Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755698Ab0GMKSx (ORCPT ); Tue, 13 Jul 2010 06:18:53 -0400 Received: from mx1.redhat.com ([209.132.183.28]:1027 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753155Ab0GMKSu (ORCPT ); Tue, 13 Jul 2010 06:18:50 -0400 Date: Tue, 13 Jul 2010 06:17:59 -0400 From: Xiaotian Feng To: linux-mm@kvack.org, linux-nfs@vger.kernel.org, netdev@vger.kernel.org Cc: riel@redhat.com, cl@linux-foundation.org, a.p.zijlstra@chello.nl, Xiaotian Feng , linux-kernel@vger.kernel.org, lwang@redhat.com, penberg@cs.helsinki.fi, akpm@linux-foundation.org, davem@davemloft.net Message-Id: <20100713101758.2835.26517.sendpatchset@danny.redhat> In-Reply-To: <20100713101650.2835.15245.sendpatchset@danny.redhat> References: <20100713101650.2835.15245.sendpatchset@danny.redhat> Subject: [PATCH -mmotm 06/30] mm: kmem_alloc_estimate() Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9288 Lines: 321 >From 4a2dff5cf02e9d7f6ee9345c337697c4ab66c6dc Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Tue, 13 Jul 2010 10:41:22 +0800 Subject: [PATCH 06/30] mm: kmem_alloc_estimate() Provide a method to get the upper bound on the pages needed to allocate a given number of objects from a given kmem_cache. This lays the foundation for a generic reserve framework as presented in a later patch in this series. This framework needs to convert object demand (kmalloc() bytes, kmem_cache_alloc() objects) to pages. Signed-off-by: Peter Zijlstra Signed-off-by: Suresh Jayaraman Signed-off-by: Xiaotian Feng --- include/linux/slab.h | 4 ++ mm/slab.c | 75 +++++++++++++++++++++++++++++++++++++++++++ mm/slob.c | 67 ++++++++++++++++++++++++++++++++++++++ mm/slub.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 233 insertions(+), 0 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index 49d1247..b57b9ca 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -108,6 +108,8 @@ unsigned int kmem_cache_size(struct kmem_cache *); const char *kmem_cache_name(struct kmem_cache *); int kern_ptr_validate(const void *ptr, unsigned long size); int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); +unsigned kmem_alloc_estimate(struct kmem_cache *cachep, + gfp_t flags, int objects); /* * Please use this macro to create slab caches. Simply specify the @@ -144,6 +146,8 @@ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +unsigned kmalloc_estimate_objs(size_t, gfp_t, int); +unsigned kmalloc_estimate_bytes(gfp_t, size_t); /* * Allocator specific definitions. These are mainly used to establish optimized diff --git a/mm/slab.c b/mm/slab.c index d8cd757..2a0dd0d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3913,6 +3913,81 @@ const char *kmem_cache_name(struct kmem_cache *cachep) EXPORT_SYMBOL_GPL(kmem_cache_name); /* + * Calculate the upper bound of pages required to sequentially allocate + * @objects objects from @cachep. + */ +unsigned kmem_alloc_estimate(struct kmem_cache *cachep, + gfp_t flags, int objects) +{ + /* + * (1) memory for objects, + */ + unsigned nr_slabs = DIV_ROUND_UP(objects, cachep->num); + unsigned nr_pages = nr_slabs << cachep->gfporder; + + /* + * (2) memory for each per-cpu queue (nr_cpu_ids), + * (3) memory for each per-node alien queues (nr_cpu_ids), and + * (4) some amount of memory for the slab management structures + * + * XXX: truely account these + */ + nr_pages += 1 + ilog2(nr_pages); + + return nr_pages; +} + +/* + * Calculate the upper bound of pages required to sequentially allocate + * @count objects of @size bytes from kmalloc given @flags. + */ +unsigned kmalloc_estimate_objs(size_t size, gfp_t flags, int count) +{ + struct kmem_cache *s = kmem_find_general_cachep(size, flags); + if (!s) + return 0; + + return kmem_alloc_estimate(s, flags, count); +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_objs); + +/* + * Calculate the upper bound of pages requires to sequentially allocate @bytes + * from kmalloc in an unspecified number of allocations of nonuniform size. + */ +unsigned kmalloc_estimate_bytes(gfp_t flags, size_t bytes) +{ + unsigned long pages; + struct cache_sizes *csizep = malloc_sizes; + + /* + * multiply by two, in order to account the worst case slack space + * due to the power-of-two allocation sizes. + */ + pages = DIV_ROUND_UP(2 * bytes, PAGE_SIZE); + + /* + * add the kmem_cache overhead of each possible kmalloc cache + */ + for (csizep = malloc_sizes; csizep->cs_cachep; csizep++) { + struct kmem_cache *s; + +#ifdef CONFIG_ZONE_DMA + if (unlikely(flags & __GFP_DMA)) + s = csizep->cs_dmacachep; + else +#endif + s = csizep->cs_cachep; + + if (s) + pages += kmem_alloc_estimate(s, flags, 0); + } + + return pages; +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_bytes); + +/* * This initializes kmem_list3 or resizes various caches for all nodes. */ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) diff --git a/mm/slob.c