[RFC 00/26] Slab defragmentation V5

@@ -2595,6 +2595,19 @@ void kfree(const void *x)
 }
 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

@@ -3331,19 +3344,6 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	return n;
 }
 
-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;
-}
-
 enum slab_stat_type {
 	SL_FULL,
 	SL_PARTIAL,

@@ -3501,16 +3501,18 @@ static ssize_t order_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(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->ops->ctor);
+		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)
 {

@@ -3761,7 +3763,7 @@ static struct attribute * slab_attrs[] = {
 	&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,

@@ -54,6 +54,9 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			void (*)(void *, struct kmem_cache *, unsigned long));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
+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));
 void kmem_cache_free(struct kmem_cache *, void *);
 unsigned int kmem_cache_size(struct kmem_cache *);
 const char *kmem_cache_name(struct kmem_cache *);

@@ -50,6 +50,38 @@ struct kmem_cache {
 	int objects;		/* Number of objects in slab */
 	int refcount;		/* Refcount for slab cache destroy */
 	void (*ctor)(void *, struct kmem_cache *, unsigned long);
+
+	/*
+	 * Called with slab lock held and interrupts disabled.
+	 * No slab operation may be performed in get().
+	 *
+	 * Parameters passed are the number of objects to process
+	 * and an array of pointers to objects for which we
+	 * need references.
+	 *
+	 * Returns a pointer that is passed to the kick function.
+	 * If all objects cannot be moved then the pointer may
+	 * indicate that this wont work and then kick can simply
+	 * remove the references that were already obtained.
+	 *
+	 * The array passed to get() is also passed to kick(). The
+	 * function may remove objects by setting array elements to NULL.
+	 */
+	void *(*get)(struct kmem_cache *, int nr, void **);
+
+	/*
+	 * Called with no locks held and interrupts enabled.
+	 * Any operation may be performed in kick().
+	 *
+	 * Parameters passed are the number of objects in the array,
+	 * the array of pointers to the objects and the pointer
+	 * returned by get().
+	 *
+	 * Success is checked by examining the number of remaining
+	 * objects in the slab.
+	 */
+	void (*kick)(struct kmem_cache *, int nr, void **, void *private);
+
 	int inuse;		/* Offset to metadata */
 	int align;		/* Alignment */
 	int defrag_ratio;	/*

@@ -2597,6 +2597,20 @@ void kfree(const void *x)
 }
 EXPORT_SYMBOL(kfree);
 
+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))
+{
+	/*
+	 * 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;
+}
+EXPORT_SYMBOL(kmem_cache_setup_defrag);
+
 static unsigned long count_partial(struct kmem_cache_node *n)
 {
 	unsigned long flags;

@@ -2777,7 +2791,7 @@ static int slab_unmergeable(struct kmem_cache *s)
 	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
 		return 1;
 
-	if (s->ctor)
+	if (s->ctor || s->kick || s->get)
 		return 1;
 
 	/*

@@ -3507,7 +3521,21 @@ static ssize_t ops_show(struct kmem_cache *s, char *buf)
 
 	if (s->ctor) {
 		x += sprintf(buf + x, "ctor : ");
-		x += sprint_symbol(buf + x, (unsigned long)s->ops->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 x;

@@ -30,6 +30,8 @@ struct slabinfo {
 	int hwcache_align, object_size, objs_per_slab;
 	int sanity_checks, slab_size, store_user, trace;
 	int order, poison, reclaim_account, red_zone;
+	int defrag, ctor;
+	int defrag_ratio, remote_node_defrag_ratio;
 	unsigned long partial, objects, slabs;
 	int numa[MAX_NODES];
 	int numa_partial[MAX_NODES];

@@ -56,6 +58,8 @@ int show_slab = 0;
 int skip_zero = 1;
 int show_numa = 0;
 int show_track = 0;
+int show_defrag = 0;
+int show_ctor = 0;
 int show_first_alias = 0;
 int validate = 0;
 int shrink = 0;

