X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fslub.c;h=a3e2d552ff46374d8bf9d10f01a3c5f09c533aad;hb=73d342b169db700b5a6ad626fe4b86911efec8db;hp=b49570ca08b5de961332b466a9d2cfe959a84ecf;hpb=27d9e4e94862c89d171cf70911b4f11ad69fb54e;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/slub.c b/mm/slub.c
index b49570c..a3e2d55 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5,7 +5,7 @@
  * The allocator synchronizes using per slab locks and only
  * uses a centralized lock to manage a pool of partial slabs.
  *
- * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 SGI, Christoph Lameter
  */
 
 #include <linux/mm.h>
@@ -14,13 +14,17 @@
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
+#include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/memory.h>
+#include <linux/math64.h>
+#include <linux/fault-inject.h>
 
 /*
  * Lock order:
@@ -100,44 +104,12 @@
  * 			the fast path and disables lockless freelists.
  */
 
-#define FROZEN (1 << PG_active)
-
 #ifdef CONFIG_SLUB_DEBUG
-#define SLABDEBUG (1 << PG_error)
+#define SLABDEBUG 1
 #else
 #define SLABDEBUG 0
 #endif
 
-static inline int SlabFrozen(struct page *page)
-{
-	return page->flags & FROZEN;
-}
-
-static inline void SetSlabFrozen(struct page *page)
-{
-	page->flags |= FROZEN;
-}
-
-static inline void ClearSlabFrozen(struct page *page)
-{
-	page->flags &= ~FROZEN;
-}
-
-static inline int SlabDebug(struct page *page)
-{
-	return page->flags & SLABDEBUG;
-}
-
-static inline void SetSlabDebug(struct page *page)
-{
-	page->flags |= SLABDEBUG;
-}
-
-static inline void ClearSlabDebug(struct page *page)
-{
-	page->flags &= ~SLABDEBUG;
-}
-
 /*
  * Issues still to be resolved:
  *
@@ -149,25 +121,6 @@ static inline void ClearSlabDebug(struct page *page)
 /* Enable to test recovery from slab corruption on boot */
 #undef SLUB_RESILIENCY_TEST
 
-#if PAGE_SHIFT <= 12
-
-/*
- * Small page size. Make sure that we do not fragment memory
- */
-#define DEFAULT_MAX_ORDER 1
-#define DEFAULT_MIN_OBJECTS 4
-
-#else
-
-/*
- * Large page machines are customarily able to handle larger
- * page orders.
- */
-#define DEFAULT_MAX_ORDER 2
-#define DEFAULT_MIN_OBJECTS 8
-
-#endif
-
 /*
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -201,16 +154,13 @@ static inline void ClearSlabDebug(struct page *page)
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
 
+#define OO_SHIFT	16
+#define OO_MASK		((1 << OO_SHIFT) - 1)
+#define MAX_OBJS_PER_PAGE	65535 /* since page.objects is u16 */
+
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000 /* Poison object */
 #define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
-#define __KMALLOC_CACHE		0x20000000 /* objects freed using kfree */
-#define __PAGE_ALLOC_FALLBACK	0x10000000 /* Allow fallback to page alloc */
-
-/* Not all arches define cache_line_size */
-#ifndef cache_line_size
-#define cache_line_size()	L1_CACHE_BYTES
-#endif
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -233,7 +183,7 @@ static LIST_HEAD(slab_caches);
  * Tracking user of a slab.
  */
 struct track {
-	void *addr;		/* Called from address */
+	unsigned long addr;	/* Called from address */
 	int cpu;		/* Was running on cpu */
 	int pid;		/* Pid context */
 	unsigned long when;	/* When did the operation occur */
@@ -241,7 +191,7 @@ struct track {
 
 enum track_item { TRACK_ALLOC, TRACK_FREE };
 
-#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
+#ifdef CONFIG_SLUB_DEBUG
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void sysfs_slab_remove(struct kmem_cache *);
@@ -291,6 +241,7 @@ static inline struct kmem_cache_cpu *get_cpu_slab(struct kmem_cache *s, int cpu)
 #endif
 }
 
+/* Verify that a pointer has an address that is valid within a slab page */
 static inline int check_valid_pointer(struct kmem_cache *s,
 				struct page *page, const void *object)
 {
@@ -300,7 +251,7 @@ static inline int check_valid_pointer(struct kmem_cache *s,
 		return 1;
 
 	base = page_address(page);
-	if (object < base || object >= base + s->objects * s->size ||
+	if (object < base || object >= base + page->objects * s->size ||
 		(object - base) % s->size) {
 		return 0;
 	}
@@ -326,8 +277,8 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 }
 
 /* Loop over all objects in a slab */
-#define for_each_object(__p, __s, __addr) \
-	for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+#define for_each_object(__p, __s, __addr, __objects) \
+	for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
 			__p += (__s)->size)
 
 /* Scan freelist */
@@ -340,6 +291,26 @@ static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
 	return (p - addr) / s->size;
 }
 
+static inline struct kmem_cache_order_objects oo_make(int order,
+						unsigned long size)
+{
+	struct kmem_cache_order_objects x = {
+		(order << OO_SHIFT) + (PAGE_SIZE << order) / size
+	};
+
+	return x;
+}
+
+static inline int oo_order(struct kmem_cache_order_objects x)
+{
+	return x.x >> OO_SHIFT;
+}
+
+static inline int oo_objects(struct kmem_cache_order_objects x)
+{
+	return x.x & OO_MASK;
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 /*
  * Debug settings:
@@ -401,7 +372,7 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 }
 
 static void set_track(struct kmem_cache *s, void *object,
-				enum track_item alloc, void *addr)
+			enum track_item alloc, unsigned long addr)
 {
 	struct track *p;
 
@@ -414,7 +385,7 @@ static void set_track(struct kmem_cache *s, void *object,
 	if (addr) {
 		p->addr = addr;
 		p->cpu = smp_processor_id();
-		p->pid = current ? current->pid : -1;
+		p->pid = current->pid;
 		p->when = jiffies;
 	} else
 		memset(p, 0, sizeof(struct track));
@@ -425,8 +396,8 @@ static void init_tracking(struct kmem_cache *s, void *object)
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
-	set_track(s, object, TRACK_FREE, NULL);
-	set_track(s, object, TRACK_ALLOC, NULL);
+	set_track(s, object, TRACK_FREE, 0UL);
+	set_track(s, object, TRACK_ALLOC, 0UL);
 }
 
 static void print_track(const char *s, struct track *t)
@@ -434,9 +405,8 @@ static void print_track(const char *s, struct track *t)
 	if (!t->addr)
 		return;
 
-	printk(KERN_ERR "INFO: %s in ", s);
-	__print_symbol("%s", (unsigned long)t->addr);
-	printk(" age=%lu cpu=%u pid=%d\n", jiffies - t->when, t->cpu, t->pid);
+	printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
+		s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid);
 }
 
 static void print_tracking(struct kmem_cache *s, void *object)
@@ -450,8 +420,8 @@ static void print_tracking(struct kmem_cache *s, void *object)
 
 static void print_page_info(struct page *page)
 {
-	printk(KERN_ERR "INFO: Slab 0x%p used=%u fp=0x%p flags=0x%04lx\n",
-		page, page->inuse, page->freelist, page->flags);
+	printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
+		page, page->objects, page->inuse, page->freelist, page->flags);
 
 }
 
@@ -496,7 +466,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	if (p > addr + 16)
 		print_section("Bytes b4", p - 16, 16);
 
-	print_section("Object", p, min(s->objsize, 128));
+	print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE));
 
 	if (s->flags & SLAB_RED_ZONE)
 		print_section("Redzone", p + s->objsize,
@@ -520,7 +490,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 static void object_err(struct kmem_cache *s, struct page *page,
 			u8 *object, char *reason)
 {
-	slab_bug(s, reason);
+	slab_bug(s, "%s", reason);
 	print_trailer(s, page, object);
 }
 
@@ -532,7 +502,7 @@ static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
-	slab_bug(s, fmt);
+	slab_bug(s, "%s", buf);
 	print_page_info(page);
 	dump_stack();
 }
@@ -619,7 +589,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
  * 	A. Free pointer (if we cannot overwrite object on free)
  * 	B. Tracking data for SLAB_STORE_USER
  * 	C. Padding to reach required alignment boundary or at mininum
- * 		one word if debuggin is on to be able to detect writes
+ * 		one word if debugging is on to be able to detect writes
  * 		before the word boundary.
  *
  *	Padding is done using 0x5a (POISON_INUSE)
@@ -651,6 +621,7 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 				p + off, POISON_INUSE, s->size - off);
 }
 
+/* Check the pad bytes at the end of a slab page */
 static int slab_pad_check(struct kmem_cache *s, struct page *page)
 {
 	u8 *start;
@@ -663,20 +634,20 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		return 1;
 
 	start = page_address(page);
-	end = start + (PAGE_SIZE << s->order);
-	length = s->objects * s->size;
-	remainder = end - (start + length);
+	length = (PAGE_SIZE << compound_order(page));
+	end = start + length;
+	remainder = length % s->size;
 	if (!remainder)
 		return 1;
 
