/mm/slab.c
C | 3825 lines | 3110 code | 628 blank | 87 comment | 502 complexity | 5dd169ce434a83938b6a2464e0584eca MD5 | raw file
Possible License(s): GPL-2.0
Large files files are truncated, but you can click here to view the full file
- /*
- * 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 'cache_chain_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 <shai@scalex86.org>.
- * Shobhit Dayal <shobhit@calsoftinc.com>
- * Alok N Kataria <alokk@calsoftinc.com>
- * Christoph Lameter <christoph@lameter.com>
- *
- * 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 <linux/slab.h>
- #include <linux/mm.h>
- #include <linux/poison.h>
- #include <linux/swap.h>
- #include <linux/cache.h>
- #include <linux/interrupt.h>
- #include <linux/init.h>
- #include <linux/compiler.h>
- #include <linux/cpuset.h>
- #include <linux/proc_fs.h>
- #include <linux/seq_file.h>
- #include <linux/notifier.h>
- #include <linux/kallsyms.h>
- #include <linux/cpu.h>
- #include <linux/sysctl.h>
- #include <linux/module.h>
- #include <linux/rcupdate.h>
- #include <linux/string.h>
- #include <linux/uaccess.h>
- #include <linux/nodemask.h>
- #include <linux/kmemleak.h>
- #include <linux/mempolicy.h>
- #include <linux/mutex.h>
- #include <linux/fault-inject.h>
- #include <linux/rtmutex.h>
- #include <linux/reciprocal_div.h>
- #include <linux/debugobjects.h>
- #include <linux/kmemcheck.h>
- #include <linux/memory.h>
- #include <linux/prefetch.h>
- #include <asm/cacheflush.h>
- #include <asm/tlbflush.h>
- #include <asm/page.h>
- #include <trace/events/kmem.h>
- #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
- #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
- #if DEBUG
- # define CREATE_MASK (SLAB_RED_ZONE | \
- SLAB_POISON | SLAB_HWCACHE_ALIGN | \
- SLAB_CACHE_DMA | \
- SLAB_STORE_USER | \
- SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
- SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
- SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
- #else
- # define CREATE_MASK (SLAB_HWCACHE_ALIGN | \
- SLAB_CACHE_DMA | \
- SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
- SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
- SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
- #endif
- 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 {
- struct rcu_head head;
- struct kmem_cache *cachep;
- void *addr;
- };
- struct slab {
- union {
- struct {
- struct list_head list;
- unsigned long colouroff;
- void *s_mem;
- unsigned int inuse;
- kmem_bufctl_t free;
- unsigned short nodeid;
- };
- struct slab_rcu __slab_cover_slab_rcu;
- };
- };
- struct array_cache {
- unsigned int avail;
- unsigned int limit;
- unsigned int batchcount;
- unsigned int touched;
- spinlock_t lock;
- void *entry[];
- };
- #define BOOT_CPUCACHE_ENTRIES 1
- struct arraycache_init {
- struct array_cache cache;
- void *entries[BOOT_CPUCACHE_ENTRIES];
- };
- struct kmem_list3 {
- struct list_head slabs_partial;
- struct list_head slabs_full;
- struct list_head slabs_free;
- unsigned long free_objects;
- unsigned int free_limit;
- unsigned int colour_next;
- spinlock_t list_lock;
- struct array_cache *shared;
- struct array_cache **alien;
- unsigned long next_reap;
- int free_touched;
- };
- #define NUM_INIT_LISTS (3 * MAX_NUMNODES)
- static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
- #define CACHE_CACHE 0
- #define SIZE_AC MAX_NUMNODES
- #define SIZE_L3 (2 * 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, gfp_t gfp);
- static void cache_reap(struct work_struct *unused);
- static __always_inline int index_of(const size_t size)
- {
- extern void __bad_size(void);
- if (__builtin_constant_p(size)) {
- int i = 0;
- #define CACHE(x) \
- if (size <=x) \
- return i; \
- else \
- i++;
- #include <linux/kmalloc_sizes.h>
- #undef CACHE
- __bad_size();
- } else
- __bad_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))
