X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fslab.c;h=d0bd7f07ab041d3d7da06c5cec610035c3058b33;hb=987b0145d94eecf292d8b301228356f44611ab7c;hp=6b3cedfc6b2dfa5accba98b97c570e13ae9c6921;hpb=daddc0d38b3571bed170afa273a49a0eba090c1e;p=linux-2.6.git diff --git a/mm/slab.c b/mm/slab.c index 6b3cedfc6..d0bd7f07a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -55,7 +55,7 @@ * * SMP synchronization: * constructors and destructors are called without any locking. - * Several members in kmem_cache_t and struct slab never change, they + * 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. @@ -68,13 +68,22 @@ * Further notes from the original documentation: * * 11 April '97. Started multi-threading - markhe - * The global cache-chain is protected by the semaphore 'cache_chain_sem'. + * 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 . + * 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 @@ -91,10 +100,16 @@ #include #include #include +#include +#include +#include +#include +#include #include #include #include +#include /* * DEBUG - 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL, @@ -117,7 +132,6 @@ #define FORCED_DEBUG 0 #endif - /* Shouldn't this be in a header file somewhere? */ #define BYTES_PER_WORD sizeof(void *) @@ -126,20 +140,45 @@ #endif #ifndef ARCH_KMALLOC_MINALIGN +/* + * Enforce a minimum alignment for the kmalloc caches. + * Usually, the kmalloc caches are cache_line_size() aligned, except when + * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that. + * Note that this flag disables some debug features. + */ #define ARCH_KMALLOC_MINALIGN 0 #endif +#ifndef ARCH_SLAB_MINALIGN +/* + * Enforce a minimum alignment for all caches. + * Intended for archs that get misalignment faults even for BYTES_PER_WORD + * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. + * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables + * some debug features. + */ +#define ARCH_SLAB_MINALIGN 0 +#endif + +#ifndef ARCH_KMALLOC_FLAGS +#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN +#endif + /* Legal flag mask for kmem_cache_create(). */ #if DEBUG # define CREATE_MASK (SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \ SLAB_POISON | SLAB_HWCACHE_ALIGN | \ SLAB_NO_REAP | SLAB_CACHE_DMA | \ SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \ - SLAB_RECLAIM_ACCOUNT ) + SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \ + SLAB_DESTROY_BY_RCU) #else # define CREATE_MASK (SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | \ SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \ - SLAB_RECLAIM_ACCOUNT) + SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \ + SLAB_DESTROY_BY_RCU) #endif /* @@ -161,10 +200,10 @@ * is less than 512 (PAGE_SIZE<<3), but greater than 256. */ -#define BUFCTL_END 0xffffFFFF -#define BUFCTL_FREE 0xffffFFFE -#define SLAB_LIMIT 0xffffFFFD typedef unsigned int kmem_bufctl_t; +#define BUFCTL_END (((kmem_bufctl_t)(~0U))-0) +#define BUFCTL_FREE (((kmem_bufctl_t)(~0U))-1) +#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-2) /* Max number of objs-per-slab for caches which use off-slab slabs. * Needed to avoid a possible looping condition in cache_grow(). @@ -179,17 +218,39 @@ static unsigned long offslab_limit; * Slabs are chained into three list: fully used, partial, fully free slabs. */ struct slab { - 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; + 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_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. + * + * We assume struct slab_rcu can overlay struct slab when destroying. + */ +struct slab_rcu { + struct rcu_head head; + struct kmem_cache *cachep; + void *addr; }; /* * struct array_cache * - * Per cpu structures * Purpose: * - LIFO ordering, to hand out cache-warm objects from _alloc * - reduce the number of linked list operations @@ -204,6 +265,13 @@ struct array_cache { unsigned int limit; unsigned int batchcount; unsigned int touched; + spinlock_t lock; + void *entry[0]; /* + * Must have this definition in here for the proper + * alignment of array_cache. Also simplifies accessing + * the entries. + * [0] is for gcc 2.95. It should really be []. + */ }; /* bootstrap: The caches do not work without cpuarrays anymore, @@ -212,100 +280,157 @@ struct array_cache { #define BOOT_CPUCACHE_ENTRIES 1 struct arraycache_init { struct array_cache cache; - void * entries[BOOT_CPUCACHE_ENTRIES]; + void *entries[BOOT_CPUCACHE_ENTRIES]; }; /* - * The slab lists of all objects. - * Hopefully reduce the internal fragmentation - * NUMA: The spinlock could be moved from the kmem_cache_t - * into this structure, too. Figure out what causes - * fewer cross-node spinlock operations. + * The slab lists for all objects. */ struct kmem_list3 { - struct list_head slabs_partial; /* partial list first, better asm code */ - struct list_head slabs_full; - struct list_head slabs_free; - unsigned long free_objects; - int free_touched; - unsigned long next_reap; - struct array_cache *shared; + struct list_head slabs_partial; /* partial list first, better asm code */ + struct list_head slabs_full; + struct list_head slabs_free; + unsigned long free_objects; + unsigned long next_reap; + int free_touched; + unsigned int free_limit; + unsigned int colour_next; /* Per-node cache coloring */ + spinlock_t list_lock; + struct array_cache *shared; /* shared per node */ + struct array_cache **alien; /* on other nodes */ }; -#define LIST3_INIT(parent) \ - { \ - .slabs_full = LIST_HEAD_INIT(parent.slabs_full), \ - .slabs_partial = LIST_HEAD_INIT(parent.slabs_partial), \ - .slabs_free = LIST_HEAD_INIT(parent.slabs_free) \ - } -#define list3_data(cachep) \ - (&(cachep)->lists) +/* + * Need this for bootstrapping a per node allocator. + */ +#define NUM_INIT_LISTS (2 * MAX_NUMNODES + 1) +struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS]; +#define CACHE_CACHE 0 +#define SIZE_AC 1 +#define SIZE_L3 (1 + MAX_NUMNODES) + +/* + * This function must be completely optimized away if + * a constant is passed to it. Mostly the same as + * what is in linux/slab.h except it returns an + * index. + */ +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; +} + +#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) -/* NUMA: per-node */ -#define list3_data_ptr(cachep, ptr) \ - list3_data(cachep) +#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) /* - * kmem_cache_t + * struct kmem_cache * * manages a cache. */ - -struct kmem_cache_s { + +struct kmem_cache { /* 1) per-cpu data, touched during every alloc/free */ - struct array_cache *array[NR_CPUS]; - unsigned int batchcount; - unsigned int limit; + struct array_cache *array[NR_CPUS]; + unsigned int batchcount; + unsigned int limit; + unsigned int shared; + unsigned int buffer_size; /* 2) touched by every alloc & free from the backend */ - struct kmem_list3 lists; - /* NUMA: kmem_3list_t *nodelists[MAX_NUMNODES] */ - unsigned int objsize; - unsigned int flags; /* constant flags */ - unsigned int num; /* # of objs per slab */ - unsigned int free_limit; /* upper limit of objects in the lists */ - spinlock_t spinlock; + struct kmem_list3 *nodelists[MAX_NUMNODES]; + unsigned int flags; /* constant flags */ + unsigned int num; /* # of objs per slab */ + spinlock_t spinlock; /* 3) cache_grow/shrink */ /* order of pgs per slab (2^n) */ - unsigned int gfporder; + unsigned int gfporder; /* force GFP flags, e.g. GFP_DMA */ - unsigned int gfpflags; + gfp_t gfpflags; - size_t colour; /* cache colouring range */ - unsigned int colour_off; /* colour offset */ - unsigned int colour_next; /* cache colouring */ - kmem_cache_t *slabp_cache; - unsigned int slab_size; - unsigned int dflags; /* dynamic flags */ + size_t colour; /* cache colouring range */ + unsigned int colour_off; /* colour offset */ + struct kmem_cache *slabp_cache; + unsigned int slab_size; + unsigned int dflags; /* dynamic flags */ /* constructor func */ - void (*ctor)(void *, kmem_cache_t *, unsigned long); + void (*ctor) (void *, struct kmem_cache *, unsigned long); /* de-constructor func */ - void (*dtor)(void *, kmem_cache_t *, unsigned long); + void (*dtor) (void *, struct kmem_cache *, unsigned long); /* 4) cache creation/removal */ - const char *name; - struct list_head next; + const char *name; + struct list_head next; /* 5) statistics */ #if STATS - unsigned long num_active; - unsigned long num_allocations; - unsigned long high_mark; - unsigned long grown; - unsigned long reaped; - unsigned long errors; - unsigned long max_freeable; - atomic_t allochit; - atomic_t allocmiss; - atomic_t freehit; - atomic_t freemiss; + unsigned long num_active; + unsigned long num_allocations; + unsigned long high_mark; + unsigned long grown; + unsigned long reaped; + unsigned long errors; + unsigned long max_freeable; + unsigned long node_allocs; + unsigned long node_frees; + atomic_t allochit; + atomic_t allocmiss; + atomic_t freehit; + atomic_t freemiss; #endif #if DEBUG - int dbghead; - int reallen; + /* + * If debugging is enabled, then the allocator can add additional + * fields and/or padding to every object. buffer_size contains the total + * object size including these internal fields, the following two + * variables contain the offset to the user object and its size. + */ + int obj_offset; + int obj_size; #endif }; @@ -316,7 +441,7 @@ struct kmem_cache_s { /* Optimization question: fewer reaps means less * probability for unnessary cpucache drain/refill cycles. * - * OTHO the cpuarrays can contain lots of objects, + * OTOH the cpuarrays can contain lots of objects, * which could lock up otherwise freeable slabs. */ #define REAPTIMEOUT_CPUC (2*HZ) @@ -332,6 +457,8 @@ struct kmem_cache_s { (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_SET_FREEABLE(x, i) \ do { if ((x)->max_freeable < i) \ (x)->max_freeable = i; \ @@ -349,6 +476,8 @@ struct kmem_cache_s { #define STATS_INC_REAPED(x) do { } while (0) #define STATS_SET_HIGH(x) do { } while (0) #define STATS_INC_ERR(x) do { } while (0) +#define STATS_INC_NODEALLOCS(x) do { } while (0) +#define STATS_INC_NODEFREES(x) do { } while (0) #define STATS_SET_FREEABLE(x, i) \ do { } while (0) @@ -372,68 +501,54 @@ struct kmem_cache_s { /* memory layout of objects: * 0 : objp - * 0 .. cachep->dbghead - BYTES_PER_WORD - 1: padding. This ensures that + * 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->dbghead - BYTES_PER_WORD .. cachep->dbghead - 1: + * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1: * redzone word. - * cachep->dbghead: The real object. - * cachep->objsize - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] - * cachep->objsize - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long] + * cachep->obj_offset: The real object. + * cachep->buffer_size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] + * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long] */ -static inline int obj_dbghead(kmem_cache_t *cachep) +static int obj_offset(struct kmem_cache *cachep) { - return cachep->dbghead; + return cachep->obj_offset; } -static inline int obj_reallen(kmem_cache_t *cachep) +static int obj_size(struct kmem_cache *cachep) { - return cachep->reallen; + return cachep->obj_size; } -static unsigned long *dbg_redzone1(kmem_cache_t *cachep, void *objp) +static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); - return (unsigned long*) (objp+obj_dbghead(cachep)-BYTES_PER_WORD); + return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD); } -static unsigned long *dbg_redzone2(kmem_cache_t *cachep, void *objp) +static unsigned long *dbg_redzone2(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); if (cachep->flags & SLAB_STORE_USER) - return (unsigned long*) (objp+cachep->objsize-2*BYTES_PER_WORD); - return (unsigned long*) (objp+cachep->objsize-BYTES_PER_WORD); + return (unsigned long *)(objp + cachep->buffer_size - + 2 * BYTES_PER_WORD); + return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD); } -static void **dbg_userword(kmem_cache_t *cachep, void *objp) +static void **dbg_userword(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_STORE_USER)); - return (void**)(objp+cachep->objsize-BYTES_PER_WORD); + return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD); } + #else -static inline int obj_dbghead(kmem_cache_t *cachep) -{ - return 0; -} -static inline int obj_reallen(kmem_cache_t *cachep) -{ - return cachep->objsize; -} -static inline unsigned long *dbg_redzone1(kmem_cache_t *cachep, void *objp) -{ - BUG(); - return 0; -} -static inline unsigned long *dbg_redzone2(kmem_cache_t *cachep, void *objp) -{ - BUG(); - return 0; -} -static inline void **dbg_userword(kmem_cache_t *cachep, void *objp) -{ - BUG(); - return 0; -} + +#define obj_offset(x) 0 +#define obj_size(cachep) (cachep->buffer_size) +#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long *)NULL;}) +#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long *)NULL;}) +#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;}) + #endif /* @@ -458,57 +573,86 @@ static inline void **dbg_userword(kmem_cache_t *cachep, void *objp) #define BREAK_GFP_ORDER_LO 0 static int slab_break_gfp_order = BREAK_GFP_ORDER_LO; -/* Macros for storing/retrieving the cachep and or slab from the +/* Functions for storing/retrieving the cachep and or slab from the * global 'mem_map'. These are used to find the slab an obj belongs to. * With kfree(), these are used to find the cache which an obj belongs to. */ -#define SET_PAGE_CACHE(pg,x) ((pg)->lru.next = (struct list_head *)(x)) -#define GET_PAGE_CACHE(pg) ((kmem_cache_t *)(pg)->lru.next) -#define SET_PAGE_SLAB(pg,x) ((pg)->lru.prev = (struct list_head *)(x)) -#define GET_PAGE_SLAB(pg) ((struct slab *)(pg)->lru.prev) +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) +{ + 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) +{ + return (struct slab *)page->lru.prev; +} + +static inline struct kmem_cache *virt_to_cache(const void *obj) +{ + struct page *page = virt_to_page(obj); + return page_get_cache(page); +} + +static inline struct slab *virt_to_slab(const void *obj) +{ + struct page *page = virt_to_page(obj); + return page_get_slab(page); +} /* These are the default caches for kmalloc. Custom caches can have other sizes. */ struct cache_sizes malloc_sizes[] = { #define CACHE(x) { .cs_size = (x) }, #include - { 0, } + CACHE(ULONG_MAX) #undef CACHE }; - EXPORT_SYMBOL(malloc_sizes); /* Must match cache_sizes above. Out of line to keep cache footprint low. */ -static struct cache_names { +struct cache_names { char *name; char *name_dma; -} cache_names[] = { +}; + +static struct cache_names __initdata cache_names[] = { #define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" }, #include - { 0, } + {NULL,} #undef CACHE }; -struct arraycache_init initarray_cache __initdata = { { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; -struct arraycache_init initarray_generic __initdata = { { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; +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} }; /* internal cache of cache description objs */ -static kmem_cache_t cache_cache = { - .lists = LIST3_INIT(cache_cache.lists), - .batchcount = 1, - .limit = BOOT_CPUCACHE_ENTRIES, - .objsize = sizeof(kmem_cache_t), - .flags = SLAB_NO_REAP, - .spinlock = SPIN_LOCK_UNLOCKED, - .name = "kmem_cache", +static struct kmem_cache cache_cache = { + .batchcount = 1, + .limit = BOOT_CPUCACHE_ENTRIES, + .shared = 1, + .buffer_size = sizeof(struct kmem_cache), + .flags = SLAB_NO_REAP, + .spinlock = SPIN_LOCK_UNLOCKED, + .name = "kmem_cache", #if DEBUG - .reallen = sizeof(kmem_cache_t), + .obj_size = sizeof(struct kmem_cache), #endif }; /* Guard access to the cache-chain. */ -static struct semaphore cache_chain_sem; - -struct list_head cache_chain; +static DEFINE_MUTEX(cache_chain_mutex); +static struct list_head cache_chain; /* * vm_enough_memory() looks at this to determine how many @@ -517,168 +661,520 @@ struct list_head cache_chain; * SLAB_RECLAIM_ACCOUNT turns this on per-slab */ atomic_t slab_reclaim_pages; -EXPORT_SYMBOL(slab_reclaim_pages); /* * chicken and egg problem: delay the per-cpu array allocation * until the general caches are up. */ -enum { +static enum { NONE, - PARTIAL, + PARTIAL_AC, + PARTIAL_L3, FULL } g_cpucache_up; -static DEFINE_PER_CPU(struct timer_list, reap_timers); +static DEFINE_PER_CPU(struct work_struct, reap_work); -static void reap_timer_fnc(unsigned long data); -static void free_block(kmem_cache_t* cachep, void** objpp, int len); -static void enable_cpucache (kmem_cache_t *cachep); +static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node); +static void enable_cpucache(struct kmem_cache *cachep); +static void cache_reap(void *unused); +static int __node_shrink(struct kmem_cache *cachep, int node); -static inline void ** ac_entry(struct array_cache *ac) +static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { - return (void**)(ac+1); + return cachep->array[smp_processor_id()]; } -static inline struct array_cache *ac_data(kmem_cache_t *cachep) +static inline struct kmem_cache *__find_general_cachep(size_t size, gfp_t gfpflags) { - return cachep->array[smp_processor_id()]; + struct cache_sizes *csizep = malloc_sizes; + +#if DEBUG + /* This happens if someone tries to call + * kmem_cache_create(), or __kmalloc(), before + * the generic caches are initialized. + */ + BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL); +#endif + while (size > csizep->cs_size) + csizep++; + + /* + * Really subtle: The last entry with cs->cs_size==ULONG_MAX + * has cs_{dma,}cachep==NULL. Thus no special case + * for large kmalloc calls required. + */ + if (unlikely(gfpflags & GFP_DMA)) + return csizep->cs_dmacachep; + return csizep->cs_cachep; } -/* Cal the num objs, wastage, and bytes left over for a given slab size. */ -static void cache_estimate (unsigned long gfporder, size_t size, size_t align, - int flags, size_t *left_over, unsigned int *num) +struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags) { - int i; - size_t wastage = PAGE_SIZE< 0) - i--; +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 (i > SLAB_LIMIT) - i = SLAB_LIMIT; + if (nr_objs > SLAB_LIMIT) + nr_objs = SLAB_LIMIT; - *num = i; - wastage -= i*size; - wastage -= ALIGN(base+i*extra, align); - *left_over = wastage; + 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(__FUNCTION__, cachep, msg) -static void __slab_error(const char *function, kmem_cache_t *cachep, char *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); + function, cachep->name, msg); dump_stack(); } +#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, reap_node); + +static void init_reap_node(int cpu) +{ + int node; + + node = next_node(cpu_to_node(cpu), node_online_map); + if (node == MAX_NUMNODES) + node = 0; + + __get_cpu_var(reap_node) = node; +} + +static void next_reap_node(void) +{ + int node = __get_cpu_var(reap_node); + + /* + * Also drain per cpu pages on remote zones + */ + if (node != numa_node_id()) + drain_node_pages(node); + + node = next_node(node, node_online_map); + if (unlikely(node >= MAX_NUMNODES)) + node = first_node(node_online_map); + __get_cpu_var(reap_node) = node; +} + +#else +#define init_reap_node(cpu) do { } while (0) +#define next_reap_node(void) do { } while (0) +#endif + /* - * Start the reap timer running on the target CPU. We run at around 1 to 2Hz. - * Add the CPU number into the expiry time to minimize the possibility of the - * CPUs getting into lockstep and contending for the global cache chain lock. + * 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 __devinit start_cpu_timer(int cpu) { - struct timer_list *rt = &per_cpu(reap_timers, cpu); + struct work_struct *reap_work = &per_cpu(reap_work, cpu); + + /* + * When this gets called from do_initcalls via cpucache_init(), + * init_workqueues() has already run, so keventd will be setup + * at that time. + */ + if (keventd_up() && reap_work->func == NULL) { + init_reap_node(cpu); + INIT_WORK(reap_work, cache_reap, NULL); + schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu); + } +} + +static struct array_cache *alloc_arraycache(int node, int entries, + int batchcount) +{ + int memsize = sizeof(void *) * entries + sizeof(struct array_cache); + struct array_cache *nc = NULL; - if (rt->function == NULL) { - init_timer(rt); - rt->expires = jiffies + HZ + 3*cpu; - rt->data = cpu; - rt->function = reap_timer_fnc; - add_timer_on(rt, cpu); + nc = kmalloc_node(memsize, GFP_KERNEL, node); + if (nc) { + nc->avail = 0; + nc->limit = entries; + nc->batchcount = batchcount; + nc->touched = 0; + spin_lock_init(&nc->lock); } + return nc; } -#ifdef CONFIG_HOTPLUG_CPU -static void stop_cpu_timer(int cpu) +#ifdef CONFIG_NUMA +static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int); + +static struct array_cache **alloc_alien_cache(int node, int limit) +{ + struct array_cache **ac_ptr; + int memsize = sizeof(void *) * MAX_NUMNODES; + int i; + + if (limit > 1) + limit = 12; + ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node); + if (ac_ptr) { + for_each_node(i) { + if (i == node || !node_online(i)) { + ac_ptr[i] = NULL; + continue; + } + ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d); + 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); + free_block(cachep, ac->entry, ac->avail, node); + ac->avail = 0; + spin_unlock(&rl3->list_lock); + } +} + +/* + * Called from cache_reap() to regularly drain alien caches round robin. + */ +static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) { - struct timer_list *rt = &per_cpu(reap_timers, cpu); + int node = __get_cpu_var(reap_node); - if (rt->function) { - del_timer_sync(rt); - WARN_ON(timer_pending(rt)); - rt->function = NULL; + if (l3->alien) { + struct array_cache *ac = l3->alien[node]; + if (ac && ac->avail) { + spin_lock_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); + } + } +} +#else + +#define drain_alien_cache(cachep, alien) do { } while (0) +#define reap_alien(cachep, l3) do { } while (0) + +static inline struct array_cache **alloc_alien_cache(int node, int limit) +{ + return (struct array_cache **) 0x01020304ul; +} + +static inline void free_alien_cache(struct array_cache **ac_ptr) +{ +} + #endif static int __devinit cpuup_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) + unsigned long action, void *hcpu) { long cpu = (long)hcpu; - kmem_cache_t* cachep; + struct kmem_cache *cachep; + struct kmem_list3 *l3 = NULL; + int node = cpu_to_node(cpu); + int memsize = sizeof(struct kmem_list3); switch (action) { case CPU_UP_PREPARE: - down(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); + /* 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_list3 and not this cpu's kmem_list3 + */ + + list_for_each_entry(cachep, &cache_chain, next) { + /* setup 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->nodelists[node]) { + if (!(l3 = kmalloc_node(memsize, + GFP_KERNEL, node))) + goto bad; + kmem_list3_init(l3); + l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + + /* + * The l3s don't come and go as CPUs come and + * go. cache_chain_mutex is sufficient + * protection here. + */ + 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); + } + + /* Now we can go ahead with allocating the shared array's + & array cache's */ list_for_each_entry(cachep, &cache_chain, next) { - int memsize; struct array_cache *nc; + struct array_cache *shared; + struct array_cache **alien; - memsize = sizeof(void*)*cachep->limit+sizeof(struct array_cache); - nc = kmalloc(memsize, GFP_KERNEL); + nc = alloc_arraycache(node, cachep->limit, + cachep->batchcount); if (!nc) goto bad; - nc->avail = 0; - nc->limit = cachep->limit; - nc->batchcount = cachep->batchcount; - nc->touched = 0; + shared = alloc_arraycache(node, + cachep->shared * cachep->batchcount, + 0xbaadf00d); + if (!shared) + goto bad; - spin_lock_irq(&cachep->spinlock); + alien = alloc_alien_cache(node, cachep->limit); + if (!alien) + goto bad; cachep->array[cpu] = nc; - cachep->free_limit = (1+num_online_cpus())*cachep->batchcount - + cachep->num; - spin_unlock_irq(&cachep->spinlock); + l3 = cachep->nodelists[node]; + BUG_ON(!l3); + + spin_lock_irq(&l3->list_lock); + if (!l3->shared) { + /* + * We are serialised from CPU_DEAD or + * CPU_UP_CANCELLED by the cpucontrol lock + */ + 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); } - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); break; case CPU_ONLINE: start_cpu_timer(cpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: - stop_cpu_timer(cpu); + /* + * Even if all the cpus of a node are down, we don't free the + * kmem_list3 of any cache. This to avoid a race between + * cpu_down, and a kmalloc allocation from another cpu for + * memory from the node of the cpu going down. The list3 + * structure is usually allocated from kmem_cache_create() and + * gets destroyed at kmem_cache_destroy(). + */ /* fall thru */ case CPU_UP_CANCELED: - down(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; + struct array_cache *shared; + struct array_cache **alien; + cpumask_t mask; - spin_lock_irq(&cachep->spinlock); + mask = node_to_cpumask(node); /* cpu is dead; no one can alloc from it. */ nc = cachep->array[cpu]; cachep->array[cpu] = NULL; - cachep->free_limit -= cachep->batchcount; - free_block(cachep, ac_entry(nc), nc->avail); - spin_unlock_irq(&cachep->spinlock); + l3 = cachep->nodelists[node]; + + if (!l3) + goto free_array_cache; + + spin_lock_irq(&l3->list_lock); + + /* Free limit for this kmem_list3 */ + l3->free_limit -= cachep->batchcount; + if (nc) + free_block(cachep, nc->entry, nc->avail, node); + + if (!cpus_empty(mask)) { + spin_unlock_irq(&l3->list_lock); + goto free_array_cache; + } + + shared = l3->shared; + if (shared) { + free_block(cachep, l3->shared->entry, + l3->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); } - up(&cache_chain_sem); + /* + * 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, &cache_chain, next) { + l3 = cachep->nodelists[node]; + if (!l3) + continue; + spin_lock_irq(&l3->list_lock); + /* free slabs belonging to this node */ + __node_shrink(cachep, node); + spin_unlock_irq(&l3->list_lock); + } + mutex_unlock(&cache_chain_mutex); break; #endif } return NOTIFY_OK; -bad: - up(&cache_chain_sem); + bad: + mutex_unlock(&cache_chain_mutex); return NOTIFY_BAD; } static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 }; +/* + * swap the static kmem_list3 with kmalloced memory + */ +static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, int nodeid) +{ + struct kmem_list3 *ptr; + + BUG_ON(cachep->nodelists[nodeid] != list); + ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid); + BUG_ON(!ptr); + + local_irq_disable(); + memcpy(ptr, list, sizeof(struct kmem_list3)); + MAKE_ALL_LISTS(cachep, ptr, nodeid); + cachep->nodelists[nodeid] = ptr; + local_irq_enable(); +} + /* Initialisation. * Called after the gfp() functions have been enabled, and before smp_init(). */ @@ -687,6 +1183,14 @@ void __init kmem_cache_init(void) size_t left_over; struct cache_sizes *sizes; struct cache_names *names; + int i; + int order; + + for (i = 0; i < NUM_INIT_LISTS; i++) { + kmem_list3_init(&initkmem_list3[i]); + if (i < MAX_NUMNODES) + cache_cache.nodelists[i] = NULL; + } /* * Fragmentation resistance on low memory - only use bigger @@ -695,117 +1199,170 @@ void __init kmem_cache_init(void) if (num_physpages > (32 << 20) >> PAGE_SHIFT) slab_break_gfp_order = BREAK_GFP_ORDER_HI; - /* Bootstrap is tricky, because several objects are allocated * from caches that do not exist yet: - * 1) initialize the cache_cache cache: it contains the kmem_cache_t + * 1) initialize the cache_cache cache: it contains the struct kmem_cache * structures of all caches, except cache_cache itself: cache_cache * is statically allocated. - * Initially an __init data area is used for the head array, it's - * replaced with a kmalloc allocated array at the end of the bootstrap. + * Initially an __init data area is used for the head array and the + * kmem_list3 structures, it's replaced with a kmalloc allocated + * array at the end of the bootstrap. * 2) Create the first kmalloc cache. - * The kmem_cache_t 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. + * 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 cache_cache and the first * kmalloc cache with kmalloc allocated arrays. - * 5) Resize the head arrays of the kmalloc caches to their final sizes. + * 5) Replace the __init data