@@ -90,18 +94,20 @@ void fatal(const char *x, ...)
 void usage(void)
 {
 	printf("slabinfo 5/7/2007. (c) 2007 sgi. clameter@sgi.com\n\n"
-		"slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
+		"slabinfo [-aCDefhilnosSrtTvz1] [-d debugopts] [slab-regexp]\n"
 		"-a|--aliases           Show aliases\n"
+		"-C|--ctor              Show slabs with ctors\n"
 		"-d<options>|--debug=<options> Set/Clear Debug options\n"
-		"-e|--empty		Show empty slabs\n"
+		"-D|--defrag            Show defragmentable caches\n"
+		"-e|--empty             Show empty slabs\n"
 		"-f|--first-alias       Show first alias\n"
 		"-h|--help              Show usage information\n"
 		"-i|--inverted          Inverted list\n"
 		"-l|--slabs             Show slabs\n"
 		"-n|--numa              Show NUMA information\n"
-		"-o|--ops		Show kmem_cache_ops\n"
+		"-o|--ops               Show kmem_cache_ops\n"
 		"-s|--shrink            Shrink slabs\n"
-		"-r|--report		Detailed report on single slabs\n"
+		"-r|--report            Detailed report on single slabs\n"
 		"-S|--Size              Sort by size\n"
 		"-t|--tracking          Show alloc/free information\n"
 		"-T|--Totals            Show summary information\n"

@@ -281,7 +287,7 @@ int line = 0;
 void first_line(void)
 {
 	printf("Name                   Objects Objsize    Space "
-		"Slabs/Part/Cpu  O/S O %%Fr %%Ef Flg\n");
+		"Slabs/Part/Cpu  O/S O %%Ra %%Ef Flg\n");
 }
 
 /*

@@ -324,7 +330,7 @@ void slab_numa(struct slabinfo *s, int mode)
 		return;
 
 	if (!line) {
-		printf("\n%-21s:", mode ? "NUMA nodes" : "Slab");
+		printf("\n%-21s: Rto ", mode ? "NUMA nodes" : "Slab");
 		for(node = 0; node <= highest_node; node++)
 			printf(" %4d", node);
 		printf("\n----------------------");

@@ -333,6 +339,7 @@ void slab_numa(struct slabinfo *s, int mode)
 		printf("\n");
 	}
 	printf("%-21s ", mode ? "All slabs" : s->name);
+	printf("%3d ", s->remote_node_defrag_ratio);
 	for(node = 0; node <= highest_node; node++) {
 		char b[20];
 

@@ -406,6 +413,8 @@ void report(struct slabinfo *s)
 		printf("** Slabs are destroyed via RCU\n");
 	if (s->reclaim_account)
 		printf("** Reclaim accounting active\n");
+	if (s->defrag)
+		printf("** Defragmentation at %d%%\n", s->defrag_ratio);
 
 	printf("\nSizes (bytes)     Slabs              Debug                Memory\n");
 	printf("------------------------------------------------------------------------\n");

@@ -452,6 +461,12 @@ void slabcache(struct slabinfo *s)
 	if (show_empty && s->slabs)
 		return;
 
+	if (show_defrag && !s->defrag)
+		return;
+
+	if (show_ctor && !s->ctor)
+		return;
+
 	store_size(size_str, slab_size(s));
 	sprintf(dist_str,"%lu/%lu/%d", s->slabs, s->partial, s->cpu_slabs);
 

@@ -462,6 +477,10 @@ void slabcache(struct slabinfo *s)
 		*p++ = '*';
 	if (s->cache_dma)
 		*p++ = 'd';
+	if (s->defrag)
+		*p++ = 'D';
+	if (s->ctor)
+		*p++ = 'C';
 	if (s->hwcache_align)
 		*p++ = 'A';
 	if (s->poison)

@@ -481,7 +500,7 @@ void slabcache(struct slabinfo *s)
 	printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n",
 		s->name, s->objects, s->object_size, size_str, dist_str,
 		s->objs_per_slab, s->order,
-		s->slabs ? (s->partial * 100) / s->slabs : 100,
+		s->slabs ? (s->objects * 100) / (s->slabs * s->objs_per_slab) : 100,
 		s->slabs ? (s->objects * s->object_size * 100) /
 			(s->slabs * (page_size << s->order)) : 100,
 		flags);

