diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300e..07375e7 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@
 	P		Poisoning (object and padding)
 	U		User tracking (free and alloc)
 	T		Trace (please only use on single slabs)
+	A		Toggle failslab filter mark for the cache
 	O		Switch debugging off for caches that would have
 			caused higher minimum slab orders
 	-		Switch all debugging off (useful if the kernel is
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 06ca9b2..7b64ad4 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -82,9 +82,10 @@
 #endif /* CONFIG_FAULT_INJECTION */
 
 #ifdef CONFIG_FAILSLAB
-extern bool should_failslab(size_t size, gfp_t gfpflags);
+extern bool should_failslab(size_t size, gfp_t gfpflags, unsigned long flags);
 #else
-static inline bool should_failslab(size_t size, gfp_t gfpflags)
+static inline bool should_failslab(size_t size, gfp_t gfpflags,
+				unsigned long flags)
 {
 	return false;
 }
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 2da8372..4884462 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -70,6 +70,11 @@
 #else
 # define SLAB_NOTRACK		0x00000000UL
 #endif
+#ifdef CONFIG_FAILSLAB
+# define SLAB_FAILSLAB		0x02000000UL	/* Fault injection mark */
+#else
+# define SLAB_FAILSLAB		0x00000000UL
+#endif
 
 /* The following flags affect the page allocator grouping pages by mobility */
 #define SLAB_RECLAIM_ACCOUNT	0x00020000UL		/* Objects are reclaimable */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 1e14beb..0249d41 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -38,8 +38,6 @@
 	void **freelist;	/* Pointer to first free per cpu object */
 	struct page *page;	/* The slab from which we are allocating */
 	int node;		/* The node of the page (or -1 for debug) */
-	unsigned int offset;	/* Freepointer offset (in word units) */
-	unsigned int objsize;	/* Size of an object (from kmem_cache) */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif
@@ -69,6 +67,7 @@
  * Slab cache management.
  */
 struct kmem_cache {
+	struct kmem_cache_cpu *cpu_slab;
 	/* Used for retriving partial slabs etc */
 	unsigned long flags;
 	int size;		/* The size of an object including meta data */
@@ -104,11 +103,6 @@
 	int remote_node_defrag_ratio;
 	struct kmem_cache_node *node[MAX_NUMNODES];
 #endif
-#ifdef CONFIG_SMP
-	struct kmem_cache_cpu *cpu_slab[NR_CPUS];
-#else
-	struct kmem_cache_cpu cpu_slab;
-#endif
 };
 
 /*
@@ -135,11 +129,21 @@
 
 #define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
 
+#ifdef CONFIG_ZONE_DMA
+#define SLUB_DMA __GFP_DMA
+/* Reserve extra caches for potential DMA use */
+#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6)
+#else
+/* Disable DMA functionality */
+#define SLUB_DMA (__force gfp_t)0
+#define KMALLOC_CACHES SLUB_PAGE_SHIFT
+#endif
+
 /*
  * 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[SLUB_PAGE_SHIFT];
+extern struct kmem_cache kmalloc_caches[KMALLOC_CACHES];
 
 /*
  * Sorry that the following has to be that ugly but some versions of GCC
@@ -207,13 +211,6 @@
 	return &kmalloc_caches[index];
 }
 
-#ifdef CONFIG_ZONE_DMA
-#define SLUB_DMA __GFP_DMA
-#else
-/* Disable DMA functionality */
-#define SLUB_DMA (__force gfp_t)0
-#endif
-
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
diff --git a/mm/failslab.c b/mm/failslab.c
index 9339de5..bb41f98 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -1,18 +1,22 @@
 #include <linux/fault-inject.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 
 static struct {
 	struct fault_attr attr;
 	u32 ignore_gfp_wait;
+	int cache_filter;
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 	struct dentry *ignore_gfp_wait_file;
+	struct dentry *cache_filter_file;
 #endif
 } failslab = {
 	.attr = FAULT_ATTR_INITIALIZER,
 	.ignore_gfp_wait = 1,
+	.cache_filter = 0,
 };
 
