Merge branches 'slab/next' and 'slub/partial' into slab/for-linus

Documentation/vm/00-INDEX

@@ -30,8 +30,6 @@ page_migration
 	- description of page migration in NUMA systems.
 pagemap.txt
 	- pagemap, from the userspace perspective
-slabinfo.c
-	- source code for a tool to get reports about slabs.
 slub.txt
 	- a short users guide for SLUB.
 unevictable-lru.txt

include/linux/mm_types.h

@@ -79,9 +79,21 @@ struct page {
 	};
 
 	/* Third double word block */
-	struct list_head lru;		/* Pageout list, eg. active_list
+	union {
+		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
 					 */
+		struct {		/* slub per cpu partial pages */
+			struct page *next;	/* Next partial slab */
+#ifdef CONFIG_64BIT
+			int pages;	/* Nr of partial slabs left */
+			int pobjects;	/* Approximate # of objects */
+#else
+			short int pages;
+			short int pobjects;
+#endif
+		};
+	};
 
 	/* Remainder is not double word aligned */
 	union {

include/linux/slub_def.h

@@ -36,12 +36,15 @@ enum stat_item {
 	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
+	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
+	CPU_PARTIAL_FREE,	/* USed cpu partial on free */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
 	void **freelist;	/* Pointer to next available object */
 	unsigned long tid;	/* Globally unique transaction id */
 	struct page *page;	/* The slab from which we are allocating */
+	struct page *partial;	/* Partially allocated frozen slabs */
 	int node;		/* The node of the page (or -1 for debug) */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
@@ -79,6 +82,7 @@ struct kmem_cache {
 	int size;		/* The size of an object including meta data */
 	int objsize;		/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
+	int cpu_partial;	/* Number of per cpu partial objects to keep around */
 	struct kmem_cache_order_objects oo;
 
 	/* Allocation and freeing of slabs */

mm/slab.c

@@ -1851,15 +1851,15 @@ static void dump_line(char *data, int offset, int limit)
 	unsigned char error = 0;
 	int bad_count = 0;
 
-	printk(KERN_ERR "%03x:", offset);
+	printk(KERN_ERR "%03x: ", offset);
 	for (i = 0; i < limit; i++) {
 		if (data[offset + i] != POISON_FREE) {
 			error = data[offset + i];
 			bad_count++;
 		}
-		printk(" %02x", (unsigned char)data[offset + i]);
 	}
-	printk("\n");
+	print_hex_dump(KERN_CONT, "", 0, 16, 1,
+			&data[offset], limit, 1);
 
 	if (bad_count == 1) {
 		error ^= POISON_FREE;
@@ -3039,14 +3039,9 @@ bad:
 		printk(KERN_ERR "slab: Internal list corruption detected in "
 				"cache '%s'(%d), slabp %p(%d). Hexdump:\n",
 			cachep->name, cachep->num, slabp, slabp->inuse);
-		for (i = 0;
-		     i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t);
-		     i++) {
-			if (i % 16 == 0)
-				printk("\n%03x:", i);
-			printk(" %02x", ((unsigned char *)slabp)[i]);
-		}
-		printk("\n");
+		print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp,
+			sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t),
+			1);
 		BUG();
 	}
 }
@@ -4584,7 +4579,7 @@ static const struct file_operations proc_slabstats_operations = {
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
+	proc_create("slabinfo",S_IWUSR|S_IRUSR,NULL,&proc_slabinfo_operations);
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 	proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
 #endif

mm/slub.c

@@ -467,34 +467,8 @@ static int disable_higher_order_debug;
  */
 static void print_section(char *text, u8 *addr, unsigned int length)
 {
-	int i, offset;
-	int newline = 1;
-	char ascii[17];
-
-	ascii[16] = 0;
-
-	for (i = 0; i < length; i++) {
-		if (newline) {
-			printk(KERN_ERR "%8s 0x%p: ", text, addr + i);
-			newline = 0;
-		}
-		printk(KERN_CONT " %02x", addr[i]);
-		offset = i % 16;
-		ascii[offset] = isgraph(addr[i]) ? addr[i] : '.';
-		if (offset == 15) {
-			printk(KERN_CONT " %s\n", ascii);
-			newline = 1;
-		}
-	}
-	if (!newline) {
-		i %= 16;
-		while (i < 16) {
-			printk(KERN_CONT "   ");
-			ascii[i] = ' ';
-			i++;
-		}
-		printk(KERN_CONT " %s\n", ascii);
-	}
+	print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
+			length, 1);
 }
 
