From b8c24c4aef94b1f0daafb450363fef13a1163780 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 13 Jun 2012 10:24:52 -0500 Subject: slob: Define page struct fields used in mm_types.h Define the fields used by slob in mm_types.h and use struct page instead of struct slob_page in slob. This cleans up numerous of typecasts in slob.c and makes readers aware of slob's use of page struct fields. [Also cleans up some bitrot in slob.c. The page struct field layout in slob.c is an old layout and does not match the one in mm_types.h] Reviewed-by: Glauber Costa Acked-by: David Rientjes Reviewed-by: Joonsoo Kim Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slob.c | 95 +++++++++++++++++++++++++-------------------------------------- 1 file changed, 37 insertions(+), 58 deletions(-) (limited to 'mm/slob.c') diff --git a/mm/slob.c b/mm/slob.c index 8105be42cad..30862a2d56a 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -91,34 +91,13 @@ struct slob_block { }; typedef struct slob_block slob_t; -/* - * We use struct page fields to manage some slob allocation aspects, - * however to avoid the horrible mess in include/linux/mm_types.h, we'll - * just define our own struct page type variant here. - */ -struct slob_page { - union { - struct { - unsigned long flags; /* mandatory */ - atomic_t _count; /* mandatory */ - slobidx_t units; /* free units left in page */ - unsigned long pad[2]; - slob_t *free; /* first free slob_t in page */ - struct list_head list; /* linked list of free pages */ - }; - struct page page; - }; -}; -static inline void struct_slob_page_wrong_size(void) -{ BUILD_BUG_ON(sizeof(struct slob_page) != sizeof(struct page)); } - /* * free_slob_page: call before a slob_page is returned to the page allocator. */ -static inline void free_slob_page(struct slob_page *sp) +static inline void free_slob_page(struct page *sp) { - reset_page_mapcount(&sp->page); - sp->page.mapping = NULL; + reset_page_mapcount(sp); + sp->mapping = NULL; } /* @@ -133,44 +112,44 @@ static LIST_HEAD(free_slob_large); /* * is_slob_page: True for all slob pages (false for bigblock pages) */ -static inline int is_slob_page(struct slob_page *sp) +static inline int is_slob_page(struct page *sp) { - return PageSlab((struct page *)sp); + return PageSlab(sp); } -static inline void set_slob_page(struct slob_page *sp) +static inline void set_slob_page(struct page *sp) { - __SetPageSlab((struct page *)sp); + __SetPageSlab(sp); } -static inline void clear_slob_page(struct slob_page *sp) +static inline void clear_slob_page(struct page *sp) { - __ClearPageSlab((struct page *)sp); + __ClearPageSlab(sp); } -static inline struct slob_page *slob_page(const void *addr) +static inline struct page *slob_page(const void *addr) { - return (struct slob_page *)virt_to_page(addr); + return virt_to_page(addr); } /* * slob_page_free: true for pages on free_slob_pages list. */ -static inline int slob_page_free(struct slob_page *sp) +static inline int slob_page_free(struct page *sp) { - return PageSlobFree((struct page *)sp); + return PageSlobFree(sp); } -static void set_slob_page_free(struct slob_page *sp, struct list_head *list) +static void set_slob_page_free(struct page *sp, struct list_head *list) { list_add(&sp->list, list); - __SetPageSlobFree((struct page *)sp); + __SetPageSlobFree(sp); } -static inline void clear_slob_page_free(struct slob_page *sp) +static inline void clear_slob_page_free(struct page *sp) { list_del(&sp->list); - __ClearPageSlobFree((struct page *)sp); + __ClearPageSlobFree(sp); } #define SLOB_UNIT sizeof(slob_t) @@ -267,12 +246,12 @@ static void slob_free_pages(void *b, int order) /* * Allocate a slob block within a given slob_page sp. */ -static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) +static void *slob_page_alloc(struct page *sp, size_t size, int align) { slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); - for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) { + for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { slobidx_t avail = slob_units(cur); if (align) { @@ -296,12 +275,12 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) if (prev) set_slob(prev, slob_units(prev), next); else - sp->free = next; + sp->freelist = next; } else { /* fragment */ if (prev) set_slob(prev, slob_units(prev), cur + units); else - sp->free = cur + units; + sp->freelist = cur + units; set_slob(cur + units, avail - units, next); } @@ -320,7 +299,7 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) */ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) { - struct slob_page *sp; + struct page *sp; struct list_head *prev; struct list_head *slob_list; slob_t *b = NULL; @@ -341,7 +320,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) * If there's a node specification, search for a partial * page with a matching node id in the freelist. */ - if (node != -1 && page_to_nid(&sp->page) != node) + if (node != -1 && page_to_nid(sp) != node) continue; #endif /* Enough room on this page? */ @@ -374,7 +353,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) spin_lock_irqsave(&slob_lock, flags); sp->units = SLOB_UNITS(PAGE_SIZE); - sp->free = b; + sp->freelist = b; INIT_LIST_HEAD(&sp->list); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); @@ -392,7 +371,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) */ static void slob_free(void *block, int size) { - struct slob_page *sp; + struct page *sp; slob_t *prev, *next, *b = (slob_t *)block; slobidx_t units; unsigned long flags; @@ -421,7 +400,7 @@ static void slob_free(void *block, int size) if (!slob_page_free(sp)) { /* This slob page is about to become partially free. Easy! */ sp->units = units; - sp->free = b; + sp->freelist = b; set_slob(b, units, (void *)((unsigned long)(b + SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK)); @@ -441,15 +420,15 @@ static void slob_free(void *block, int size) */ sp->units += units; - if (b < sp->free) { - if (b + units == sp->free) { - units += slob_units(sp->free); - sp->free = slob_next(sp->free); + if (b < (slob_t *)sp->freelist) { + if (b + units == sp->freelist) { + units += slob_units(sp->freelist); + sp->freelist = slob_next(sp->freelist); } - set_slob(b, units, sp->free); - sp->free = b; + set_slob(b, units, sp->freelist); + sp->freelist = b; } else { - prev = sp->free; + prev = sp->freelist; next = slob_next(prev); while (b > next) { prev = next; @@ -522,7 +501,7 @@ EXPORT_SYMBOL(__kmalloc_node); void kfree(const void *block) { - struct slob_page *sp; + struct page *sp; trace_kfree(_RET_IP_, block); @@ -536,14 +515,14 @@ void kfree(const void *block) unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); } else - put_page(&sp->page); + put_page(sp); } EXPORT_SYMBOL(kfree); /* can't use ksize for kmem_cache_alloc memory, only kmalloc */ size_t ksize(const void *block) { - struct slob_page *sp; + struct page *sp; BUG_ON(!block); if (unlikely(block == ZERO_SIZE_PTR)) @@ -555,7 +534,7 @@ size_t ksize(const void *block) unsigned int *m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } else - return sp->page.private; + return sp->private; } EXPORT_SYMBOL(ksize); -- cgit v1.2.3-70-g09d2 From 690d5777392180fdc05a82c0c7979e50e8d93de8 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 13 Jun 2012 10:24:53 -0500 Subject: slob: No need to zero mapping since it is no longer in use Reviewed-by: Joonsoo Kim Acked-by: David Rientjes Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slob.