Merge branch 'master' into for-next

Fast-forward merge with Linus to be able to merge patches
based on more recent version of the tree.

1 files changed, 517 insertions, 255 deletions

diff --git a/mm/slub.c b/mm/slub.c
index f8f5e8efeb88..9f662d70eb47 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2,10 +2,11 @@
  * SLUB: A slab allocator that limits cache line use instead of queuing
  * objects in per cpu and per node lists.
  *
- * The allocator synchronizes using per slab locks and only
- * uses a centralized lock to manage a pool of partial slabs.
+ * The allocator synchronizes using per slab locks or atomic operatios
+ * and only uses a centralized lock to manage a pool of partial slabs.
  *
  * (C) 2007 SGI, Christoph Lameter
+ * (C) 2011 Linux Foundation, Christoph Lameter
  */
 
 #include <linux/mm.h>
@@ -33,15 +34,27 @@
 
 /*
  * Lock order:
- *   1. slab_lock(page)
- *   2. slab->list_lock
+ *   1. slub_lock (Global Semaphore)
+ *   2. node->list_lock
+ *   3. slab_lock(page) (Only on some arches and for debugging)
  *
- *   The slab_lock protects operations on the object of a particular
- *   slab and its metadata in the page struct. If the slab lock
- *   has been taken then no allocations nor frees can be performed
- *   on the objects in the slab nor can the slab be added or removed
- *   from the partial or full lists since this would mean modifying
- *   the page_struct of the slab.
+ *   slub_lock
+ *
+ *   The role of the slub_lock is to protect the list of all the slabs
+ *   and to synchronize major metadata changes to slab cache structures.
+ *
+ *   The slab_lock is only used for debugging and on arches that do not
+ *   have the ability to do a cmpxchg_double. It only protects the second
+ *   double word in the page struct. Meaning
+ *	A. page->freelist	-> List of object free in a page
+ *	B. page->counters	-> Counters of objects
+ *	C. page->frozen		-> frozen state
+ *
+ *   If a slab is frozen then it is exempt from list management. It is not
+ *   on any list. The processor that froze the slab is the one who can
+ *   perform list operations on the page. Other processors may put objects
+ *   onto the freelist but the processor that froze the slab is the only
+ *   one that can retrieve the objects from the page's freelist.
  *
  *   The list_lock protects the partial and full list on each node and
  *   the partial slab counter. If taken then no new slabs may be added or
@@ -54,20 +67,6 @@
  *   slabs, operations can continue without any centralized lock. F.e.
  *   allocating a long series of objects that fill up slabs does not require
  *   the list lock.
- *
- *   The lock order is sometimes inverted when we are trying to get a slab
- *   off a list. We take the list_lock and then look for a page on the list
- *   to use. While we do that objects in the slabs may be freed. We can
- *   only operate on the slab if we have also taken the slab_lock. So we use
- *   a slab_trylock() on the slab. If trylock was successful then no frees
- *   can occur anymore and we can use the slab for allocations etc. If the
- *   slab_trylock() does not succeed then frees are in progress in the slab and
- *   we must stay away from it for a while since we may cause a bouncing
- *   cacheline if we try to acquire the lock. So go onto the next slab.
- *   If all pages are busy then we may allocate a new slab instead of reusing
- *   a partial slab. A new slab has no one operating on it and thus there is
- *   no danger of cacheline contention.
- *
  *   Interrupts are disabled during allocation and deallocation in order to
  *   make the slab allocator safe to use in the context of an irq. In addition
  *   interrupts are disabled to ensure that the processor does not change
@@ -132,6 +131,9 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 /* Enable to test recovery from slab corruption on boot */
 #undef SLUB_RESILIENCY_TEST
 
+/* Enable to log cmpxchg failures */
+#undef SLUB_DEBUG_CMPXCHG
+
 /*
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -167,10 +169,11 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 
 #define OO_SHIFT	16
 #define OO_MASK		((1 << OO_SHIFT) - 1)
-#define MAX_OBJS_PER_PAGE	65535 /* since page.objects is u16 */
+#define MAX_OBJS_PER_PAGE	32767 /* since page.objects is u15 */
 
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
+#define __CMPXCHG_DOUBLE	0x40000000UL /* Use cmpxchg_double */
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -343,11 +346,99 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
 	return x.x & OO_MASK;
 }
 
