Slab defragmentation V7

Index: linux-2.6.24-rc2-mm1/Documentation/vm/slabinfo.c
===================================================================
@@ -31,6 +31,8 @@ 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];

@@ -57,6 +59,8 @@ 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;

@@ -91,18 +95,20 @@ void fatal(const char *x, ...)
 void usage(void)
 {
 	printf("slabinfo 5/7/2007. (c) 2007 sgi. [email protected]\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"

@@ -282,7 +288,7 @@ 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");
 }
 
 /*

@@ -325,7 +331,7 @@ void slab_numa(struct slabinfo *s, int m
 		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----------------------");

@@ -334,6 +340,7 @@ void slab_numa(struct slabinfo *s, int m
 		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];
 

@@ -407,6 +414,8 @@ 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");

@@ -453,6 +462,12 @@ 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));
 	snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs, s->partial, s->cpu_slabs);
 

@@ -463,6 +478,10 @@ 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)

@@ -482,7 +501,7 @@ 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);

@@ -1074,7 +1093,16 @@ void read_slab_dir(void)
 			free(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++;

@@ -1124,7 +1152,9 @@ 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' },

@@ -1149,7 +1179,7 @@ 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':

@@ -1199,6 +1229,12 @@ 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;

Index: linux-2.6.24-rc2-mm1/include/linux/slub_def.h
===================================================================
@@ -53,6 +53,13 @@ struct kmem_cache {
 	void (*ctor)(struct kmem_cache *, void *);
 	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

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -2363,6 +2363,7 @@ static int kmem_cache_open(struct kmem_c
 		goto error;
 
 	s->refcount = 1;
+	s->defrag_ratio = 30;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 100;
 #endif

@@ -4009,6 +4010,22 @@ static ssize_t free_calls_show(struct km
 }
 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)
 {

@@ -4051,6 +4068,7 @@ 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

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -3793,16 +3793,18 @@ static ssize_t order_show(struct kmem_ca
 }
 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)
 {

@@ -4053,7 +4055,7 @@ 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,

Index: linux-2.6.24-rc2-mm1/include/linux/slub_def.h
===================================================================
@@ -51,6 +51,37 @@ struct kmem_cache {
 	int objects;		/* Number of objects in slab */
 	int refcount;		/* Refcount for slab cache destroy */
 	void (*ctor)(struct kmem_cache *, void *);
+	/*
+	 * 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;	/*

@@ -211,4 +242,8 @@ static __always_inline void *kmalloc_nod
 }
 #endif
 
+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));
+
 #endif /* _LINUX_SLUB_DEF_H */

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -2760,6 +2760,20 @@ 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;

@@ -3061,7 +3075,7 @@ static int slab_unmergeable(struct kmem_
 	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
 		return 1;
 
-	if (s->ctor)
+	if (s->ctor || s->kick || s->get)
 		return 1;
 
 	/*

@@ -3799,7 +3813,21 @@ static ssize_t ops_show(struct kmem_cach
 
 	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;

Index: linux-2.6.24-rc2-mm1/include/linux/slab_def.h
===================================================================
@@ -98,4 +98,8 @@ found:
 extern const struct seq_operations slabinfo_op;
 ssize_t slabinfo_write(struct file *, const char __user *, size_t, loff_t *);
 
+static inline 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)) {}
+
 #endif	/* _LINUX_SLAB_DEF_H */

Index: linux-2.6.24-rc2-mm1/include/linux/slob_def.h
===================================================================
@@ -33,4 +33,8 @@ static inline void *__kmalloc(size_t siz
 	return kmalloc(size, flags);
 }
 
+static inline 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)) {}
+
 #endif /* __LINUX_SLOB_DEF_H */

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -198,6 +198,9 @@ static enum {
 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.
  */

@@ -2546,7 +2549,7 @@ static struct kmem_cache *create_kmalloc
 			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;

@@ -2760,6 +2763,13 @@ void kfree(const void *x)
 }
 EXPORT_SYMBOL(kfree);
 
+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))

@@ -2771,6 +2781,11 @@ void kmem_cache_setup_defrag(struct kmem
 	BUG_ON(!s->ctor);
 	s->get = get;
 	s->kick = kick;
+	down_write(&slub_lock);
+	list_move(&s->list, &slab_caches);
+	if (s->objects > max_defrag_slab_objects)
+		max_defrag_slab_objects = s->objects;
+	up_write(&slub_lock);
 }
 EXPORT_SYMBOL(kmem_cache_setup_defrag);
 

