X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fslab.c;h=a684778b2b41af38e06aa47e5fe66a7a988ad4c7;hb=75ecb1a4d148b274aa9acd1d6ccaca0a4654784e;hp=4cbac24ae2f1f25c2a81e728aa576f1ae8b9d254;hpb=e0cc09e295f346b7921e921f385fe5213472316a;p=linux-2.6

diff --git a/mm/slab.c b/mm/slab.c
index 4cbac24ae2..a684778b2b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -116,8 +116,7 @@
 #include	<asm/page.h>
 
 /*
- * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL,
- *		  SLAB_RED_ZONE & SLAB_POISON.
+ * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
  *		  0 for faster, smaller code (especially in the critical paths).
  *
  * STATS	- 1 to collect stats for /proc/slabinfo.
@@ -138,6 +137,7 @@
 
 /* Shouldn't this be in a header file somewhere? */
 #define	BYTES_PER_WORD		sizeof(void *)
+#define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))
 
 #ifndef cache_line_size
 #define cache_line_size()	L1_CACHE_BYTES
@@ -149,10 +149,11 @@
  * Usually, the kmalloc caches are cache_line_size() aligned, except when
  * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
  * Some archs want to perform DMA into kmalloc caches and need a guaranteed
- * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that.
- * Note that this flag disables some debug features.
+ * alignment larger than the alignment of a 64-bit integer.
+ * ARCH_KMALLOC_MINALIGN allows that.
+ * Note that increasing this value may disable some debug features.
  */
-#define ARCH_KMALLOC_MINALIGN 0
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
 #endif
 
 #ifndef ARCH_SLAB_MINALIGN
@@ -172,15 +173,15 @@
 
 /* Legal flag mask for kmem_cache_create(). */
 #if DEBUG
-# define CREATE_MASK	(SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
+# define CREATE_MASK	(SLAB_RED_ZONE | \
 			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | \
-			 SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
+			 SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
 #else
 # define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
-			 SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
+			 SLAB_CACHE_DMA | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
 #endif
@@ -389,7 +390,6 @@ struct kmem_cache {
 	unsigned int buffer_size;
 	u32 reciprocal_buffer_size;
 /* 3) 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 */
@@ -410,9 +410,6 @@ struct kmem_cache {
 	/* constructor func */
 	void (*ctor) (void *, struct kmem_cache *, unsigned long);
 
-	/* de-constructor func */
-	void (*dtor) (void *, struct kmem_cache *, unsigned long);
-
 /* 5) cache creation/removal */
 	const char *name;
 	struct list_head next;
@@ -444,6 +441,17 @@ struct kmem_cache {
 	int obj_offset;
 	int obj_size;
 #endif
+	/*
+	 * We put nodelists[] at the end of kmem_cache, because we want to size
+	 * this array to nr_node_ids slots instead of MAX_NUMNODES
+	 * (see kmem_cache_init())
+	 * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
+	 * is statically defined, so we reserve the max number of nodes.
+	 */
+	struct kmem_list3 *nodelists[MAX_NUMNODES];
+	/*
+	 * Do not add fields after nodelists[]
+	 */
 };
 
 #define CFLGS_OFF_SLAB		(0x80000000UL)
@@ -527,19 +535,22 @@ static int obj_size(struct kmem_cache *cachep)
 	return cachep->obj_size;
 }
 
-static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
+static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
 {
 	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD);
+	return (unsigned long long*) (objp + obj_offset(cachep) -
+				      sizeof(unsigned long long));
 }
 
-static unsigned long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
+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 *)(objp + cachep->buffer_size -
-					 2 * BYTES_PER_WORD);
-	return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD);
+		return (unsigned long long *)(objp + cachep->buffer_size -
+					      sizeof(unsigned long long) -
+					      REDZONE_ALIGN);
+	return (unsigned long long *) (objp + cachep->buffer_size -
+				       sizeof(unsigned long long));
 }
 
 static void **dbg_userword(struct kmem_cache *cachep, void *objp)
@@ -552,27 +563,12 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #define obj_offset(x)			0
 #define obj_size(cachep)		(cachep->buffer_size)
-#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long *)NULL;})
-#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long *)NULL;})
+#define dbg_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;})
 
