diff options
Diffstat (limited to 'mm/slab.c')
| -rw-r--r-- | mm/slab.c | 1194 |
1 files changed, 610 insertions, 584 deletions
diff --git a/mm/slab.c b/mm/slab.c index e5ec26e0c460..6f8495e2185b 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -68,7 +68,7 @@ * 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()). @@ -103,6 +103,8 @@ #include <linux/rcupdate.h> #include <linux/string.h> #include <linux/nodemask.h> +#include <linux/mempolicy.h> +#include <linux/mutex.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -130,7 +132,6 @@ #define FORCED_DEBUG 0 #endif - /* Shouldn't this be in a header file somewhere? */ #define BYTES_PER_WORD sizeof(void *) @@ -217,12 +218,12 @@ 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; - unsigned short nodeid; + 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; }; /* @@ -242,9 +243,9 @@ struct slab { * We assume struct slab_rcu can overlay struct slab when destroying. */ struct slab_rcu { - struct rcu_head head; - kmem_cache_t *cachep; - void *addr; + struct rcu_head head; + kmem_cache_t *cachep; + void *addr; }; /* @@ -279,23 +280,23 @@ 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 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; - unsigned long next_reap; - int free_touched; - unsigned int free_limit; - spinlock_t list_lock; - struct array_cache *shared; /* shared per node */ - struct array_cache **alien; /* on other nodes */ + 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; + spinlock_t list_lock; + struct array_cache *shared; /* shared per node */ + struct array_cache **alien; /* on other nodes */ }; /* @@ -367,63 +368,63 @@ static inline void kmem_list3_init(struct kmem_list3 *parent) * * manages a cache. */ - + struct kmem_cache { /* 1) per-cpu data, touched during every alloc/free */ - struct array_cache *array[NR_CPUS]; - unsigned int batchcount; - unsigned int limit; - unsigned int shared; - unsigned int objsize; + struct array_cache *array[NR_CPUS]; + unsigned int batchcount; + unsigned int limit; + unsigned int shared; + unsigned int objsize; /* 2) touched by every alloc & free from the backend */ - struct kmem_list3 *nodelists[MAX_NUMNODES]; - unsigned int flags; /* constant flags */ - unsigned int num; /* # of objs per slab */ - 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 */ - gfp_t 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 */ + unsigned int colour_next; /* cache colouring */ + kmem_cache_t *slabp_cache; + unsigned int slab_size; + unsigned int dflags; /* dynamic flags */ /* constructor func */ - void (*ctor)(void *, kmem_cache_t *, unsigned long); + void (*ctor) (void *, kmem_cache_t *, unsigned long); /* de-constructor func */ - void (*dtor)(void *, kmem_cache_t *, unsigned long); + void (*dtor) (void *, kmem_cache_t *, 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; - unsigned long node_allocs; - unsigned long node_frees; - 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; + int dbghead; + int reallen; #endif }; @@ -523,14 +524,15 @@ static unsigned long *dbg_redzone2(kmem_cache_t *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->objsize - + 2 * BYTES_PER_WORD); + return (unsigned long *)(objp + cachep->objsize - BYTES_PER_WORD); } static void **dbg_userword(kmem_cache_t *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_STORE_USER)); - return (void**)(objp+cachep->objsize-BYTES_PER_WORD); + return (void **)(objp + cachep->objsize - BYTES_PER_WORD); } #else @@ -607,31 +609,31 @@ struct cache_names { static struct cache_names __initdata cache_names[] = { #define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" }, #include <linux/kmalloc_sizes.h> - { NULL, } + {NULL,} #undef CACHE }; static struct arraycache_init initarray_cache __initdata = - { { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; + { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; static struct arraycache_init initarray_generic = - { { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; + { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ static kmem_cache_t cache_cache = { - .batchcount = 1, - .limit = BOOT_CPUCACHE_ENTRIES, - .shared = 1, - .objsize = sizeof(kmem_cache_t), - .flags = SLAB_NO_REAP, - .spinlock = SPIN_LOCK_UNLOCKED, - .name = "kmem_cache", + .batchcount = 1, + .limit = BOOT_CPUCACHE_ENTRIES, + .shared = 1, + .objsize = sizeof(kmem_cache_t), + .flags = SLAB_NO_REAP, + .spinlock = SPIN_LOCK_UNLOCKED, + .name = "kmem_cache", #if DEBUG - .reallen = sizeof(kmem_cache_t), + .reallen = sizeof(kmem_cache_t), #endif }; /* Guard access to the cache-chain. */ -static struct semaphore cache_chain_sem; +static DEFINE_MUTEX(cache_chain_mutex); static struct list_head cache_chain; /* @@ -655,9 +657,9 @@ static enum { static DEFINE_PER_CPU(struct work_struct, reap_work); -static void free_block(kmem_cache_t* cachep, void** objpp, int len, int node); -static void enable_cpucache (kmem_cache_t *cachep); -static void cache_reap (void *unused); +static void free_block(kmem_cache_t *cachep, void **objpp, int len, int node); +static void enable_cpucache(kmem_cache_t *cachep); +static void cache_reap(void *unused); static int __node_shrink(kmem_cache_t *cachep, int node); static inline struct array_cache *ac_data(kmem_cache_t *cachep) @@ -671,9 +673,9 @@ static inline kmem_cache_t *__find_general_cachep(size_t size, gfp_t gfpflags) #if DEBUG /* This happens if someone tries to call - * kmem_cache_create(), or __kmalloc(), before - * the generic caches are initialized. - */ + * 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) @@ -697,10 +699,10 @@ EXPORT_SYMBOL(kmem_find_general_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) + int flags, size_t *left_over, unsigned int *num) { int i; - size_t wastage = PAGE_SIZE<<gfporder; + size_t wastage = PAGE_SIZE << gfporder; size_t extra = 0; size_t base = 0; @@ -709,7 +711,7 @@ static void cache_estimate(unsigned long gfporder, size_t size, size_t align, extra = sizeof(kmem_bufctl_t); } i = 0; - while (i*size + ALIGN(base+i*extra, align) <= wastage) + while (i * size + ALIGN(base + i * extra, align) <= wastage) i++; if (i > 0) i--; @@ -718,8 +720,8 @@ static void cache_estimate(unsigned long gfporder, size_t size, size_t align, i = SLAB_LIMIT; *num = i; - wastage -= i*size; - wastage -= ALIGN(base+i*extra, align); + wastage -= i * size; + wastage -= ALIGN(base + i * extra, align); *left_over = wastage; } @@ -728,7 +730,7 @@ static void cache_estimate(unsigned long gfporder, size_t size, size_t align, static void __slab_error(const char *function, kmem_cache_t *cachep, char *msg) { printk(KERN_ERR "slab error in %s(): cache `%s': %s\n", - function, cachep->name, msg); + function, cachep->name, msg); dump_stack(); } @@ -755,9 +757,9 @@ static void __devinit start_cpu_timer(int cpu) } static struct array_cache *alloc_arraycache(int node, int entries, - int batchcount) + int batchcount) { - int memsize = sizeof(void*)*entries+sizeof(struct array_cache); + int memsize = sizeof(void *) * entries + sizeof(struct array_cache); struct array_cache *nc = NULL; nc = kmalloc_node(memsize, GFP_KERNEL, node); @@ -772,10 +774,12 @@ static struct array_cache *alloc_arraycache(int node, int entries, } #ifdef CONFIG_NUMA +static void *__cache_alloc_node(kmem_cache_t *, gfp_t, int); + static inline struct array_cache **alloc_alien_cache(int node, int limit) { struct array_cache **ac_ptr; - int memsize = sizeof(void*)*MAX_NUMNODES; + int memsize = sizeof(void *) * MAX_NUMNODES; int i; if (limit > 1) @@ -789,7 +793,7 @@ static inline struct array_cache **alloc_alien_cache(int node, int limit) } ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d); if (!ac_ptr[i]) { - for (i--; i <=0; i--) + for (i--; i <= 0; i--) kfree(ac_ptr[i]); kfree(ac_ptr); return NULL; @@ -807,12 +811,13 @@ static inline void free_alien_cache(struct array_cache **ac_ptr) return; for_each_node(i) - kfree(ac_ptr[i]); + kfree(ac_ptr[i]); kfree(ac_ptr); } -static inline void __drain_alien_cache(kmem_cache_t *cachep, struct array_cache *ac, int node) +static inline void __drain_alien_cache(kmem_cache_t *cachep, + struct array_cache *ac, int node) { struct kmem_list3 *rl3 = cachep->nodelists[node]; @@ -826,7 +831,7 @@ static inline void __drain_alien_cache(kmem_cache_t *cachep, struct array_cache static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3) { - int i=0; + int i = 0; struct array_cache *ac; unsigned long flags; @@ -846,18 +851,17 @@ static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3) #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; + kmem_cache_t *cachep; struct kmem_list3 *l3 = NULL; int node = cpu_to_node(cpu); int memsize = sizeof(struct kmem_list3); - struct array_cache *nc = NULL; 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 @@ -871,27 +875,29 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, */ if (!cachep->nodelists[node]) { if (!(l3 = kmalloc_node(memsize, - GFP_KERNEL, node))) + GFP_KERNEL, node))) goto bad; kmem_list3_init(l3); l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep)%REAPTIMEOUT_LIST3; + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; cachep->nodelists[node] = l3; } spin_lock_irq(&cachep->nodelists[node]->list_lock); cachep->nodelists[node]->free_limit = - (1 + nr_cpus_node(node)) * - cachep->batchcount + cachep->num; + (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 */ + & array cache's */ list_for_each_entry(cachep, &cache_chain, next) { + struct array_cache *nc; + nc = alloc_arraycache(node, cachep->limit, - cachep->batchcount); + cachep->batchcount); if (!nc) goto bad; cachep->array[cpu] = nc; @@ -900,16 +906,17 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, BUG_ON(!l3); if (!l3->shared) { if (!(nc = alloc_arraycache(node, - cachep->shared*cachep->batchcount, - 0xbaadf00d))) - goto bad; + cachep->shared * + cachep->batchcount, + 0xbaadf00d))) + goto bad; /* we are serialised from CPU_DEAD or - CPU_UP_CANCELLED by the cpucontrol lock */ + CPU_UP_CANCELLED by the cpucontrol lock */ l3->shared = nc; } } - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); break; case CPU_ONLINE: start_cpu_timer(cpu); @@ -918,7 +925,7 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, case CPU_DEAD: /* 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; @@ -942,13 +949,13 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, free_block(cachep, nc->entry, nc->avail, node); if (!cpus_empty(mask)) { - spin_unlock(&l3->list_lock); - goto unlock_cache; - } + spin_unlock(&l3->list_lock); + goto unlock_cache; + } if (l3->shared) { free_block(cachep, l3->shared->entry, - l3->shared->avail, node); + l3->shared->avail, node); kfree(l3->shared); l3->shared = NULL; } @@ -966,17 +973,17 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, } else { spin_unlock(&l3->list_lock); } -unlock_cache: + unlock_cache: spin_unlock_irq(&cachep->spinlock); kfree(nc); } - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); break; #endif } return NOTIFY_OK; -bad: - up(&cache_chain_sem); + bad: + mutex_unlock(&cache_chain_mutex); return NOTIFY_BAD; } @@ -985,8 +992,7 @@ static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 }; /* * swap the static kmem_list3 with kmalloced memory */ -static void init_list(kmem_cache_t *cachep, struct kmem_list3 *list, - int nodeid) +static void init_list(kmem_cache_t *cachep, struct kmem_list3 *list, int nodeid) { struct kmem_list3 *ptr; @@ -1045,7 +1051,6 @@ void __init kmem_cache_init(void) */ /* 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(); @@ -1055,14 +1060,14 @@ void __init kmem_cache_init(void) cache_cache.objsize = ALIGN(cache_cache.objsize, cache_line_size()); cache_estimate(0, cache_cache.objsize, cache_line_size(), 0, - &left_over, &cache_cache.num); + &left_over, &cache_cache.num); if (!cache_cache.num) BUG(); - cache_cache.colour = left_over/cache_cache.colour_off; + 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.