc_size(INDEX_AC), ARCH_KMALLOC_FLAGS); if (INDEX_AC != INDEX_NODE) kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node", kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS); slab_early_init = 0; /* 4) Replace the bootstrap head arrays */ { struct array_cache *ptr; ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT); 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); kmem_cache->array[smp_processor_id()] = ptr; ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT); BUG_ON(cpu_cache_get(kmalloc_caches[INDEX_AC]) != &initarray_generic.cache); memcpy(ptr, cpu_cache_get(kmalloc_caches[INDEX_AC]), sizeof(struct arraycache_init)); /* * Do not assume that spinlocks can be initialized via memcpy: */ spin_lock_init(&ptr->lock); kmalloc_caches[INDEX_AC]->array[smp_processor_id()] = ptr; } /* 5) Replace the bootstrap kmem_cache_node */ { int nid; for_each_online_node(nid) { init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid); init_list(kmalloc_caches[INDEX_AC], &init_kmem_cache_node[SIZE_AC + nid], nid); if (INDEX_AC != INDEX_NODE) { init_list(kmalloc_caches[INDEX_NODE], &init_kmem_cache_node[SIZE_NODE + nid], nid); } } } create_kmalloc_caches(ARCH_KMALLOC_FLAGS); } void __init kmem_cache_init_late(void) { struct kmem_cache *cachep; slab_state = UP; /* 6) resize the head arrays to their final sizes */ mutex_lock(&slab_mutex); list_for_each_entry(cachep, &slab_caches, list) if (enable_cpucache(cachep, GFP_NOWAIT)) BUG(); mutex_unlock(&slab_mutex); /* Annotate slab for lockdep -- annotate the malloc caches */ init_lock_keys(); /* Done! */ slab_state = FULL; /* * Register a cpu startup notifier callback that initializes * cpu_cache_get for all new cpus */ register_cpu_notifier(&cpucache_notifier); #ifdef CONFIG_NUMA /* * Register a memory hotplug callback that initializes and frees * node. */ hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); #endif /* * The reap timers are started later, with a module init call: That part * of the kernel is not yet operational. */ } static int __init cpucache_init(void) { int cpu; /* * Register the timers that return unneeded pages to the page allocator */ for_each_online_cpu(cpu) start_cpu_timer(cpu); /* Done! */ slab_state = FULL; return 0; } __initcall(cpucache_init); static noinline void slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) { struct kmem_cache_node *n; struct slab *slabp; unsigned long flags; int node; printk(KERN_WARNING "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", nodeid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n", cachep->name, cachep->size, cachep->gfporder); for_each_online_node(node) { unsigned long active_objs = 0, num_objs = 0, free_objects = 0; unsigned long active_slabs = 0, num_slabs = 0; n = cachep->node[node]; if (!n) continue; spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(slabp, &n->slabs_full, list) { active_objs += cachep->num; active_slabs++; } list_for_each_entry(slabp, &n->slabs_partial, list) { active_objs += slabp->inuse; active_slabs++; } list_for_each_entry(slabp, &n->slabs_free, list) num_slabs++; free_objects += n->free_objects; spin_unlock_irqrestore(&n->list_lock, flags); num_slabs += active_slabs; num_objs = num_slabs * cachep->num; printk(KERN_WARNING " node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n", node, active_slabs, num_slabs, active_objs, num_objs, free_objects); } } /* * Interface to system's page allocator. No need to hold the cache-lock. * * If we requested dmaable memory, we will get it. Even if we * did not request dmaable memory, we might get it, but that * would be relatively rare and ignorable. */ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct page *page; int nr_pages; int i; #ifndef CONFIG_MMU /* * Nommu uses slab's for process anonymous memory allocations, and thus * requires __GFP_COMP to properly refcount higher order allocations */ flags |= __GFP_COMP; #endif flags |= cachep->allocflags; if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) { if (!