-bool should_failslab(size_t size, gfp_t gfpflags)
+bool should_failslab(size_t size, gfp_t gfpflags, unsigned long cache_flags)
 {
 	if (gfpflags & __GFP_NOFAIL)
 		return false;
@@ -20,6 +24,9 @@
         if (failslab.ignore_gfp_wait && (gfpflags & __GFP_WAIT))
 		return false;
 
+	if (failslab.cache_filter && !(cache_flags & SLAB_FAILSLAB))
+		return false;
+
 	return should_fail(&failslab.attr, size);
 }
 
@@ -30,7 +37,6 @@
 __setup("failslab=", setup_failslab);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-
 static int __init failslab_debugfs_init(void)
 {
 	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
@@ -46,8 +52,14 @@
 		debugfs_create_bool("ignore-gfp-wait", mode, dir,
 				      &failslab.ignore_gfp_wait);
 
-	if (!failslab.ignore_gfp_wait_file) {
+	failslab.cache_filter_file =
+		debugfs_create_bool("cache-filter", mode, dir,
+				      &failslab.cache_filter);
+
+	if (!failslab.ignore_gfp_wait_file ||
+	    !failslab.cache_filter_file) {
 		err = -ENOMEM;
+		debugfs_remove(failslab.cache_filter_file);
 		debugfs_remove(failslab.ignore_gfp_wait_file);
 		cleanup_fault_attr_dentries(&failslab.attr);
 	}
diff --git a/mm/slab.c b/mm/slab.c
index 7451bda..a9f325b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -935,7 +935,6 @@
 
 	from->avail -= nr;
 	to->avail += nr;
-	to->touched = 1;
 	return nr;
 }
 
@@ -983,13 +982,11 @@
 
 	if (limit > 1)
 		limit = 12;
-	ac_ptr = kmalloc_node(memsize, gfp, node);
+	ac_ptr = kzalloc_node(memsize, gfp, node);
 	if (ac_ptr) {
 		for_each_node(i) {
-			if (i == node || !node_online(i)) {
-				ac_ptr[i] = NULL;
+			if (i == node || !node_online(i))
 				continue;
-			}
 			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d, gfp);
 			if (!ac_ptr[i]) {
 				for (i--; i >= 0; i--)
@@ -2963,8 +2960,10 @@
 	spin_lock(&l3->list_lock);
 
 	/* See if we can refill from the shared array */
-	if (l3->shared && transfer_objects(ac, l3->shared, batchcount))
+	if (l3->shared && transfer_objects(ac, l3->shared, batchcount)) {
+		l3->shared->touched = 1;
 		goto alloc_done;
+	}
 
 	while (batchcount > 0) {
 		struct list_head *entry;
@@ -3101,7 +3100,7 @@
 	if (cachep == &cache_cache)
 		return false;
 
-	return should_failslab(obj_size(cachep), flags);
+	return should_failslab(obj_size(cachep), flags, cachep->flags);
 }
 
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
diff --git a/mm/slub.c b/mm/slub.c
index 8d71aaf..3525a4e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -151,7 +151,8 @@
  * Set of flags that will prevent slab merging
  */
 #define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
-		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE)
+		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
+		SLAB_FAILSLAB)
 
 #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
 		SLAB_CACHE_DMA | SLAB_NOTRACK)
@@ -217,10 +218,10 @@
 
 #endif
 
-static inline void stat(struct kmem_cache_cpu *c, enum stat_item si)
+static inline void stat(struct kmem_cache *s, enum stat_item si)
 {
 #ifdef CONFIG_SLUB_STATS
-	c->stat[si]++;
+	__this_cpu_inc(s->cpu_slab->stat[si]);
 #endif
 }
 