+/*
+ * Per slab locking using the pagelock
+ */
+static __always_inline void slab_lock(struct page *page)
+{
+	bit_spin_lock(PG_locked, &page->flags);
+}
+
+static __always_inline void slab_unlock(struct page *page)
+{
+	__bit_spin_unlock(PG_locked, &page->flags);
+}
+
+/* Interrupts must be disabled (for the fallback code to work right) */
+static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
+		void *freelist_old, unsigned long counters_old,
+		void *freelist_new, unsigned long counters_new,
+		const char *n)
+{
+	VM_BUG_ON(!irqs_disabled());
+#ifdef CONFIG_CMPXCHG_DOUBLE
+	if (s->flags & __CMPXCHG_DOUBLE) {
+		if (cmpxchg_double(&page->freelist,
+			freelist_old, counters_old,
+			freelist_new, counters_new))
+		return 1;
+	} else
+#endif
+	{
+		slab_lock(page);
+		if (page->freelist == freelist_old && page->counters == counters_old) {
+			page->freelist = freelist_new;
+			page->counters = counters_new;
+			slab_unlock(page);
+			return 1;
+		}
+		slab_unlock(page);
+	}
+
+	cpu_relax();
+	stat(s, CMPXCHG_DOUBLE_FAIL);
+
+#ifdef SLUB_DEBUG_CMPXCHG
+	printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name);
+#endif
+
+	return 0;
+}
+
+static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
+		void *freelist_old, unsigned long counters_old,
+		void *freelist_new, unsigned long counters_new,
+		const char *n)
+{
+#ifdef CONFIG_CMPXCHG_DOUBLE
+	if (s->flags & __CMPXCHG_DOUBLE) {
+		if (cmpxchg_double(&page->freelist,
+			freelist_old, counters_old,
+			freelist_new, counters_new))
+		return 1;
+	} else
+#endif
+	{
+		unsigned long flags;
+
+		local_irq_save(flags);
+		slab_lock(page);
+		if (page->freelist == freelist_old && page->counters == counters_old) {
+			page->freelist = freelist_new;
+			page->counters = counters_new;
+			slab_unlock(page);
+			local_irq_restore(flags);
+			return 1;
+		}
+		slab_unlock(page);
+		local_irq_restore(flags);
+	}
+
+	cpu_relax();
+	stat(s, CMPXCHG_DOUBLE_FAIL);
+
+#ifdef SLUB_DEBUG_CMPXCHG
+	printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name);
+#endif
+
+	return 0;
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 /*
  * Determine a map of object in use on a page.
  *
- * Slab lock or node listlock must be held to guarantee that the page does
+ * Node listlock must be held to guarantee that the page does
  * not vanish from under us.
  */
 static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
@@ -610,7 +701,7 @@ static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes)
 		return check_bytes8(start, value, bytes);
 
 	value64 = value | value << 8 | value << 16 | value << 24;
-	value64 = value64 | value64 << 32;
+	value64 = (value64 & 0xffffffff) | value64 << 32;
 	prefix = 8 - ((unsigned long)start) % 8;
 
 	if (prefix) {
@@ -838,10 +929,11 @@ static int check_slab(struct kmem_cache *s, struct page *page)
 static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 {
 	int nr = 0;
-	void *fp = page->freelist;
+	void *fp;
 	void *object = NULL;
 	unsigned long max_objects;
 
+	fp = page->freelist;
 	while (fp && nr <= page->objects) {
 		if (fp == search)
 			return 1;
@@ -946,26 +1038,27 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 
 /*
  * Tracking of fully allocated slabs for debugging purposes.
+ *
+ * list_lock must be held.
  */
-static void add_full(struct kmem_cache_node *n, struct page *page)
+static void add_full(struct kmem_cache *s,
+	struct kmem_cache_node *n, struct page *page)
 {
-	spin_lock(&n->list_lock);
+	if (!(s->flags & SLAB_STORE_USER))
+		return;
+
 	list_add(&page->lru, &n->full);
-	spin_unlock(&n->list_lock);
 }
 
+/*
+ * list_lock must be held.
+ */
 static void remove_full(struct kmem_cache *s, struct page *page)
 {
-	struct kmem_cache_node *n;
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
-	n = get_node(s, page_to_nid(page));
-
-	spin_lock(&n->list_lock);
 	list_del(&page->lru);
-	spin_unlock(&n->list_lock);
 }
 