(flags & __GFP_NOWARN) && printk_ratelimit()) slab_out_of_memory(cachep, flags, nodeid); return NULL; } /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ if (unlikely(page->pfmemalloc)) pfmemalloc_active = true; nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) 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); if (page->pfmemalloc) SetPageSlabPfmemalloc(page + i); } memcg_bind_pages(cachep, cachep->gfporder); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); if (cachep->ctor) kmemcheck_mark_uninitialized_pages(page, nr_pages); else kmemcheck_mark_unallocated_pages(page, nr_pages); } return page_address(page); } /* * Interface to system's page release. */ static void kmem_freepages(struct kmem_cache *cachep, void *addr) { unsigned long i = (1 << cachep->gfporder); struct page *page = virt_to_page(addr); const unsigned long nr_freed = i; kmemcheck_free_shadow(page, cachep->gfporder); 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)); __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); page++; } memcg_release_pages(cachep, cachep->gfporder); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder); } static void kmem_rcu_free(struct rcu_head *head) { struct slab_rcu *slab_rcu = (struct slab_rcu *)head; struct kmem_cache *cachep = slab_rcu->cachep; kmem_freepages(cachep, slab_rcu->addr); if (OFF_SLAB(cachep)) kmem_cache_free(cachep->slabp_cache, slab_rcu); } #if DEBUG #ifdef CONFIG_DEBUG_PAGEALLOC static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, unsigned long caller) { int size = cachep->object_size; addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)]; if (size < 5 * sizeof(unsigned long)) return; *addr++ = 0x12345678; *addr++ = caller; *addr++ = smp_processor_id(); size -= 3 * sizeof(unsigned long); { unsigned long *sptr = &caller; unsigned long svalue; while (!kstack_end(sptr)) { svalue = *sptr++; if (kernel_text_address(svalue)) { *addr++ = svalue; size -= sizeof(unsigned long); if (size <= sizeof(unsigned long)) break; } } } *addr++ = 0x87654321; } #endif static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) { int size = cachep->object_size; addr = &((char *)addr)[obj_offset(cachep)]; memset(addr, val, size); *(unsigned char *)(addr + size - 1) = POISON_END; } 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++) { if (data[offset + i] != POISON_FREE) { error = data[offset + i]; bad_count++; } } print_hex_dump(KERN_CONT, "", 0, 16, 1, &data[offset], limit, 1); 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 #if DEBUG static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) { int i, size; char *realobj; if (cachep->flags & SLAB_RED_ZONE) { printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n", *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } if (cachep->flags & SLAB_STORE_USER) { printk(KERN_ERR "Last user: [<%p>](%pSR)\n", *dbg_userword(cachep, objp), *dbg_userword(cachep, objp)); } realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; for (i = 0; i < size && lines; i += 16, lines--) { int limit; limit = 16; if (i + limit > size) limit = size - i; dump_line(realobj, i, limit); } } static void check_poison_obj(struct kmem_cache *cachep, void *objp) { char *realobj; int size, i; int lines = 0; realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; for (i = 0; i < size; i++) { char exp = POISON_FREE; if (i == size - 1) exp = POISON_END; if (realobj[i] != exp) { int limit; /* Mismatch ! */ /* Print header */ if (lines == 0) { printk(KERN_ERR "Slab corruption (%s): %s start=%p, len=%d\n", print_tainted(), cachep->name, realobj, size); print_objinfo(cachep, objp, 0); } /* Hexdump the affected line */ i = (i / 16) * 16; limit = 16; if (i + limit > size) limit = size - i; dump_line(realobj, i, limit); i += 16; lines++; /* Limit to 5 lines */ if (lines > 5) break; } } if (lines != 0) { /* Print some data about the neighboring objects, if they * exist: */ struct slab *slabp = virt_to_slab(objp); unsigned int objnr; objnr = obj_to_index(cachep, slabp, objp); if (objnr) { objp = index_to_obj(cachep, slabp, objnr - 1); realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Prev obj: start=%p, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } if (objnr + 1 < cachep->num) { objp = index_to_obj(cachep, slabp, objnr + 1); realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Next obj: start=%p, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } } } #endif #if DEBUG static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp) { int i; for (i = 0; i < cachep->num; i++) { void *objp = index_to_obj(cachep, slabp, i); if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC if (cachep->size % PAGE_SIZE == 0 && OFF_SLAB(cachep)) kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else check_poison_obj(cachep, objp); #endif } if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) slab_error(cachep, "start of a freed object " "was overwritten"); if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) slab_error(cachep, "end of a freed object " "was overwritten"); } } } #else static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp) { } #endif /** * slab_destroy - destroy and release all objects in a slab * @cachep: cache pointer being destroyed * @slabp: slab pointer being destroyed * * Destroy all the objs in a slab, and release the mem back to the system. * Before