This gets rid of all kmalloc caches larger than page size. A kmalloc request larger than PAGE_SIZE > 2 is going to be passed through to the page allocator. This works both inline where we will call __get_free_pages instead of kmem_cache_alloc and in __kmalloc. kfree is modified to check if the object is in a slab page. If not then the page is freed via the page allocator instead. Drawbacks: - No accounting for large kmalloc slab allocations anymore - No debugging of large kmalloc slab allocations. - Meshing of slab allocations and page allocator allocations become possible. - Strange discontinuity in kmalloc operations. If larger than page size then full page allocator semantics apply. But SLOB is already doing that. - kmalloc objects are aligned to ARCH_KMALLOC_MINALIGN if smaller than PAGE_SIZE otherwise they are page aligned. - Additional check of the size in kmalloc and kfree. Advantages: - Significantly reduces memory overhead for kmalloc array - Large kmalloc operations are faster since they do not need to pass through the slab allocator to get to the page allocator. - Large kmallocs yields page aligned object which is what SLAB does. Bad things like using page sized kmalloc allocations can be transparently handled and are not distinguishable from page allocator uses. - Checking for too large objects can be removed since it is done by the page allocator. Signed-off-by: Christoph Lameter --- include/linux/slub_def.h | 57 +++++++++++++++++------------------------- mm/slub.c | 63 ++++++++++++++++++++++++++++------------------- 2 files changed, 62 insertions(+), 58 deletions(-) Index: linux-2.6.22-rc6-mm1/mm/slub.c =================================================================== --- linux-2.6.22-rc6-mm1.orig/mm/slub.c 2007-07-06 16:08:36.000000000 -0700 +++ linux-2.6.22-rc6-mm1/mm/slub.c 2007-07-06 16:08:36.000000000 -0700 @@ -2239,11 +2239,11 @@ EXPORT_SYMBOL(kmem_cache_destroy); * Kmalloc subsystem *******************************************************************/ -struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __cacheline_aligned; +struct kmem_cache kmalloc_caches[PAGE_SHIFT] __cacheline_aligned; EXPORT_SYMBOL(kmalloc_caches); #ifdef CONFIG_ZONE_DMA -static struct kmem_cache *kmalloc_caches_dma[KMALLOC_SHIFT_HIGH + 1]; +static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT]; #endif static int __init setup_slub_min_order(char *str) @@ -2379,12 +2379,8 @@ static struct kmem_cache *get_slab(size_ return ZERO_SIZE_PTR; index = size_index[(size - 1) / 8]; - } else { - if (size > KMALLOC_MAX_SIZE) - return NULL; - + } else index = fls(size - 1); - } #ifdef CONFIG_ZONE_DMA if (unlikely((flags & SLUB_DMA))) @@ -2396,9 +2392,15 @@ static struct kmem_cache *get_slab(size_ void *__kmalloc(size_t size, gfp_t flags) { - struct kmem_cache *s = get_slab(size, flags); + struct kmem_cache *s; - if (ZERO_OR_NULL_PTR(s)) + if (unlikely(size > PAGE_SIZE / 2)) + return (void *)__get_free_pages(flags | __GFP_COMP, + get_order(size)); + + s = get_slab(size, flags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) return s; return slab_alloc(s, flags, -1, __builtin_return_address(0)); @@ -2408,9 +2410,15 @@ EXPORT_SYMBOL(__kmalloc); #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) { - struct kmem_cache *s = get_slab(size, flags); + struct kmem_cache *s; - if (ZERO_OR_NULL_PTR(s)) + if (unlikely(size > PAGE_SIZE / 2)) + return (void *)__get_free_pages(flags | __GFP_COMP, + get_order(size)); + + s = get_slab(size, flags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) return s; return slab_alloc(s, flags, node, __builtin_return_address(0)); @@ -2455,22 +2463,17 @@ EXPORT_SYMBOL(ksize); void kfree(const void *x) { - struct kmem_cache *s; struct page *page; - /* - * This has to be an unsigned comparison. According to Linus - * some gcc version treat a pointer as a signed entity. Then - * this comparison would be true for all "negative" pointers - * (which would cover the whole upper half of the address space). - */ if (ZERO_OR_NULL_PTR(x)) return; page = virt_to_head_page(x); - s = page->slab; - - slab_free(s, page, (void *)x, __builtin_return_address(0)); + if (unlikely(!PageSlab(page))) { + put_page(page); + return; + } + slab_free(page->slab, page, (void *)x, __builtin_return_address(0)); } EXPORT_SYMBOL(kfree); @@ -2927,7 +2930,7 @@ void __init