Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2008-04-09 22:01:41.000000000 -0700
+++ linux-2.6/mm/slub.c	2008-04-10 10:18:19.000000000 -0700
@@ -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, 2008 SGI, Christoph Lameter <clameter@sgi.com>
  */
 
 #include <linux/mm.h>
@@ -101,6 +101,7 @@
  */
 
 #define FROZEN (1 << PG_active)
+#define KICKABLE (1 << PG_dirty)
 
 #ifdef CONFIG_SLUB_DEBUG
 #define SLABDEBUG (1 << PG_error)
@@ -138,6 +139,21 @@
 	page->flags &= ~SLABDEBUG;
 }
 
+static inline int SlabKickable(struct page *page)
+{
+	return page->flags & KICKABLE;
+}
+
+static inline void SetSlabKickable(struct page *page)
+{
+	page->flags |= KICKABLE;
+}
+
+static inline void ClearSlabKickable(struct page *page)
+{
+	page->flags &= ~KICKABLE;
+}
+
 /*
  * Issues still to be resolved:
  *
@@ -149,25 +165,6 @@
 /* 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.
@@ -176,10 +173,10 @@
 
 /*
  * Maximum number of desirable partial slabs.
- * The existence of more partial slabs makes kmem_cache_shrink
- * sort the partial list by the number of objects in the.
+ * More slabs cause kmem_cache_shrink to sort the slabs by objects
+ * and triggers slab defragmentation.
  */
-#define MAX_PARTIAL 10
+#define MAX_PARTIAL 20
 
 #define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
 				SLAB_POISON | SLAB_STORE_USER)
@@ -204,8 +201,6 @@
 /* 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
@@ -229,6 +224,9 @@
 static DECLARE_RWSEM(slub_lock);
 static LIST_HEAD(slab_caches);
 
+/* Maximum objects in defragmentable slabs */
+static unsigned int max_defrag_slab_objects = 0;
+
 /*
  * Tracking user of a slab.
  */
@@ -301,7 +299,7 @@
 		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;
 	}
@@ -327,8 +325,8 @@
 }
 
 /* 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 */
@@ -341,6 +339,25 @@
 	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 << 16) + (PAGE_SIZE << order) / size };
+
+	return x;
+}
+
+static inline int oo_order(struct kmem_cache_order_objects x)
+{
+	return x.x >> 16;
+}
+
+static inline int oo_objects(struct kmem_cache_order_objects x)
+{
+	return x.x & ((1 << 16) - 1);
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 /*
  * Debug settings:
@@ -451,8 +468,8 @@
 
 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);
 
 }
 
@@ -652,6 +669,7 @@
 				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;
@@ -664,20 +682,20 @@
 		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;
@@ -739,15 +757,24 @@
 
 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 */
@@ -764,8 +791,9 @@
 	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)) {
@@ -777,7 +805,7 @@
 			} 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;
 			}
@@ -788,10 +816,20 @@
 		nr++;
 	}
 
-	if (page->inuse != s->objects - nr) {
+	max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+	if (max_objects > 65535)
+		max_objects = 65535;
+
+	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;
@@ -837,6 +875,38 @@
 	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)
 {
@@ -881,7 +951,7 @@
 		 * 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;
@@ -1028,29 +1098,55 @@
 	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;
 }
@@ -1066,10 +1162,10 @@
 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;
+	struct kmem_cache_order_objects oo = s->oo;
 
 	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1078,22 +1174,23 @@
 	if (!page)
 		goto out;
 
-	n = get_node(s, page_to_nid(page));
-	if (n)
-		atomic_long_inc(&n->nr_slabs);
+	inc_slabs_node(s, node, 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);
 
+	if (s->kick)
+		SetSlabKickable(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 << oo_order(oo));
 
 	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;
@@ -1109,13 +1206,15 @@
 
 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))) {
 		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);
 	}
@@ -1125,7 +1224,10 @@
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		-pages);
 