calling the slab must have been unlinked from the cache. The * cache-lock is not held/needed. */ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) { void *addr = slabp->s_mem - slabp->colouroff; slab_destroy_debugcheck(cachep, slabp); if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) { struct slab_rcu *slab_rcu; slab_rcu = (struct slab_rcu *)slabp; slab_rcu->cachep = cachep; slab_rcu->addr = addr; call_rcu(&slab_rcu->head, kmem_rcu_free); } else { kmem_freepages(cachep, addr); if (OFF_SLAB(cachep)) kmem_cache_free(cachep->slabp_cache, slabp); } } /** * calculate_slab_order - calculate size (page order) of slabs * @cachep: pointer to the cache that is being created * @size: size of objects to be created in this cache. * @align: required alignment for the objects. * @flags: slab allocation flags * * Also calculates the number of objects per slab. * * This could be made much more intelligent. For now, try to avoid using * high order pages for slabs. When the gfp() functions are more friendly * towards high-order requests, this should be changed. */ static size_t calculate_slab_order(struct kmem_cache *cachep, size_t size, size_t align, unsigned long flags) { unsigned long offslab_limit; size_t left_over = 0; int gfporder; for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) { unsigned int num; size_t remainder; cache_estimate(gfporder, size, align, flags, &remainder, &num); if (!num) continue; if (flags & CFLGS_OFF_SLAB) { /* * Max number of objs-per-slab for caches which * use off-slab slabs. Needed to avoid a possible * looping condition in cache_grow(). */ offslab_limit = size - sizeof(struct slab); offslab_limit /= sizeof(kmem_bufctl_t); if (num > offslab_limit) break; } /* Found something acceptable - save it away */ cachep->num = num; cachep->gfporder = gfporder; left_over = remainder; /* * A VFS-reclaimable slab tends to have most allocations * as GFP_NOFS and we really don't want to have to be allocating * higher-order pages when we are unable to shrink dcache. */ if (flags & SLAB_RECLAIM_ACCOUNT) break; /* * Large number of objects is good, but very large slabs are * currently bad for the gfp()s. */ if (gfporder >= slab_max_order) break; /* * Acceptable internal fragmentation? */ if (left_over * 8 <= (PAGE_SIZE << gfporder)) break; } return left_over; } static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) { if (slab_state >= FULL) return enable_cpucache(cachep, gfp); if (slab_state == DOWN) { /* * Note: Creation of first cache (kmem_cache). * The setup_node is taken care * of by the caller of __kmem_cache_create */ cachep->array[smp_processor_id()] = &initarray_generic.cache; slab_state = PARTIAL; } else if (slab_state == PARTIAL) { /* * Note: the second kmem_cache_create must create the cache * that's used by kmalloc(24), otherwise the creation of * further caches will BUG(). */ cachep->array[smp_processor_id()] = &initarray_generic.cache; /* * If the cache that's used by kmalloc(sizeof(kmem_cache_node)) is * the second cache, then we need to set up all its node/, * otherwise the creation of further caches will BUG(). */ set_up_node(cachep, SIZE_AC); if (INDEX_AC == INDEX_NODE) slab_state = PARTIAL_NODE; else slab_state = PARTIAL_ARRAYCACHE; } else { /* Remaining boot caches */ cachep->array[smp_processor_id()] = kmalloc(sizeof(struct arraycache_init), gfp); if (slab_state == PARTIAL_ARRAYCACHE) { set_up_node(cachep, SIZE_NODE); slab_state = PARTIAL_NODE; } else { int node; for_each_online_node(node) { cachep->node[node] = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); BUG_ON(!cachep->node[node]); kmem_cache_node_init(cachep->node[node]); } } } cachep->node[numa_mem_id()]->next_reap = jiffies + REAPTIMEOUT_LIST3 + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; cpu_cache_get(cachep)->avail = 0; cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES; cpu_cache_get(cachep)->batchcount = 1; cpu_cache_get(cachep)->touched = 0; cachep->batchcount = 1; cachep->limit = BOOT_CPUCACHE_ENTRIES; return 0; } /** * __kmem_cache_create - Create a cache. * @cachep: cache management descriptor * @flags: SLAB flags * * Returns a ptr to the cache on success, NULL on failure. * Cannot be called within a int, but can be interrupted. * The @ctor is run when new pages are allocated by the cache. * * The flags are * * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) * to catch references to uninitialised memory. * * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check * for buffer overruns. * * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { size_t left_over, slab_size, ralign; gfp_t gfp; int err; size_t size = cachep->size; #if DEBUG #if FORCED_DEBUG /* * Enable redzoning and last user accounting, except for caches with * large objects, if the increased size would increase the object size * above the next power of two: caches with object sizes just above a * power of two have a significant amount of internal fragmentation. */ if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN + 2 * sizeof(unsigned long long))) flags |= SLAB_RED_ZONE | SLAB_STORE_USER; if (!