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

Pull SLAB changes from Pekka Enberg:
 "New and noteworthy:

  * More SLAB allocator unification patches from Christoph Lameter and
    others.  This paves the way for slab memcg patches that hopefully
    will land in v3.8.

  * SLAB tracing improvements from Ezequiel Garcia.

  * Kernel tainting upon SLAB corruption from Dave Jones.

  * Miscellanous SLAB allocator bug fixes and improvements from various
    people."

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux: (43 commits)
  slab: Fix build failure in __kmem_cache_create()
  slub: init_kmem_cache_cpus() and put_cpu_partial() can be static
  mm/slab: Fix kmem_cache_alloc_node_trace() declaration
  Revert "mm/slab: Fix kmem_cache_alloc_node_trace() declaration"
  mm, slob: fix build breakage in __kmalloc_node_track_caller
  mm/slab: Fix kmem_cache_alloc_node_trace() declaration
  mm/slab: Fix typo _RET_IP -> _RET_IP_
  mm, slub: Rename slab_alloc() -> slab_alloc_node() to match SLAB
  mm, slab: Rename __cache_alloc() -> slab_alloc()
  mm, slab: Match SLAB and SLUB kmem_cache_alloc_xxx_trace() prototype
  mm, slab: Replace 'caller' type, void* -> unsigned long
  mm, slob: Add support for kmalloc_track_caller()
  mm, slab: Remove silly function slab_buffer_size()
  mm, slob: Use NUMA_NO_NODE instead of -1
  mm, sl[au]b: Taint kernel when we detect a corrupted slab
  slab: Only define slab_error for DEBUG
  slab: fix the DEADLOCK issue on l3 alien lock
  slub: Zero initial memory segment for kmem_cache and kmem_cache_node
  Revert "mm/sl[aou]b: Move sysfs_slab_add to common"
  mm/sl[aou]b: Move kmem_cache refcounting to common code
  ...

include/linux/slab.h

@@ -321,7 +321,8 @@ static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
  * request comes from.
  */
 #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING))
+	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
+	(defined(CONFIG_SLOB) && 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_)
@@ -340,7 +341,8 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
  * allocation request comes from.
  */
 #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING))
+	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
+	(defined(CONFIG_SLOB) && 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, \

include/linux/slab_def.h

@@ -45,7 +45,6 @@ struct kmem_cache {
 	unsigned int colour_off;	/* colour offset */
 	struct kmem_cache *slabp_cache;
 	unsigned int slab_size;
-	unsigned int dflags;		/* dynamic flags */
 
 	/* constructor func */
 	void (*ctor)(void *obj);
@@ -112,19 +111,13 @@ void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
 #ifdef CONFIG_TRACING
-extern void *kmem_cache_alloc_trace(size_t size,
-				    struct kmem_cache *cachep, gfp_t flags);
-extern size_t slab_buffer_size(struct kmem_cache *cachep);
+extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t);
 #else
 static __always_inline void *
-kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags)
+kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
 {
 	return kmem_cache_alloc(cachep, flags);
 }
-static inline size_t slab_buffer_size(struct kmem_cache *cachep)
-{
-	return 0;
-}
 #endif
 
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
@@ -154,7 +147,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 #endif
 			cachep = malloc_sizes[i].cs_cachep;
 
-		ret = kmem_cache_alloc_trace(size, cachep, flags);
+		ret = kmem_cache_alloc_trace(cachep, flags, size);
 
 		return ret;
 	}
@@ -166,16 +159,16 @@ extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
 extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
 #ifdef CONFIG_TRACING
-extern void *kmem_cache_alloc_node_trace(size_t size,
-					 struct kmem_cache *cachep,
+extern void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
 					 gfp_t flags,
-					 int nodeid);
+					 int nodeid,
+					 size_t size);
 #else
 static __always_inline void *
-kmem_cache_alloc_node_trace(size_t size,
-			    struct kmem_cache *cachep,
+kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
 			    gfp_t flags,
-			    int nodeid)
+			    int nodeid,
+			    size_t size)
 {
 	return kmem_cache_alloc_node(cachep, flags, nodeid);
 }
@@ -207,7 +200,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 #endif
 			cachep = malloc_sizes[i].cs_cachep;
 