-	__free_pages(page, s->order);
+	ClearSlabKickable(page);
+	__ClearPageSlab(page);
+	reset_page_mapcount(page);
+	__free_pages(page, order);
 }
 
 static void rcu_free_slab(struct rcu_head *h)
@@ -1151,11 +1253,7 @@
 
 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);
 }
 
@@ -1335,6 +1433,8 @@
 			stat(c, DEACTIVATE_FULL);
 			if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
 				add_full(n, page);
+			if (s->kick)
+				SetSlabKickable(page);
 		}
 		slab_unlock(page);
 	} else {
@@ -1470,9 +1570,6 @@
 	void **object;
 	struct page *new;
 
-	/* We handle __GFP_ZERO in the caller */
-	gfpflags &= ~__GFP_ZERO;
-
 	if (!c->page)
 		goto new_slab;
 
@@ -1490,7 +1587,7 @@
 		goto debug;
 
 	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:
@@ -1527,27 +1624,6 @@
 		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)) {
-		if (gfpflags & __GFP_WAIT)
-			local_irq_enable();
-		object = kmalloc_large(s->objsize, gfpflags);
-		if (gfpflags & __GFP_WAIT)
-			local_irq_disable();
-		return object;
-	}
 	return NULL;
 debug:
 	if (!alloc_debug_processing(s, c->page, object, addr))
@@ -1748,8 +1824,8 @@
  * 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 = 0;
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
@@ -1764,7 +1840,7 @@
  * 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
@@ -1789,6 +1865,9 @@
 	int rem;
 	int min_order = slub_min_order;
 
+	if ((PAGE_SIZE << min_order) / size > 65535)
+		return get_order(size * 65535) - 1;
+
 	for (order = max(min_order,
 				fls(min_objects * size - 1) - PAGE_SHIFT);
 			order <= max_order; order++) {
@@ -1823,8 +1902,10 @@
 	 * we reduce the minimum objects required in a slab.
 	 */
 	min_objects = slub_min_objects;
+	if (!min_objects)
+		min_objects = 4 * fls(nr_cpu_ids);
 	while (min_objects > 1) {
-		fraction = 8;
+		fraction = 16;
 		while (fraction >= 4) {
 			order = slab_order(size, min_objects,
 						slub_max_order, fraction);
@@ -1886,15 +1967,18 @@
 	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)
 {
 	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);
 	INIT_LIST_HEAD(&n->full);
 #endif
 }
@@ -2063,7 +2147,7 @@
 	init_tracking(kmalloc_caches, n);
 #endif
 	init_kmem_cache_node(n);
-	atomic_long_inc(&n->nr_slabs);
+	inc_slabs_node(kmalloc_caches, node, page->objects);
 
 	/*
 	 * lockdep requires consistent irq usage for each lock
@@ -2139,11 +2223,12 @@
  * 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
@@ -2227,26 +2312,16 @@
 	 */
 	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)
@@ -2258,9 +2333,12 @@
 	/*
 	 * 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);
 
 }
 
@@ -2276,10 +2354,11 @@
 	s->align = align;
 	s->flags = kmem_cache_flags(size, flags, name, ctor);
 
-	if (!calculate_sizes(s))
+	if (!calculate_sizes(s, -1))
 		goto error;
 
 	s->refcount = 1;
+	s->defrag_ratio = 30;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 100;
 #endif
@@ -2293,7 +2372,7 @@
 	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;
 }
@@ -2376,7 +2455,7 @@
 		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))
+		if (slabs_node(s, node))
 			return 1;
 	}
 	free_kmem_cache_nodes(s);
@@ -2409,10 +2488,6 @@
 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);
@@ -2458,10 +2533,10 @@
 
 	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);
+	list_add_tail(&s->list, &slab_caches);
 	up_write(&slub_lock);
 	if (sysfs_slab_add(s))
 		goto panic;
@@ -2472,6 +2547,7 @@
 }
 
 #ifdef CONFIG_ZONE_DMA
+static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
 
 static void sysfs_add_func(struct work_struct *w)
 {
@@ -2688,91 +2764,269 @@
 }
 EXPORT_SYMBOL(kfree);
 