@@ -1071,7 +1090,16 @@ void read_slab_dir(void)
 			decode_numa_list(slab->numa, t);
 			slab->store_user = get_obj("store_user");
 			slab->trace = get_obj("trace");
+			slab->defrag_ratio = get_obj("defrag_ratio");
+			slab->remote_node_defrag_ratio =
+					get_obj("remote_node_defrag_ratio");
 			chdir("..");
+			if (read_slab_obj(slab, "ops")) {
+				if (strstr(buffer, "ctor :"))
+					slab->ctor = 1;
+				if (strstr(buffer, "kick :"))
+					slab->defrag = 1;
+			}
 			if (slab->name[0] == ':')
 				alias_targets++;
 			slab++;

@@ -1121,7 +1149,9 @@ void output_slabs(void)
 
 struct option opts[] = {
 	{ "aliases", 0, NULL, 'a' },
+	{ "ctor", 0, NULL, 'C' },
 	{ "debug", 2, NULL, 'd' },
+	{ "defrag", 0, NULL, 'D' },
 	{ "empty", 0, NULL, 'e' },
 	{ "first-alias", 0, NULL, 'f' },
 	{ "help", 0, NULL, 'h' },

@@ -1146,7 +1176,7 @@ int main(int argc, char *argv[])
 
 	page_size = getpagesize();
 
-	while ((c = getopt_long(argc, argv, "ad::efhil1noprstvzTS",
+	while ((c = getopt_long(argc, argv, "ad::efhil1noprstvzCDTS",
 						opts, NULL)) != -1)
 	switch(c) {
 		case '1':

@@ -1196,6 +1226,12 @@ int main(int argc, char *argv[])
 		case 'z':
 			skip_zero = 0;
 			break;
+		case 'C':
+			show_ctor = 1;
+			break;
+		case 'D':
+			show_defrag = 1;
+			break;
 		case 'T':
 			show_totals = 1;
 			break;

@@ -1173,19 +1173,15 @@ static __always_inline int slab_trylock(
 /*
  * Management of partially allocated slabs
  */
-static void add_partial_tail(struct kmem_cache_node *n, struct page *page)
+static void add_partial(struct kmem_cache_node *n,
+				struct page *page, int tail)
 {
 	spin_lock(&n->list_lock);
 	n->nr_partial++;
-	list_add_tail(&page->lru, &n->partial);
-	spin_unlock(&n->list_lock);
-}
-
-static void add_partial(struct kmem_cache_node *n, struct page *page)
-{
-	spin_lock(&n->list_lock);
-	n->nr_partial++;
-	list_add(&page->lru, &n->partial);
+	if (tail)
+		list_add_tail(&page->lru, &n->partial);
+	else
+		list_add(&page->lru, &n->partial);
 	spin_unlock(&n->list_lock);
 }
 

@@ -1314,7 +1310,7 @@ static struct page *get_partial(struct k
  *
  * On exit the slab lock will have been dropped.
  */
-static void unfreeze_slab(struct kmem_cache *s, struct page *page)
+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));
 

@@ -1322,7 +1318,7 @@ static void unfreeze_slab(struct kmem_ca
 	if (page->inuse) {
 
 		if (page->freelist)
-			add_partial(n, page);
+			add_partial(n, page, tail);
 		else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
 			add_full(n, page);
 		slab_unlock(page);

@@ -1337,7 +1333,7 @@ static void unfreeze_slab(struct kmem_ca
 			 * partial list stays small. kmem_cache_shrink can
 			 * reclaim empty slabs from the partial list.
 			 */
-			add_partial_tail(n, page);
+			add_partial(n, page, 1);
 			slab_unlock(page);
 		} else {
 			slab_unlock(page);

@@ -1352,6 +1348,7 @@ static void unfreeze_slab(struct kmem_ca
 static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	struct page *page = c->page;
+	int tail = 1;
 	/*
 	 * Merge cpu freelist into freelist. Typically we get here
 	 * because both freelists are empty. So this is unlikely

@@ -1360,6 +1357,8 @@ static void deactivate_slab(struct kmem_
 	while (unlikely(c->freelist)) {
 		void **object;
 
+		tail = 0;	/* Hot objects. Put the slab first */
+
 		/* Retrieve object from cpu_freelist */
 		object = c->freelist;
 		c->freelist = c->freelist[c->offset];

