1 files changed, 115 insertions, 232 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 73004808537..ae7b9f1ad39 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -169,16 +169,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
  */
 #define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
 
-/*
- * Set of flags that will prevent slab merging
- */
-#define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
-		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
-		SLAB_FAILSLAB)
-
-#define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA | SLAB_NOTRACK)
-
 #define OO_SHIFT	16
 #define OO_MASK		((1 << OO_SHIFT) - 1)
 #define MAX_OBJS_PER_PAGE	32767 /* since page.objects is u15 */
@@ -233,11 +223,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
  * 			Core slab cache functions
  *******************************************************************/
 
-static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
-{
-	return s->node[node];
-}
-
 /* Verify that a pointer has an address that is valid within a slab page */
 static inline int check_valid_pointer(struct kmem_cache *s,
 				struct page *page, const void *object)
@@ -288,6 +273,10 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 	for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
 			__p += (__s)->size)
 
+#define for_each_object_idx(__p, __idx, __s, __addr, __objects) \
+	for (__p = (__addr), __idx = 1; __idx <= __objects;\
+			__p += (__s)->size, __idx++)
+
 /* Determine object index from a given position */
 static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
 {
@@ -382,9 +371,9 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page
     defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
 	if (s->flags & __CMPXCHG_DOUBLE) {
 		if (cmpxchg_double(&page->freelist, &page->counters,
-			freelist_old, counters_old,
-			freelist_new, counters_new))
-		return 1;
+				   freelist_old, counters_old,
+				   freelist_new, counters_new))
+			return 1;
 	} else
 #endif
 	{
@@ -418,9 +407,9 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
     defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
 	if (s->flags & __CMPXCHG_DOUBLE) {
 		if (cmpxchg_double(&page->freelist, &page->counters,
-			freelist_old, counters_old,
-			freelist_new, counters_new))
-		return 1;
+				   freelist_old, counters_old,
+				   freelist_new, counters_new))
+			return 1;
 	} else
 #endif
 	{
@@ -945,60 +934,6 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 }
 
 /*
- * Hooks for other subsystems that check memory allocations. In a typical
- * production configuration these hooks all should produce no code at all.
- */
-static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
-{
-	kmemleak_alloc(ptr, size, 1, flags);
-}
-
-static inline void kfree_hook(const void *x)
-{
-	kmemleak_free(x);
-}
-
-static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
-{
-	flags &= gfp_allowed_mask;
-	lockdep_trace_alloc(flags);
-	might_sleep_if(flags & __GFP_WAIT);
-
-	return should_failslab(s->object_size, flags, s->flags);
-}
-
-static inline void slab_post_alloc_hook(struct kmem_cache *s,
-					gfp_t flags, void *object)
-{
-	flags &= gfp_allowed_mask;
-	kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
-	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
-}
-
-static inline void slab_free_hook(struct kmem_cache *s, void *x)
-{
-	kmemleak_free_recursive(x, s->flags);
-
-	/*
-	 * Trouble is that we may no longer disable interrupts in the fast path
-	 * So in order to make the debug calls that expect irqs to be
-	 * disabled we need to disable interrupts temporarily.
-	 */
-#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
-	{
-		unsigned long flags;
-
-		local_irq_save(flags);
-		kmemcheck_slab_free(s, x, s->object_size);
-		debug_check_no_locks_freed(x, s->object_size);
-		local_irq_restore(flags);
-	}
-#endif
-	if (!(s->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(x, s->object_size);
-}
-
-/*
  * Tracking of fully allocated slabs for debugging purposes.
  */
 static void add_full(struct kmem_cache *s,
@@ -1231,7 +1166,7 @@ out:
 
 __setup("slub_debug", setup_slub_debug);
 
-static unsigned long kmem_cache_flags(unsigned long object_size,
+unsigned long kmem_cache_flags(unsigned long object_size,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1263,7 +1198,7 @@ static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
-static inline unsigned long kmem_cache_flags(unsigned long object_size,
+unsigned long kmem_cache_flags(unsigned long object_size,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1282,6 +1217,12 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+#endif /* CONFIG_SLUB_DEBUG */
+
+/*
+ * Hooks for other subsystems that check memory allocations. In a typical
+ * production configuration these hooks all should produce no code at all.
+ */
 static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
 {
 	kmemleak_alloc(ptr, size, 1, flags);
@@ -1293,21 +1234,44 @@ static inline void kfree_hook(const void *x)
 }
 
 static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
-							{ return 0; }
+{
+	flags &= gfp_allowed_mask;
+	lockdep_trace_alloc(flags);
+	might_sleep_if(flags & __GFP_WAIT);
+
+	return should_failslab(s->object_size, flags, s->flags);
+}
 
