Merge branch 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux

Pull SLAB changes from Pekka Enberg:
 "There's the new kmalloc_array() API, minor fixes and performance
  improvements, but quite honestly, nothing terribly exciting."

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux:
  mm: SLAB Out-of-memory diagnostics
  slab: introduce kmalloc_array()
  slub: per cpu partial statistics change
  slub: include include for prefetch
  slub: Do not hold slub_lock when calling sysfs_slab_add()
  slub: prefetch next freelist pointer in slab_alloc()
  slab, cleanup: remove unneeded return

mm/slub.c

@@ -29,6 +29,7 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
+#include <linux/prefetch.h>
 
 #include <trace/events/kmem.h>
 
@@ -269,6 +270,11 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
 	return *(void **)(object + s->offset);
 }
 
+static void prefetch_freepointer(const struct kmem_cache *s, void *object)
+{
+	prefetch(object + s->offset);
+}
+
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
 	void *p;
@@ -1560,6 +1566,7 @@ static void *get_partial_node(struct kmem_cache *s,
 		} else {
 			page->freelist = t;
 			available = put_cpu_partial(s, page, 0);
+			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
 			break;
@@ -1983,6 +1990,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 				local_irq_restore(flags);
 				pobjects = 0;
 				pages = 0;
+				stat(s, CPU_PARTIAL_DRAIN);
 			}
 		}
 
@@ -1994,7 +2002,6 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
 
@@ -2319,6 +2326,8 @@ redo:
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
+		void *next_object = get_freepointer_safe(s, object);
+
 		/*
 		 * The cmpxchg will only match if there was no additional
 		 * operation and if we are on the right processor.
@@ -2334,11 +2343,12 @@ redo:
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
 				object, tid,
-				get_freepointer_safe(s, object), next_tid(tid)))) {
+				next_object, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_alloc", s, tid);
 			goto redo;
 		}
+		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
 
@@ -2475,9 +2485,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 * If we just froze the page then put it onto the
 		 * per cpu partial list.
 		 */
-		if (new.frozen && !was_frozen)
+		if (new.frozen && !was_frozen) {
 			put_cpu_partial(s, page, 1);
-
+			stat(s, CPU_PARTIAL_FREE);
+		}
 		/*
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
@@ -3939,13 +3950,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
+			up_write(&slub_lock);
 			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
 				list_del(&s->list);
 				kfree(n);
 				kfree(s);
 				goto err;
 			}
-			up_write(&slub_lock);
 			return s;
 		}
 		kfree(n);
@@ -5069,6 +5081,8 @@ 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);
+STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
+STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -5134,6 +5148,8 @@ static struct attribute *slab_attrs[] = {
 	&cmpxchg_double_cpu_fail_attr.attr,
 	&cpu_partial_alloc_attr.attr,
 	&cpu_partial_free_attr.attr,
+	&cpu_partial_node_attr.attr,
+	&cpu_partial_drain_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,