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm/slob.c') diff --git a/mm/slob.c b/mm/slob.c index 30862a2d56a..74c3bb25f64 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -97,7 +97,6 @@ typedef struct slob_block slob_t; static inline void free_slob_page(struct page *sp) { reset_page_mapcount(sp); - sp->mapping = NULL; } /* -- cgit v1.2.3-70-g09d2 From b5568280c9b9162b384be9d447013b74d682d4b3 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 13 Jun 2012 10:24:54 -0500 Subject: slob: Remove various small accessors Those have become so simple that they are no longer needed. Reviewed-by: Joonsoo Kim Acked-by: David Rientjes signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slob.c | 49 +++++++++---------------------------------------- 1 file changed, 9 insertions(+), 40 deletions(-) (limited to 'mm/slob.c') diff --git a/mm/slob.c b/mm/slob.c index 74c3bb25f64..c85265d22e0 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -91,14 +91,6 @@ struct slob_block { }; typedef struct slob_block slob_t; -/* - * free_slob_page: call before a slob_page is returned to the page allocator. - */ -static inline void free_slob_page(struct page *sp) -{ - reset_page_mapcount(sp); -} - /* * All partially free slob pages go on these lists. */ @@ -108,29 +100,6 @@ static LIST_HEAD(free_slob_small); static LIST_HEAD(free_slob_medium); static LIST_HEAD(free_slob_large); -/* - * is_slob_page: True for all slob pages (false for bigblock pages) - */ -static inline int is_slob_page(struct page *sp) -{ - return PageSlab(sp); -} - -static inline void set_slob_page(struct page *sp) -{ - __SetPageSlab(sp); -} - -static inline void clear_slob_page(struct page *sp) -{ - __ClearPageSlab(sp); -} - -static inline struct page *slob_page(const void *addr) -{ - return virt_to_page(addr); -} - /* * slob_page_free: true for pages on free_slob_pages list. */ @@ -347,8 +316,8 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node); if (!b) return NULL; - sp = slob_page(b); - set_slob_page(sp); + sp = virt_to_page(b); + __SetPageSlab(sp); spin_lock_irqsave(&slob_lock, flags); sp->units = SLOB_UNITS(PAGE_SIZE); @@ -380,7 +349,7 @@ static void slob_free(void *block, int size) return; BUG_ON(!size); - sp = slob_page(block); + sp = virt_to_page(block); units = SLOB_UNITS(size); spin_lock_irqsave(&slob_lock, flags); @@ -390,8 +359,8 @@ static void slob_free(void *block, int size) if (slob_page_free(sp)) clear_slob_page_free(sp); spin_unlock_irqrestore(&slob_lock, flags); - clear_slob_page(sp); - free_slob_page(sp); + __ClearPageSlab(sp); + reset_page_mapcount(sp); slob_free_pages(b, 0); return; } @@ -508,8 +477,8 @@ void kfree(const void *block) return; kmemleak_free(block); - sp = slob_page(block); - if (is_slob_page(sp)) { + sp = virt_to_page(block); + if (PageSlab(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); @@ -527,8 +496,8 @@ size_t ksize(const void *block) if (unlikely(block == ZERO_SIZE_PTR)) return 0; - sp = slob_page(block); - if (is_slob_page(sp)) { + sp = virt_to_page(block); + if (PageSlab(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; -- cgit v1.2.3-70-g09d2 From 3b0efdfa1e719303536c04d9abca43abeb40f80a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 13 Jun 2012 10:24:57 -0500 Subject: mm, sl[aou]b: Extract common fields from struct kmem_cache Define a struct that describes common fields used in all slab allocators. A slab allocator either uses the common definition (like SLOB) or is required to provide members of kmem_cache with the definition given. After that it will be possible to share code that only operates on those fields of kmem_cache. The patch basically takes the slob definition of kmem cache and uses the field namees for the other allocators. It also standardizes the names used for basic object lengths in allocators: object_size Struct size specified at kmem_cache_create. Basically the payload expected to be used by the subsystem. size The size of memory allocator for each object. This size is larger than object_size and includes padding, alignment and extra metadata for each object (f.e. for debugging and rcu). Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 24 ++++++++++ include/linux/slab_def.h | 10 ++-- include/linux/slub_def.h | 2 +- mm/slab.c | 117 +++++++++++++++++++++++------------------------ mm/slob.c | 9 +--- mm/slub.c | 80 ++++++++++++++++---------------- 6 files changed, 130 insertions(+), 112 deletions(-) (limited to 'mm/slob.c') diff --git a/include/linux/slab.h b/include/linux/slab.h index 67d5d94b783..0dd2dfa7bec 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -92,6 +92,30 @@ #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) +/* + * Common fields provided in kmem_cache by all slab allocators + * This struct is either used directly by the allocator (SLOB) + * or the allocator must include definitions for all fields + * provided in kmem_cache_common in their definition of kmem_cache. + * + * Once we can do anonymous structs (C11 standard) we could put a + * anonymous struct definition in these allocators so that the + * separate allocations in the kmem_cache structure of SLAB and + * SLUB is no longer needed. + */ +#ifdef CONFIG_SLOB +struct kmem_cache { + unsigned int object_size;/* The original size of the object */ + unsigned int size; /* The aligned/padded/added on size */ + unsigned int align; /* Alignment as calculated */ + unsigned long flags; /* Active flags on the slab */ + const char *name; /* Slab name for sysfs */ + int refcount; /* Use counter */ + void (*ctor)(void *); /* Called on object slot creation */ + struct list_head list; /* List of all slab caches on the system */ +}; +#endif + /* * struct kmem_cache related prototypes */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index fbd1117fdfd..1d93f27d81d 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -27,7 +27,7 @@ struct kmem_cache { unsigned int limit; unsigned int shared; - unsigned int buffer_size; + unsigned int size; u32 reciprocal_buffer_size; /* 2) touched by every alloc & free from the backend */ @@ -52,7 +52,10 @@ struct kmem_cache { /* 4) cache creation/removal */ const char *name; - struct list_head next; + struct list_head list; + int refcount; + int object_size; + int align; /* 5) statistics */ #ifdef CONFIG_DEBUG_SLAB @@ -73,12 +76,11 @@ struct kmem_cache { /* * If debugging is enabled, then the allocator can add additional - * fields and/or padding to every object. buffer_size contains the total + * fields and/or padding to every object. 