-	fault = check_bytes(start + length, POISON_INUSE, remainder);
+	fault = check_bytes(end - remainder, POISON_INUSE, remainder);
 	if (!fault)
 		return 1;
 	while (end > fault && end[-1] == POISON_INUSE)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding", start, length);
+	print_section("Padding", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, start, end);
 	return 0;
@@ -726,7 +697,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 	if (!check_valid_pointer(s, page, get_freepointer(s, p))) {
 		object_err(s, page, p, "Freepointer corrupt");
 		/*
-		 * No choice but to zap it and thus loose the remainder
+		 * No choice but to zap it and thus lose the remainder
 		 * of the free objects in this slab. May cause
 		 * another error because the object count is now wrong.
 		 */
@@ -738,15 +709,24 @@ static int check_object(struct kmem_cache *s, struct page *page,
 
 static int check_slab(struct kmem_cache *s, struct page *page)
 {
+	int maxobj;
+
 	VM_BUG_ON(!irqs_disabled());
 
 	if (!PageSlab(page)) {
 		slab_err(s, page, "Not a valid slab page");
 		return 0;
 	}
-	if (page->inuse > s->objects) {
+
+	maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+	if (page->objects > maxobj) {
+		slab_err(s, page, "objects %u > max %u",
+			s->name, page->objects, maxobj);
+		return 0;
+	}
+	if (page->inuse > page->objects) {
 		slab_err(s, page, "inuse %u > max %u",
-			s->name, page->inuse, s->objects);
+			s->name, page->inuse, page->objects);
 		return 0;
 	}
 	/* Slab_pad_check fixes things up after itself */
@@ -763,8 +743,9 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 	int nr = 0;
 	void *fp = page->freelist;
 	void *object = NULL;
+	unsigned long max_objects;
 
-	while (fp && nr <= s->objects) {
+	while (fp && nr <= page->objects) {
 		if (fp == search)
 			return 1;
 		if (!check_valid_pointer(s, page, fp)) {
@@ -776,7 +757,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 			} else {
 				slab_err(s, page, "Freepointer corrupt");
 				page->freelist = NULL;
-				page->inuse = s->objects;
+				page->inuse = page->objects;
 				slab_fix(s, "Freelist cleared");
 				return 0;
 			}
@@ -787,16 +768,27 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 		nr++;
 	}
 
-	if (page->inuse != s->objects - nr) {
+	max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+	if (max_objects > MAX_OBJS_PER_PAGE)
+		max_objects = MAX_OBJS_PER_PAGE;
+
+	if (page->objects != max_objects) {
+		slab_err(s, page, "Wrong number of objects. Found %d but "
+			"should be %d", page->objects, max_objects);
+		page->objects = max_objects;
+		slab_fix(s, "Number of objects adjusted.");
+	}
+	if (page->inuse != page->objects - nr) {
 		slab_err(s, page, "Wrong object count. Counter is %d but "
-			"counted were %d", page->inuse, s->objects - nr);
-		page->inuse = s->objects - nr;
+			"counted were %d", page->inuse, page->objects - nr);
+		page->inuse = page->objects - nr;
 		slab_fix(s, "Object count adjusted.");
 	}
 	return search == NULL;
 }
 
-static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc)
+static void trace(struct kmem_cache *s, struct page *page, void *object,
+								int alloc)
 {
 	if (s->flags & SLAB_TRACE) {
 		printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
@@ -836,6 +828,38 @@ static void remove_full(struct kmem_cache *s, struct page *page)
 	spin_unlock(&n->list_lock);
 }
 
+/* Tracking of the number of slabs for debugging purposes */
+static inline unsigned long slabs_node(struct kmem_cache *s, int node)
+{
+	struct kmem_cache_node *n = get_node(s, node);
+
+	return atomic_long_read(&n->nr_slabs);
+}
+
+static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
+{
+	struct kmem_cache_node *n = get_node(s, node);
+
+	/*
+	 * May be called early in order to allocate a slab for the
+	 * kmem_cache_node structure. Solve the chicken-egg
+	 * dilemma by deferring the increment of the count during
+	 * bootstrap (see early_kmem_cache_node_alloc).
+	 */
+	if (!NUMA_BUILD || n) {
+		atomic_long_inc(&n->nr_slabs);
+		atomic_long_add(objects, &n->total_objects);
+	}
+}
+static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
+{
+	struct kmem_cache_node *n = get_node(s, node);
+
+	atomic_long_dec(&n->nr_slabs);
+	atomic_long_sub(objects, &n->total_objects);
+}
+
+/* Object debug checks for alloc/free paths */
 static void setup_object_debug(struct kmem_cache *s, struct page *page,
 								void *object)
 {
@@ -847,7 +871,7 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page,
 }
 
 static int alloc_debug_processing(struct kmem_cache *s, struct page *page,
-						void *object, void *addr)
+					void *object, unsigned long addr)
 {
 	if (!check_slab(s, page))
 		goto bad;
@@ -880,14 +904,14 @@ bad:
 		 * as used avoids touching the remaining objects.
 		 */
 		slab_fix(s, "Marking all objects used");
-		page->inuse = s->objects;
+		page->inuse = page->objects;
 		page->freelist = NULL;
 	}
 	return 0;
 }
 
 static int free_debug_processing(struct kmem_cache *s, struct page *page,
-						void *object, void *addr)
+					void *object, unsigned long addr)
 {
 	if (!check_slab(s, page))
 		goto fail;
@@ -921,7 +945,7 @@ static int free_debug_processing(struct kmem_cache *s, struct page *page,
 	}
 
 	/* Special debug activities for freeing objects */
-	if (!SlabFrozen(page) && !page->freelist)
+	if (!PageSlubFrozen(page) && !page->freelist)
 		remove_full(s, page);
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
@@ -994,7 +1018,7 @@ __setup("slub_debug", setup_slub_debug);
 
 static unsigned long kmem_cache_flags(unsigned long objsize,
 	unsigned long flags, const char *name,
-	void (*ctor)(struct kmem_cache *, void *))
+	void (*ctor)(void *))
 {
 	/*
 	 * Enable debugging if selected on the kernel commandline.
@@ -1010,10 +1034,10 @@ static inline void setup_object_debug(struct kmem_cache *s,
 			struct page *page, void *object) {}
 
 static inline int alloc_debug_processing(struct kmem_cache *s,
-	struct page *page, void *object, void *addr) { return 0; }
+	struct page *page, void *object, unsigned long addr) { return 0; }
 
 static inline int free_debug_processing(struct kmem_cache *s,
-	struct page *page, void *object, void *addr) { return 0; }
+	struct page *page, void *object, unsigned long addr) { return 0; }
 
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 			{ return 1; }
@@ -1022,34 +1046,60 @@ static inline int check_object(struct kmem_cache *s, struct page *page,
 static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
 static inline unsigned long kmem_cache_flags(unsigned long objsize,
 	unsigned long flags, const char *name,
-	void (*ctor)(struct kmem_cache *, void *))
+	void (*ctor)(void *))
 {
 	return flags;
 }
 #define slub_debug 0
+
+static inline unsigned long slabs_node(struct kmem_cache *s, int node)
+							{ return 0; }
+static inline void inc_slabs_node(struct kmem_cache *s, int node,
+							int objects) {}
+static inline void dec_slabs_node(struct kmem_cache *s, int node,
+							int objects) {}
 #endif
+
 /*
  * Slab allocation and freeing
  */
+static inline struct page *alloc_slab_page(gfp_t flags, int node,
+					struct kmem_cache_order_objects oo)
+{
+	int order = oo_order(oo);
+
+	if (node == -1)
+		return alloc_pages(flags, order);
+	else
+		return alloc_pages_node(node, flags, order);
+}
+
 static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
-	int pages = 1 << s->order;
+	struct kmem_cache_order_objects oo = s->oo;
 
 	flags |= s->allocflags;
 
-	if (node == -1)
-		page = alloc_pages(flags, s->order);
-	else
-		page = alloc_pages_node(node, flags, s->order);
-
-	if (!page)
-		return NULL;
+	page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
+									oo);
+	if (unlikely(!page)) {
+		oo = s->min;
+		/*
+		 * Allocation may have failed due to fragmentation.
+		 * Try a lower order alloc if possible
+		 */
+		page = alloc_slab_page(flags, node, oo);
+		if (!page)
+			return NULL;
 
+		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+	}
+	page->objects = oo_objects(oo);
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-		pages);
+		1 << oo_order(oo));
 
 	return page;
 }
@@ -1059,13 +1109,12 @@ static void setup_object(struct kmem_cache *s, struct page *page,
 {
 	setup_object_debug(s, page, object);
 	if (unlikely(s->ctor))
-		s->ctor(s, object);
+		s->ctor(object);
 }
 
 static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
-	struct kmem_cache_node *n;
 	void *start;
 	void *last;
 	void *p;
@@ -1077,22 +1126,20 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		goto out;
 