@@ -1370,7 +1369,7 @@ static void deactivate_slab(struct kmem_
 		page->inuse--;
 	}
 	c->page = NULL;
-	unfreeze_slab(s, page);
+	unfreeze_slab(s, page, tail);
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)

@@ -1603,7 +1602,7 @@ checks_ok:
 	 * then add it.
 	 */
 	if (unlikely(!prior))
-		add_partial(get_node(s, page_to_nid(page)), page);
+		add_partial(get_node(s, page_to_nid(page)), page, 0);
 
 out_unlock:
 	slab_unlock(page);

@@ -2012,7 +2011,7 @@ static struct kmem_cache_node * __init e
 #endif
 	init_kmem_cache_node(n);
 	atomic_long_inc(&n->nr_slabs);
-	add_partial(n, page);
+	add_partial(n, page, 0);
 
 	/*
 	 * new_slab() disables interupts. If we do not reenable interrupts here

@@ -52,6 +52,13 @@ struct kmem_cache {
 	void (*ctor)(void *, struct kmem_cache *, unsigned long);
 	int inuse;		/* Offset to metadata */
 	int align;		/* Alignment */
+	int defrag_ratio;	/*
+				 * objects/possible-objects limit. If we have
+				 * less that the specified percentage of
+				 * objects allocated then defrag passes
+				 * will start to occur during reclaim.
+				 */
+
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
 #ifdef CONFIG_SLUB_DEBUG

@@ -2200,6 +2200,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 		goto error;
 
 	s->refcount = 1;
+	s->defrag_ratio = 30;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 100;
 #endif

@@ -3717,6 +3718,22 @@ static ssize_t free_calls_show(struct kmem_cache *s, char *buf)
 }
 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)
 {

@@ -3759,6 +3776,7 @@ static struct attribute * slab_attrs[] = {
 	&shrink_attr.attr,
 	&alloc_calls_attr.attr,
 	&free_calls_attr.attr,
+	&defrag_ratio_attr.attr,
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
 #endif

@@ -59,7 +59,10 @@ struct kmem_cache {
 #endif
 
 #ifdef CONFIG_NUMA
-	int defrag_ratio;
+	/*
+	 * Defragmentation by allocating from a remote node.
+	 */
+	int remote_node_defrag_ratio;
 	struct kmem_cache_node *node[MAX_NUMNODES];
 #endif
 #ifdef CONFIG_SMP

@@ -1267,7 +1267,8 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 	 * expensive if we do it every time we are trying to find a slab
 	 * with available objects.
 	 */
-	if (!s->defrag_ratio || get_cycles() % 1024 > s->defrag_ratio)
+	if (!s->remote_node_defrag_ratio ||
+			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
 	zonelist = &NODE_DATA(slab_node(current->mempolicy))

@@ -2200,7 +2201,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 
 	s->refcount = 1;
 #ifdef CONFIG_NUMA
-	s->defrag_ratio = 100;
+	s->remote_node_defrag_ratio = 100;
 #endif
 
 	if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))

@@ -3717,21 +3718,21 @@ static ssize_t free_calls_show(struct kmem_cache *s, char *buf)
 SLAB_ATTR_RO(free_calls);
 
 #ifdef CONFIG_NUMA
-static ssize_t defrag_ratio_show(struct kmem_cache *s, char *buf)
+static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->defrag_ratio / 10);
+	return sprintf(buf, "%d\n", s->remote_node_defrag_ratio / 10);
 }
 
-static ssize_t defrag_ratio_store(struct kmem_cache *s,
+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);
 
 	if (n < 100)
-		s->defrag_ratio = n * 10;
+		s->remote_node_defrag_ratio = n * 10;
 	return length;
 }
-SLAB_ATTR(defrag_ratio);
+SLAB_ATTR(remote_node_defrag_ratio);
 #endif
 
 static struct attribute * slab_attrs[] = {

@@ -3762,7 +3763,7 @@ static struct attribute * slab_attrs[] = {
 	&cache_dma_attr.attr,
 #endif
 #ifdef CONFIG_NUMA
-	&defrag_ratio_attr.attr,
+	&remote_node_defrag_ratio_attr.attr,
 #endif
 	NULL
 };