@@ -242,15 +243,6 @@
 #endif
 }
 
-static inline struct kmem_cache_cpu *get_cpu_slab(struct kmem_cache *s, int cpu)
-{
-#ifdef CONFIG_SMP
-	return s->cpu_slab[cpu];
-#else
-	return &s->cpu_slab;
-#endif
-}
-
 /* Verify that a pointer has an address that is valid within a slab page */
 static inline int check_valid_pointer(struct kmem_cache *s,
 				struct page *page, const void *object)
@@ -269,13 +261,6 @@
 	return 1;
 }
 
-/*
- * Slow version of get and set free pointer.
- *
- * This version requires touching the cache lines of kmem_cache which
- * we avoid to do in the fast alloc free paths. There we obtain the offset
- * from the page struct.
- */
 static inline void *get_freepointer(struct kmem_cache *s, void *object)
 {
 	return *(void **)(object + s->offset);
@@ -1020,6 +1005,9 @@
 		case 't':
 			slub_debug |= SLAB_TRACE;
 			break;
+		case 'a':
+			slub_debug |= SLAB_FAILSLAB;
+			break;
 		default:
 			printk(KERN_ERR "slub_debug option '%c' "
 				"unknown. skipped\n", *str);
@@ -1124,7 +1112,7 @@
 		if (!page)
 			return NULL;
 
-		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+		stat(s, ORDER_FALLBACK);
 	}
 
 	if (kmemcheck_enabled
@@ -1422,23 +1410,22 @@
 static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-	struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id());
 
 	__ClearPageSlubFrozen(page);
 	if (page->inuse) {
 
 		if (page->freelist) {
 			add_partial(n, page, tail);
-			stat(c, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
+			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
 		} else {
-			stat(c, DEACTIVATE_FULL);
+			stat(s, DEACTIVATE_FULL);
 			if (SLABDEBUG && PageSlubDebug(page) &&
 						(s->flags & SLAB_STORE_USER))
 				add_full(n, page);
 		}
 		slab_unlock(page);
 	} else {
-		stat(c, DEACTIVATE_EMPTY);
+		stat(s, DEACTIVATE_EMPTY);
 		if (n->nr_partial < s->min_partial) {
 			/*
 			 * Adding an empty slab to the partial slabs in order
@@ -1454,7 +1441,7 @@
 			slab_unlock(page);
 		} else {
 			slab_unlock(page);
-			stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB);
+			stat(s, FREE_SLAB);
 			discard_slab(s, page);
 		}
 	}
@@ -1469,7 +1456,7 @@
 	int tail = 1;
 
 	if (page->freelist)
-		stat(c, DEACTIVATE_REMOTE_FREES);
+		stat(s, DEACTIVATE_REMOTE_FREES);
 	/*
 	 * Merge cpu freelist into slab freelist. Typically we get here
 	 * because both freelists are empty. So this is unlikely
@@ -1482,10 +1469,10 @@
 
 		/* Retrieve object from cpu_freelist */
 		object = c->freelist;
-		c->freelist = c->freelist[c->offset];
+		c->freelist = get_freepointer(s, c->freelist);
 
 		/* And put onto the regular freelist */
-		object[c->offset] = page->freelist;
+		set_freepointer(s, object, page->freelist);
 		page->freelist = object;
 		page->inuse--;
 	}
@@ -1495,7 +1482,7 @@
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
-	stat(c, CPUSLAB_FLUSH);
+	stat(s, CPUSLAB_FLUSH);
 	slab_lock(c->page);
 	deactivate_slab(s, c);
 }
@@ -1507,7 +1494,7 @@
  */
 static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 {
-	struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
 	if (likely(c && c->page))
 		flush_slab(s, c);
@@ -1635,7 +1622,7 @@
 	if (unlikely(!node_match(c, node)))
 		goto another_slab;
 
-	stat(c, ALLOC_REFILL);
+	stat(s, ALLOC_REFILL);
 
 load_freelist:
 	object = c->page->freelist;
@@ -1644,13 +1631,13 @@
 	if (unlikely(SLABDEBUG && PageSlubDebug(c->page)))
 		goto debug;
 