-	n = get_node(s, page_to_nid(page));
-	if (n)
-		atomic_long_inc(&n->nr_slabs);
+	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
 	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
 			SLAB_STORE_USER | SLAB_TRACE))
-		SetSlabDebug(page);
+		__SetPageSlubDebug(page);
 
 	start = page_address(page);
 
 	if (unlikely(s->flags & SLAB_POISON))
-		memset(start, POISON_INUSE, PAGE_SIZE << s->order);
+		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
 
 	last = start;
-	for_each_object(p, s, start) {
+	for_each_object(p, s, start, page->objects) {
 		setup_object(s, page, last);
 		set_freepointer(s, last, p);
 		last = p;
@@ -1108,15 +1155,17 @@ out:
 
 static void __free_slab(struct kmem_cache *s, struct page *page)
 {
-	int pages = 1 << s->order;
+	int order = compound_order(page);
+	int pages = 1 << order;
 
-	if (unlikely(SlabDebug(page))) {
+	if (unlikely(SLABDEBUG && PageSlubDebug(page))) {
 		void *p;
 
 		slab_pad_check(s, page);
-		for_each_object(p, s, page_address(page))
+		for_each_object(p, s, page_address(page),
+						page->objects)
 			check_object(s, page, p, 0);
-		ClearSlabDebug(page);
+		__ClearPageSlubDebug(page);
 	}
 
 	mod_zone_page_state(page_zone(page),
@@ -1124,7 +1173,9 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		-pages);
 
-	__free_pages(page, s->order);
+	__ClearPageSlab(page);
+	reset_page_mapcount(page);
+	__free_pages(page, order);
 }
 
 static void rcu_free_slab(struct rcu_head *h)
@@ -1150,11 +1201,7 @@ static void free_slab(struct kmem_cache *s, struct page *page)
 
 static void discard_slab(struct kmem_cache *s, struct page *page)
 {
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-	atomic_long_dec(&n->nr_slabs);
-	reset_page_mapcount(page);
-	__ClearPageSlab(page);
+	dec_slabs_node(s, page_to_nid(page), page->objects);
 	free_slab(s, page);
 }
 
@@ -1194,8 +1241,7 @@ static void add_partial(struct kmem_cache_node *n,
 	spin_unlock(&n->list_lock);
 }
 
-static void remove_partial(struct kmem_cache *s,
-						struct page *page)
+static void remove_partial(struct kmem_cache *s, struct page *page)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
@@ -1210,12 +1256,13 @@ static void remove_partial(struct kmem_cache *s,
  *
  * Must hold list_lock.
  */
-static inline int lock_and_freeze_slab(struct kmem_cache_node *n, struct page *page)
+static inline int lock_and_freeze_slab(struct kmem_cache_node *n,
+							struct page *page)
 {
 	if (slab_trylock(page)) {
 		list_del(&page->lru);
 		n->nr_partial--;
-		SetSlabFrozen(page);
+		__SetPageSlubFrozen(page);
 		return 1;
 	}
 	return 0;
@@ -1254,7 +1301,9 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;
-	struct zone **z;
+	struct zoneref *z;
+	struct zone *zone;
+	enum zone_type high_zoneidx = gfp_zone(flags);
 	struct page *page;
 
 	/*
@@ -1268,7 +1317,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 	 * may return off node objects because partial slabs are obtained
 	 * from other nodes and filled up.
 	 *
-	 * If /sys/slab/xx/defrag_ratio is set to 100 (which makes
+	 * If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes
 	 * defrag_ratio = 1000) then every (well almost) allocation will
 	 * first attempt to defrag slab caches on other nodes. This means
 	 * scanning over all nodes to look for partial slabs which may be
@@ -1279,15 +1328,14 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	zonelist = &NODE_DATA(
-		slab_node(current->mempolicy))->node_zonelists[gfp_zone(flags)];
-	for (z = zonelist->zones; *z; z++) {
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		struct kmem_cache_node *n;
 
-		n = get_node(s, zone_to_nid(*z));
+		n = get_node(s, zone_to_nid(zone));
 
-		if (n && cpuset_zone_allowed_hardwall(*z, flags) &&
-				n->nr_partial > MIN_PARTIAL) {
+		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+				n->nr_partial > s->min_partial) {
 			page = get_partial_node(n);
 			if (page)
 				return page;
@@ -1324,7 +1372,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 	struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id());
 
-	ClearSlabFrozen(page);
+	__ClearPageSlubFrozen(page);
 	if (page->inuse) {
 
 		if (page->freelist) {
@@ -1332,20 +1380,23 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 			stat(c, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
 		} else {
 			stat(c, DEACTIVATE_FULL);
-			if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
+			if (SLABDEBUG && PageSlubDebug(page) &&
+						(s->flags & SLAB_STORE_USER))
 				add_full(n, page);
 		}
 		slab_unlock(page);
 	} else {
 		stat(c, DEACTIVATE_EMPTY);
-		if (n->nr_partial < MIN_PARTIAL) {
+		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
-			 * order to fill them up. That way the size of the
-			 * partial list stays small. kmem_cache_shrink can
-			 * reclaim empty slabs from the partial list.
+			 * 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);
@@ -1365,10 +1416,10 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 	struct page *page = c->page;
 	int tail = 1;
 
-	if (c->freelist)
+	if (page->freelist)
 		stat(c, DEACTIVATE_REMOTE_FREES);
 	/*
-	 * Merge cpu freelist into freelist. Typically we get here
+	 * Merge cpu freelist into slab freelist. Typically we get here
 	 * because both freelists are empty. So this is unlikely
 	 * to occur.
 	 */
@@ -1399,6 +1450,7 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 
 /*
  * Flush cpu slab.
+ *
  * Called from IPI handler with interrupts disabled.
  */
 static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
@@ -1418,15 +1470,7 @@ static void flush_cpu_slab(void *d)
 
 static void flush_all(struct kmem_cache *s)
 {
-#ifdef CONFIG_SMP
-	on_each_cpu(flush_cpu_slab, s, 1, 1);
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	flush_cpu_slab(s);
-	local_irq_restore(flags);
-#endif
+	on_each_cpu(flush_cpu_slab, s, 1);
 }
 
 /*
@@ -1457,31 +1501,36 @@ static inline int node_match(struct kmem_cache_cpu *c, int node)
  * rest of the freelist to the lockless freelist.
  *
  * And if we were unable to get a new slab from the partial slab lists then
- * we need to allocate a new slab. This is slowest path since we may sleep.
+ * we need to allocate a new slab. This is the slowest path since it involves
+ * a call to the page allocator and the setup of a new slab.
  */
-static void *__slab_alloc(struct kmem_cache *s,
-		gfp_t gfpflags, int node, void *addr, struct kmem_cache_cpu *c)
+static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
+			  unsigned long addr, struct kmem_cache_cpu *c)
 {
 	void **object;
 	struct page *new;
 
+	/* We handle __GFP_ZERO in the caller */
+	gfpflags &= ~__GFP_ZERO;
+
 	if (!c->page)
 		goto new_slab;
 
 	slab_lock(c->page);
 	if (unlikely(!node_match(c, node)))
 		goto another_slab;
+
 	stat(c, ALLOC_REFILL);
+
 load_freelist:
 	object = c->page->freelist;
 	if (unlikely(!object))
 		goto another_slab;
-	if (unlikely(SlabDebug(c->page)))
+	if (unlikely(SLABDEBUG && PageSlubDebug(c->page)))
 		goto debug;
 
-	object = c->page->freelist;
 	c->freelist = object[c->offset];
-	c->page->inuse = s->objects;
+	c->page->inuse = c->page->objects;
 	c->page->freelist = NULL;
 	c->node = page_to_nid(c->page);
 unlock_out:
@@ -1514,28 +1563,12 @@ new_slab:
 		if (c->page)
 			flush_slab(s, c);
 		slab_lock(new);
-		SetSlabFrozen(new);
+		__SetPageSlubFrozen(new);
 		c->page = new;
 		goto load_freelist;
 	}
-
-	/*
-	 * No memory available.
-	 *
-	 * If the slab uses higher order allocs but the object is
-	 * smaller than a page size then we can fallback in emergencies
-	 * to the page allocator via kmalloc_large. The page allocator may
-	 * have failed to obtain a higher order page and we can try to
-	 * allocate a single page if the object fits into a single page.
-	 * That is only possible if certain conditions are met that are being
-	 * checked when a slab is created.
-	 */
-	if (!(gfpflags & __GFP_NORETRY) && (s->flags & __PAGE_ALLOC_FALLBACK))
-		return kmalloc_large(s->objsize, gfpflags);
-
 	return NULL;
 debug:
-	object = c->page->freelist;
 	if (!alloc_debug_processing(s, c->page, object, addr))
 		goto another_slab;
 
@@ -1556,14 +1589,21 @@ debug:
  * Otherwise we can simply pick the next object from the lockless free list.
  */
 static __always_inline void *slab_alloc(struct kmem_cache *s,
-		gfp_t gfpflags, int node, void *addr)
+		gfp_t gfpflags, int node, unsigned long addr)
 {
 	void **object;
 	struct kmem_cache_cpu *c;
 	unsigned long flags;
+	unsigned int objsize;
+
+	might_sleep_if(gfpflags & __GFP_WAIT);
+
+	if (should_failslab(s->objsize, gfpflags))
+		return NULL;
 