@@ -3162,7 +3177,7 @@ struct kmem_cache *kmem_cache_create(con
 	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;

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -143,14 +143,14 @@
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
  */
-#define MIN_PARTIAL 2
+#define MIN_PARTIAL 5
 
 /*
  * 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)

@@ -2802,80 +2802,237 @@ static unsigned long count_partial(struc
 	return x;
 }
 
+ /*
+ * 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 objects;
+	void *private;
+	unsigned long flags;
+	unsigned long state;
+
+	BUG_ON(!PageSlab(page));
+	local_irq_save(flags);
+	state = slab_lock(page);
+	BUG_ON(!(state & FROZEN));
+
+	s = page->slab;
+	map = scratch + max_defrag_slab_objects * sizeof(void **);
+	if (!page->inuse || !s->kick)
+		goto out;
+
+	/* Determine used objects */
+	bitmap_fill(map, s->objects);
+	for_each_free_object(p, s, page->freelist)
+			__clear_bit(slab_index(p, s, addr), map);
+
+	objects = 0;
+	memset(vector, 0, s->objects * sizeof(void **));
+	for_each_object(p, s, addr)
+		if (test_bit(slab_index(p, s, addr), map))
+			vector[objects++] = p;
+
+	private = s->get(s, objects, 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, state);
+	local_irq_restore(flags);
+
+	/*
+	 * Perform the KICK callbacks to remove the objects.
+	 */
+	s->kick(s, objects, vector, private);
+
+	local_irq_save(flags);
+	state = slab_lock(page);
+out:
+	/*
+	 * Check the result and unfreeze the slab
+	 */
+	leftover = page->inuse;
+	unfreeze_slab(s, page, leftover > 0, state);
+	local_irq_restore(flags);
+	return leftover;
+}
+
 /*
- * 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);
-	unsigned long flags;
-	unsigned long state;
+	struct page *page2;
 
-	if (!slabs_by_inuse)
-		return -ENOMEM;
+	if (list_empty(zaplist))
+		return 0;
 
-	flush_all(s);
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		n = get_node(s, node);
+	scratch = alloc_scratch();
+	if (!scratch)
+		return 0;
 
-		if (!n->nr_partial)
-			continue;
+	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;
+}
 
-		for (i = 0; i < s->objects; i++)
-			INIT_LIST_HEAD(slabs_by_inuse + i);
+/*
+ * 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,
+	struct kmem_cache_node *n)
+{
+	unsigned long flags;
+	struct page *page, *page2;
+	LIST_HEAD(zaplist);
+	int freed = 0;
+	unsigned long state;
 
-		spin_lock_irqsave(&n->list_lock, flags);
+	spin_lock_irqsave(&n->list_lock, flags);
+	list_for_each_entry_safe(page, page2, &n->partial, lru) {
+		if (page->inuse > s->objects / 4)
+			continue;
+		state = slab_trylock(page);
+		if (!state)
+			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) {
-				list_move(&page->lru,
-				slabs_by_inuse + page->inuse);
-				continue;
+		if (page->inuse) {
+
+			list_move(&page->lru, &zaplist);
+			if (s->kick) {
+				n->nr_partial--;
+				state |= FROZEN;
 			}
-			state = slab_trylock(page);
-			if (!state)
-				continue;
-			/*
-			 * Must hold slab lock here because slab_free may have
-			 * freed the last object and be waiting to release the
-			 * slab.
-			 */
+			slab_unlock(page, state);
+
+		} else {
 			list_del(&page->lru);
 			n->nr_partial--;
 			slab_unlock(page, state);
 			discard_slab(s, page);
+			freed++;
 		}
+	}
 
-		/*
-		 * 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--)
-			list_splice(slabs_by_inuse + i, n->partial.prev);
+	if (!s->kick)
+		/* Simply put the zaplist at the end */
+		list_splice(&zaplist, n->partial.prev);
 
