X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=mm%2Fslab.c;h=add05d808a4a6fe96823cf3a5899d1c9a5a3f95b;hb=a00428f5b149e36b8225b2a0812742a6dfb07b8c;hp=33aab345cd4a0fddbd0c20b5763cfe9aae194162;hpb=977127174a7dff52d17faeeb4c4949a54221881f;p=linux-2.6-omap-h63xx.git

diff --git a/mm/slab.c b/mm/slab.c
index 33aab345cd4..add05d808a4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -55,7 +55,7 @@
  *
  * SMP synchronization:
  *  constructors and destructors are called without any locking.
- *  Several members in kmem_cache_t and struct slab never change, they
+ *  Several members in struct kmem_cache and struct slab never change, they
  *	are accessed without any locking.
  *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
  *  	and local interrupts are disabled so slab code is preempt-safe.
@@ -68,7 +68,7 @@
  * Further notes from the original documentation:
  *
  * 11 April '97.  Started multi-threading - markhe
- *	The global cache-chain is protected by the semaphore 'cache_chain_sem'.
+ *	The global cache-chain is protected by the mutex 'cache_chain_mutex'.
  *	The sem is only needed when accessing/extending the cache-chain, which
  *	can never happen inside an interrupt (kmem_cache_create(),
  *	kmem_cache_shrink() and kmem_cache_reap()).
@@ -103,6 +103,8 @@
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
 #include	<linux/nodemask.h>
+#include	<linux/mempolicy.h>
+#include	<linux/mutex.h>
 
 #include	<asm/uaccess.h>
 #include	<asm/cacheflush.h>
@@ -242,7 +244,7 @@ struct slab {
  */
 struct slab_rcu {
 	struct rcu_head head;
-	kmem_cache_t *cachep;
+	struct kmem_cache *cachep;
 	void *addr;
 };
 
@@ -292,6 +294,7 @@ struct kmem_list3 {
 	unsigned long next_reap;
 	int free_touched;
 	unsigned int free_limit;
+	unsigned int colour_next;	/* Per-node cache coloring */
 	spinlock_t list_lock;
 	struct array_cache *shared;	/* shared per node */
 	struct array_cache **alien;	/* on other nodes */
@@ -314,6 +317,8 @@ struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
  */
 static __always_inline int index_of(const size_t size)
 {
+	extern void __bad_size(void);
+
 	if (__builtin_constant_p(size)) {
 		int i = 0;
 
@@ -324,25 +329,23 @@ static __always_inline int index_of(const size_t size)
 		i++;
 #include "linux/kmalloc_sizes.h"
 #undef CACHE
-		{
-			extern void __bad_size(void);
-			__bad_size();
-		}
+		__bad_size();
 	} else
-		BUG();
+		__bad_size();
 	return 0;
 }
 
 #define INDEX_AC index_of(sizeof(struct arraycache_init))
 #define INDEX_L3 index_of(sizeof(struct kmem_list3))
 
-static inline void kmem_list3_init(struct kmem_list3 *parent)
+static void kmem_list3_init(struct kmem_list3 *parent)
 {
 	INIT_LIST_HEAD(&parent->slabs_full);
 	INIT_LIST_HEAD(&parent->slabs_partial);
 	INIT_LIST_HEAD(&parent->slabs_free);
 	parent->shared = NULL;
 	parent->alien = NULL;
+	parent->colour_next = 0;
 	spin_lock_init(&parent->list_lock);
 	parent->free_objects = 0;
 	parent->free_touched = 0;
@@ -362,7 +365,7 @@ static inline void kmem_list3_init(struct kmem_list3 *parent)
 	} while (0)
 
 /*
- * kmem_cache_t
+ * struct kmem_cache
  *
  * manages a cache.
  */
@@ -373,7 +376,7 @@ struct kmem_cache {
 	unsigned int batchcount;
 	unsigned int limit;
 	unsigned int shared;
-	unsigned int objsize;
+	unsigned int buffer_size;
 /* 2) touched by every alloc & free from the backend */
 	struct kmem_list3 *nodelists[MAX_NUMNODES];
 	unsigned int flags;	/* constant flags */
@@ -389,16 +392,15 @@ struct kmem_cache {
 
 	size_t colour;		/* cache colouring range */
 	unsigned int colour_off;	/* colour offset */
-	unsigned int colour_next;	/* cache colouring */
-	kmem_cache_t *slabp_cache;
+	struct kmem_cache *slabp_cache;
 	unsigned int slab_size;
 	unsigned int dflags;	/* dynamic flags */
 
 	/* constructor func */
-	void (*ctor) (void *, kmem_cache_t *, unsigned long);
+	void (*ctor) (void *, struct kmem_cache *, unsigned long);
 
 	/* de-constructor func */
-	void (*dtor) (void *, kmem_cache_t *, unsigned long);
+	void (*dtor) (void *, struct kmem_cache *, unsigned long);
 
 /* 4) cache creation/removal */
 	const char *name;
@@ -421,8 +423,14 @@ struct kmem_cache {
 	atomic_t freemiss;
 #endif
 #if DEBUG
-	int dbghead;
-	int reallen;
+	/*
+	 * If debugging is enabled, then the allocator can add additional
+	 * fields and/or padding to every object. buffer_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
 };
 
@@ -493,50 +501,50 @@ struct kmem_cache {
 
 /* memory layout of objects:
  * 0		: objp
- * 0 .. cachep->dbghead - BYTES_PER_WORD - 1: padding. This ensures that
+ * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
  * 		the end of an object is aligned with the end of the real
  * 		allocation. Catches writes behind the end of the allocation.
- * cachep->dbghead - BYTES_PER_WORD .. cachep->dbghead - 1:
+ * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
  * 		redzone word.
- * cachep->dbghead: The real object.
- * cachep->objsize - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->objsize - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long]
+ * 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 [BYTES_PER_WORD long]
  */
-static int obj_dbghead(kmem_cache_t *cachep)
+static int obj_offset(struct kmem_cache *cachep)
 {
-	return cachep->dbghead;
+	return cachep->obj_offset;
 }
 
-static int obj_reallen(kmem_cache_t *cachep)
+static int obj_size(struct kmem_cache *cachep)
 {
-	return cachep->reallen;
+	return cachep->obj_size;
 }
 
-static unsigned long *dbg_redzone1(kmem_cache_t *cachep, void *objp)
+static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
 {
 	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long*) (objp+obj_dbghead(cachep)-BYTES_PER_WORD);
+	return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD);
 }
 
-static unsigned long *dbg_redzone2(kmem_cache_t *cachep, void *objp)
+static unsigned 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->objsize -
+		return (unsigned long *)(objp + cachep->buffer_size -
 					 2 * BYTES_PER_WORD);
-	return (unsigned long *)(objp + cachep->objsize - BYTES_PER_WORD);
+	return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD);
 }
 
-static void **dbg_userword(kmem_cache_t *cachep, void *objp)
+static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 {
 	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
-	return (void **)(objp + cachep->objsize - BYTES_PER_WORD);
+	return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD);
 }
 
 #else
 
-#define obj_dbghead(x)			0
-#define obj_reallen(cachep)		(cachep->objsize)
+#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_userword(cachep, objp)	({BUG(); (void **)NULL;})
@@ -589,6 +597,18 @@ static inline struct slab *page_get_slab(struct page *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);
+	return page_get_cache(page);
+}
+
+static inline struct slab *virt_to_slab(const void *obj)
+{
+	struct page *page = virt_to_page(obj);
+	return page_get_slab(page);
+}
+
 /* These are the default caches for kmalloc. Custom caches can have other sizes. */
 struct cache_sizes malloc_sizes[] = {
 #define CACHE(x) { .cs_size = (x) },
@@ -617,21 +637,21 @@ static struct arraycache_init initarray_generic =
     { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
 
 /* internal cache of cache description objs */
-static kmem_cache_t cache_cache = {
+static struct kmem_cache cache_cache = {
 	.batchcount = 1,
 	.limit = BOOT_CPUCACHE_ENTRIES,
 	.shared = 1,
-	.objsize = sizeof(kmem_cache_t),
+	.buffer_size = sizeof(struct kmem_cache),
 	.flags = SLAB_NO_REAP,
 	.spinlock = SPIN_LOCK_UNLOCKED,
 	.name = "kmem_cache",
 #if DEBUG
-	.reallen = sizeof(kmem_cache_t),
+	.obj_size = sizeof(struct kmem_cache),
 #endif
 };
 
 /* Guard access to the cache-chain. */
-static struct semaphore cache_chain_sem;
+static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
 /*
@@ -655,17 +675,17 @@ static enum {
 
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
-static void free_block(kmem_cache_t *cachep, void **objpp, int len, int node);
-static void enable_cpucache(kmem_cache_t *cachep);
+static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node);
+static void enable_cpucache(struct kmem_cache *cachep);
 static void cache_reap(void *unused);
-static int __node_shrink(kmem_cache_t *cachep, int node);
+static int __node_shrink(struct kmem_cache *cachep, int node);
 
-static inline struct array_cache *ac_data(kmem_cache_t *cachep)
+static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
 	return cachep->array[smp_processor_id()];
 }
 
