Merge branch 'slab/next' into slab/for-linus

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;
 	}

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_common.c

@@ -23,49 +23,17 @@ enum slab_state slab_state;
 LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 
-/*
- * kmem_cache_create - Create a cache.
- * @name: A string which is used in /proc/slabinfo to identify this cache.
- * @size: The size of objects to be created in this cache.
- * @align: The required alignment for the objects.
- * @flags: SLAB flags
- * @ctor: A constructor for the objects.
- *
- * Returns a ptr to the cache on success, NULL on failure.
- * Cannot be called within a interrupt, but can be interrupted.
- * The @ctor is run when new pages are allocated by the cache.
- *
- * The flags are
- *
- * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
- * to catch references to uninitialised memory.
- *
- * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
- * for buffer overruns.
- *
- * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
- * cacheline.  This can be beneficial if you're counting cycles as closely
- * as davem.
- */
-
-struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align,
-		unsigned long flags, void (*ctor)(void *))
+#ifdef CONFIG_DEBUG_VM
+static int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	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;
+		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
+		return -EINVAL;
 	}
-#endif
 
-	get_online_cpus();
-	mutex_lock(&slab_mutex);
-
-#ifdef CONFIG_DEBUG_VM
 	list_for_each_entry(s, &slab_caches, list) {
 		char tmp;
 		int res;
@@ -77,36 +45,67 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 		 */
 		res = probe_kernel_address(s->name, tmp);
 		if (res) {
-			printk(KERN_ERR
-			       "Slab cache with size %d has lost its name\n",
+			pr_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);
+			pr_err("%s (%s): Cache name already exists.\n",
+			       __func__, name);
 			dump_stack();
 			s = NULL;
-			goto oops;
+			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
 
-	s = __kmem_cache_create(name, size, align, flags, ctor);
+/*
+ * kmem_cache_create - Create a cache.
+ * @name: A string which is used in /proc/slabinfo to identify this cache.
+ * @size: The size of objects to be created in this cache.
+ * @align: The required alignment for the objects.
+ * @flags: SLAB flags
+ * @ctor: A constructor for the objects.
+ *
+ * Returns a ptr to the cache on success, NULL on failure.
+ * Cannot be called within a interrupt, but can be interrupted.
+ * The @ctor is run when new pages are allocated by the cache.
+ *
+ * The flags are
+ *
+ * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
+ * to catch references to uninitialised memory.
+ *
+ * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
+ * for buffer overruns.
+ *
+ * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
+ * cacheline.  This can be beneficial if you're counting cycles as closely
+ * as davem.
+ */
+
+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
-oops:
-#endif
+	get_online_cpus();
+	mutex_lock(&slab_mutex);
+	if (kmem_cache_sanity_check(name, size) == 0)
+		s = __kmem_cache_create(name, size, align, flags, ctor);
 	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);
 

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 gfpflags,
+					int node, unsigned long caller)
+{
+	return __do_kmalloc_node(size, gfp, node, caller);
+}
+#endif
+#endif
+
 void kfree(const void *block)
 {
 	struct page *sp;
@@ -514,7 +535,7 @@ struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
 	struct kmem_cache *c;
 
 	c = slob_alloc(sizeof(struct kmem_cache),
-		GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);
+		GFP_KERNEL, ARCH_KMALLOC_MINALIGN, NUMA_NO_NODE);
 
 	if (c) {
 		c->name = name;

mm/slub.c

@@ -568,6 +568,8 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
 	printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf);
 	printk(KERN_ERR "----------------------------------------"
 			"-------------------------------------\n\n");
+
+	add_taint(TAINT_BAD_PAGE);
 }
 
 static void slab_fix(struct kmem_cache *s, char *fmt, ...)
@@ -1069,13 +1071,13 @@ static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *pa
 	return 0;
 }
 