for kmem_list3 for cache_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 cache_cache */ - init_MUTEX(&cache_chain_sem); INIT_LIST_HEAD(&cache_chain); list_add(&cache_cache.next, &cache_chain); cache_cache.colour_off = cache_line_size(); cache_cache.array[smp_processor_id()] = &initarray_cache.cache; + cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE]; - cache_cache.objsize = ALIGN(cache_cache.objsize, cache_line_size()); + cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size()); - cache_estimate(0, cache_cache.objsize, cache_line_size(), 0, - &left_over, &cache_cache.num); + 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; + } if (!cache_cache.num) BUG(); - - cache_cache.colour = left_over/cache_cache.colour_off; - cache_cache.colour_next = 0; - cache_cache.slab_size = ALIGN(cache_cache.num*sizeof(kmem_bufctl_t) + - sizeof(struct slab), cache_line_size()); + 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()); /* 2+3) create the kmalloc caches */ sizes = malloc_sizes; names = cache_names; - while (sizes->cs_size) { - /* For performance, all the general caches are L1 aligned. + /* Initialize the caches that provide memory for the array cache + * and the kmem_list3 structures first. + * Without this, further allocations will bug + */ + + sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name, + sizes[INDEX_AC].cs_size, + ARCH_KMALLOC_MINALIGN, + (ARCH_KMALLOC_FLAGS | + SLAB_PANIC), NULL, 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, + NULL); + + while (sizes->cs_size != ULONG_MAX) { + /* + * For performance, all the general caches are L1 aligned. * This should be particularly beneficial on SMP boxes, as it * eliminates "false sharing". * Note for systems short on memory removing the alignment will - * allow tighter packing of the smaller caches. */ - sizes->cs_cachep = kmem_cache_create( - names->name, sizes->cs_size, - ARCH_KMALLOC_MINALIGN, 0, NULL, NULL); + * allow tighter packing of the smaller caches. + */ if (!sizes->cs_cachep) - BUG(); + sizes->cs_cachep = kmem_cache_create(names->name, + sizes->cs_size, + ARCH_KMALLOC_MINALIGN, + (ARCH_KMALLOC_FLAGS + | SLAB_PANIC), + NULL, NULL); /* Inc off-slab bufctl limit until the ceiling is hit. */ if (!(OFF_SLAB(sizes->cs_cachep))) { - offslab_limit = sizes->cs_size-sizeof(struct slab); + offslab_limit = sizes->cs_size - sizeof(struct slab); offslab_limit /= sizeof(kmem_bufctl_t); } - sizes->cs_dmacachep = kmem_cache_create( - names->name_dma, sizes->cs_size, - ARCH_KMALLOC_MINALIGN, SLAB_CACHE_DMA, NULL, NULL); - if (!sizes->cs_dmacachep) - BUG(); + sizes->cs_dmacachep = kmem_cache_create(names->name_dma, + sizes->cs_size, + ARCH_KMALLOC_MINALIGN, + (ARCH_KMALLOC_FLAGS | + SLAB_CACHE_DMA | + SLAB_PANIC), NULL, + NULL); sizes++; names++; } /* 4) Replace the bootstrap head arrays */ { - void * ptr; - + void *ptr; + ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); + local_irq_disable(); - BUG_ON(ac_data(&cache_cache) != &initarray_cache.cache); - memcpy(ptr, ac_data(&cache_cache), sizeof(struct arraycache_init)); + BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache); + memcpy(ptr, cpu_cache_get(&cache_cache), + sizeof(struct arraycache_init)); cache_cache.array[smp_processor_id()] = ptr; local_irq_enable(); - + ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); + local_irq_disable(); - BUG_ON(ac_data(malloc_sizes[0].cs_cachep) != &initarray_generic.cache); - memcpy(ptr, ac_data(malloc_sizes[0].cs_cachep), - sizeof(struct arraycache_init)); - malloc_sizes[0].cs_cachep->array[smp_processor_id()] = ptr; + 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)); + malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] = + ptr; local_irq_enable(); } + /* 5) Replace the bootstrap kmem_list3's */ + { + int node; + /* Replace the static kmem_list3 structures for the boot cpu */ + init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], + numa_node_id()); + + for_each_online_node(node) { + init_list(malloc_sizes[INDEX_AC].cs_cachep, + &initkmem_list3[SIZE_AC + node], node); + + if (INDEX_AC != INDEX_L3) { + init_list(malloc_sizes[INDEX_L3].cs_cachep, + &initkmem_list3[SIZE_L3 + node], + node); + } + } + } - /* 5) resize the head arrays to their final sizes */ + /* 6) resize the head arrays to their final sizes */ { - kmem_cache_t *cachep; - down(&cache_chain_sem); + struct kmem_cache *cachep; + mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) - enable_cpucache(cachep); - up(&cache_chain_sem); + enable_cpucache(cachep); + mutex_unlock(&cache_chain_mutex); } /* Done! */ g_cpucache_up = FULL; /* Register a cpu startup notifier callback - * that initializes ac_data for all new cpus + * that initializes cpu_cache_get for all new cpus */ register_cpu_notifier(&cpucache_notifier); - /* The reap timers are started later, with a module init call: * That part of the kernel is not yet operational. */ } -int __init cpucache_init(void) +static int __init cpucache_init(void) { int cpu; @@ -813,10 +1370,8 @@ int __init cpucache_init(void) * Register the timers that return unneeded * pages to gfp. */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { - if (cpu_online(cpu)) - start_cpu_timer(cpu); - } + for_each_online_cpu(cpu) + start_cpu_timer(cpu); return 0; } @@ -830,23 +1385,25 @@ __initcall(cpucache_init); * did not request dmaable memory, we might get it, but that * would be relatively rare and ignorable. */ -static inline void *kmem_getpages(kmem_cache_t *cachep, unsigned long flags) +static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) { + struct page *page; void *addr; + int i; flags |= cachep->gfpflags; - addr = (void*)__get_free_pages(flags, cachep->gfporder); - if (addr) { - int i = (1 << cachep->gfporder); - struct page *page = virt_to_page(addr); - - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_add(i, &slab_reclaim_pages); - add_page_state(nr_slab, i); - while (i--) { - SetPageSlab(page); - page++; - } + page = alloc_pages_node(nodeid, flags, cachep->gfporder); + if (!page) + return NULL; + addr = page_address(page); + + i = (1 << cachep->gfporder); + if (cachep->flags & SLAB_RECLAIM_ACCOUNT) + atomic_add(i, &slab_reclaim_pages); + add_page_state(nr_slab, i); + while (i--) { + SetPageSlab(page); + page++; } return addr; } @@ -854,9 +1411,9 @@ static inline void *kmem_getpages(kmem_cache_t *cachep, unsigned long flags) /* * Interface to system's page release. */ -static inline void kmem_freepages(kmem_cache_t *cachep, void *addr) +static void kmem_freepages(struct kmem_cache *cachep, void *addr) { - unsigned long i = (1<gfporder); + unsigned long i = (1 << cachep->gfporder); struct page *page = virt_to_page(addr); const unsigned long nr_freed = i; @@ -869,26 +1426,37 @@ static inline void kmem_freepages(kmem_cache_t *cachep, void *addr) if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; free_pages((unsigned long)addr, cachep->gfporder); - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_sub(1<gfporder, &slab_reclaim_pages); + if (cachep->flags & SLAB_RECLAIM_ACCOUNT) + atomic_sub(1 << cachep->gfporder, &slab_reclaim_pages); +} + +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(kmem_cache_t *cachep, unsigned long *addr, unsigned long caller) +static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, + unsigned long caller) { - int size = obj_reallen(cachep); + int size = obj_size(cachep); - addr = (unsigned long *)&((char*)addr)[obj_dbghead(cachep)]; + addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)]; - if (size < 5*sizeof(unsigned long)) + if (size < 5 * sizeof(unsigned long)) return; - *addr++=0x12345678; - *addr++=caller; - *addr++=smp_processor_id(); - size -= 3*sizeof(unsigned long); + *addr++ = 0x12345678; + *addr++ = caller; + *addr++ = smp_processor_id(); + size -= 3 * sizeof(unsigned long); { unsigned long *sptr = &caller; unsigned long svalue; @@ -896,7 +1464,7 @@ static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr, unsigned while (!kstack_end(sptr)) { svalue = *sptr++; if (kernel_text_address(svalue)) { - *addr++=svalue; + *addr++ = svalue; size -= sizeof(unsigned long); if (size <= sizeof(unsigned long)) break; @@ -904,88 +1472,89 @@ static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr, unsigned } } - *addr++=0x87654321; + *addr++ = 0x87654321; } #endif -static void poison_obj(kmem_cache_t *cachep, void *addr, unsigned char val) +static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) { - int size = obj_reallen(cachep); - addr = &((char*)addr)[obj_dbghead(cachep)]; + int size = obj_size(cachep); + addr = &((char *)addr)[obj_offset(cachep)]; memset(addr, val, size); - *(unsigned char *)(addr+size-1) = POISON_END; + *(unsigned char *)(addr + size - 1) = POISON_END; } static void dump_line(char *data, int offset, int limit) { int i; printk(KERN_ERR "%03x:", offset); - for (i=0;iflags & SLAB_RED_ZONE) { printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n", - *dbg_redzone1(cachep, objp), - *dbg_redzone2(cachep, objp)); + *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(KERN_ERR "Last user: [<%p>]", + *dbg_userword(cachep, objp)); + print_symbol("(%s)", + (unsigned long)*dbg_userword(cachep, objp)); printk("\n"); } - realobj = (char*)objp+obj_dbghead(cachep); - size = obj_reallen(cachep); - for (i=0; i size) - limit = size-i; + if (i + limit > size) + limit = size - i; dump_line(realobj, i, limit); } -#endif } -#if DEBUG - -static void check_poison_obj(kmem_cache_t *cachep, void *objp) +static void check_poison_obj(struct kmem_cache *cachep, void *objp) { char *realobj; int size, i; int lines = 0; - realobj = (char*)objp+obj_dbghead(cachep); - size = obj_reallen(cachep); + realobj = (char *)objp + obj_offset(cachep); + size = obj_size(cachep); - for (i=0;i size) - limit = size-i; + if (i + limit > size) + limit = size - i; dump_line(realobj, i, limit); i += 16; lines++; @@ -998,43 +1567,46 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp) /* Print some data about the neighboring objects, if they * exist: */ - struct slab *slabp = GET_PAGE_SLAB(virt_to_page(objp)); + struct slab *slabp = virt_to_slab(objp); int objnr; - objnr = (objp-slabp->s_mem)/cachep->objsize; + objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size; if (objnr) { - objp = slabp->s_mem+(objnr-1)*cachep->objsize; - realobj = (char*)objp+obj_dbghead(cachep); + objp = slabp->s_mem + (objnr - 1) * cachep->buffer_size; + realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Prev obj: start=%p, len=%d\n", - realobj, size); + realobj, size); print_objinfo(cachep, objp, 2); } - if (objnr+1 < cachep->num) { - objp = slabp->s_mem+(objnr+1)*cachep->objsize; - realobj = (char*)objp+obj_dbghead(cachep); + if (objnr + 1 < cachep->num) { + objp = slabp->s_mem + (objnr + 1) * cachep->buffer_size; + realobj = (char *)objp + obj_offset(cachep); printk(KERN_ERR "Next obj: start=%p, len=%d\n", - realobj, size); + realobj, size); print_objinfo(cachep, objp, 2); } } } #endif -/* 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. +#if DEBUG +/** + * slab_destroy_objs - call the registered destructor for each object in + * a slab that is to be destroyed. */ -static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) +static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp) { -#if DEBUG int i; for (i = 0; i < cachep->num; i++) { - void *objp = slabp->s_mem + cachep->objsize * i; + void *objp = slabp->s_mem + cachep->buffer_size * i; if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->objsize%PAGE_SIZE)==0 && OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE,1); + 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 @@ -1044,27 +1616,124 @@ static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) slab_error(cachep, "start of a freed object " - "was overwritten"); + "was overwritten"); if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) slab_error(cachep, "end of a freed object " - "was overwritten"); + "was overwritten"); } if (cachep->dtor && !(cachep->flags & SLAB_POISON)) - (cachep->dtor)(objp+obj_dbghead(cachep), cachep, 0); + (cachep->dtor) (objp + obj_offset(cachep), cachep, 0); } +} #else +static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp) +{ if (cachep->dtor) { int i; for (i = 0; i < cachep->num; i++) { - void* objp = slabp->s_mem+cachep->objsize*i; - (cachep->dtor)(objp, cachep, 0); + void *objp = slabp->s_mem + cachep->buffer_size * i; + (cachep->dtor) (objp, cachep, 0); } } +} #endif - - kmem_freepages(cachep, slabp->s_mem-slabp->colouroff); - if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->slabp_cache, slabp); + +/** + * 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_objs(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); + } +} + +/* For setting up all the kmem_list3s for cache whose buffer_size is same + as size of kmem_list3. */ +static void set_up_list3s(struct kmem_cache *cachep, int index) +{ + 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; + } +} + +/** + * 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 inline size_t calculate_slab_order(struct kmem_cache *cachep, + size_t size, size_t align, unsigned long flags) +{ + size_t left_over = 0; + int gfporder; + + for (gfporder = 0 ; gfporder <= MAX_GFP_ORDER; gfporder++) { + unsigned int num; + size_t remainder; + + cache_estimate(gfporder, size, align, flags, &remainder, &num); + if (!num) + continue; + + /* More than offslab_limit objects will cause problems */ + if ((flags & CFLGS_OFF_SLAB) && 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_break_gfp_order) + break; + + /* + * Acceptable internal fragmentation? + */ + if ((left_over * 8) <= (PAGE_SIZE << gfporder)) + break; + } + return left_over; } /** @@ -1096,40 +1765,74 @@ static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) * %SLAB_NO_REAP - Don't automatically reap this cache when we're under * memory pressure. * - * %SLAB_HWCACHE_ALIGN - This flag has no effect and will be removed soon. - * + * %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. */ -kmem_cache_t * +struct kmem_cache * kmem_cache_create (const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void*, kmem_cache_t *, unsigned long), - void (*dtor)(void*, kmem_cache_t *, unsigned