- static void kmem_list3_init(struct kmem_list3 *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->nodelists[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
- #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
- static int obj_offset(struct kmem_cache *cachep)
- {
- return cachep->obj_offset;
- }
- static int obj_size(struct kmem_cache *cachep)
- {
- return cachep->obj_size;
- }
- 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->buffer_size -
- sizeof(unsigned long long) -
- REDZONE_ALIGN);
- return (unsigned long long *) (objp + cachep->buffer_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->buffer_size - BYTES_PER_WORD);
- }
- #else
- #define obj_offset(x) 0
- #define obj_size(cachep) (cachep->buffer_size)
- #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
- #ifdef CONFIG_TRACING
- size_t slab_buffer_size(struct kmem_cache *cachep)
- {
- return cachep->buffer_size;
- }
- EXPORT_SYMBOL(slab_buffer_size);
- #endif
- #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 void page_set_cache(struct page *page, struct kmem_cache *cache)
- {
- page->lru.next = (struct list_head *)cache;
- }
- static inline struct kmem_cache *page_get_cache(struct page *page)
- {
- page = compound_head(page);
- BUG_ON(!PageSlab(page));
- return (struct kmem_cache *)page->lru.next;
- }
- static inline void page_set_slab(struct page *page, struct slab *slab)
- {
- page->lru.prev = (struct list_head *)slab;
- }
- static inline struct slab *page_get_slab(struct page *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_head_page(obj);
- return page_get_cache(page);
- }
- static inline struct slab *virt_to_slab(const void *obj)
- {
- struct page *page = virt_to_head_page(obj);
- return page_get_slab(page);
- }
- static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
- unsigned int idx)
- {
- return slab->s_mem + cache->buffer_size * idx;
- }
- 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);
- }
- struct cache_sizes malloc_sizes[] = {
- #define CACHE(x) { .cs_size = (x) },
- #include <linux/kmalloc_sizes.h>
- CACHE(ULONG_MAX)
- #undef CACHE
- };
- EXPORT_SYMBOL(malloc_sizes);
- struct cache_names {
- char *name;
- char *name_dma;
- };
- static struct cache_names __initdata cache_names[] = {
- #define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
- #include <linux/kmalloc_sizes.h>
- {NULL,}
- #undef CACHE
- };
- static struct arraycache_init initarray_cache __initdata =
- { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
- static struct arraycache_init initarray_generic =
- { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
- static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES];
- static struct kmem_cache cache_cache = {
- .nodelists = cache_cache_nodelists,
- .batchcount = 1,
- .limit = BOOT_CPUCACHE_ENTRIES,
- .shared = 1,
- .buffer_size = sizeof(struct kmem_cache),
- .name = "kmem_cache",
- };
- #define BAD_ALIEN_MAGIC 0x01020304ul
- static enum {
- NONE,
- PARTIAL_AC,
- PARTIAL_L3,
- EARLY,
- LATE,
- FULL
- } g_cpucache_up;
- int slab_is_available(void)
- {
- return g_cpucache_up >= EARLY;
- }
- #ifdef CONFIG_LOCKDEP
- 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_list3 *l3;
- int r;
- l3 = cachep->nodelists[q];
- if (!l3)
- return;
- lockdep_set_class(&l3->list_lock, l3_key);
- alc = l3->alien;
- 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)
- {
- struct cache_sizes *s = malloc_sizes;
- if (g_cpucache_up < LATE)
- return;
- for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
- struct kmem_list3 *l3;
- l3 = s->cs_cachep->nodelists[q];
- if (!l3 || OFF_SLAB(s->cs_cachep))
- continue;
- slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key,
- &on_slab_alc_key, q);
- }
- }
- 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 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_MUTEX(cache_chain_mutex);
- static struct list_head cache_chain;