-static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-		void *object)
+static inline void slab_post_alloc_hook(struct kmem_cache *s,
+					gfp_t flags, void *object)
 {
-	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags,
-		flags & gfp_allowed_mask);
+	flags &= gfp_allowed_mask;
+	kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
+	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
 }
 
 static inline void slab_free_hook(struct kmem_cache *s, void *x)
 {
 	kmemleak_free_recursive(x, s->flags);
-}
 
-#endif /* CONFIG_SLUB_DEBUG */
+	/*
+	 * Trouble is that we may no longer disable interrupts in the fast path
+	 * So in order to make the debug calls that expect irqs to be
+	 * disabled we need to disable interrupts temporarily.
+	 */
+#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
+	{
+		unsigned long flags;
+
+		local_irq_save(flags);
+		kmemcheck_slab_free(s, x, s->object_size);
+		debug_check_no_locks_freed(x, s->object_size);
+		local_irq_restore(flags);
+	}
+#endif
+	if (!(s->flags & SLAB_DEBUG_OBJECTS))
+		debug_check_no_obj_freed(x, s->object_size);
+}
 
 /*
  * Slab allocation and freeing
@@ -1409,9 +1373,9 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
 	void *start;
-	void *last;
 	void *p;
 	int order;
+	int idx;
 
 	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1432,14 +1396,13 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (unlikely(s->flags & SLAB_POISON))
 		memset(start, POISON_INUSE, PAGE_SIZE << order);
 
-	last = start;
-	for_each_object(p, s, start, page->objects) {
-		setup_object(s, page, last);
-		set_freepointer(s, last, p);
-		last = p;
+	for_each_object_idx(p, idx, s, start, page->objects) {
+		setup_object(s, page, p);
+		if (likely(idx < page->objects))
+			set_freepointer(s, p, p + s->size);
+		else
+			set_freepointer(s, p, NULL);
 	}
-	setup_object(s, page, last);
-	set_freepointer(s, last, NULL);
 
 	page->freelist = start;
 	page->inuse = page->objects;
@@ -1726,7 +1689,12 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 		struct kmem_cache_cpu *c)
 {
 	void *object;
-	int searchnode = (node == NUMA_NO_NODE) ? numa_mem_id() : node;
+	int searchnode = node;
+
+	if (node == NUMA_NO_NODE)
+		searchnode = numa_mem_id();
+	else if (!node_present_pages(node))
+		searchnode = node_to_mem_node(node);
 
 	object = get_partial_node(s, get_node(s, searchnode), c, flags);
 	if (object || node != NUMA_NO_NODE)
@@ -2162,6 +2130,7 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 	static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 	int node;
+	struct kmem_cache_node *n;
 
 	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs))
 		return;
@@ -2176,15 +2145,11 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 		pr_warn("  %s debugging increased min order, use slub_debug=O to disable.\n",
 			s->name);
 
-	for_each_online_node(node) {
-		struct kmem_cache_node *n = get_node(s, node);
+	for_each_kmem_cache_node(s, node, n) {
 		unsigned long nr_slabs;
 		unsigned long nr_objs;
 		unsigned long nr_free;
 
-		if (!n)
-			continue;
-
 		nr_free  = count_partial(n, count_free);
 		nr_slabs = node_nr_slabs(n);
 		nr_objs  = node_nr_objs(n);
@@ -2310,11 +2275,18 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 redo:
 
 	if (unlikely(!node_match(page, node))) {
-		stat(s, ALLOC_NODE_MISMATCH);
-		deactivate_slab(s, page, c->freelist);
-		c->page = NULL;
-		c->freelist = NULL;
-		goto new_slab;
+		int searchnode = node;
+
+		if (node != NUMA_NO_NODE && !node_present_pages(node))
+			searchnode = node_to_mem_node(node);
+
+		if (unlikely(!node_match(page, searchnode))) {
+			stat(s, ALLOC_NODE_MISMATCH);
+			deactivate_slab(s, page, c->freelist);
+			c->page = NULL;
+			c->freelist = NULL;
+			goto new_slab;
+		}
 	}
 
 	/*
@@ -2737,12 +2709,6 @@ static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
 static int slub_min_objects;
 
 /*
- * Merge control. If this is set then no merging of slab caches will occur.
- * (Could be removed. This was introduced to pacify the merge skeptics.)
- */
-static int slub_nomerge;
-
-/*
  * Calculate the order of allocation given an slab object size.
  *
  * The order of allocation has significant impact on performance and other
@@ -2928,13 +2894,10 @@ static void early_kmem_cache_node_alloc(int node)
 static void free_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
+	struct kmem_cache_node *n;
 