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
+	objsize = c->objsize;
 	if (unlikely(!c->freelist || !node_match(c, node)))
 
 		object = __slab_alloc(s, gfpflags, node, addr, c);
@@ -1576,21 +1616,21 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	local_irq_restore(flags);
 
 	if (unlikely((gfpflags & __GFP_ZERO) && object))
-		memset(object, 0, c->objsize);
+		memset(object, 0, objsize);
 
 	return object;
 }
 
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-	return slab_alloc(s, gfpflags, -1, __builtin_return_address(0));
+	return slab_alloc(s, gfpflags, -1, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-	return slab_alloc(s, gfpflags, node, __builtin_return_address(0));
+	return slab_alloc(s, gfpflags, node, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 #endif
@@ -1604,7 +1644,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node);
  * handling required then we can return immediately.
  */
 static void __slab_free(struct kmem_cache *s, struct page *page,
-				void *x, void *addr, unsigned int offset)
+			void *x, unsigned long addr, unsigned int offset)
 {
 	void *prior;
 	void **object = (void *)x;
@@ -1614,14 +1654,15 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 	stat(c, FREE_SLOWPATH);
 	slab_lock(page);
 
-	if (unlikely(SlabDebug(page)))
+	if (unlikely(SLABDEBUG && PageSlubDebug(page)))
 		goto debug;
+
 checks_ok:
 	prior = object[offset] = page->freelist;
 	page->freelist = object;
 	page->inuse--;
 
-	if (unlikely(SlabFrozen(page))) {
+	if (unlikely(PageSlubFrozen(page))) {
 		stat(c, FREE_FROZEN);
 		goto out_unlock;
 	}
@@ -1630,8 +1671,7 @@ checks_ok:
 		goto slab_empty;
 
 	/*
-	 * Objects left in the slab. If it
-	 * was not on the partial list before
+	 * Objects left in the slab. If it was not on the partial list before
 	 * then add it.
 	 */
 	if (unlikely(!prior)) {
@@ -1674,7 +1714,7 @@ debug:
  * with all sorts of special processing.
  */
 static __always_inline void slab_free(struct kmem_cache *s,
-			struct page *page, void *x, void *addr)
+			struct page *page, void *x, unsigned long addr)
 {
 	void **object = (void *)x;
 	struct kmem_cache_cpu *c;
@@ -1683,6 +1723,8 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
 	debug_check_no_locks_freed(object, c->objsize);
+	if (!(s->flags & SLAB_DEBUG_OBJECTS))
+		debug_check_no_obj_freed(object, s->objsize);
 	if (likely(page == c->page && c->node >= 0)) {
 		object[c->offset] = c->freelist;
 		c->freelist = object;
@@ -1699,11 +1741,11 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 
 	page = virt_to_head_page(x);
 
-	slab_free(s, page, x, __builtin_return_address(0));
+	slab_free(s, page, x, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-/* Figure out on which slab object the object resides */
+/* Figure out on which slab page the object resides */
 static struct page *get_object_page(const void *x)
 {
 	struct page *page = virt_to_head_page(x);
@@ -1734,8 +1776,8 @@ static struct page *get_object_page(const void *x)
  * take the list_lock.
  */
 static int slub_min_order;
-static int slub_max_order = DEFAULT_MAX_ORDER;
-static int slub_min_objects = DEFAULT_MIN_OBJECTS;
+static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static int slub_min_objects;
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
@@ -1750,7 +1792,7 @@ static int slub_nomerge;
  * system components. Generally order 0 allocations should be preferred since
  * order 0 does not cause fragmentation in the page allocator. Larger objects
  * be problematic to put into order 0 slabs because there may be too much
- * unused space left. We go to a higher order if more than 1/8th of the slab
+ * unused space left. We go to a higher order if more than 1/16th of the slab
  * would be wasted.
  *
  * In order to reach satisfactory performance we must ensure that a minimum
@@ -1775,6 +1817,9 @@ static inline int slab_order(int size, int min_objects,
 	int rem;
 	int min_order = slub_min_order;
 
+	if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE)
+		return get_order(size * MAX_OBJS_PER_PAGE) - 1;
+
 	for (order = max(min_order,
 				fls(min_objects * size - 1) - PAGE_SHIFT);
 			order <= max_order; order++) {
@@ -1809,8 +1854,10 @@ static inline int calculate_order(int size)
 	 * we reduce the minimum objects required in a slab.
 	 */
 	min_objects = slub_min_objects;
+	if (!min_objects)
+		min_objects = 4 * (fls(nr_cpu_ids) + 1);
 	while (min_objects > 1) {
-		fraction = 8;
+		fraction = 16;
 		while (fraction >= 4) {
 			order = slab_order(size, min_objects,
 						slub_max_order, fraction);
@@ -1845,20 +1892,21 @@ static unsigned long calculate_alignment(unsigned long flags,
 		unsigned long align, unsigned long size)
 {
 	/*
-	 * If the user wants hardware cache aligned objects then
-	 * follow that suggestion if the object is sufficiently
-	 * large.
+	 * If the user wants hardware cache aligned objects then follow that
+	 * suggestion if the object is sufficiently large.
 	 *
-	 * The hardware cache alignment cannot override the
-	 * specified alignment though. If that is greater
-	 * then use it.
+	 * The hardware cache alignment cannot override the specified
+	 * alignment though. If that is greater then use it.
 	 */
-	if ((flags & SLAB_HWCACHE_ALIGN) &&
-			size > cache_line_size() / 2)
-		return max_t(unsigned long, align, cache_line_size());
+	if (flags & SLAB_HWCACHE_ALIGN) {
+		unsigned long ralign = cache_line_size();
+		while (size <= ralign / 2)
+			ralign /= 2;
+		align = max(align, ralign);
+	}
 
 	if (align < ARCH_SLAB_MINALIGN)
-		return ARCH_SLAB_MINALIGN;
+		align = ARCH_SLAB_MINALIGN;
 
 	return ALIGN(align, sizeof(void *));
 }
@@ -1871,15 +1919,20 @@ static void init_kmem_cache_cpu(struct kmem_cache *s,
 	c->node = 0;
 	c->offset = s->offset / sizeof(void *);
 	c->objsize = s->objsize;
+#ifdef CONFIG_SLUB_STATS
+	memset(c->stat, 0, NR_SLUB_STAT_ITEMS * sizeof(unsigned));
+#endif
 }
 
-static void init_kmem_cache_node(struct kmem_cache_node *n)
+static void
+init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 {
 	n->nr_partial = 0;
-	atomic_long_set(&n->nr_slabs, 0);
 	spin_lock_init(&n->list_lock);
 	INIT_LIST_HEAD(&n->partial);
 #ifdef CONFIG_SLUB_DEBUG
+	atomic_long_set(&n->nr_slabs, 0);
+	atomic_long_set(&n->total_objects, 0);
 	INIT_LIST_HEAD(&n->full);
 #endif
 }
@@ -1906,7 +1959,7 @@ static DEFINE_PER_CPU(struct kmem_cache_cpu,
 				kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
 
 static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
-static cpumask_t kmem_cach_cpu_free_init_once = CPU_MASK_NONE;
+static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
 
 static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
 							int cpu, gfp_t flags)
@@ -1932,7 +1985,7 @@ static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
 static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu)
 {
 	if (c < per_cpu(kmem_cache_cpu, cpu) ||
-			c > per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
+			c >= per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
 		kfree(c);
 		return;
 	}
@@ -1981,13 +2034,13 @@ static void init_alloc_cpu_cpu(int cpu)
 {
 	int i;
 
-	if (cpu_isset(cpu, kmem_cach_cpu_free_init_once))
+	if (cpumask_test_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once)))
 		return;
 
 	for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--)
 		free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu);
 
-	cpu_set(cpu, kmem_cach_cpu_free_init_once);
+	cpumask_set_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once));
 }
 
 static void __init init_alloc_cpu(void)
@@ -2019,8 +2072,7 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
  * when allocating for the kmalloc_node_cache. This is used for bootstrapping
  * memory on a fresh node that has no slab structures yet.
  */
-static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
-							   int node)
+static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node)
 {
 	struct page *page;
 	struct kmem_cache_node *n;
@@ -2047,8 +2099,9 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
 	init_object(kmalloc_caches, n, 1);
 	init_tracking(kmalloc_caches, n);
 #endif
-	init_kmem_cache_node(n);
-	atomic_long_inc(&n->nr_slabs);
+	init_kmem_cache_node(n, kmalloc_caches);
+	inc_slabs_node(kmalloc_caches, node, page->objects);
+
 	/*
 	 * lockdep requires consistent irq usage for each lock
 	 * so even though there cannot be a race this early in
@@ -2057,7 +2110,6 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
 	local_irq_save(flags);
 	add_partial(n, page, 0);
 	local_irq_restore(flags);
-	return n;
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2089,8 +2141,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 			n = &s->local_node;
 		else {
 			if (slab_state == DOWN) {
-				n = early_kmem_cache_node_alloc(gfpflags,
-								node);
+				early_kmem_cache_node_alloc(gfpflags, node);
 				continue;
 			}
 			n = kmem_cache_alloc_node(kmalloc_caches,
@@ -2103,7 +2154,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 
 		}
 		s->node[node] = n;
-		init_kmem_cache_node(n);
+		init_kmem_cache_node(n, s);
 	}
 	return 1;
 }
@@ -2114,21 +2165,39 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 
 static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 {
-	init_kmem_cache_node(&s->local_node);
+	init_kmem_cache_node(&s->local_node, s);
 	return 1;
 }
 #endif
 