-#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SLABINFO)
-static unsigned long count_partial(struct kmem_cache_node *n)
+static inline void *alloc_scratch(void)
+{
+	return kmalloc(max_defrag_slab_objects * sizeof(void *) +
+	    BITS_TO_LONGS(max_defrag_slab_objects) * sizeof(unsigned long),
+								GFP_KERNEL);
+}
+
+void kmem_cache_setup_defrag(struct kmem_cache *s,
+	void *(*get)(struct kmem_cache *, int nr, void **),
+	void (*kick)(struct kmem_cache *, int nr, void **, void *private))
+{
+	int max_objects = oo_objects(s->max);
+
+	/*
+	 * Defragmentable slabs must have a ctor otherwise objects may be
+	 * in an undetermined state after they are allocated.
+	 */
+	BUG_ON(!s->ctor);
+	s->get = get;
+	s->kick = kick;
+	down_write(&slub_lock);
+	list_move(&s->list, &slab_caches);
+	if (max_objects > max_defrag_slab_objects)
+		max_defrag_slab_objects = max_objects;
+	up_write(&slub_lock);
+}
+EXPORT_SYMBOL(kmem_cache_setup_defrag);
+
+/*
+ * Vacate all objects in the given slab.
+ *
+ * The scratch aread passed to list function is sufficient to hold
+ * struct listhead times objects per slab. We use it to hold void ** times
+ * objects per slab plus a bitmap for each object.
+ */
+static int kmem_cache_vacate(struct page *page, void *scratch)
 {
+	void **vector = scratch;
+	void *p;
+	void *addr = page_address(page);
+	struct kmem_cache *s;
+	unsigned long *map;
+	int leftover;
+	int count;
+	void *private;
 	unsigned long flags;
-	unsigned long x = 0;
-	struct page *page;
+	unsigned long objects;
+	struct kmem_cache_cpu *c;
 
-	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;
+	BUG_ON(!PageSlab(page));
+	local_irq_save(flags);
+	slab_lock(page);
+	BUG_ON(!SlabFrozen(page));
+
+	s = page->slab;
+	objects = page->objects;
+	c= get_cpu_slab(s, smp_processor_id());
+	map = scratch + max_defrag_slab_objects * sizeof(void **);
+	if (!page->inuse || !s->kick || !SlabKickable(page)) {
+		stat(c, SHRINK_SLAB_SKIPPED);
+		goto out;
+	}
+
+	/* Determine used objects */
+	bitmap_fill(map, objects);
+	for_each_free_object(p, s, page->freelist)
+		__clear_bit(slab_index(p, s, addr), map);
+
+	count = 0;
+	memset(vector, 0, objects * sizeof(void **));
+	for_each_object(p, s, addr, objects)
+		if (test_bit(slab_index(p, s, addr), map))
+			vector[count++] = p;
+
+	private = s->get(s, count, vector);
+
+	/*
+	 * Got references. Now we can drop the slab lock. The slab
+	 * is frozen so it cannot vanish from under us nor will
+	 * allocations be performed on the slab. However, unlocking the
+	 * slab will allow concurrent slab_frees to proceed.
+	 */
+	slab_unlock(page);
+	local_irq_restore(flags);
+
+	/*
+	 * Perform the KICK callbacks to remove the objects.
+	 */
+	s->kick(s, count, vector, private);
+
+	local_irq_save(flags);
+	slab_lock(page);
+out:
+	/*
+	 * Check the result and unfreeze the slab
+	 */
+	leftover = page->inuse;
+	if (leftover) {
+		stat(c, SHRINK_OBJECT_RECLAIM_FAILED);
+		ClearSlabKickable(page);
+	} else
+		stat(c, SHRINK_SLAB_RECLAIMED);
+
+	unfreeze_slab(s, page, leftover > 0);
+	local_irq_restore(flags);
+	return leftover;
 }
-#endif
 