-		spin_unlock_irqrestore(&n->list_lock, flags);
+	spin_unlock_irqrestore(&n->list_lock, flags);
+
+	if (s->kick)
+		freed += kmem_cache_reclaim(&zaplist);
+	return freed;
+}
+
+static unsigned long __kmem_cache_defrag(struct kmem_cache *s, int node)
+{
+	unsigned long capacity;
+	unsigned long objects_in_full_slabs;
+	unsigned long ratio;
+	struct kmem_cache_node *n = get_node(s, node);
+
+	/*
+	 * An insignificant number of partial slabs means that the
+	 * slab cache does not need any defragmentation.
+	 */
+	if (n->nr_partial <= MAX_PARTIAL)
+		return 0;
+
+	capacity = atomic_long_read(&n->nr_slabs) * s->objects;
+	objects_in_full_slabs =
+			(atomic_long_read(&n->nr_slabs) - n->nr_partial)
+							* s->objects;
+	/*
+	 * Worst case calculation: If we would be over the ratio
+	 * even if all partial slabs would only have one object
+	 * then we can skip the next test that requires a scan
+	 * through all the partial page structs to sum up the actual
+	 * number of objects in the partial slabs.
+	 */
+	ratio = (objects_in_full_slabs + 1 * n->nr_partial) * 100 / capacity;
+	if (ratio > s->defrag_ratio)
+		return 0;
+
+	/*
+	 * Now for the real calculation. If usage ratio is more than required
+	 * then no defragmentation is necessary.
+	 */
+	ratio = (objects_in_full_slabs + count_partial(n)) * 100 / capacity;
+	if (ratio > s->defrag_ratio)
+		return 0;
+
+	return __kmem_cache_shrink(s, n) << s->order;
+}
+
+/*
+ * Defrag slabs conditional on the amount of fragmentation on each node.
+ */
+int kmem_cache_defrag(int node)
+{
+	struct kmem_cache *s;
+	unsigned long pages = 0;
+
+	/*
+	 * 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 (node == -1) {
+			int nid;
+
+			for_each_node_state(nid, N_NORMAL_MEMORY)
+				pages += __kmem_cache_defrag(s, nid);
+		} else
+			pages += __kmem_cache_defrag(s, node);
 	}
+	up_read(&slub_lock);
+	return pages;
+}
+EXPORT_SYMBOL(kmem_cache_defrag);
+
+/*
+ * kmem_cache_shrink removes empty slabs from the partial lists.
+ * If the slab cache support 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, get_node(s, node));
 
-	kfree(slabs_by_inuse);
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_shrink);

Index: linux-2.6.24-rc2-mm1/include/linux/slab_def.h
===================================================================
@@ -101,5 +101,6 @@ ssize_t slabinfo_write(struct file *, co
 static inline 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)) {}
+static inline int kmem_cache_defrag(int node) { return 0; }
 
 #endif	/* _LINUX_SLAB_DEF_H */

Index: linux-2.6.24-rc2-mm1/include/linux/slob_def.h
===================================================================
@@ -36,5 +36,6 @@ static inline void *__kmalloc(size_t siz
 static inline 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)) {}
+static inline int kmem_cache_defrag(int node) { return 0; }
 
 #endif /* __LINUX_SLOB_DEF_H */

Index: linux-2.6.24-rc2-mm1/include/linux/slub_def.h
===================================================================
@@ -245,5 +245,6 @@ static __always_inline void *kmalloc_nod
 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 kmem_cache_defrag(int node);
 
 #endif /* _LINUX_SLUB_DEF_H */

Index: linux-2.6.24-rc2-mm1/fs/drop_caches.c
===================================================================
@@ -52,7 +52,7 @@ 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);
 }
 

Index: linux-2.6.24-rc2-mm1/mm/vmscan.c
===================================================================
@@ -168,10 +168,18 @@ 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;

@@ -234,6 +242,8 @@ unsigned long shrink_slab(unsigned long 
 		shrinker->nr += total_scan;
 	}
 	up_read(&shrinker_rwsem);
+	if (gfp_mask & __GFP_FS)
+		kmem_cache_defrag(zone ? zone_to_nid(zone) : -1);
 	return ret;
 }
 

@@ -1291,7 +1301,7 @@ static unsigned long do_try_to_free_page
 		 * over limit cgroups
 		 */
 		if (sc->mem_cgroup == NULL)
-			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;

@@ -1515,7 +1525,7 @@ 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_is_all_unreclaimable(zone))

@@ -1756,7 +1766,7 @@ unsigned long shrink_all_memory(unsigned
 	/* 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;
 