-static inline kmem_cache_t *__find_general_cachep(size_t size, gfp_t gfpflags)
+static inline struct kmem_cache *__find_general_cachep(size_t size, gfp_t gfpflags)
 {
 	struct cache_sizes *csizep = malloc_sizes;
 
@@ -689,43 +709,80 @@ static inline kmem_cache_t *__find_general_cachep(size_t size, gfp_t gfpflags)
 	return csizep->cs_cachep;
 }
 
-kmem_cache_t *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
+struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
 {
 	return __find_general_cachep(size, gfpflags);
 }
 EXPORT_SYMBOL(kmem_find_general_cachep);
 
-/* Cal the num objs, wastage, and bytes left over for a given slab size. */
-static void cache_estimate(unsigned long gfporder, size_t size, size_t align,
-			   int flags, size_t *left_over, unsigned int *num)
+static size_t slab_mgmt_size(size_t nr_objs, size_t align)
 {
-	int i;
-	size_t wastage = PAGE_SIZE << gfporder;
-	size_t extra = 0;
-	size_t base = 0;
+	return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
+}
 
-	if (!(flags & CFLGS_OFF_SLAB)) {
-		base = sizeof(struct slab);
-		extra = sizeof(kmem_bufctl_t);
-	}
-	i = 0;
-	while (i * size + ALIGN(base + i * extra, align) <= wastage)
-		i++;
-	if (i > 0)
-		i--;
+/* Calculate the number of objects and left-over bytes for a given
+   buffer size. */
+static void cache_estimate(unsigned long gfporder, size_t buffer_size,
+			   size_t align, int flags, size_t *left_over,
+			   unsigned int *num)
+{
+	int nr_objs;
+	size_t mgmt_size;
+	size_t slab_size = PAGE_SIZE << gfporder;
+
+	/*
+	 * The slab management structure can be either off the slab or
+	 * on it. For the latter case, the memory allocated for a
+	 * slab is used for:
+	 *
+	 * - The struct slab
+	 * - One kmem_bufctl_t for each object
+	 * - Padding to respect alignment of @align
+	 * - @buffer_size bytes for each object
+	 *
+	 * If the slab management structure is off the slab, then the
+	 * alignment will already be calculated into the size. Because
+	 * the slabs are all pages aligned, the objects will be at the
+	 * correct alignment when allocated.
+	 */
+	if (flags & CFLGS_OFF_SLAB) {
+		mgmt_size = 0;
+		nr_objs = slab_size / buffer_size;
+
+		if (nr_objs > SLAB_LIMIT)
+			nr_objs = SLAB_LIMIT;
+	} else {
+		/*
+		 * Ignore padding for the initial guess. The padding
+		 * is at most @align-1 bytes, and @buffer_size is at
+		 * least @align. In the worst case, this result will
+		 * be one greater than the number of objects that fit
+		 * into the memory allocation when taking the padding
+		 * into account.
+		 */
+		nr_objs = (slab_size - sizeof(struct slab)) /
+			  (buffer_size + sizeof(kmem_bufctl_t));
+
+		/*
+		 * This calculated number will be either the right
+		 * amount, or one greater than what we want.
+		 */
+		if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size
+		       > slab_size)
+			nr_objs--;
 
-	if (i > SLAB_LIMIT)
-		i = SLAB_LIMIT;
+		if (nr_objs > SLAB_LIMIT)
+			nr_objs = SLAB_LIMIT;
 
-	*num = i;
-	wastage -= i * size;
-	wastage -= ALIGN(base + i * extra, align);
-	*left_over = wastage;
+		mgmt_size = slab_mgmt_size(nr_objs, align);
+	}
+	*num = nr_objs;
+	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
 }
 
 #define slab_error(cachep, msg) __slab_error(__FUNCTION__, cachep, msg)
 
-static void __slab_error(const char *function, kmem_cache_t *cachep, char *msg)
+static void __slab_error(const char *function, struct kmem_cache *cachep, char *msg)
 {
 	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
 	       function, cachep->name, msg);
@@ -772,7 +829,9 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 }
 
 #ifdef CONFIG_NUMA
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
+static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+
+static struct array_cache **alloc_alien_cache(int node, int limit)
 {
 	struct array_cache **ac_ptr;
 	int memsize = sizeof(void *) * MAX_NUMNODES;
@@ -799,7 +858,7 @@ static inline struct array_cache **alloc_alien_cache(int node, int limit)
 	return ac_ptr;
 }
 
-static inline void free_alien_cache(struct array_cache **ac_ptr)
+static void free_alien_cache(struct array_cache **ac_ptr)
 {
 	int i;
 
@@ -812,8 +871,8 @@ static inline void free_alien_cache(struct array_cache **ac_ptr)
 	kfree(ac_ptr);
 }
 
-static inline void __drain_alien_cache(kmem_cache_t *cachep,
-				       struct array_cache *ac, int node)
+static void __drain_alien_cache(struct kmem_cache *cachep,
+				struct array_cache *ac, int node)
 {
 	struct kmem_list3 *rl3 = cachep->nodelists[node];
 
@@ -825,14 +884,14 @@ static inline void __drain_alien_cache(kmem_cache_t *cachep,
 	}
 }
 
-static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3)
+static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien)
 {
 	int i = 0;
 	struct array_cache *ac;
 	unsigned long flags;
 
 	for_each_online_node(i) {
-		ac = l3->alien[i];
+		ac = alien[i];
 		if (ac) {
 			spin_lock_irqsave(&ac->lock, flags);
 			__drain_alien_cache(cachep, ac, i);
@@ -841,23 +900,32 @@ static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3)
 	}
 }
 #else
-#define alloc_alien_cache(node, limit) do { } while (0)
-#define free_alien_cache(ac_ptr) do { } while (0)
-#define drain_alien_cache(cachep, l3) do { } while (0)
+
+#define drain_alien_cache(cachep, alien) do { } while (0)
+
+static inline struct array_cache **alloc_alien_cache(int node, int limit)
+{
+	return (struct array_cache **) 0x01020304ul;
+}
+
+static inline void free_alien_cache(struct array_cache **ac_ptr)
+{
+}
+
 #endif
 
 static int __devinit cpuup_callback(struct notifier_block *nfb,
 				    unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
-	kmem_cache_t *cachep;
+	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
 	int memsize = sizeof(struct kmem_list3);
 
 	switch (action) {
 	case CPU_UP_PREPARE:
-		down(&cache_chain_sem);
+		mutex_lock(&cache_chain_mutex);
 		/* we need to do this right in the beginning since
 		 * alloc_arraycache's are going to use this list.
 		 * kmalloc_node allows us to add the slab to the right
@@ -877,6 +945,11 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 				l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
 				    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
 
+				/*
+				 * The l3s don't come and go as CPUs come and
+				 * go.  cache_chain_mutex is sufficient
+				 * protection here.
+				 */
 				cachep->nodelists[node] = l3;
 			}
 
@@ -891,53 +964,82 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 		   & array cache's */
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
+			struct array_cache *shared;
+			struct array_cache **alien;
 
 			nc = alloc_arraycache(node, cachep->limit,
-					      cachep->batchcount);
+						cachep->batchcount);
 			if (!nc)
 				goto bad;
+			shared = alloc_arraycache(node,
+					cachep->shared * cachep->batchcount,
+					0xbaadf00d);
+			if (!shared)
+				goto bad;
+
+			alien = alloc_alien_cache(node, cachep->limit);
+			if (!alien)
+				goto bad;
 			cachep->array[cpu] = nc;
 
 			l3 = cachep->nodelists[node];
 			BUG_ON(!l3);
-			if (!l3->shared) {
-				if (!(nc = alloc_arraycache(node,
-							    cachep->shared *
-							    cachep->batchcount,
-							    0xbaadf00d)))
-					goto bad;
 
-				/* we are serialised from CPU_DEAD or
-				   CPU_UP_CANCELLED by the cpucontrol lock */
-				l3->shared = nc;
+			spin_lock_irq(&l3->list_lock);
+			if (!l3->shared) {
+				/*
+				 * We are serialised from CPU_DEAD or
+				 * CPU_UP_CANCELLED by the cpucontrol lock
+				 */
+				l3->shared = shared;
+				shared = NULL;
+			}
+#ifdef CONFIG_NUMA
+			if (!l3->alien) {
+				l3->alien = alien;
+				alien = NULL;
 			}
+#endif
+			spin_unlock_irq(&l3->list_lock);
+
+			kfree(shared);
+			free_alien_cache(alien);
 		}
-		up(&cache_chain_sem);
+		mutex_unlock(&cache_chain_mutex);
 		break;
 	case CPU_ONLINE:
 		start_cpu_timer(cpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
+		/*
+		 * 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
+		 * cpu_down, and a kmalloc allocation from another cpu for
+		 * memory from the node of the cpu going down.  The list3
+		 * structure is usually allocated from kmem_cache_create() and
+		 * gets destroyed at kmem_cache_destroy().
+		 */
 		/* fall thru */
 	case CPU_UP_CANCELED:
-		down(&cache_chain_sem);
+		mutex_lock(&cache_chain_mutex);
 