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; @@ -1074,14 +1079,18 @@ void __init kmem_cache_init(void) */ 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); + 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); + 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) { /* @@ -1091,35 +1100,41 @@ void __init kmem_cache_init(void) * Note for systems short on memory removing the alignment will * allow tighter packing of the smaller caches. */ - if(!sizes->cs_cachep) + if (!sizes->cs_cachep) sizes->cs_cachep = kmem_cache_create(names->name, - sizes->cs_size, ARCH_KMALLOC_MINALIGN, - (ARCH_KMALLOC_FLAGS | SLAB_PANIC), NULL, NULL); + 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, - (ARCH_KMALLOC_FLAGS | SLAB_CACHE_DMA | SLAB_PANIC), - NULL, NULL); + 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)); + sizeof(struct arraycache_init)); cache_cache.array[smp_processor_id()] = ptr; local_irq_enable(); @@ -1127,11 +1142,11 @@ void __init kmem_cache_init(void) local_irq_disable(); BUG_ON(ac_data(malloc_sizes[INDEX_AC].cs_cachep) - != &initarray_generic.cache); + != &initarray_generic.cache); memcpy(ptr, ac_data(malloc_sizes[INDEX_AC].cs_cachep), - sizeof(struct arraycache_init)); + sizeof(struct arraycache_init)); malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] = - ptr; + ptr; local_irq_enable(); } /* 5) Replace the bootstrap kmem_list3's */ @@ -1139,16 +1154,16 @@ void __init kmem_cache_init(void) int node; /* Replace the static kmem_list3 structures for the boot cpu */ init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], - numa_node_id()); + numa_node_id()); for_each_online_node(node) { init_list(malloc_sizes[INDEX_AC].cs_cachep, - &initkmem_list3[SIZE_AC+node], node); + &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); + &initkmem_list3[SIZE_L3 + node], + node); } } } @@ -1156,10 +1171,10 @@ void __init kmem_cache_init(void) /* 6) resize the head arrays to their final sizes */ { kmem_cache_t *cachep; - down(&cache_chain_sem); + 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! */ @@ -1184,7 +1199,7 @@ static int __init cpucache_init(void) * pages to gfp. */ for_each_online_cpu(cpu) - start_cpu_timer(cpu); + start_cpu_timer(cpu); return 0; } @@ -1226,7 +1241,7 @@ static void *kmem_getpages(kmem_cache_t *cachep, gfp_t flags, int nodeid) */ static void kmem_freepages(kmem_cache_t *cachep, void *addr) { - unsigned long i = (1<<cachep->gfporder); + unsigned long i = (1 << cachep->gfporder); struct page *page = virt_to_page(addr); const unsigned long nr_freed = i; @@ -1239,13 +1254,13 @@ static 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<<cachep->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 slab_rcu *slab_rcu = (struct slab_rcu *)head; kmem_cache_t *cachep = slab_rcu->cachep; kmem_freepages(cachep, slab_rcu->addr); @@ -1257,19 +1272,19 @@ static void kmem_rcu_free(struct rcu_head *head) #ifdef CONFIG_DEBUG_PAGEALLOC static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr, - unsigned long caller) + unsigned long caller) { int size = obj_reallen(cachep); - addr = (unsigned long *)&((char*)addr)[obj_dbghead(cachep)]; + addr = (unsigned long *)&((char *)addr)[obj_dbghead(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; @@ -1277,7 +1292,7 @@ static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr, 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; @@ -1285,25 +1300,25 @@ static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr, } } - *addr++=0x87654321; + *addr++ = 0x87654321; } #endif static void poison_obj(kmem_cache_t *cachep, void *addr, unsigned char val) { int size = obj_reallen(cachep); - addr = &((char*)addr)[obj_dbghead(cachep)]; + addr = &((char *)addr)[obj_dbghead(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;i<limit;i++) { - printk(" %02x", (unsigned char)data[offset+i]); + for (i = 0; i < limit; i++) { + printk(" %02x", (unsigned char)data[offset + i]); } printk("\n"); } @@ -1318,24 +1333,24 @@ static void print_objinfo(kmem_cache_t *cachep, void *objp, int lines) if (cachep->flags & 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)); + *dbg_userword(cachep, objp)); print_symbol("(%s)", - (unsigned long)*dbg_userword(cachep, objp)); + (unsigned long)*dbg_userword(cachep, objp)); printk("\n"); } - realobj = (char*)objp+obj_dbghead(cachep); + realobj = (char *)objp + obj_dbghead(cachep); size = obj_reallen(cachep); - for (i=0; i<size && lines;i+=16, lines--) { + for (i = 0; i < size && lines; i += 16, lines--) { int limit; limit = 16; - if (i+limit > size) - limit = size-i; + if (i + limit > size) + limit = size - i; dump_line(realobj, i, limit); } } @@ -1346,27 +1361,28 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp) int size, i; int lines = 0; - realobj = (char*)objp+obj_dbghead(cachep); + realobj = (char *)objp + obj_dbghead(cachep); size = obj_reallen(cachep); - for (i=0;i<size;i++) { + for (i = 0; i < size; i++) { char exp = POISON_FREE; - if (i == size-1) + if (i == size - 1) exp = POISON_END; if (realobj[i] != exp) { int limit; /* Mismatch ! */ /* Print header */ if (lines == 0) { - printk(KERN_ERR "Slab corruption: start=%p, len=%d\n", - realobj, size); + printk(KERN_ERR + "Slab corruption: start=%p, len=%d\n", + realobj, size); print_objinfo(cachep, objp, 0); } /* Hexdump the affected line */ - i = (i/16)*16; + i = (i / 16) * 16; limit = 16; - if (i+limit > size) - limit = size-i; + if (i + limit > size) + limit = size - i; dump_line(realobj, i, limit); i += 16; lines++; @@ -1382,19 +1398,19 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp) struct slab *slabp = page_get_slab(virt_to_page(objp)); int objnr; - objnr = (objp-slabp->s_mem)/cachep->objsize; + objnr = (objp - slabp->s_mem) / cachep->objsize; if (objnr) { - objp = slabp->s_mem+(objnr-1)*cachep->objsize; - realobj = (char*)objp+obj_dbghead(cachep); + objp = slabp->s_mem + (objnr - 1) * cachep->objsize; + realobj = (char *)objp + obj_dbghead(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->objsize; + realobj = (char *)objp + obj_dbghead(cachep); printk(KERN_ERR "Next obj: start=%p, len=%d\n", - realobj, size); + realobj, size); print_objinfo(cachep, objp, 2); } } @@ -1405,7 +1421,7 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp) * Before calling the slab must have been unlinked from the cache. * The