 static struct track *get_track(struct kmem_cache *s, void *object,
@@ -625,12 +599,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 			p, p - addr, get_freepointer(s, p));
 
 	if (p > addr + 16)
-		print_section("Bytes b4", p - 16, 16);
-
-	print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE));
+		print_section("Bytes b4 ", p - 16, 16);
 
+	print_section("Object ", p, min_t(unsigned long, s->objsize,
+				PAGE_SIZE));
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone", p + s->objsize,
+		print_section("Redzone ", p + s->objsize,
 			s->inuse - s->objsize);
 
 	if (s->offset)
@@ -643,7 +617,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 
 	if (off != s->size)
 		/* Beginning of the filler is the free pointer */
-		print_section("Padding", p + off, s->size - off);
+		print_section("Padding ", p + off, s->size - off);
 
 	dump_stack();
 }
@@ -838,7 +812,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding", end - remainder, remainder);
+	print_section("Padding ", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
 	return 0;
@@ -987,7 +961,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 			page->freelist);
 
 		if (!alloc)
-			print_section("Object", (void *)object, s->objsize);
+			print_section("Object ", (void *)object, s->objsize);
 
 		dump_stack();
 	}
@@ -1447,7 +1421,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	set_freepointer(s, last, NULL);
 
 	page->freelist = start;
-	page->inuse = 0;
+	page->inuse = page->objects;
 	page->frozen = 1;
 out:
 	return page;
@@ -1534,7 +1508,7 @@ static inline void add_partial(struct kmem_cache_node *n,
 				struct page *page, int tail)
 {
 	n->nr_partial++;
-	if (tail)
+	if (tail == DEACTIVATE_TO_TAIL)
 		list_add_tail(&page->lru, &n->partial);
 	else
 		list_add(&page->lru, &n->partial);
@@ -1554,10 +1528,13 @@ static inline void remove_partial(struct kmem_cache_node *n,
  * Lock slab, remove from the partial list and put the object into the
  * per cpu freelist.
  *
+ * Returns a list of objects or NULL if it fails.
+ *
  * Must hold list_lock.
  */
-static inline int acquire_slab(struct kmem_cache *s,
-		struct kmem_cache_node *n, struct page *page)
+static inline void *acquire_slab(struct kmem_cache *s,
+		struct kmem_cache_node *n, struct page *page,
+		int mode)
 {
 	void *freelist;
 	unsigned long counters;
@@ -1572,7 +1549,8 @@ static inline int acquire_slab(struct kmem_cache *s,
 		freelist = page->freelist;
 		counters = page->counters;
 		new.counters = counters;
-		new.inuse = page->objects;
+		if (mode)
+			new.inuse = page->objects;
 
 		VM_BUG_ON(new.frozen);
 		new.frozen = 1;
@@ -1583,32 +1561,19 @@ static inline int acquire_slab(struct kmem_cache *s,
 			"lock and freeze"));
 
 	remove_partial(n, page);
-
-	if (freelist) {
-		/* Populate the per cpu freelist */
-		this_cpu_write(s->cpu_slab->freelist, freelist);
-		this_cpu_write(s->cpu_slab->page, page);
-		this_cpu_write(s->cpu_slab->node, page_to_nid(page));
-		return 1;
-	} else {
-		/*
-		 * Slab page came from the wrong list. No object to allocate
-		 * from. Put it onto the correct list and continue partial
-		 * scan.
-		 */
-		printk(KERN_ERR "SLUB: %s : Page without available objects on"
-			" partial list\n", s->name);
-		return 0;
-	}
+	return freelist;
 }
 