 #endif
 
-/*
- * Maximum size of an obj (in 2^order pages) and absolute limit for the gfp
- * order.
- */
-#if defined(CONFIG_LARGE_ALLOCS)
-#define	MAX_OBJ_ORDER	13	/* up to 32Mb */
-#define	MAX_GFP_ORDER	13	/* up to 32Mb */
-#elif defined(CONFIG_MMU)
-#define	MAX_OBJ_ORDER	5	/* 32 pages */
-#define	MAX_GFP_ORDER	5	/* 32 pages */
-#else
-#define	MAX_OBJ_ORDER	8	/* up to 1Mb */
-#define	MAX_GFP_ORDER	8	/* up to 1Mb */
-#endif
-
 /*
  * Do not go above this order unless 0 objects fit into the slab.
  */
@@ -592,8 +588,7 @@ static inline void page_set_cache(struct page *page, struct kmem_cache *cache)
 
 static inline struct kmem_cache *page_get_cache(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
+	page = compound_head(page);
 	BUG_ON(!PageSlab(page));
 	return (struct kmem_cache *)page->lru.next;
 }
@@ -605,21 +600,19 @@ static inline void page_set_slab(struct page *page, struct slab *slab)
 
 static inline struct slab *page_get_slab(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
 	BUG_ON(!PageSlab(page));
 	return (struct slab *)page->lru.prev;
 }
 
 static inline struct kmem_cache *virt_to_cache(const void *obj)
 {
-	struct page *page = virt_to_page(obj);
+	struct page *page = virt_to_head_page(obj);
 	return page_get_cache(page);
 }
 
 static inline struct slab *virt_to_slab(const void *obj)
 {
-	struct page *page = virt_to_page(obj);
+	struct page *page = virt_to_head_page(obj);
 	return page_get_slab(page);
 }
 
@@ -678,9 +671,6 @@ static struct kmem_cache cache_cache = {
 	.shared = 1,
 	.buffer_size = sizeof(struct kmem_cache),
 	.name = "kmem_cache",
-#if DEBUG
-	.obj_size = sizeof(struct kmem_cache),
-#endif
 };
 
 #define BAD_ALIEN_MAGIC 0x01020304ul
@@ -785,6 +775,9 @@ static inline struct kmem_cache *__find_general_cachep(size_t size,
 	 */
 	BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
 #endif
+	if (!size)
+		return ZERO_SIZE_PTR;
+
 	while (size > csizep->cs_size)
 		csizep++;
 
@@ -921,12 +914,6 @@ static void next_reap_node(void)
 {
 	int node = __get_cpu_var(reap_node);
 
-	/*
-	 * Also drain per cpu pages on remote zones
-	 */
-	if (node != numa_node_id())
-		drain_node_pages(node);
-
 	node = next_node(node, node_online_map);
 	if (unlikely(node >= MAX_NUMNODES))
 		node = first_node(node_online_map);
@@ -945,7 +932,7 @@ static void next_reap_node(void)
  * the CPUs getting into lockstep and contending for the global cache chain
  * lock.
  */
-static void __devinit start_cpu_timer(int cpu)
+static void __cpuinit start_cpu_timer(int cpu)
 {
 	struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
 
@@ -1146,7 +1133,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 	 * Make sure we are not freeing a object from another node to the array
 	 * cache on this cpu.
 	 */
-	if (likely(slabp->nodeid == node) || unlikely(!use_alien_caches))
+	if (likely(slabp->nodeid == node))
 		return 0;
 
 	l3 = cachep->nodelists[node];
@@ -1176,11 +1163,14 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
-	int memsize = sizeof(struct kmem_list3);
+	const int memsize = sizeof(struct kmem_list3);
 
 	switch (action) {
-	case CPU_UP_PREPARE:
+	case CPU_LOCK_ACQUIRE:
 		mutex_lock(&cache_chain_mutex);
+		break;
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		/*
 		 * We need to do this right in the beginning since
 		 * alloc_arraycache's are going to use this list.
@@ -1223,19 +1213,20 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		 */
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
-			struct array_cache *shared;
+			struct array_cache *shared = NULL;
 			struct array_cache **alien = NULL;
 