 /* Tracking of the number of slabs for debugging purposes */
@@ -1021,11 +1114,6 @@ static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *pa
 	if (!check_slab(s, page))
 		goto bad;
 
-	if (!on_freelist(s, page, object)) {
-		object_err(s, page, object, "Object already allocated");
-		goto bad;
-	}
-
 	if (!check_valid_pointer(s, page, object)) {
 		object_err(s, page, object, "Freelist Pointer check fails");
 		goto bad;
@@ -1058,6 +1146,12 @@ bad:
 static noinline int free_debug_processing(struct kmem_cache *s,
 		 struct page *page, void *object, unsigned long addr)
 {
+	unsigned long flags;
+	int rc = 0;
+
+	local_irq_save(flags);
+	slab_lock(page);
+
 	if (!check_slab(s, page))
 		goto fail;
 
@@ -1072,7 +1166,7 @@ static noinline int free_debug_processing(struct kmem_cache *s,
 	}
 
 	if (!check_object(s, page, object, SLUB_RED_ACTIVE))
-		return 0;
+		goto out;
 
 	if (unlikely(s != page->slab)) {
 		if (!PageSlab(page)) {
@@ -1089,18 +1183,19 @@ static noinline int free_debug_processing(struct kmem_cache *s,
 		goto fail;
 	}
 
-	/* Special debug activities for freeing objects */
-	if (!PageSlubFrozen(page) && !page->freelist)
-		remove_full(s, page);
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
 	init_object(s, object, SLUB_RED_INACTIVE);
-	return 1;
+	rc = 1;
+out:
+	slab_unlock(page);
+	local_irq_restore(flags);
+	return rc;
 
 fail:
 	slab_fix(s, "Object at 0x%p not freed", object);
-	return 0;
+	goto out;
 }
 
 static int __init setup_slub_debug(char *str)
@@ -1200,7 +1295,9 @@ static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 			{ return 1; }
 static inline int check_object(struct kmem_cache *s, struct page *page,
 			void *object, u8 val) { return 1; }
-static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
+static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
+					struct page *page) {}
+static inline void remove_full(struct kmem_cache *s, struct page *page) {}
 static inline unsigned long kmem_cache_flags(unsigned long objsize,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
@@ -1252,6 +1349,11 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	struct kmem_cache_order_objects oo = s->oo;
 	gfp_t alloc_gfp;
 
+	flags &= gfp_allowed_mask;
+
+	if (flags & __GFP_WAIT)
+		local_irq_enable();
+
 	flags |= s->allocflags;
 
 	/*
@@ -1268,12 +1370,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 		 * Try a lower order alloc if possible
 		 */
 		page = alloc_slab_page(flags, node, oo);
-		if (!page)
-			return NULL;
 
-		stat(s, ORDER_FALLBACK);
+		if (page)
+			stat(s, ORDER_FALLBACK);
 	}
 
+	if (flags & __GFP_WAIT)
+		local_irq_disable();
+
+	if (!page)
+		return NULL;
+
 	if (kmemcheck_enabled
 		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
 		int pages = 1 << oo_order(oo);
@@ -1341,6 +1448,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	page->freelist = start;
 	page->inuse = 0;
+	page->frozen = 1;
 out:
 	return page;
 }
@@ -1418,77 +1526,87 @@ static void discard_slab(struct kmem_cache *s, struct page *page)
 }
 
 /*
- * Per slab locking using the pagelock
- */
-static __always_inline void slab_lock(struct page *page)
-{
-	bit_spin_lock(PG_locked, &page->flags);
-}
-
-static __always_inline void slab_unlock(struct page *page)
-{
-	__bit_spin_unlock(PG_locked, &page->flags);
-}
-
-static __always_inline int slab_trylock(struct page *page)
-{
-	int rc = 1;
-
-	rc = bit_spin_trylock(PG_locked, &page->flags);
-	return rc;
-}
-
-/*
- * Management of partially allocated slabs
+ * Management of partially allocated slabs.
+ *
+ * list_lock must be held.
  */
-static void add_partial(struct kmem_cache_node *n,
+static inline void add_partial(struct kmem_cache_node *n,
 				struct page *page, int tail)
 {
-	spin_lock(&n->list_lock);
 	n->nr_partial++;
 	if (tail)
 		list_add_tail(&page->lru, &n->partial);
 	else
 		list_add(&page->lru, &n->partial);
-	spin_unlock(&n->list_lock);
 }
 