+static void calculate_min_partial(struct kmem_cache *s, unsigned long min)
+{
+	if (min < MIN_PARTIAL)
+		min = MIN_PARTIAL;
+	else if (min > MAX_PARTIAL)
+		min = MAX_PARTIAL;
+	s->min_partial = min;
+}
+
 /*
  * calculate_sizes() determines the order and the distribution of data within
  * a slab object.
  */
-static int calculate_sizes(struct kmem_cache *s)
+static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	unsigned long flags = s->flags;
 	unsigned long size = s->objsize;
 	unsigned long align = s->align;
+	int order;
+
+	/*
+	 * Round up object size to the next word boundary. We can only
+	 * place the free pointer at word boundaries and this determines
+	 * the possible location of the free pointer.
+	 */
+	size = ALIGN(size, sizeof(void *));
 
+#ifdef CONFIG_SLUB_DEBUG
 	/*
 	 * Determine if we can poison the object itself. If the user of
 	 * the slab may touch the object after free or before allocation
@@ -2140,14 +2209,7 @@ static int calculate_sizes(struct kmem_cache *s)
 	else
 		s->flags &= ~__OBJECT_POISON;
 
-	/*
-	 * Round up object size to the next word boundary. We can only
-	 * place the free pointer at word boundaries and this determines
-	 * the possible location of the free pointer.
-	 */
-	size = ALIGN(size, sizeof(void *));
 
-#ifdef CONFIG_SLUB_DEBUG
 	/*
 	 * If we are Redzoning then check if there is some space between the
 	 * end of the object and the free pointer. If not then add an
@@ -2190,7 +2252,7 @@ static int calculate_sizes(struct kmem_cache *s)
 		 * Add some empty padding so that we can catch
 		 * overwrites from earlier objects rather than let
 		 * tracking information or the free pointer be
-		 * corrupted if an user writes before the start
+		 * corrupted if a user writes before the start
 		 * of the object.
 		 */
 		size += sizeof(void *);
@@ -2210,26 +2272,16 @@ static int calculate_sizes(struct kmem_cache *s)
 	 */
 	size = ALIGN(size, align);
 	s->size = size;
+	if (forced_order >= 0)
+		order = forced_order;
+	else
+		order = calculate_order(size);
 
-	if ((flags & __KMALLOC_CACHE) &&
-			PAGE_SIZE / size < slub_min_objects) {
-		/*
-		 * Kmalloc cache that would not have enough objects in
-		 * an order 0 page. Kmalloc slabs can fallback to
-		 * page allocator order 0 allocs so take a reasonably large
-		 * order that will allows us a good number of objects.
-		 */
-		s->order = max(slub_max_order, PAGE_ALLOC_COSTLY_ORDER);
-		s->flags |= __PAGE_ALLOC_FALLBACK;
-		s->allocflags |= __GFP_NOWARN;
-	} else
-		s->order = calculate_order(size);
-
-	if (s->order < 0)
+	if (order < 0)
 		return 0;
 
 	s->allocflags = 0;
-	if (s->order)
+	if (order)
 		s->allocflags |= __GFP_COMP;
 
 	if (s->flags & SLAB_CACHE_DMA)
@@ -2241,16 +2293,19 @@ static int calculate_sizes(struct kmem_cache *s)
 	/*
 	 * Determine the number of objects per slab
 	 */
-	s->objects = (PAGE_SIZE << s->order) / size;
+	s->oo = oo_make(order, size);
+	s->min = oo_make(get_order(size), size);
+	if (oo_objects(s->oo) > oo_objects(s->max))
+		s->max = s->oo;
 
-	return !!s->objects;
+	return !!oo_objects(s->oo);
 
 }
 
 static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 		const char *name, size_t size,
 		size_t align, unsigned long flags,
-		void (*ctor)(struct kmem_cache *, void *))
+		void (*ctor)(void *))
 {
 	memset(s, 0, kmem_size);
 	s->name = name;
@@ -2259,12 +2314,17 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 	s->align = align;
 	s->flags = kmem_cache_flags(size, flags, name, ctor);
 
-	if (!calculate_sizes(s))
+	if (!calculate_sizes(s, -1))
 		goto error;
 
+	/*
+	 * The larger the object size is, the more pages we want on the partial
+	 * list to avoid pounding the page allocator excessively.
+	 */
+	calculate_min_partial(s, ilog2(s->size));
 	s->refcount = 1;
 #ifdef CONFIG_NUMA
-	s->remote_node_defrag_ratio = 100;
+	s->remote_node_defrag_ratio = 1000;
 #endif
 	if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
 		goto error;
@@ -2276,7 +2336,7 @@ error:
 	if (flags & SLAB_PANIC)
 		panic("Cannot create slab %s size=%lu realsize=%u "
 			"order=%u offset=%u flags=%lx\n",
-			s->name, (unsigned long)size, s->size, s->order,
+			s->name, (unsigned long)size, s->size, oo_order(s->oo),
 			s->offset, flags);
 	return 0;
 }
@@ -2300,7 +2360,7 @@ int kmem_ptr_validate(struct kmem_cache *s, const void *object)
 	/*
 	 * We could also check if the object is on the slabs freelist.
 	 * But this would be too expensive and it seems that the main
-	 * purpose of kmem_ptr_valid is to check if the object belongs
+	 * purpose of kmem_ptr_valid() is to check if the object belongs
 	 * to a certain slab.
 	 */
 	return 1;
@@ -2322,26 +2382,52 @@ const char *kmem_cache_name(struct kmem_cache *s)
 }
 EXPORT_SYMBOL(kmem_cache_name);
 
+static void list_slab_objects(struct kmem_cache *s, struct page *page,
+							const char *text)
+{
+#ifdef CONFIG_SLUB_DEBUG
+	void *addr = page_address(page);
+	void *p;
+	DECLARE_BITMAP(map, page->objects);
+
+	bitmap_zero(map, page->objects);
+	slab_err(s, page, "%s", text);
+	slab_lock(page);
+	for_each_free_object(p, s, page->freelist)
+		set_bit(slab_index(p, s, addr), map);
+
+	for_each_object(p, s, addr, page->objects) {
+
+		if (!test_bit(slab_index(p, s, addr), map)) {
+			printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n",
+							p, p - addr);
+			print_tracking(s, p);
+		}
+	}
+	slab_unlock(page);
+#endif
+}
+
 /*
- * Attempt to free all slabs on a node. Return the number of slabs we
- * were unable to free.
+ * Attempt to free all partial slabs on a node.
  */
-static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
-			struct list_head *list)
+static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
-	int slabs_inuse = 0;
 	unsigned long flags;
 	struct page *page, *h;
 
 	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry_safe(page, h, list, lru)
+	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
 			list_del(&page->lru);
 			discard_slab(s, page);
-		} else
-			slabs_inuse++;
+			n->nr_partial--;
+		} else {
+			list_slab_objects(s, page,
+				"Objects remaining on kmem_cache_close()");
+		}
+	}
 	spin_unlock_irqrestore(&n->list_lock, flags);
-	return slabs_inuse;
 }
 
 /*
@@ -2358,8 +2444,8 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
-		n->nr_partial -= free_list(s, n, &n->partial);
-		if (atomic_long_read(&n->nr_slabs))
+		free_partial(s, n);
+		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
 	free_kmem_cache_nodes(s);
@@ -2377,8 +2463,11 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (!s->refcount) {
 		list_del(&s->list);
 		up_write(&slub_lock);
-		if (kmem_cache_close(s))
-			WARN_ON(1);
+		if (kmem_cache_close(s)) {
+			printk(KERN_ERR "SLUB %s: %s called for cache that "
+				"still has objects.\n", s->name, __func__);
+			dump_stack();
+		}
 		sysfs_slab_remove(s);
 	} else
 		up_write(&slub_lock);
@@ -2392,10 +2481,6 @@ EXPORT_SYMBOL(kmem_cache_destroy);
 struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned;
 EXPORT_SYMBOL(kmalloc_caches);
 
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
-#endif
-
 static int __init setup_slub_min_order(char *str)
 {
 	get_option(&str, &slub_min_order);
@@ -2441,7 +2526,7 @@ static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
 
 	down_write(&slub_lock);
 	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
-			flags | __KMALLOC_CACHE, NULL))
+								flags, NULL))
 		goto panic;
 
 	list_add(&s->list, &slab_caches);
@@ -2455,6 +2540,7 @@ panic:
 }
 
 #ifdef CONFIG_ZONE_DMA
+static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
 
 static void sysfs_add_func(struct work_struct *w)
 {
@@ -2583,24 +2669,35 @@ void *__kmalloc(size_t size, gfp_t flags)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, flags, -1, __builtin_return_address(0));
+	return slab_alloc(s, flags, -1, _RET_IP_);
 }
 EXPORT_SYMBOL(__kmalloc);
 