 			nc = alloc_arraycache(node, cachep->limit,
 						cachep->batchcount);
 			if (!nc)
 				goto bad;
-			shared = alloc_arraycache(node,
+			if (cachep->shared) {
+				shared = alloc_arraycache(node,
 					cachep->shared * cachep->batchcount,
 					0xbaadf00d);
-			if (!shared)
-				goto bad;
-
+				if (!shared)
+					goto bad;
+			}
 			if (use_alien_caches) {
                                 alien = alloc_alien_cache(node, cachep->limit);
                                 if (!alien)
@@ -1266,17 +1257,28 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		}
 		break;
 	case CPU_ONLINE:
-		mutex_unlock(&cache_chain_mutex);
+	case CPU_ONLINE_FROZEN:
 		start_cpu_timer(cpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DOWN_PREPARE:
-		mutex_lock(&cache_chain_mutex);
-		break;
-	case CPU_DOWN_FAILED:
-		mutex_unlock(&cache_chain_mutex);
-		break;
+  	case CPU_DOWN_PREPARE:
+  	case CPU_DOWN_PREPARE_FROZEN:
+		/*
+		 * Shutdown cache reaper. Note that the cache_chain_mutex is
+		 * held so that if cache_reap() is invoked it cannot do
+		 * anything expensive but will only modify reap_work
+		 * and reschedule the timer.
+		*/
+		cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+		/* Now the cache_reaper is guaranteed to be not running. */
+		per_cpu(reap_work, cpu).work.func = NULL;
+  		break;
+  	case CPU_DOWN_FAILED:
+  	case CPU_DOWN_FAILED_FROZEN:
+		start_cpu_timer(cpu);
+  		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		/*
 		 * Even if all the cpus of a node are down, we don't free the
 		 * kmem_list3 of any cache. This to avoid a race between
@@ -1288,6 +1290,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		/* fall thru */
 #endif
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
 			struct array_cache *shared;
@@ -1317,8 +1320,8 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 
 			shared = l3->shared;
 			if (shared) {
-				free_block(cachep, l3->shared->entry,
-					   l3->shared->avail, node);
+				free_block(cachep, shared->entry,
+					   shared->avail, node);
 				l3->shared = NULL;
 			}
 
@@ -1346,6 +1349,8 @@ free_array_cache:
 				continue;
 			drain_freelist(cachep, l3, l3->free_objects);
 		}
+		break;
+	case CPU_LOCK_RELEASE:
 		mutex_unlock(&cache_chain_mutex);
 		break;
 	}
@@ -1394,6 +1399,9 @@ void __init kmem_cache_init(void)
 	int order;
 	int node;
 
+	if (num_possible_nodes() == 1)
+		use_alien_caches = 0;
+
 	for (i = 0; i < NUM_INIT_LISTS; i++) {
 		kmem_list3_init(&initkmem_list3[i]);
 		if (i < MAX_NUMNODES)
@@ -1436,6 +1444,15 @@ void __init kmem_cache_init(void)
 	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
 	cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
 
+	/*
+	 * struct kmem_cache size depends on nr_node_ids, which
+	 * can be less than MAX_NUMNODES.
+	 */
+	cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
+				 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_line_size());
 	cache_cache.reciprocal_buffer_size =
@@ -1467,7 +1484,7 @@ void __init kmem_cache_init(void)
 					sizes[INDEX_AC].cs_size,
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 
 	if (INDEX_AC != INDEX_L3) {
 		sizes[INDEX_L3].cs_cachep =
@@ -1475,7 +1492,7 @@ void __init kmem_cache_init(void)
 				sizes[INDEX_L3].cs_size,
 				ARCH_KMALLOC_MINALIGN,
 				ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-				NULL, NULL);
+				NULL);
 	}
 
 	slab_early_init = 0;
@@ -1493,7 +1510,7 @@ void __init kmem_cache_init(void)
 					sizes->cs_size,
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 		}
 #ifdef CONFIG_ZONE_DMA
 		sizes->cs_dmacachep = kmem_cache_create(
@@ -1502,7 +1519,7 @@ void __init kmem_cache_init(void)
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
 						SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 #endif
 		sizes++;
 		names++;
@@ -1760,7 +1777,7 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
 	char *realobj;
 