@@ -50,7 +50,7 @@ void drop_slab(void)
 	int nr_objects;
 
 	do {
-		nr_objects = shrink_slab(1000, GFP_KERNEL, 1000);
+		nr_objects = shrink_slab(1000, GFP_KERNEL, 1000, NULL);
 	} while (nr_objects > 10);
 }
 

@@ -1202,7 +1202,7 @@ int in_gate_area_no_task(unsigned long addr);
 int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,
 					void __user *, size_t *, loff_t *);
 unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
-			unsigned long lru_pages);
+			unsigned long lru_pages, struct zone *zone);
 void drop_pagecache(void);
 void drop_slab(void);
 

@@ -61,6 +61,7 @@ void kmem_cache_free(struct kmem_cache *, void *);
 unsigned int kmem_cache_size(struct kmem_cache *);
 const char *kmem_cache_name(struct kmem_cache *);
 int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr);
+int kmem_cache_defrag(int node);
 
 /*
  * Please use this macro to create slab caches. Simply specify the

@@ -150,10 +150,18 @@ EXPORT_SYMBOL(unregister_shrinker);
  * are eligible for the caller's allocation attempt.  It is used for balancing
  * slab reclaim versus page reclaim.
  *
+ * zone is the zone for which we are shrinking the slabs. If the intent
+ * is to do a global shrink then zone may be NULL. Specification of a
+ * zone is currently only used to limit slab defragmentation to a NUMA node.
+ * The performace of shrink_slab would be better (in particular under NUMA)
+ * if it could be targeted as a whole to the zone that is under memory
+ * pressure but the VFS infrastructure does not allow that at the present
+ * time.
+ *
  * Returns the number of slab objects which we shrunk.
  */
 unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
-			unsigned long lru_pages)
+			unsigned long lru_pages, struct zone *zone)
 {
 	struct shrinker *shrinker;
 	unsigned long ret = 0;

@@ -210,6 +218,8 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 		shrinker->nr += total_scan;
 	}
 	up_read(&shrinker_rwsem);
+	if (gfp_mask & __GFP_FS)
+		kmem_cache_defrag(zone ? zone_to_nid(zone) : -1);
 	return ret;
 }
 

@@ -1151,7 +1161,8 @@ unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
 		if (!priority)
 			disable_swap_token();
 		nr_reclaimed += shrink_zones(priority, zones, &sc);
-		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
+		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages,
+						NULL);
 		if (reclaim_state) {
 			nr_reclaimed += reclaim_state->reclaimed_slab;
 			reclaim_state->reclaimed_slab = 0;

@@ -1321,7 +1332,7 @@ loop_again:
 			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
-						lru_pages);
+						lru_pages, zone);
 			nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)

@@ -1559,7 +1570,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	/* If slab caches are huge, it's better to hit them first */
 	while (nr_slab >= lru_pages) {
 		reclaim_state.reclaimed_slab = 0;
-		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+		shrink_slab(nr_pages, sc.gfp_mask, lru_pages, NULL);
 		if (!reclaim_state.reclaimed_slab)
 			break;
 

@@ -1597,7 +1608,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-					count_lru_pages());
+					count_lru_pages(), NULL);
 			ret += reclaim_state.reclaimed_slab;
 			if (ret >= nr_pages)
 				goto out;

@@ -1614,7 +1625,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	if (!ret) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
+			shrink_slab(nr_pages, sc.gfp_mask,
+					count_lru_pages(), NULL);
 			ret += reclaim_state.reclaimed_slab;
 		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
 	}

@@ -1774,7 +1786,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * Note that shrink_slab will free memory on all zones and may
 		 * take a long time.
 		 */
-		while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
+		while (shrink_slab(sc.nr_scanned, gfp_mask, order,
+						zone) &&
 			zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
 				slab_reclaimable - nr_pages)
 			;

@@ -62,6 +62,8 @@ unsigned int kmem_cache_size(struct kmem
 const char *kmem_cache_name(struct kmem_cache *);
 int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr);
 int kmem_cache_defrag(int node);
+int kmem_cache_isolate_slab(struct page *);
+int kmem_cache_reclaim(struct list_head *);
 