-	c->freelist = object[c->offset];
+	c->freelist = get_freepointer(s, object);
 	c->page->inuse = c->page->objects;
 	c->page->freelist = NULL;
 	c->node = page_to_nid(c->page);
 unlock_out:
 	slab_unlock(c->page);
-	stat(c, ALLOC_SLOWPATH);
+	stat(s, ALLOC_SLOWPATH);
 	return object;
 
 another_slab:
@@ -1660,7 +1647,7 @@
 	new = get_partial(s, gfpflags, node);
 	if (new) {
 		c->page = new;
-		stat(c, ALLOC_FROM_PARTIAL);
+		stat(s, ALLOC_FROM_PARTIAL);
 		goto load_freelist;
 	}
 
@@ -1673,8 +1660,8 @@
 		local_irq_disable();
 
 	if (new) {
-		c = get_cpu_slab(s, smp_processor_id());
-		stat(c, ALLOC_SLAB);
+		c = __this_cpu_ptr(s->cpu_slab);
+		stat(s, ALLOC_SLAB);
 		if (c->page)
 			flush_slab(s, c);
 		slab_lock(new);
@@ -1690,7 +1677,7 @@
 		goto another_slab;
 
 	c->page->inuse++;
-	c->page->freelist = object[c->offset];
+	c->page->freelist = get_freepointer(s, object);
 	c->node = -1;
 	goto unlock_out;
 }
@@ -1711,35 +1698,33 @@
 	void **object;
 	struct kmem_cache_cpu *c;
 	unsigned long flags;
-	unsigned int objsize;
 
 	gfpflags &= gfp_allowed_mask;
 
 	lockdep_trace_alloc(gfpflags);
 	might_sleep_if(gfpflags & __GFP_WAIT);
 
-	if (should_failslab(s->objsize, gfpflags))
+	if (should_failslab(s->objsize, gfpflags, s->flags))
 		return NULL;
 
 	local_irq_save(flags);
-	c = get_cpu_slab(s, smp_processor_id());
-	objsize = c->objsize;
-	if (unlikely(!c->freelist || !node_match(c, node)))
+	c = __this_cpu_ptr(s->cpu_slab);
+	object = c->freelist;
+	if (unlikely(!object || !node_match(c, node)))
 
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
-		object = c->freelist;
-		c->freelist = object[c->offset];
-		stat(c, ALLOC_FASTPATH);
+		c->freelist = get_freepointer(s, object);
+		stat(s, ALLOC_FASTPATH);
 	}
 	local_irq_restore(flags);
 
 	if (unlikely(gfpflags & __GFP_ZERO) && object)
-		memset(object, 0, objsize);
+		memset(object, 0, s->objsize);
 
-	kmemcheck_slab_alloc(s, gfpflags, object, c->objsize);
-	kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags);
+	kmemcheck_slab_alloc(s, gfpflags, object, s->objsize);
+	kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, gfpflags);
 
 	return object;
 }
@@ -1794,26 +1779,25 @@
  * handling required then we can return immediately.
  */
 static void __slab_free(struct kmem_cache *s, struct page *page,
-			void *x, unsigned long addr, unsigned int offset)
+			void *x, unsigned long addr)
 {
 	void *prior;
 	void **object = (void *)x;
-	struct kmem_cache_cpu *c;
 
-	c = get_cpu_slab(s, raw_smp_processor_id());
-	stat(c, FREE_SLOWPATH);
+	stat(s, FREE_SLOWPATH);
 	slab_lock(page);
 
 	if (unlikely(SLABDEBUG && PageSlubDebug(page)))
 		goto debug;
 
 checks_ok:
-	prior = object[offset] = page->freelist;
+	prior = page->freelist;
+	set_freepointer(s, object, prior);
 	page->freelist = object;
 	page->inuse--;
 
 	if (unlikely(PageSlubFrozen(page))) {
-		stat(c, FREE_FROZEN);
+		stat(s, FREE_FROZEN);
 		goto out_unlock;
 	}
 