(flags & SLAB_DESTROY_BY_RCU)) flags |= SLAB_POISON; #endif if (flags & SLAB_DESTROY_BY_RCU) BUG_ON(flags & SLAB_POISON); #endif /* * Check that size is in terms of words. This is needed to avoid * unaligned accesses for some archs when redzoning is used, and makes * sure any on-slab bufctl's are also correctly aligned. */ if (size & (BYTES_PER_WORD - 1)) { size += (BYTES_PER_WORD - 1); size &= ~(BYTES_PER_WORD - 1); } /* * Redzoning and user store require word alignment or possibly larger. * Note this will be overridden by architecture or caller mandated * alignment if either is greater than BYTES_PER_WORD. */ if (flags & SLAB_STORE_USER) ralign = BYTES_PER_WORD; if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably * aligned, by adjusting the object size accordingly. */ size += REDZONE_ALIGN - 1; size &= ~(REDZONE_ALIGN - 1); } /* 3) caller mandated alignment */ if (ralign < cachep->align) { ralign = cachep->align; } /* disable debug if necessary */ if (ralign > __alignof__(unsigned long long)) flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); /* * 4) Store it. */ cachep->align = ralign; if (slab_is_available()) gfp = GFP_KERNEL; else gfp = GFP_NOWAIT; setup_node_pointer(cachep); #if DEBUG /* * Both debugging options require word-alignment which is calculated * into align above. */ if (flags & SLAB_RED_ZONE) { /* add space for red zone words */ cachep->obj_offset += sizeof(unsigned long long); size += 2 * sizeof(unsigned long long); } if (flags & SLAB_STORE_USER) { /* user store requires one word storage behind the end of * the real object. But if the second red zone needs to be * aligned to 64 bits, we must allow that much space. */ if (flags & SLAB_RED_ZONE) size += REDZONE_ALIGN; else size += BYTES_PER_WORD; } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) if (size >= kmalloc_size(INDEX_NODE + 1) && 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 #endif /* * Determine if the slab management is 'on' or 'off' slab. * (bootstrapping cannot cope with offslab caches so don't do * it too early on. Always use on-slab management when * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak) */ if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init && !(flags & SLAB_NOLEAKTRACE)) /* * Size is large, assume best to place the slab management obj * off-slab (should allow better packing of objs). */ flags |= CFLGS_OFF_SLAB; size = ALIGN(size, cachep->align); left_over = calculate_slab_order(cachep, size, cachep->align, flags); if (!cachep->num) return -E2BIG; slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab), cachep->align); /* * If the slab has been placed off-slab, and we have enough space then * move it on-slab. This is at the expense of any extra colouring. */ if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) { flags &= ~CFLGS_OFF_SLAB; left_over -= slab_size; } if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ slab_size = cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab); #ifdef CONFIG_PAGE_POISONING /* If we're going to use the generic kernel_map_pages() * poisoning, then it's going to smash the contents of * the redzone and userword anyhow, so switch them off. */ if (size % PAGE_SIZE == 0 && flags & SLAB_POISON) flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); #endif } cachep->colour_off = cache_line_size(); /* Offset must be a multiple of the alignment. */ 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; cachep->allocflags = 0; if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) cachep->allocflags |= GFP_DMA; cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); if (flags & CFLGS_OFF_SLAB) { cachep->slabp_cache = kmalloc_slab(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(ZERO_OR_NULL_PTR(cachep->slabp_cache)); } err = setup_cpu_cache(cachep, gfp); if (err) { __kmem_cache_shutdown(cachep); return err; } if (flags & SLAB_DEBUG_OBJECTS) { /* * Would deadlock through slab_destroy()->call_rcu()-> * debug_object_activate()->kmem_cache_alloc(). */ WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU); slab_set_debugobj_lock_classes(cachep); } else if (!OFF_SLAB(cachep) && !(flags & SLAB_DESTROY_BY_RCU)) on_slab_lock_classes(cachep); return 0; } #if DEBUG static void check_irq_off(vo