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
+			struct array_cache *shared;
+			struct array_cache **alien;
 			cpumask_t mask;
 
 			mask = node_to_cpumask(node);
-			spin_lock_irq(&cachep->spinlock);
 			/* cpu is dead; no one can alloc from it. */
 			nc = cachep->array[cpu];
 			cachep->array[cpu] = NULL;
 			l3 = cachep->nodelists[node];
 
 			if (!l3)
-				goto unlock_cache;
+				goto free_array_cache;
 
-			spin_lock(&l3->list_lock);
+			spin_lock_irq(&l3->list_lock);
 
 			/* Free limit for this kmem_list3 */
 			l3->free_limit -= cachep->batchcount;
@@ -945,41 +1047,51 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 				free_block(cachep, nc->entry, nc->avail, node);
 
 			if (!cpus_empty(mask)) {
-				spin_unlock(&l3->list_lock);
-				goto unlock_cache;
+				spin_unlock_irq(&l3->list_lock);
+				goto free_array_cache;
 			}
 
-			if (l3->shared) {
+			shared = l3->shared;
+			if (shared) {
 				free_block(cachep, l3->shared->entry,
 					   l3->shared->avail, node);
-				kfree(l3->shared);
 				l3->shared = NULL;
 			}
-			if (l3->alien) {
-				drain_alien_cache(cachep, l3);
-				free_alien_cache(l3->alien);
-				l3->alien = NULL;
-			}
 
-			/* free slabs belonging to this node */
-			if (__node_shrink(cachep, node)) {
-				cachep->nodelists[node] = NULL;
-				spin_unlock(&l3->list_lock);
-				kfree(l3);
-			} else {
-				spin_unlock(&l3->list_lock);
+			alien = l3->alien;
+			l3->alien = NULL;
+
+			spin_unlock_irq(&l3->list_lock);
+
+			kfree(shared);
+			if (alien) {
+				drain_alien_cache(cachep, alien);
+				free_alien_cache(alien);
 			}
-		      unlock_cache:
-			spin_unlock_irq(&cachep->spinlock);
+free_array_cache:
 			kfree(nc);
 		}
-		up(&cache_chain_sem);
+		/*
+		 * In the previous loop, all the objects were freed to
+		 * 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) {
+			l3 = cachep->nodelists[node];
+			if (!l3)
+				continue;
+			spin_lock_irq(&l3->list_lock);
+			/* free slabs belonging to this node */
+			__node_shrink(cachep, node);
+			spin_unlock_irq(&l3->list_lock);
+		}
+		mutex_unlock(&cache_chain_mutex);
 		break;
 #endif
 	}
 	return NOTIFY_OK;
       bad:
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
 	return NOTIFY_BAD;
 }
 
@@ -988,7 +1100,7 @@ static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };
 /*
  * swap the static kmem_list3 with kmalloced memory
  */
-static void init_list(kmem_cache_t *cachep, struct kmem_list3 *list, int nodeid)
+static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, int nodeid)
 {
 	struct kmem_list3 *ptr;
 
@@ -1028,14 +1140,14 @@ void __init kmem_cache_init(void)
 
 	/* Bootstrap is tricky, because several objects are allocated
 	 * from caches that do not exist yet:
-	 * 1) initialize the cache_cache cache: it contains the kmem_cache_t
+	 * 1) initialize the cache_cache cache: it contains the struct kmem_cache
 	 *    structures of all caches, except cache_cache itself: cache_cache
 	 *    is statically allocated.
 	 *    Initially an __init data area is used for the head array and the
 	 *    kmem_list3 structures, it's replaced with a kmalloc allocated
 	 *    array at the end of the bootstrap.
 	 * 2) Create the first kmalloc cache.
-	 *    The kmem_cache_t for the new cache is allocated normally.
+	 *    The struct kmem_cache for the new cache is allocated normally.
 	 *    An __init data area is used for the head array.
 	 * 3) Create the remaining kmalloc caches, with minimally sized
 	 *    head arrays.
@@ -1047,22 +1159,20 @@ void __init kmem_cache_init(void)
 	 */
 
 	/* 1) create the cache_cache */
-	init_MUTEX(&cache_chain_sem);
 	INIT_LIST_HEAD(&cache_chain);
 	list_add(&cache_cache.next, &cache_chain);
 	cache_cache.colour_off = cache_line_size();
 	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
 	cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE];
 
-	cache_cache.objsize = ALIGN(cache_cache.objsize, cache_line_size());
+	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size());
 
-	cache_estimate(0, cache_cache.objsize, cache_line_size(), 0,
+	cache_estimate(0, cache_cache.buffer_size, cache_line_size(), 0,
 		       &left_over, &cache_cache.num);
 	if (!cache_cache.num)
 		BUG();
 
 	cache_cache.colour = left_over / cache_cache.colour_off;
-	cache_cache.colour_next = 0;
 	cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
 				      sizeof(struct slab), cache_line_size());
 
@@ -1129,8 +1239,8 @@ void __init kmem_cache_init(void)
 		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
 
 		local_irq_disable();
-		BUG_ON(ac_data(&cache_cache) != &initarray_cache.cache);
-		memcpy(ptr, ac_data(&cache_cache),
+		BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
+		memcpy(ptr, cpu_cache_get(&cache_cache),
 		       sizeof(struct arraycache_init));
 		cache_cache.array[smp_processor_id()] = ptr;
 		local_irq_enable();
@@ -1138,9 +1248,9 @@ void __init kmem_cache_init(void)
 		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
 
 		local_irq_disable();
-		BUG_ON(ac_data(malloc_sizes[INDEX_AC].cs_cachep)
+		BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
 		       != &initarray_generic.cache);
-		memcpy(ptr, ac_data(malloc_sizes[INDEX_AC].cs_cachep),
+		memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
 		       sizeof(struct arraycache_init));
 		malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
 		    ptr;
@@ -1167,18 +1277,18 @@ void __init kmem_cache_init(void)
 
 	/* 6) resize the head arrays to their final sizes */
 	{
-		kmem_cache_t *cachep;
-		down(&cache_chain_sem);
+		struct kmem_cache *cachep;
+		mutex_lock(&cache_chain_mutex);
 		list_for_each_entry(cachep, &cache_chain, next)
 		    enable_cpucache(cachep);
-		up(&cache_chain_sem);
+		mutex_unlock(&cache_chain_mutex);
 	}
 
 	/* Done! */
 	g_cpucache_up = FULL;
 
 	/* Register a cpu startup notifier callback
-	 * that initializes ac_data for all new cpus
+	 * that initializes cpu_cache_get for all new cpus
 	 */
 	register_cpu_notifier(&cpucache_notifier);
 
@@ -1210,7 +1320,7 @@ __initcall(cpucache_init);
  * did not request dmaable memory, we might get it, but that
  * would be relatively rare and ignorable.
  */
-static void *kmem_getpages(kmem_cache_t *cachep, gfp_t flags, int nodeid)
+static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	struct page *page;
 	void *addr;
@@ -1236,7 +1346,7 @@ static void *kmem_getpages(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 /*
  * Interface to system's page release.
  */
-static void kmem_freepages(kmem_cache_t *cachep, void *addr)
+static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 {
 	unsigned long i = (1 << cachep->gfporder);
 	struct page *page = virt_to_page(addr);
@@ -1258,7 +1368,7 @@ static void kmem_freepages(kmem_cache_t *cachep, void *addr)
 static void kmem_rcu_free(struct rcu_head *head)
 {
 	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
-	kmem_cache_t *cachep = slab_rcu->cachep;
+	struct kmem_cache *cachep = slab_rcu->cachep;
 
 	kmem_freepages(cachep, slab_rcu->addr);
 	if (OFF_SLAB(cachep))
@@ -1268,12 +1378,12 @@ static void kmem_rcu_free(struct rcu_head *head)
 #if DEBUG
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr,
+static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
 			    unsigned long caller)
 {
-	int size = obj_reallen(cachep);
+	int size = obj_size(cachep);
 
-	addr = (unsigned long *)&((char *)addr)[obj_dbghead(cachep)];
+	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
 
 	if (size < 5 * sizeof(unsigned long))
 		return;
@@ -1301,10 +1411,10 @@ static void store_stackinfo(kmem_cache_t *cachep, unsigned long *addr,
 }
 #endif
 
-static void poison_obj(kmem_cache_t *cachep, void *addr, unsigned char val)
+static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
 {
-	int size = obj_reallen(cachep);
-	addr = &((char *)addr)[obj_dbghead(cachep)];
+	int size = obj_size(cachep);
+	addr = &((char *)addr)[obj_offset(cachep)];
 
 	memset(addr, val, size);
 	*(unsigned char *)(addr + size - 1) = POISON_END;
@@ -1323,7 +1433,7 @@ static void dump_line(char *data, int offset, int limit)
 