 	if (cachep->flags & SLAB_RED_ZONE) {
-		printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n",
+		printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
 			*dbg_redzone1(cachep, objp),
 			*dbg_redzone2(cachep, objp));
 	}
@@ -1880,20 +1897,11 @@ static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 				slab_error(cachep, "end of a freed object "
 					   "was overwritten");
 		}
-		if (cachep->dtor && !(cachep->flags & SLAB_POISON))
-			(cachep->dtor) (objp + obj_offset(cachep), cachep, 0);
 	}
 }
 #else
 static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 {
-	if (cachep->dtor) {
-		int i;
-		for (i = 0; i < cachep->num; i++) {
-			void *objp = index_to_obj(cachep, slabp, i);
-			(cachep->dtor) (objp, cachep, 0);
-		}
-	}
 }
 #endif
 
@@ -1929,7 +1937,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
  * For setting up all the kmem_list3s for cache whose buffer_size is same as
  * size of kmem_list3.
  */
-static void set_up_list3s(struct kmem_cache *cachep, int index)
+static void __init set_up_list3s(struct kmem_cache *cachep, int index)
 {
 	int node;
 
@@ -1982,7 +1990,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 	size_t left_over = 0;
 	int gfporder;
 
-	for (gfporder = 0; gfporder <= MAX_GFP_ORDER; gfporder++) {
+	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
 		unsigned int num;
 		size_t remainder;
 
@@ -2032,7 +2040,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 	return left_over;
 }
 
-static int setup_cpu_cache(struct kmem_cache *cachep)
+static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
 {
 	if (g_cpucache_up == FULL)
 		return enable_cpucache(cachep);
@@ -2093,12 +2101,10 @@ static int setup_cpu_cache(struct kmem_cache *cachep)
  * @align: The required alignment for the objects.
  * @flags: SLAB flags
  * @ctor: A constructor for the objects.
- * @dtor: A destructor for the objects.
  *
  * Returns a ptr to the cache on success, NULL on failure.
  * Cannot be called within a int, but can be interrupted.
- * The @ctor is run when new pages are allocated by the cache
- * and the @dtor is run before the pages are handed back.
+ * The @ctor is run when new pages are allocated by the cache.
  *
  * @name must be valid until the cache is destroyed. This implies that
  * the module calling this has to destroy the cache before getting unloaded.
@@ -2118,8 +2124,7 @@ static int setup_cpu_cache(struct kmem_cache *cachep)
 struct kmem_cache *
 kmem_cache_create (const char *name, size_t size, size_t align,
 	unsigned long flags,
-	void (*ctor)(void*, struct kmem_cache *, unsigned long),
-	void (*dtor)(void*, struct kmem_cache *, unsigned long))
+	void (*ctor)(void*, struct kmem_cache *, unsigned long))
 {
 	size_t left_over, slab_size, ralign;
 	struct kmem_cache *cachep = NULL, *pc;
@@ -2128,7 +2133,7 @@ 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)) {
+	    size > KMALLOC_MAX_SIZE) {
 		printk(KERN_ERR "%s: Early error in slab %s\n", __FUNCTION__,
 				name);
 		BUG();
@@ -2151,13 +2156,15 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		 */
 		res = probe_kernel_address(pc->name, tmp);
 		if (res) {
-			printk("SLAB: cache with size %d has lost its name\n",
+			printk(KERN_ERR
+			       "SLAB: cache with size %d has lost its name\n",
 			       pc->buffer_size);
 			continue;
 		}
 
 		if (!strcmp(pc->name, name)) {
-			printk("kmem_cache_create: duplicate cache %s\n", name);
+			printk(KERN_ERR
+			       "kmem_cache_create: duplicate cache %s\n", name);
 			dump_stack();
 			goto oops;
 		}
@@ -2165,12 +2172,6 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 
 #if DEBUG
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
-	if ((flags & SLAB_DEBUG_INITIAL) && !ctor) {
-		/* No constructor, but inital state check requested */
-		printk(KERN_ERR "%s: No con, but init state check "
-		       "requested - %s\n", __FUNCTION__, name);
-		flags &= ~SLAB_DEBUG_INITIAL;
-	}
 #if FORCED_DEBUG
 	/*
 	 * Enable redzoning and last user accounting, except for caches with
@@ -2178,7 +2179,8 @@ 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))
+	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
+						2 * sizeof(unsigned long long)))
 		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
 	if (!(flags & SLAB_DESTROY_BY_RCU))
 		flags |= SLAB_POISON;
@@ -2186,9 +2188,6 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	if (flags & SLAB_DESTROY_BY_RCU)
 		BUG_ON(flags & SLAB_POISON);
 #endif
-	if (flags & SLAB_DESTROY_BY_RCU)
-		BUG_ON(dtor);
-
 	/*
 	 * Always checks flags, a caller might be expecting debug support which
 	 * isn't available.
@@ -2222,13 +2221,21 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	}
 