cache-lock is not held/needed. */ -static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) +static void slab_destroy(kmem_cache_t *cachep, struct slab *slabp) { void *addr = slabp->s_mem - slabp->colouroff; @@ -1416,8 +1432,11 @@ static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) 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->objsize % PAGE_SIZE) == 0 + && OFF_SLAB(cachep)) + kernel_map_pages(virt_to_page(objp), + cachep->objsize / PAGE_SIZE, + 1); else check_poison_obj(cachep, objp); #else @@ -1427,20 +1446,20 @@ 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_dbghead(cachep), cachep, 0); } #else 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->objsize * i; + (cachep->dtor) (objp, cachep, 0); } } #endif @@ -1448,7 +1467,7 @@ static void slab_destroy (kmem_cache_t *cachep, struct slab *slabp) if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) { struct slab_rcu *slab_rcu; - slab_rcu = (struct slab_rcu *) slabp; + slab_rcu = (struct slab_rcu *)slabp; slab_rcu->cachep = cachep; slab_rcu->addr = addr; call_rcu(&slab_rcu->head, kmem_rcu_free); @@ -1466,11 +1485,58 @@ static inline void set_up_list3s(kmem_cache_t *cachep, int index) int node; for_each_online_node(node) { - cachep->nodelists[node] = &initkmem_list3[index+node]; + cachep->nodelists[node] = &initkmem_list3[index + node]; cachep->nodelists[node]->next_reap = jiffies + - REAPTIMEOUT_LIST3 + - ((unsigned long)cachep)%REAPTIMEOUT_LIST3; + REAPTIMEOUT_LIST3 + + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + } +} + +/** + * calculate_slab_order - calculate size (page order) of slabs and 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(kmem_cache_t *cachep, size_t size, + size_t align, gfp_t flags) +{ + size_t left_over = 0; + + for (;; cachep->gfporder++) { + unsigned int num; + size_t remainder; + + if (cachep->gfporder > MAX_GFP_ORDER) { + cachep->num = 0; + break; + } + + cache_estimate(cachep->gfporder, size, align, flags, + &remainder, &num); + if (!num) + continue; + /* More than offslab_limit objects will cause problems */ + if (flags & CFLGS_OFF_SLAB && cachep->num > offslab_limit) + break; + + cachep->num = num; + left_over = remainder; + + /* + * Large number of objects is good, but very large slabs are + * currently bad for the gfp()s. + */ + if (cachep->gfporder >= slab_break_gfp_order) + break; + + if ((left_over * 8) <= (PAGE_SIZE << cachep->gfporder)) + /* Acceptable internal fragmentation */ + break; } + return left_over; } /** @@ -1519,16 +1585,15 @@ kmem_cache_create (const char *name, size_t size, size_t align, * Sanity checks... these are all serious usage bugs. */ if ((!name) || - in_interrupt() || - (size < BYTES_PER_WORD) || - (size > (1<<MAX_OBJ_ORDER)*PAGE_SIZE) || - (dtor && !ctor)) { - printk(KERN_ERR "%s: Early error in slab %s\n", - __FUNCTION__, name); - BUG(); - } + in_interrupt() || + (size < BYTES_PER_WORD) || + (size > (1 << MAX_OBJ_ORDER) * PAGE_SIZE) || (dtor && !ctor)) { + printk(KERN_ERR "%s: Early error in slab %s\n", + __FUNCTION__, name); + BUG(); + } - down(&cache_chain_sem); + mutex_lock(&cache_chain_mutex); list_for_each(p, &cache_chain) { kmem_cache_t *pc = list_entry(p, kmem_cache_t, next); @@ -1546,11 +1611,11 @@ kmem_cache_create (const char *name, size_t size, size_t align, set_fs(old_fs); if (res) { printk("SLAB: cache with size %d has lost its name\n", - pc->objsize); + pc->objsize); continue; } - if (!strcmp(pc->name,name)) { + if (!strcmp(pc->name, name)) { printk("kmem_cache_create: duplicate cache %s\n", name); dump_stack(); goto oops; @@ -1562,10 +1627,9 @@ kmem_cache_create (const char *name, size_t size, size_t align, 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 @@ -1573,8 +1637,9 @@ 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; + 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 @@ -1595,9 +1660,9 @@ kmem_cache_create (const char *name, size_t size, size_t align, * 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 (size & (BYTES_PER_WORD - 1)) { + size += (BYTES_PER_WORD - 1); + size &= ~(BYTES_PER_WORD - 1); } /* calculate out the final buffer alignment: */ @@ -1608,7 +1673,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, * objects into one cacheline. */ ralign = cache_line_size(); - while (size <= ralign/2) + while (size <= ralign / 2) ralign /= 2; } else { ralign = BYTES_PER_WORD; @@ -1617,13 +1682,13 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (ralign < ARCH_SLAB_MINALIGN) { ralign = ARCH_SLAB_MINALIGN; if (ralign > BYTES_PER_WORD) - flags &= ~(SLAB_RED_ZONE|SLAB_STORE_USER); + 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); + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); } /* 4) Store it. Note that the debug code below can reduce * the alignment to BYTES_PER_WORD. @@ -1645,7 +1710,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, /* add space for red zone words */ cachep->dbghead += BYTES_PER_WORD; - size += 2*BYTES_PER_WORD; + size += 2 * BYTES_PER_WORD; } if (flags & SLAB_STORE_USER) { /* user store requires word alignment and @@ -1656,7 +1721,8 @@ 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 >= malloc_sizes[INDEX_L3+1].cs_size && cachep->reallen > cache_line_size() && size < PAGE_SIZE) { + if (size >= malloc_sizes[INDEX_L3 + 1].cs_size + && cachep->reallen > cache_line_size() && size < PAGE_SIZE) { cachep->dbghead += PAGE_SIZE - size; size = PAGE_SIZE; } @@ -1664,7 +1730,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, #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). @@ -1681,47 +1747,9 @@ kmem_cache_create (const char *name, size_t size, size_t align, */ 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<<cachep->gfporder)) - break; /* Acceptable internal fragmentation. */ -next: - cachep->gfporder++; - } while (1); - } + &left_over, &cachep->num); + } else + left_over = calculate_slab_order(cachep, size, align, flags); if (!cachep->num) { printk("kmem_cache_create: couldn't create cache %s.