- 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 inline struct kmem_cache *__find_general_cachep(size_t size,
- gfp_t gfpflags)
- {
- struct cache_sizes *csizep = malloc_sizes;
- #if DEBUG
- BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
- #endif
- if (!size)
- return ZERO_SIZE_PTR;
- while (size > csizep->cs_size)
- csizep++;
- #ifdef CONFIG_ZONE_DMA
- if (unlikely(gfpflags & GFP_DMA))
- return csizep->cs_dmacachep;
- #endif
- return csizep->cs_cachep;
- }
- static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
- {
- return __find_general_cachep(size, gfpflags);
- }
- 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);
- }
- 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;
- if (flags & CFLGS_OFF_SLAB) {
- mgmt_size = 0;
- nr_objs = slab_size / buffer_size;
- if (nr_objs > SLAB_LIMIT)
- nr_objs = SLAB_LIMIT;
- } else {
- nr_objs = (slab_size - sizeof(struct slab)) /
- (buffer_size + sizeof(kmem_bufctl_t));
- 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;
- }
- #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();
- }
- 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
- 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
- static void __cpuinit start_cpu_timer(int cpu)
- {
- struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
- if (keventd_up() && reap_work->work.func == NULL) {
- init_reap_node(cpu);
- INIT_DELAYED_WORK_DEFERRABLE(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);
- 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 int transfer_objects(struct array_cache *to,
- struct array_cache *from, unsigned int max)
- {
-
- 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, l3) 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
- 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_list3 *rl3 = cachep->nodelists[node];
- if (ac->avail) {
- spin_lock(&rl3->list_lock);
- if (rl3->shared)
- transfer_objects(rl3->shared, ac, ac->limit);
- free_block(cachep, ac->entry, ac->avail, node);
- ac->avail = 0;
- spin_unlock(&rl3->list_lock);
- }
- }
- static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
- {
- int node = __this_cpu_read(slab_reap_node);
- if (l3->alien) {
- struct array_cache *ac = l3->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_list3 *l3;
- struct array_cache *alien = NULL;
- int node;
- node = numa_mem_id();
- if (likely(slabp->nodeid == node))
- return 0;
- l3 = cachep->nodelists[node];
- STATS_INC_NODEFREES(cachep);
- if (l3->alien && l3->alien[nodeid]) {
- alien = l3->alien[nodeid];
- spin_lock(&alien->lock);
- if (unlikely(alien->avail == alien->limit)) {
- STATS_INC_ACOVERFLOW(cachep);
- __drain_alien_cache(cachep, alien, nodeid);
- }
- alien->entry[alien->avail++] = objp;
- spin_unlock(&alien->lock);
- } else {
- spin_lock(&(cachep->nodelists[nodeid])->list_lock);
- free_block(cachep, &objp, 1, nodeid);
- spin_unlock(&(cachep->nodelists[nodeid])->list_lock);
- }
- return 1;
- }
- #endif
- static int init_cache_nodelists_node(int node)
- {
- struct kmem_cache *cachep;
- struct kmem_list3 *l3;
- const int memsize = sizeof(struct kmem_list3);
- list_for_each_entry(cachep, &cache_chain, next) {
- if (!cachep->nodelists[node]) {
- l3 = kmalloc_node(memsize, GFP_KERNEL, node);
- if (!l3)
- return -ENOMEM;
- kmem_list3_init(l3);
- l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
- cachep->nodelists[node] = l3;
- }
- spin_lock_irq(&cachep->nodelists[node]->list_lock);
- cachep->nodelists[node]->free_limit =
- (1 + nr_cpus_node(node)) *
- cachep->batchcount + cachep->num;
- spin_unlock_irq(&cachep->nodelists[node]->list_lock);
- }
- return 0;
- }
- static void __cpuinit cpuup_canceled(long cpu)
- {
- struct kmem_cache *cachep;
- struct kmem_list3 *l3 = NULL;
- int node = cpu_to_mem(cpu);
- const struct cpumask *mask = cpumask_of_node(node);
- list_for_each_entry(cachep, &cache_chain, next) {
- struct array_cache *nc;
- struct array_cache *shared;