b/mm/slob.c index b84b611..0caf938 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -695,6 +695,73 @@ int slab_is_available(void) return slob_ready; } +static __slob_estimate(unsigned size, unsigned align, unsigned objects) +{ + unsigned nr_pages; + + size = SLOB_UNIT * SLOB_UNITS(size + align - 1); + + if (size <= PAGE_SIZE) { + nr_pages = DIV_ROUND_UP(objects, PAGE_SIZE / size); + } else { + nr_pages = objects << get_order(size); + } + + return nr_pages; +} + +/* + * Calculate the upper bound of pages required to sequentially allocate + * @objects objects from @cachep. + */ +unsigned kmem_alloc_estimate(struct kmem_cache *c, gfp_t flags, int objects) +{ + unsigned size = c->size; + + if (c->flags & SLAB_DESTROY_BY_RCU) + size += sizeof(struct slob_rcu); + + return __slob_estimate(size, c->align, objects); +} + +/* + * Calculate the upper bound of pages required to sequentially allocate + * @count objects of @size bytes from kmalloc given @flags. + */ +unsigned kmalloc_estimate_objs(size_t size, gfp_t flags, int count) +{ + unsigned align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + + return __slob_estimate(size, align, count); +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_objs); + +/* + * Calculate the upper bound of pages requires to sequentially allocate @bytes + * from kmalloc in an unspecified number of allocations of nonuniform size. + */ +unsigned kmalloc_estimate_bytes(gfp_t flags, size_t bytes) +{ + unsigned long pages; + + /* + * Multiply by two, in order to account the worst case slack space + * due to the power-of-two allocation sizes. + * + * While not true for slob, it cannot do worse than that for sequential + * allocations. + */ + pages = DIV_ROUND_UP(2 * bytes, PAGE_SIZE); + + /* + * Our power of two series starts at PAGE_SIZE, so add one page. + */ + pages++; + + return pages; +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_bytes); + void __init kmem_cache_init(void) { slob_ready = 1; diff --git a/mm/slub.c b/mm/slub.c index 7a5d6dc..056545e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2435,6 +2435,42 @@ const char *kmem_cache_name(struct kmem_cache *s) } EXPORT_SYMBOL(kmem_cache_name); +/* + * Calculate the upper bound of pages required to sequentially allocate + * @objects objects from @cachep. + * + * We should use s->min_objects because those are the least efficient. + */ +unsigned kmem_alloc_estimate(struct kmem_cache *s, gfp_t flags, int objects) +{ + unsigned long pages; + struct kmem_cache_order_objects x; + + if (WARN_ON(!s) || WARN_ON(!oo_objects(s->min))) + return 0; + + x = s->min; + pages = DIV_ROUND_UP(objects, oo_objects(x)) << oo_order(x); + + /* + * Account the possible additional overhead if the slab holds more that + * one object. Use s->max_objects because that's the worst case. + */ + x = s->oo; + if (oo_objects(x) > 1) { + /* + * Account the possible additional overhead if per cpu slabs + * are currently empty and have to be allocated. This is very + * unlikely but a possible scenario immediately after + * kmem_cache_shrink. + */ + pages += num_possible_cpus() << oo_order(x); + } + + return pages; +} +EXPORT_SYMBOL_GPL(kmem_alloc_estimate); + static void list_slab_objects(struct kmem_cache *s, struct page *page, const char *text) { @@ -2868,6 +2904,57 @@ void kfree(const void *x) EXPORT_SYMBOL(kfree); /* + * Calculate the upper bound of pages required to sequentially allocate + * @count objects of @size bytes from kmalloc given @flags. + */ +unsigned kmalloc_estimate_objs(size_t size, gfp_t flags, int count) +{ + struct kmem_cache *s = get_slab(size, flags); + if (!s) + return 0; + + return kmem_alloc_estimate(s, flags, count); + +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_objs); + +/* + * Calculate the upper bound of pages requires to sequentially allocate @bytes + * from kmalloc in an unspecified number of allocations of nonuniform size. + */ +unsigned kmalloc_estimate_bytes(gfp_t flags, size_t bytes) +{ + int i; + unsigned long pages; + + /* + * multiply by two, in order to account the worst case slack space + * due to the power-of-two allocation sizes. + */ + pages = DIV_ROUND_UP(2 * bytes, PAGE_SIZE); + + /* + * add the kmem_cache overhead of each possible kmalloc cache + */ + for (i = 1; i < PAGE_SHIFT; i++) { + struct kmem_cache *s; + +#ifdef CONFIG_ZONE_DMA + if (unlikely(flags & SLUB_DMA)) + s = dma_kmalloc_cache(i, flags); + else +#endif + s = &kmalloc_caches[i]; + + if (s) + pages += kmem_alloc_estimate(s, flags, 0); + } + + return pages; +} +EXPORT_SYMBOL_GPL(kmalloc_estimate_bytes); + +/* * kmem_cache_shrink removes empty slabs from the partial lists and sorts * the remaining slabs by the number of items in use. The slabs with the * most items in use come first. New allocations will then fill those up -- 1.7.1.1 -- 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/