+static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static struct page *get_partial_node(struct kmem_cache *s,
-					struct kmem_cache_node *n)
+static void *get_partial_node(struct kmem_cache *s,
+		struct kmem_cache_node *n, struct kmem_cache_cpu *c)
 {
-	struct page *page;
+	struct page *page, *page2;
+	void *object = NULL;
 
 	/*
 	 * Racy check. If we mistakenly see no partial slabs then we
@@ -1620,26 +1585,43 @@ static struct page *get_partial_node(struct kmem_cache *s,
 		return NULL;
 
 	spin_lock(&n->list_lock);
-	list_for_each_entry(page, &n->partial, lru)
-		if (acquire_slab(s, n, page))
-			goto out;
-	page = NULL;
-out:
+	list_for_each_entry_safe(page, page2, &n->partial, lru) {
+		void *t = acquire_slab(s, n, page, object == NULL);
+		int available;
+
+		if (!t)
+			break;
+
+		if (!object) {
+			c->page = page;
+			c->node = page_to_nid(page);
+			stat(s, ALLOC_FROM_PARTIAL);
+			object = t;
+			available =  page->objects - page->inuse;
+		} else {
+			page->freelist = t;
+			available = put_cpu_partial(s, page, 0);
+		}
+		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
+			break;
+
+	}
 	spin_unlock(&n->list_lock);
-	return page;
+	return object;
 }
 
 /*
  * Get a page from somewhere. Search in increasing NUMA distances.
  */
-static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
+static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags,
+		struct kmem_cache_cpu *c)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
-	struct page *page;
+	void *object;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between
@@ -1672,10 +1654,10 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > s->min_partial) {
-			page = get_partial_node(s, n);
-			if (page) {
+			object = get_partial_node(s, n, c);
+			if (object) {
 				put_mems_allowed();
-				return page;
+				return object;
 			}
 		}
 	}
@@ -1687,16 +1669,17 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 /*
  * Get a partial page, lock it and return it.
  */
-static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
+static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
+		struct kmem_cache_cpu *c)
 {
-	struct page *page;
+	void *object;
 	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-	page = get_partial_node(s, get_node(s, searchnode));
-	if (page || node != NUMA_NO_NODE)
-		return page;
+	object = get_partial_node(s, get_node(s, searchnode), c);
+	if (object || node != NUMA_NO_NODE)
+		return object;
 
-	return get_any_partial(s, flags);
+	return get_any_partial(s, flags, c);
 }
 
 #ifdef CONFIG_PREEMPT
@@ -1765,9 +1748,6 @@ void init_kmem_cache_cpus(struct kmem_cache *s)
 	for_each_possible_cpu(cpu)
 		per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
 }
-/*
- * Remove the cpu slab
- */
 
 /*
  * Remove the cpu slab
@@ -1781,13 +1761,13 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 	enum slab_modes l = M_NONE, m = M_NONE;
 	void *freelist;
 	void *nextfree;
-	int tail = 0;
+	int tail = DEACTIVATE_TO_HEAD;
 	struct page new;
 	struct page old;
 
 	if (page->freelist) {
 		stat(s, DEACTIVATE_REMOTE_FREES);
-		tail = 1;
+		tail = DEACTIVATE_TO_TAIL;
 	}
 
 	c->tid = next_tid(c->tid);
@@ -1893,7 +1873,7 @@ redo:
 		if (m == M_PARTIAL) {
 
 			add_partial(n, page, tail);
-			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
+			stat(s, tail);
 