- struct array_cache **alien;
-
- nc = cachep->array[cpu];
- cachep->array[cpu] = NULL;
- l3 = cachep->nodelists[node];
- if (!l3)
- goto free_array_cache;
- spin_lock_irq(&l3->list_lock);
-
- l3->free_limit -= cachep->batchcount;
- if (nc)
- free_block(cachep, nc->entry, nc->avail, node);
- if (!cpumask_empty(mask)) {
- spin_unlock_irq(&l3->list_lock);
- goto free_array_cache;
- }
- shared = l3->shared;
- if (shared) {
- free_block(cachep, shared->entry,
- shared->avail, node);
- l3->shared = NULL;
- }
- alien = l3->alien;
- l3->alien = NULL;
- spin_unlock_irq(&l3->list_lock);
- kfree(shared);
- if (alien) {
- drain_alien_cache(cachep, alien);
- free_alien_cache(alien);
- }
- free_array_cache:
- kfree(nc);
- }
- list_for_each_entry(cachep, &cache_chain, next) {
- l3 = cachep->nodelists[node];
- if (!l3)
- continue;
- drain_freelist(cachep, l3, l3->free_objects);
- }
- }
- static int __cpuinit cpuup_prepare(long cpu)
- {
- struct kmem_cache *cachep;
- struct kmem_list3 *l3 = NULL;
- int node = cpu_to_mem(cpu);
- int err;
- err = init_cache_nodelists_node(node);
- if (err < 0)
- goto bad;
- list_for_each_entry(cachep, &cache_chain, next) {
- 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;
- l3 = cachep->nodelists[node];
- BUG_ON(!l3);
- spin_lock_irq(&l3->list_lock);
- if (!l3->shared) {
- l3->shared = shared;
- shared = NULL;
- }
- #ifdef CONFIG_NUMA
- if (!l3->alien) {
- l3->alien = alien;
- alien = NULL;
- }
- #endif
- spin_unlock_irq(&l3->list_lock);
- kfree(shared);
- free_alien_cache(alien);
- if (cachep->flags & SLAB_DEBUG_OBJECTS)
- slab_set_debugobj_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(&cache_chain_mutex);
- err = cpuup_prepare(cpu);
- 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:
- cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
-
- 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:
-
- #endif
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- mutex_lock(&cache_chain_mutex);
- cpuup_canceled(cpu);
- mutex_unlock(&cache_chain_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)
- static int __meminit drain_cache_nodelists_node(int node)
- {
- struct kmem_cache *cachep;
- int ret = 0;
- list_for_each_entry(cachep, &cache_chain, next) {
- struct kmem_list3 *l3;
- l3 = cachep->nodelists[node];
- if (!l3)
- continue;
- drain_freelist(cachep, l3, l3->free_objects);
- if (!list_empty(&l3->slabs_full) ||
- !list_empty(&l3->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(&cache_chain_mutex);
- ret = init_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
- break;
- case MEM_GOING_OFFLINE:
- mutex_lock(&cache_chain_mutex);
- ret = drain_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
- break;
- case MEM_ONLINE:
- case MEM_OFFLINE:
- case MEM_CANCEL_ONLINE:
- case MEM_CANCEL_OFFLINE:
- break;
- }
- out:
- return notifier_from_errno(ret);
- }
- #endif
- static void __init init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
- int nodeid)
- {
- struct kmem_list3 *ptr;
- ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_NOWAIT, nodeid);
- BUG_ON(!ptr);
- memcpy(ptr, list, sizeof(struct kmem_list3));
- spin_lock_init(&ptr->list_lock);
- MAKE_ALL_LISTS(cachep, ptr, nodeid);
- cachep->nodelists[nodeid] = ptr;
- }
- static void __init set_up_list3s(struct kmem_cache *cachep, int index)
- {
- int node;
- for_each_online_node(node) {
- cachep->nodelists[node] = &initkmem_list3[index + node];
- cachep->nodelists[node]->next_reap = jiffies +
- REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
- }
- }
- void __init kmem_cache_init(void)
- {
- size_t left_over;
- struct cache_sizes *sizes;
- 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]);
- if (i < MAX_NUMNODES)
- cache_cache.nodelists[i] = NULL;
- }
- set_up_list3s(&cache_cache, CACHE_CACHE);
- if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
- slab_max_order = SLAB_MAX_ORDER_HI;