@@ -1794,7 +1804,7 @@ unsigned long shrink_all_memory(unsigned
 
 			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;

@@ -1811,7 +1821,8 @@ unsigned long shrink_all_memory(unsigned
 	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);
 	}

@@ -1974,7 +1985,8 @@ static int __zone_reclaim(struct zone *z
 		 * 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)
 			;

Index: linux-2.6.24-rc2-mm1/include/linux/mm.h
===================================================================
@@ -1165,7 +1165,7 @@ int in_gate_area_no_task(unsigned long a
 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 *z);
 extern void drop_pagecache_sb(struct super_block *);
 void drop_pagecache(void);
 void drop_slab(void);

Index: linux-2.6.24-rc2-mm1/fs/buffer.c
===================================================================
@@ -3227,6 +3227,106 @@ init_buffer_head(struct kmem_cache *cach
 	INIT_LIST_HEAD(&bh->b_assoc_buffers);
 }
 
+/*
+ * Writeback a page to clean the dirty state
+ */
+static void trigger_write(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	int rc;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_NONE,
+		.nr_to_write = 1,
+		.range_start = 0,
+		.range_end = LLONG_MAX,
+		.nonblocking = 1,
+		.for_reclaim = 0
+	};
+
+	if (!mapping->a_ops->writepage)
+		/* No write method for the address space */
+		return;
+
+	if (!clear_page_dirty_for_io(page))
+		/* Someone else already triggered a write */
+		return;
+
+	rc = mapping->a_ops->writepage(page, &wbc);
+	if (rc < 0)
+		/* I/O Error writing */
+		return;
+
+	if (rc == AOP_WRITEPAGE_ACTIVATE)
+		unlock_page(page);
+}
+
+/*
+ * Get references on buffers.
+ *
+ * We obtain references on the page that uses the buffer. v[i] will point to
+ * the corresponding page after get_buffers() is through.
+ *
+ * We are safe from the underlying page being removed simply by doing
+ * a get_page_unless_zero. The buffer head removal may race at will.
+ * try_to_free_buffes will later take appropriate locks to remove the
+ * buffers if they are still there.
+ */
+static void *get_buffers(struct kmem_cache *s, int nr, void **v)
+{
+	struct page *page;
+	struct buffer_head *bh;
+	int i,j;
+	int n = 0;
+
+	for (i = 0; i < nr; i++) {
+		bh = v[i];
+		v[i] = NULL;
+
+		page = bh->b_page;
+
+		if (page && PagePrivate(page)) {
+			for (j = 0; j < n; j++)
+				if (page == v[j])
+					goto cont;
+		}
+
+		if (get_page_unless_zero(page))
+			v[n++] = page;
+cont:	;
+	}
+	return NULL;
+}
+
+/*
+ * Despite its name: kick_buffers operates on a list of pointers to
+ * page structs that was setup by get_buffer
+ */
+static void kick_buffers(struct kmem_cache *s, int nr, void **v,
+							void *private)
+{
+	struct page *page;
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		page = v[i];
+
+		if (!page || PageWriteback(page))
+			continue;
+
+
+		if (!TestSetPageLocked(page)) {
+			if (PageDirty(page))
+				trigger_write(page);
+			else {
+				if (PagePrivate(page))
+					try_to_free_buffers(page);
+				unlock_page(page);
+			}
+		}
+		put_page(page);
+	}
+}
+
 void __init buffer_init(void)
 {
 	int nrpages;

@@ -3236,6 +3336,7 @@ void __init buffer_init(void)
 				(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
 				SLAB_MEM_SPREAD),
 				init_buffer_head);
+	kmem_cache_setup_defrag(bh_cachep, get_buffers, kick_buffers);
 
 	/*
 	 * Limit the bh occupancy to 10% of ZONE_NORMAL

Index: linux-2.6.24-rc2-mm1/fs/inode.c
===================================================================
@@ -1380,6 +1380,101 @@ static int __init set_ihash_entries(char
 }
 __setup("ihash_entries=", set_ihash_entries);
 