+static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
+{
+	struct page *page = alloc_pages_node(node, flags | __GFP_COMP,
+						get_order(size));
+
+	if (page)
+		return page_address(page);
+	else
+		return NULL;
+}
+
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	struct kmem_cache *s;
 
 	if (unlikely(size > PAGE_SIZE))
-		return kmalloc_large(size, flags);
+		return kmalloc_large_node(size, flags, node);
 
 	s = get_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, flags, node, __builtin_return_address(0));
+	return slab_alloc(s, flags, node, _RET_IP_);
 }
 EXPORT_SYMBOL(__kmalloc_node);
 #endif
@@ -2610,19 +2707,18 @@ size_t ksize(const void *object)
 	struct page *page;
 	struct kmem_cache *s;
 
-	BUG_ON(!object);
 	if (unlikely(object == ZERO_SIZE_PTR))
 		return 0;
 
 	page = virt_to_head_page(object);
-	BUG_ON(!page);
 
-	if (unlikely(!PageSlab(page)))
+	if (unlikely(!PageSlab(page))) {
+		WARN_ON(!PageCompound(page));
 		return PAGE_SIZE << compound_order(page);
-
+	}
 	s = page->slab;
-	BUG_ON(!s);
 
+#ifdef CONFIG_SLUB_DEBUG
 	/*
 	 * Debugging requires use of the padding between object
 	 * and whatever may come after it.
@@ -2630,6 +2726,7 @@ size_t ksize(const void *object)
 	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
 		return s->objsize;
 
+#endif
 	/*
 	 * If we have the need to store the freelist pointer
 	 * back there or track user information then we can
@@ -2637,13 +2734,11 @@ size_t ksize(const void *object)
 	 */
 	if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
 		return s->inuse;
-
 	/*
 	 * Else we can use all the padding etc for the allocation
 	 */
 	return s->size;
 }
-EXPORT_SYMBOL(ksize);
 
 void kfree(const void *x)
 {
@@ -2655,26 +2750,14 @@ void kfree(const void *x)
 
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
+		BUG_ON(!PageCompound(page));
 		put_page(page);
 		return;
 	}
-	slab_free(page->slab, page, object, __builtin_return_address(0));
+	slab_free(page->slab, page, object, _RET_IP_);
 }
 EXPORT_SYMBOL(kfree);
 
-static unsigned long count_partial(struct kmem_cache_node *n)
-{
-	unsigned long flags;
-	unsigned long x = 0;
-	struct page *page;
-
-	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(page, &n->partial, lru)
-		x += page->inuse;
-	spin_unlock_irqrestore(&n->list_lock, flags);
-	return x;
-}
-
 /*
  * kmem_cache_shrink removes empty slabs from the partial lists and sorts
  * the remaining slabs by the number of items in use. The slabs with the
@@ -2692,8 +2775,9 @@ int kmem_cache_shrink(struct kmem_cache *s)
 	struct kmem_cache_node *n;
 	struct page *page;
 	struct page *t;
+	int objects = oo_objects(s->max);
 	struct list_head *slabs_by_inuse =
-		kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+		kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
 	unsigned long flags;
 
 	if (!slabs_by_inuse)
@@ -2706,7 +2790,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		if (!n->nr_partial)
 			continue;
 
-		for (i = 0; i < s->objects; i++)
+		for (i = 0; i < objects; i++)
 			INIT_LIST_HEAD(slabs_by_inuse + i);
 
 		spin_lock_irqsave(&n->list_lock, flags);
@@ -2738,7 +2822,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		 * Rebuild the partial list with the slabs filled up most
 		 * first and the least used slabs at the end.
 		 */
-		for (i = s->objects - 1; i >= 0; i--)
+		for (i = objects - 1; i >= 0; i--)
 			list_splice(slabs_by_inuse + i, n->partial.prev);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
@@ -2788,7 +2872,7 @@ static void slab_mem_offline_callback(void *arg)
 			 * and offline_pages() function shoudn't call this
 			 * callback. So, we must fail.
 			 */
-			BUG_ON(atomic_long_read(&n->nr_slabs));
+			BUG_ON(slabs_node(s, offline_node));
 
 			s->node[offline_node] = NULL;
 			kmem_cache_free(kmalloc_caches, n);
@@ -2813,7 +2897,7 @@ static int slab_mem_going_online_callback(void *arg)
 		return 0;
 
 	/*
-	 * We are bringing a node online. No memory is availabe yet. We must
+	 * We are bringing a node online. No memory is available yet. We must
 	 * allocate a kmem_cache_node structure in order to bring the node
 	 * online.
 	 */
@@ -2829,7 +2913,7 @@ static int slab_mem_going_online_callback(void *arg)
 			ret = -ENOMEM;
 			goto out;
 		}
-		init_kmem_cache_node(n);
+		init_kmem_cache_node(n, s);
 		s->node[nid] = n;
 	}
 out:
@@ -2857,8 +2941,10 @@ static int slab_memory_callback(struct notifier_block *self,
 	case MEM_CANCEL_OFFLINE:
 		break;
 	}
-
-	ret = notifier_from_errno(ret);
+	if (ret)
+		ret = notifier_from_errno(ret);
+	else
+		ret = NOTIFY_OK;
 	return ret;
 }
 
@@ -2886,7 +2972,7 @@ void __init kmem_cache_init(void)
 	kmalloc_caches[0].refcount = -1;
 	caches++;
 
-	hotplug_memory_notifier(slab_memory_callback, 1);
+	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
 #endif
 
 	/* Able to allocate the per node structures */
@@ -2897,8 +2983,6 @@ void __init kmem_cache_init(void)
 		create_kmalloc_cache(&kmalloc_caches[1],
 				"kmalloc-96", 96, GFP_KERNEL);
 		caches++;
-	}
-	if (KMALLOC_MIN_SIZE <= 128) {
 		create_kmalloc_cache(&kmalloc_caches[2],
 				"kmalloc-192", 192, GFP_KERNEL);
 		caches++;
@@ -2914,7 +2998,7 @@ void __init kmem_cache_init(void)
 	/*
 	 * Patch up the size_index table if we have strange large alignment
 	 * requirements for the kmalloc array. This is only the case for
-	 * mips it seems. The standard arches will not generate any code here.
+	 * MIPS it seems. The standard arches will not generate any code here.
 	 *
 	 * Largest permitted alignment is 256 bytes due to the way we
 	 * handle the index determination for the smaller caches.
@@ -2928,6 +3012,16 @@ void __init kmem_cache_init(void)
 	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8)
 		size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW;
 
+	if (KMALLOC_MIN_SIZE == 128) {
+		/*
+		 * The 192 byte sized cache is not used if the alignment
+		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
+		 * instead.
+		 */
+		for (i = 128 + 8; i <= 192; i += 8)
+			size_index[(i - 1) / 8] = 8;
+	}
+
 	slab_state = UP;
 
 	/* Provide the correct kmalloc names now that the caches are up */
@@ -2943,7 +3037,6 @@ void __init kmem_cache_init(void)
 	kmem_size = sizeof(struct kmem_cache);
 #endif
 
-
 	printk(KERN_INFO
 		"SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
 		" CPUs=%d, Nodes=%d\n",
@@ -2960,9 +3053,6 @@ static int slab_unmergeable(struct kmem_cache *s)
 	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
 		return 1;
 
-	if ((s->flags & __PAGE_ALLOC_FALLBACK))
-		return 1;
-
 	if (s->ctor)
 		return 1;
 
@@ -2977,7 +3067,7 @@ static int slab_unmergeable(struct kmem_cache *s)
 
 static struct kmem_cache *find_mergeable(size_t size,
 		size_t align, unsigned long flags, const char *name,
-		void (*ctor)(struct kmem_cache *, void *))
+		void (*ctor)(void *))
 {
 	struct kmem_cache *s;
 
@@ -3017,8 +3107,7 @@ static struct kmem_cache *find_mergeable(size_t size,
 }
 
 struct kmem_cache *kmem_cache_create(const char *name, size_t size,
-		size_t align, unsigned long flags,
-		void (*ctor)(struct kmem_cache *, void *))
+		size_t align, unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
 
@@ -3040,20 +3129,32 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		 */
 		for_each_online_cpu(cpu)
 			get_cpu_slab(s, cpu)->objsize = s->objsize;
+
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 		up_write(&slub_lock);
-		if (sysfs_slab_alias(s, name))
+
+		if (sysfs_slab_alias(s, name)) {
+			down_write(&slub_lock);
+			s->refcount--;
+			up_write(&slub_lock);
 			goto err;
+		}
 		return s;
 	}
+
 	s = kmalloc(kmem_size, GFP_KERNEL);
 	if (s) {
 		if (kmem_cache_open(s, GFP_KERNEL, name,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
 			up_write(&slub_lock);
-			if (sysfs_slab_add(s))
+			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
+				list_del(&s->list);
+				up_write(&slub_lock);
+				kfree(s);
 				goto err;
+			}
 			return s;
 		}
 		kfree(s);
@@ -3120,7 +3221,7 @@ static struct notifier_block __cpuinitdata slab_notifier = {
 
 #endif
 
-void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
+void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 {
 	struct kmem_cache *s;
 