- node = numa_mem_id();
-
- 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[node] = &initkmem_list3[CACHE_CACHE + node];
- cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
- 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,
- cache_line_size(), 0, &left_over, &cache_cache.num);
- if (cache_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) +
- sizeof(struct slab), cache_line_size());
-
- sizes = malloc_sizes;
- names = cache_names;
- 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);
- 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);
- }
- slab_early_init = 0;
- while (sizes->cs_size != ULONG_MAX) {
- if (!sizes->cs_cachep) {
- sizes->cs_cachep = kmem_cache_create(names->name,
- sizes->cs_size,
- ARCH_KMALLOC_MINALIGN,
- ARCH_KMALLOC_FLAGS|SLAB_PANIC,
- NULL);
- }
- #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);
- #endif
- sizes++;
- names++;
- }
-
- {
- struct array_cache *ptr;
- 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),
- sizeof(struct arraycache_init));
- spin_lock_init(&ptr->lock);
- cache_cache.array[smp_processor_id()] = ptr;
- ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
- BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
- != &initarray_generic.cache);
- memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
- sizeof(struct arraycache_init));
- spin_lock_init(&ptr->lock);
- malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
- ptr;
- }
-
- {
- int nid;
- for_each_online_node(nid) {
- init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
- init_list(malloc_sizes[INDEX_AC].cs_cachep,
- &initkmem_list3[SIZE_AC + nid], nid);
- if (INDEX_AC != INDEX_L3) {
- init_list(malloc_sizes[INDEX_L3].cs_cachep,
- &initkmem_list3[SIZE_L3 + nid], nid);
- }
- }
- }
- g_cpucache_up = EARLY;
- }
- void __init kmem_cache_init_late(void)
- {
- struct kmem_cache *cachep;
- g_cpucache_up = LATE;
-
- init_lock_keys();
-
- mutex_lock(&cache_chain_mutex);
- list_for_each_entry(cachep, &cache_chain, next)
- if (enable_cpucache(cachep, GFP_NOWAIT))
- BUG();
- mutex_unlock(&cache_chain_mutex);
-
- g_cpucache_up = FULL;
- register_cpu_notifier(&cpucache_notifier);
- #ifdef CONFIG_NUMA
- hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
- #endif
- }
- static int __init cpucache_init(void)
- {
- int cpu;
- for_each_online_cpu(cpu)
- start_cpu_timer(cpu);
- return 0;
- }
- __initcall(cpucache_init);
- static noinline void
- slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
- {
- struct kmem_list3 *l3;
- 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->buffer_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;
- l3 = cachep->nodelists[node];
- if (!l3)
- continue;
- spin_lock_irqsave(&l3->list_lock, flags);
- list_for_each_entry(slabp, &l3->slabs_full, list) {
- active_objs += cachep->num;
- active_slabs++;
- }
- list_for_each_entry(slabp, &l3->slabs_partial, list) {
- active_objs += slabp->inuse;
- active_slabs++;
- }
- list_for_each_entry(slabp, &l3->slabs_free, list)
- num_slabs++;
- free_objects += l3->free_objects;
- spin_unlock_irqrestore(&l3->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);
- }
- }
- static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
- {
- struct page *page;
- int nr_pages;
- int i;
- #ifndef CONFIG_MMU
- flags |= __GFP_COMP;
- #endif
- flags |= cachep->gfpflags;
- 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;
- }
- 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 (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);
- }
- 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));
- __ClearPageSlab(page);
- page++;
- }
- if (current->reclaim_state)
- current->reclaim_state->reclaimed_slab += nr_freed;
- free_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 = obj_size(cachep);
- 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 = obj_size(cachep);
- 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>]",