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = s->node[node];
-
-		if (n)
-			kmem_cache_free(kmem_cache_node, n);
-
+	for_each_kmem_cache_node(s, node, n) {
+		kmem_cache_free(kmem_cache_node, n);
 		s->node[node] = NULL;
 	}
 }
@@ -3222,12 +3185,11 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 static inline int kmem_cache_close(struct kmem_cache *s)
 {
 	int node;
+	struct kmem_cache_node *n;
 
 	flush_all(s);
 	/* Attempt to free all objects */
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
-
+	for_each_kmem_cache_node(s, node, n) {
 		free_partial(s, n);
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
@@ -3274,14 +3236,6 @@ static int __init setup_slub_min_objects(char *str)
 
 __setup("slub_min_objects=", setup_slub_min_objects);
 
-static int __init setup_slub_nomerge(char *str)
-{
-	slub_nomerge = 1;
-	return 1;
-}
-
-__setup("slub_nomerge", setup_slub_nomerge);
-
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
@@ -3412,9 +3366,7 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 		return -ENOMEM;
 
 	flush_all(s);
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		n = get_node(s, node);
-
+	for_each_kmem_cache_node(s, node, n) {
 		if (!n->nr_partial)
 			continue;
 
@@ -3586,6 +3538,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 {
 	int node;
 	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+	struct kmem_cache_node *n;
 
 	memcpy(s, static_cache, kmem_cache->object_size);
 
@@ -3595,19 +3548,16 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 	 * IPIs around.
 	 */
 	__flush_cpu_slab(s, smp_processor_id());
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
+	for_each_kmem_cache_node(s, node, n) {
 		struct page *p;
 
-		if (n) {
-			list_for_each_entry(p, &n->partial, lru)
-				p->slab_cache = s;
+		list_for_each_entry(p, &n->partial, lru)
+			p->slab_cache = s;
 
 #ifdef CONFIG_SLUB_DEBUG
-			list_for_each_entry(p, &n->full, lru)
-				p->slab_cache = s;
+		list_for_each_entry(p, &n->full, lru)
+			p->slab_cache = s;
 #endif
-		}
 	}
 	list_add(&s->list, &slab_caches);
 	return s;
@@ -3663,69 +3613,6 @@ void __init kmem_cache_init_late(void)
 {
 }
 
-/*
- * Find a mergeable slab cache
- */
-static int slab_unmergeable(struct kmem_cache *s)
-{
-	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
-		return 1;
-
-	if (!is_root_cache(s))
-		return 1;
-
-	if (s->ctor)
-		return 1;
-
-	/*
-	 * We may have set a slab to be unmergeable during bootstrap.
-	 */
-	if (s->refcount < 0)
-		return 1;
-
-	return 0;
-}
-
-static struct kmem_cache *find_mergeable(size_t size, size_t align,
-		unsigned long flags, const char *name, void (*ctor)(void *))
-{
-	struct kmem_cache *s;
-
-	if (slub_nomerge || (flags & SLUB_NEVER_MERGE))
-		return NULL;
-
-	if (ctor)
-		return NULL;
-
-	size = ALIGN(size, sizeof(void *));
-	align = calculate_alignment(flags, align, size);
-	size = ALIGN(size, align);
-	flags = kmem_cache_flags(size, flags, name, NULL);
-
-	list_for_each_entry(s, &slab_caches, list) {
-		if (slab_unmergeable(s))
-			continue;
-
-		if (size > s->size)
-			continue;
-
-		if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME))
-			continue;
-		/*
-		 * Check if alignment is compatible.
-		 * Courtesy of Adrian Drzewiecki
-		 */
-		if ((s->size & ~(align - 1)) != s->size)
-			continue;
-
-		if (s->size - size >= sizeof(void *))
-			continue;
-
-		return s;
-	}
-	return NULL;
-}
-
 struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
@@ -3960,16 +3847,14 @@ static long validate_slab_cache(struct kmem_cache *s)
 	unsigned long count = 0;
 	unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
 				sizeof(unsigned long), GFP_KERNEL);
+	struct kmem_cache_node *n;
 
 	if (!map)
 		return -ENOMEM;
 
 	flush_all(s);
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
-
+	for_each_kmem_cache_node(s, node, n)
 		count += validate_slab_node(s, n, map);
-	}
 	kfree(map);
 	return count;
 }
@@ -4123,6 +4008,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	int node;
 	unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
 				     sizeof(unsigned long), GFP_KERNEL);
+	struct kmem_cache_node *n;
 
 	if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
 				     GFP_TEMPORARY)) {
@@ -4132,8 +4018,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	/* Push back cpu slabs */
 	flush_all(s);
 