-static inline void __remove_partial(struct kmem_cache_node *n,
+/*
+ * list_lock must be held.
+ */
+static inline void remove_partial(struct kmem_cache_node *n,
 					struct page *page)
 {
 	list_del(&page->lru);
 	n->nr_partial--;
 }
 
-static void remove_partial(struct kmem_cache *s, struct page *page)
-{
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-	spin_lock(&n->list_lock);
-	__remove_partial(n, page);
-	spin_unlock(&n->list_lock);
-}
-
 /*
- * Lock slab and remove from the partial list.
+ * Lock slab, remove from the partial list and put the object into the
+ * per cpu freelist.
  *
  * Must hold list_lock.
  */
-static inline int lock_and_freeze_slab(struct kmem_cache_node *n,
-							struct page *page)
+static inline int acquire_slab(struct kmem_cache *s,
+		struct kmem_cache_node *n, struct page *page)
 {
-	if (slab_trylock(page)) {
-		__remove_partial(n, page);
-		__SetPageSlubFrozen(page);
+	void *freelist;
+	unsigned long counters;
+	struct page new;
+
+	/*
+	 * Zap the freelist and set the frozen bit.
+	 * The old freelist is the list of objects for the
+	 * per cpu allocation list.
+	 */
+	do {
+		freelist = page->freelist;
+		counters = page->counters;
+		new.counters = counters;
+		new.inuse = page->objects;
+
+		VM_BUG_ON(new.frozen);
+		new.frozen = 1;
+
+	} while (!__cmpxchg_double_slab(s, page,
+			freelist, counters,
+			NULL, new.counters,
+			"lock and freeze"));
+
+	remove_partial(n, page);
+
+	if (freelist) {
+		/* Populate the per cpu freelist */
+		this_cpu_write(s->cpu_slab->freelist, freelist);
+		this_cpu_write(s->cpu_slab->page, page);
+		this_cpu_write(s->cpu_slab->node, page_to_nid(page));
 		return 1;
+	} else {
+		/*
+		 * Slab page came from the wrong list. No object to allocate
+		 * from. Put it onto the correct list and continue partial
+		 * scan.
+		 */
+		printk(KERN_ERR "SLUB: %s : Page without available objects on"
+			" partial list\n", s->name);
+		return 0;
 	}
-	return 0;
 }
 
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static struct page *get_partial_node(struct kmem_cache_node *n)
+static struct page *get_partial_node(struct kmem_cache *s,
+					struct kmem_cache_node *n)
 {
 	struct page *page;
 
@@ -1503,7 +1621,7 @@ static struct page *get_partial_node(struct kmem_cache_node *n)
 
 	spin_lock(&n->list_lock);
 	list_for_each_entry(page, &n->partial, lru)
-		if (lock_and_freeze_slab(n, page))
+		if (acquire_slab(s, n, page))
 			goto out;
 	page = NULL;
 out:
@@ -1554,7 +1672,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > s->min_partial) {
-			page = get_partial_node(n);
+			page = get_partial_node(s, n);
 			if (page) {
 				put_mems_allowed();
 				return page;
@@ -1574,60 +1692,13 @@ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
 	struct page *page;
 	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-	page = get_partial_node(get_node(s, searchnode));
+	page = get_partial_node(s, get_node(s, searchnode));
 	if (page || node != NUMA_NO_NODE)
 		return page;
 