+void *get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	int i;
+
+	spin_lock(&inode_lock);
+	for (i = 0; i < nr; i++) {
+		struct inode *inode = v[i];
+
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+			v[i] = NULL;
+		else
+			__iget(inode);
+	}
+	spin_unlock(&inode_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(get_inodes);
+
+/*
+ * Function for filesystems that embedd struct inode into their own
+ * structures. The offset is the offset of the struct inode in the fs inode.
+ */
+void *fs_get_inodes(struct kmem_cache *s, int nr, void **v,
+						unsigned long offset)
+{
+	int i;
+
+	for (i = 0; i < nr; i++)
+		v[i] += offset;
+
+	return get_inodes(s, nr, v);
+}
+EXPORT_SYMBOL(fs_get_inodes);
+
+void kick_inodes(struct kmem_cache *s, int nr, void **v, void *private)
+{
+	struct inode *inode;
+	int i;
+	int abort = 0;
+	LIST_HEAD(freeable);
+	struct super_block *sb;
+
+	for (i = 0; i < nr; i++) {
+		inode = v[i];
+		if (!inode)
+			continue;
+
+		if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+			if (remove_inode_buffers(inode))
+				invalidate_mapping_pages(&inode->i_data,
+								0, -1);
+		}
+
+		/* Invalidate children and dentry */
+		if (S_ISDIR(inode->i_mode)) {
+			struct dentry *d = d_find_alias(inode);
+
+			if (d) {
+				d_invalidate(d);
+				dput(d);
+			}
+		}
+
+		if (inode->i_state & I_DIRTY)
+			write_inode_now(inode, 1);
+
+		d_prune_aliases(inode);
+	}
+
+	mutex_lock(&iprune_mutex);
+	for (i = 0; i < nr; i++) {
+		inode = v[i];
+		if (!inode)
+			continue;
+
+		sb = inode->i_sb;
+		iput(inode);
+		if (abort || !(sb->s_flags & MS_ACTIVE))
+			continue;
+
+		spin_lock(&inode_lock);
+		abort =  !can_unuse(inode);
+
+		if (!abort) {
+			list_move(&inode->i_list, &freeable);
+			inode->i_state |= I_FREEING;
+			inodes_stat.nr_unused--;
+		}
+		spin_unlock(&inode_lock);
+	}
+	dispose_list(&freeable);
+	mutex_unlock(&iprune_mutex);
+}
+EXPORT_SYMBOL(kick_inodes);
+
 /*
  * Initialize the waitqueues and inode hash table.
  */

@@ -1419,6 +1514,7 @@ void __init inode_init(void)
 					 SLAB_MEM_SPREAD),
 					 init_once);
 	register_shrinker(&icache_shrinker);
+	kmem_cache_setup_defrag(inode_cachep, get_inodes, kick_inodes);
 
 	/* Hash may have been set up in inode_init_early */
 	if (!hashdist)

Index: linux-2.6.24-rc2-mm1/include/linux/fs.h
===================================================================
@@ -1775,6 +1775,12 @@ static inline void insert_inode_hash(str
 	__insert_inode_hash(inode, inode->i_ino);
 }
 
+/* Helper functions for inode defragmentation support in filesystems */
+extern void kick_inodes(struct kmem_cache *, int, void **, void *);
+extern void *get_inodes(struct kmem_cache *, int nr, void **);
+extern void *fs_get_inodes(struct kmem_cache *, int nr, void **,
+						unsigned long offset);
+
 extern struct file * get_empty_filp(void);
 extern void file_move(struct file *f, struct list_head *list);
 extern void file_kill(struct file *f);

Index: linux-2.6.24-rc2-mm1/fs/ext2/super.c
===================================================================
@@ -171,6 +171,12 @@ static void init_once(struct kmem_cache 
 	inode_init_once(&ei->vfs_inode);
 }
 
+static void *ext2_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct ext2_inode_info, vfs_inode));
+}
+
 static int init_inodecache(void)
 {
 	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",

@@ -180,6 +186,9 @@ static int init_inodecache(void)
 					     init_once);
 	if (ext2_inode_cachep == NULL)
 		return -ENOMEM;
+
+	kmem_cache_setup_defrag(ext2_inode_cachep,
+			ext2_get_inodes, kick_inodes);
 	return 0;
 }
 

Index: linux-2.6.24-rc2-mm1/fs/ext3/super.c
===================================================================
@@ -484,6 +484,12 @@ static void init_once(struct kmem_cache 
 	inode_init_once(&ei->vfs_inode);
 }
 
+static void *ext3_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct ext3_inode_info, vfs_inode));
+}
+
 static int init_inodecache(void)
 {
 	ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",