@@ -3136,12 +3237,12 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
 }
 
 void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
-					int node, void *caller)
+					int node, unsigned long caller)
 {
 	struct kmem_cache *s;
 
 	if (unlikely(size > PAGE_SIZE))
-		return kmalloc_large(size, gfpflags);
+		return kmalloc_large_node(size, gfpflags, node);
 
 	s = get_slab(size, gfpflags);
 
@@ -3151,7 +3252,36 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	return slab_alloc(s, gfpflags, node, caller);
 }
 
-#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
+#ifdef CONFIG_SLUB_DEBUG
+static unsigned long count_partial(struct kmem_cache_node *n,
+					int (*get_count)(struct page *))
+{
+	unsigned long flags;
+	unsigned long x = 0;
+	struct page *page;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	list_for_each_entry(page, &n->partial, lru)
+		x += get_count(page);
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	return x;
+}
+
+static int count_inuse(struct page *page)
+{
+	return page->inuse;
+}
+
+static int count_total(struct page *page)
+{
+	return page->objects;
+}
+
+static int count_free(struct page *page)
+{
+	return page->objects - page->inuse;
+}
+
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {
@@ -3163,7 +3293,7 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 		return 0;
 
 	/* Now we know that a valid freelist exists */
-	bitmap_zero(map, s->objects);
+	bitmap_zero(map, page->objects);
 
 	for_each_free_object(p, s, page->freelist) {
 		set_bit(slab_index(p, s, addr), map);
@@ -3171,7 +3301,7 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 			return 0;
 	}
 
-	for_each_object(p, s, addr)
+	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
 			if (!check_object(s, page, p, 1))
 				return 0;
@@ -3189,12 +3319,12 @@ static void validate_slab_slab(struct kmem_cache *s, struct page *page,
 			s->name, page);
 
 	if (s->flags & DEBUG_DEFAULT_FLAGS) {
-		if (!SlabDebug(page))
-			printk(KERN_ERR "SLUB %s: SlabDebug not set "
+		if (!PageSlubDebug(page))
+			printk(KERN_ERR "SLUB %s: SlubDebug not set "
 				"on slab 0x%p\n", s->name, page);
 	} else {
-		if (SlabDebug(page))
-			printk(KERN_ERR "SLUB %s: SlabDebug set on "
+		if (PageSlubDebug(page))
+			printk(KERN_ERR "SLUB %s: SlubDebug set on "
 				"slab 0x%p\n", s->name, page);
 	}
 }
@@ -3237,7 +3367,7 @@ static long validate_slab_cache(struct kmem_cache *s)
 {
 	int node;
 	unsigned long count = 0;
-	unsigned long *map = kmalloc(BITS_TO_LONGS(s->objects) *
+	unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
 				sizeof(unsigned long), GFP_KERNEL);
 
 	if (!map)
@@ -3318,13 +3448,13 @@ static void resiliency_test(void) {};
 
 struct location {
 	unsigned long count;
-	void *addr;
+	unsigned long addr;
 	long long sum_time;
 	long min_time;
 	long max_time;
 	long min_pid;
 	long max_pid;
-	cpumask_t cpus;
+	DECLARE_BITMAP(cpus, NR_CPUS);
 	nodemask_t nodes;
 };
 
@@ -3366,7 +3496,7 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 {
 	long start, end, pos;
 	struct location *l;
-	void *caddr;
+	unsigned long caddr;
 	unsigned long age = jiffies - track->when;
 
 	start = -1;
@@ -3399,7 +3529,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 				if (track->pid > l->max_pid)
 					l->max_pid = track->pid;
 
-				cpu_set(track->cpu, l->cpus);
+				cpumask_set_cpu(track->cpu,
+						to_cpumask(l->cpus));
 			}
 			node_set(page_to_nid(virt_to_page(track)), l->nodes);
 			return 1;
@@ -3429,8 +3560,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 	l->max_time = age;
 	l->min_pid = track->pid;
 	l->max_pid = track->pid;
-	cpus_clear(l->cpus);
-	cpu_set(track->cpu, l->cpus);
+	cpumask_clear(to_cpumask(l->cpus));
+	cpumask_set_cpu(track->cpu, to_cpumask(l->cpus));
 	nodes_clear(l->nodes);
 	node_set(page_to_nid(virt_to_page(track)), l->nodes);
 	return 1;
@@ -3440,14 +3571,14 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 		struct page *page, enum track_item alloc)
 {
 	void *addr = page_address(page);
-	DECLARE_BITMAP(map, s->objects);
+	DECLARE_BITMAP(map, page->objects);
 	void *p;
 
-	bitmap_zero(map, s->objects);
+	bitmap_zero(map, page->objects);
 	for_each_free_object(p, s, page->freelist)
 		set_bit(slab_index(p, s, addr), map);
 
-	for_each_object(p, s, addr)
+	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
 			add_location(t, s, get_track(s, p, alloc));
 }
@@ -3486,7 +3617,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	for (i = 0; i < t.count; i++) {
 		struct location *l = &t.loc[i];
 
-		if (len > PAGE_SIZE - 100)
+		if (len > PAGE_SIZE - KSYM_SYMBOL_LEN - 100)
 			break;
 		len += sprintf(buf + len, "%7ld ", l->count);
 
@@ -3496,12 +3627,10 @@ static int list_locations(struct kmem_cache *s, char *buf,
 			len += sprintf(buf + len, "<not-available>");
 
 		if (l->sum_time != l->min_time) {
-			unsigned long remainder;
-
 			len += sprintf(buf + len, " age=%ld/%ld/%ld",
-			l->min_time,
-			div_long_long_rem(l->sum_time, l->count, &remainder),
-			l->max_time);
+				l->min_time,
+				(long)div_u64(l->sum_time, l->count),
+				l->max_time);
 		} else
 			len += sprintf(buf + len, " age=%ld",
 				l->min_time);
@@ -3513,11 +3642,12 @@ static int list_locations(struct kmem_cache *s, char *buf,
 			len += sprintf(buf + len, " pid=%ld",
 				l->min_pid);
 
-		if (num_online_cpus() > 1 && !cpus_empty(l->cpus) &&
+		if (num_online_cpus() > 1 &&
+				!cpumask_empty(to_cpumask(l->cpus)) &&
 				len < PAGE_SIZE - 60) {
 			len += sprintf(buf + len, " cpus=");
 			len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50,
-					l->cpus);
+						 to_cpumask(l->cpus));
 		}
 
 		if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&
@@ -3537,80 +3667,87 @@ static int list_locations(struct kmem_cache *s, char *buf,
 }
 
 enum slab_stat_type {
-	SL_FULL,
-	SL_PARTIAL,
-	SL_CPU,
-	SL_OBJECTS
+	SL_ALL,			/* All slabs */
+	SL_PARTIAL,		/* Only partially allocated slabs */
+	SL_CPU,			/* Only slabs used for cpu caches */
+	SL_OBJECTS,		/* Determine allocated objects not slabs */
+	SL_TOTAL		/* Determine object capacity not slabs */
 };
 
-#define SO_FULL		(1 << SL_FULL)
+#define SO_ALL		(1 << SL_ALL)
 #define SO_PARTIAL	(1 << SL_PARTIAL)
 #define SO_CPU		(1 << SL_CPU)
 #define SO_OBJECTS	(1 << SL_OBJECTS)
+#define SO_TOTAL	(1 << SL_TOTAL)
 
-static unsigned long show_slab_objects(struct kmem_cache *s,
-			char *buf, unsigned long flags)
+static ssize_t show_slab_objects(struct kmem_cache *s,
+			    char *buf, unsigned long flags)
 {
 	unsigned long total = 0;
-	int cpu;
 	int node;
 	int x;
 	unsigned long *nodes;
 	unsigned long *per_cpu;
 
 	nodes = kzalloc(2 * sizeof(unsigned long) * nr_node_ids, GFP_KERNEL);
+	if (!nodes)
+		return -ENOMEM;
 	per_cpu = nodes + nr_node_ids;
 
-	for_each_possible_cpu(cpu) {
-		struct page *page;
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+	if (flags & SO_CPU) {
+		int cpu;
 
-		if (!c)
-			continue;
+		for_each_possible_cpu(cpu) {
+			struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
 
-		page = c->page;
-		node = c->node;
-		if (node < 0)
-			continue;
-		if (page) {
-			if (flags & SO_CPU) {
-				if (flags & SO_OBJECTS)
-					x = page->inuse;
+			if (!c || c->node < 0)
+				continue;
+
+			if (c->page) {
+					if (flags & SO_TOTAL)
+						x = c->page->objects;
+				else if (flags & SO_OBJECTS)
+					x = c->page->inuse;
 				else
 					x = 1;
+
 				total += x;
-				nodes[node] += x;
+				nodes[c->node] += x;
 			}
-			per_cpu[node]++;
+			per_cpu[c->node]++;
 		}
 	}
 
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
+	if (flags & SO_ALL) {
+		for_each_node_state(node, N_NORMAL_MEMORY) {
+			struct kmem_cache_node *n = get_node(s, node);
+
+		if (flags & SO_TOTAL)
+			x = atomic_long_read(&n->total_objects);
+		else if (flags & SO_OBJECTS)
+			x = atomic_long_read(&n->total_objects) -
+				count_partial(n, count_free);
 