 /*
- * 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
- * most items in use come first. New allocations will then fill those up
- * and thus they can be removed from the partial lists.
- *
- * The slabs with the least items are placed last. This results in them
- * being allocated from last increasing the chance that the last objects
- * are freed in them.
+ * Remove objects from a list of slab pages that have been gathered.
+ * Must be called with slabs that have been isolated before.
  */
-int kmem_cache_shrink(struct kmem_cache *s)
+int kmem_cache_reclaim(struct list_head *zaplist)
 {
-	int node;
-	int i;
-	struct kmem_cache_node *n;
+	int freed = 0;
+	void **scratch;
 	struct page *page;
-	struct page *t;
-	struct list_head *slabs_by_inuse =
-		kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+	struct page *page2;
+
+	if (list_empty(zaplist))
+		return 0;
+
+	scratch = alloc_scratch();
+	if (!scratch)
+		return 0;
+
+	list_for_each_entry_safe(page, page2, zaplist, lru) {
+		list_del(&page->lru);
+		if (kmem_cache_vacate(page, scratch) == 0)
+				freed++;
+	}
+	kfree(scratch);
+	return freed;
+}
+
+/*
+ * Shrink the slab cache on a particular node of the cache
+ * by releasing slabs with zero objects and trying to reclaim
+ * slabs with less than a quarter of objects allocated.
+ */
+static unsigned long __kmem_cache_shrink(struct kmem_cache *s, int node,
+							unsigned long limit)
+{
 	unsigned long flags;
+	struct page *page, *page2;
+	LIST_HEAD(zaplist);
+	int freed = 0;
+	struct kmem_cache_node *n = get_node(s, node);
+	struct kmem_cache_cpu *c;
 
-	if (!slabs_by_inuse)
-		return -ENOMEM;
+	if (n->nr_partial <= limit)
+		return 0;
 
-	flush_all(s);
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		n = get_node(s, node);
+	spin_lock_irqsave(&n->list_lock, flags);
+	c = get_cpu_slab(s, smp_processor_id());
+	stat(c, SHRINK_CALLS);
+	list_for_each_entry_safe(page, page2, &n->partial, lru) {
+		if (page->inuse) {
 
-		if (!n->nr_partial)
-			continue;
+			if (!SlabKickable(page))
+				continue;
 
-		for (i = 0; i < s->objects; i++)
-			INIT_LIST_HEAD(slabs_by_inuse + i);
+			if (page->inuse * 100 >=
+					s->defrag_ratio * page->objects)
+				continue;
 
-		spin_lock_irqsave(&n->list_lock, flags);
+			if (!slab_trylock(page))
+				continue;
 
-		/*
-		 * Build lists indexed by the items in use in each slab.
-		 *
-		 * Note that concurrent frees may occur while we hold the
-		 * 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.
-				 */
-				list_del(&page->lru);
+			list_move(&page->lru, &zaplist);
+			if (s->kick) {
+				stat(c, SHRINK_ATTEMPT_DEFRAG);
 				n->nr_partial--;
-				slab_unlock(page);
-				discard_slab(s, page);
-			} else {
-				list_move(&page->lru,
-				slabs_by_inuse + page->inuse);
+				SetSlabFrozen(page);
 			}
+			slab_unlock(page);
+
+		} else {
+			stat(c, SHRINK_EMPTY_SLAB);
+			list_del(&page->lru);
+			n->nr_partial--;
+			slab_unlock(page);
+			discard_slab(s, page);
+			freed++;
 		}
+	}
+
+	if (!s->kick)
+		/* Simply put the zaplist at the end */
+		list_splice(&zaplist, n->partial.prev);
+
+	spin_unlock_irqrestore(&n->list_lock, flags);
+
+	if (s->kick)
+		freed += kmem_cache_reclaim(&zaplist);
+
+	return freed;
+}
+
+/*
+ * Defrag slabs conditional on the amount of fragmentation in a page.
+ */
+int kmem_cache_defrag(int node)
+{
+	struct kmem_cache *s;
+	unsigned long slabs = 0;
+	unsigned long reclaimed;
+
+	/*
+	 * kmem_cache_defrag may be called from the reclaim path which may be
+	 * called for any page allocator alloc. So there is the danger that we
+	 * get called in a situation where slub already acquired the slub_lock
+	 * for other purposes.
+	 */
+	if (!down_read_trylock(&slub_lock))
+		return 0;
+
+	list_for_each_entry(s, &slab_caches, list) {
+
+		if (time_before(jiffies, s->next_defrag))
+			continue;
 
