Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
  slub: Allow removal of slab caches during boot
  Revert "slub: Allow removal of slab caches during boot"
  slub numa: Fix rare allocation from unexpected node
  slab: use deferable timers for its periodic housekeeping
  slub: Use kmem_cache flags to detect if slab is in debugging mode.
  slub: Allow removal of slab caches during boot
  slub: Check kasprintf results in kmem_cache_init()
  SLUB: Constants need UL
  slub: Use a constant for a unspecified node.
  SLOB: Free objects to their own list
  slab: fix caller tracking on !CONFIG_DEBUG_SLAB && CONFIG_TRACING

include/linux/page-flags.h

@@ -128,7 +128,6 @@ enum pageflags {
 
 	/* SLUB */
 	PG_slub_frozen = PG_active,
-	PG_slub_debug = PG_error,
 };
 
 #ifndef __GENERATING_BOUNDS_H
@@ -215,7 +214,6 @@ PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 __PAGEFLAG(SlobFree, slob_free)
 
 __PAGEFLAG(SlubFrozen, slub_frozen)
-__PAGEFLAG(SlubDebug, slub_debug)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page

include/linux/slab.h

@@ -268,7 +268,8 @@ static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
  * allocator where we care about the real place the memory allocation
  * request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB)
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
+	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
 #define kmalloc_track_caller(size, flags) \
 	__kmalloc_track_caller(size, flags, _RET_IP_)
@@ -286,7 +287,8 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
  * standard allocator where we care about the real place the memory
  * allocation request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB)
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
+	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
 #define kmalloc_node_track_caller(size, flags, node) \
 	__kmalloc_node_track_caller(size, flags, node, \

mm/slab.c

@@ -860,7 +860,7 @@ static void __cpuinit start_cpu_timer(int cpu)
 	 */
 	if (keventd_up() && reap_work->work.func == NULL) {
 		init_reap_node(cpu);
-		INIT_DELAYED_WORK(reap_work, cache_reap);
+		INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap);
 		schedule_delayed_work_on(cpu, reap_work,
 					__round_jiffies_relative(HZ, cpu));
 	}

mm/slob.c

@@ -396,6 +396,7 @@ static void slob_free(void *block, int size)
 	slob_t *prev, *next, *b = (slob_t *)block;
 	slobidx_t units;
 	unsigned long flags;
+	struct list_head *slob_list;
 
 	if (unlikely(ZERO_OR_NULL_PTR(block)))
 		return;
@@ -424,7 +425,13 @@ static void slob_free(void *block, int size)
 		set_slob(b, units,
 			(void *)((unsigned long)(b +
 					SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
-		set_slob_page_free(sp, &free_slob_small);
+		if (size < SLOB_BREAK1)
+			slob_list = &free_slob_small;
+		else if (size < SLOB_BREAK2)
+			slob_list = &free_slob_medium;
+		else
+			slob_list = &free_slob_large;
+		set_slob_page_free(sp, slob_list);
 		goto out;
 	}
 

mm/slub.c

@@ -106,11 +106,17 @@
  * 			the fast path and disables lockless freelists.
  */
 
+#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
+		SLAB_TRACE | SLAB_DEBUG_FREE)
+
+static inline int kmem_cache_debug(struct kmem_cache *s)
+{
 #ifdef CONFIG_SLUB_DEBUG
-#define SLABDEBUG 1
+	return unlikely(s->flags & SLAB_DEBUG_FLAGS);
 #else
-#define SLABDEBUG 0
+	return 0;
 #endif
+}
 
 /*
  * Issues still to be resolved:
@@ -161,8 +167,8 @@
 #define MAX_OBJS_PER_PAGE	65535 /* since page.objects is u16 */
 
 /* Internal SLUB flags */
-#define __OBJECT_POISON		0x80000000 /* Poison object */
-#define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
+#define __OBJECT_POISON		0x80000000UL /* Poison object */
+#define __SYSFS_ADD_DEFERRED	0x40000000UL /* Not yet visible via sysfs */
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -1072,7 +1078,7 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node,
 
 	flags |= __GFP_NOTRACK;
 
-	if (node == -1)
+	if (node == NUMA_NO_NODE)
 		return alloc_pages(flags, order);
 	else
 		return alloc_pages_exact_node(node, flags, order);
@@ -1156,9 +1162,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
-	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
-			SLAB_STORE_USER | SLAB_TRACE))
-		__SetPageSlubDebug(page);
 
 	start = page_address(page);
 
@@ -1185,14 +1188,13 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 	int order = compound_order(page);
 	int pages = 1 << order;
 