 		} else if (m == M_FULL) {
 
@@ -1920,6 +1900,123 @@ redo:
 	}
 }
 
+/* Unfreeze all the cpu partial slabs */
+static void unfreeze_partials(struct kmem_cache *s)
+{
+	struct kmem_cache_node *n = NULL;
+	struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
+	struct page *page;
+
+	while ((page = c->partial)) {
+		enum slab_modes { M_PARTIAL, M_FREE };
+		enum slab_modes l, m;
+		struct page new;
+		struct page old;
+
+		c->partial = page->next;
+		l = M_FREE;
+
+		do {
+
+			old.freelist = page->freelist;
+			old.counters = page->counters;
+			VM_BUG_ON(!old.frozen);
+
+			new.counters = old.counters;
+			new.freelist = old.freelist;
+
+			new.frozen = 0;
+
+			if (!new.inuse && (!n || n->nr_partial > s->min_partial))
+				m = M_FREE;
+			else {
+				struct kmem_cache_node *n2 = get_node(s,
+							page_to_nid(page));
+
+				m = M_PARTIAL;
+				if (n != n2) {
+					if (n)
+						spin_unlock(&n->list_lock);
+
+					n = n2;
+					spin_lock(&n->list_lock);
+				}
+			}
+
+			if (l != m) {
+				if (l == M_PARTIAL)
+					remove_partial(n, page);
+				else
+					add_partial(n, page, 1);
+
+				l = m;
+			}
+
+		} while (!cmpxchg_double_slab(s, page,
+				old.freelist, old.counters,
+				new.freelist, new.counters,
+				"unfreezing slab"));
+
+		if (m == M_FREE) {
+			stat(s, DEACTIVATE_EMPTY);
+			discard_slab(s, page);
+			stat(s, FREE_SLAB);
+		}
+	}
+
+	if (n)
+		spin_unlock(&n->list_lock);
+}
+
+/*
+ * Put a page that was just frozen (in __slab_free) into a partial page
+ * slot if available. This is done without interrupts disabled and without
+ * preemption disabled. The cmpxchg is racy and may put the partial page
+ * onto a random cpus partial slot.
+ *
+ * If we did not find a slot then simply move all the partials to the
+ * per node partial list.
+ */
+int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+{
+	struct page *oldpage;
+	int pages;
+	int pobjects;
+
+	do {
+		pages = 0;
+		pobjects = 0;
+		oldpage = this_cpu_read(s->cpu_slab->partial);
+
+		if (oldpage) {
+			pobjects = oldpage->pobjects;
+			pages = oldpage->pages;
+			if (drain && pobjects > s->cpu_partial) {
+				unsigned long flags;
+				/*
+				 * partial array is full. Move the existing
+				 * set to the per node partial list.
+				 */
+				local_irq_save(flags);
+				unfreeze_partials(s);
+				local_irq_restore(flags);
+				pobjects = 0;
+				pages = 0;
+			}
+		}
+
+		pages++;
+		pobjects += page->objects - page->inuse;
+
+		page->pages = pages;
+		page->pobjects = pobjects;
+		page->next = oldpage;
+
+	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+	stat(s, CPU_PARTIAL_FREE);
+	return pobjects;
+}
+
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	stat(s, CPUSLAB_FLUSH);
@@ -1935,8 +2032,12 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 {
 	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
-	if (likely(c && c->page))
-		flush_slab(s, c);
+	if (likely(c)) {
+		if (c->page)
+			flush_slab(s, c);
+
+		unfreeze_partials(s);
+	}
 }
 
 static void flush_cpu_slab(void *d)
@@ -2027,12 +2128,39 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 	}
 }
 
+static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
+			int node, struct kmem_cache_cpu **pc)
+{
+	void *object;
+	struct kmem_cache_cpu *c;
+	struct page *page = new_slab(s, flags, node);
+
+	if (page) {
+		c = __this_cpu_ptr(s->cpu_slab);
+		if (c->page)
+			flush_slab(s, c);
+
+		/*
+		 * No other reference to the page yet so we can
+		 * muck around with it freely without cmpxchg
+		 */
+		object = page->freelist;
+		page->freelist = NULL;
+
+		stat(s, ALLOC_SLAB);
+		c->node = page_to_nid(page);
+		c->page = page;
+		*pc = c;
+	} else
+		object = NULL;
+
+	return object;
+}
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
  *
- * Interrupts are disabled.
- *
  * Processing is still very fast if new objects have been freed to the
  * regular freelist. In that case we simply take over the regular freelist
  * as the lockless freelist and zap the regular freelist.
@@ -2049,7 +2177,6 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			  unsigned long addr, struct kmem_cache_cpu *c)
 {
 	void **object;
-	struct page *page;
 	unsigned long flags;
 	struct page new;
 	unsigned long counters;
@@ -2064,13 +2191,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	c = this_cpu_ptr(s->cpu_slab);
 #endif
 