 	/*
-	 * Redzoning and user store require word alignment. Note this will be
-	 * overridden by architecture or caller mandated alignment if either
-	 * is greater than BYTES_PER_WORD.
+	 * Redzoning and user store require word alignment or possibly larger.
+	 * Note this will be overridden by architecture or caller mandated
+	 * alignment if either is greater than BYTES_PER_WORD.
 	 */
-	if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
+	if (flags & SLAB_STORE_USER)
 		ralign = BYTES_PER_WORD;
 
+	if (flags & SLAB_RED_ZONE) {
+		ralign = REDZONE_ALIGN;
+		/* If redzoning, ensure that the second redzone is suitably
+		 * aligned, by adjusting the object size accordingly. */
+		size += REDZONE_ALIGN - 1;
+		size &= ~(REDZONE_ALIGN - 1);
+	}
+
 	/* 2) arch mandated alignment */
 	if (ralign < ARCH_SLAB_MINALIGN) {
 		ralign = ARCH_SLAB_MINALIGN;
@@ -2238,7 +2245,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		ralign = align;
 	}
 	/* disable debug if necessary */
-	if (ralign > BYTES_PER_WORD)
+	if (ralign > __alignof__(unsigned long long))
 		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	/*
 	 * 4) Store it.
@@ -2259,14 +2266,18 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 */
 	if (flags & SLAB_RED_ZONE) {
 		/* add space for red zone words */
-		cachep->obj_offset += BYTES_PER_WORD;
-		size += 2 * BYTES_PER_WORD;
+		cachep->obj_offset += sizeof(unsigned long long);
+		size += 2 * sizeof(unsigned long long);
 	}
 	if (flags & SLAB_STORE_USER) {
 		/* user store requires one word storage behind the end of
-		 * the real object.
+		 * the real object. But if the second red zone needs to be
+		 * aligned to 64 bits, we must allow that much space.
 		 */
-		size += BYTES_PER_WORD;
+		if (flags & SLAB_RED_ZONE)
+			size += REDZONE_ALIGN;
+		else
+			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
 	if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
@@ -2294,7 +2305,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	left_over = calculate_slab_order(cachep, size, align, flags);
 
 	if (!cachep->num) {
-		printk("kmem_cache_create: couldn't create cache %s.\n", name);
+		printk(KERN_ERR
+		       "kmem_cache_create: couldn't create cache %s.\n", name);
 		kmem_cache_free(&cache_cache, cachep);
 		cachep = NULL;
 		goto oops;
@@ -2339,10 +2351,9 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		 * this should not happen at all.
 		 * But leave a BUG_ON for some lucky dude.
 		 */
-		BUG_ON(!cachep->slabp_cache);
+		BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
 	}
 	cachep->ctor = ctor;
-	cachep->dtor = dtor;
 	cachep->name = name;
 
 	if (setup_cpu_cache(cachep)) {
@@ -2597,7 +2608,7 @@ static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp)
 }
 
 static void cache_init_objs(struct kmem_cache *cachep,
-			    struct slab *slabp, unsigned long ctor_flags)
+			    struct slab *slabp)
 {
 	int i;
 
@@ -2621,7 +2632,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		 */
 		if (cachep->ctor && !(cachep->flags & SLAB_POISON))
 			cachep->ctor(objp + obj_offset(cachep), cachep,
-				     ctor_flags);
+				     0);
 