-		return kmem_cache_alloc_node_trace(size, cachep, flags, node);
+		return kmem_cache_alloc_node_trace(cachep, flags, node, size);
 	}
 	return __kmalloc_node(size, flags, node);
 }

include/linux/slob_def.h

 #ifndef __LINUX_SLOB_DEF_H
 #define __LINUX_SLOB_DEF_H
 
+#include <linux/numa.h>
+
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
 static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep,
 					      gfp_t flags)
 {
-	return kmem_cache_alloc_node(cachep, flags, -1);
+	return kmem_cache_alloc_node(cachep, flags, NUMA_NO_NODE);
 }
 
 void *__kmalloc_node(size_t size, gfp_t flags, int node);
@@ -26,7 +28,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
  */
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
-	return __kmalloc_node(size, flags, -1);
+	return __kmalloc_node(size, flags, NUMA_NO_NODE);
 }
 
 static __always_inline void *__kmalloc(size_t size, gfp_t flags)

mm/slab.h

@@ -25,9 +25,26 @@ extern enum slab_state slab_state;
 
 /* The slab cache mutex protects the management structures during changes */
 extern struct mutex slab_mutex;
+
+/* The list of all slab caches on the system */
 extern struct list_head slab_caches;
 
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
+/* The slab cache that manages slab cache information */
+extern struct kmem_cache *kmem_cache;
+
+/* Functions provided by the slab allocators */
+extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
+
+#ifdef CONFIG_SLUB
+struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
 	size_t align, unsigned long flags, void (*ctor)(void *));
+#else
+static inline struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
+	size_t align, unsigned long flags, void (*ctor)(void *))
+{ return NULL; }
+#endif
+
+
+int __kmem_cache_shutdown(struct kmem_cache *);
 
 #endif

mm/slab_common.c

@@ -22,6 +22,53 @@
 enum slab_state slab_state;
 LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
+struct kmem_cache *kmem_cache;
+
+#ifdef CONFIG_DEBUG_VM
+static int kmem_cache_sanity_check(const char *name, size_t size)
+{
+	struct kmem_cache *s = NULL;
+
+	if (!name || in_interrupt() || size < sizeof(void *) ||
+		size > KMALLOC_MAX_SIZE) {
+		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
+		return -EINVAL;
+	}
+
+	list_for_each_entry(s, &slab_caches, list) {
+		char tmp;
+		int res;
+
+		/*
+		 * This happens when the module gets unloaded and doesn't
+		 * destroy its slab cache and no-one else reuses the vmalloc
+		 * area of the module.  Print a warning.
+		 */
+		res = probe_kernel_address(s->name, tmp);
+		if (res) {
+			pr_err("Slab cache with size %d has lost its name\n",
+			       s->object_size);
+			continue;
+		}
+
+		if (!strcmp(s->name, name)) {
+			pr_err("%s (%s): Cache name already exists.\n",
+			       __func__, name);
+			dump_stack();
+			s = NULL;
+			return -EINVAL;
+		}
+	}
+
+	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
+	return 0;
+}
+#else
+static inline int kmem_cache_sanity_check(const char *name, size_t size)
+{
+	return 0;
+}
+#endif
 
 /*
  * kmem_cache_create - Create a cache.
@@ -52,68 +99,92 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 		unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s = NULL;
-
-#ifdef CONFIG_DEBUG_VM
-	if (!name || in_interrupt() || size < sizeof(void *) ||
-		size > KMALLOC_MAX_SIZE) {
-		printk(KERN_ERR "kmem_cache_create(%s) integrity check"
-			" failed\n", name);
-		goto out;
-	}
-#endif
+	int err = 0;
 
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 
-#ifdef CONFIG_DEBUG_VM
-	list_for_each_entry(s, &slab_caches, list) {
-		char tmp;
-		int res;
+	if (!kmem_cache_sanity_check(name, size) == 0)
+		goto out_locked;
 
-		/*
-		 * This happens when the module gets unloaded and doesn't
-		 * destroy its slab cache and no-one else reuses the vmalloc
-		 * area of the module.  Print a warning.
-		 */
-		res = probe_kernel_address(s->name, tmp);
-		if (res) {
-			printk(KERN_ERR
-			       "Slab cache with size %d has lost its name\n",
-			       s->object_size);
-			continue;
-		}
 