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
+	for_each_kmem_cache_node(s, node, n) {
 		unsigned long flags;
 		struct page *page;
 
@@ -4205,7 +4090,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 #endif
 
 #ifdef SLUB_RESILIENCY_TEST
-static void resiliency_test(void)
+static void __init resiliency_test(void)
 {
 	u8 *p;
 
@@ -4332,8 +4217,9 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 	get_online_mems();
 #ifdef CONFIG_SLUB_DEBUG
 	if (flags & SO_ALL) {
-		for_each_node_state(node, N_NORMAL_MEMORY) {
-			struct kmem_cache_node *n = get_node(s, node);
+		struct kmem_cache_node *n;
+
+		for_each_kmem_cache_node(s, node, n) {
 
 			if (flags & SO_TOTAL)
 				x = atomic_long_read(&n->total_objects);
@@ -4349,9 +4235,9 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 	} else
 #endif
 	if (flags & SO_PARTIAL) {
-		for_each_node_state(node, N_NORMAL_MEMORY) {
-			struct kmem_cache_node *n = get_node(s, node);
+		struct kmem_cache_node *n;
 
+		for_each_kmem_cache_node(s, node, n) {
 			if (flags & SO_TOTAL)
 				x = count_partial(n, count_total);
 			else if (flags & SO_OBJECTS)
@@ -4364,7 +4250,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 	}
 	x = sprintf(buf, "%lu", total);
 #ifdef CONFIG_NUMA
-	for_each_node_state(node, N_NORMAL_MEMORY)
+	for (node = 0; node < nr_node_ids; node++)
 		if (nodes[node])
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
@@ -4378,16 +4264,12 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 static int any_slab_objects(struct kmem_cache *s)
 {
 	int node;
+	struct kmem_cache_node *n;
 
-	for_each_online_node(node) {
-		struct kmem_cache_node *n = get_node(s, node);
-
-		if (!n)
-			continue;
-
+	for_each_kmem_cache_node(s, node, n)
 		if (atomic_long_read(&n->total_objects))
 			return 1;
-	}
+
 	return 0;
 }
 #endif
@@ -4509,7 +4391,7 @@ SLAB_ATTR_RO(ctor);
 
 static ssize_t aliases_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->refcount - 1);
+	return sprintf(buf, "%d\n", s->refcount < 0 ? 0 : s->refcount - 1);
 }
 SLAB_ATTR_RO(aliases);
 
@@ -4647,6 +4529,14 @@ static ssize_t trace_show(struct kmem_cache *s, char *buf)
 static ssize_t trace_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
+	/*
+	 * Tracing a merged cache is going to give confusing results
+	 * as well as cause other issues like converting a mergeable
+	 * cache into an umergeable one.
+	 */
+	if (s->refcount > 1)
+		return -EINVAL;
+
 	s->flags &= ~SLAB_TRACE;
 	if (buf[0] == '1') {
 		s->flags &= ~__CMPXCHG_DOUBLE;
@@ -4764,6 +4654,9 @@ static ssize_t failslab_show(struct kmem_cache *s, char *buf)
 static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
+	if (s->refcount > 1)
+		return -EINVAL;
+
 	s->flags &= ~SLAB_FAILSLAB;
 	if (buf[0] == '1')
 		s->flags |= SLAB_FAILSLAB;
@@ -5171,12 +5064,6 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = '-';
 	p += sprintf(p, "%07d", s->size);
 
-#ifdef CONFIG_MEMCG_KMEM
-	if (!is_root_cache(s))
-		p += sprintf(p, "-%08d",
-				memcg_cache_id(s->memcg_params->memcg));
-#endif
-
 	BUG_ON(p > name + ID_STR_LENGTH - 1);
 	return name;
 }
@@ -5342,13 +5229,9 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	unsigned long nr_objs = 0;
 	unsigned long nr_free = 0;
 	int node;
+	struct kmem_cache_node *n;
 
-	for_each_online_node(node) {
-		struct kmem_cache_node *n = get_node(s, node);
-
-		if (!n)
-			continue;
-
+	for_each_kmem_cache_node(s, node, n) {
 		nr_slabs += node_nr_slabs(n);
 		nr_objs += node_nr_objs(n);
 		nr_free += count_partial(n, count_free);