kmem_cache_init(void) caches++; } - for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { + for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++) { create_kmalloc_cache(&kmalloc_caches[i], "kmalloc", 1 << i, GFP_KERNEL); caches++; @@ -2954,7 +2957,7 @@ void __init kmem_cache_init(void) slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ - for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) + for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++) kmalloc_caches[i]. name = kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i); @@ -3142,7 +3145,12 @@ static struct notifier_block __cpuinitda void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller) { - struct kmem_cache *s = get_slab(size, gfpflags); + struct kmem_cache *s; + + if (unlikely(size > PAGE_SIZE / 2)) + return (void *)__get_free_pages(gfpflags | __GFP_COMP, + get_order(size)); + s = get_slab(size, gfpflags); if (ZERO_OR_NULL_PTR(s)) return s; @@ -3153,7 +3161,12 @@ void *__kmalloc_track_caller(size_t size void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, int node, void *caller) { - struct kmem_cache *s = get_slab(size, gfpflags); + struct kmem_cache *s; + + if (unlikely(size > PAGE_SIZE / 2)) + return (void *)__get_free_pages(gfpflags | __GFP_COMP, + get_order(size)); + s = get_slab(size, gfpflags); if (ZERO_OR_NULL_PTR(s)) return s; Index: linux-2.6.22-rc6-mm1/include/linux/slub_def.h =================================================================== --- linux-2.6.22-rc6-mm1.orig/include/linux/slub_def.h 2007-07-06 16:07:53.000000000 -0700 +++ linux-2.6.22-rc6-mm1/include/linux/slub_def.h 2007-07-06 16:08:36.000000000 -0700 @@ -81,7 +81,7 @@ struct kmem_cache { * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache kmalloc_caches[PAGE_SHIFT]; /* * Sorry that the following has to be that ugly but some versions of GCC @@ -92,9 +92,6 @@ static inline int kmalloc_index(size_t s if (!size) return 0; - if (size > KMALLOC_MAX_SIZE) - return -1; - if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; @@ -111,6 +108,10 @@ static inline int kmalloc_index(size_t s if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; +/* + * The following is only needed to support architectures with a larger page + * size than 4k. + */ if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; @@ -118,13 +119,9 @@ static inline int kmalloc_index(size_t s if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; - if (size <= 512 * 1024) return 19; + if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; - if (size <= 4 * 1024 * 1024) return 22; - if (size <= 8 * 1024 * 1024) return 23; - if (size <= 16 * 1024 * 1024) return 24; - if (size <= 32 * 1024 * 1024) return 25; return -1; /* @@ -149,19 +146,6 @@ static inline struct kmem_cache *kmalloc if (index == 0) return NULL; - /* - * This function only gets expanded if __builtin_constant_p(size), so - * testing it here shouldn't be needed. But some versions of gcc need - * help. - */ - if (__builtin_constant_p(size) && index < 0) { - /* - * Generate a link failure. Would be great if we could - * do something to stop the compile here. - */ - extern void __kmalloc_size_too_large(void); - __kmalloc_size_too_large(); - } return &kmalloc_caches[index]; } @@ -177,15 +161,21 @@ void *__kmalloc(size_t size, gfp_t flags static inline void *kmalloc(size_t size, gfp_t flags) { - if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (__builtin_constant_p(size)) { + if (size > PAGE_SIZE / 2) + return (void *)__get_free_pages(flags | __GFP_COMP, + get_order(size)); - if (!s) - return ZERO_SIZE_PTR; + if (!(flags & SLUB_DMA)) { + struct kmem_cache *s = kmalloc_slab(size); + + if (!s) + return ZERO_SIZE_PTR; - return kmem_cache_alloc(s, flags); - } else - return __kmalloc(size, flags); + return kmem_cache_alloc(s, flags); + } + } + return __kmalloc(size, flags); } #ifdef CONFIG_NUMA @@ -194,15 +184,16 @@ void *kmem_cache_alloc_node(struct kmem_ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) { - if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (__builtin_constant_p(size) && + size <= PAGE_SIZE / 2 && !(flags & SLUB_DMA)) { + struct kmem_cache *s = kmalloc_slab(size); if (!s) return ZERO_SIZE_PTR; return kmem_cache_alloc_node(s, flags, node); - } else - return __kmalloc_node(size, flags, node); + } + return __kmalloc_node(size, flags, node); } #endif -- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/