-static noinline int free_debug_processing(struct kmem_cache *s,
-		 struct page *page, void *object, unsigned long addr)
+static noinline struct kmem_cache_node *free_debug_processing(
+	struct kmem_cache *s, struct page *page, void *object,
+	unsigned long addr, unsigned long *flags)
 {
-	unsigned long flags;
-	int rc = 0;
+	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&n->list_lock, *flags);
 	slab_lock(page);
 
 	if (!check_slab(s, page))
@@ -1113,15 +1115,19 @@ static noinline int free_debug_processing(struct kmem_cache *s,
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
 	init_object(s, object, SLUB_RED_INACTIVE);
-	rc = 1;
 out:
 	slab_unlock(page);
-	local_irq_restore(flags);
-	return rc;
+	/*
+	 * Keep node_lock to preserve integrity
+	 * until the object is actually freed
+	 */
+	return n;
 
 fail:
+	slab_unlock(page);
+	spin_unlock_irqrestore(&n->list_lock, *flags);
 	slab_fix(s, "Object at 0x%p not freed", object);
-	goto out;
+	return NULL;
 }
 
 static int __init setup_slub_debug(char *str)
@@ -1214,8 +1220,9 @@ static inline void setup_object_debug(struct kmem_cache *s,
 static inline int alloc_debug_processing(struct kmem_cache *s,
 	struct page *page, void *object, unsigned long addr) { return 0; }
 
-static inline int free_debug_processing(struct kmem_cache *s,
-	struct page *page, void *object, unsigned long addr) { return 0; }
+static inline struct kmem_cache_node *free_debug_processing(
+	struct kmem_cache *s, struct page *page, void *object,
+	unsigned long addr, unsigned long *flags) { return NULL; }
 
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 			{ return 1; }
@@ -1714,7 +1721,7 @@ static inline void note_cmpxchg_failure(const char *n,
 	stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
 }
 
-void init_kmem_cache_cpus(struct kmem_cache *s)
+static void init_kmem_cache_cpus(struct kmem_cache *s)
 {
 	int cpu;
 
@@ -1939,7 +1946,7 @@ static void unfreeze_partials(struct kmem_cache *s)
  * 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)
+static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 {
 	struct page *oldpage;
 	int pages;
@@ -1962,6 +1969,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 				local_irq_save(flags);
 				unfreeze_partials(s);
 				local_irq_restore(flags);
+				oldpage = NULL;
 				pobjects = 0;
 				pages = 0;
 				stat(s, CPU_PARTIAL_DRAIN);
@@ -2310,7 +2318,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
  *
  * Otherwise we can simply pick the next object from the lockless free list.
  */
-static __always_inline void *slab_alloc(struct kmem_cache *s,
+static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 		gfp_t gfpflags, int node, unsigned long addr)
 {
 	void **object;
@@ -2380,9 +2388,15 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	return object;
 }
 
+static __always_inline void *slab_alloc(struct kmem_cache *s,
+		gfp_t gfpflags, unsigned long addr)
+{
+	return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr);
+}
+
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-	void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, _RET_IP_);
 
 	trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags);
 
@@ -2393,7 +2407,7 @@ EXPORT_SYMBOL(kmem_cache_alloc);
 #ifdef CONFIG_TRACING
 void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
-	void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, _RET_IP_);
 	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
 	return ret;
 }
@@ -2411,7 +2425,7 @@ EXPORT_SYMBOL(kmalloc_order_trace);
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-	void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
 
 	trace_kmem_cache_alloc_node(_RET_IP_, ret,
 				    s->object_size, s->size, gfpflags, node);
@@ -2425,7 +2439,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 				    gfp_t gfpflags,
 				    int node, size_t size)
 {
-	void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
 
 	trace_kmalloc_node(_RET_IP_, ret,
 			   size, s->size, gfpflags, node);
@@ -2457,7 +2471,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 
 	stat(s, FREE_SLOWPATH);
 
-	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
+	if (kmem_cache_debug(s) &&
+		!(n = free_debug_processing(s, page, x, addr, &flags)))
 		return;
 
 	do {
@@ -3362,7 +3377,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_);
+	ret = slab_alloc(s, flags, _RET_IP_);
 
 	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
 
@@ -3405,7 +3420,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, flags, node, _RET_IP_);
+	ret = slab_alloc_node(s, flags, node, _RET_IP_);
 
 	trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
 
@@ -3482,7 +3497,7 @@ void kfree(const void *x)
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
 		kmemleak_free(x);
-		put_page(page);
+		__free_pages(page, compound_order(page));
 		return;
 	}
 	slab_free(page->slab, page, object, _RET_IP_);
@@ -4033,7 +4048,7 @@ 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, NUMA_NO_NODE, caller);
+	ret = slab_alloc(s, gfpflags, caller);
 
 	/* Honor the call site pointer we received. */
 	trace_kmalloc(caller, ret, size, s->size, gfpflags);
@@ -4063,7 +4078,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, gfpflags, node, caller);
+	ret = slab_alloc_node(s, gfpflags, node, caller);
 
 	/* Honor the call site pointer we received. */
 	trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);

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);