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 /* CONFIG_DEBUG_SLAB */ /* 6) per-cpu/per-node data, touched during every alloc/free */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index ebdcf4ba42e..df448adb728 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -82,7 +82,7 @@ struct kmem_cache { unsigned long flags; unsigned long min_partial; int size; /* The size of an object including meta data */ - int objsize; /* The size of an object without meta data */ + int object_size; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ int cpu_partial; /* Number of per cpu partial objects to keep around */ struct kmem_cache_order_objects oo; diff --git a/mm/slab.c b/mm/slab.c index 28a8f7d29d4..e2b3907b7b0 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -424,8 +424,8 @@ static void kmem_list3_init(struct kmem_list3 *parent) * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1: * redzone word. * 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 + * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] + * cachep->size - 1* BYTES_PER_WORD: last caller address * [BYTES_PER_WORD long] */ static int obj_offset(struct kmem_cache *cachep) @@ -435,7 +435,7 @@ static int obj_offset(struct kmem_cache *cachep) static int obj_size(struct kmem_cache *cachep) { - return cachep->obj_size; + return cachep->object_size; } static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp) @@ -449,23 +449,23 @@ static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); if (cachep->flags & SLAB_STORE_USER) - return (unsigned long long *)(objp + cachep->buffer_size - + return (unsigned long long *)(objp + cachep->size - sizeof(unsigned long long) - REDZONE_ALIGN); - return (unsigned long long *) (objp + cachep->buffer_size - + return (unsigned long long *) (objp + cachep->size - sizeof(unsigned long long)); } static void **dbg_userword(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_STORE_USER)); - return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD); + return (void **)(objp + cachep->size - BYTES_PER_WORD); } #else #define obj_offset(x) 0 -#define obj_size(cachep) (cachep->buffer_size) +#define obj_size(cachep) (cachep->size) #define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) #define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) #define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;}) @@ -475,7 +475,7 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #ifdef CONFIG_TRACING size_t slab_buffer_size(struct kmem_cache *cachep) { - return cachep->buffer_size; + return cachep->size; } EXPORT_SYMBOL(slab_buffer_size); #endif @@ -513,13 +513,13 @@ static inline struct slab *virt_to_slab(const void *obj) static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, unsigned int idx) { - return slab->s_mem + cache->buffer_size * idx; + return slab->s_mem + cache->size * idx; } /* - * We want to avoid an expensive divide : (offset / cache->buffer_size) - * Using the fact that buffer_size is a constant for a particular cache, - * we can replace (offset / cache->buffer_size) by + * We want to avoid an expensive divide : (offset / cache->size) + * Using the fact that size is a constant for a particular cache, + * we can replace (offset / cache->size) by * reciprocal_divide(offset, cache->reciprocal_buffer_size) */ static inline unsigned int obj_to_index(const struct kmem_cache *cache, @@ -565,7 +565,7 @@ static struct kmem_cache cache_cache = { .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, - .buffer_size = sizeof(struct kmem_cache), + .size = sizeof(struct kmem_cache), .name = "kmem_cache", }; @@ -1134,7 +1134,7 @@ static int init_cache_nodelists_node(int node) struct kmem_list3 *l3; const int memsize = sizeof(struct kmem_list3); - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &cache_chain, list) { /* * Set up the size64 kmemlist for cpu before we can * begin anything. Make sure some other cpu on this @@ -1172,7 +1172,7 @@ static void __cpuinit cpuup_canceled(long cpu) int node = cpu_to_mem(cpu); const struct cpumask *mask = cpumask_of_node(node); - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &cache_chain, list) { struct array_cache *nc; struct array_cache *shared; struct array_cache **alien; @@ -1222,7 +1222,7 @@ free_array_cache: * 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) { + list_for_each_entry(cachep, &cache_chain, list) { l3 = cachep->nodelists[node]; if (!l3) continue; @@ -1251,7 +1251,7 @@ static int __cpuinit cpuup_prepare(long cpu) * Now we can go ahead with allocating the shared arrays and * array caches */ - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &cache_chain, list) { struct array_cache *nc; struct array_cache *shared = NULL; struct array_cache **alien = NULL; @@ -1383,7 +1383,7 @@ static int __meminit drain_cache_nodelists_node(int node) struct kmem_cache *cachep; int ret = 0; - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &cache_chain, list) { struct kmem_list3 *l3; l3 = cachep->nodelists[node]; @@ -1526,7 +1526,7 @@ void __init kmem_cache_init(void) /* 1) create the cache_cache */ INIT_LIST_HEAD(&cache_chain); - list_add(&cache_cache.next, &cache_chain); + list_add(&cache_cache.list, &cache_chain); cache_cache.colour_off = cache_line_size(); cache_cache.array[smp_processor_id()] = &initarray_cache.cache; cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; @@ -1534,18 +1534,16 @@ void __init kmem_cache_init(void) /* * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + cache_cache.size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + nr_node_ids * sizeof(struct kmem_list3 *); -#if DEBUG - cache_cache.obj_size = cache_cache.buffer_size; -#endif - cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, + cache_cache.object_size = cache_cache.size; + cache_cache.size = ALIGN(cache_cache.size, cache_line_size()); cache_cache.reciprocal_buffer_size = - reciprocal_value(cache_cache.buffer_size); + reciprocal_value(cache_cache.size); for (order = 0; order < MAX_ORDER; order++) { - cache_estimate(order, cache_cache.buffer_size, + cache_estimate(order, cache_cache.size, cache_line_size(), 0, &left_over, &cache_cache.num); if (cache_cache.num) break; @@ -1671,7 +1669,7 @@ void __init kmem_cache_init_late(void) /* 6) resize the head arrays to their final sizes */ mutex_lock(&cache_chain_mutex); - list_for_each_entry(cachep, &cache_chain, next) + list_for_each_entry(cachep, &cache_chain, list) if (enable_cpucache(cachep, GFP_NOWAIT)) BUG(); mutex_unlock(&cache_chain_mutex); @@ -1724,7 +1722,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", nodeid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n", - cachep->name, cachep->buffer_size, cachep->gfporder); + cachep->name, cachep->size, cachep->gfporder); for_each_online_node(node) { unsigned long active_objs = 0, num_objs = 0, free_objects = 0; @@ -2028,10 +2026,10 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if (cachep->buffer_size % PAGE_SIZE == 0 && + if (cachep->size % PAGE_SIZE == 0 && OFF_SLAB(cachep)) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 1); + cachep->size / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else @@ -2281,7 +2279,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, mutex_lock(&cache_chain_mutex); } - list_for_each_entry(pc, &cache_chain, next) { + list_for_each_entry(pc, &cache_chain, list) { char tmp; int res; @@ -2294,7 +2292,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (res) { printk(KERN_ERR "SLAB: cache with size %d has lost its name\n", - pc->buffer_size); + pc->size); continue; } @@ -2399,8 +2397,9 @@ kmem_cache_create (const char *name, size_t size, size_t align, goto oops; cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; + cachep->object_size = size; + cachep->align = align; #if DEBUG - cachep->obj_size = size; /* * Both debugging options require word-alignment which is calculated @@ -2423,7 +2422,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) if (size >= malloc_sizes[INDEX_L3 + 1].cs_size - && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { + && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { cachep->obj_offset += PAGE_SIZE - ALIGN(size, align); size = PAGE_SIZE; } @@ -2492,7 +2491,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, cachep->gfpflags = 0; if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) cachep->gfpflags |= GFP_DMA; - cachep->buffer_size = size; + cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); if (flags & CFLGS_OFF_SLAB) { @@ -2526,7 +2525,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, } /* cache setup completed, link it into the list */ - list_add(&cachep->next, &cache_chain); + list_add(&cachep->list, &cache_chain); oops: if (!cachep && (flags & SLAB_PANIC)) panic("kmem_cache_create(): failed to create slab `%s'\n", @@ -2721,10 +2720,10 @@ void kmem_cache_destroy(struct kmem_cache *cachep) /* * the chain is never empty, cache_cache is never destroyed */ - list_del(&cachep->next); + list_del(&cachep->list); if (__cache_shrink(cachep)) { slab_error(cachep, "Can't free all objects"); - list_add(&cachep->next, &cache_chain); + list_add(&cachep->list, &cache_chain); mutex_unlock(&cache_chain_mutex); put_online_cpus(); return; @@ -2821,10 +2820,10 @@ static void cache_init_objs(struct kmem_cache *cachep, slab_error(cachep, "constructor overwrote the" " start of an object"); } - if ((cachep->buffer_size % PAGE_SIZE) == 0 && + if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep) && cachep->flags & SLAB_POISON) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 0); + cachep->size / PAGE_SIZE, 0); #else if (cachep->ctor) cachep->ctor(objp); @@ -3058,10 +3057,10 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, #endif if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { + if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { store_stackinfo(cachep, objp, (unsigned long)caller); kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 0); + cachep->size / PAGE_SIZE, 0); } else { poison_obj(cachep, objp, POISON_FREE); } @@ -3211,9 +3210,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, return objp; if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) + if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 1); + cachep->size / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else @@ -3243,7 +3242,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, unsigned objnr; slabp = virt_to_head_page(objp)->slab_page; - objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size; + objnr = (unsigned)(objp - slabp->s_mem) / cachep->size; slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE; } #endif @@ -3747,7 +3746,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); trace_kmem_cache_alloc(_RET_IP_, ret, - obj_size(cachep), cachep->buffer_size, flags); + obj_size(cachep), cachep->size, flags); return ret; } @@ -3775,7 +3774,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) __builtin_return_address(0)); trace_kmem_cache_alloc_node(_RET_IP_, ret, - obj_size(cachep), cachep->buffer_size, + obj_size(cachep), cachep->size, flags, nodeid); return ret; @@ -3857,7 +3856,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, ret = __cache_alloc(cachep, flags, caller); trace_kmalloc((unsigned long) caller, ret, - size, cachep->buffer_size, flags); + size, cachep->size, flags); return ret; } @@ -4011,7 +4010,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) return 0; fail: - if (!cachep->next.next) { + if (!cachep->list.next) { /* Cache is not active yet. Roll back what we did */ node--; while (node >= 0) { @@ -4105,13 +4104,13 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) * The numbers are guessed, we should auto-tune as described by * Bonwick. */ - if (cachep->buffer_size > 131072) + if (cachep->size > 131072) limit = 1; - else if (cachep->buffer_size > PAGE_SIZE) + else if (cachep->size > PAGE_SIZE) limit = 8; - else if (cachep->buffer_size > 1024) + else if (cachep->size > 1024) limit = 24; - else if (cachep->buffer_size > 256) + else if (cachep->size > 256) limit = 54; else limit = 120; @@ -4126,7 +4125,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) * to a larger limit. Thus disabled by default. */ shared = 0; - if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1) + if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1) shared = 8; #if DEBUG @@ -4196,7 +4195,7 @@ static void cache_reap(struct work_struct *w) /* Give up. Setup the next iteration. */ goto out; - list_for_each_entry(searchp, &cache_chain, next) { + list_for_each_entry(searchp, &cache_chain, list) { check_irq_on(); /* @@ -4289,7 +4288,7 @@ static void s_stop(struct seq_file *m, void *p) static int s_show(struct seq_file *m, void *p) { - struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next); + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); struct slab *slabp; unsigned long active_objs; unsigned long num_objs; @@ -4345,7 +4344,7 @@ static int s_show(struct seq_file *m, void *p) 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->buffer_size, + name, active_objs, num_objs, cachep->size, cachep->num, (1 << cachep->gfporder)); seq_printf(m, " : tunables %4u %4u %4u", cachep->limit, cachep->batchcount, cachep->shared); @@ -4437,7 +4436,7 @@ static ssize_t slabinfo_write(struct file *file, const char __user *buffer, /* Find the cache in the chain of caches. */ mutex_lock(&cache_chain_mutex); res = -EINVAL; - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &cache_chain, list) { if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || batchcount > limit || shared < 0) { @@ -4513,7 +4512,7 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s) int i; if (n[0] == n[1]) return; - for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) { + for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) { if (slab_bufctl(s)[i] != BUFCTL_ACTIVE) continue; if (!add_caller(n, (unsigned long)*dbg_userword(c, p))) diff --git a/mm/slob.c b/mm/slob.c index c85265d22e0..95d1c7dd88e 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -506,13 +506,6 @@ size_t ksize(const void *block) } EXPORT_SYMBOL(ksize); -struct kmem_cache { - unsigned int size, align; - unsigned long flags; - const char *name; - void (*ctor)(void *); -}; - struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { @@ -523,7 +516,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, if (c) { c->name = name; - c->size = size; + c->size = c->object_size; if (flags & SLAB_DESTROY_BY_RCU) { /* leave room for rcu footer at the end of object */ c->size += sizeof(struct slob_rcu); diff --git a/mm/slub.c b/mm/slub.c index 2de3c996f32..797271f5afb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -311,7 +311,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s) * and whatever may come after it. */ if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) - return s->objsize; + return s->object_size; #endif /* @@ -609,11 +609,11 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (p > addr + 16) print_section("Bytes b4 ", p - 16, 16); - print_section("Object ", p, min_t(unsigned long, s->objsize, + print_section("Object ", p, min_t(unsigned long, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p + s->objsize, - s->inuse - s->objsize); + print_section("Redzone ", p + s->object_size, + s->inuse - s->object_size); if (s->offset) off = s->offset + sizeof(void *); @@ -655,12 +655,12 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) u8 *p = object; if (s->flags & __OBJECT_POISON) { - memset(p, POISON_FREE, s->objsize - 1); - p[s->objsize - 1] = POISON_END; + memset(p, POISON_FREE, s->object_size - 1); + p[s->object_size - 1] = POISON_END; } if (s->flags & SLAB_RED_ZONE) - memset(p + s->objsize, val, s->inuse - s->objsize); + memset(p + s->object_size, val, s->inuse - s->object_size); } static void restore_bytes(struct kmem_cache *s, char *message, u8 data, @@ -705,10 +705,10 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) * - * object + s->objsize + * object + s->object_size * Padding to reach word boundary. This is also used for Redzoning. * Padding is extended by another word if Redzoning is enabled and - * objsize == inuse. + * object_size == inuse. * * We fill with 0xbb (RED_INACTIVE) for inactive objects and with * 0xcc (RED_ACTIVE) for objects in use. @@ -727,7 +727,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object + s->size * Nothing is used beyond s->size. * - * If slabcaches are merged then the objsize and inuse boundaries are mostly + * If slabcaches are merged then the object_size and inuse boundaries are mostly * ignored. And therefore no slab options that rely on these boundaries * may be used with merged slabcaches. */ @@ -787,25 +787,25 @@ static int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { u8 *p = object; - u8 *endobject = object + s->objsize; + u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { if (!check_bytes_and_report(s, page, object, "Redzone", - endobject, val, s->inuse - s->objsize)) + endobject, val, s->inuse - s->object_size)) return 0; } else { - if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) { + if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { check_bytes_and_report(s, page, p, "Alignment padding", - endobject, POISON_INUSE, s->inuse - s->objsize); + endobject, POISON_INUSE, s->inuse - s->object_size); } } if (s->flags & SLAB_POISON) { if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, - POISON_FREE, s->objsize - 1) || + POISON_FREE, s->object_size - 1) || !check_bytes_and_report(s, page, p, "Poison", - p + s->objsize - 1, POISON_END, 1))) + p + s->object_size - 1, POISON_END, 1))) return 0; /* * check_pad_bytes cleans up on its own. @@ -926,7 +926,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object ", (void *)object, s->objsize); + print_section("Object ", (void *)object, s->object_size); dump_stack(); } @@ -942,14 +942,14 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) lockdep_trace_alloc(flags); might_sleep_if(flags & __GFP_WAIT); - return should_failslab(s->objsize, flags, s->flags); + return should_failslab(s->object_size, flags, s->flags); } static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object) { flags &= gfp_allowed_mask; kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); - kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags); + kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags); } static inline void slab_free_hook(struct kmem_cache *s, void *x) @@ -966,13 +966,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) unsigned long flags; local_irq_save(flags); - kmemcheck_slab_free(s, x, s->objsize); - debug_check_no_locks_freed(x, s->objsize); + kmemcheck_slab_free(s, x, s->object_size); + debug_check_no_locks_freed(x, s->object_size); local_irq_restore(flags); } #endif if (!