 		/*
-		 * Rebuild the partial list with the slabs filled up most
-		 * first and the least used slabs at the end.
+		 * Defragmentable caches come first. If the slab cache is not
+		 * defragmentable then we can stop traversing the list.
 		 */
-		for (i = s->objects - 1; i >= 0; i--)
-			list_splice(slabs_by_inuse + i, n->partial.prev);
+		if (!s->kick)
+			break;
 
-		spin_unlock_irqrestore(&n->list_lock, flags);
+		if (node == -1) {
+			int nid;
+
+			for_each_node_state(nid, N_NORMAL_MEMORY)
+				reclaimed = __kmem_cache_shrink(s, nid,
+								MAX_PARTIAL);
+		} else
+			reclaimed = __kmem_cache_shrink(s, node, MAX_PARTIAL);
+
+		if (reclaimed)
+			s->next_defrag = jiffies + HZ / 10;
+		else
+			s->next_defrag = jiffies + HZ;
+
+		slabs += reclaimed;
 	}
+	up_read(&slub_lock);
+	return slabs;
+}
+EXPORT_SYMBOL(kmem_cache_defrag);
+
+/*
+ * kmem_cache_shrink removes empty slabs from the partial lists.
+ * If the slab cache supports defragmentation then objects are
+ * reclaimed.
+ */
+int kmem_cache_shrink(struct kmem_cache *s)
+{
+	int node;
+
+	flush_all(s);
+	for_each_node_state(node, N_NORMAL_MEMORY)
+		__kmem_cache_shrink(s, node, 0);
 
-	kfree(slabs_by_inuse);
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
@@ -2816,7 +3070,7 @@
 			 * 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);
@@ -2841,7 +3095,7 @@
 		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.
 	 */
@@ -2987,10 +3241,7 @@
 	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
 		return 1;
 
-	if ((s->flags & __PAGE_ALLOC_FALLBACK))
-		return 1;
-
-	if (s->ctor)
+	if (s->ctor || s->kick || s->get)
 		return 1;
 
 	/*
@@ -3080,7 +3331,7 @@
 	if (s) {
 		if (kmem_cache_open(s, GFP_KERNEL, name,
 				size, align, flags, ctor)) {
-			list_add(&s->list, &slab_caches);
+			list_add_tail(&s->list, &slab_caches);
 			up_write(&slub_lock);
 			if (sysfs_slab_add(s))
 				goto err;
@@ -3181,6 +3432,37 @@
 	return slab_alloc(s, gfpflags, node, caller);
 }
 
+#if (defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)) || defined(CONFIG_SLABINFO)
+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;
+}
+#endif
+
 #if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
@@ -3193,7 +3475,7 @@
 		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);
@@ -3201,7 +3483,7 @@
 			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;
@@ -3267,7 +3549,7 @@
 {
 	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)
@@ -3470,14 +3752,14 @@
 		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));
 }
@@ -3567,22 +3849,23 @@
 }
 
 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 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;
@@ -3593,56 +3876,60 @@
 		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;
-
-			if (flags & SO_OBJECTS)
-				x = full_slabs * s->objects;
+	} 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_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)
@@ -3657,14 +3944,6 @@
 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);
@@ -3672,7 +3951,7 @@
 		if (!n)
 			continue;
 
-		if (n->nr_partial || atomic_long_read(&n->nr_slabs))
+		if (atomic_read(&n->total_objects))
 			return 1;
 	}
 	return 0;
@@ -3714,26 +3993,54 @@
 
 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)
+{
+	int order = simple_strtoul(buf, NULL, 10);
+
+	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 ctor_show(struct kmem_cache *s, char *buf)
+static ssize_t ops_show(struct kmem_cache *s, char *buf)
 {
-	if (s->ctor) {
-		int n = sprint_symbol(buf, (unsigned long)s->ctor);
+	int x = 0;
 