\n", name); @@ -1729,8 +1757,8 @@ next: cachep = NULL; 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 @@ -1743,14 +1771,15 @@ 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; @@ -1777,7 +1806,7 @@ next: * the creation of further caches will BUG(). */ cachep->array[smp_processor_id()] = - &initarray_generic.cache; + &initarray_generic.cache; /* If the cache that's used by * kmalloc(sizeof(kmem_list3)) is the first cache, @@ -1791,8 +1820,7 @@ next: g_cpucache_up = PARTIAL_AC; } else { cachep->array[smp_processor_id()] = - kmalloc(sizeof(struct arraycache_init), - GFP_KERNEL); + kmalloc(sizeof(struct arraycache_init), GFP_KERNEL); if (g_cpucache_up == PARTIAL_AC) { set_up_list3s(cachep, SIZE_L3); @@ -1802,16 +1830,18 @@ next: for_each_online_node(node) { cachep->nodelists[node] = - kmalloc_node(sizeof(struct kmem_list3), - GFP_KERNEL, node); + kmalloc_node(sizeof + (struct kmem_list3), + GFP_KERNEL, node); BUG_ON(!cachep->nodelists[node]); - kmem_list3_init(cachep->nodelists[node]); + kmem_list3_init(cachep-> + nodelists[node]); } } } cachep->nodelists[numa_node_id()]->next_reap = - jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep)%REAPTIMEOUT_LIST3; + jiffies + REAPTIMEOUT_LIST3 + + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; BUG_ON(!ac_data(cachep)); ac_data(cachep)->avail = 0; @@ -1820,16 +1850,16 @@ next: ac_data(cachep)->touched = 0; cachep->batchcount = 1; cachep->limit = BOOT_CPUCACHE_ENTRIES; - } + } /* cache setup completed, link it into the list */ list_add(&cachep->next, &cache_chain); unlock_cpu_hotplug(); -oops: + oops: if (!cachep && (flags & SLAB_PANIC)) panic("kmem_cache_create(): failed to create slab `%s'\n", - name); - up(&cache_chain_sem); + name); + mutex_unlock(&cache_chain_mutex); return cachep; } EXPORT_SYMBOL(kmem_cache_create); @@ -1871,7 +1901,7 @@ static inline void check_spinlock_acquired_node(kmem_cache_t *cachep, int node) /* * 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(); @@ -1886,12 +1916,12 @@ 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, int node); +static void drain_array_locked(kmem_cache_t *cachep, struct array_cache *ac, + int force, int node); static void do_drain(void *arg) { - kmem_cache_t *cachep = (kmem_cache_t*)arg; + kmem_cache_t *cachep = (kmem_cache_t *) arg; struct array_cache *ac; int node = numa_node_id(); @@ -1911,7 +1941,7 @@ static void drain_cpu_caches(kmem_cache_t *cachep) smp_call_function_all_cpus(do_drain, cachep); check_irq_on(); spin_lock_irq(&cachep->spinlock); - for_each_online_node(node) { + for_each_online_node(node) { l3 = cachep->nodelists[node]; if (l3) { spin_lock(&l3->list_lock); @@ -1949,8 +1979,7 @@ static int __node_shrink(kmem_cache_t *cachep, int node) slab_destroy(cachep, slabp); spin_lock_irq(&l3->list_lock); } - ret = !list_empty(&l3->slabs_full) || - !list_empty(&l3->slabs_partial); + ret = !list_empty(&l3->slabs_full) || !list_empty(&l3->slabs_partial); return ret; } @@ -2006,7 +2035,7 @@ 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(kmem_cache_t *cachep) { int i; struct kmem_list3 *l3; @@ -2018,18 +2047,18 @@ 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; } @@ -2038,7 +2067,7 @@ int kmem_cache_destroy(kmem_cache_t * cachep) synchronize_rcu(); for_each_online_cpu(i) - kfree(cachep->array[i]); + kfree(cachep->array[i]); /* NUMA: free the list3 structures */ for_each_online_node(i) { @@ -2057,39 +2086,39 @@ int kmem_cache_destroy(kmem_cache_t * cachep) EXPORT_SYMBOL(kmem_cache_destroy); /* Get the memory for a slab management obj. */ -static struct slab* alloc_slabmgmt(kmem_cache_t *cachep, void *objp, - int colour_off, gfp_t local_flags) +static struct slab *alloc_slabmgmt(kmem_cache_t *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) + 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->objsize * i; #if DEBUG /* need to poison the objs? */ if (cachep->flags & SLAB_POISON) @@ -2107,25 +2136,28 @@ 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_dbghead(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->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep) + && cachep->flags & SLAB_POISON) + kernel_map_pages(virt_to_page(objp), + cachep->objsize / 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; } @@ -2161,17 +2193,17 @@ static void set_slab_attr(kmem_cache_t *cachep, struct slab *slabp, void *objp) */ static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid) { - struct slab *slabp; - void *objp; - size_t offset; - gfp_t 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; @@ -2237,9 +2269,9 @@ static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid) 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; @@ -2259,18 +2291,19 @@ static void kfree_debugcheck(const void *objp) 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(); } } static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp, - void *caller) + void *caller) { struct page *page; unsigned int objnr; @@ -2281,20 +2314,26 @@ static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp, page = virt_to_page(objp); 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 + "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", page_get_cache(page), page_get_cache(page)->name); + printk(KERN_ERR "%p is %s.\n", page_get_cache(page), + page_get_cache(page)->name); WARN_ON(1); } 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; @@ -2302,30 +2341,31 @@ static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp, if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = caller; - objnr = (objp-slabp->s_mem)/cachep->objsize; + objnr = (objp - slabp->s_mem) / cachep->objsize; BUG_ON(objnr >= cachep->num); - BUG_ON(objp != slabp->s_mem + objnr*cachep->objsize); + BUG_ON(objp != slabp->s_mem + objnr * cachep->objsize); 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_dbghead(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_dbghead(cachep), cachep, 0); } if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC if ((cachep->objsize % 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->objsize / PAGE_SIZE, 0); } else { poison_obj(cachep, objp, POISON_FREE); } @@ -2340,7 +2380,7 @@ static void check_slabp(kmem_cache_t *cachep, struct slab *slabp) { kmem_bufctl_t i; int entries = 0; - + /* Check slab's freelist to see if this obj is there. */ for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) { entries++; @@ -2348,13 +2388,16 @@ static void check_slabp(kmem_cache_t *cachep, struct slab *slabp) goto bad; } if (entries != cachep->num - slabp->inuse) { -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) + 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(); @@ -2374,7 +2417,7 @@ static void *cache_alloc_refill(kmem_cache_t *cachep, gfp_t flags) check_irq_off(); ac = ac_data(cachep); -retry: + retry: batchcount = ac->batchcount; if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { /* if there was little recent activity on this @@ -2396,8 +2439,8 @@ retry: shared_array->avail -= batchcount; ac->avail = batchcount; memcpy(ac->entry, - &(shared_array->entry[shared_array->avail]), - sizeof(void*)*batchcount); + &(shared_array->entry[shared_array->avail]), + sizeof(void *) * batchcount); shared_array->touched = 1; goto alloc_done; } @@ -2425,7 +2468,7 @@ retry: /* get obj pointer */ ac->entry[ac->avail++] = slabp->s_mem + - slabp->free*cachep->objsize; + slabp->free * cachep->objsize; slabp->inuse++; next = slab_bufctl(slabp)[slabp->free]; @@ -2433,7 +2476,7 @@ retry: slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; WARN_ON(numa_node_id() != slabp->nodeid); #endif - slabp->free = next; + slabp->free = next; } check_slabp(cachep, slabp); @@ -2445,9 +2488,9 @@ retry: list_add(&slabp->list, &l3->slabs_partial); } -must_grow: + must_grow: l3->free_objects -= ac->avail; -alloc_done: + alloc_done: spin_unlock(&l3->list_lock); if (unlikely(!ac->avail)) { @@ -2459,7 +2502,7 @@ alloc_done: 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; @@ -2476,16 +2519,16 @@ cache_alloc_debugcheck_before(kmem_cache_t *cachep, gfp_t flags) } #if DEBUG -static void * -cache_alloc_debugcheck_after(kmem_cache_t *cachep, - gfp_t flags, void *objp, void *caller) +static void *cache_alloc_debugcheck_after(kmem_cache_t *cachep, gfp_t flags, + void *objp, void *caller) { - if (!objp) + 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); + kernel_map_pages(virt_to_page(objp), + cachep->objsize / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else @@ -2497,24 +2540,28 @@ 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); 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); - } + } return objp; } #else @@ -2523,9 +2570,18 @@ cache_alloc_debugcheck_after(kmem_cache_t *cachep, static inline void *____cache_alloc(kmem_cache_t *cachep, gfp_t flags) { - void* objp; + void *objp; struct array_cache *ac; +#ifdef CONFIG_NUMA + if (unlikely(current->mempolicy && !in_interrupt())) { + int nid = slab_node(current->mempolicy); + + if (nid != numa_node_id()) + return __cache_alloc_node(cachep, flags, nid); + } +#endif + check_irq_off(); ac = ac_data(cachep); if (likely(ac->avail)) { @@ -2542,7 +2598,7 @@ static inline void *____cache_alloc(kmem_cache_t *cachep, gfp_t flags) static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags) { unsigned long save_flags; - void* objp; + void *objp; cache_alloc_debugcheck_before(cachep, flags); @@ -2550,7 +2606,7 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags) objp = ____cache_alloc(cachep, flags); local_irq_restore(save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, - __builtin_return_address(0)); + __builtin_return_address(0)); prefetchw(objp); return objp; } @@ -2562,74 +2618,75 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags) static void *__cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid) { struct list_head *entry; - struct slab *slabp; - struct kmem_list3 *l3; - void *obj; - kmem_bufctl_t next; - int x; - - l3 = cachep->nodelists[nodeid]; - BUG_ON(!l3); - -retry: - 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); - - /* get obj pointer */ - obj = slabp->s_mem + slabp->free*cachep->objsize; - slabp->inuse++; - next = slab_bufctl(slabp)[slabp->free]; + struct slab *slabp; + struct kmem_list3 *l3; + void *obj; + kmem_bufctl_t next; + int x; + + l3 = cachep->nodelists[nodeid]; + BUG_ON(!l3); + + retry: + 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); + + /* get obj pointer */ + obj = slabp->s_mem + slabp->free * cachep->objsize; + slabp->inuse++; + next = slab_bufctl(slabp)[slabp->free]; #if DEBUG - slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; + slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; #endif - slabp->free = next; - 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); - } + slabp->free = next; + 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; + spin_unlock(&l3->list_lock); + goto done; -must_grow: - spin_unlock(&l3->list_lock); - x = cache_grow(cachep, flags, nodeid); + must_grow: + spin_unlock(&l3->list_lock); + x = cache_grow(cachep, flags, nodeid); - if (!x) - return NULL; + if (!x) + return NULL; - goto retry; -done: - return obj; + goto retry; + done: + return obj; } #endif /* * Caller needs to acquire correct kmem_list's list_lock */ -static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects, int node) +static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects, + int node) { int i; struct kmem_list3 *l3; @@ -2652,7 +2709,7 @@ static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects, int n if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) { printk(KERN_ERR "slab: double free detected in cache " - "'%s', objp %p\n", cachep->name, objp); + "'%s', objp %p\n", cachep->name, objp); BUG(); } #endif @@ -2696,20 +2753,19 @@ static void cache_flusharray(kmem_cache_t *cachep, struct array_cache *ac) spin_lock(&l3->list_lock); if (l3->shared) { struct array_cache *shared_array = l3->shared; - int max = shared_array->limit-shared_array->avail; + int max = shared_array->limit - shared_array->avail; if (max) { if (batchcount > max) batchcount = max; memcpy(&(shared_array->entry[shared_array->avail]), - ac->entry, - sizeof(void*)*batchcount); + ac->entry, sizeof(void *) * batchcount); shared_array->avail += batchcount; goto