@@ -493,6 +499,8 @@ static int init_inodecache(void)
 					     init_once);
 	if (ext3_inode_cachep == NULL)
 		return -ENOMEM;
+	kmem_cache_setup_defrag(ext3_inode_cachep,
+			ext3_get_inodes, kick_inodes);
 	return 0;
 }
 

Index: linux-2.6.24-rc2-mm1/fs/ext4/super.c
===================================================================
@@ -600,6 +600,12 @@ static void init_once(struct kmem_cache 
 	inode_init_once(&ei->vfs_inode);
 }
 
+static void *ext4_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct ext4_inode_info, vfs_inode));
+}
+
 static int init_inodecache(void)
 {
 	ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",

@@ -609,6 +615,8 @@ static int init_inodecache(void)
 					     init_once);
 	if (ext4_inode_cachep == NULL)
 		return -ENOMEM;
+	kmem_cache_setup_defrag(ext4_inode_cachep,
+			ext4_get_inodes, kick_inodes);
 	return 0;
 }
 

Index: linux-2.6.24-rc2-mm1/fs/xfs/linux-2.6/xfs_super.c
===================================================================
@@ -375,6 +375,7 @@ xfs_init_zones(void)
 	xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
 	if (!xfs_ioend_zone)
 		goto out_destroy_vnode_zone;
+	kmem_cache_setup_defrag(xfs_vnode_zone, get_inodes, kick_inodes);
 
 	xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
 						  xfs_ioend_zone);

Index: linux-2.6.24-rc2-mm1/fs/proc/inode.c
===================================================================
@@ -109,6 +109,12 @@ static void init_once(struct kmem_cache 
 	inode_init_once(&ei->vfs_inode);
 }
 
+static void *proc_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct proc_inode, vfs_inode));
+};
+
 int __init proc_init_inodecache(void)
 {
 	proc_inode_cachep = kmem_cache_create("proc_inode_cache",

@@ -116,6 +122,8 @@ int __init proc_init_inodecache(void)
 					     0, (SLAB_RECLAIM_ACCOUNT|
 						SLAB_MEM_SPREAD|SLAB_PANIC),
 					     init_once);
+	kmem_cache_setup_defrag(proc_inode_cachep,
+				proc_get_inodes, kick_inodes);
 	return 0;
 }
 

Index: linux-2.6.24-rc2-mm1/fs/reiserfs/super.c
===================================================================
@@ -532,6 +532,12 @@ static void init_once(struct kmem_cache 
 #endif
 }
 
+static void *reiserfs_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct reiserfs_inode_info, vfs_inode));
+}
+
 static int init_inodecache(void)
 {
 	reiserfs_inode_cachep = kmem_cache_create("reiser_inode_cache",

@@ -542,6 +548,8 @@ static int init_inodecache(void)
 						  init_once);
 	if (reiserfs_inode_cachep == NULL)
 		return -ENOMEM;
+	kmem_cache_setup_defrag(reiserfs_inode_cachep,
+			reiserfs_get_inodes, kick_inodes);
 	return 0;
 }
 

index 5d879fd..78a193f 100644
@@ -265,6 +265,12 @@ static void init_once(struct kmem_cache *cachep, void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
+static void *sock_get_inodes(struct kmem_cache *s, int nr, void **v)
+{
+	return fs_get_inodes(s, nr, v,
+		offsetof(struct socket_alloc, vfs_inode));
+}
+
 static int init_inodecache(void)
 {
 	sock_inode_cachep = kmem_cache_create("sock_inode_cache",

@@ -276,6 +282,8 @@ static int init_inodecache(void)
 					      init_once);
 	if (sock_inode_cachep == NULL)
 		return -ENOMEM;
+	kmem_cache_setup_defrag(sock_inode_cachep,
+			sock_get_inodes, kick_inodes);
 	return 0;
 }
 

Index: linux-2.6.24-rc2-mm1/fs/dcache.c
===================================================================
@@ -871,6 +871,16 @@ static struct shrinker dcache_shrinker =
 	.seeks = DEFAULT_SEEKS,
 };
 
+void dcache_ctor(struct kmem_cache *s, void *p)
+{
+	struct dentry *dentry = p;
+
+	spin_lock_init(&dentry->d_lock);
+	dentry->d_inode = NULL;
+	INIT_LIST_HEAD(&dentry->d_lru);
+	INIT_LIST_HEAD(&dentry->d_alias);
+}
+
 /**
  * d_alloc	-	allocate a dcache entry
  * @parent: parent of entry to allocate