@@ -1826,7 +1810,7 @@
 	 */
 	if (unlikely(!prior)) {
 		add_partial(get_node(s, page_to_nid(page)), page, 1);
-		stat(c, FREE_ADD_PARTIAL);
+		stat(s, FREE_ADD_PARTIAL);
 	}
 
 out_unlock:
@@ -1839,10 +1823,10 @@
 		 * Slab still on the partial list.
 		 */
 		remove_partial(s, page);
-		stat(c, FREE_REMOVE_PARTIAL);
+		stat(s, FREE_REMOVE_PARTIAL);
 	}
 	slab_unlock(page);
-	stat(c, FREE_SLAB);
+	stat(s, FREE_SLAB);
 	discard_slab(s, page);
 	return;
 
@@ -1872,17 +1856,17 @@
 
 	kmemleak_free_recursive(x, s->flags);
 	local_irq_save(flags);
-	c = get_cpu_slab(s, smp_processor_id());
-	kmemcheck_slab_free(s, object, c->objsize);
-	debug_check_no_locks_freed(object, c->objsize);
+	c = __this_cpu_ptr(s->cpu_slab);
+	kmemcheck_slab_free(s, object, s->objsize);
+	debug_check_no_locks_freed(object, s->objsize);
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(object, c->objsize);
+		debug_check_no_obj_freed(object, s->objsize);
 	if (likely(page == c->page && c->node >= 0)) {
-		object[c->offset] = c->freelist;
+		set_freepointer(s, object, c->freelist);
 		c->freelist = object;
-		stat(c, FREE_FASTPATH);
+		stat(s, FREE_FASTPATH);
 	} else
-		__slab_free(s, page, x, addr, c->offset);
+		__slab_free(s, page, x, addr);
 
 	local_irq_restore(flags);
 }
@@ -2069,19 +2053,6 @@
 	return ALIGN(align, sizeof(void *));
 }
 
-static void init_kmem_cache_cpu(struct kmem_cache *s,
-			struct kmem_cache_cpu *c)
-{
-	c->page = NULL;
-	c->freelist = NULL;
-	c->node = 0;
-	c->offset = s->offset / sizeof(void *);
-	c->objsize = s->objsize;
-#ifdef CONFIG_SLUB_STATS
-	memset(c->stat, 0, NR_SLUB_STAT_ITEMS * sizeof(unsigned));
-#endif
-}
-
 static void
 init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 {
@@ -2095,130 +2066,24 @@
 #endif
 }
 
-#ifdef CONFIG_SMP
-/*
- * Per cpu array for per cpu structures.
- *
- * The per cpu array places all kmem_cache_cpu structures from one processor
- * close together meaning that it becomes possible that multiple per cpu
- * structures are contained in one cacheline. This may be particularly
- * beneficial for the kmalloc caches.
- *
- * A desktop system typically has around 60-80 slabs. With 100 here we are
- * likely able to get per cpu structures for all caches from the array defined
- * here. We must be able to cover all kmalloc caches during bootstrap.
- *
- * If the per cpu array is exhausted then fall back to kmalloc
- * of individual cachelines. No sharing is possible then.
- */
-#define NR_KMEM_CACHE_CPU 100
-
-static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU],
-		      kmem_cache_cpu);
-
-static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
-static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
-
-static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
-							int cpu, gfp_t flags)
-{
-	struct kmem_cache_cpu *c = per_cpu(kmem_cache_cpu_free, cpu);
-
-	if (c)
-		per_cpu(kmem_cache_cpu_free, cpu) =
-				(void *)c->freelist;
-	else {
-		/* Table overflow: So allocate ourselves */
-		c = kmalloc_node(
-			ALIGN(sizeof(struct kmem_cache_cpu), cache_line_size()),
-			flags, cpu_to_node(cpu));
-		if (!c)
-			return NULL;
-	}
-
-	init_kmem_cache_cpu(s, c);
-	return c;
-}
-
-static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu)
-{
-	if (c < per_cpu(kmem_cache_cpu, cpu) ||
-			c >= per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
-		kfree(c);
-		return;
-	}
-	c->freelist = (void *)per_cpu(kmem_cache_cpu_free, cpu);
-	per_cpu(kmem_cache_cpu_free, cpu) = c;
-}
-
-static void free_kmem_cache_cpus(struct kmem_cache *s)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
-		if (c) {
-			s->cpu_slab[cpu] = NULL;
-			free_kmem_cache_cpu(c, cpu);
-		}
-	}
-}
-
-static int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
-		if (c)
-			continue;
-
-		c = alloc_kmem_cache_cpu(s, cpu, flags);
-		if (!c) {
-			free_kmem_cache_cpus(s);
-			return 0;
-		}
-		s->cpu_slab[cpu] = c;
-	}
-	return 1;
-}
-
-/*
- * Initialize the per cpu array.
- */
-static void init_alloc_cpu_cpu(int cpu)
-{
-	int i;
-
-	if (cpumask_test_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once)))
-		return;
-
-	for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--)
-		free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu);
-
-	cpumask_set_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once));
-}
-
-static void __init init_alloc_cpu(void)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		init_alloc_cpu_cpu(cpu);
-  }
-
-#else
-static inline void free_kmem_cache_cpus(struct kmem_cache *s) {}
-static inline void init_alloc_cpu(void) {}
+static DEFINE_PER_CPU(struct kmem_cache_cpu, kmalloc_percpu[KMALLOC_CACHES]);
 