 #if DEBUG
 
-static void print_objinfo(kmem_cache_t *cachep, void *objp, int lines)
+static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
 {
 	int i, size;
 	char *realobj;
@@ -1341,8 +1451,8 @@ static void print_objinfo(kmem_cache_t *cachep, void *objp, int lines)
 			     (unsigned long)*dbg_userword(cachep, objp));
 		printk("\n");
 	}
-	realobj = (char *)objp + obj_dbghead(cachep);
-	size = obj_reallen(cachep);
+	realobj = (char *)objp + obj_offset(cachep);
+	size = obj_size(cachep);
 	for (i = 0; i < size && lines; i += 16, lines--) {
 		int limit;
 		limit = 16;
@@ -1352,14 +1462,14 @@ static void print_objinfo(kmem_cache_t *cachep, void *objp, int lines)
 	}
 }
 
-static void check_poison_obj(kmem_cache_t *cachep, void *objp)
+static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 {
 	char *realobj;
 	int size, i;
 	int lines = 0;
 
-	realobj = (char *)objp + obj_dbghead(cachep);
-	size = obj_reallen(cachep);
+	realobj = (char *)objp + obj_offset(cachep);
+	size = obj_size(cachep);
 
 	for (i = 0; i < size; i++) {
 		char exp = POISON_FREE;
@@ -1392,20 +1502,20 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp)
 		/* Print some data about the neighboring objects, if they
 		 * exist:
 		 */
-		struct slab *slabp = page_get_slab(virt_to_page(objp));
+		struct slab *slabp = virt_to_slab(objp);
 		int objnr;
 
-		objnr = (objp - slabp->s_mem) / cachep->objsize;
+		objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
 		if (objnr) {
-			objp = slabp->s_mem + (objnr - 1) * cachep->objsize;
-			realobj = (char *)objp + obj_dbghead(cachep);
+			objp = slabp->s_mem + (objnr - 1) * cachep->buffer_size;
+			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
 			       realobj, size);
 			print_objinfo(cachep, objp, 2);
 		}
 		if (objnr + 1 < cachep->num) {
-			objp = slabp->s_mem + (objnr + 1) * cachep->objsize;
-			realobj = (char *)objp + obj_dbghead(cachep);
+			objp = slabp->s_mem + (objnr + 1) * cachep->buffer_size;
+			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
 			       realobj, size);
 			print_objinfo(cachep, objp, 2);
@@ -1414,25 +1524,23 @@ static void check_poison_obj(kmem_cache_t *cachep, void *objp)
 }
 #endif
 
-/* Destroy all the objs in a slab, and release the mem back to the system.
- * Before calling the slab must have been unlinked from the cache.
- * The cache-lock is not held/needed.
+#if DEBUG
+/**
+ * slab_destroy_objs - call the registered destructor for each object in
+ *      a slab that is to be destroyed.
  */
-static void slab_destroy(kmem_cache_t *cachep, struct slab *slabp)
+static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 {
-	void *addr = slabp->s_mem - slabp->colouroff;
-
-#if DEBUG
 	int i;
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = slabp->s_mem + cachep->objsize * i;
+		void *objp = slabp->s_mem + cachep->buffer_size * i;
 
 		if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
-			if ((cachep->objsize % PAGE_SIZE) == 0
+			if ((cachep->buffer_size % PAGE_SIZE) == 0
 			    && OFF_SLAB(cachep))
 				kernel_map_pages(virt_to_page(objp),
-						 cachep->objsize / PAGE_SIZE,
+						 cachep->buffer_size / PAGE_SIZE,
 						 1);
 			else
 				check_poison_obj(cachep, objp);
@@ -1449,18 +1557,32 @@ static void slab_destroy(kmem_cache_t *cachep, struct slab *slabp)
 					   "was overwritten");
 		}
 		if (cachep->dtor && !(cachep->flags & SLAB_POISON))
-			(cachep->dtor) (objp + obj_dbghead(cachep), cachep, 0);
+			(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 = slabp->s_mem + cachep->objsize * i;
+			void *objp = slabp->s_mem + cachep->buffer_size * i;
 			(cachep->dtor) (objp, cachep, 0);
 		}
 	}
+}
 #endif
 
+/**
+ * Destroy all the objs in a slab, and release the mem back to the system.
+ * Before calling the slab must have been unlinked from the cache.
+ * The cache-lock is not held/needed.
+ */
+static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
+{
+	void *addr = slabp->s_mem - slabp->colouroff;
+
+	slab_destroy_objs(cachep, slabp);
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
 		struct slab_rcu *slab_rcu;
 
@@ -1475,9 +1597,9 @@ static void slab_destroy(kmem_cache_t *cachep, struct slab *slabp)
 	}
 }
 
-/* For setting up all the kmem_list3s for cache whose objsize is same
+/* For setting up all the kmem_list3s for cache whose buffer_size is same
    as size of kmem_list3. */
-static inline void set_up_list3s(kmem_cache_t *cachep, int index)
+static void set_up_list3s(struct kmem_cache *cachep, int index)
 {
 	int node;
 
@@ -1490,15 +1612,20 @@ static inline void set_up_list3s(kmem_cache_t *cachep, int index)
 }
 
 /**
- * calculate_slab_order - calculate size (page order) of slabs and the number
- *                        of objects per slab.
+ * calculate_slab_order - calculate size (page order) of slabs
+ * @cachep: pointer to the cache that is being created
+ * @size: size of objects to be created in this cache.
+ * @align: required alignment for the objects.
+ * @flags: slab allocation flags
+ *
+ * Also calculates the number of objects per slab.
  *
  * This could be made much more intelligent.  For now, try to avoid using
  * high order pages for slabs.  When the gfp() functions are more friendly
  * towards high-order requests, this should be changed.
  */
-static inline size_t calculate_slab_order(kmem_cache_t *cachep, size_t size,
-					  size_t align, gfp_t flags)
+static inline size_t calculate_slab_order(struct kmem_cache *cachep,
+			size_t size, size_t align, unsigned long flags)
 {
 	size_t left_over = 0;
 
@@ -1569,13 +1696,13 @@ static inline size_t calculate_slab_order(kmem_cache_t *cachep, size_t size,
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
  */
-kmem_cache_t *
+struct kmem_cache *
 kmem_cache_create (const char *name, size_t size, size_t align,
-	unsigned long flags, void (*ctor)(void*, kmem_cache_t *, unsigned long),
-	void (*dtor)(void*, kmem_cache_t *, unsigned long))
+	unsigned long flags, void (*ctor)(void*, struct kmem_cache *, unsigned long),
+	void (*dtor)(void*, struct kmem_cache *, unsigned long))
 {
 	size_t left_over, slab_size, ralign;
-	kmem_cache_t *cachep = NULL;
+	struct kmem_cache *cachep = NULL;
 	struct list_head *p;
 
 	/*
@@ -1590,10 +1717,16 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		BUG();
 	}
 
-	down(&cache_chain_sem);
+	/*
+	 * Prevent CPUs from coming and going.
+	 * lock_cpu_hotplug() nests outside cache_chain_mutex
+	 */
+	lock_cpu_hotplug();
+
+	mutex_lock(&cache_chain_mutex);
 
 	list_for_each(p, &cache_chain) {
-		kmem_cache_t *pc = list_entry(p, kmem_cache_t, next);
+		struct kmem_cache *pc = list_entry(p, struct kmem_cache, next);
 		mm_segment_t old_fs = get_fs();
 		char tmp;
 		int res;
@@ -1608,7 +1741,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		set_fs(old_fs);
 		if (res) {
 			printk("SLAB: cache with size %d has lost its name\n",
-			       pc->objsize);
+			       pc->buffer_size);
 			continue;
 		}
 
@@ -1693,20 +1826,20 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	align = ralign;
 
 	/* Get cache's description obj. */
-	cachep = (kmem_cache_t *) kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
+	cachep = kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
 	if (!cachep)
 		goto oops;
-	memset(cachep, 0, sizeof(kmem_cache_t));
+	memset(cachep, 0, sizeof(struct kmem_cache));
 
 #if DEBUG
-	cachep->reallen = size;
+	cachep->obj_size = size;
 
 	if (flags & SLAB_RED_ZONE) {
 		/* redzoning only works with word aligned caches */
 		align = BYTES_PER_WORD;
 
 		/* add space for red zone words */
-		cachep->dbghead += BYTES_PER_WORD;
+		cachep->obj_offset += BYTES_PER_WORD;
 		size += 2 * BYTES_PER_WORD;
 	}
 	if (flags & SLAB_STORE_USER) {
@@ -1719,8 +1852,8 @@ 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->reallen > cache_line_size() && size < PAGE_SIZE) {
-		cachep->dbghead += PAGE_SIZE - size;
+	    && cachep->obj_size > cache_line_size() && size < PAGE_SIZE) {
+		cachep->obj_offset += PAGE_SIZE - size;
 		size = PAGE_SIZE;
 	}
 #endif
@@ -1783,7 +1916,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	if (flags & SLAB_CACHE_DMA)
 		cachep->gfpflags |= GFP_DMA;
 	spin_lock_init(&cachep->spinlock);
-	cachep->objsize = size;
+	cachep->buffer_size = size;
 
 	if (flags & CFLGS_OFF_SLAB)
 		cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
@@ -1791,8 +1924,6 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	cachep->dtor = dtor;
 	cachep->name = name;
 