@@ -908,8 +918,6 @@ struct dentry *d_alloc(struct dentry * p
 
 	atomic_set(&dentry->d_count, 1);
 	dentry->d_flags = DCACHE_UNHASHED;
-	spin_lock_init(&dentry->d_lock);
-	dentry->d_inode = NULL;
 	dentry->d_parent = NULL;
 	dentry->d_sb = NULL;
 	dentry->d_op = NULL;

@@ -919,9 +927,7 @@ struct dentry *d_alloc(struct dentry * p
 	dentry->d_cookie = NULL;
 #endif
 	INIT_HLIST_NODE(&dentry->d_hash);
-	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_LIST_HEAD(&dentry->d_subdirs);
-	INIT_LIST_HEAD(&dentry->d_alias);
 
 	if (parent) {
 		dentry->d_parent = dget(parent);

@@ -2102,14 +2108,10 @@ static void __init dcache_init(void)
 {
 	int loop;
 
-	/* 
-	 * A constructor could be added for stable state like the lists,
-	 * but it is probably not worth it because of the cache nature
-	 * of the dcache. 
-	 */
-	dentry_cache = KMEM_CACHE(dentry,
-		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
-	
+	dentry_cache = kmem_cache_create("dentry_cache", sizeof(struct dentry),
+		0, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD,
+		dcache_ctor);
+
 	register_shrinker(&dcache_shrinker);
 
 	/* Hash may have been set up in dcache_init_early */

Index: linux-2.6.24-rc2-mm1/fs/dcache.c
===================================================================
@@ -31,6 +31,7 @@
 #include <linux/seqlock.h>
 #include <linux/swap.h>
 #include <linux/bootmem.h>
+#include <linux/backing-dev.h>
 #include "internal.h"
 
 

@@ -143,7 +144,10 @@ static struct dentry *d_kill(struct dent
 
 	list_del(&dentry->d_u.d_child);
 	dentry_stat.nr_dentry--;	/* For d_free, below */
-	/*drops the locks, at that point nobody can reach this dentry */
+	/*
+	 * drops the locks, at that point nobody (aside from defrag)
+	 * can reach this dentry
+	 */
 	dentry_iput(dentry);
 	parent = dentry->d_parent;
 	d_free(dentry);

@@ -2104,6 +2108,100 @@ static void __init dcache_init_early(voi
 		INIT_HLIST_HEAD(&dentry_hashtable[loop]);
 }
 
+/*
+ * The slab allocator is holding off frees. We can safely examine
+ * the object without the danger of it vanishing from under us.
+ */
+static void *get_dentries(struct kmem_cache *s, int nr, void **v)
+{
+	struct dentry *dentry;
+	int i;
+
+	spin_lock(&dcache_lock);
+	for (i = 0; i < nr; i++) {
+		dentry = v[i];
+
+		/*
+		 * Three sorts of dentries cannot be reclaimed:
+		 *
+		 * 1. dentries that are in the process of being allocated
+		 *    or being freed. In that case the dentry is neither
+		 *    on the LRU nor hashed.
+		 *
+		 * 2. Fake hashed entries as used for anonymous dentries
+		 *    and pipe I/O. The fake hashed entries have d_flags
+		 *    set to indicate a hashed entry. However, the
+		 *    d_hash field indicates that the entry is not hashed.
+		 *
+		 * 3. dentries that have a backing store that is not
+		 *    writable. This is true for tmpsfs and other in
+		 *    memory filesystems. Removing dentries from them
+		 *    would loose dentries for good.
+		 */
+		if ((d_unhashed(dentry) && list_empty(&dentry->d_lru)) ||
+		   (!d_unhashed(dentry) && hlist_unhashed(&dentry->d_hash)) ||
+		   (dentry->d_inode &&
+		   !mapping_cap_writeback_dirty(dentry->d_inode->i_mapping)))
+			/* Ignore this dentry */
+			v[i] = NULL;
+		else
+			/* dget_locked will remove the dentry from the LRU */
+			dget_locked(dentry);
+	}
+	spin_unlock(&dcache_lock);
+	return NULL;
+}
+
+/*
+ * Slab has dropped all the locks. Get rid of the refcount obtained
+ * earlier and also free the object.
+ */
+static void kick_dentries(struct kmem_cache *s,
+				int nr, void **v, void *private)
+{
+	struct dentry *dentry;
+	int i;
+
+	/*
+	 * First invalidate the dentries without holding the dcache lock
+	 */
+	for (i = 0; i < nr; i++) {
+		dentry = v[i];
+
+		if (dentry)
+			d_invalidate(dentry);
+	}
+
+	/*
+	 * If we are the last one holding a reference then the dentries can
+	 * be freed. We need the dcache_lock.
+	 */
+	spin_lock(&dcache_lock);
+	for (i = 0; i < nr; i++) {
+		dentry = v[i];
+		if (!dentry)
+			continue;
+
+		spin_lock(&dentry->d_lock);
+		if (atomic_read(&dentry->d_count) > 1) {
+			spin_unlock(&dentry->d_lock);
+			spin_unlock(&dcache_lock);
+			dput(dentry);
+			spin_lock(&dcache_lock);
+			continue;
+		}
+
+		prune_one_dentry(dentry);
+	}
+	spin_unlock(&dcache_lock);
+
+	/*
+	 * dentries are freed using RCU so we need to wait until RCU
+	 * operations are complete
+	 */
+	synchronize_rcu();
+}
+
 static void __init dcache_init(void)
 {
 	int loop;