- *dbg_userword(cachep, objp));
- print_symbol("(%s)",
- (unsigned long)*dbg_userword(cachep, objp));
- printk("\n");
- }
- realobj = (char *)objp + obj_offset(cachep);
- size = obj_size(cachep);
- 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 = obj_size(cachep);
- for (i = 0; i < size; i++) {
- char exp = POISON_FREE;
- if (i == size - 1)
- exp = POISON_END;
- if (realobj[i] != exp) {
- int limit;
-
-
- 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);
- }
-
- i = (i / 16) * 16;
- limit = 16;
- if (i + limit > size)
- limit = size - i;
- dump_line(realobj, i, limit);
- i += 16;
- lines++;
-
- if (lines > 5)
- break;
- }
- }
- if (lines != 0) {
- 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->buffer_size % PAGE_SIZE == 0 &&
- OFF_SLAB(cachep))
- kernel_map_pages(virt_to_page(objp),
- cachep->buffer_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
- 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);
- }
- }
- static void __kmem_cache_destroy(struct kmem_cache *cachep)
- {
- int i;
- struct kmem_list3 *l3;
- for_each_online_cpu(i)
- kfree(cachep->array[i]);
-
- 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);
- }
- 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) {
- offslab_limit = size - sizeof(struct slab);
- offslab_limit /= sizeof(kmem_bufctl_t);
- if (num > offslab_limit)
- break;
- }
-
- cachep->num = num;
- cachep->gfporder = gfporder;
- left_over = remainder;
- if (flags & SLAB_RECLAIM_ACCOUNT)
- break;
- if (gfporder >= slab_max_order)
- break;
- 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 (g_cpucache_up == FULL)
- return enable_cpucache(cachep, gfp);
- if (g_cpucache_up == NONE) {
- cachep->array[smp_processor_id()] = &initarray_generic.cache;
- set_up_list3s(cachep, SIZE_AC);
- if (INDEX_AC == INDEX_L3)
- g_cpucache_up = PARTIAL_L3;
- else
- g_cpucache_up = PARTIAL_AC;
- } else {
- cachep->array[smp_processor_id()] =
- kmalloc(sizeof(struct arraycache_init), gfp);
- if (g_cpucache_up == PARTIAL_AC) {
- set_up_list3s(cachep, SIZE_L3);
- g_cpucache_up = PARTIAL_L3;
- } else {
- int node;
- for_each_online_node(node) {
- cachep->nodelists[node] =
- kmalloc_node(sizeof(struct kmem_list3),
- gfp, node);
- BUG_ON(!cachep->nodelists[node]);
- kmem_list3_init(cachep->nodelists[node]);
- }
- }
- }
- cachep->nodelists[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;
- }
- struct kmem_cache *
- kmem_cache_create (const char *name, size_t size, size_t align,
- unsigned long flags, void (*ctor)(void *))
- {
- size_t left_over, slab_size, ralign;
- struct kmem_cache *cachep = NULL, *pc;
- gfp_t gfp;
- if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
- size > KMALLOC_MAX_SIZE) {
- printk(KERN_ERR "%s: Early error in slab %s\n", __func__,
- name);
- BUG();
- }
- if (slab_is_available()) {
- get_online_cpus();
- mutex_lock(&cache_chain_mutex);
- }
- list_for_each_entry(pc, &cache_chain, next) {
- char tmp;
- int res;
- res = probe_kernel_address(pc->name, tmp);
- if (res) {
- printk(KERN_ERR
- "SLAB: cache with size %d has lost its name\n",
- pc->buffer_size);
- continue;
- }
- if (!strcmp(pc->name, name)) {
- printk(KERN_ERR
- "kmem_cache_create: duplicate cache %s\n", name);
- dump_stack();
- goto oops;
- }
- }
- #if DEBUG
- WARN_ON(strchr(name, ' '));
- #if FORCED_DEBUG
- 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
- BUG_ON(flags & ~CREATE_MASK);
- if (size & (BYTES_PER_WORD - 1)) {
- size += (BYTES_PER_WORD - 1);
- size &= ~(BYTES_PER_WORD - 1);
- }
-
-
- if (flags & SLAB_HWCACHE_ALIGN) {
- ralign = cache_line_size();
- while (size <= ralign / 2)
- ralign /= 2;
- } else {
- ralign = BYTES_PER_WORD;
- }
- if (flags & SLAB_STORE_USER)
- ralign = BYTES_PER_WORD;
- if (flags & SLAB_RED_ZONE) {
- ralign = REDZONE_ALIGN;
- size += REDZONE_ALIGN - 1;
- size &= ~(REDZONE_ALIGN - 1);
- }
-
- if (ralign < ARCH_SLAB_MINALIGN) {
- ralign = ARCH_SLAB_MINALIGN;