long)) + unsigned long flags, void (*ctor)(void*, struct kmem_cache *, unsigned long), + void (*dtor)(void*, struct kmem_cache *, unsigned long)) { - size_t left_over, slab_size; - kmem_cache_t *cachep = NULL; + size_t left_over, slab_size, ralign; + struct kmem_cache *cachep = NULL; + struct list_head *p; /* * Sanity checks... these are all serious usage bugs. */ if ((!name) || - in_interrupt() || - (size < BYTES_PER_WORD) || - (size > (1< (1 << MAX_OBJ_ORDER) * PAGE_SIZE) || (dtor && !ctor)) { + printk(KERN_ERR "%s: Early error in slab %s\n", + __FUNCTION__, name); + BUG(); + } + + /* + * Prevent CPUs from coming and going. + * lock_cpu_hotplug() nests outside cache_chain_mutex + */ + lock_cpu_hotplug(); + + mutex_lock(&cache_chain_mutex); + + list_for_each(p, &cache_chain) { + struct kmem_cache *pc = list_entry(p, struct kmem_cache, next); + mm_segment_t old_fs = get_fs(); + char tmp; + int res; + + /* + * This happens when the module gets unloaded and doesn't + * destroy its slab cache and no-one else reuses the vmalloc + * area of the module. Print a warning. + */ + set_fs(KERNEL_DS); + res = __get_user(tmp, pc->name); + set_fs(old_fs); + if (res) { + printk("SLAB: cache with size %d has lost its name\n", + pc->buffer_size); + continue; + } + + if (!strcmp(pc->name, name)) { + printk("kmem_cache_create: duplicate cache %s\n", name); + dump_stack(); + goto oops; } + } #if DEBUG WARN_ON(strchr(name, ' ')); /* It confuses parsers */ if ((flags & SLAB_DEBUG_INITIAL) && !ctor) { /* No constructor, but inital state check requested */ printk(KERN_ERR "%s: No con, but init state check " - "requested - %s\n", __FUNCTION__, name); + "requested - %s\n", __FUNCTION__, name); flags &= ~SLAB_DEBUG_INITIAL; } - #if FORCED_DEBUG /* * Enable redzoning and last user accounting, except for caches with @@ -1137,11 +1840,18 @@ kmem_cache_create (const char *name, size_t size, size_t align, * 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+3*BYTES_PER_WORD))) - flags |= SLAB_RED_ZONE|SLAB_STORE_USER; - flags |= SLAB_POISON; + if ((size < 4096 + || fls(size - 1) == fls(size - 1 + 3 * BYTES_PER_WORD))) + 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 + if (flags & SLAB_DESTROY_BY_RCU) + BUG_ON(dtor); + /* * Always checks flags, a caller might be expecting debug * support which isn't available. @@ -1149,50 +1859,61 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (flags & ~CREATE_MASK) BUG(); - if (align) { - /* combinations of forced alignment and advanced debugging is - * not yet implemented. + /* 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); + } + + /* calculate out the final buffer alignment: */ + /* 1) arch recommendation: can be overridden for debug */ + if (flags & SLAB_HWCACHE_ALIGN) { + /* Default alignment: as specified by the arch code. + * Except if an object is really small, then squeeze multiple + * objects into one cacheline. */ - flags &= ~(SLAB_RED_ZONE|SLAB_STORE_USER); + ralign = cache_line_size(); + while (size <= ralign / 2) + ralign /= 2; } else { - if (flags & SLAB_HWCACHE_ALIGN) { - /* Default alignment: as specified by the arch code. - * Except if an object is really small, then squeeze multiple - * into one cacheline. - */ - align = cache_line_size(); - while (size <= align/2) - align /= 2; - } else { - align = BYTES_PER_WORD; - } - } + ralign = BYTES_PER_WORD; + } + /* 2) arch mandated alignment: disables debug if necessary */ + if (ralign < ARCH_SLAB_MINALIGN) { + ralign = ARCH_SLAB_MINALIGN; + if (ralign > BYTES_PER_WORD) + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); + } + /* 3) caller mandated alignment: disables debug if necessary */ + if (ralign < align) { + ralign = align; + if (ralign > BYTES_PER_WORD) + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); + } + /* 4) Store it. Note that the debug code below can reduce + * the alignment to BYTES_PER_WORD. + */ + align = ralign; /* Get cache's description obj. */ - cachep = (kmem_cache_t *) kmem_cache_alloc(&cache_cache, SLAB_KERNEL); + cachep = kmem_cache_alloc(&cache_cache, SLAB_KERNEL); if (!cachep) - goto opps; - memset(cachep, 0, sizeof(kmem_cache_t)); + goto oops; + memset(cachep, 0, sizeof(struct kmem_cache)); - /* 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); - } - #if DEBUG - cachep->reallen = size; + cachep->obj_size = size; if (flags & SLAB_RED_ZONE) { /* redzoning only works with word aligned caches */ align = BYTES_PER_WORD; /* add space for red zone words */ - cachep->dbghead += BYTES_PER_WORD; - size += 2*BYTES_PER_WORD; + cachep->obj_offset += BYTES_PER_WORD; + size += 2 * BYTES_PER_WORD; } if (flags & SLAB_STORE_USER) { /* user store requires word alignment and @@ -1203,15 +1924,16 @@ kmem_cache_create (const char *name, size_t size, size_t align, size += BYTES_PER_WORD; } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) - if (size > 128 && cachep->reallen > cache_line_size() && size < PAGE_SIZE) { - cachep->dbghead += PAGE_SIZE - size; + if (size >= malloc_sizes[INDEX_L3 + 1].cs_size + && cachep->obj_size > cache_line_size() && size < PAGE_SIZE) { + cachep->obj_offset += PAGE_SIZE - size; size = PAGE_SIZE; } #endif #endif /* Determine if the slab management is 'on' or 'off' slab. */ - if (size >= (PAGE_SIZE>>3)) + if (size >= (PAGE_SIZE >> 3)) /* * Size is large, assume best to place the slab management obj * off-slab (should allow better packing of objs). @@ -1220,64 +1942,16 @@ kmem_cache_create (const char *name, size_t size, size_t align, size = ALIGN(size, align); - if ((flags & SLAB_RECLAIM_ACCOUNT) && size <= PAGE_SIZE) { - /* - * 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. - */ - cachep->gfporder = 0; - cache_estimate(cachep->gfporder, size, align, flags, - &left_over, &cachep->num); - } else { - /* - * Calculate size (in pages) of slabs, and the num of objs per - * slab. This could be made much more intelligent. For now, - * try to avoid using high page-orders for slabs. When the - * gfp() funcs are more friendly towards high-order requests, - * this should be changed. - */ - do { - unsigned int break_flag = 0; -cal_wastage: - cache_estimate(cachep->gfporder, size, align, flags, - &left_over, &cachep->num); - if (break_flag) - break; - if (cachep->gfporder >= MAX_GFP_ORDER) - break; - if (!cachep->num) - goto next; - if (flags & CFLGS_OFF_SLAB && - cachep->num > offslab_limit) { - /* This num of objs will cause problems. */ - cachep->gfporder--; - break_flag++; - goto cal_wastage; - } - - /* - * Large num of objs is good, but v. large slabs are - * currently bad for the gfp()s. - */ - if (cachep->gfporder >= slab_break_gfp_order) - break; - - if ((left_over*8) <= (PAGE_SIZE<gfporder)) - break; /* Acceptable internal fragmentation. */ -next: - cachep->gfporder++; - } while (1); - } + left_over = calculate_slab_order(cachep, size, align, flags); if (!cachep->num) { printk("kmem_cache_create: couldn't create cache %s.\n", name); kmem_cache_free(&cache_cache, cachep); cachep = NULL; - goto opps; + goto oops; } - slab_size = ALIGN(cachep->num*sizeof(kmem_bufctl_t) - + sizeof(struct slab), align); + slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) + + sizeof(struct slab), align); /* * If the slab has been placed off-slab, and we have enough space then @@ -1290,34 +1964,29 @@ next: if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ - slab_size = cachep->num*sizeof(kmem_bufctl_t)+sizeof(struct slab); + slab_size = + cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab); } cachep->colour_off = cache_line_size(); /* Offset must be a multiple of the alignment. */ if (cachep->colour_off < align) cachep->colour_off = align; - cachep->colour = left_over/cachep->colour_off; + cachep->colour = left_over / cachep->colour_off; cachep->slab_size = slab_size; cachep->flags = flags; cachep->gfpflags = 0; if (flags & SLAB_CACHE_DMA) cachep->gfpflags |= GFP_DMA; spin_lock_init(&cachep->spinlock); - cachep->objsize = size; - /* NUMA */ - INIT_LIST_HEAD(&cachep->lists.slabs_full); - INIT_LIST_HEAD(&cachep->lists.slabs_partial); - INIT_LIST_HEAD(&cachep->lists.slabs_free); + cachep->buffer_size = size; if (flags & CFLGS_OFF_SLAB) - cachep->slabp_cache = kmem_find_general_cachep(slab_size,0); + cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u); cachep->ctor = ctor; cachep->dtor = dtor; cachep->name = name; - /* Don't let CPUs to come and go */ - lock_cpu_hotplug(); if (g_cpucache_up == FULL) { enable_cpucache(cachep); @@ -1327,90 +1996,103 @@ next: * the cache that's used by kmalloc(24), otherwise * the creation of further caches will BUG(). */ - cachep->array[smp_processor_id()] = &initarray_generic.cache; - g_cpucache_up = PARTIAL; + cachep->array[smp_processor_id()] = + &initarray_generic.cache; + + /* If the cache that's used by + * kmalloc(sizeof(kmem_list3)) is the first cache, + * then we need to set up all its list3s, otherwise + * the creation of further caches will BUG(). + */ + 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_KERNEL); + cachep->array[smp_processor_id()] = + kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); + + 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_KERNEL, node); + BUG_ON(!cachep->nodelists[node]); + kmem_list3_init(cachep-> + nodelists[node]); + } + } } - BUG_ON(!ac_data(cachep)); - ac_data(cachep)->avail = 0; - ac_data(cachep)->limit = BOOT_CPUCACHE_ENTRIES; - ac_data(cachep)->batchcount = 1; - ac_data(cachep)->touched = 0; + cachep->nodelists[numa_node_id()]->next_reap = + jiffies + REAPTIMEOUT_LIST3 + + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + + BUG_ON(!cpu_cache_get(cachep)); + 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; - cachep->free_limit = (1+num_online_cpus())*cachep->batchcount - + cachep->num; - } - - cachep->lists.next_reap = jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep)%REAPTIMEOUT_LIST3; - - /* Need the semaphore to access the chain. */ - down(&cache_chain_sem); - { - struct list_head *p; - mm_segment_t old_fs; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - list_for_each(p, &cache_chain) { - kmem_cache_t *pc = list_entry(p, kmem_cache_t, next); - char tmp; - /* This happens when the module gets unloaded and doesn't - destroy its slab cache and noone else reuses the vmalloc - area of the module. Print a warning. */ - if (__get_user(tmp,pc->name)) { - printk("SLAB: cache with size %d has lost its name\n", - pc->objsize); - continue; - } - if (!strcmp(pc->name,name)) { - printk("kmem_cache_create: duplicate cache %s\n",name); - up(&cache_chain_sem); - unlock_cpu_hotplug(); - BUG(); - } - } - set_fs(old_fs); } /* cache setup completed, link it into the list */ list_add(&cachep->next, &cache_chain); - up(&cache_chain_sem); + oops: + if (!cachep && (flags & SLAB_PANIC)) + panic("kmem_cache_create(): failed to create slab `%s'\n", + name); + mutex_unlock(&cache_chain_mutex); unlock_cpu_hotplug(); -opps: return cachep; } - EXPORT_SYMBOL(kmem_cache_create); -static inline void check_irq_off(void) -{ #if DEBUG +static void check_irq_off(void) +{ BUG_ON(!irqs_disabled()); -#endif } -static inline void check_irq_on(void) +static void check_irq_on(void) { -#if DEBUG 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_node_id()]->list_lock); #endif } -static inline void check_spinlock_acquired(kmem_cache_t *cachep) +static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) { #ifdef CONFIG_SMP check_irq_off(); - BUG_ON(spin_trylock(&cachep->spinlock)); + 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 + /* * Waits for all CPUs to execute func(). */ -static void smp_call_function_all_cpus(void (*func) (void *arg), void *arg) +static void smp_call_function_all_cpus(void (*func)(void *arg), void *arg) { check_irq_on(); preempt_disable(); @@ -1425,69 +2107,90 @@ static void smp_call_function_all_cpus(void (*func) (void *arg), void *arg) preempt_enable(); } -static void drain_array_locked(kmem_cache_t* cachep, - struct array_cache *ac, int force); +static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac, + int force, int node); static void do_drain(void *arg) { - kmem_cache_t *cachep = (kmem_cache_t*)arg; + struct kmem_cache *cachep = (struct kmem_cache *) arg; struct array_cache *ac; + int node = numa_node_id(); check_irq_off(); - ac = ac_data(cachep); - spin_lock(&cachep->spinlock); - free_block(cachep, &ac_entry(ac)[0], ac->avail); - spin_unlock(&cachep->spinlock); + ac = cpu_cache_get(cachep); + spin_lock(&cachep->nodelists[node]->list_lock); + free_block(cachep, ac->entry, ac->avail, node); + spin_unlock(&cachep->nodelists[node]->list_lock); ac->avail = 0; } -static void drain_cpu_caches(kmem_cache_t *cachep) +static void drain_cpu_caches(struct kmem_cache *cachep) { + struct kmem_list3 *l3; + int node; + smp_call_function_all_cpus(do_drain, cachep); check_irq_on(); - spin_lock_irq(&cachep->spinlock); - if (cachep->lists.shared) - drain_array_locked(cachep, cachep->lists.shared, 1); - spin_unlock_irq(&cachep->spinlock); + for_each_online_node(node) { + l3 = cachep->nodelists[node]; + if (l3) { + spin_lock_irq(&l3->list_lock); + drain_array_locked(cachep, l3->shared, 1, node); + spin_unlock_irq(&l3->list_lock); + if (l3->alien) + drain_alien_cache(cachep, l3->alien); + } + } } - -/* NUMA shrink all list3s */ -static int __cache_shrink(kmem_cache_t *cachep) +static int __node_shrink(struct kmem_cache *cachep, int node) { struct slab *slabp; + struct kmem_list3 *l3 = cachep->nodelists[node]; int ret; - drain_cpu_caches(cachep); - - check_irq_on(); - spin_lock_irq(&cachep->spinlock); - - for(;;) { + for (;;) { struct list_head *p; - p = cachep->lists.slabs_free.prev; - if (p == &cachep->lists.slabs_free) + p = l3->slabs_free.prev; + if (p == &l3->slabs_free) break; - slabp = list_entry(cachep->lists.slabs_free.prev, struct slab, list); + slabp = list_entry(l3->slabs_free.prev, struct slab, list); #if DEBUG if (slabp->inuse) BUG(); #endif list_del(&slabp->list); - cachep->lists.free_objects -= cachep->num; - spin_unlock_irq(&cachep->spinlock); + l3->free_objects -= cachep->num; + spin_unlock_irq(&l3->list_lock); slab_destroy(cachep, slabp); - spin_lock_irq(&cachep->spinlock); + spin_lock_irq(&l3->list_lock); } - ret = !list_empty(&cachep->lists.slabs_full) || - !list_empty(&cachep->lists.slabs_partial); - spin_unlock_irq(&cachep->spinlock); + ret = !list_empty(&l3->slabs_full) || !list_empty(&l3->slabs_partial); return ret; } +static int __cache_shrink(struct kmem_cache *cachep) +{ + int ret = 0, i = 0; + struct kmem_list3 *l3; + + drain_cpu_caches(cachep); + + check_irq_on(); + for_each_online_node(i) { + l3 = cachep->nodelists[i]; + if (l3) { + spin_lock_irq(&l3->list_lock); + ret += __node_shrink(cachep, i); + spin_unlock_irq(&l3->list_lock); + } + } + return (ret ? 