 	return get_any_partial(s, flags);
 }
 
-/*
- * Move a page back to the lists.
- *
- * Must be called with the slab lock held.
- *
- * On exit the slab lock will have been dropped.
- */
-static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
-	__releases(bitlock)
-{
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-	__ClearPageSlubFrozen(page);
-	if (page->inuse) {
-
-		if (page->freelist) {
-			add_partial(n, page, tail);
-			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
-		} else {
-			stat(s, DEACTIVATE_FULL);
-			if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER))
-				add_full(n, page);
-		}
-		slab_unlock(page);
-	} else {
-		stat(s, DEACTIVATE_EMPTY);
-		if (n->nr_partial < s->min_partial) {
-			/*
-			 * Adding an empty slab to the partial slabs in order
-			 * to avoid page allocator overhead. This slab needs
-			 * to come after the other slabs with objects in
-			 * so that the others get filled first. That way the
-			 * size of the partial list stays small.
-			 *
-			 * kmem_cache_shrink can reclaim any empty slabs from
-			 * the partial list.
-			 */
-			add_partial(n, page, 1);
-			slab_unlock(page);
-		} else {
-			slab_unlock(page);
-			stat(s, FREE_SLAB);
-			discard_slab(s, page);
-		}
-	}
-}
-
 #ifdef CONFIG_PREEMPT
 /*
  * Calculate the next globally unique transaction for disambiguiation
@@ -1697,42 +1768,161 @@ void init_kmem_cache_cpus(struct kmem_cache *s)
 /*
  * Remove the cpu slab
  */
+
+/*
+ * Remove the cpu slab
+ */
 static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
-	__releases(bitlock)
 {
+	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
 	struct page *page = c->page;
-	int tail = 1;
-
-	if (page->freelist)
+	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+	int lock = 0;
+	enum slab_modes l = M_NONE, m = M_NONE;
+	void *freelist;
+	void *nextfree;
+	int tail = 0;
+	struct page new;
+	struct page old;
+
+	if (page->freelist) {
 		stat(s, DEACTIVATE_REMOTE_FREES);
+		tail = 1;
+	}
+
+	c->tid = next_tid(c->tid);
+	c->page = NULL;
+	freelist = c->freelist;
+	c->freelist = NULL;
+
 	/*
-	 * Merge cpu freelist into slab freelist. Typically we get here
-	 * because both freelists are empty. So this is unlikely
-	 * to occur.
+	 * Stage one: Free all available per cpu objects back
+	 * to the page freelist while it is still frozen. Leave the
+	 * last one.
+	 *
+	 * There is no need to take the list->lock because the page
+	 * is still frozen.
+	 */
+	while (freelist && (nextfree = get_freepointer(s, freelist))) {
+		void *prior;
+		unsigned long counters;
+
+		do {
+			prior = page->freelist;
+			counters = page->counters;
+			set_freepointer(s, freelist, prior);
+			new.counters = counters;
+			new.inuse--;
+			VM_BUG_ON(!new.frozen);
+
+		} while (!__cmpxchg_double_slab(s, page,
+			prior, counters,
+			freelist, new.counters,
+			"drain percpu freelist"));
+
+		freelist = nextfree;
+	}
+
+	/*
+	 * Stage two: Ensure that the page is unfrozen while the
+	 * list presence reflects the actual number of objects
+	 * during unfreeze.
+	 *
+	 * We setup the list membership and then perform a cmpxchg
+	 * with the count. If there is a mismatch then the page
+	 * is not unfrozen but the page is on the wrong list.
+	 *
+	 * Then we restart the process which may have to remove
+	 * the page from the list that we just put it on again
+	 * because the number of objects in the slab may have
+	 * changed.
 	 */
-	while (unlikely(c->freelist)) {
-		void **object;
+redo:
 
-		tail = 0;	/* Hot objects. Put the slab first */
+	old.freelist = page->freelist;
+	old.counters = page->counters;
+	VM_BUG_ON(!old.frozen);
 
-		/* Retrieve object from cpu_freelist */
-		object = c->freelist;
-		c->freelist = get_freepointer(s, c->freelist);
+	/* Determine target state of the slab */
+	new.counters = old.counters;
+	if (freelist) {
+		new.inuse--;
+		set_freepointer(s, freelist, old.freelist);
+		new.freelist = freelist;
+	} else
+		new.freelist = old.freelist;
 