@@ -2113,6 +2211,7 @@ static void __init dcache_init(void)
 		dcache_ctor);
 
 	register_shrinker(&dcache_shrinker);
+	kmem_cache_setup_defrag(dentry_cache, get_dentries, kick_dentries);
 
 	/* Hash may have been set up in dcache_init_early */
 	if (!hashdist)

Index: linux-2.6.24-rc2-mm1/mm/slub.c
===================================================================
@@ -102,6 +102,7 @@
 
 #define FROZEN (1 << PG_active)
 #define LOCKED (1 << PG_locked)
+#define KICKABLE (1 << PG_dirty)
 
 #ifdef CONFIG_SLUB_DEBUG
 #define SLABDEBUG (1 << PG_error)

@@ -1098,6 +1099,8 @@ static noinline struct page *new_slab(st
 	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
 			SLAB_STORE_USER | SLAB_TRACE))
 		state |= SLABDEBUG;
+	if (s->kick)
+		state |= KICKABLE;
 
 	page->flags |= state;
 	start = page_address(page);

@@ -1170,6 +1173,7 @@ static void discard_slab(struct kmem_cac
 
 	atomic_long_dec(&n->nr_slabs);
 	reset_page_mapcount(page);
+	page->flags &= ~KICKABLE;
 	__ClearPageSlab(page);
 	free_slab(s, page);
 }

@@ -1402,8 +1406,11 @@ static void unfreeze_slab(struct kmem_ca
 
 		if (page->freelist != page->end)
 			add_partial(s, page, tail);
-		else
+		else {
 			add_full(s, page, state);
+			if (s->kick)
+				state |= KICKABLE;
+		}
 		slab_unlock(page, state);
 
 	} else {

@@ -2829,7 +2836,7 @@ static int kmem_cache_vacate(struct page
 
 	s = page->slab;
 	map = scratch + max_defrag_slab_objects * sizeof(void **);
-	if (!page->inuse || !s->kick)
+	if (!page->inuse || !s->kick || !(state & KICKABLE))
 		goto out;
 
 	/* Determine used objects */

@@ -2866,6 +2873,8 @@ out:
 	 * Check the result and unfreeze the slab
 	 */
 	leftover = page->inuse;
+	if (leftover)
+		state &= ~KICKABLE;
 	unfreeze_slab(s, page, leftover > 0, state);
 	local_irq_restore(flags);
 	return leftover;

@@ -2914,14 +2923,14 @@ static unsigned long __kmem_cache_shrink
 
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, page2, &n->partial, lru) {
-		if (page->inuse > s->objects / 4)
-			continue;
+		if (page->inuse > s->objects / 4 ||
+			(!(page->flags & KICKABLE) && s->kick))
+				continue;
 		state = slab_trylock(page);
 		if (!state)
 			continue;
 
 		if (page->inuse) {
-
 			list_move(&page->lru, &zaplist);
 			if (s->kick) {
 				n->nr_partial--;