-	/* Don't let CPUs to come and go */
-	lock_cpu_hotplug();
 
 	if (g_cpucache_up == FULL) {
 		enable_cpucache(cachep);
@@ -1840,23 +1971,23 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		    jiffies + REAPTIMEOUT_LIST3 +
 		    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
 
-		BUG_ON(!ac_data(cachep));
-		ac_data(cachep)->avail = 0;
-		ac_data(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
-		ac_data(cachep)->batchcount = 1;
-		ac_data(cachep)->touched = 0;
+		BUG_ON(!cpu_cache_get(cachep));
+		cpu_cache_get(cachep)->avail = 0;
+		cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
+		cpu_cache_get(cachep)->batchcount = 1;
+		cpu_cache_get(cachep)->touched = 0;
 		cachep->batchcount = 1;
 		cachep->limit = BOOT_CPUCACHE_ENTRIES;
 	}
 
 	/* cache setup completed, link it into the list */
 	list_add(&cachep->next, &cache_chain);
-	unlock_cpu_hotplug();
       oops:
 	if (!cachep && (flags & SLAB_PANIC))
 		panic("kmem_cache_create(): failed to create slab `%s'\n",
 		      name);
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
+	unlock_cpu_hotplug();
 	return cachep;
 }
 EXPORT_SYMBOL(kmem_cache_create);
@@ -1872,7 +2003,7 @@ static void check_irq_on(void)
 	BUG_ON(irqs_disabled());
 }
 
-static void check_spinlock_acquired(kmem_cache_t *cachep)
+static void check_spinlock_acquired(struct kmem_cache *cachep)
 {
 #ifdef CONFIG_SMP
 	check_irq_off();
@@ -1880,7 +2011,7 @@ static void check_spinlock_acquired(kmem_cache_t *cachep)
 #endif
 }
 
-static inline void check_spinlock_acquired_node(kmem_cache_t *cachep, int node)
+static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
 {
 #ifdef CONFIG_SMP
 	check_irq_off();
@@ -1913,45 +2044,43 @@ static void smp_call_function_all_cpus(void (*func)(void *arg), void *arg)
 	preempt_enable();
 }
 
-static void drain_array_locked(kmem_cache_t *cachep, struct array_cache *ac,
+static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
 				int force, int node);
 
 static void do_drain(void *arg)
 {
-	kmem_cache_t *cachep = (kmem_cache_t *) arg;
+	struct kmem_cache *cachep = (struct kmem_cache *) arg;
 	struct array_cache *ac;
 	int node = numa_node_id();
 
 	check_irq_off();
-	ac = ac_data(cachep);
+	ac = cpu_cache_get(cachep);
 	spin_lock(&cachep->nodelists[node]->list_lock);
 	free_block(cachep, ac->entry, ac->avail, node);
 	spin_unlock(&cachep->nodelists[node]->list_lock);
 	ac->avail = 0;
 }
 
-static void drain_cpu_caches(kmem_cache_t *cachep)
+static void drain_cpu_caches(struct kmem_cache *cachep)
 {
 	struct kmem_list3 *l3;
 	int node;
 
 	smp_call_function_all_cpus(do_drain, cachep);
 	check_irq_on();
-	spin_lock_irq(&cachep->spinlock);
 	for_each_online_node(node) {
 		l3 = cachep->nodelists[node];
 		if (l3) {
-			spin_lock(&l3->list_lock);
+			spin_lock_irq(&l3->list_lock);
 			drain_array_locked(cachep, l3->shared, 1, node);
-			spin_unlock(&l3->list_lock);
+			spin_unlock_irq(&l3->list_lock);
 			if (l3->alien)
-				drain_alien_cache(cachep, l3);
+				drain_alien_cache(cachep, l3->alien);
 		}
 	}
-	spin_unlock_irq(&cachep->spinlock);
 }
 
-static int __node_shrink(kmem_cache_t *cachep, int node)
+static int __node_shrink(struct kmem_cache *cachep, int node)
 {
 	struct slab *slabp;
 	struct kmem_list3 *l3 = cachep->nodelists[node];
@@ -1980,7 +2109,7 @@ static int __node_shrink(kmem_cache_t *cachep, int node)
 	return ret;
 }
 
-static int __cache_shrink(kmem_cache_t *cachep)
+static int __cache_shrink(struct kmem_cache *cachep)
 {
 	int ret = 0, i = 0;
 	struct kmem_list3 *l3;
@@ -2006,7 +2135,7 @@ static int __cache_shrink(kmem_cache_t *cachep)
  * Releases as many slabs as possible for a cache.
  * To help debugging, a zero exit status indicates all slabs were released.
  */
-int kmem_cache_shrink(kmem_cache_t *cachep)
+int kmem_cache_shrink(struct kmem_cache *cachep)
 {
 	if (!cachep || in_interrupt())
 		BUG();
@@ -2019,7 +2148,7 @@ EXPORT_SYMBOL(kmem_cache_shrink);
  * kmem_cache_destroy - delete a cache
  * @cachep: the cache to destroy
  *
- * Remove a kmem_cache_t object from the slab cache.
+ * Remove a struct kmem_cache object from the slab cache.
  * Returns 0 on success.
  *
  * It is expected this function will be called by a module when it is
@@ -2032,7 +2161,7 @@ EXPORT_SYMBOL(kmem_cache_shrink);
  * The caller must guarantee that noone will allocate memory from the cache
  * during the kmem_cache_destroy().
  */
-int kmem_cache_destroy(kmem_cache_t *cachep)
+int kmem_cache_destroy(struct kmem_cache *cachep)
 {
 	int i;
 	struct kmem_list3 *l3;
@@ -2044,18 +2173,18 @@ int kmem_cache_destroy(kmem_cache_t *cachep)
 	lock_cpu_hotplug();
 
 	/* Find the cache in the chain of caches. */
-	down(&cache_chain_sem);
+	mutex_lock(&cache_chain_mutex);
 	/*
 	 * the chain is never empty, cache_cache is never destroyed
 	 */
 	list_del(&cachep->next);
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
 
 	if (__cache_shrink(cachep)) {
 		slab_error(cachep, "Can't free all objects");
-		down(&cache_chain_sem);
+		mutex_lock(&cache_chain_mutex);
 		list_add(&cachep->next, &cache_chain);
-		up(&cache_chain_sem);
+		mutex_unlock(&cache_chain_mutex);
 		unlock_cpu_hotplug();
 		return 1;
 	}
@@ -2083,7 +2212,7 @@ int kmem_cache_destroy(kmem_cache_t *cachep)
 EXPORT_SYMBOL(kmem_cache_destroy);
 
 /* Get the memory for a slab management obj. */
-static struct slab *alloc_slabmgmt(kmem_cache_t *cachep, void *objp,
+static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 				   int colour_off, gfp_t local_flags)
 {
 	struct slab *slabp;
@@ -2109,13 +2238,13 @@ static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp)
 	return (kmem_bufctl_t *) (slabp + 1);
 }
 
-static void cache_init_objs(kmem_cache_t *cachep,
+static void cache_init_objs(struct kmem_cache *cachep,
 			    struct slab *slabp, unsigned long ctor_flags)
 {
 	int i;
 
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = slabp->s_mem + cachep->objsize * i;
+		void *objp = slabp->s_mem + cachep->buffer_size * i;
 #if DEBUG
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON)
@@ -2133,7 +2262,7 @@ static void cache_init_objs(kmem_cache_t *cachep,
 		 * Otherwise, deadlock. They must also be threaded.
 		 */
 		if (cachep->ctor && !(cachep->flags & SLAB_POISON))
-			cachep->ctor(objp + obj_dbghead(cachep), cachep,
+			cachep->ctor(objp + obj_offset(cachep), cachep,
 				     ctor_flags);
 
 		if (cachep->flags & SLAB_RED_ZONE) {
@@ -2144,10 +2273,10 @@ static void cache_init_objs(kmem_cache_t *cachep,
 				slab_error(cachep, "constructor overwrote the"
 					   " start of an object");
 		}
-		if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep)
+		if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)
 		    && cachep->flags & SLAB_POISON)
 			kernel_map_pages(virt_to_page(objp),
-					 cachep->objsize / PAGE_SIZE, 0);
+					 cachep->buffer_size / PAGE_SIZE, 0);
 #else
 		if (cachep->ctor)
 			cachep->ctor(objp, cachep, ctor_flags);
@@ -2158,7 +2287,7 @@ static void cache_init_objs(kmem_cache_t *cachep,
 	slabp->free = 0;
 }
 
-static void kmem_flagcheck(kmem_cache_t *cachep, gfp_t flags)
+static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 {
 	if (flags & SLAB_DMA) {
 		if (!(cachep->gfpflags & GFP_DMA))
@@ -2169,7 +2298,43 @@ static void kmem_flagcheck(kmem_cache_t *cachep, gfp_t flags)
 	}
 }
 