 static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
 {
-	init_kmem_cache_cpu(s, &s->cpu_slab);
+	if (s < kmalloc_caches + KMALLOC_CACHES && s >= kmalloc_caches)
+		/*
+		 * Boot time creation of the kmalloc array. Use static per cpu data
+		 * since the per cpu allocator is not available yet.
+		 */
+		s->cpu_slab = per_cpu_var(kmalloc_percpu) + (s - kmalloc_caches);
+	else
+		s->cpu_slab =  alloc_percpu(struct kmem_cache_cpu);
+
+	if (!s->cpu_slab)
+		return 0;
+
 	return 1;
 }
-#endif
 
 #ifdef CONFIG_NUMA
 /*
@@ -2287,7 +2152,8 @@
 	int node;
 	int local_node;
 
-	if (slab_state >= UP)
+	if (slab_state >= UP && (s < kmalloc_caches ||
+			s > kmalloc_caches + KMALLOC_CACHES))
 		local_node = page_to_nid(virt_to_page(s));
 	else
 		local_node = 0;
@@ -2502,6 +2368,7 @@
 
 	if (alloc_kmem_cache_cpus(s, gfpflags & ~SLUB_DMA))
 		return 1;
+
 	free_kmem_cache_nodes(s);
 error:
 	if (flags & SLAB_PANIC)
@@ -2609,9 +2476,8 @@
 	int node;
 
 	flush_all(s);
-
+	free_percpu(s->cpu_slab);
 	/* Attempt to free all objects */
-	free_kmem_cache_cpus(s);
 	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
@@ -2651,7 +2517,7 @@
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[KMALLOC_CACHES] __cacheline_aligned;
 EXPORT_SYMBOL(kmalloc_caches);
 
 static int __init setup_slub_min_order(char *str)
@@ -2741,6 +2607,7 @@
 	char *text;
 	size_t realsize;
 	unsigned long slabflags;
+	int i;
 
 	s = kmalloc_caches_dma[index];
 	if (s)
@@ -2760,7 +2627,14 @@
 	realsize = kmalloc_caches[index].objsize;
 	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
 			 (unsigned int)realsize);
-	s = kmalloc(kmem_size, flags & ~SLUB_DMA);
+
+	s = NULL;
+	for (i = 0; i < KMALLOC_CACHES; i++)
+		if (!kmalloc_caches[i].size)
+			break;
+
+	BUG_ON(i >= KMALLOC_CACHES);
+	s = kmalloc_caches + i;
 
 	/*
 	 * Must defer sysfs creation to a workqueue because we don't know
@@ -2772,9 +2646,9 @@
 	if (slab_state >= SYSFS)
 		slabflags |= __SYSFS_ADD_DEFERRED;
 