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
@@ -2637,7 +2648,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 					 cachep->buffer_size / PAGE_SIZE, 0);
 #else
 		if (cachep->ctor)
-			cachep->ctor(objp, cachep, ctor_flags);
+			cachep->ctor(objp, cachep, 0);
 #endif
 		slab_bufctl(slabp)[i] = i + 1;
 	}
@@ -2726,26 +2737,15 @@ static int cache_grow(struct kmem_cache *cachep,
 	struct slab *slabp;
 	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().
 	 */
-	BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK | __GFP_NO_GROW));
-	if (flags & __GFP_NO_GROW)
-		return 0;
+	BUG_ON(flags & ~(GFP_DMA | __GFP_ZERO | GFP_LEVEL_MASK));
 
-	ctor_flags = SLAB_CTOR_CONSTRUCTOR;
 	local_flags = (flags & GFP_LEVEL_MASK);
-	if (!(local_flags & __GFP_WAIT))
-		/*
-		 * Not allowed to sleep.  Need to tell a constructor about
-		 * this - it might need to know...
-		 */
-		ctor_flags |= SLAB_CTOR_ATOMIC;
-
 	/* Take the l3 list lock to change the colour_next on this node */
 	check_irq_off();
 	l3 = cachep->nodelists[nodeid];
@@ -2776,7 +2776,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * 'nodeid'.
 	 */
 	if (!objp)
-		objp = kmem_getpages(cachep, flags, nodeid);
+		objp = kmem_getpages(cachep, local_flags, nodeid);
 	if (!objp)
 		goto failed;
 
@@ -2789,7 +2789,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	slabp->nodeid = nodeid;
 	slab_map_pages(cachep, slabp, objp);
 
-	cache_init_objs(cachep, slabp, ctor_flags);
+	cache_init_objs(cachep, slabp);
 
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
@@ -2816,7 +2816,6 @@ failed:
  * Perform extra freeing checks:
  * - detect bad pointers.
  * - POISON/RED_ZONE checking
- * - destructor calls, for caches with POISON+dtor
  */
 static void kfree_debugcheck(const void *objp)
 {
@@ -2829,7 +2828,7 @@ static void kfree_debugcheck(const void *objp)
 
 static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
 {
-	unsigned long redzone1, redzone2;
+	unsigned long long redzone1, redzone2;
 
 	redzone1 = *dbg_redzone1(cache, obj);
 	redzone2 = *dbg_redzone2(cache, obj);
@@ -2845,7 +2844,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
 	else
 		slab_error(cache, "memory outside object was overwritten");
 
-	printk(KERN_ERR "%p: redzone 1:0x%lx, redzone 2:0x%lx.\n",
+	printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n",
 			obj, redzone1, redzone2);
 }
 
@@ -2858,7 +2857,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 
 	objp -= obj_offset(cachep);
 	kfree_debugcheck(objp);
-	page = virt_to_page(objp);
+	page = virt_to_head_page(objp);
 
 	slabp = page_get_slab(page);
 
@@ -2875,21 +2874,6 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	BUG_ON(objnr >= cachep->num);
 	BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
 
-	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_offset(cachep),
-			     cachep, SLAB_CTOR_CONSTRUCTOR | SLAB_CTOR_VERIFY);
-	}
-	if (cachep->flags & SLAB_POISON && cachep->dtor) {
-		/* we want to cache poison the object,
-		 * call the destruction callback
-		 */
-		cachep->dtor(objp + obj_offset(cachep), cachep, 0);
-	}
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 	slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
 #endif
@@ -2987,6 +2971,14 @@ retry:
 		slabp = list_entry(entry, struct slab, list);
 		check_slabp(cachep, slabp);
 		check_spinlock_acquired(cachep);
+
+		/*
+		 * The slab was either on partial or free list so
+		 * there must be at least one object available for
+		 * allocation.
+		 */
+		BUG_ON(slabp->inuse < 0 || slabp->inuse >= cachep->num);
+
 		while (slabp->inuse < cachep->num && batchcount--) {
 			STATS_INC_ALLOCED(cachep);
 			STATS_INC_ACTIVE(cachep);
@@ -3062,7 +3054,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 			slab_error(cachep, "double free, or memory outside"
 						" object was overwritten");
 			printk(KERN_ERR
-				"%p: redzone 1:0x%lx, redzone 2:0x%lx\n",
+				"%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
 				objp, *dbg_redzone1(cachep, objp),
 				*dbg_redzone2(cachep, objp));
 		}
@@ -3074,20 +3066,14 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		struct slab *slabp;
 		unsigned objnr;
 