-		return n + sprintf(buf + n, "\n");
+	if (s->ctor) {
+		x += sprintf(buf + x, "ctor : ");
+		x += sprint_symbol(buf + x, (unsigned long)s->ctor);
+		x += sprintf(buf + x, "\n");
+	}
+
+	if (s->get) {
+		x += sprintf(buf + x, "get : ");
+		x += sprint_symbol(buf + x,
+				(unsigned long)s->get);
+		x += sprintf(buf + x, "\n");
+	}
+
+	if (s->kick) {
+		x += sprintf(buf + x, "kick : ");
+		x += sprint_symbol(buf + x,
+				(unsigned long)s->kick);
+		x += sprintf(buf + x, "\n");
 	}
-	return 0;
+	return x;
 }
-SLAB_ATTR_RO(ctor);
+SLAB_ATTR_RO(ops);
 
 static ssize_t aliases_show(struct kmem_cache *s, char *buf)
 {
@@ -3743,7 +4050,7 @@
 
 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);
 
@@ -3761,10 +4068,22 @@
 
 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));
@@ -3844,7 +4163,7 @@
 	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);
@@ -3863,7 +4182,7 @@
 	s->flags &= ~SLAB_POISON;
 	if (buf[0] == '1')
 		s->flags |= SLAB_POISON;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(poison);
@@ -3882,7 +4201,7 @@
 	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);
@@ -3941,6 +4260,22 @@
 }
 SLAB_ATTR_RO(free_calls);
 
+static ssize_t defrag_ratio_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%d\n", s->defrag_ratio);
+}
+
+static ssize_t defrag_ratio_store(struct kmem_cache *s,
+				const char *buf, size_t length)
+{
+	int n = simple_strtoul(buf, NULL, 10);
+
+	if (n < 100)
+		s->defrag_ratio = n;
+	return length;
+}
+SLAB_ATTR(defrag_ratio);
+
 #ifdef CONFIG_NUMA
 static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
 {
@@ -3979,10 +4314,12 @@
 
 	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");
 }
@@ -4011,7 +4348,13 @@
 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);
+STAT_ATTR(SHRINK_CALLS, shrink_calls);
+STAT_ATTR(SHRINK_ATTEMPT_DEFRAG, shrink_attempt_defrag);
+STAT_ATTR(SHRINK_EMPTY_SLAB, shrink_empty_slab);
+STAT_ATTR(SHRINK_SLAB_SKIPPED, shrink_slab_skipped);
+STAT_ATTR(SHRINK_SLAB_RECLAIMED, shrink_slab_reclaimed);
+STAT_ATTR(SHRINK_OBJECT_RECLAIM_FAILED, shrink_object_reclaim_failed);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -4020,10 +4363,12 @@
 	&objs_per_slab_attr.attr,
 	&order_attr.attr,
 	&objects_attr.attr,
+	&objects_partial_attr.attr,
+	&total_objects_attr.attr,
 	&slabs_attr.attr,
 	&partial_attr.attr,
 	&cpu_slabs_attr.attr,
-	&ctor_attr.attr,
+	&ops_attr.attr,
 	&aliases_attr.attr,
 	&align_attr.attr,
 	&sanity_checks_attr.attr,
@@ -4038,6 +4383,7 @@
 	&shrink_attr.attr,
 	&alloc_calls_attr.attr,
 	&free_calls_attr.attr,
+	&defrag_ratio_attr.attr,
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
 #endif
@@ -4062,6 +4408,13 @@
 	&deactivate_to_head_attr.attr,
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
+	&order_fallback_attr.attr,
+	&shrink_calls_attr.attr,
+	&shrink_attempt_defrag_attr.attr,
+	&shrink_empty_slab_attr.attr,
+	&shrink_slab_skipped_attr.attr,
+	&shrink_slab_reclaimed_attr.attr,
+	&shrink_object_reclaim_failed_attr.attr,
 #endif
 	NULL
 };
@@ -4348,7 +4701,8 @@
 	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;
 
@@ -4362,14 +4716,15 @@
 
 		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);