-		if (!strcmp(s->name, name)) {
-			printk(KERN_ERR "kmem_cache_create(%s): Cache name"
-				" already exists.\n",
-				name);
-			dump_stack();
-			s = NULL;
-			goto oops;
+	s = __kmem_cache_alias(name, size, align, flags, ctor);
+	if (s)
+		goto out_locked;
+
+	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
+	if (s) {
+		s->object_size = s->size = size;
+		s->align = align;
+		s->ctor = ctor;
+		s->name = kstrdup(name, GFP_KERNEL);
+		if (!s->name) {
+			kmem_cache_free(kmem_cache, s);
+			err = -ENOMEM;
+			goto out_locked;
 		}
-	}
 
-	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
-#endif
+		err = __kmem_cache_create(s, flags);
+		if (!err) {
 
-	s = __kmem_cache_create(name, size, align, flags, ctor);
+			s->refcount = 1;
+			list_add(&s->list, &slab_caches);
 
-#ifdef CONFIG_DEBUG_VM
-oops:
-#endif
+		} else {
+			kfree(s->name);
+			kmem_cache_free(kmem_cache, s);
+		}
+	} else
+		err = -ENOMEM;
+
+out_locked:
 	mutex_unlock(&slab_mutex);
 	put_online_cpus();
 
-#ifdef CONFIG_DEBUG_VM
-out:
-#endif
-	if (!s && (flags & SLAB_PANIC))
-		panic("kmem_cache_create: Failed to create slab '%s'\n", name);
+	if (err) {
+
+		if (flags & SLAB_PANIC)
+			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
+				name, err);
+		else {
+			printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
+				name, err);
+			dump_stack();
+		}
+
+		return NULL;
+	}
 
 	return s;
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
+void kmem_cache_destroy(struct kmem_cache *s)
+{
+	get_online_cpus();
+	mutex_lock(&slab_mutex);
+	s->refcount--;
+	if (!s->refcount) {
+		list_del(&s->list);
+
+		if (!__kmem_cache_shutdown(s)) {
+			if (s->flags & SLAB_DESTROY_BY_RCU)
+				rcu_barrier();
+
+			kfree(s->name);
+			kmem_cache_free(kmem_cache, s);
+		} else {
+			list_add(&s->list, &slab_caches);
+			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
+				s->name);
+			dump_stack();
+		}
+	}
+	mutex_unlock(&slab_mutex);
+	put_online_cpus();
+}
+EXPORT_SYMBOL(kmem_cache_destroy);
+
 int slab_is_available(void)
 {
 	return slab_state >= UP;

mm/slob.c

@@ -194,7 +194,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 	void *page;
 
 #ifdef CONFIG_NUMA
-	if (node != -1)
+	if (node != NUMA_NO_NODE)
 		page = alloc_pages_exact_node(node, gfp, order);
 	else
 #endif
@@ -290,7 +290,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		 * If there's a node specification, search for a partial
 		 * page with a matching node id in the freelist.
 		 */
-		if (node != -1 && page_to_nid(sp) != node)
+		if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
 			continue;
 #endif
 		/* Enough room on this page? */
@@ -425,7 +425,8 @@ static void slob_free(void *block, int size)
  * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
  */
 
-void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+static __always_inline void *
+__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
 	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
@@ -446,7 +447,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 		*m = size;
 		ret = (void *)m + align;
 
-		trace_kmalloc_node(_RET_IP_, ret,
+		trace_kmalloc_node(caller, ret,
 				   size, size + align, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
@@ -460,15 +461,35 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 			page->private = size;
 		}
 
-		trace_kmalloc_node(_RET_IP_, ret,
+		trace_kmalloc_node(caller, ret,
 				   size, PAGE_SIZE << order, gfp, node);
 	}
 
 	kmemleak_alloc(ret, size, 1, gfp);
 	return ret;
 }
+
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+{
+	return __do_kmalloc_node(size, gfp, node, _RET_IP_);
+}
 EXPORT_SYMBOL(__kmalloc_node);
 
+#ifdef CONFIG_TRACING
+void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
+{
+	return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
+}
+
+#ifdef CONFIG_NUMA
+void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
+					int node, unsigned long caller)
+{
+	return __do_kmalloc_node(size, gfp, node, caller);
+}
+#endif
+#endif
+
 void kfree(const void *block)
 {
 	struct page *sp;
@@ -508,44 +529,24 @@ size_t ksize(const void *block)
 }
 EXPORT_SYMBOL(ksize);
 