-		slabp = page_get_slab(virt_to_page(objp));
+		slabp = page_get_slab(virt_to_head_page(objp));
 		objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
 		slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
 	}
 #endif
 	objp += obj_offset(cachep);
-	if (cachep->ctor && cachep->flags & SLAB_POISON) {
-		unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
-
-		if (!(flags & __GFP_WAIT))
-			ctor_flags |= SLAB_CTOR_ATOMIC;
-
-		cachep->ctor(objp, cachep, ctor_flags);
-	}
+	if (cachep->ctor && cachep->flags & SLAB_POISON)
+		cachep->ctor(objp, cachep, 0);
 #if ARCH_SLAB_MINALIGN
 	if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) {
 		printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
@@ -3142,7 +3128,7 @@ static int __init failslab_debugfs(void)
 	struct dentry *dir;
 	int err;
 
-       	err = init_fault_attr_dentries(&failslab.attr, "failslab");
+	err = init_fault_attr_dentries(&failslab.attr, "failslab");
 	if (err)
 		return err;
 	dir = failslab.attr.dentries.dir;
@@ -3180,9 +3166,6 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 
 	check_irq_off();
 
-	if (should_failslab(cachep, flags))
-		return NULL;
-
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
 		STATS_INC_ALLOCHIT(cachep);
@@ -3256,7 +3239,7 @@ retry:
 					flags | GFP_THISNODE, nid);
 	}
 
-	if (!obj && !(flags & __GFP_NO_GROW)) {
+	if (!obj) {
 		/*
 		 * This allocation will be performed within the constraints
 		 * of the current cpuset / memory policy requirements.
@@ -3374,6 +3357,9 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 
+	if (should_failslab(cachep, flags))
+		return NULL;
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
@@ -3403,6 +3389,9 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	local_irq_restore(save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
 
+	if (unlikely((flags & __GFP_ZERO) && ptr))
+		memset(ptr, 0, obj_size(cachep));
+
 	return ptr;
 }
 
@@ -3444,6 +3433,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	unsigned long save_flags;
 	void *objp;
 
+	if (should_failslab(cachep, flags))
+		return NULL;
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 	objp = __do_cache_alloc(cachep, flags);
@@ -3451,6 +3443,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
 	prefetchw(objp);
 
+	if (unlikely((flags & __GFP_ZERO) && objp))
+		memset(objp, 0, obj_size(cachep));
+
 	return objp;
 }
 
@@ -3591,23 +3586,6 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
-/**
- * kmem_cache_zalloc - Allocate an object. The memory is set to zero.
- * @cache: The cache to allocate from.
- * @flags: See kmalloc().
- *
- * Allocate an object from this cache and set the allocated memory to zero.
- * The flags are only relevant if the cache has no available objects.
- */
-void *kmem_cache_zalloc(struct kmem_cache *cache, gfp_t flags)
-{
-	void *ret = __cache_alloc(cache, flags, __builtin_return_address(0));
-	if (ret)
-		memset(ret, 0, obj_size(cache));
-	return ret;
-}
-EXPORT_SYMBOL(kmem_cache_zalloc);
-
 /**
  * kmem_ptr_validate - check if an untrusted pointer might
  *	be a slab entry.
@@ -3664,8 +3642,8 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
 	struct kmem_cache *cachep;
 
 	cachep = kmem_find_general_cachep(size, flags);
-	if (unlikely(cachep == NULL))
-		return NULL;
+	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
+		return cachep;
 	return kmem_cache_alloc_node(cachep, flags, node);
 }
 
@@ -3709,8 +3687,8 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	 * functions.
 	 */
 	cachep = __find_general_cachep(size, flags);
-	if (unlikely(cachep == NULL))
-		return NULL;
+	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
+		return cachep;
 	return __cache_alloc(cachep, flags, caller);
 }
 
@@ -3771,7 +3749,7 @@ void kfree(const void *objp)
 	struct kmem_cache *c;
 	unsigned long flags;
 
-	if (unlikely(!objp))
+	if (unlikely(ZERO_OR_NULL_PTR(objp)))
 		return;
 	local_irq_save(flags);
 	kfree_debugcheck(objp);
@@ -3812,12 +3790,15 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
                                 goto fail;
                 }
 