 /*
  * Please use this macro to create slab caches. Simply specify the

@@ -2532,6 +2532,19 @@ int kmem_cache_defrag(int node)
 	return 0;
 }
 
+/*
+ * SLAB does not support slab defragmentation
+ */
+int kmem_cache_isolate_slab(struct page *page)
+{
+	return -ENOSYS;
+}
+
+int kmem_cache_reclaim(struct list_head *zaplist)
+{
+	return 0;
+}
+
 /**
  * kmem_cache_destroy - delete a cache
  * @cachep: the cache to destroy

@@ -1006,6 +1006,7 @@ static inline int slab_pad_check(struct 
 static inline int check_object(struct kmem_cache *s, struct page *page,
 			void *object, int active) { return 1; }
 static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
+static inline void remove_full(struct kmem_cache *s, struct page *page) {}
 static inline void kmem_cache_open_debug_check(struct kmem_cache *s) {}
 #define slub_debug 0
 #endif

@@ -1068,11 +1069,9 @@ static struct page *new_slab(struct kmem
 	n = get_node(s, page_to_nid(page));
 	if (n)
 		atomic_long_inc(&n->nr_slabs);
+
+	page->inuse = 0;
 	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);
 
 	start = page_address(page);
 	end = start + s->objects * s->size;

@@ -1090,8 +1089,18 @@ static struct page *new_slab(struct kmem
 	set_freepointer(s, last, NULL);
 
 	page->freelist = start;
-	page->inuse = 0;
-out:
+
+	/*
+	 * page->inuse must be 0 when PageSlab(page) becomes
+	 * true so that defrag knows that this slab is not in use.
+	 */
+	smp_wmb();
+	__SetPageSlab(page);
+	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
+			SLAB_STORE_USER | SLAB_TRACE))
+		SetSlabDebug(page);
+
+ out:
 	if (flags & __GFP_WAIT)
 		local_irq_disable();
 	return page;

@@ -2638,6 +2647,73 @@ static unsigned long count_partial(struc
 	return x;
 }
 
+ /*
+ * Isolate page from the slab partial lists. Return 0 if succesful.
+ *
+ * After isolation the LRU field can be used to put the page onto
+ * a reclaim list.
+ */
+int kmem_cache_isolate_slab(struct page *page)
+{
+	unsigned long flags;
+	struct kmem_cache *s;
+	int rc = -ENOENT;
+
+	if (!PageSlab(page) || SlabFrozen(page))
+		return rc;
+
+	/*
+	 * Get a reference to the page. Return if its freed or being freed.
+	 * This is necessary to make sure that the page does not vanish
+	 * from under us before we are able to check the result.
+	 */
+	if (!get_page_unless_zero(page))
+		return rc;
+
+	local_irq_save(flags);
+	slab_lock(page);
+
+	/*
+	 * Check a variety of conditions to insure that the page was not
+	 *  1. Freed
+	 *  2. Frozen
+	 *  3. Is in the process of being freed (min one remaining object)
+	 */
+	if (!PageSlab(page) || SlabFrozen(page) || !page->inuse) {
+		slab_unlock(page);
+		put_page(page);
+		goto out;
+	}
+
+	/*
+	 * Drop reference. There are object remaining and therefore
+	 * the slab lock will be taken before the last objects can
+	 * be removed. So we cannot be in the process of freeing the
+	 * object.
+	 *
+	 * We set the slab frozen before releasing the lock. This means
+	 * that no free action will be performed. If it becomes empty
+	 * then we will free it during kmem_cache_reclaim().
+	 */
+	BUG_ON(page_count(page) <= 1);
+	put_page(page);
+
+	/*
+	 * Remove the slab from the lists and mark it frozen
+	 */
+	s = page->slab;
+	if (page->inuse < s->objects)
+		remove_partial(s, page);
+	else if (s->flags & SLAB_STORE_USER)
+		remove_full(s, page);
+	SetSlabFrozen(page);
+	slab_unlock(page);
+	rc = 0;
+out:
+	local_irq_restore(flags);
+	return rc;
+}
+
 /*
  * Vacate all objects in the given slab.
  *