free_done; } } free_block(cachep, ac->entry, batchcount, node); -free_done: + free_done: #if STATS { int i = 0; @@ -2731,10 +2787,9 @@ free_done: spin_unlock(&l3->list_lock); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), - sizeof(void*)*ac->avail); + sizeof(void *) * ac->avail); } - /* * __cache_free * Release an obj back to its cache. If the obj has a constructed @@ -2759,7 +2814,8 @@ static inline void __cache_free(kmem_cache_t *cachep, void *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()]; + struct kmem_list3 *l3 = + cachep->nodelists[numa_node_id()]; STATS_INC_NODEFREES(cachep); if (l3->alien && l3->alien[nodeid]) { @@ -2767,15 +2823,15 @@ static inline void __cache_free(kmem_cache_t *cachep, void *objp) spin_lock(&alien->lock); if (unlikely(alien->avail == alien->limit)) __drain_alien_cache(cachep, - alien, nodeid); + alien, nodeid); alien->entry[alien->avail++] = objp; spin_unlock(&alien->lock); } else { spin_lock(&(cachep->nodelists[nodeid])-> - list_lock); + list_lock); free_block(cachep, &objp, 1, nodeid); spin_unlock(&(cachep->nodelists[nodeid])-> - list_lock); + list_lock); } return; } @@ -2822,9 +2878,9 @@ EXPORT_SYMBOL(kmem_cache_alloc); */ int fastcall kmem_ptr_validate(kmem_cache_t *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 align_mask = BYTES_PER_WORD - 1; unsigned long size = cachep->objsize; struct page *page; @@ -2844,7 +2900,7 @@ int fastcall kmem_ptr_validate(kmem_cache_t *cachep, void *ptr) if (unlikely(page_get_cache(page) != cachep)) goto out; return 1; -out: + out: return 0; } @@ -2871,8 +2927,10 @@ void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid) if (unlikely(!cachep->nodelists[nodeid])) { /* Fall back to __cache_alloc if we run into trouble */ - printk(KERN_WARNING "slab: not allocating in inactive node %d for cache %s\n", nodeid, cachep->name); - return __cache_alloc(cachep,flags); + printk(KERN_WARNING + "slab: not allocating in inactive node %d for cache %s\n", + nodeid, cachep->name); + return __cache_alloc(cachep, flags); } cache_alloc_debugcheck_before(cachep, flags); @@ -2882,7 +2940,9 @@ void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid) 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)); + ptr = + cache_alloc_debugcheck_after(cachep, flags, ptr, + __builtin_return_address(0)); return ptr; } @@ -2944,12 +3004,11 @@ EXPORT_SYMBOL(__kmalloc); * 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; @@ -2973,9 +3032,9 @@ void *__alloc_percpu(size_t size, size_t align) } /* 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; @@ -3006,20 +3065,6 @@ void kmem_cache_free(kmem_cache_t *cachep, void *objp) EXPORT_SYMBOL(kmem_cache_free); /** - * kzalloc - allocate memory. The memory is set to zero. - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate. - */ -void *kzalloc(size_t size, gfp_t flags) -{ - void *ret = kmalloc(size, flags); - if (ret) - memset(ret, 0, size); - return ret; -} -EXPORT_SYMBOL(kzalloc); - -/** * kfree - free previously allocated memory * @objp: pointer returned by kmalloc. * @@ -3038,7 +3083,8 @@ void kfree(const void *objp) local_irq_save(flags); kfree_debugcheck(objp); c = page_get_cache(virt_to_page(objp)); - __cache_free(c, (void*)objp); + mutex_debug_check_no_locks_freed(objp, obj_reallen(c)); + __cache_free(c, (void *)objp); local_irq_restore(flags); } EXPORT_SYMBOL(kfree); @@ -3051,17 +3097,16 @@ 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); /* * We allocate for all cpus so we cannot use for online cpu here. */ for_each_cpu(i) - kfree(p->ptrs[i]); + kfree(p->ptrs[i]); kfree(p); } EXPORT_SYMBOL(free_percpu); @@ -3095,44 +3140,44 @@ static int alloc_kmemlist(kmem_cache_t *cachep) if (!(new_alien = alloc_alien_cache(node, cachep->limit))) goto fail; #endif - if (!(new = alloc_arraycache(node, (cachep->shared* - cachep->batchcount), 0xbaadf00d))) + 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); + 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; + 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; } if (!(l3 = kmalloc_node(sizeof(struct kmem_list3), - GFP_KERNEL, node))) + GFP_KERNEL, node))) goto fail; kmem_list3_init(l3); l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + - ((unsigned long)cachep)%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; + l3->free_limit = (1 + nr_cpus_node(node)) * + cachep->batchcount + cachep->num; cachep->nodelists[node] = l3; } return err; -fail: + fail: err = -ENOMEM; return err; } @@ -3154,18 +3199,19 @@ static void do_ccupdate_local(void *info) new->new[smp_processor_id()] = old; } - static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount, - int shared) + int shared) { struct ccupdate_struct new; int i, err; - memset(&new.new,0,sizeof(new.new)); + memset(&new.new, 0, sizeof(new.new)); for_each_online_cpu(i) { - new.new[i] = alloc_arraycache(cpu_to_node(i), limit, batchcount); + new.new[i] = + alloc_arraycache(cpu_to_node(i), limit, batchcount); if (!new.new[i]) { - for (i--; i >= 0; i--) kfree(new.new[i]); + for (i--; i >= 0; i--) + kfree(new.new[i]); return -ENOMEM; } } @@ -3193,13 +3239,12 @@ static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount, err = alloc_kmemlist(cachep); if (err) { printk(KERN_ERR "alloc_kmemlist failed for %s, error %d.