1 : 0); +} + /** * kmem_cache_shrink - Shrink a cache. * @cachep: The cache to shrink. @@ -1495,21 +2198,20 @@ static int __cache_shrink(kmem_cache_t *cachep) * Releases as many slabs as possible for a cache. * To help debugging, a zero exit status indicates all slabs were released. */ -int kmem_cache_shrink(kmem_cache_t *cachep) +int kmem_cache_shrink(struct kmem_cache *cachep) { if (!cachep || in_interrupt()) BUG(); return __cache_shrink(cachep); } - EXPORT_SYMBOL(kmem_cache_shrink); /** * kmem_cache_destroy - delete a cache * @cachep: the cache to destroy * - * Remove a kmem_cache_t object from the slab cache. + * Remove a struct kmem_cache object from the slab cache. * Returns 0 on success. * * It is expected this function will be called by a module when it is @@ -1522,9 +2224,10 @@ EXPORT_SYMBOL(kmem_cache_shrink); * The caller must guarantee that noone will allocate memory from the cache * during the kmem_cache_destroy(). */ -int kmem_cache_destroy (kmem_cache_t * cachep) +int kmem_cache_destroy(struct kmem_cache *cachep) { int i; + struct kmem_list3 *l3; if (!cachep || in_interrupt()) BUG(); @@ -1533,74 +2236,78 @@ int kmem_cache_destroy (kmem_cache_t * cachep) lock_cpu_hotplug(); /* Find the cache in the chain of caches. */ - down(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); /* * the chain is never empty, cache_cache is never destroyed */ list_del(&cachep->next); - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); if (__cache_shrink(cachep)) { slab_error(cachep, "Can't free all objects"); - down(&cache_chain_sem); - list_add(&cachep->next,&cache_chain); - up(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); + list_add(&cachep->next, &cache_chain); + mutex_unlock(&cache_chain_mutex); unlock_cpu_hotplug(); return 1; } - /* no cpu_online check required here since we clear the percpu - * array on cpu offline and set this to NULL. - */ - for (i = 0; i < NR_CPUS; i++) - kfree(cachep->array[i]); + if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) + synchronize_rcu(); + + for_each_online_cpu(i) + kfree(cachep->array[i]); /* NUMA: free the list3 structures */ - kfree(cachep->lists.shared); - cachep->lists.shared = NULL; + for_each_online_node(i) { + if ((l3 = cachep->nodelists[i])) { + kfree(l3->shared); + free_alien_cache(l3->alien); + kfree(l3); + } + } kmem_cache_free(&cache_cache, cachep); unlock_cpu_hotplug(); return 0; } - EXPORT_SYMBOL(kmem_cache_destroy); /* Get the memory for a slab management obj. */ -static inline struct slab* alloc_slabmgmt (kmem_cache_t *cachep, - void *objp, int colour_off, int local_flags) +static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, + int colour_off, gfp_t local_flags) { struct slab *slabp; - + if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ slabp = kmem_cache_alloc(cachep->slabp_cache, local_flags); if (!slabp) return NULL; } else { - slabp = objp+colour_off; + slabp = objp + colour_off; colour_off += cachep->slab_size; } slabp->inuse = 0; slabp->colouroff = colour_off; - slabp->s_mem = objp+colour_off; + slabp->s_mem = objp + colour_off; return slabp; } static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp) { - return (kmem_bufctl_t *)(slabp+1); + return (kmem_bufctl_t *) (slabp + 1); } -static void cache_init_objs (kmem_cache_t * cachep, - struct slab * slabp, unsigned long ctor_flags) +static void cache_init_objs(struct kmem_cache *cachep, + struct slab *slabp, unsigned long ctor_flags) { int i; for (i = 0; i < cachep->num; i++) { - void* objp = slabp->s_mem+cachep->objsize*i; + void *objp = slabp->s_mem + cachep->buffer_size * i; #if DEBUG /* need to poison the objs? */ if (cachep->flags & SLAB_POISON) @@ -1618,29 +2325,32 @@ static void cache_init_objs (kmem_cache_t * cachep, * Otherwise, deadlock. They must also be threaded. */ if (cachep->ctor && !(cachep->flags & SLAB_POISON)) - cachep->ctor(objp+obj_dbghead(cachep), cachep, ctor_flags); + cachep->ctor(objp + obj_offset(cachep), cachep, + ctor_flags); if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone2(cachep, objp) != RED_INACTIVE) slab_error(cachep, "constructor overwrote the" - " end of an object"); + " end of an object"); if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) slab_error(cachep, "constructor overwrote the" - " start of an object"); + " start of an object"); } - if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep) && cachep->flags & SLAB_POISON) - kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE, 0); + if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep) + && cachep->flags & SLAB_POISON) + kernel_map_pages(virt_to_page(objp), + cachep->buffer_size / PAGE_SIZE, 0); #else if (cachep->ctor) cachep->ctor(objp, cachep, ctor_flags); #endif - slab_bufctl(slabp)[i] = i+1; + slab_bufctl(slabp)[i] = i + 1; } - slab_bufctl(slabp)[i-1] = BUFCTL_END; + slab_bufctl(slabp)[i - 1] = BUFCTL_END; slabp->free = 0; } -static void kmem_flagcheck(kmem_cache_t *cachep, int flags) +static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) { if (flags & SLAB_DMA) { if (!(cachep->gfpflags & GFP_DMA)) @@ -1651,23 +2361,74 @@ static void kmem_flagcheck(kmem_cache_t *cachep, int flags) } } +static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, int nodeid) +{ + void *objp = slabp->s_mem + (slabp->free * cachep->buffer_size); + kmem_bufctl_t next; + + slabp->inuse++; + next = slab_bufctl(slabp)[slabp->free]; +#if DEBUG + slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; + WARN_ON(slabp->nodeid != nodeid); +#endif + slabp->free = next; + + return objp; +} + +static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, void *objp, + int nodeid) +{ + unsigned int objnr = (unsigned)(objp-slabp->s_mem) / cachep->buffer_size; + +#if DEBUG + /* Verify that the slab belongs to the intended node */ + WARN_ON(slabp->nodeid != nodeid); + + if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) { + printk(KERN_ERR "slab: double free detected in cache " + "'%s', objp %p\n", cachep->name, objp); + BUG(); + } +#endif + slab_bufctl(slabp)[objnr] = slabp->free; + slabp->free = objnr; + slabp->inuse--; +} + +static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp, void *objp) +{ + int i; + struct page *page; + + /* Nasty!!!!!! I hope this is OK. */ + i = 1 << cachep->gfporder; + page = virt_to_page(objp); + do { + page_set_cache(page, cachep); + page_set_slab(page, slabp); + page++; + } while (--i); +} + /* * Grow (by 1) the number of slabs within a cache. This is called by * kmem_cache_alloc() when there are no active objs left in a cache. */ -static int cache_grow (kmem_cache_t * cachep, int flags) +static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - struct slab *slabp; - struct page *page; - void *objp; - size_t offset; - unsigned int i, local_flags; - unsigned long ctor_flags; + struct slab *slabp; + void *objp; + size_t offset; + gfp_t local_flags; + unsigned long ctor_flags; + struct kmem_list3 *l3; /* Be lazy and only check for valid flags here, - * keeping it out of the critical path in kmem_cache_alloc(). + * keeping it out of the critical path in kmem_cache_alloc(). */ - if (flags & ~(SLAB_DMA|SLAB_LEVEL_MASK|SLAB_NO_GROW)) + if (flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW)) BUG(); if (flags & SLAB_NO_GROW) return 0; @@ -1681,18 +2442,19 @@ static int cache_grow (kmem_cache_t * cachep, int flags) */ ctor_flags |= SLAB_CTOR_ATOMIC; - /* About to mess with non-constant members - lock. */ + /* Take the l3 list lock to change the colour_next on this node */ check_irq_off(); - spin_lock(&cachep->spinlock); + l3 = cachep->nodelists[nodeid]; + spin_lock(&l3->list_lock); /* Get colour for the slab, and cal the next value. */ - offset = cachep->colour_next; - cachep->colour_next++; - if (cachep->colour_next >= cachep->colour) - cachep->colour_next = 0; - offset *= cachep->colour_off; + offset = l3->colour_next; + l3->colour_next++; + if (l3->colour_next >= cachep->colour) + l3->colour_next = 0; + spin_unlock(&l3->list_lock); - spin_unlock(&cachep->spinlock); + offset *= cachep->colour_off; if (local_flags & __GFP_WAIT) local_irq_enable(); @@ -1705,95 +2467,97 @@ static int cache_grow (kmem_cache_t * cachep, int flags) */ kmem_flagcheck(cachep, flags); - - /* Get mem for the objs. */ - if (!(objp = kmem_getpages(cachep, flags))) + /* Get mem for the objs. + * Attempt to allocate a physical page from 'nodeid', + */ + if (!(objp = kmem_getpages(cachep, flags, nodeid))) goto failed; /* Get slab management. */ if (!(slabp = alloc_slabmgmt(cachep, objp, offset, local_flags))) goto opps1; - /* Nasty!!!!!! I hope this is OK. */ - i = 1 << cachep->gfporder; - page = virt_to_page(objp); - do { - SET_PAGE_CACHE(page, cachep); - SET_PAGE_SLAB(page, slabp); - page++; - } while (--i); + slabp->nodeid = nodeid; + set_slab_attr(cachep, slabp, objp); cache_init_objs(cachep, slabp, ctor_flags); if (local_flags & __GFP_WAIT) local_irq_disable(); check_irq_off(); - spin_lock(&cachep->spinlock); + spin_lock(&l3->list_lock); /* Make slab active. */ - list_add_tail(&slabp->list, &(list3_data(cachep)->slabs_free)); + list_add_tail(&slabp->list, &(l3->slabs_free)); STATS_INC_GROWN(cachep); - list3_data(cachep)->free_objects += cachep->num; - spin_unlock(&cachep->spinlock); + l3->free_objects += cachep->num; + spin_unlock(&l3->list_lock); return 1; -opps1: + opps1: kmem_freepages(cachep, objp); -failed: + failed: if (local_flags & __GFP_WAIT) local_irq_disable(); return 0; } +#if DEBUG + /* * Perform extra freeing checks: * - detect bad pointers. * - POISON/RED_ZONE checking * - destructor calls, for caches with POISON+dtor */ -static inline void kfree_debugcheck(const void *objp) +static void kfree_debugcheck(const void *objp) { -#if DEBUG struct page *page; if (!virt_addr_valid(objp)) { printk(KERN_ERR "kfree_debugcheck: out of range ptr %lxh.\n", - (unsigned long)objp); - BUG(); + (unsigned long)objp); + BUG(); } page = virt_to_page(objp); if (!PageSlab(page)) { - printk(KERN_ERR "kfree_debugcheck: bad ptr %lxh.\n", (unsigned long)objp); + printk(KERN_ERR "kfree_debugcheck: bad ptr %lxh.\n", + (unsigned long)objp); BUG(); } -#endif } -static inline void *cache_free_debugcheck (kmem_cache_t * cachep, void * objp, void *caller) +static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, + void *caller) { -#if DEBUG struct page *page; unsigned int objnr; struct slab *slabp; - objp -= obj_dbghead(cachep); + objp -= obj_offset(cachep); kfree_debugcheck(objp); page = virt_to_page(objp); - if (GET_PAGE_CACHE(page) != cachep) { - printk(KERN_ERR "mismatch in kmem_cache_free: expected cache %p, got %p\n", - GET_PAGE_CACHE(page),cachep); + if (page_get_cache(page) != cachep) { + printk(KERN_ERR + "mismatch in kmem_cache_free: expected cache %p, got %p\n", + page_get_cache(page), cachep); printk(KERN_ERR "%p is %s.\n", cachep, cachep->name); - printk(KERN_ERR "%p is %s.\n", GET_PAGE_CACHE(page), GET_PAGE_CACHE(page)->name); + printk(KERN_ERR "%p is %s.\n", page_get_cache(page), + page_get_cache(page)->name); WARN_ON(1); } - slabp = GET_PAGE_SLAB(page); + slabp = page_get_slab(page); if (cachep->flags & SLAB_RED_ZONE) { - if (*dbg_redzone1(cachep, objp) != RED_ACTIVE || *dbg_redzone2(cachep, objp) != RED_ACTIVE) { - slab_error(cachep, "double free, or memory outside" - " object was overwritten"); - printk(KERN_ERR "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n", - objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); + if (*dbg_redzone1(cachep, objp) != RED_ACTIVE + || *dbg_redzone2(cachep, objp) != RED_ACTIVE) { + slab_error(cachep, + "double free, or memory outside" + " object was overwritten"); + printk(KERN_ERR + "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n", + objp, *dbg_redzone1(cachep, objp), + *dbg_redzone2(cachep, objp)); } *dbg_redzone1(cachep, objp) = RED_INACTIVE; *dbg_redzone2(cachep, objp) = RED_INACTIVE; @@ -1801,30 +2565,31 @@ static inline void *cache_free_debugcheck (kmem_cache_t * cachep, void * objp, v if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = caller; - objnr = (objp-slabp->s_mem)/cachep->objsize; + objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size; BUG_ON(objnr >= cachep->num); - BUG_ON(objp != slabp->s_mem + objnr*cachep->objsize); + BUG_ON(objp != slabp->s_mem + objnr * cachep->buffer_size); if (cachep->flags & SLAB_DEBUG_INITIAL) { /* Need to call the slab's constructor so the * caller can perform a verify of its state (debugging). * Called without the cache-lock held. */ - cachep->ctor(objp+obj_dbghead(cachep), - cachep, SLAB_CTOR_CONSTRUCTOR|SLAB_CTOR_VERIFY); + cachep->ctor(objp + obj_offset(cachep), + cachep, SLAB_CTOR_CONSTRUCTOR | SLAB_CTOR_VERIFY); } if (cachep->flags & SLAB_POISON && cachep->dtor) { /* we want to cache poison the object, * call the destruction callback */ - cachep->dtor(objp+obj_dbghead(cachep), cachep, 0); + cachep->dtor(objp + obj_offset(cachep), cachep, 0); } if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) { + if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) { store_stackinfo(cachep, objp, (unsigned long)caller); - kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE, 0); + kernel_map_pages(virt_to_page(objp), + cachep->buffer_size / PAGE_SIZE, 0); } else { poison_obj(cachep, objp, POISON_FREE); } @@ -1832,48 +2597,51 @@ static inline void *cache_free_debugcheck (kmem_cache_t * cachep, void * objp, v poison_obj(cachep, objp, POISON_FREE); #endif } -#endif return objp; } -static inline void check_slabp(kmem_cache_t *cachep, struct slab *slabp) +static void check_slabp(struct kmem_cache *cachep, struct slab *slabp) { -#if DEBUG - int i; + kmem_bufctl_t i; int entries = 0; - - check_spinlock_acquired(cachep); + /* Check slab's