-	/* We handle __GFP_ZERO in the caller */
-	gfpflags &= ~__GFP_ZERO;
-
-	page = c->page;
-	if (!page)
+	if (!c->page)
 		goto new_slab;
-
+redo:
 	if (unlikely(!node_match(c, node))) {
 		stat(s, ALLOC_NODE_MISMATCH);
 		deactivate_slab(s, c);
@@ -2080,8 +2203,8 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	stat(s, ALLOC_SLOWPATH);
 
 	do {
-		object = page->freelist;
-		counters = page->counters;
+		object = c->page->freelist;
+		counters = c->page->counters;
 		new.counters = counters;
 		VM_BUG_ON(!new.frozen);
 
@@ -2093,17 +2216,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 		 *
 		 * If there are objects left then we retrieve them
 		 * and use them to refill the per cpu queue.
-		*/
+		 */
 
-		new.inuse = page->objects;
+		new.inuse = c->page->objects;
 		new.frozen = object != NULL;
 
-	} while (!__cmpxchg_double_slab(s, page,
+	} while (!__cmpxchg_double_slab(s, c->page,
 			object, counters,
 			NULL, new.counters,
 			"__slab_alloc"));
 
-	if (unlikely(!object)) {
+	if (!object) {
 		c->page = NULL;
 		stat(s, DEACTIVATE_BYPASS);
 		goto new_slab;
@@ -2112,58 +2235,47 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
-	VM_BUG_ON(!page->frozen);
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
 	return object;
 
 new_slab:
-	page = get_partial(s, gfpflags, node);
-	if (page) {
-		stat(s, ALLOC_FROM_PARTIAL);
-		object = c->freelist;
 
-		if (kmem_cache_debug(s))
-			goto debug;
-		goto load_freelist;
+	if (c->partial) {
+		c->page = c->partial;
+		c->partial = c->page->next;
+		c->node = page_to_nid(c->page);
+		stat(s, CPU_PARTIAL_ALLOC);
+		c->freelist = NULL;
+		goto redo;
 	}
 
-	page = new_slab(s, gfpflags, node);
+	/* Then do expensive stuff like retrieving pages from the partial lists */
+	object = get_partial(s, gfpflags, node, c);
 
-	if (page) {
-		c = __this_cpu_ptr(s->cpu_slab);
-		if (c->page)
-			flush_slab(s, c);
+	if (unlikely(!object)) {
 
-		/*
-		 * No other reference to the page yet so we can
-		 * muck around with it freely without cmpxchg
-		 */
-		object = page->freelist;
-		page->freelist = NULL;
-		page->inuse = page->objects;
+		object = new_slab_objects(s, gfpflags, node, &c);
 
-		stat(s, ALLOC_SLAB);
-		c->node = page_to_nid(page);
-		c->page = page;
+		if (unlikely(!object)) {
+			if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+				slab_out_of_memory(s, gfpflags, node);
 
-		if (kmem_cache_debug(s))
-			goto debug;
-		goto load_freelist;
+			local_irq_restore(flags);
+			return NULL;
+		}
 	}
-	if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
-		slab_out_of_memory(s, gfpflags, node);
-	local_irq_restore(flags);
-	return NULL;
 
-debug:
-	if (!object || !alloc_debug_processing(s, page, object, addr))
-		goto new_slab;
+	if (likely(!kmem_cache_debug(s)))
+		goto load_freelist;
+
+	/* Only entered in the debug case */
+	if (!alloc_debug_processing(s, c->page, object, addr))
+		goto new_slab;	/* Slab failed checks. Next slab needed */
 