-	if (!s || !text || !kmem_cache_open(s, flags, text,
+	if (!text || !kmem_cache_open(s, flags, text,
 			realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) {
-		kfree(s);
+		s->size = 0;
 		kfree(text);
 		goto unlock_out;
 	}
@@ -3176,8 +3050,6 @@
 	int i;
 	int caches = 0;
 
-	init_alloc_cpu();
-
 #ifdef CONFIG_NUMA
 	/*
 	 * Must first have the slab cache available for the allocations of the
@@ -3261,8 +3133,10 @@
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
-	kmem_size = offsetof(struct kmem_cache, cpu_slab) +
-				nr_cpu_ids * sizeof(struct kmem_cache_cpu *);
+#endif
+#ifdef CONFIG_NUMA
+	kmem_size = offsetof(struct kmem_cache, node) +
+				nr_node_ids * sizeof(struct kmem_cache_node *);
 #else
 	kmem_size = sizeof(struct kmem_cache);
 #endif
@@ -3351,22 +3225,12 @@
 	down_write(&slub_lock);
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
-		int cpu;
-
 		s->refcount++;
 		/*
 		 * Adjust the object sizes so that we clear
 		 * the complete object on kzalloc.
 		 */
 		s->objsize = max(s->objsize, (int)size);
-
-		/*
-		 * And then we need to update the object size in the
-		 * per cpu structures
-		 */
-		for_each_online_cpu(cpu)
-			get_cpu_slab(s, cpu)->objsize = s->objsize;
-
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 		up_write(&slub_lock);
 
@@ -3420,29 +3284,15 @@
 	unsigned long flags;
 
 	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		init_alloc_cpu_cpu(cpu);
-		down_read(&slub_lock);
-		list_for_each_entry(s, &slab_caches, list)
-			s->cpu_slab[cpu] = alloc_kmem_cache_cpu(s, cpu,
-							GFP_KERNEL);
-		up_read(&slub_lock);
-		break;
-
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		down_read(&slub_lock);
 		list_for_each_entry(s, &slab_caches, list) {
-			struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
 			local_irq_save(flags);
 			__flush_cpu_slab(s, cpu);
 			local_irq_restore(flags);
-			free_kmem_cache_cpu(c, cpu);
-			s->cpu_slab[cpu] = NULL;
 		}
 		up_read(&slub_lock);
 		break;
@@ -3928,7 +3778,7 @@
 		int cpu;
 
 		for_each_possible_cpu(cpu) {
-			struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
 			if (!c || c->node < 0)
 				continue;
@@ -4171,6 +4021,23 @@
 }
 SLAB_ATTR(trace);
 
+#ifdef CONFIG_FAILSLAB
+static ssize_t failslab_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB));
+}
+
+static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
+							size_t length)
+{
+	s->flags &= ~SLAB_FAILSLAB;
+	if (buf[0] == '1')
+		s->flags |= SLAB_FAILSLAB;
+	return length;
+}
+SLAB_ATTR(failslab);
+#endif
+
 static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
 {
 	return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
@@ -4353,7 +4220,7 @@
 		return -ENOMEM;
 
 	for_each_online_cpu(cpu) {
-		unsigned x = get_cpu_slab(s, cpu)->stat[si];
+		unsigned x = per_cpu_ptr(s->cpu_slab, cpu)->stat[si];
 
 		data[cpu] = x;
 		sum += x;
@@ -4376,7 +4243,7 @@
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		get_cpu_slab(s, cpu)->stat[si] = 0;
+		per_cpu_ptr(s->cpu_slab, cpu)->stat[si] = 0;
 }
 
 #define STAT_ATTR(si, text) 					\
@@ -4467,6 +4334,10 @@
 	&deactivate_remote_frees_attr.attr,
 	&order_fallback_attr.attr,
 #endif
+#ifdef CONFIG_FAILSLAB
+	&failslab_attr.attr,
+#endif
+
 	NULL
 };