freelist to see if this obj is there. */ for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) { entries++; - if (entries > cachep->num || i < 0 || i >= cachep->num) + if (entries > cachep->num || i >= cachep->num) goto bad; } if (entries != cachep->num - slabp->inuse) { - int i; -bad: - printk(KERN_ERR "slab: Internal list corruption detected in cache '%s'(%d), slabp %p(%d). Hexdump:\n", - cachep->name, cachep->num, slabp, slabp->inuse); - for (i=0;inum*sizeof(kmem_bufctl_t);i++) { - if ((i%16)==0) + bad: + printk(KERN_ERR + "slab: Internal list corruption detected in cache '%s'(%d), slabp %p(%d). Hexdump:\n", + cachep->name, cachep->num, slabp, slabp->inuse); + for (i = 0; + i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t); + i++) { + if ((i % 16) == 0) printk("\n%03x:", i); - printk(" %02x", ((unsigned char*)slabp)[i]); + printk(" %02x", ((unsigned char *)slabp)[i]); } printk("\n"); BUG(); } -#endif } +#else +#define kfree_debugcheck(x) do { } while(0) +#define cache_free_debugcheck(x,objp,z) (objp) +#define check_slabp(x,y) do { } while(0) +#endif -static void* cache_alloc_refill(kmem_cache_t* cachep, int flags) +static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) { int batchcount; struct kmem_list3 *l3; struct array_cache *ac; check_irq_off(); - ac = ac_data(cachep); -retry: + ac = cpu_cache_get(cachep); + retry: batchcount = ac->batchcount; if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { /* if there was little recent activity on this @@ -1882,10 +2650,11 @@ retry: */ batchcount = BATCHREFILL_LIMIT; } - l3 = list3_data(cachep); + l3 = cachep->nodelists[numa_node_id()]; + + BUG_ON(ac->avail > 0 || !l3); + spin_lock(&l3->list_lock); - BUG_ON(ac->avail > 0); - spin_lock(&cachep->spinlock); if (l3->shared) { struct array_cache *shared_array = l3->shared; if (shared_array->avail) { @@ -1893,8 +2662,9 @@ retry: batchcount = shared_array->avail; shared_array->avail -= batchcount; ac->avail = batchcount; - memcpy(ac_entry(ac), &ac_entry(shared_array)[shared_array->avail], - sizeof(void*)*batchcount); + memcpy(ac->entry, + &(shared_array->entry[shared_array->avail]), + sizeof(void *) * batchcount); shared_array->touched = 1; goto alloc_done; } @@ -1915,20 +2685,12 @@ retry: check_slabp(cachep, slabp); check_spinlock_acquired(cachep); while (slabp->inuse < cachep->num && batchcount--) { - kmem_bufctl_t next; STATS_INC_ALLOCED(cachep); STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); - /* get obj pointer */ - ac_entry(ac)[ac->avail++] = slabp->s_mem + slabp->free*cachep->objsize; - - slabp->inuse++; - next = slab_bufctl(slabp)[slabp->free]; -#if DEBUG - slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; -#endif - slabp->free = next; + ac->entry[ac->avail++] = slab_get_obj(cachep, slabp, + numa_node_id()); } check_slabp(cachep, slabp); @@ -1940,29 +2702,29 @@ retry: list_add(&slabp->list, &l3->slabs_partial); } -must_grow: + must_grow: l3->free_objects -= ac->avail; -alloc_done: - spin_unlock(&cachep->spinlock); + alloc_done: + spin_unlock(&l3->list_lock); if (unlikely(!ac->avail)) { int x; - x = cache_grow(cachep, flags); - + x = cache_grow(cachep, flags, numa_node_id()); + // cache_grow can reenable interrupts, then ac could change. - ac = ac_data(cachep); + ac = cpu_cache_get(cachep); if (!x && ac->avail == 0) // no objects in sight? abort return NULL; - if (!ac->avail) // objects refilled by interrupt? + if (!ac->avail) // objects refilled by interrupt? goto retry; } ac->touched = 1; - return ac_entry(ac)[--ac->avail]; + return ac->entry[--ac->avail]; } static inline void -cache_alloc_debugcheck_before(kmem_cache_t *cachep, int flags) +cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags) { might_sleep_if(flags & __GFP_WAIT); #if DEBUG @@ -1970,17 +2732,17 @@ cache_alloc_debugcheck_before(kmem_cache_t *cachep, int flags) #endif } -static inline void * -cache_alloc_debugcheck_after(kmem_cache_t *cachep, - unsigned long flags, void *objp, void *caller) -{ #if DEBUG - if (!objp) +static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags, + void *objp, void *caller) +{ + if (!objp) return objp; - if (cachep->flags & SLAB_POISON) { + if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), cachep->objsize/PAGE_SIZE, 1); + 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 @@ -1992,141 +2754,218 @@ cache_alloc_debugcheck_after(kmem_cache_t *cachep, *dbg_userword(cachep, objp) = caller; if (cachep->flags & SLAB_RED_ZONE) { - if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || *dbg_redzone2(cachep, objp) != RED_INACTIVE) { - slab_error(cachep, "double free, or memory outside" - " object was overwritten"); - printk(KERN_ERR "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n", - objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); + if (*dbg_redzone1(cachep, objp) != RED_INACTIVE + || *dbg_redzone2(cachep, objp) != RED_INACTIVE) { + slab_error(cachep, + "double free, or memory outside" + " object was overwritten"); + printk(KERN_ERR + "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n", + objp, *dbg_redzone1(cachep, objp), + *dbg_redzone2(cachep, objp)); } *dbg_redzone1(cachep, objp) = RED_ACTIVE; *dbg_redzone2(cachep, objp) = RED_ACTIVE; } - objp += obj_dbghead(cachep); + objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) { - unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR; + unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR; if (!(flags & __GFP_WAIT)) ctor_flags |= SLAB_CTOR_ATOMIC; cachep->ctor(objp, cachep, ctor_flags); - } -#endif + } return objp; } +#else +#define cache_alloc_debugcheck_after(a,b,objp,d) (objp) +#endif - -static inline void * __cache_alloc (kmem_cache_t *cachep, int flags) +static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - unsigned long save_flags; - void* objp; + void *objp; struct array_cache *ac; - cache_alloc_debugcheck_before(cachep, flags); +#ifdef CONFIG_NUMA + if (unlikely(current->mempolicy && !in_interrupt())) { + int nid = slab_node(current->mempolicy); - local_irq_save(save_flags); - ac = ac_data(cachep); + if (nid != numa_node_id()) + return __cache_alloc_node(cachep, flags, nid); + } +#endif + + check_irq_off(); + ac = cpu_cache_get(cachep); if (likely(ac->avail)) { STATS_INC_ALLOCHIT(cachep); ac->touched = 1; - objp = ac_entry(ac)[--ac->avail]; + objp = ac->entry[--ac->avail]; } else { STATS_INC_ALLOCMISS(cachep); objp = cache_alloc_refill(cachep, flags); } + return objp; +} + +static __always_inline void * +__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) +{ + unsigned long save_flags; + void *objp; + + cache_alloc_debugcheck_before(cachep, flags); + + local_irq_save(save_flags); + objp = ____cache_alloc(cachep, flags); local_irq_restore(save_flags); - objp = cache_alloc_debugcheck_after(cachep, flags, objp, __builtin_return_address(0)); + objp = cache_alloc_debugcheck_after(cachep, flags, objp, + caller); + prefetchw(objp); return objp; } -/* - * NUMA: different approach needed if the spinlock is moved into - * the l3 structure +#ifdef CONFIG_NUMA +/* + * A interface to enable slab creation on nodeid */ - -static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects) +static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - int i; + struct list_head *entry; + struct slab *slabp; + struct kmem_list3 *l3; + void *obj; + int x; + + l3 = cachep->nodelists[nodeid]; + BUG_ON(!l3); + + retry: + check_irq_off(); + spin_lock(&l3->list_lock); + entry = l3->slabs_partial.next; + if (entry == &l3->slabs_partial) { + l3->free_touched = 1; + entry = l3->slabs_free.next; + if (entry == &l3->slabs_free) + goto must_grow; + } + + slabp = list_entry(entry, struct slab, list); + check_spinlock_acquired_node(cachep, nodeid); + check_slabp(cachep, slabp); + + STATS_INC_NODEALLOCS(cachep); + STATS_INC_ACTIVE(cachep); + STATS_SET_HIGH(cachep); + + BUG_ON(slabp->inuse == cachep->num); + + obj = slab_get_obj(cachep, slabp, nodeid); + check_slabp(cachep, slabp); + l3->free_objects--; + /* move slabp to correct slabp list: */ + list_del(&slabp->list); + + if (slabp->free == BUFCTL_END) { + list_add(&slabp->list, &l3->slabs_full); + } else { + list_add(&slabp->list, &l3->slabs_partial); + } + + spin_unlock(&l3->list_lock); + goto done; + + must_grow: + spin_unlock(&l3->list_lock); + x = cache_grow(cachep, flags, nodeid); + + if (!x) + return NULL; - check_spinlock_acquired(cachep); + goto retry; + done: + return obj; +} +#endif - /* NUMA: move add into loop */ - cachep->lists.free_objects += nr_objects; +/* + * Caller needs to acquire correct kmem_list's list_lock + */ +static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, + int node) +{ + int i; + struct kmem_list3 *l3; for (i = 0; i < nr_objects; i++) { void *objp = objpp[i]; struct slab *slabp; - unsigned int objnr; - slabp = GET_PAGE_SLAB(virt_to_page(objp)); + slabp = virt_to_slab(objp); + l3 = cachep->nodelists[node]; list_del(&slabp->list); - objnr = (objp - slabp->s_mem) / cachep->objsize; + check_spinlock_acquired_node(cachep, node); check_slabp(cachep, slabp); -#if DEBUG - if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) { - printk(KERN_ERR "slab: double free detected in cache '%s', objp %p.\n", - cachep->name, objp); - BUG(); - } -#endif - slab_bufctl(slabp)[objnr] = slabp->free; - slabp->free = objnr; + slab_put_obj(cachep, slabp, objp, node); STATS_DEC_ACTIVE(cachep); - slabp->inuse--; + l3->free_objects++; check_slabp(cachep, slabp); /* fixup slab chains */ if (slabp->inuse == 0) { - if (cachep->lists.free_objects > cachep->free_limit) { - cachep->lists.free_objects -= cachep->num; + if (l3->free_objects > l3->free_limit) { + l3->free_objects -= cachep->num; slab_destroy(cachep, slabp); } else { - list_add(&slabp->list, - &list3_data_ptr(cachep, objp)->slabs_free); + list_add(&slabp->list, &l3->slabs_free); } } else { /* Unconditionally move a slab to the end of the * partial list on free - maximum time for the * other objects to be freed, too. */ - list_add_tail(&slabp->list, - &list3_data_ptr(cachep, objp)->slabs_partial); + list_add_tail(&slabp->list, &l3->slabs_partial); } } } -static void cache_flusharray (kmem_cache_t* cachep, struct array_cache *ac) +static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) { int batchcount; + struct kmem_list3 *l3; + int node = numa_node_id(); batchcount = ac->batchcount; #if DEBUG BUG_ON(!batchcount || batchcount > ac->avail); #endif check_irq_off(); - spin_lock(&cachep->spinlock); - if (cachep->lists.shared) { - struct array_cache *shared_array = cachep->lists.shared; - int max = shared_array->limit-shared_array->avail; + l3 = cachep->nodelists[node]; + spin_lock(&l3->list_lock); + if (l3->shared) { + struct array_cache *shared_array = l3->shared; + int max = shared_array->limit - shared_array->avail; if (max) { if (batchcount > max) batchcount = max; - memcpy(&ac_entry(shared_array)[shared_array->avail], - &ac_entry(ac)[0], - sizeof(void*)*batchcount); + memcpy(&(shared_array->entry[shared_array->avail]), + ac->entry, sizeof(void *) * batchcount); shared_array->avail += batchcount; goto free_done; } } - free_block(cachep, &ac_entry(ac)[0], batchcount); -free_done: + free_block(cachep, ac->entry, batchcount, node); + free_done: #if STATS { int i = 0; struct list_head *p; - p = list3_data(cachep)->slabs_free.next; - while (p != &(list3_data(cachep)->slabs_free)) { + p = l3->slabs_free.next; + while (p != &(l3->slabs_free)) { struct slab *slabp; slabp = list_entry(p, struct slab, list); @@ -2138,10 +2977,10 @@ free_done: STATS_SET_FREEABLE(cachep, i); } #endif - spin_unlock(&cachep->spinlock); + spin_unlock(&l3->list_lock); ac->avail -= batchcount; - memmove(&ac_entry(ac)[0], &ac_entry(ac)[batchcount], - sizeof(void*)*ac->avail); + memmove(ac->entry, &(ac->entry[batchcount]), + sizeof(void *) * ac->avail); } /* @@ -2151,21 +2990,54 @@ free_done: * * Called with disabled ints. */ -static inline void __cache_free (kmem_cache_t *cachep, void* objp) +static inline void __cache_free(struct kmem_cache *cachep, void *objp) { - struct array_cache *ac = ac_data(cachep); + struct array_cache *ac = cpu_cache_get(cachep); check_irq_off(); objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0)); + /* Make sure we are not freeing a object from another + * node to the array cache on this cpu. + */ +#ifdef CONFIG_NUMA + { + struct slab *slabp; + slabp = virt_to_slab(objp); + if (unlikely(slabp->nodeid != numa_node_id())) { + struct array_cache *alien = NULL; + int nodeid = slabp->nodeid; + struct kmem_list3 *l3 = + cachep->nodelists[numa_node_id()]; + + STATS_INC_NODEFREES(cachep); + if (l3->alien && l3->alien[nodeid]) { + alien = l3->alien[nodeid]; + spin_lock(&alien->lock); + if (unlikely(alien->avail == alien->limit)) + __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; + } + } +#endif if (likely(ac->avail < ac->limit)) { STATS_INC_FREEHIT(cachep); - ac_entry(ac)[ac->avail++] = objp; + ac->entry[ac->avail++] = objp; return; } else { STATS_INC_FREEMISS(cachep); cache_flusharray(cachep, ac); - ac_entry(ac)[ac->avail++] = objp; + ac->entry[ac->avail++] = objp; } } @@ -2177,11 +3049,10 @@ static inline void __cache_free (kmem_cache_t *cachep, void* objp) * Allocate an object from this cache. The flags are only relevant * if the cache has no available objects. */ -void * kmem_cache_alloc (kmem_cache_t *cachep, int flags) +void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - return __cache_alloc(cachep, flags); + return __cache_alloc(cachep, flags, __builtin_return_address(0)); } - EXPORT_SYMBOL(kmem_cache_alloc); /** @@ -2198,12 +3069,12 @@ EXPORT_SYMBOL(kmem_cache_alloc); * * Currently only used for dentry validation. */ -int fastcall kmem_ptr_validate(kmem_cache_t *cachep, void *ptr) +int fastcall kmem_ptr_validate(struct kmem_cache *cachep, void *ptr) { - unsigned long addr = (unsigned long) ptr; + unsigned long addr = (unsigned long)ptr; unsigned long min_addr = PAGE_OFFSET; - unsigned long align_mask = BYTES_PER_WORD-1; - unsigned long size = cachep->objsize; + unsigned long align_mask = BYTES_PER_WORD - 1; + unsigned long size = cachep->buffer_size; struct page *page; if (unlikely(addr < min_addr)) @@ -2219,13 +3090,60 @@ int fastcall kmem_ptr_validate(kmem_cache_t *cachep, void *ptr) page = virt_to_page(ptr); if (unlikely(!PageSlab(page))) goto out; - if (unlikely(GET_PAGE_CACHE(page) != cachep)) + if (unlikely(page_get_cache(page) != cachep)) goto out; return 1; -out: + out: return 0; } +#ifdef CONFIG_NUMA +/** + * kmem_cache_alloc_node - Allocate an object on the specified node + * @cachep: The cache to allocate from. + * @flags: See kmalloc(). + * @nodeid: node number of the target node. + * + * Identical to kmem_cache_alloc, except that this function is slow + * and can sleep. And it will allocate memory on the given node, which + * can improve the performance for cpu bound structures. + * New and improved: it will now make sure that the object gets + * put on the correct node list so that there is no false sharing. + */ +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) +{ + unsigned long save_flags; + void *ptr; + + cache_alloc_debugcheck_before(cachep, flags); + local_irq_save(save_flags); + + if (nodeid == -1 || nodeid == numa_node_id() || + !cachep->nodelists[nodeid]) + ptr = ____cache_alloc(cachep, flags); + else + ptr = __cache_alloc_node(cachep, flags, nodeid); + local_irq_restore(save_flags); + + ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, + __builtin_return_address(0)); + + return ptr; +} +EXPORT_SYMBOL(kmem_cache_alloc_node); + +void *kmalloc_node(size_t size, gfp_t flags, int node) +{ + struct kmem_cache *cachep; + + cachep = kmem_find_general_cachep(size, flags); + if (unlikely(cachep == NULL)) + return NULL; + return kmem_cache_alloc_node(cachep, flags, node); +} +EXPORT_SYMBOL(kmalloc_node); +#endif + /** * kmalloc - allocate memory * @size: how many bytes of memory are required. @@ -2247,59 +3165,78 @@ out: * platforms. For example, on i386, it means that the memory must come * from the first 16MB. */ -void * __kmalloc (size_t size, int flags) +static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, + void *caller) { - struct cache_sizes *csizep = malloc_sizes; + struct kmem_cache *cachep; - for (; csizep->cs_size; csizep++) { - if (size > csizep->cs_size) - continue; -#if DEBUG - /* This happens if someone tries to call - * kmem_cache_create(), or kmalloc(), before - * the generic caches are initialized. - */ - BUG_ON(csizep->cs_cachep == NULL); -#endif - return __cache_alloc(flags & GFP_DMA ? - csizep->cs_dmacachep : csizep->cs_cachep, flags); - } - return NULL; + /* If you want to save a few bytes .text space: replace + * __ with kmem_. + * Then kmalloc uses the uninlined functions instead of the inline + * functions. + */ + cachep = __find_general_cachep(size, flags); + if (unlikely(cachep == NULL)) + return NULL; + return __cache_alloc(cachep, flags, caller); } +#ifndef CONFIG_DEBUG_SLAB + +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc(size, flags, NULL); +} EXPORT_SYMBOL(__kmalloc); +#else + +void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller) +{ + return __do_kmalloc(size, flags, caller); +} +EXPORT_SYMBOL(__kmalloc_track_caller); + +#endif + #ifdef CONFIG_SMP /** * __alloc_percpu - allocate one copy of the object for every present * cpu in the system, zeroing them. - * Objects should be dereferenced using per_cpu_ptr/get_cpu_ptr - * macros only. + * Objects should be dereferenced using the per_cpu_ptr macro only. * * @size: how many bytes of memory are required. - * @align: the alignment, which can't be greater than SMP_CACHE_BYTES. */ -void *__alloc_percpu(size_t size, size_t align) +void *__alloc_percpu(size_t size) { int i; - struct percpu_data *pdata = kmalloc(sizeof (*pdata), GFP_KERNEL); + struct percpu_data *pdata = kmalloc(sizeof(*pdata), GFP_KERNEL); if (!pdata) return NULL; - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_possible(i)) - continue; - pdata->ptrs[i] = kmalloc(size, GFP_KERNEL); + /* + * Cannot use for_each_online_cpu since a cpu may come online + * and we have no way of figuring out how to fix the array + * that we have allocated then.... + */ + for_each_cpu(i) { + int node = cpu_to_node(i); + + if (node_online(node)) + pdata->ptrs[i] = kmalloc_node(size, GFP_KERNEL, node); + else + pdata->ptrs[i] = kmalloc(size, GFP_KERNEL); + if (!pdata->ptrs[i]) goto unwind_oom; memset(pdata->ptrs[i], 0, size); } /* Catch derefs w/o wrappers */ - return (void *) (~(unsigned long) pdata); + return (void *)(~(unsigned long)pdata); -unwind_oom: + unwind_oom: while (--i >= 0) { if (!cpu_possible(i)) continue; @@ -2308,7 +3245,6 @@ unwind_oom: kfree(pdata); return NULL; } - EXPORT_SYMBOL(__alloc_percpu); #endif @@ -2320,7 +3256,7 @@ EXPORT_SYMBOL(__alloc_percpu); * Free an object which was previously allocated from this * cache. */ -void kmem_cache_free (kmem_cache_t *cachep, void *objp) +void kmem_cache_free(struct kmem_cache *cachep, void *objp) { unsigned long flags; @@ -2328,30 +3264,31 @@ void kmem_cache_free (kmem_cache_t *cachep, void *objp) __cache_free(cachep, objp); local_irq_restore(flags); } - EXPORT_SYMBOL(kmem_cache_free); /** * kfree - free previously allocated memory * @objp: pointer returned by kmalloc. * + * If @objp is NULL, no operation is performed. + * * Don't free memory not originally allocated by kmalloc() * or you will run into trouble. */ -void kfree (const void *objp) +void kfree(const void *objp) { - kmem_cache_t *c; + struct kmem_cache *c; unsigned long flags; - if (!objp) + if (unlikely(!objp)) return; local_irq_save(flags); kfree_debugcheck(objp); - c = GET_PAGE_CACHE(virt_to_page(objp)); - __cache_free(c, (void*)objp); + c = virt_to_cache(objp); + mutex_debug_check_no_locks_freed(objp, obj_size(c)); + __cache_free(c, (void *)objp); local_irq_restore(flags); } - EXPORT_SYMBOL(kfree); #ifdef CONFIG_SMP @@ -2362,49 +3299,93 @@ EXPORT_SYMBOL(kfree); * Don't free memory not originally allocated by alloc_percpu() * The complemented objp is to check for that. */ -void -free_percpu(const void *objp) +void free_percpu(const void *objp) { int i; - struct percpu_data *p = (struct percpu_data *) (~(unsigned long) objp); + struct percpu_data *p = (struct percpu_data *)(~(unsigned long)objp); - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_possible(i)) - continue; - kfree(p->ptrs[i]); - } + /* + * We allocate for all cpus so we cannot use for online cpu here. + */ + for_each_cpu(i) + kfree(p->ptrs[i]); + kfree(p); } - EXPORT_SYMBOL(free_percpu); #endif -unsigned int kmem_cache_size(kmem_cache_t *cachep) +unsigned int kmem_cache_size(struct kmem_cache *cachep) { - return obj_reallen(cachep); + return obj_size(cachep); } - EXPORT_SYMBOL(kmem_cache_size); -kmem_cache_t * kmem_find_general_cachep (size_t size, int gfpflags) +const char *kmem_cache_name(struct kmem_cache *cachep) { - struct cache_sizes *csizep = malloc_sizes; + return cachep->name; +} +EXPORT_SYMBOL_GPL(kmem_cache_name); - /* This function could be moved to the header file, and - * made inline so consumers can quickly determine what - * cache pointer they require. - */ - for ( ; csizep->cs_size; csizep++) { - if (size > csizep->cs_size) +/* + * This initializes kmem_list3 for all nodes. + */ +static int alloc_kmemlist(struct kmem_cache *cachep) +{ + int node; + struct kmem_list3 *l3; + int err = 0; + + for_each_online_node(node) { + struct array_cache *nc = NULL, *new; + struct array_cache **new_alien = NULL; +#ifdef CONFIG_NUMA + if (!(new_alien = alloc_alien_cache(node, cachep->limit))) + goto fail; +#endif + if (!(new = alloc_arraycache(node, (cachep->shared * + cachep->batchcount), + 0xbaadf00d))) + goto fail; + if ((l3 = cachep->nodelists[node])) { + + spin_lock_irq(&l3->list_lock); + + if ((nc = cachep->nodelists[node]->shared)) + free_block(cachep, nc->entry, nc->avail, node); + + l3->shared = new; + if (!cachep->nodelists[node]->alien) { + l3->alien = new_alien; + new_alien = NULL; + } + l3->free_limit = (1 + nr_cpus_node(node)) * + cachep->batchcount + cachep->num; + spin_unlock_irq(&l3->list_lock); + kfree(nc); + free_alien_cache(new_alien); continue; - break; + } + if (!(l3 = kmalloc_node(sizeof(struct kmem_list3), + GFP_KERNEL, node))) + goto fail; + + kmem_list3_init(l3); + l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + l3->shared = new; + l3->alien = new_alien; + l3->free_limit = (1 + nr_cpus_node(node)) * + cachep->batchcount + cachep->num; + cachep->nodelists[node] = l3; } - return (gfpflags & GFP_DMA) ? csizep->cs_dmacachep : csizep->cs_cachep; + return err; + fail: + err = -ENOMEM; + return err; } -EXPORT_SYMBOL(kmem_find_general_cachep); - struct ccupdate_struct { - kmem_cache_t *cachep; + struct kmem_cache *cachep; struct array_cache *new[NR_CPUS]; }; @@ -2414,78 +3395,59 @@ static void do_ccupdate_local(void *info) struct array_cache *old; check_irq_off(); - old = ac_data(new->cachep); - + old = cpu_cache_get(new->cachep); + new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()]; new->new[smp_processor_id()] = old; } - -static int do_tune_cpucache (kmem_cache_t* cachep, int limit, int batchcount, int shared) +static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount, + int shared) { struct ccupdate_struct new; - struct array_cache *new_shared; - int i; - - memset(&new.new,0,sizeof(new.new)); - for (i = 0; i < NR_CPUS; i++) { - struct array_cache *ccnew; - - ccnew = kmalloc(sizeof(void*)*limit+ - sizeof(struct array_cache), GFP_KERNEL); - if (!ccnew) { - for (i--; i >= 0; i--) kfree(new.new[i]); + int i, err; + + memset(&new.new, 0, sizeof(new.new)); + for_each_online_cpu(i) { + new.new[i] = + alloc_arraycache(cpu_to_node(i), limit, batchcount); + if (!new.new[i]) { + for (i--; i >= 0; i--) + kfree(new.new[i]); return -ENOMEM; } - ccnew->avail = 0; - ccnew->limit = limit; - ccnew->batchcount = batchcount; - ccnew->touched = 0; - new.new[i] = ccnew; } new.cachep = cachep; smp_call_function_all_cpus(do_ccupdate_local, (void *)&new); - + check_irq_on(); - spin_lock_irq(&cachep->spinlock); + spin_lock(&cachep->spinlock); cachep->batchcount = batchcount; cachep->limit = limit; - cachep->free_limit = (1+num_online_cpus())*cachep->batchcount + cachep->num; - spin_unlock_irq(&cachep->spinlock); + cachep->shared = shared; + spin_unlock(&cachep->spinlock); - for (i = 0; i < NR_CPUS; i++) { + for_each_online_cpu(i) { struct array_cache *ccold = new.new[i]; if (!ccold) continue; - spin_lock_irq(&cachep->spinlock); - free_block(cachep, ac_entry(ccold), ccold->avail); - spin_unlock_irq(&cachep->spinlock); + spin_lock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock); + free_block(cachep, ccold->entry, ccold->avail, cpu_to_node(i)); + spin_unlock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock); kfree(ccold); } - new_shared = kmalloc(sizeof(void*)*batchcount*shared+ - sizeof(struct array_cache), GFP_KERNEL); - if (new_shared) { - struct array_cache *old; - new_shared->avail = 0; - new_shared->limit = batchcount*shared; - new_shared->batchcount = 0xbaadf00d; - new_shared->touched = 0; - spin_lock_irq(&cachep->spinlock); - old = cachep->lists.shared; - cachep->lists.shared = new_shared; - if (old) - free_block(cachep, ac_entry(old), old->avail); - spin_unlock_irq(&cachep->spinlock); - kfree(old); + err = alloc_kmemlist(cachep); + if (err) { + printk(KERN_ERR "alloc_kmemlist failed for %s, error %d.\n", + cachep->name, -err); + BUG(); } - return 0; } - -static void enable_cpucache (kmem_cache_t *cachep) +static void enable_cpucache(struct kmem_cache *cachep) { int err; int limit, shared; @@ -2498,13 +3460,13 @@ static void enable_cpucache (kmem_cache_t *cachep) * The numbers are guessed, we should auto-tune as described by * Bonwick. */ - if (cachep->objsize > 131072) + if (cachep->buffer_size > 131072) limit = 1; - else if (cachep->objsize > PAGE_SIZE) + else if (cachep->buffer_size > PAGE_SIZE) limit = 8; - else if (cachep->objsize > 1024) + else if (cachep->buffer_size > 1024) limit = 24; - else if (cachep->objsize > 256) + else if (cachep->buffer_size > 256) limit = 54; else limit = 120; @@ -2519,7 +3481,7 @@ static void enable_cpucache (kmem_cache_t *cachep) */ shared = 0; #ifdef CONFIG_SMP - if (cachep->objsize <= PAGE_SIZE) + if (cachep->buffer_size <= PAGE_SIZE) shared = 8; #endif @@ -2531,111 +3493,96 @@ static void enable_cpucache (kmem_cache_t *cachep) if (limit > 32) limit = 32; #endif - err = do_tune_cpucache(cachep, limit, (limit+1)/2, shared); + err = do_tune_cpucache(cachep, limit, (limit + 1) / 2, shared); if (err) printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n", - cachep->name, -err); -} - -static void drain_array(kmem_cache_t *cachep, struct array_cache *ac) -{ - int tofree; - - check_irq_off(); - if (ac->touched) { - ac->touched = 0; - } else if (ac->avail) { - tofree = (ac->limit+4)/5; - if (tofree > ac->avail) { - tofree = (ac->avail+1)/2; - } - spin_lock(&cachep->spinlock); - free_block(cachep, ac_entry(ac), tofree); - spin_unlock(&cachep->spinlock); - ac->avail -= tofree; - memmove(&ac_entry(ac)[0], &ac_entry(ac)[tofree], - sizeof(void*)*ac->avail); - } + cachep->name, -err); } -static void drain_array_locked(kmem_cache_t *cachep, - struct array_cache *ac, int force) +static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac, + int force, int node) { int tofree; - check_spinlock_acquired(cachep); + check_spinlock_acquired_node(cachep, node); if (ac->touched && !force) { ac->touched = 0; } else if (ac->avail) { - tofree = force ? ac->avail : (ac->limit+4)/5; + tofree = force ? ac->avail : (ac->limit + 4) / 5; if (tofree > ac->avail) { - tofree = (ac->avail+1)/2; + tofree = (ac->avail + 1) / 2; } - free_block(cachep, ac_entry(ac), tofree); + free_block(cachep, ac->entry, tofree, node); ac->avail -= tofree; - memmove(&ac_entry(ac)[0], &ac_entry(ac)[tofree], - sizeof(void*)*ac->avail); + memmove(ac->entry, &(ac->entry[tofree]), + sizeof(void *) * ac->avail); } } /** * cache_reap - Reclaim memory from caches. + * @unused: unused parameter * - * Called from a timer, every few seconds + * Called from workqueue/eventd every few seconds. * Purpose: * - clear the per-cpu caches for this CPU. * - return freeable pages to the main free memory pool. * - * If we cannot acquire the cache chain semaphore then just give up - we'll - * try again next timer interrupt. + * If we cannot acquire the cache chain mutex then just give up - we'll + * try again