-		if (flags & SO_PARTIAL) {
-			if (flags & SO_OBJECTS)
-				x = count_partial(n);
 			else
-				x = n->nr_partial;
+				x = atomic_long_read(&n->nr_slabs);
 			total += x;
 			nodes[node] += x;
 		}
 
-		if (flags & SO_FULL) {
-			int full_slabs = atomic_long_read(&n->nr_slabs)
-					- per_cpu[node]
-					- n->nr_partial;
+	} else if (flags & SO_PARTIAL) {
+		for_each_node_state(node, N_NORMAL_MEMORY) {
+			struct kmem_cache_node *n = get_node(s, node);
 
-			if (flags & SO_OBJECTS)
-				x = full_slabs * s->objects;
+			if (flags & SO_TOTAL)
+				x = count_partial(n, count_total);
+			else if (flags & SO_OBJECTS)
+				x = count_partial(n, count_inuse);
 			else
-				x = full_slabs;
+				x = n->nr_partial;
 			total += x;
 			nodes[node] += x;
 		}
 	}
-
 	x = sprintf(buf, "%lu", total);
 #ifdef CONFIG_NUMA
 	for_each_node_state(node, N_NORMAL_MEMORY)
@@ -3625,14 +3762,6 @@ static unsigned long show_slab_objects(struct kmem_cache *s,
 static int any_slab_objects(struct kmem_cache *s)
 {
 	int node;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
-		if (c && c->page)
-			return 1;
-	}
 
 	for_each_online_node(node) {
 		struct kmem_cache_node *n = get_node(s, node);
@@ -3640,7 +3769,7 @@ static int any_slab_objects(struct kmem_cache *s)
 		if (!n)
 			continue;
 
-		if (n->nr_partial || atomic_long_read(&n->nr_slabs))
+		if (atomic_long_read(&n->total_objects))
 			return 1;
 	}
 	return 0;
@@ -3682,15 +3811,52 @@ SLAB_ATTR_RO(object_size);
 
 static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->objects);
+	return sprintf(buf, "%d\n", oo_objects(s->oo));
 }
 SLAB_ATTR_RO(objs_per_slab);
 
+static ssize_t order_store(struct kmem_cache *s,
+				const char *buf, size_t length)
+{
+	unsigned long order;
+	int err;
+
+	err = strict_strtoul(buf, 10, &order);
+	if (err)
+		return err;
+
+	if (order > slub_max_order || order < slub_min_order)
+		return -EINVAL;
+
+	calculate_sizes(s, order);
+	return length;
+}
+
 static ssize_t order_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->order);
+	return sprintf(buf, "%d\n", oo_order(s->oo));
 }
-SLAB_ATTR_RO(order);
+SLAB_ATTR(order);
+
+static ssize_t min_partial_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%lu\n", s->min_partial);
+}
+
+static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
+				 size_t length)
+{
+	unsigned long min;
+	int err;
+
+	err = strict_strtoul(buf, 10, &min);
+	if (err)
+		return err;
+
+	calculate_min_partial(s, min);
+	return length;
+}
+SLAB_ATTR(min_partial);
 
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
@@ -3711,7 +3877,7 @@ SLAB_ATTR_RO(aliases);
 
 static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
-	return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU);
+	return show_slab_objects(s, buf, SO_ALL);
 }
 SLAB_ATTR_RO(slabs);
 
@@ -3729,10 +3895,22 @@ SLAB_ATTR_RO(cpu_slabs);
 
 static ssize_t objects_show(struct kmem_cache *s, char *buf)
 {
-	return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU|SO_OBJECTS);
+	return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS);
 }
 SLAB_ATTR_RO(objects);
 
+static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
+{
+	return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS);
+}
+SLAB_ATTR_RO(objects_partial);
+
+static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
+{
+	return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
+}
+SLAB_ATTR_RO(total_objects);
+
 static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
 {
 	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
@@ -3812,7 +3990,7 @@ static ssize_t red_zone_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_RED_ZONE;
 	if (buf[0] == '1')
 		s->flags |= SLAB_RED_ZONE;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(red_zone);
@@ -3831,7 +4009,7 @@ static ssize_t poison_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_POISON;
 	if (buf[0] == '1')
 		s->flags |= SLAB_POISON;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(poison);
@@ -3850,7 +4028,7 @@ static ssize_t store_user_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_STORE_USER;
 	if (buf[0] == '1')
 		s->flags |= SLAB_STORE_USER;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(store_user);
@@ -3918,17 +4096,22 @@ static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
 static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
-	int n = simple_strtoul(buf, NULL, 10);
+	unsigned long ratio;
+	int err;
+
+	err = strict_strtoul(buf, 10, &ratio);
+	if (err)
+		return err;
+
+	if (ratio <= 100)
+		s->remote_node_defrag_ratio = ratio * 10;
 
-	if (n < 100)
-		s->remote_node_defrag_ratio = n * 10;
 	return length;
 }
 SLAB_ATTR(remote_node_defrag_ratio);
 #endif
 
 #ifdef CONFIG_SLUB_STATS
-
 static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si)
 {
 	unsigned long sum  = 0;
@@ -3948,10 +4131,12 @@ static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si)
 
 	len = sprintf(buf, "%lu", sum);
 
+#ifdef CONFIG_SMP
 	for_each_online_cpu(cpu) {
 		if (data[cpu] && len < PAGE_SIZE - 20)
-			len += sprintf(buf + len, " c%d=%u", cpu, data[cpu]);
+			len += sprintf(buf + len, " C%d=%u", cpu, data[cpu]);
 	}
+#endif
 	kfree(data);
 	return len + sprintf(buf + len, "\n");
 }
@@ -3980,7 +4165,7 @@ 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(ORDER_FALLBACK, order_fallback);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -3988,7 +4173,10 @@ static struct attribute *slab_attrs[] = {
 	&object_size_attr.attr,
 	&objs_per_slab_attr.attr,
 	&order_attr.attr,
+	&min_partial_attr.attr,
 	&objects_attr.attr,
+	&objects_partial_attr.attr,
+	&total_objects_attr.attr,
 	&slabs_attr.attr,
 	&partial_attr.attr,
 	&cpu_slabs_attr.attr,
@@ -4031,6 +4219,7 @@ static struct attribute *slab_attrs[] = {
 	&deactivate_to_head_attr.attr,
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
+	&order_fallback_attr.attr,
 #endif
 	NULL
 };
@@ -4112,8 +4301,8 @@ static struct kset *slab_kset;
 #define ID_STR_LENGTH 64
 
 /* Create a unique string id for a slab cache:
- * format
- * :[flags-]size:[memory address of kmemcache]
+ *
+ * Format	:[flags-]size
  */
 static char *create_unique_id(struct kmem_cache *s)
 {
@@ -4198,7 +4387,7 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 
 /*
  * Need to buffer aliases during bootup until sysfs becomes
- * available lest we loose that information.
+ * available lest we lose that information.
  */
 struct saved_alias {
 	struct kmem_cache *s;
@@ -4273,14 +4462,6 @@ __initcall(slab_sysfs_init);
  * The /proc/slabinfo ABI
  */
 #ifdef CONFIG_SLABINFO
-
-ssize_t slabinfo_write(struct file *file, const char __user * buffer,
-                       size_t count, loff_t *ppos)
-{
-	return -EINVAL;
-}
-
-
 static void print_slabinfo_header(struct seq_file *m)
 {
 	seq_puts(m, "slabinfo - version: 2.1\n");
@@ -4317,7 +4498,8 @@ static int s_show(struct seq_file *m, void *p)
 	unsigned long nr_partials = 0;
 	unsigned long nr_slabs = 0;
 	unsigned long nr_inuse = 0;
-	unsigned long nr_objs;
+	unsigned long nr_objs = 0;
+	unsigned long nr_free = 0;
 	struct kmem_cache *s;
 	int node;
 
@@ -4331,14 +4513,15 @@ static int s_show(struct seq_file *m, void *p)
 
 		nr_partials += n->nr_partial;
 		nr_slabs += atomic_long_read(&n->nr_slabs);
-		nr_inuse += count_partial(n);
+		nr_objs += atomic_long_read(&n->total_objects);
+		nr_free += count_partial(n, count_free);
 	}
 
-	nr_objs = nr_slabs * s->objects;
-	nr_inuse += (nr_slabs - nr_partials) * s->objects;
+	nr_inuse = nr_objs - nr_free;
 
 	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
-		   nr_objs, s->size, s->objects, (1 << s->order));
+		   nr_objs, s->size, oo_objects(s->oo),
+		   (1 << oo_order(s->oo)));
 	seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
 	seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
 		   0UL);
@@ -4346,11 +4529,29 @@ static int s_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-const struct seq_operations slabinfo_op = {
+static const struct seq_operations slabinfo_op = {
 	.start = s_start,
 	.next = s_next,
 	.stop = s_stop,
 	.show = s_show,
 };
 
+static int slabinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slabinfo_op);
+}
+
+static const struct file_operations proc_slabinfo_operations = {
+	.open		= slabinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init slab_proc_init(void)
+{
+	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
+	return 0;
+}
+module_init(slab_proc_init);
 #endif /* CONFIG_SLABINFO */