(s->flags & SLAB_DEBUG_OBJECTS)) - debug_check_no_obj_freed(x, s->objsize); + debug_check_no_obj_freed(x, s->object_size); } /* @@ -1207,7 +1207,7 @@ out: __setup("slub_debug", setup_slub_debug); -static unsigned long kmem_cache_flags(unsigned long objsize, +static unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) { @@ -1237,7 +1237,7 @@ static inline int check_object(struct kmem_cache *s, struct page *page, static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) {} static inline void remove_full(struct kmem_cache *s, struct page *page) {} -static inline unsigned long kmem_cache_flags(unsigned long objsize, +static inline unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) { @@ -2098,10 +2098,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", nid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " - "default order: %d, min order: %d\n", s->name, s->objsize, + "default order: %d, min order: %d\n", s->name, s->object_size, s->size, oo_order(s->oo), oo_order(s->min)); - if (oo_order(s->min) > get_order(s->objsize)) + if (oo_order(s->min) > get_order(s->object_size)) printk(KERN_WARNING " %s debugging increased min order, use " "slub_debug=O to disable.\n", s->name); @@ -2374,7 +2374,7 @@ redo: } if (unlikely(gfpflags & __GFP_ZERO) && object) - memset(object, 0, s->objsize); + memset(object, 0, s->object_size); slab_post_alloc_hook(s, gfpflags, object); @@ -2385,7 +2385,7 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); - trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); + trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); return ret; } @@ -2415,7 +2415,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, - s->objsize, s->size, gfpflags, node); + s->object_size, s->size, gfpflags, node); return ret; } @@ -2910,7 +2910,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min) static int calculate_sizes(struct kmem_cache *s, int forced_order) { unsigned long flags = s->flags; - unsigned long size = s->objsize; + unsigned long size = s->object_size; unsigned long align = s->align; int order; @@ -2939,7 +2939,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * end of the object and the free pointer. If not then add an * additional word to have some bytes to store Redzone information. */ - if ((flags & SLAB_RED_ZONE) && size == s->objsize) + if ((flags & SLAB_RED_ZONE) && size == s->object_size) size += sizeof(void *); #endif @@ -2987,7 +2987,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * user specified and the dynamic determination of cache line size * on bootup. */ - align = calculate_alignment(flags, align, s->objsize); + align = calculate_alignment(flags, align, s->object_size); s->align = align; /* @@ -3035,7 +3035,7 @@ static int kmem_cache_open(struct kmem_cache *s, memset(s, 0, kmem_size); s->name = name; s->ctor = ctor; - s->objsize = size; + s->object_size = size; s->align = align; s->flags = kmem_cache_flags(size, flags, name, ctor); s->reserved = 0; @@ -3050,7 +3050,7 @@ static int kmem_cache_open(struct kmem_cache *s, * Disable debugging flags that store metadata if the min slab * order increased. */ - if (get_order(s->size) > get_order(s->objsize)) { + if (get_order(s->size) > get_order(s->object_size)) { s->flags &= ~DEBUG_METADATA_FLAGS; s->offset = 0; if (!calculate_sizes(s, -1)) @@ -3124,7 +3124,7 @@ error: */ unsigned int kmem_cache_size(struct kmem_cache *s) { - return s->objsize; + return s->object_size; } EXPORT_SYMBOL(kmem_cache_size); @@ -3853,11 +3853,11 @@ void __init kmem_cache_init(void) if (s && s->size) { char *name = kasprintf(GFP_NOWAIT, - "dma-kmalloc-%d", s->objsize); + "dma-kmalloc-%d", s->object_size); BUG_ON(!name); kmalloc_dma_caches[i] = create_kmalloc_cache(name, - s->objsize, SLAB_CACHE_DMA); + s->object_size, SLAB_CACHE_DMA); } } #endif @@ -3951,7 +3951,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, * Adjust the object sizes so that we clear * the complete object on kzalloc. */ - s->objsize = max(s->objsize, (int)size); + s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); if (sysfs_slab_alias(s, name)) { @@ -4634,7 +4634,7 @@ SLAB_ATTR_RO(align); static ssize_t object_size_show(struct kmem_cache *s, char *buf) { - return sprintf(buf, "%d\n", s->objsize); + return sprintf(buf, "%d\n", s->object_size); } SLAB_ATTR_RO(object_size); @@ -5438,7 +5438,7 @@ __initcall(slab_sysfs_init); static void print_slabinfo_header(struct seq_file *m) { seq_puts(m, "slabinfo - version: 2.1\n"); - seq_puts(m, "# name " + seq_puts(m, "# name " " "); seq_puts(m, " : tunables "); seq_puts(m, " : slabdata "); -- cgit v1.2.3-70-g09d2 From 039363f38bfe5f6281e9eae5e0518b11577d9d50 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 6 Jul 2012 15:25:10 -0500 Subject: mm, sl[aou]b: Extract common code for kmem_cache_create() Kmem_cache_create() does a variety of sanity checks but those vary depending on the allocator. Use the strictest tests and put them into a slab_common file. Make the tests conditional on CONFIG_DEBUG_VM. This patch has the effect of adding sanity checks for SLUB and SLOB under CONFIG_DEBUG_VM and removes the checks in SLAB for !CONFIG_DEBUG_VM. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 4 ++++ mm/Makefile | 3 ++- mm/slab.c | 24 +++++++------------ mm/slab_common.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/slob.c | 8 +++---- mm/slub.c | 11 +-------- 6 files changed, 87 insertions(+), 31 deletions(-) create mode 100644 mm/slab_common.c (limited to 'mm/slob.c') diff --git a/include/linux/slab.h b/include/linux/slab.h index 0dd2dfa7bec..0cb7c7eb041 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -130,6 +130,10 @@ int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); +/* Slab internal function */ +struct kmem_cache *__kmem_cache_create(const char *, size_t, size_t, + unsigned long, + void (*)(void *)); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. diff --git a/mm/Makefile b/mm/Makefile index a156285ce88..ae370783612 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,8 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o mmu_context.o percpu.o \ - compaction.o $(mmu-y) + compaction.o slab_common.o $(mmu-y) + obj-y += init-mm.o ifdef CONFIG_NO_BOOTMEM diff --git a/mm/slab.c b/mm/slab.c index 105f188d14a..10c821e492b 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1558,7 +1558,7 @@ void __init kmem_cache_init(void) * bug. */ - sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name, + 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, @@ -1566,7 +1566,7 @@ void __init kmem_cache_init(void) if (INDEX_AC != INDEX_L3) { sizes[INDEX_L3].cs_cachep = - kmem_cache_create(names[INDEX_L3].name, + __kmem_cache_create(names[INDEX_L3].name, sizes[INDEX_L3].cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_PANIC, @@ -1584,14 +1584,14 @@ void __init kmem_cache_init(void) * allow tighter packing of the smaller caches. */ if (!sizes->cs_cachep) { - sizes->cs_cachep = kmem_cache_create(names->name, + sizes->cs_cachep = __kmem_cache_create(names->name, sizes->cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_PANIC, NULL); } #ifdef CONFIG_ZONE_DMA - sizes->cs_dmacachep = kmem_cache_create( + sizes->cs_dmacachep = __kmem_cache_create( names->name_dma, sizes->cs_size, ARCH_KMALLOC_MINALIGN, @@ -2220,7 +2220,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) } /** - * kmem_cache_create - Create a cache. + * __kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. @@ -2247,7 +2247,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) * as davem. */ struct kmem_cache * -kmem_cache_create (const char *name, size_t size, size_t align, +__kmem_cache_create (const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { size_t left_over, slab_size, ralign; @@ -2388,7 +2388,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, /* Get cache's description obj. */ cachep = kmem_cache_zalloc(&cache_cache, gfp); if (!cachep) - goto oops; + return NULL; cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; cachep->object_size = size; @@ -2445,8 +2445,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, printk(KERN_ERR "kmem_cache_create: couldn't create cache %s.