 	c->freelist = get_freepointer(s, object);
 	deactivate_slab(s, c);
-	c->page = NULL;
 	c->node = NUMA_NO_NODE;
 	local_irq_restore(flags);
 	return object;
@@ -2333,16 +2445,29 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		was_frozen = new.frozen;
 		new.inuse--;
 		if ((!new.inuse || !prior) && !was_frozen && !n) {
-                        n = get_node(s, page_to_nid(page));
-			/*
-			 * Speculatively acquire the list_lock.
-			 * If the cmpxchg does not succeed then we may
-			 * drop the list_lock without any processing.
-			 *
-			 * Otherwise the list_lock will synchronize with
-			 * other processors updating the list of slabs.
-			 */
-                        spin_lock_irqsave(&n->list_lock, flags);
+
+			if (!kmem_cache_debug(s) && !prior)
+
+				/*
+				 * Slab was on no list before and will be partially empty
+				 * We can defer the list move and instead freeze it.
+				 */
+				new.frozen = 1;
+
+			else { /* Needs to be taken off a list */
+
+	                        n = get_node(s, page_to_nid(page));
+				/*
+				 * Speculatively acquire the list_lock.
+				 * If the cmpxchg does not succeed then we may
+				 * drop the list_lock without any processing.
+				 *
+				 * Otherwise the list_lock will synchronize with
+				 * other processors updating the list of slabs.
+				 */
+				spin_lock_irqsave(&n->list_lock, flags);
+
+			}
 		}
 		inuse = new.inuse;
 
@@ -2352,7 +2477,15 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		"__slab_free"));
 
 	if (likely(!n)) {
-                /*
+
+		/*
+		 * If we just froze the page then put it onto the
+		 * per cpu partial list.
+		 */
+		if (new.frozen && !was_frozen)
+			put_cpu_partial(s, page, 1);
+
+		/*
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
 		 */
@@ -2377,7 +2510,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 */
 		if (unlikely(!prior)) {
 			remove_full(s, page);
-			add_partial(n, page, 1);
+			add_partial(n, page, DEACTIVATE_TO_TAIL);
 			stat(s, FREE_ADD_PARTIAL);
 		}
 	}
@@ -2421,7 +2554,6 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	slab_free_hook(s, x);
 
 redo:
-
 	/*
 	 * Determine the currently cpus per cpu slab.
 	 * The cpu may change afterward. However that does not matter since
@@ -2685,7 +2817,7 @@ static void early_kmem_cache_node_alloc(int node)
 	n = page->freelist;
 	BUG_ON(!n);
 	page->freelist = get_freepointer(kmem_cache_node, n);
-	page->inuse++;
+	page->inuse = 1;
 	page->frozen = 0;
 	kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG
@@ -2695,7 +2827,7 @@ static void early_kmem_cache_node_alloc(int node)
 	init_kmem_cache_node(n, kmem_cache_node);
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
-	add_partial(n, page, 0);
+	add_partial(n, page, DEACTIVATE_TO_HEAD);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2911,7 +3043,34 @@ static int kmem_cache_open(struct kmem_cache *s,
 	 * The larger the object size is, the more pages we want on the partial
 	 * list to avoid pounding the page allocator excessively.
 	 */
-	set_min_partial(s, ilog2(s->size));
+	set_min_partial(s, ilog2(s->size) / 2);
+
+	/*
+	 * cpu_partial determined the maximum number of objects kept in the
+	 * per cpu partial lists of a processor.
+	 *
+	 * Per cpu partial lists mainly contain slabs that just have one
+	 * object freed. If they are used for allocation then they can be
+	 * filled up again with minimal effort. The slab will never hit the
+	 * per node partial lists and therefore no locking will be required.
+	 *
+	 * This setting also determines
+	 *
+	 * A) The number of objects from per cpu partial slabs dumped to the
+	 *    per node list when we reach the limit.
+	 * B) The number of objects in cpu partial slabs to extract from the
+	 *    per node list when we run out of per cpu objects. We only fetch 50%
+	 *    to keep some capacity around for frees.
+	 */
+	if (s->size >= PAGE_SIZE)
+		s->cpu_partial = 2;
+	else if (s->size >= 1024)
+		s->cpu_partial = 6;
+	else if (s->size >= 256)
+		s->cpu_partial = 13;
+	else
+		s->cpu_partial = 30;
+
 	s->refcount = 1;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 1000;
@@ -2970,13 +3129,13 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 
 /*
  * Attempt to free all partial slabs on a node.
+ * This is called from kmem_cache_close(). We must be the last thread
+ * using the cache and therefore we do not need to lock anymore.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
-	unsigned long flags;
 	struct page *page, *h;
 