-static void set_slab_attr(kmem_cache_t *cachep, struct slab *slabp, void *objp)
+static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, int nodeid)
+{
+	void *objp = slabp->s_mem + (slabp->free * cachep->buffer_size);
+	kmem_bufctl_t next;
+
+	slabp->inuse++;
+	next = slab_bufctl(slabp)[slabp->free];
+#if DEBUG
+	slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE;
+	WARN_ON(slabp->nodeid != nodeid);
+#endif
+	slabp->free = next;
+
+	return objp;
+}
+
+static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, void *objp,
+			  int nodeid)
+{
+	unsigned int objnr = (unsigned)(objp-slabp->s_mem) / cachep->buffer_size;
+
+#if DEBUG
+	/* Verify that the slab belongs to the intended node */
+	WARN_ON(slabp->nodeid != nodeid);
+
+	if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) {
+		printk(KERN_ERR "slab: double free detected in cache "
+		       "'%s', objp %p\n", cachep->name, objp);
+		BUG();
+	}
+#endif
+	slab_bufctl(slabp)[objnr] = slabp->free;
+	slabp->free = objnr;
+	slabp->inuse--;
+}
+
+static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp, void *objp)
 {
 	int i;
 	struct page *page;
@@ -2188,7 +2353,7 @@ static void set_slab_attr(kmem_cache_t *cachep, struct slab *slabp, void *objp)
  * Grow (by 1) the number of slabs within a cache.  This is called by
  * kmem_cache_alloc() when there are no active objs left in a cache.
  */
-static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid)
+static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	struct slab *slabp;
 	void *objp;
@@ -2214,20 +2379,20 @@ static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 		 */
 		ctor_flags |= SLAB_CTOR_ATOMIC;
 
-	/* About to mess with non-constant members - lock. */
+	/* Take the l3 list lock to change the colour_next on this node */
 	check_irq_off();
-	spin_lock(&cachep->spinlock);
+	l3 = cachep->nodelists[nodeid];
+	spin_lock(&l3->list_lock);
 
 	/* Get colour for the slab, and cal the next value. */
-	offset = cachep->colour_next;
-	cachep->colour_next++;
-	if (cachep->colour_next >= cachep->colour)
-		cachep->colour_next = 0;
-	offset *= cachep->colour_off;
+	offset = l3->colour_next;
+	l3->colour_next++;
+	if (l3->colour_next >= cachep->colour)
+		l3->colour_next = 0;
+	spin_unlock(&l3->list_lock);
 
-	spin_unlock(&cachep->spinlock);
+	offset *= cachep->colour_off;
 
-	check_irq_off();
 	if (local_flags & __GFP_WAIT)
 		local_irq_enable();
 
@@ -2257,7 +2422,6 @@ static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
 	check_irq_off();
-	l3 = cachep->nodelists[nodeid];
 	spin_lock(&l3->list_lock);
 
 	/* Make slab active. */
@@ -2299,14 +2463,14 @@ static void kfree_debugcheck(const void *objp)
 	}
 }
 
-static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp,
+static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 				   void *caller)
 {
 	struct page *page;
 	unsigned int objnr;
 	struct slab *slabp;
 
-	objp -= obj_dbghead(cachep);
+	objp -= obj_offset(cachep);
 	kfree_debugcheck(objp);
 	page = virt_to_page(objp);
 
@@ -2338,31 +2502,31 @@ static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp,
 	if (cachep->flags & SLAB_STORE_USER)
 		*dbg_userword(cachep, objp) = caller;
 
-	objnr = (objp - slabp->s_mem) / cachep->objsize;
+	objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
 
 	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != slabp->s_mem + objnr * cachep->objsize);
+	BUG_ON(objp != slabp->s_mem + objnr * cachep->buffer_size);
 
 	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_dbghead(cachep),
+		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_dbghead(cachep), cachep, 0);
+		cachep->dtor(objp + obj_offset(cachep), cachep, 0);
 	}
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) {
+		if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) {
 			store_stackinfo(cachep, objp, (unsigned long)caller);
 			kernel_map_pages(virt_to_page(objp),
-					 cachep->objsize / PAGE_SIZE, 0);
+					 cachep->buffer_size / PAGE_SIZE, 0);
 		} else {
 			poison_obj(cachep, objp, POISON_FREE);
 		}
@@ -2373,7 +2537,7 @@ static void *cache_free_debugcheck(kmem_cache_t *cachep, void *objp,
 	return objp;
 }
 
-static void check_slabp(kmem_cache_t *cachep, struct slab *slabp)
+static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
 {
 	kmem_bufctl_t i;
 	int entries = 0;
@@ -2406,14 +2570,14 @@ static void check_slabp(kmem_cache_t *cachep, struct slab *slabp)
 #define check_slabp(x,y) do { } while(0)
 #endif
 
-static void *cache_alloc_refill(kmem_cache_t *cachep, gfp_t flags)
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 {
 	int batchcount;
 	struct kmem_list3 *l3;
 	struct array_cache *ac;
 
 	check_irq_off();
-	ac = ac_data(cachep);
+	ac = cpu_cache_get(cachep);
       retry:
 	batchcount = ac->batchcount;
 	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
@@ -2458,22 +2622,12 @@ static void *cache_alloc_refill(kmem_cache_t *cachep, gfp_t flags)
 		check_slabp(cachep, slabp);
 		check_spinlock_acquired(cachep);
 		while (slabp->inuse < cachep->num && batchcount--) {
-			kmem_bufctl_t next;
 			STATS_INC_ALLOCED(cachep);
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			/* get obj pointer */
-			ac->entry[ac->avail++] = slabp->s_mem +
-			    slabp->free * cachep->objsize;
-
-			slabp->inuse++;
-			next = slab_bufctl(slabp)[slabp->free];
-#if DEBUG
-			slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE;
-			WARN_ON(numa_node_id() != slabp->nodeid);
-#endif
-			slabp->free = next;
+			ac->entry[ac->avail++] = slab_get_obj(cachep, slabp,
+							    numa_node_id());
 		}
 		check_slabp(cachep, slabp);
 
@@ -2495,7 +2649,7 @@ static void *cache_alloc_refill(kmem_cache_t *cachep, gfp_t flags)
 		x = cache_grow(cachep, flags, numa_node_id());
 
 		// cache_grow can reenable interrupts, then ac could change.
-		ac = ac_data(cachep);
+		ac = cpu_cache_get(cachep);
 		if (!x && ac->avail == 0)	// no objects in sight? abort
 			return NULL;
 
@@ -2507,7 +2661,7 @@ static void *cache_alloc_refill(kmem_cache_t *cachep, gfp_t flags)
 }
 
 static inline void
-cache_alloc_debugcheck_before(kmem_cache_t *cachep, gfp_t flags)
+cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags)
 {
 	might_sleep_if(flags & __GFP_WAIT);
 #if DEBUG
@@ -2516,16 +2670,16 @@ cache_alloc_debugcheck_before(kmem_cache_t *cachep, gfp_t flags)
 }
 
 #if DEBUG
-static void *cache_alloc_debugcheck_after(kmem_cache_t *cachep, gfp_t flags,
+static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags,
 					void *objp, void *caller)
 {
 	if (!objp)
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((cachep->objsize % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
+		if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
 			kernel_map_pages(virt_to_page(objp),
-					 cachep->objsize / PAGE_SIZE, 1);
+					 cachep->buffer_size / PAGE_SIZE, 1);
 		else
 			check_poison_obj(cachep, objp);
 #else
@@ -2550,7 +2704,7 @@ static void *cache_alloc_debugcheck_after(kmem_cache_t *cachep, gfp_t flags,
 		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
-	objp += obj_dbghead(cachep);
+	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON) {
 		unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
 
@@ -2565,13 +2719,22 @@ static void *cache_alloc_debugcheck_after(kmem_cache_t *cachep, gfp_t flags,
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
-static inline void *____cache_alloc(kmem_cache_t *cachep, gfp_t flags)
+static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
 	struct array_cache *ac;
 
+#ifdef CONFIG_NUMA
+	if (unlikely(current->mempolicy && !in_interrupt())) {
+		int nid = slab_node(current->mempolicy);
+
+		if (nid != numa_node_id())
+			return __cache_alloc_node(cachep, flags, nid);
+	}
+#endif
+
 	check_irq_off();
-	ac = ac_data(cachep);
+	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
 		STATS_INC_ALLOCHIT(cachep);
 		ac->touched = 1;
@@ -2583,7 +2746,8 @@ static inline void *____cache_alloc(kmem_cache_t *cachep, gfp_t flags)
 	return objp;
 }
 
-static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags)
+static __always_inline void *
+__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 {
 	unsigned long save_flags;
 	void *objp;
@@ -2594,7 +2758,7 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags)
 	objp = ____cache_alloc(cachep, flags);
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp,
-					    __builtin_return_address(0));
+					    caller);
 	prefetchw(objp);
 	return objp;
 }
@@ -2603,19 +2767,19 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags)
 /*
  * A interface to enable slab creation on nodeid
  */
-static void *__cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid)
+static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	struct list_head *entry;
 	struct slab *slabp;
 	struct kmem_list3 *l3;
 	void *obj;
-	kmem_bufctl_t next;
 	int x;
 
 	l3 = cachep->nodelists[nodeid];
 	BUG_ON(!l3);
 
       retry:
+	check_irq_off();
 	spin_lock(&l3->list_lock);
 	entry = l3->slabs_partial.next;
 	if (entry == &l3->slabs_partial) {
@@ -2635,14 +2799,7 @@ static void *__cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 
 	BUG_ON(slabp->inuse == cachep->num);
 