-		new_shared = alloc_arraycache(node,
+		new_shared = NULL;
+		if (cachep->shared) {
+			new_shared = alloc_arraycache(node,
 				cachep->shared*cachep->batchcount,
 					0xbaadf00d);
-		if (!new_shared) {
-			free_alien_cache(new_alien);
-			goto fail;
+			if (!new_shared) {
+				free_alien_cache(new_alien);
+				goto fail;
+			}
 		}
 
 		l3 = cachep->nodelists[node];
@@ -3975,10 +3956,8 @@ static int enable_cpucache(struct kmem_cache *cachep)
 	 * to a larger limit. Thus disabled by default.
 	 */
 	shared = 0;
-#ifdef CONFIG_SMP
-	if (cachep->buffer_size <= PAGE_SIZE)
+	if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1)
 		shared = 8;
-#endif
 
 #if DEBUG
 	/*
@@ -4088,7 +4067,6 @@ next:
 	check_irq_on();
 	mutex_unlock(&cache_chain_mutex);
 	next_reap_node();
-	refresh_cpu_vm_stats(smp_processor_id());
 out:
 	/* Set up the next iteration */
 	schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
@@ -4122,26 +4100,17 @@ static void print_slabinfo_header(struct seq_file *m)
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
 	loff_t n = *pos;
-	struct list_head *p;
 
 	mutex_lock(&cache_chain_mutex);
 	if (!n)
 		print_slabinfo_header(m);
-	p = cache_chain.next;
-	while (n--) {
-		p = p->next;
-		if (p == &cache_chain)
-			return NULL;
-	}
-	return list_entry(p, struct kmem_cache, next);
+
+	return seq_list_start(&cache_chain, *pos);
 }
 
 static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 {
-	struct kmem_cache *cachep = p;
-	++*pos;
-	return cachep->next.next == &cache_chain ?
-		NULL : list_entry(cachep->next.next, struct kmem_cache, next);
+	return seq_list_next(p, &cache_chain, pos);
 }
 
 static void s_stop(struct seq_file *m, void *p)
@@ -4151,7 +4120,7 @@ static void s_stop(struct seq_file *m, void *p)
 
 static int s_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *cachep = p;
+	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
 	struct slab *slabp;
 	unsigned long active_objs;
 	unsigned long num_objs;
@@ -4320,17 +4289,8 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 
 static void *leaks_start(struct seq_file *m, loff_t *pos)
 {
-	loff_t n = *pos;
-	struct list_head *p;
-
 	mutex_lock(&cache_chain_mutex);
-	p = cache_chain.next;
-	while (n--) {
-		p = p->next;
-		if (p == &cache_chain)
-			return NULL;
-	}
-	return list_entry(p, struct kmem_cache, next);
+	return seq_list_start(&cache_chain, *pos);
 }
 
 static inline int add_caller(unsigned long *n, unsigned long v)
@@ -4380,16 +4340,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
 static void show_symbol(struct seq_file *m, unsigned long address)
 {
 #ifdef CONFIG_KALLSYMS
-	char *modname;
-	const char *name;
 	unsigned long offset, size;
-	char namebuf[KSYM_NAME_LEN+1];
-
-	name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+	char modname[MODULE_NAME_LEN], name[KSYM_NAME_LEN];
 
-	if (name) {
+	if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
 		seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
-		if (modname)
+		if (modname[0])
 			seq_printf(m, " [%s]", modname);
 		return;
 	}
@@ -4399,7 +4355,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 
 static int leaks_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *cachep = p;
+	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
 	struct slab *slabp;
 	struct kmem_list3 *l3;
 	const char *name;
@@ -4478,9 +4434,9 @@ const struct seq_operations slabstats_op = {
  * allocated with either kmalloc() or kmem_cache_alloc(). The object
  * must not be freed during the duration of the call.
  */
-unsigned int ksize(const void *objp)
+size_t ksize(const void *objp)
 {
-	if (unlikely(objp == NULL))
+	if (unlikely(ZERO_OR_NULL_PTR(objp)))
 		return 0;
 
 	return obj_size(virt_to_cache(objp));