-	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
 			remove_partial(n, page);
@@ -2986,7 +3145,6 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 				"Objects remaining on kmem_cache_close()");
 		}
 	}
-	spin_unlock_irqrestore(&n->list_lock, flags);
 }
 
 /*
@@ -3020,6 +3178,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	s->refcount--;
 	if (!s->refcount) {
 		list_del(&s->list);
+		up_write(&slub_lock);
 		if (kmem_cache_close(s)) {
 			printk(KERN_ERR "SLUB %s: %s called for cache that "
 				"still has objects.\n", s->name, __func__);
@@ -3028,8 +3187,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 		if (s->flags & SLAB_DESTROY_BY_RCU)
 			rcu_barrier();
 		sysfs_slab_remove(s);
-	}
-	up_write(&slub_lock);
+	} else
+		up_write(&slub_lock);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -3347,23 +3506,23 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			if (!page->inuse) {
-				remove_partial(n, page);
-				discard_slab(s, page);
-			} else {
-				list_move(&page->lru,
-				slabs_by_inuse + page->inuse);
-			}
+			list_move(&page->lru, slabs_by_inuse + page->inuse);
+			if (!page->inuse)
+				n->nr_partial--;
 		}
 
 		/*
 		 * Rebuild the partial list with the slabs filled up most
 		 * first and the least used slabs at the end.
 		 */
-		for (i = objects - 1; i >= 0; i--)
+		for (i = objects - 1; i > 0; i--)
 			list_splice(slabs_by_inuse + i, n->partial.prev);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
+
+		/* Release empty slabs */
+		list_for_each_entry_safe(page, t, slabs_by_inuse, lru)
+			discard_slab(s, page);
 	}
 
 	kfree(slabs_by_inuse);
@@ -4319,6 +4478,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 		for_each_possible_cpu(cpu) {
 			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+			struct page *page;
 
 			if (!c || c->node < 0)
 				continue;
@@ -4334,6 +4494,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 				total += x;
 				nodes[c->node] += x;
 			}
+			page = c->partial;
+
+			if (page) {
+				x = page->pobjects;
+                                total += x;
+                                nodes[c->node] += x;
+			}
 			per_cpu[c->node]++;
 		}
 	}
@@ -4412,11 +4579,12 @@ struct slab_attribute {
 };
 
 #define SLAB_ATTR_RO(_name) \
-	static struct slab_attribute _name##_attr = __ATTR_RO(_name)
+	static struct slab_attribute _name##_attr = \
+	__ATTR(_name, 0400, _name##_show, NULL)
 
 #define SLAB_ATTR(_name) \
 	static struct slab_attribute _name##_attr =  \
-	__ATTR(_name, 0644, _name##_show, _name##_store)
+	__ATTR(_name, 0600, _name##_show, _name##_store)
 
 static ssize_t slab_size_show(struct kmem_cache *s, char *buf)
 {
@@ -4485,6 +4653,27 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
 }
 SLAB_ATTR(min_partial);
 
+static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%u\n", s->cpu_partial);
+}
+
+static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
+				 size_t length)
+{
+	unsigned long objects;
+	int err;
+
+	err = strict_strtoul(buf, 10, &objects);
+	if (err)
+		return err;
+
+	s->cpu_partial = objects;
+	flush_all(s);
+	return length;
+}
+SLAB_ATTR(cpu_partial);
+
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
 	if (!s->ctor)
@@ -4523,6 +4712,37 @@ static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(objects_partial);
 