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
-	size_t align, unsigned long flags, void (*ctor)(void *))
+int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
 {
-	struct kmem_cache *c;
-
-	c = slob_alloc(sizeof(struct kmem_cache),
-		GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);
+	size_t align = c->size;
 
-	if (c) {
-		c->name = name;
-		c->size = size;
-		if (flags & SLAB_DESTROY_BY_RCU) {
-			/* leave room for rcu footer at the end of object */
-			c->size += sizeof(struct slob_rcu);
-		}
-		c->flags = flags;
-		c->ctor = ctor;
-		/* ignore alignment unless it's forced */
-		c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
-		if (c->align < ARCH_SLAB_MINALIGN)
-			c->align = ARCH_SLAB_MINALIGN;
-		if (c->align < align)
-			c->align = align;
-
-		kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
-		c->refcount = 1;
+	if (flags & SLAB_DESTROY_BY_RCU) {
+		/* leave room for rcu footer at the end of object */
+		c->size += sizeof(struct slob_rcu);
 	}
-	return c;
-}
+	c->flags = flags;
+	/* ignore alignment unless it's forced */
+	c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
+	if (c->align < ARCH_SLAB_MINALIGN)
+		c->align = ARCH_SLAB_MINALIGN;
+	if (c->align < align)
+		c->align = align;
 
-void kmem_cache_destroy(struct kmem_cache *c)
-{
-	kmemleak_free(c);
-	if (c->flags & SLAB_DESTROY_BY_RCU)
-		rcu_barrier();
-	slob_free(c, sizeof(struct kmem_cache));
+	return 0;
 }
-EXPORT_SYMBOL(kmem_cache_destroy);
 
 void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 {
@@ -613,14 +614,28 @@ unsigned int kmem_cache_size(struct kmem_cache *c)
 }
 EXPORT_SYMBOL(kmem_cache_size);
 
+int __kmem_cache_shutdown(struct kmem_cache *c)
+{
+	/* No way to check for remaining objects */
+	return 0;
+}
+
 int kmem_cache_shrink(struct kmem_cache *d)
 {
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
+struct kmem_cache kmem_cache_boot = {
+	.name = "kmem_cache",
+	.size = sizeof(struct kmem_cache),
+	.flags = SLAB_PANIC,
+	.align = ARCH_KMALLOC_MINALIGN,
+};
+
 void __init kmem_cache_init(void)
 {
+	kmem_cache = &kmem_cache_boot;
 	slab_state = UP;
 }
 

mm/util.c

@@ -105,6 +105,25 @@ void *memdup_user(const void __user *src, size_t len)
 }
 EXPORT_SYMBOL(memdup_user);
 
+static __always_inline void *__do_krealloc(const void *p, size_t new_size,
+					   gfp_t flags)
+{
+	void *ret;
+	size_t ks = 0;
+
+	if (p)
+		ks = ksize(p);
+
+	if (ks >= new_size)
+		return (void *)p;
+
+	ret = kmalloc_track_caller(new_size, flags);
+	if (ret && p)
+		memcpy(ret, p, ks);
+
+	return ret;
+}
+
 /**
  * __krealloc - like krealloc() but don't free @p.
  * @p: object to reallocate memory for.
@@ -117,23 +136,11 @@ EXPORT_SYMBOL(memdup_user);
  */
 void *__krealloc(const void *p, size_t new_size, gfp_t flags)
 {
-	void *ret;
-	size_t ks = 0;
-
 	if (unlikely(!new_size))
 		return ZERO_SIZE_PTR;
 
-	if (p)
-		ks = ksize(p);
+	return __do_krealloc(p, new_size, flags);
 
-	if (ks >= new_size)
-		return (void *)p;
-
-	ret = kmalloc_track_caller(new_size, flags);
-	if (ret && p)
-		memcpy(ret, p, ks);
-
-	return ret;
 }
 EXPORT_SYMBOL(__krealloc);
 
@@ -157,7 +164,7 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags)
 		return ZERO_SIZE_PTR;
 	}
 
-	ret = __krealloc(p, new_size, flags);
+	ret = __do_krealloc(p, new_size, flags);
 	if (ret && p != ret)
 		kfree(p);