-	if (unlikely(SLABDEBUG && PageSlubDebug(page))) {
+	if (kmem_cache_debug(s)) {
 		void *p;
 
 		slab_pad_check(s, page);
 		for_each_object(p, s, page_address(page),
 						page->objects)
 			check_object(s, page, p, 0);
-		__ClearPageSlubDebug(page);
 	}
 
 	kmemcheck_free_shadow(page, compound_order(page));
@@ -1386,10 +1388,10 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
-	int searchnode = (node == -1) ? numa_node_id() : node;
+	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
 	page = get_partial_node(get_node(s, searchnode));
-	if (page || (flags & __GFP_THISNODE))
+	if (page || node != -1)
 		return page;
 
 	return get_any_partial(s, flags);
@@ -1414,8 +1416,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
 		} else {
 			stat(s, DEACTIVATE_FULL);
-			if (SLABDEBUG && PageSlubDebug(page) &&
-						(s->flags & SLAB_STORE_USER))
+			if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER))
 				add_full(n, page);
 		}
 		slab_unlock(page);
@@ -1514,7 +1515,7 @@ static void flush_all(struct kmem_cache *s)
 static inline int node_match(struct kmem_cache_cpu *c, int node)
 {
 #ifdef CONFIG_NUMA
-	if (node != -1 && c->node != node)
+	if (node != NUMA_NO_NODE && c->node != node)
 		return 0;
 #endif
 	return 1;
@@ -1623,7 +1624,7 @@ load_freelist:
 	object = c->page->freelist;
 	if (unlikely(!object))
 		goto another_slab;
-	if (unlikely(SLABDEBUG && PageSlubDebug(c->page)))
+	if (kmem_cache_debug(s))
 		goto debug;
 
 	c->freelist = get_freepointer(s, object);
@@ -1726,7 +1727,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-	void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
 
 	trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags);
 
@@ -1737,7 +1738,7 @@ EXPORT_SYMBOL(kmem_cache_alloc);
 #ifdef CONFIG_TRACING
 void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
 {
-	return slab_alloc(s, gfpflags, -1, _RET_IP_);
+	return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_alloc_notrace);
 #endif
@@ -1782,7 +1783,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 	stat(s, FREE_SLOWPATH);
 	slab_lock(page);
 
-	if (unlikely(SLABDEBUG && PageSlubDebug(page)))
+	if (kmem_cache_debug(s))
 		goto debug;
 
 checks_ok:
@@ -2489,7 +2490,6 @@ 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__);
@@ -2498,8 +2498,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 		if (s->flags & SLAB_DESTROY_BY_RCU)
 			rcu_barrier();
 		sysfs_slab_remove(s);
-	} else
-		up_write(&slub_lock);
+	}
+	up_write(&slub_lock);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -2727,7 +2727,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, flags, -1, _RET_IP_);
+	ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_);
 
 	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
 
@@ -3117,9 +3117,12 @@ void __init kmem_cache_init(void)
 	slab_state = UP;
 
 	/* Provide the correct kmalloc names now that the caches are up */
-	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++)
-		kmalloc_caches[i]. name =
-			kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
+	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
+		char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
+
+		BUG_ON(!s);
+		kmalloc_caches[i].name = s;
+	}
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
@@ -3222,14 +3225,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		 */
 		s->objsize = max(s->objsize, (int)size);
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
-		up_write(&slub_lock);
 
 		if (sysfs_slab_alias(s, name)) {
-			down_write(&slub_lock);
 			s->refcount--;
-			up_write(&slub_lock);
 			goto err;
 		}
+		up_write(&slub_lock);
 		return s;
 	}
 
@@ -3238,14 +3239,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		if (kmem_cache_open(s, GFP_KERNEL, name,
 				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);
-				up_write(&slub_lock);
 				kfree(s);
 				goto err;
 			}
+			up_write(&slub_lock);
 			return s;
 		}
 		kfree(s);
@@ -3311,7 +3310,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, gfpflags, -1, caller);
+	ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, caller);
 
 	/* Honor the call site pointer we recieved. */
 	trace_kmalloc(caller, ret, size, s->size, gfpflags);
@@ -3394,16 +3393,6 @@ static void validate_slab_slab(struct kmem_cache *s, struct page *page,
 	} else
 		printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n",
 			s->name, page);
-
-	if (s->flags & DEBUG_DEFAULT_FLAGS) {
-		if (!PageSlubDebug(page))
-			printk(KERN_ERR "SLUB %s: SlubDebug not set "
-				"on slab 0x%p\n", s->name, page);
-	} else {
-		if (PageSlubDebug(page))
-			printk(KERN_ERR "SLUB %s: SlubDebug set on "
-				"slab 0x%p\n", s->name, page);
-	}
 }
 
 static int validate_slab_node(struct kmem_cache *s,
@@ -4503,6 +4492,13 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 static void sysfs_slab_remove(struct kmem_cache *s)
 {
+	if (slab_state < SYSFS)
+		/*
+		 * Sysfs has not been setup yet so no need to remove the
+		 * cache from sysfs.
+		 */
+		return;
+
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
 	kobject_del(&s->kobj);
 	kobject_put(&s->kobj);
@@ -4548,8 +4544,11 @@ static int __init slab_sysfs_init(void)
 	struct kmem_cache *s;
 	int err;
 
+	down_write(&slub_lock);
+
 	slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj);
 	if (!slab_kset) {
+		up_write(&slub_lock);
 		printk(KERN_ERR "Cannot register slab subsystem.\n");
 		return -ENOSYS;
 	}
@@ -4574,6 +4573,7 @@ static int __init slab_sysfs_init(void)
 		kfree(al);
 	}
 
+	up_write(&slub_lock);
 	resiliency_test();
 	return 0;
 }