on the next iteration. */ -static inline void cache_reap (void) +static void cache_reap(void *unused) { struct list_head *walk; + struct kmem_list3 *l3; -#if DEBUG - BUG_ON(!in_interrupt()); - BUG_ON(in_irq()); -#endif - if (down_trylock(&cache_chain_sem)) + if (!mutex_trylock(&cache_chain_mutex)) { + /* Give up. Setup the next iteration. */ + schedule_delayed_work(&__get_cpu_var(reap_work), + REAPTIMEOUT_CPUC); return; + } list_for_each(walk, &cache_chain) { - kmem_cache_t *searchp; - struct list_head* p; + struct kmem_cache *searchp; + struct list_head *p; int tofree; struct slab *slabp; - searchp = list_entry(walk, kmem_cache_t, next); + searchp = list_entry(walk, struct kmem_cache, next); if (searchp->flags & SLAB_NO_REAP) goto next; check_irq_on(); - local_irq_disable(); - drain_array(searchp, ac_data(searchp)); - if(time_after(searchp->lists.next_reap, jiffies)) - goto next_irqon; + l3 = searchp->nodelists[numa_node_id()]; + reap_alien(searchp, l3); + spin_lock_irq(&l3->list_lock); + + drain_array_locked(searchp, cpu_cache_get(searchp), 0, + numa_node_id()); - spin_lock(&searchp->spinlock); - if(time_after(searchp->lists.next_reap, jiffies)) { + if (time_after(l3->next_reap, jiffies)) goto next_unlock; - } - searchp->lists.next_reap = jiffies + REAPTIMEOUT_LIST3; - if (searchp->lists.shared) - drain_array_locked(searchp, searchp->lists.shared, 0); + l3->next_reap = jiffies + REAPTIMEOUT_LIST3; + + if (l3->shared) + drain_array_locked(searchp, l3->shared, 0, + numa_node_id()); - if (searchp->lists.free_touched) { - searchp->lists.free_touched = 0; + if (l3->free_touched) { + l3->free_touched = 0; goto next_unlock; } - tofree = (searchp->free_limit+5*searchp->num-1)/(5*searchp->num); + tofree = + (l3->free_limit + 5 * searchp->num - + 1) / (5 * searchp->num); do { - p = list3_data(searchp)->slabs_free.next; - if (p == &(list3_data(searchp)->slabs_free)) + p = l3->slabs_free.next; + if (p == &(l3->slabs_free)) break; slabp = list_entry(p, struct slab, list); @@ -2648,168 +3595,160 @@ static inline void cache_reap (void) * searchp cannot disappear, we hold * cache_chain_lock */ - searchp->lists.free_objects -= searchp->num; - spin_unlock_irq(&searchp->spinlock); + l3->free_objects -= searchp->num; + spin_unlock_irq(&l3->list_lock); slab_destroy(searchp, slabp); - spin_lock_irq(&searchp->spinlock); - } while(--tofree > 0); -next_unlock: - spin_unlock(&searchp->spinlock); -next_irqon: - local_irq_enable(); -next: - ; + spin_lock_irq(&l3->list_lock); + } while (--tofree > 0); + next_unlock: + spin_unlock_irq(&l3->list_lock); + next: + cond_resched(); } check_irq_on(); - up(&cache_chain_sem); -} - -/* - * This is a timer handler. There is one per CPU. It is called periodially - * to shrink this CPU's caches. Otherwise there could be memory tied up - * for long periods (or for ever) due to load changes. - */ -static void reap_timer_fnc(unsigned long cpu) -{ - struct timer_list *rt = &__get_cpu_var(reap_timers); - - /* CPU hotplug can drag us off cpu: don't run on wrong CPU */ - if (!cpu_is_offline(cpu)) { - cache_reap(); - mod_timer(rt, jiffies + REAPTIMEOUT_CPUC + cpu); - } + mutex_unlock(&cache_chain_mutex); + next_reap_node(); + /* Setup the next iteration */ + schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC); } #ifdef CONFIG_PROC_FS -static void *s_start(struct seq_file *m, loff_t *pos) +static void print_slabinfo_header(struct seq_file *m) { - loff_t n = *pos; - struct list_head *p; - - down(&cache_chain_sem); - if (!n) { - /* - * Output format version, so at least we can change it - * without _too_ many complaints. - */ + /* + * Output format version, so at least we can change it + * without _too_ many complaints. + */ #if STATS - seq_puts(m, "slabinfo - version: 2.0 (statistics)\n"); + seq_puts(m, "slabinfo - version: 2.1 (statistics)\n"); #else - seq_puts(m, "slabinfo - version: 2.0\n"); + seq_puts(m, "slabinfo - version: 2.1\n"); #endif - seq_puts(m, "# name "); - seq_puts(m, " : tunables "); - seq_puts(m, " : slabdata "); + seq_puts(m, "# name " + " "); + seq_puts(m, " : tunables "); + seq_puts(m, " : slabdata "); #if STATS - seq_puts(m, " : globalstat "); - seq_puts(m, " : cpustat "); + seq_puts(m, " : globalstat " + " "); + seq_puts(m, " : cpustat "); #endif - seq_putc(m, '\n'); - } + seq_putc(m, '\n'); +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + loff_t n = *pos; + struct list_head *p; + + mutex_lock(&cache_chain_mutex); + if (!n) + print_slabinfo_header(m); p = cache_chain.next; while (n--) { p = p->next; if (p == &cache_chain) return NULL; } - return list_entry(p, kmem_cache_t, next); + return list_entry(p, struct kmem_cache, next); } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { - kmem_cache_t *cachep = p; + struct kmem_cache *cachep = p; ++*pos; return cachep->next.next == &cache_chain ? NULL - : list_entry(cachep->next.next, kmem_cache_t, next); + : list_entry(cachep->next.next, struct kmem_cache, next); } static void s_stop(struct seq_file *m, void *p) { - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); } static int s_show(struct seq_file *m, void *p) { - kmem_cache_t *cachep = p; + struct kmem_cache *cachep = p; struct list_head *q; - struct slab *slabp; - unsigned long active_objs; - unsigned long num_objs; - unsigned long active_slabs = 0; - unsigned long num_slabs; - const char *name; + struct slab *slabp; + unsigned long active_objs; + unsigned long num_objs; + unsigned long active_slabs = 0; + unsigned long num_slabs, free_objects = 0, shared_avail = 0; + const char *name; char *error = NULL; - mm_segment_t old_fs; - char tmp; + int node; + struct kmem_list3 *l3; - check_irq_on(); - spin_lock_irq(&cachep->spinlock); + spin_lock(&cachep->spinlock); active_objs = 0; num_slabs = 0; - list_for_each(q,&cachep->lists.slabs_full) { - slabp = list_entry(q, struct slab, list); - if (slabp->inuse != cachep->num && !error) - error = "slabs_full accounting error"; - active_objs += cachep->num; - active_slabs++; - } - list_for_each(q,&cachep->lists.slabs_partial) { - slabp = list_entry(q, struct slab, list); - if (slabp->inuse == cachep->num && !error) - error = "slabs_partial inuse accounting error"; - if (!slabp->inuse && !error) - error = "slabs_partial/inuse accounting error"; - active_objs += slabp->inuse; - active_slabs++; - } - list_for_each(q,&cachep->lists.slabs_free) { - slabp = list_entry(q, struct slab, list); - if (slabp->inuse && !error) - error = "slabs_free/inuse accounting error"; - num_slabs++; - } - num_slabs+=active_slabs; - num_objs = num_slabs*cachep->num; - if (num_objs - active_objs != cachep->lists.free_objects && !error) - error = "free_objects accounting error"; + for_each_online_node(node) { + l3 = cachep->nodelists[node]; + if (!l3) + continue; - name = cachep->name; + check_irq_on(); + spin_lock_irq(&l3->list_lock); + + list_for_each(q, &l3->slabs_full) { + slabp = list_entry(q, struct slab, list); + if (slabp->inuse != cachep->num && !error) + error = "slabs_full accounting error"; + active_objs += cachep->num; + active_slabs++; + } + list_for_each(q, &l3->slabs_partial) { + slabp = list_entry(q, struct slab, list); + if (slabp->inuse == cachep->num && !error) + error = "slabs_partial inuse accounting error"; + if (!slabp->inuse && !error) + error = "slabs_partial/inuse accounting error"; + active_objs += slabp->inuse; + active_slabs++; + } + list_for_each(q, &l3->slabs_free) { + slabp = list_entry(q, struct slab, list); + if (slabp->inuse && !error) + error = "slabs_free/inuse accounting error"; + num_slabs++; + } + free_objects += l3->free_objects; + if (l3->shared) + shared_avail += l3->shared->avail; - /* - * Check to see if `name' resides inside a module which has been - * unloaded (someone forgot to destroy their cache) - */ - old_fs = get_fs(); - set_fs(KERNEL_DS); - if (__get_user(tmp, name)) - name = "broken"; - set_fs(old_fs); + spin_unlock_irq(&l3->list_lock); + } + num_slabs += active_slabs; + num_objs = num_slabs * cachep->num; + if (num_objs - active_objs != free_objects && !error) + error = "free_objects accounting error"; + name = cachep->name; if (error) printk(KERN_ERR "slab: cache %s error: %s\n", name, error); seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", - name, active_objs, num_objs, cachep->objsize, - cachep->num, (1<gfporder)); + name, active_objs, num_objs, cachep->buffer_size, + cachep->num, (1 << cachep->gfporder)); seq_printf(m, " : tunables %4u %4u %4u", - cachep->limit, cachep->batchcount, - cachep->lists.shared->limit/cachep->batchcount); - seq_printf(m, " : slabdata %6lu %6lu %6u", - active_slabs, num_slabs, cachep->lists.shared->avail); + cachep->limit, cachep->batchcount, cachep->shared); + seq_printf(m, " : slabdata %6lu %6lu %6lu", + active_slabs, num_slabs, shared_avail); #if STATS - { /* list3 stats */ + { /* list3 stats */ unsigned long high = cachep->high_mark; unsigned long allocs = cachep->num_allocations; unsigned long grown = cachep->grown; unsigned long reaped = cachep->reaped; unsigned long errors = cachep->errors; unsigned long max_freeable = cachep->max_freeable; - unsigned long free_limit = cachep->free_limit; + unsigned long node_allocs = cachep->node_allocs; + unsigned long node_frees = cachep->node_frees; - seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu %4lu %4lu %4lu", - allocs, high, grown, reaped, errors, - max_freeable, free_limit); + seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \ + %4lu %4lu %4lu %4lu", allocs, high, grown, reaped, errors, max_freeable, node_allocs, node_frees); } /* cpu stats */ { @@ -2819,11 +3758,11 @@ static int s_show(struct seq_file *m, void *p) unsigned long freemiss = atomic_read(&cachep->freemiss); seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu", - allochit, allocmiss, freehit, freemiss); + allochit, allocmiss, freehit, freemiss); } #endif seq_putc(m, '\n'); - spin_unlock_irq(&cachep->spinlock); + spin_unlock(&cachep->spinlock); return 0; } @@ -2842,10 +3781,10 @@ static int s_show(struct seq_file *m, void *p) */ struct seq_operations slabinfo_op = { - .start = s_start, - .next = s_next, - .stop = s_stop, - .show = s_show, + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, }; #define MAX_SLABINFO_WRITE 128 @@ -2856,18 +3795,18 @@ struct seq_operations slabinfo_op = { * @count: data length * @ppos: unused */ -ssize_t slabinfo_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos) +ssize_t slabinfo_write(struct file *file, const char __user * buffer, + size_t count, loff_t *ppos) { - char kbuf[MAX_SLABINFO_WRITE+1], *tmp; + char kbuf[MAX_SLABINFO_WRITE + 1], *tmp; int limit, batchcount, shared, res; struct list_head *p; - + if (count > MAX_SLABINFO_WRITE) return -EINVAL; if (copy_from_user(&kbuf, buffer, count)) return -EFAULT; - kbuf[MAX_SLABINFO_WRITE] = '\0'; + kbuf[MAX_SLABINFO_WRITE] = '\0'; tmp = strchr(kbuf, ' '); if (!tmp) @@ -2878,111 +3817,47 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, return -EINVAL; /* Find the cache in the chain of caches. */ - down(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); res = -EINVAL; - list_for_each(p,&cache_chain) { - kmem_cache_t *cachep = list_entry(p, kmem_cache_t, next); + list_for_each(p, &cache_chain) { + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, + next); if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || - batchcount > limit || - shared < 0) { - res = -EINVAL; + batchcount > limit || shared < 0) { + res = 0; } else { - res = do_tune_cpucache(cachep, limit, batchcount, shared); + res = do_tune_cpucache(cachep, limit, + batchcount, shared); } break; } } - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); if (res >= 0) res = count; return res; } #endif +/** + * ksize - get the actual amount of memory allocated for a given object + * @objp: Pointer to the object + * + * kmalloc may internally round up allocations and return more memory + * than requested. ksize() can be used to determine the actual amount of + * memory allocated. The caller may use this additional memory, even though + * a smaller amount of memory was initially specified with the kmalloc call. + * The caller must guarantee that objp points to a valid object previously + * allocated with either kmalloc() or kmem_cache_alloc(). The object + * must not be freed during the duration of the call. + */ unsigned int ksize(const void *objp) { - kmem_cache_t *c; - unsigned long flags; - unsigned int size = 0; - - if (likely(objp != NULL)) { - local_irq_save(flags); - c = GET_PAGE_CACHE(virt_to_page(objp)); - size = kmem_cache_size(c); - local_irq_restore(flags); - } - - return size; -} - -void ptrinfo(unsigned long addr) -{ - struct page *page; - - printk("Dumping data about address %p.\n", (void*)addr); - if (!virt_addr_valid((void*)addr)) { - printk("virt addr invalid.\n"); - return; - } -#ifdef CONFIG_MMU - do { - pgd_t *pgd = pgd_offset_k(addr); - pmd_t *pmd; - if (pgd_none(*pgd)) { - printk("No pgd.\n"); - break; - } - pmd = pmd_offset(pgd, addr); - if (pmd_none(*pmd)) { - printk("No pmd.\n"); - break; - } -#ifdef CONFIG_X86 - if (pmd_large(*pmd)) { - printk("Large page.\n"); - break; - } -#endif - printk("normal page, pte_val 0x%llx\n", - (unsigned long long)pte_val(*pte_offset_kernel(pmd, addr))); - } while(0); -#endif - - page = virt_to_page((void*)addr); - printk("struct page at %p, flags %08lx\n", - page, (unsigned long)page->flags); - if (PageSlab(page)) { - kmem_cache_t *c; - struct slab *s; - unsigned long flags; - int objnr; - void *objp; - - c = GET_PAGE_CACHE(page); - printk("belongs to cache %s.\n",c->name); - - spin_lock_irqsave(&c->spinlock, flags); - s = GET_PAGE_SLAB(page); - printk("slabp %p with %d inuse objects (from %d).\n", - s, s->inuse, c->num); - check_slabp(c,s); - - objnr = (addr-(unsigned long)s->s_mem)/c->objsize; - objp = s->s_mem+c->objsize*objnr; - printk("points into object no %d, starting at %p, len %d.\n", - objnr, objp, c->objsize); - if (objnr >= c->num) { - printk("Bad obj number.\n"); - } else { - kernel_map_pages(virt_to_page(objp), - c->objsize/PAGE_SIZE, 1); - - print_objinfo(c, objp, 2); - } - spin_unlock_irqrestore(&c->spinlock, flags); + if (unlikely(objp == NULL)) + return 0; - } + return obj_size(virt_to_cache(objp)); }