-		/* And put onto the regular freelist */
-		set_freepointer(s, object, page->freelist);
-		page->freelist = object;
-		page->inuse--;
+	new.frozen = 0;
+
+	if (!new.inuse && n->nr_partial > s->min_partial)
+		m = M_FREE;
+	else if (new.freelist) {
+		m = M_PARTIAL;
+		if (!lock) {
+			lock = 1;
+			/*
+			 * Taking the spinlock removes the possiblity
+			 * that acquire_slab() will see a slab page that
+			 * is frozen
+			 */
+			spin_lock(&n->list_lock);
+		}
+	} else {
+		m = M_FULL;
+		if (kmem_cache_debug(s) && !lock) {
+			lock = 1;
+			/*
+			 * This also ensures that the scanning of full
+			 * slabs from diagnostic functions will not see
+			 * any frozen slabs.
+			 */
+			spin_lock(&n->list_lock);
+		}
+	}
+
+	if (l != m) {
+
+		if (l == M_PARTIAL)
+
+			remove_partial(n, page);
+
+		else if (l == M_FULL)
+
+			remove_full(s, page);
+
+		if (m == M_PARTIAL) {
+
+			add_partial(n, page, tail);
+			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
+
+		} else if (m == M_FULL) {
+
+			stat(s, DEACTIVATE_FULL);
+			add_full(s, n, page);
+
+		}
+	}
+
+	l = m;
+	if (!__cmpxchg_double_slab(s, page,
+				old.freelist, old.counters,
+				new.freelist, new.counters,
+				"unfreezing slab"))
+		goto redo;
+
+	if (lock)
+		spin_unlock(&n->list_lock);
+
+	if (m == M_FREE) {
+		stat(s, DEACTIVATE_EMPTY);
+		discard_slab(s, page);
+		stat(s, FREE_SLAB);
 	}
-	c->page = NULL;
-	c->tid = next_tid(c->tid);
-	unfreeze_slab(s, page, tail);
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	stat(s, CPUSLAB_FLUSH);
-	slab_lock(c->page);
 	deactivate_slab(s, c);
 }
 
@@ -1861,6 +2051,8 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	void **object;
 	struct page *page;
 	unsigned long flags;
+	struct page new;
+	unsigned long counters;
 
 	local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -1879,72 +2071,97 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (!page)
 		goto new_slab;
 
-	slab_lock(page);
-	if (unlikely(!node_match(c, node)))
-		goto another_slab;
+	if (unlikely(!node_match(c, node))) {
+		stat(s, ALLOC_NODE_MISMATCH);
+		deactivate_slab(s, c);
+		goto new_slab;
+	}
+
+	stat(s, ALLOC_SLOWPATH);
+
+	do {
+		object = page->freelist;
+		counters = page->counters;
+		new.counters = counters;
+		VM_BUG_ON(!new.frozen);
+
+		/*
+		 * If there is no object left then we use this loop to
+		 * deactivate the slab which is simple since no objects
+		 * are left in the slab and therefore we do not need to
+		 * put the page back onto the partial list.
+		 *
+		 * If there are objects left then we retrieve them
+		 * and use them to refill the per cpu queue.
+		*/
+
+		new.inuse = page->objects;
+		new.frozen = object != NULL;
+
+	} while (!__cmpxchg_double_slab(s, page,
+			object, counters,
+			NULL, new.counters,
+			"__slab_alloc"));
+
+	if (unlikely(!object)) {
+		c->page = NULL;
+		stat(s, DEACTIVATE_BYPASS);
+		goto new_slab;
+	}
 
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
-	object = page->freelist;
-	if (unlikely(!object))
-		goto another_slab;
-	if (kmem_cache_debug(s))
-		goto debug;
-
+	VM_BUG_ON(!page->frozen);
 	c->freelist = get_freepointer(s, object);
-	page->inuse = page->objects;
-	page->freelist = NULL;
-
-	slab_unlock(page);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
-	stat(s, ALLOC_SLOWPATH);
 	return object;
 
-another_slab:
-	deactivate_slab(s, c);
-
 new_slab:
 	page = get_partial(s, gfpflags, node);
 	if (page) {
 		stat(s, ALLOC_FROM_PARTIAL);
-		c->node = page_to_nid(page);
-		c->page = page;
+		object = c->freelist;
+
+		if (kmem_cache_debug(s))
+			goto debug;
 		goto load_freelist;
 	}
 
-	gfpflags &= gfp_allowed_mask;
-	if (gfpflags & __GFP_WAIT)
-		local_irq_enable();
-
 	page = new_slab(s, gfpflags, node);
 
-	if (gfpflags & __GFP_WAIT)
-		local_irq_disable();
-
 	if (page) {
 		c = __this_cpu_ptr(s->cpu_slab);
-		stat(s, ALLOC_SLAB);
 		if (c->page)
 			flush_slab(s, c);
 