-	/* get obj pointer */
-	obj = slabp->s_mem + slabp->free * cachep->objsize;
-	slabp->inuse++;
-	next = slab_bufctl(slabp)[slabp->free];
-#if DEBUG
-	slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE;
-#endif
-	slabp->free = next;
+	obj = slab_get_obj(cachep, slabp, nodeid);
 	check_slabp(cachep, slabp);
 	l3->free_objects--;
 	/* move slabp to correct slabp list: */
@@ -2673,7 +2830,7 @@ static void *__cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 /*
  * Caller needs to acquire correct kmem_list's list_lock
  */
-static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects,
+static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 		       int node)
 {
 	int i;
@@ -2682,29 +2839,14 @@ static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects,
 	for (i = 0; i < nr_objects; i++) {
 		void *objp = objpp[i];
 		struct slab *slabp;
-		unsigned int objnr;
 
-		slabp = page_get_slab(virt_to_page(objp));
+		slabp = virt_to_slab(objp);
 		l3 = cachep->nodelists[node];
 		list_del(&slabp->list);
-		objnr = (objp - slabp->s_mem) / cachep->objsize;
 		check_spinlock_acquired_node(cachep, node);
 		check_slabp(cachep, slabp);
-
-#if DEBUG
-		/* Verify that the slab belongs to the intended node */
-		WARN_ON(slabp->nodeid != node);
-
-		if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) {
-			printk(KERN_ERR "slab: double free detected in cache "
-			       "'%s', objp %p\n", cachep->name, objp);
-			BUG();
-		}
-#endif
-		slab_bufctl(slabp)[objnr] = slabp->free;
-		slabp->free = objnr;
+		slab_put_obj(cachep, slabp, objp, node);
 		STATS_DEC_ACTIVE(cachep);
-		slabp->inuse--;
 		l3->free_objects++;
 		check_slabp(cachep, slabp);
 
@@ -2726,7 +2868,7 @@ static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects,
 	}
 }
 
-static void cache_flusharray(kmem_cache_t *cachep, struct array_cache *ac)
+static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
 {
 	int batchcount;
 	struct kmem_list3 *l3;
@@ -2785,9 +2927,9 @@ static void cache_flusharray(kmem_cache_t *cachep, struct array_cache *ac)
  *
  * Called with disabled ints.
  */
-static inline void __cache_free(kmem_cache_t *cachep, void *objp)
+static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 {
-	struct array_cache *ac = ac_data(cachep);
+	struct array_cache *ac = cpu_cache_get(cachep);
 
 	check_irq_off();
 	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
@@ -2798,7 +2940,7 @@ static inline void __cache_free(kmem_cache_t *cachep, void *objp)
 #ifdef CONFIG_NUMA
 	{
 		struct slab *slabp;
-		slabp = page_get_slab(virt_to_page(objp));
+		slabp = virt_to_slab(objp);
 		if (unlikely(slabp->nodeid != numa_node_id())) {
 			struct array_cache *alien = NULL;
 			int nodeid = slabp->nodeid;
@@ -2844,9 +2986,9 @@ static inline void __cache_free(kmem_cache_t *cachep, void *objp)
  * Allocate an object from this cache.  The flags are only relevant
  * if the cache has no available objects.
  */
-void *kmem_cache_alloc(kmem_cache_t *cachep, gfp_t flags)
+void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
-	return __cache_alloc(cachep, flags);
+	return __cache_alloc(cachep, flags, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
@@ -2864,12 +3006,12 @@ EXPORT_SYMBOL(kmem_cache_alloc);
  *
  * Currently only used for dentry validation.
  */
-int fastcall kmem_ptr_validate(kmem_cache_t *cachep, void *ptr)
+int fastcall kmem_ptr_validate(struct kmem_cache *cachep, void *ptr)
 {
 	unsigned long addr = (unsigned long)ptr;
 	unsigned long min_addr = PAGE_OFFSET;
 	unsigned long align_mask = BYTES_PER_WORD - 1;
-	unsigned long size = cachep->objsize;
+	unsigned long size = cachep->buffer_size;
 	struct page *page;
 
 	if (unlikely(addr < min_addr))
@@ -2905,32 +3047,23 @@ int fastcall kmem_ptr_validate(kmem_cache_t *cachep, void *ptr)
  * New and improved: it will now make sure that the object gets
  * put on the correct node list so that there is no false sharing.
  */
-void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid)
+void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	unsigned long save_flags;
 	void *ptr;
 
-	if (nodeid == -1)
-		return __cache_alloc(cachep, flags);
-
-	if (unlikely(!cachep->nodelists[nodeid])) {
-		/* Fall back to __cache_alloc if we run into trouble */
-		printk(KERN_WARNING
-		       "slab: not allocating in inactive node %d for cache %s\n",
-		       nodeid, cachep->name);
-		return __cache_alloc(cachep, flags);
-	}
-
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
-	if (nodeid == numa_node_id())
+
+	if (nodeid == -1 || nodeid == numa_node_id() ||
+	    !cachep->nodelists[nodeid])
 		ptr = ____cache_alloc(cachep, flags);
 	else
 		ptr = __cache_alloc_node(cachep, flags, nodeid);
 	local_irq_restore(save_flags);
-	ptr =
-	    cache_alloc_debugcheck_after(cachep, flags, ptr,
-					 __builtin_return_address(0));
+
+	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr,
+					   __builtin_return_address(0));
 
 	return ptr;
 }
@@ -2938,7 +3071,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node);
 
 void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
-	kmem_cache_t *cachep;
+	struct kmem_cache *cachep;
 
 	cachep = kmem_find_general_cachep(size, flags);
 	if (unlikely(cachep == NULL))
@@ -2969,9 +3102,10 @@ EXPORT_SYMBOL(kmalloc_node);
  * platforms.  For example, on i386, it means that the memory must come
  * from the first 16MB.
  */
-void *__kmalloc(size_t size, gfp_t flags)
+static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
+					  void *caller)
 {
-	kmem_cache_t *cachep;
+	struct kmem_cache *cachep;
 
 	/* If you want to save a few bytes .text space: replace
 	 * __ with kmem_.
@@ -2981,10 +3115,27 @@ void *__kmalloc(size_t size, gfp_t flags)
 	cachep = __find_general_cachep(size, flags);
 	if (unlikely(cachep == NULL))
 		return NULL;
-	return __cache_alloc(cachep, flags);
+	return __cache_alloc(cachep, flags, caller);
+}
+
+#ifndef CONFIG_DEBUG_SLAB
+
+void *__kmalloc(size_t size, gfp_t flags)
+{
+	return __do_kmalloc(size, flags, NULL);
 }
 EXPORT_SYMBOL(__kmalloc);
 
+#else
+
+void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller)
+{
+	return __do_kmalloc(size, flags, caller);
+}
+EXPORT_SYMBOL(__kmalloc_track_caller);
+
+#endif
+
 #ifdef CONFIG_SMP
 /**
  * __alloc_percpu - allocate one copy of the object for every present
@@ -3042,7 +3193,7 @@ EXPORT_SYMBOL(__alloc_percpu);
  * Free an object which was previously allocated from this
  * cache.
  */
-void kmem_cache_free(kmem_cache_t *cachep, void *objp)
+void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
 	unsigned long flags;
 
@@ -3063,15 +3214,15 @@ EXPORT_SYMBOL(kmem_cache_free);
  */
 void kfree(const void *objp)
 {
-	kmem_cache_t *c;
+	struct kmem_cache *c;
 	unsigned long flags;
 
 	if (unlikely(!objp))
 		return;
 	local_irq_save(flags);
 	kfree_debugcheck(objp);
-	c = page_get_cache(virt_to_page(objp));
-	mutex_debug_check_no_locks_freed(objp, objp+obj_reallen(c));
+	c = virt_to_cache(objp);
+	mutex_debug_check_no_locks_freed(objp, obj_size(c));
 	__cache_free(c, (void *)objp);
 	local_irq_restore(flags);
 }
@@ -3100,13 +3251,13 @@ void free_percpu(const void *objp)
 EXPORT_SYMBOL(free_percpu);
 #endif
 
-unsigned int kmem_cache_size(kmem_cache_t *cachep)
+unsigned int kmem_cache_size(struct kmem_cache *cachep)
 {
-	return obj_reallen(cachep);
+	return obj_size(cachep);
 }
 EXPORT_SYMBOL(kmem_cache_size);
 
-const char *kmem_cache_name(kmem_cache_t *cachep)
+const char *kmem_cache_name(struct kmem_cache *cachep)
 {
 	return cachep->name;
 }
@@ -3115,7 +3266,7 @@ EXPORT_SYMBOL_GPL(kmem_cache_name);
 /*
  * This initializes kmem_list3 for all nodes.
  */
-static int alloc_kmemlist(kmem_cache_t *cachep)
+static int alloc_kmemlist(struct kmem_cache *cachep)
 {
 	int node;
 	struct kmem_list3 *l3;
@@ -3171,7 +3322,7 @@ static int alloc_kmemlist(kmem_cache_t *cachep)
 }
 
 struct ccupdate_struct {
-	kmem_cache_t *cachep;
+	struct kmem_cache *cachep;
 	struct array_cache *new[NR_CPUS];
 };
 