+static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
+{
+	int objects = 0;
+	int pages = 0;
+	int cpu;
+	int len;
+
+	for_each_online_cpu(cpu) {
+		struct page *page = per_cpu_ptr(s->cpu_slab, cpu)->partial;
+
+		if (page) {
+			pages += page->pages;
+			objects += page->pobjects;
+		}
+	}
+
+	len = sprintf(buf, "%d(%d)", objects, pages);
+
+#ifdef CONFIG_SMP
+	for_each_online_cpu(cpu) {
+		struct page *page = per_cpu_ptr(s->cpu_slab, cpu) ->partial;
+
+		if (page && len < PAGE_SIZE - 20)
+			len += sprintf(buf + len, " C%d=%d(%d)", cpu,
+				page->pobjects, page->pages);
+	}
+#endif
+	return len + sprintf(buf + len, "\n");
+}
+SLAB_ATTR_RO(slabs_cpu_partial);
+
 static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
 {
 	return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
@@ -4845,6 +5065,8 @@ STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass);
 STAT_ATTR(ORDER_FALLBACK, order_fallback);
 STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
 STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
+STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
+STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -4853,6 +5075,7 @@ static struct attribute *slab_attrs[] = {
 	&objs_per_slab_attr.attr,
 	&order_attr.attr,
 	&min_partial_attr.attr,
+	&cpu_partial_attr.attr,
 	&objects_attr.attr,
 	&objects_partial_attr.attr,
 	&partial_attr.attr,
@@ -4865,6 +5088,7 @@ static struct attribute *slab_attrs[] = {
 	&destroy_by_rcu_attr.attr,
 	&shrink_attr.attr,
 	&reserved_attr.attr,
+	&slabs_cpu_partial_attr.attr,
 #ifdef CONFIG_SLUB_DEBUG
 	&total_objects_attr.attr,
 	&slabs_attr.attr,
@@ -4906,6 +5130,8 @@ static struct attribute *slab_attrs[] = {
 	&order_fallback_attr.attr,
 	&cmpxchg_double_fail_attr.attr,
 	&cmpxchg_double_cpu_fail_attr.attr,
+	&cpu_partial_alloc_attr.attr,
+	&cpu_partial_free_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,
@@ -5257,7 +5483,7 @@ static const struct file_operations proc_slabinfo_operations = {
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations);
+	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
 	return 0;
 }
 module_init(slab_proc_init);

tools/slub/slabinfo.c

@@ -42,6 +42,7 @@ struct slabinfo {
 	unsigned long deactivate_remote_frees, order_fallback;
 	unsigned long cmpxchg_double_cpu_fail, cmpxchg_double_fail;
 	unsigned long alloc_node_mismatch, deactivate_bypass;
+	unsigned long cpu_partial_alloc, cpu_partial_free;
 	int numa[MAX_NODES];
 	int numa_partial[MAX_NODES];
 } slabinfo[MAX_SLABS];
@@ -455,6 +456,11 @@ static void slab_stats(struct slabinfo *s)
 		s->alloc_from_partial * 100 / total_alloc,
 		s->free_remove_partial * 100 / total_free);
 
+	printf("Cpu partial list     %8lu %8lu %3lu %3lu\n",
+		s->cpu_partial_alloc, s->cpu_partial_free,
+		s->cpu_partial_alloc * 100 / total_alloc,
+		s->cpu_partial_free * 100 / total_free);
+
 	printf("RemoteObj/SlabFrozen %8lu %8lu %3lu %3lu\n",
 		s->deactivate_remote_frees, s->free_frozen,
 		s->deactivate_remote_frees * 100 / total_alloc,
@@ -1145,7 +1151,7 @@ static void read_slab_dir(void)
 		switch (de->d_type) {
 		   case DT_LNK:
 			alias->name = strdup(de->d_name);
-			count = readlink(de->d_name, buffer, sizeof(buffer));
+			count = readlink(de->d_name, buffer, sizeof(buffer)-1);
 
 			if (count < 0)
 				fatal("Cannot read symlink %s\n", de->d_name);
@@ -1209,6 +1215,8 @@ static void read_slab_dir(void)
 			slab->order_fallback = get_obj("order_fallback");
 			slab->cmpxchg_double_cpu_fail = get_obj("cmpxchg_double_cpu_fail");
 			slab->cmpxchg_double_fail = get_obj("cmpxchg_double_fail");
+			slab->cpu_partial_alloc = get_obj("cpu_partial_alloc");
+			slab->cpu_partial_free = get_obj("cpu_partial_free");
 			slab->alloc_node_mismatch = get_obj("alloc_node_mismatch");
 			slab->deactivate_bypass = get_obj("deactivate_bypass");
 			chdir("..");