- }
-
- if (ralign < align) {
- ralign = align;
- }
-
- if (ralign > __alignof__(unsigned long long))
- flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
- align = ralign;
- if (slab_is_available())
- gfp = GFP_KERNEL;
- else
- gfp = GFP_NOWAIT;
-
- cachep = kmem_cache_zalloc(&cache_cache, gfp);
- if (!cachep)
- goto oops;
- cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
- #if DEBUG
- cachep->obj_size = size;
- if (flags & SLAB_RED_ZONE) {
-
- cachep->obj_offset += sizeof(unsigned long long);
- size += 2 * sizeof(unsigned long long);
- }
- if (flags & SLAB_STORE_USER) {
- if (flags & SLAB_RED_ZONE)
- size += REDZONE_ALIGN;
- else
- size += BYTES_PER_WORD;
- }
- #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
- if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
- && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
- cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
- size = PAGE_SIZE;
- }
- #endif
- #endif
- if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
- !(flags & SLAB_NOLEAKTRACE))
- flags |= CFLGS_OFF_SLAB;
- size = ALIGN(size, align);
- left_over = calculate_slab_order(cachep, size, align, flags);
- if (!cachep->num) {
- printk(KERN_ERR
- "kmem_cache_create: couldn't create cache %s.\n", name);
- kmem_cache_free(&cache_cache, cachep);
- cachep = NULL;
- goto oops;
- }
- slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
- + sizeof(struct slab), align);
- if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
- flags &= ~CFLGS_OFF_SLAB;
- left_over -= slab_size;
- }
- if (flags & CFLGS_OFF_SLAB) {
-
- slab_size =
- cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
- #ifdef CONFIG_PAGE_POISONING
- if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
- flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
- #endif
- }
- cachep->colour_off = cache_line_size();
-
- if (cachep->colour_off < align)
- cachep->colour_off = align;
- cachep->colour = left_over / cachep->colour_off;
- cachep->slab_size = slab_size;
- cachep->flags = flags;
- cachep->gfpflags = 0;
- 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) {
- cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
- 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);
- cachep = NULL;
- goto oops;
- }
- if (flags & SLAB_DEBUG_OBJECTS) {
- WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU);
- slab_set_debugobj_lock_classes(cachep);
- }
-
- list_add(&cachep->next, &cache_chain);
- oops:
- if (!cachep && (flags & SLAB_PANIC))
- panic("kmem_cache_create(): failed to create slab `%s'\n",
- name);
- if (slab_is_available()) {
- mutex_unlock(&cache_chain_mutex);
- put_online_cpus();
- }
- return cachep;
- }
- EXPORT_SYMBOL(kmem_cache_create);
- #if DEBUG
- static void check_irq_off(void)
- {
- BUG_ON(!irqs_disabled());
- }
- static void check_irq_on(void)
- {
- BUG_ON(irqs_disabled());
- }
- static void check_spinlock_acquired(struct kmem_cache *cachep)
- {
- #ifdef CONFIG_SMP
- check_irq_off();
- assert_spin_locked(&cachep->nodelists[numa_mem_id()]->list_lock);
- #endif
- }
- static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
- {
- #ifdef CONFIG_SMP
- check_irq_off();
- assert_spin_locked(&cachep->nodelists[node]->list_lock);
- #endif
- }
- #else
- #define check_irq_off() do { } while(0)
- #define check_irq_on() do { } while(0)
- #define check_spinlock_acquired(x) do { } while(0)
- #define check_spinlock_acquired_node(x, y) do { } while(0)
- #endif
- static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
- struct array_cache *ac,
- int force, int node);
- static void do_drain(void *arg)
- {
- struct kmem_cache *cachep = arg;
- struct array_cache *ac;
- int node = numa_mem_id();
- check_irq_off();
- ac = cpu_cache_get(cachep);
- spin_lock(&cachep->nodelists[node]->list_lock);
- free_block(cachep, ac->ent…
Large files files are truncated, but you can click here to view the full file