-		slab_lock(page);
-		__SetPageSlubFrozen(page);
+		/*
+		 * No other reference to the page yet so we can
+		 * muck around with it freely without cmpxchg
+		 */
+		object = page->freelist;
+		page->freelist = NULL;
+		page->inuse = page->objects;
+
+		stat(s, ALLOC_SLAB);
 		c->node = page_to_nid(page);
 		c->page = page;
+
+		if (kmem_cache_debug(s))
+			goto debug;
 		goto load_freelist;
 	}
 	if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
 		slab_out_of_memory(s, gfpflags, node);
 	local_irq_restore(flags);
 	return NULL;
+
 debug:
-	if (!alloc_debug_processing(s, page, object, addr))
-		goto another_slab;
+	if (!object || !alloc_debug_processing(s, page, object, addr))
+		goto new_slab;
 
-	page->inuse++;
-	page->freelist = get_freepointer(s, object);
+	c->freelist = get_freepointer(s, object);
 	deactivate_slab(s, c);
 	c->page = NULL;
 	c->node = NUMA_NO_NODE;
@@ -2096,52 +2313,89 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 {
 	void *prior;
 	void **object = (void *)x;
-	unsigned long flags;
+	int was_frozen;
+	int inuse;
+	struct page new;
+	unsigned long counters;
+	struct kmem_cache_node *n = NULL;
+	unsigned long uninitialized_var(flags);
 
-	local_irq_save(flags);
-	slab_lock(page);
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
-		goto out_unlock;
+		return;
 
-	prior = page->freelist;
-	set_freepointer(s, object, prior);
-	page->freelist = object;
-	page->inuse--;
+	do {
+		prior = page->freelist;
+		counters = page->counters;
+		set_freepointer(s, object, prior);
+		new.counters = counters;
+		was_frozen = new.frozen;
+		new.inuse--;
+		if ((!new.inuse || !prior) && !was_frozen && !n) {
+                        n = get_node(s, page_to_nid(page));
+			/*
+			 * Speculatively acquire the list_lock.
+			 * If the cmpxchg does not succeed then we may
+			 * drop the list_lock without any processing.
+			 *
+			 * Otherwise the list_lock will synchronize with
+			 * other processors updating the list of slabs.
+			 */
+                        spin_lock_irqsave(&n->list_lock, flags);
+		}
+		inuse = new.inuse;
 
-	if (unlikely(PageSlubFrozen(page))) {
-		stat(s, FREE_FROZEN);
-		goto out_unlock;
-	}
+	} while (!cmpxchg_double_slab(s, page,
+		prior, counters,
+		object, new.counters,
+		"__slab_free"));
 
-	if (unlikely(!page->inuse))
-		goto slab_empty;
+	if (likely(!n)) {
+                /*
+		 * The list lock was not taken therefore no list
+		 * activity can be necessary.
+		 */
+                if (was_frozen)
+                        stat(s, FREE_FROZEN);
+                return;
+        }
 
 	/*
-	 * Objects left in the slab. If it was not on the partial list before
-	 * then add it.
+	 * was_frozen may have been set after we acquired the list_lock in
+	 * an earlier loop. So we need to check it here again.
 	 */
-	if (unlikely(!prior)) {
-		add_partial(get_node(s, page_to_nid(page)), page, 1);
-		stat(s, FREE_ADD_PARTIAL);
-	}
+	if (was_frozen)
+		stat(s, FREE_FROZEN);
+	else {
+		if (unlikely(!inuse && n->nr_partial > s->min_partial))
+                        goto slab_empty;
 
-out_unlock:
-	slab_unlock(page);
-	local_irq_restore(flags);
+		/*
+		 * Objects left in the slab. If it was not on the partial list before
+		 * then add it.
+		 */
+		if (unlikely(!prior)) {
+			remove_full(s, page);
+			add_partial(n, page, 0);
+			stat(s, FREE_ADD_PARTIAL);
+		}
+	}
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	return;
 
 slab_empty:
 	if (prior) {
 		/*
-		 * Slab still on the partial list.
+		 * Slab on the partial list.
 		 */
-		remove_partial(s, page);
+		remove_partial(n, page);
 		stat(s, FREE_REMOVE_PARTIAL);
-	}
-	slab_unlock(page);
-	local_irq_restore(flags);
+	} else
+		/* Slab must be on the full list */
+		remove_full(s, page);
+
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
 	discard_slab(s, page);
 }
@@ -2415,7 +2669,6 @@ static void early_kmem_cache_node_alloc(int node)
 {
 	struct page *page;
 	struct kmem_cache_node *n;
-	unsigned long flags;
 