@@ -3181,13 +3332,13 @@ static void do_ccupdate_local(void *info)
 	struct array_cache *old;
 
 	check_irq_off();
-	old = ac_data(new->cachep);
+	old = cpu_cache_get(new->cachep);
 
 	new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()];
 	new->new[smp_processor_id()] = old;
 }
 
-static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount,
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount,
 			    int shared)
 {
 	struct ccupdate_struct new;
@@ -3208,11 +3359,11 @@ static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount,
 	smp_call_function_all_cpus(do_ccupdate_local, (void *)&new);
 
 	check_irq_on();
-	spin_lock_irq(&cachep->spinlock);
+	spin_lock(&cachep->spinlock);
 	cachep->batchcount = batchcount;
 	cachep->limit = limit;
 	cachep->shared = shared;
-	spin_unlock_irq(&cachep->spinlock);
+	spin_unlock(&cachep->spinlock);
 
 	for_each_online_cpu(i) {
 		struct array_cache *ccold = new.new[i];
@@ -3233,7 +3384,7 @@ static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount,
 	return 0;
 }
 
-static void enable_cpucache(kmem_cache_t *cachep)
+static void enable_cpucache(struct kmem_cache *cachep)
 {
 	int err;
 	int limit, shared;
@@ -3246,13 +3397,13 @@ static void enable_cpucache(kmem_cache_t *cachep)
 	 * The numbers are guessed, we should auto-tune as described by
 	 * Bonwick.
 	 */
-	if (cachep->objsize > 131072)
+	if (cachep->buffer_size > 131072)
 		limit = 1;
-	else if (cachep->objsize > PAGE_SIZE)
+	else if (cachep->buffer_size > PAGE_SIZE)
 		limit = 8;
-	else if (cachep->objsize > 1024)
+	else if (cachep->buffer_size > 1024)
 		limit = 24;
-	else if (cachep->objsize > 256)
+	else if (cachep->buffer_size > 256)
 		limit = 54;
 	else
 		limit = 120;
@@ -3267,7 +3418,7 @@ static void enable_cpucache(kmem_cache_t *cachep)
 	 */
 	shared = 0;
 #ifdef CONFIG_SMP
-	if (cachep->objsize <= PAGE_SIZE)
+	if (cachep->buffer_size <= PAGE_SIZE)
 		shared = 8;
 #endif
 
@@ -3285,7 +3436,7 @@ static void enable_cpucache(kmem_cache_t *cachep)
 		       cachep->name, -err);
 }
 
-static void drain_array_locked(kmem_cache_t *cachep, struct array_cache *ac,
+static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
 				int force, int node)
 {
 	int tofree;
@@ -3314,7 +3465,7 @@ static void drain_array_locked(kmem_cache_t *cachep, struct array_cache *ac,
  * - clear the per-cpu caches for this CPU.
  * - return freeable pages to the main free memory pool.
  *
- * If we cannot acquire the cache chain semaphore then just give up - we'll
+ * If we cannot acquire the cache chain mutex then just give up - we'll
  * try again on the next iteration.
  */
 static void cache_reap(void *unused)
@@ -3322,7 +3473,7 @@ static void cache_reap(void *unused)
 	struct list_head *walk;
 	struct kmem_list3 *l3;
 
-	if (down_trylock(&cache_chain_sem)) {
+	if (!mutex_trylock(&cache_chain_mutex)) {
 		/* Give up. Setup the next iteration. */
 		schedule_delayed_work(&__get_cpu_var(reap_work),
 				      REAPTIMEOUT_CPUC);
@@ -3330,12 +3481,12 @@ static void cache_reap(void *unused)
 	}
 
 	list_for_each(walk, &cache_chain) {
-		kmem_cache_t *searchp;
+		struct kmem_cache *searchp;
 		struct list_head *p;
 		int tofree;
 		struct slab *slabp;
 
-		searchp = list_entry(walk, kmem_cache_t, next);
+		searchp = list_entry(walk, struct kmem_cache, next);
 
 		if (searchp->flags & SLAB_NO_REAP)
 			goto next;
@@ -3344,10 +3495,10 @@ static void cache_reap(void *unused)
 
 		l3 = searchp->nodelists[numa_node_id()];
 		if (l3->alien)
-			drain_alien_cache(searchp, l3);
+			drain_alien_cache(searchp, l3->alien);
 		spin_lock_irq(&l3->list_lock);
 
-		drain_array_locked(searchp, ac_data(searchp), 0,
+		drain_array_locked(searchp, cpu_cache_get(searchp), 0,
 				   numa_node_id());
 
 		if (time_after(l3->next_reap, jiffies))
@@ -3393,7 +3544,7 @@ static void cache_reap(void *unused)
 		cond_resched();
 	}
 	check_irq_on();
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
 	drain_remote_pages();
 	/* Setup the next iteration */
 	schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
@@ -3429,7 +3580,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	loff_t n = *pos;
 	struct list_head *p;
 
-	down(&cache_chain_sem);
+	mutex_lock(&cache_chain_mutex);
 	if (!n)
 		print_slabinfo_header(m);
 	p = cache_chain.next;
@@ -3438,25 +3589,25 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		if (p == &cache_chain)
 			return NULL;
 	}
-	return list_entry(p, kmem_cache_t, next);
+	return list_entry(p, struct kmem_cache, next);
 }
 
 static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 {
-	kmem_cache_t *cachep = p;
+	struct kmem_cache *cachep = p;
 	++*pos;
 	return cachep->next.next == &cache_chain ? NULL
-	    : list_entry(cachep->next.next, kmem_cache_t, next);
+	    : list_entry(cachep->next.next, struct kmem_cache, next);
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
 }
 
 static int s_show(struct seq_file *m, void *p)
 {
-	kmem_cache_t *cachep = p;
+	struct kmem_cache *cachep = p;
 	struct list_head *q;
 	struct slab *slabp;
 	unsigned long active_objs;
@@ -3468,8 +3619,7 @@ static int s_show(struct seq_file *m, void *p)
 	int node;
 	struct kmem_list3 *l3;
 
-	check_irq_on();
-	spin_lock_irq(&cachep->spinlock);
+	spin_lock(&cachep->spinlock);
 	active_objs = 0;
 	num_slabs = 0;
 	for_each_online_node(node) {
@@ -3477,7 +3627,8 @@ static int s_show(struct seq_file *m, void *p)
 		if (!l3)
 			continue;
 
-		spin_lock(&l3->list_lock);
+		check_irq_on();
+		spin_lock_irq(&l3->list_lock);
 
 		list_for_each(q, &l3->slabs_full) {
 			slabp = list_entry(q, struct slab, list);
@@ -3502,9 +3653,10 @@ static int s_show(struct seq_file *m, void *p)
 			num_slabs++;
 		}
 		free_objects += l3->free_objects;
-		shared_avail += l3->shared->avail;
+		if (l3->shared)
+			shared_avail += l3->shared->avail;
 
-		spin_unlock(&l3->list_lock);
+		spin_unlock_irq(&l3->list_lock);
 	}
 	num_slabs += active_slabs;
 	num_objs = num_slabs * cachep->num;
@@ -3516,7 +3668,7 @@ 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->objsize,
+		   name, active_objs, num_objs, cachep->buffer_size,
 		   cachep->num, (1 << cachep->gfporder));
 	seq_printf(m, " : tunables %4u %4u %4u",
 		   cachep->limit, cachep->batchcount, cachep->shared);
@@ -3548,7 +3700,7 @@ static int s_show(struct seq_file *m, void *p)
 	}
 #endif
 	seq_putc(m, '\n');
-	spin_unlock_irq(&cachep->spinlock);
+	spin_unlock(&cachep->spinlock);
 	return 0;
 }
 
@@ -3603,10 +3755,11 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 		return -EINVAL;
 
 	/* Find the cache in the chain of caches. */
-	down(&cache_chain_sem);
+	mutex_lock(&cache_chain_mutex);
 	res = -EINVAL;
 	list_for_each(p, &cache_chain) {
-		kmem_cache_t *cachep = list_entry(p, kmem_cache_t, next);
+		struct kmem_cache *cachep = list_entry(p, struct kmem_cache,
+						       next);
 
 		if (!strcmp(cachep->name, kbuf)) {
 			if (limit < 1 ||
@@ -3620,7 +3773,7 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 			break;
 		}
 	}
-	up(&cache_chain_sem);
+	mutex_unlock(&cache_chain_mutex);
 	if (res >= 0)
 		res = count;
 	return res;
@@ -3644,5 +3797,5 @@ unsigned int ksize(const void *objp)
 	if (unlikely(objp == NULL))
 		return 0;
 
-	return obj_reallen(page_get_cache(virt_to_page(objp)));
+	return obj_size(virt_to_cache(objp));
 }