\n", - cachep->name, -err); + cachep->name, -err); BUG(); } return 0; } - static void enable_cpucache(kmem_cache_t *cachep) { int err; @@ -3246,14 +3291,14 @@ 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); + cachep->name, -err); } -static void drain_array_locked(kmem_cache_t *cachep, - struct array_cache *ac, int force, int node) +static void drain_array_locked(kmem_cache_t *cachep, struct array_cache *ac, + int force, int node) { int tofree; @@ -3261,14 +3306,14 @@ static void drain_array_locked(kmem_cache_t *cachep, 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, tofree, node); ac->avail -= tofree; memmove(ac->entry, &(ac->entry[tofree]), - sizeof(void*)*ac->avail); + sizeof(void *) * ac->avail); } } @@ -3281,7 +3326,7 @@ static void drain_array_locked(kmem_cache_t *cachep, * - 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 + * If we cannot acquire the cache chain mutex then just give up - we'll * try again on the next iteration. */ static void cache_reap(void *unused) @@ -3289,15 +3334,16 @@ static void cache_reap(void *unused) struct list_head *walk; struct kmem_list3 *l3; - 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); + 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 list_head *p; int tofree; struct slab *slabp; @@ -3314,7 +3360,7 @@ static void cache_reap(void *unused) spin_lock_irq(&l3->list_lock); drain_array_locked(searchp, ac_data(searchp), 0, - numa_node_id()); + numa_node_id()); if (time_after(l3->next_reap, jiffies)) goto next_unlock; @@ -3323,14 +3369,16 @@ static void cache_reap(void *unused) if (l3->shared) drain_array_locked(searchp, l3->shared, 0, - numa_node_id()); + numa_node_id()); if (l3->free_touched) { l3->free_touched = 0; goto next_unlock; } - tofree = (l3->free_limit+5*searchp->num-1)/(5*searchp->num); + tofree = + (l3->free_limit + 5 * searchp->num - + 1) / (5 * searchp->num); do { p = l3->slabs_free.next; if (p == &(l3->slabs_free)) @@ -3350,14 +3398,14 @@ static void cache_reap(void *unused) spin_unlock_irq(&l3->list_lock); slab_destroy(searchp, slabp); spin_lock_irq(&l3->list_lock); - } while(--tofree > 0); -next_unlock: + } while (--tofree > 0); + next_unlock: spin_unlock_irq(&l3->list_lock); -next: + next: cond_resched(); } check_irq_on(); - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); drain_remote_pages(); /* Setup the next iteration */ schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC); @@ -3365,32 +3413,37 @@ next: #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: 2.1 (statistics)\n"); + seq_puts(m, "slabinfo - version: 2.1 (statistics)\n"); #else - seq_puts(m, "slabinfo - version: 2.1\n"); + seq_puts(m, "slabinfo - version: 2.1\n"); #endif - seq_puts(m, "# name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>"); - seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>"); - seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>"); + seq_puts(m, "# name <active_objs> <num_objs> <objsize> " + "<objperslab> <pagesperslab>"); + seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>"); + seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>"); #if STATS - seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped>" - " <error> <maxfreeable> <nodeallocs> <remotefrees>"); - seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>"); + seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> " + "<error> <maxfreeable> <nodeallocs> <remotefrees>"); + seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>"); #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; @@ -3405,23 +3458,23 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos) kmem_cache_t *cachep = p; ++*pos; return cachep->next.next == &cache_chain ? NULL - : list_entry(cachep->next.next, kmem_cache_t, next); + : list_entry(cachep->next.next, kmem_cache_t, 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 list_head *q; - 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; + 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; int node; @@ -3438,14 +3491,14 @@ static int s_show(struct seq_file *m, void *p) spin_lock(&l3->list_lock); - list_for_each(q,&l3->slabs_full) { + 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) { + 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"; @@ -3454,7 +3507,7 @@ static int s_show(struct seq_file *m, void *p) active_objs += slabp->inuse; active_slabs++; } - list_for_each(q,&l3->slabs_free) { + list_for_each(q, &l3->slabs_free) { slabp = list_entry(q, struct slab, list); if (slabp->inuse && !error) error = "slabs_free/inuse accounting error"; @@ -3465,25 +3518,24 @@ static int s_show(struct seq_file *m, void *p) spin_unlock(&l3->list_lock); } - num_slabs+=active_slabs; - num_objs = num_slabs*cachep->num; + 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; + 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<<cachep->gfporder)); + name, active_objs, num_objs, cachep->objsize, + cachep->num, (1 << cachep->gfporder)); seq_printf(m, " : tunables %4u %4u %4u", - cachep->limit, cachep->batchcount, - cachep->shared); + cachep->limit, cachep->batchcount, cachep->shared); seq_printf(m, " : slabdata %6lu %6lu %6lu", - active_slabs, num_slabs, shared_avail); + 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; @@ -3494,9 +3546,7 @@ static int s_show(struct seq_file *m, void *p) unsigned long node_frees = cachep->node_frees; seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \ - %4lu %4lu %4lu %4lu", - allocs, high, grown, reaped, errors, - max_freeable, node_allocs, node_frees); + %4lu %4lu %4lu %4lu", allocs, high, grown, reaped, errors, max_freeable, node_allocs, node_frees); } /* cpu stats */ { @@ -3506,7 +3556,7 @@ 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'); @@ -3529,10 +3579,10 @@ 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 @@ -3543,18 +3593,18 @@ 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) @@ -3565,25 +3615,24 @@ 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) { + list_for_each(p, &cache_chain) { kmem_cache_t *cachep = list_entry(p, kmem_cache_t, next); if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || - batchcount > limit || - shared < 0) { + batchcount > limit || shared < 0) { res = 0; } else { res = do_tune_cpucache(cachep, limit, - batchcount, shared); + batchcount, shared); } break; } } - up(&cache_chain_sem); + mutex_unlock(&cache_chain_mutex); if (res >= 0) res = count; return res; @@ -3609,26 +3658,3 @@ unsigned int ksize(const void *objp) return obj_reallen(page_get_cache(virt_to_page(objp))); } - - -/* - * kstrdup - allocate space for and copy an existing string - * - * @s: the string to duplicate - * @gfp: the GFP mask used in the kmalloc() call when allocating memory - */ -char *kstrdup(const char *s, gfp_t gfp) -{ - size_t len; - char *buf; - - if (!s) - return NULL; - - len = strlen(s) + 1; - buf = kmalloc(len, gfp); - if (buf) - memcpy(buf, s, len); - return buf; -} -EXPORT_SYMBOL(kstrdup); |