 	BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
 
@@ -2433,6 +2686,7 @@ static void early_kmem_cache_node_alloc(int node)
 	BUG_ON(!n);
 	page->freelist = get_freepointer(kmem_cache_node, n);
 	page->inuse++;
+	page->frozen = 0;
 	kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG
 	init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
@@ -2441,14 +2695,7 @@ static void early_kmem_cache_node_alloc(int node)
 	init_kmem_cache_node(n, kmem_cache_node);
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
-	/*
-	 * lockdep requires consistent irq usage for each lock
-	 * so even though there cannot be a race this early in
-	 * the boot sequence, we still disable irqs.
-	 */
-	local_irq_save(flags);
 	add_partial(n, page, 0);
-	local_irq_restore(flags);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2654,6 +2901,12 @@ static int kmem_cache_open(struct kmem_cache *s,
 		}
 	}
 
+#ifdef CONFIG_CMPXCHG_DOUBLE
+	if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
+		/* Enable fast mode */
+		s->flags |= __CMPXCHG_DOUBLE;
+#endif
+
 	/*
 	 * The larger the object size is, the more pages we want on the partial
 	 * list to avoid pounding the page allocator excessively.
@@ -2726,7 +2979,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			__remove_partial(n, page);
+			remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
@@ -3094,14 +3347,8 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			if (!page->inuse && slab_trylock(page)) {
-				/*
-				 * Must hold slab lock here because slab_free
-				 * may have freed the last object and be
-				 * waiting to release the slab.
-				 */
-				__remove_partial(n, page);
-				slab_unlock(page);
+			if (!page->inuse) {
+				remove_partial(n, page);
 				discard_slab(s, page);
 			} else {
 				list_move(&page->lru,
@@ -3689,12 +3936,9 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 static void validate_slab_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {
-	if (slab_trylock(page)) {
-		validate_slab(s, page, map);
-		slab_unlock(page);
-	} else
-		printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n",
-			s->name, page);
+	slab_lock(page);
+	validate_slab(s, page, map);
+	slab_unlock(page);
 }
 
 static int validate_slab_node(struct kmem_cache *s,
@@ -4342,8 +4586,10 @@ static ssize_t sanity_checks_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
 	s->flags &= ~SLAB_DEBUG_FREE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_DEBUG_FREE;
+	}
 	return length;
 }
 SLAB_ATTR(sanity_checks);
@@ -4357,8 +4603,10 @@ static ssize_t trace_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
 	s->flags &= ~SLAB_TRACE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_TRACE;
+	}
 	return length;
 }
 SLAB_ATTR(trace);
@@ -4375,8 +4623,10 @@ static ssize_t red_zone_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_RED_ZONE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_RED_ZONE;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4394,8 +4644,10 @@ static ssize_t poison_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_POISON;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_POISON;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4413,8 +4665,10 @@ static ssize_t store_user_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_STORE_USER;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_STORE_USER;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4579,6 +4833,7 @@ STAT_ATTR(FREE_REMOVE_PARTIAL, free_remove_partial);
 STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial);
 STAT_ATTR(ALLOC_SLAB, alloc_slab);
 STAT_ATTR(ALLOC_REFILL, alloc_refill);
+STAT_ATTR(ALLOC_NODE_MISMATCH, alloc_node_mismatch);
 STAT_ATTR(FREE_SLAB, free_slab);
 STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush);
 STAT_ATTR(DEACTIVATE_FULL, deactivate_full);
@@ -4586,7 +4841,10 @@ STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty);
 STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
 STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
 STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
+STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass);
 STAT_ATTR(ORDER_FALLBACK, order_fallback);
+STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
+STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -4636,6 +4894,7 @@ static struct attribute *slab_attrs[] = {
 	&alloc_from_partial_attr.attr,
 	&alloc_slab_attr.attr,
 	&alloc_refill_attr.attr,
+	&alloc_node_mismatch_attr.attr,
 	&free_slab_attr.attr,
 	&cpuslab_flush_attr.attr,
 	&deactivate_full_attr.attr,
@@ -4643,7 +4902,10 @@ static struct attribute *slab_attrs[] = {
 	&deactivate_to_head_attr.attr,
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
+	&deactivate_bypass_attr.attr,
 	&order_fallback_attr.attr,
+	&cmpxchg_double_fail_attr.attr,
+	&cmpxchg_double_cpu_fail_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,