\n", name); kmem_cache_free(&cache_cache, cachep); - cachep = NULL; - goto oops; + return NULL; } slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab), align); @@ -2504,8 +2503,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (setup_cpu_cache(cachep, gfp)) { __kmem_cache_destroy(cachep); - cachep = NULL; - goto oops; + return NULL; } if (flags & SLAB_DEBUG_OBJECTS) { @@ -2521,16 +2519,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, /* cache setup completed, link it into the list */ list_add(&cachep->list, &cache_chain); oops: - if (!cachep && (flags & SLAB_PANIC)) - panic("kmem_cache_create(): failed to create slab `%s'\n", - name); if (slab_is_available()) { mutex_unlock(&cache_chain_mutex); put_online_cpus(); } return cachep; } -EXPORT_SYMBOL(kmem_cache_create); #if DEBUG static void check_irq_off(void) diff --git a/mm/slab_common.c b/mm/slab_common.c new file mode 100644 index 00000000000..80412beb67c --- /dev/null +++ b/mm/slab_common.c @@ -0,0 +1,68 @@ +/* + * Slab allocator functions that are independent of the allocator strategy + * + * (C) 2012 Christoph Lameter + */ +#include + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * kmem_cache_create - Create a cache. + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @ctor: A constructor for the objects. + * + * Returns a ptr to the cache on success, NULL on failure. + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + */ + +struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) +{ + struct kmem_cache *s = NULL; + +#ifdef CONFIG_DEBUG_VM + if (!name || in_interrupt() || size < sizeof(void *) || + size > KMALLOC_MAX_SIZE) { + printk(KERN_ERR "kmem_cache_create(%s) integrity check" + " failed\n", name); + goto out; + } +#endif + + s = __kmem_cache_create(name, size, align, flags, ctor); + +#ifdef CONFIG_DEBUG_VM +out: +#endif + if (!s && (flags & SLAB_PANIC)) + panic("kmem_cache_create: Failed to create slab '%s'\n", name); + + return s; +} +EXPORT_SYMBOL(kmem_cache_create); diff --git a/mm/slob.c b/mm/slob.c index 95d1c7dd88e..d63923d549e 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -506,7 +506,7 @@ size_t ksize(const void *block) } EXPORT_SYMBOL(ksize); -struct kmem_cache *kmem_cache_create(const char *name, size_t size, +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *c; @@ -529,13 +529,11 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, c->align = ARCH_SLAB_MINALIGN; if (c->align < align) c->align = align; - } else if (flags & SLAB_PANIC) - panic("Cannot create slab cache %s\n", name); - kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL); + kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL); + } return c; } -EXPORT_SYMBOL(kmem_cache_create); void kmem_cache_destroy(struct kmem_cache *c) { diff --git a/mm/slub.c b/mm/slub.c index 79fe9c6b93c..6551cc9a51f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3920,15 +3920,12 @@ static struct kmem_cache *find_mergeable(size_t size, return NULL; } -struct kmem_cache *kmem_cache_create(const char *name, size_t size, +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; char *n; - if (WARN_ON(!name)) - return NULL; - down_write(&slub_lock); s = find_mergeable(size, align, flags, name, ctor); if (s) { @@ -3972,14 +3969,8 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, kfree(n); err: up_write(&slub_lock); - - if (flags & SLAB_PANIC) - panic("Cannot create slabcache %s\n", name); - else - s = NULL; return s; } -EXPORT_SYMBOL(kmem_cache_create); #ifdef CONFIG_SMP /* -- cgit v1.2.3-70-g09d2 From 97d06609158e61f6bdf538c4a6788e2de492236f Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 6 Jul 2012 15:25:11 -0500 Subject: mm, sl[aou]b: Common definition for boot state of the slab allocators All allocators have some sort of support for the bootstrap status. Setup a common definition for the boot states and make all slab allocators use that definition. Reviewed-by: Glauber Costa Reviewed-by: Joonsoo Kim Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 4 ---- mm/slab.c | 45 ++++++++++++++------------------------------- mm/slab.h | 29 +++++++++++++++++++++++++++++ mm/slab_common.c | 9 +++++++++ mm/slob.c | 14 +++++--------- mm/slub.c | 21 +++++---------------- 6 files changed, 62 insertions(+), 60 deletions(-) create mode 100644 mm/slab.h (limited to 'mm/slob.c') diff --git a/include/linux/slab.h b/include/linux/slab.h index 0cb7c7eb041..0dd2dfa7bec 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -130,10 +130,6 @@ int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); -/* Slab internal function */ -struct kmem_cache *__kmem_cache_create(const char *, size_t, size_t, - unsigned long, - void (*)(void *)); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. diff --git a/mm/slab.c b/mm/slab.c index 10c821e492b..59a466b85b0 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -87,6 +87,7 @@ */ #include +#include "slab.h" #include #include #include @@ -565,27 +566,6 @@ static struct kmem_cache cache_cache = { #define BAD_ALIEN_MAGIC 0x01020304ul -/* - * chicken and egg problem: delay the per-cpu array allocation - * until the general caches are up. - */ -static enum { - NONE, - PARTIAL_AC, - PARTIAL_L3, - EARLY, - LATE, - FULL -} g_cpucache_up; - -/* - * used by boot code to determine if it can use slab based allocator - */ -int slab_is_available(void) -{ - return g_cpucache_up >= EARLY; -} - #ifdef CONFIG_LOCKDEP /* @@ -651,7 +631,7 @@ static void init_node_lock_keys(int q) { struct cache_sizes *s = malloc_sizes; - if (g_cpucache_up < LATE) + if (slab_state < UP) return; for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { @@ -1649,14 +1629,14 @@ void __init kmem_cache_init(void) } } - g_cpucache_up = EARLY; + slab_state = UP; } void __init kmem_cache_init_late(void) { struct kmem_cache *cachep; - g_cpucache_up = LATE; + slab_state = UP; /* Annotate slab for lockdep -- annotate the malloc caches */ init_lock_keys(); @@ -1668,6 +1648,9 @@ void __init kmem_cache_init_late(void) BUG(); mutex_unlock(&cache_chain_mutex); + /* Done! */ + slab_state = FULL; + /* * Register a cpu startup notifier callback that initializes * cpu_cache_get for all new cpus @@ -1699,7 +1682,7 @@ static int __init cpucache_init(void) start_cpu_timer(cpu); /* Done! */ - g_cpucache_up = FULL; + slab_state = FULL; return 0; } __initcall(cpucache_init); @@ -2167,10 +2150,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) { - if (g_cpucache_up >= LATE) + if (slab_state >= FULL) return enable_cpucache(cachep, gfp); - if (g_cpucache_up == NONE) { + if (slab_state == DOWN) { /* * Note: the first kmem_cache_create must create the cache * that's used by kmalloc(24), otherwise the creation of @@ -2185,16 +2168,16 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) */ set_up_list3s(cachep, SIZE_AC); if (INDEX_AC == INDEX_L3) - g_cpucache_up = PARTIAL_L3; + slab_state = PARTIAL_L3; else - g_cpucache_up = PARTIAL_AC; + slab_state = PARTIAL_ARRAYCACHE; } else { cachep->array[smp_processor_id()] = kmalloc(sizeof(struct arraycache_init), gfp); - if (g_cpucache_up == PARTIAL_AC) { + if (slab_state == PARTIAL_ARRAYCACHE) { set_up_list3s(cachep, SIZE_L3); - g_cpucache_up = PARTIAL_L3; + slab_state = PARTIAL_L3; } else { int node; for_each_online_node(node) { diff --git a/mm/slab.h b/mm/slab.h new file mode 100644 index 00000000000..f9a9815cdc8 --- /dev/null +++ b/mm/slab.h @@ -0,0 +1,29 @@ +#ifndef MM_SLAB_H +#define MM_SLAB_H +/* + * Internal slab definitions + */ + +/* + * State of the slab allocator. + * + * This is used to describe the states of the allocator during bootup. + * Allocators use this to gradually bootstrap themselves. Most allocators + * have the problem that the structures used for managing slab caches are + * allocated from slab caches themselves. + */ +enum slab_state { + DOWN, /* No slab functionality yet */ + PARTIAL, /* SLUB: kmem_cache_node available */ + PARTIAL_ARRAYCACHE, /* SLAB: kmalloc size for arraycache available */ + PARTIAL_L3, /* SLAB: kmalloc size for l3 struct available */ + UP, /* Slab caches usable but not all extras yet */ + FULL /* Everything is working */ +}; + +extern enum slab_state slab_state; + +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, + size_t align, unsigned long flags, void (*ctor)(void *)); + +#endif diff --git a/mm/slab_common.c b/mm/slab_common.c index 80412beb67c..ca1aaf69a1f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -16,6 +16,10 @@ #include #include +#include "slab.h" + +enum slab_state slab_state; + /* * kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. @@ -66,3 +70,8 @@ out: return s; } EXPORT_SYMBOL(kmem_cache_create); + +int slab_is_available(void) +{ + return slab_state >= UP; +} diff --git a/mm/slob.c b/mm/slob.c index d63923d549e..0111e0dece9 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -59,6 +59,8 @@ #include #include +#include "slab.h" + #include #include /* struct reclaim_state */ #include @@ -531,6 +533,7 @@ struct kmem_cache *__kmem_cache_create(const char *name, size_t size, c->align = align; kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL); + c->refcount = 1; } return c; } @@ -616,19 +619,12 @@ int kmem_cache_shrink(struct kmem_cache *d) } EXPORT_SYMBOL(kmem_cache_shrink); -static unsigned int slob_ready __read_mostly; - -int slab_is_available(void) -{ - return slob_ready; -} - void __init kmem_cache_init(void) { - slob_ready = 1; + slab_state = UP; } void __init kmem_cache_init_late(void) { - /* Nothing to do */ + slab_state = FULL; } diff --git a/mm/slub.c b/mm/slub.c index 6551cc9a51f..4c385164d9f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -16,6 +16,7 @@ #include #include #include +#include "slab.h" #include #include #include @@ -182,13 +183,6 @@ static int kmem_size = sizeof(struct kmem_cache); static struct notifier_block slab_notifier; #endif -static enum { - DOWN, /* No slab functionality available */ - PARTIAL, /* Kmem_cache_node works */ - UP, /* Everything works but does not show up in sysfs */ - SYSFS /* Sysfs up */ -} slab_state = DOWN; - /* A list of all slab caches on the system */ static DECLARE_RWSEM(slub_lock); static LIST_HEAD(slab_caches); @@ -237,11 +231,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si) * Core slab cache functions *******************************************************************/ -int slab_is_available(void) -{ - return slab_state >= UP; -} - static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) { return s->node[node]; @@ -5274,7 +5263,7 @@ static int sysfs_slab_add(struct kmem_cache *s) const char *name; int unmergeable; - if (slab_state < SYSFS) + if (slab_state < FULL) /* Defer until later */ return 0; @@ -5319,7 +5308,7 @@ static int sysfs_slab_add(struct kmem_cache *s) static void sysfs_slab_remove(struct kmem_cache *s) { - if (slab_state < SYSFS) + if (slab_state < FULL) /* * Sysfs has not been setup yet so no need to remove the * cache from sysfs. @@ -5347,7 +5336,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name) { struct saved_alias *al; - if (slab_state == SYSFS) { + if (slab_state == FULL) { /* * If we have a leftover link then remove it. */ @@ -5380,7 +5369,7 @@ static int __init slab_sysfs_init(void) return -ENOSYS; } - slab_state = SYSFS; + slab_state = FULL; list_for_each_entry(s, &slab_caches, list) { err = sysfs_slab_add(s); -- cgit v1.2.3-70-g09d2 From 44a8bdea19dff1abcdc4528e5f7e038b18ee5255 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 10 Jul 2012 18:31:05 -0500 Subject: slob: Fix early boot kernel crash Commit fd3142a59af2012a7c5dc72ec97a4935ff1c5fc6 broke slob since a piece of a change for a later patch slipped into it. Fengguang Wu writes: The commit crashes the kernel w/o any dmesg output (the attached one is created by the script as a summary for that run). This is very reproducible in kvm for the attached config. Reported-by: Fengguang Wu Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/slob.c') diff --git a/mm/slob.c b/mm/slob.c index 0111e0dece9..45d4ca79933 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -518,7 +518,7 @@ struct kmem_cache *__kmem_cache_create(const char *name, size_t size, if (c) { c->name = name; - c->size = c->object_size; + c->size = size; if (flags & SLAB_DESTROY_BY_RCU) { /* leave room for rcu footer at the end of object */ c->size += sizeof(struct slob_rcu); -- cgit v1.2.3-70-g09d2