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

Pull slab changes from Pekka Enberg:
 "The bulk of the changes are more slab unification from Christoph.

  There's also few fixes from Aaron, Glauber, and Joonsoo thrown into
  the mix."

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux: (24 commits)
  mm, slab_common: Fix bootstrap creation of kmalloc caches
  slab: Return NULL for oversized allocations
  mm: slab: Verify the nodeid passed to ____cache_alloc_node
  slub: tid must be retrieved from the percpu area of the current processor
  slub: Do not dereference NULL pointer in node_match
  slub: add 'likely' macro to inc_slabs_node()
  slub: correct to calculate num of acquired objects in get_partial_node()
  slub: correctly bootstrap boot caches
  mm/sl[au]b: correct allocation type check in kmalloc_slab()
  slab: Fixup CONFIG_PAGE_ALLOC/DEBUG_SLAB_LEAK sections
  slab: Handle ARCH_DMA_MINALIGN correctly
  slab: Common definition for kmem_cache_node
  slab: Rename list3/l3 to node
  slab: Common Kmalloc cache determination
  stat: Use size_t for sizes instead of unsigned
  slab: Common function to create the kmalloc array
  slab: Common definition for the array of kmalloc caches
  slab: Common constants for kmalloc boundaries
  slab: Rename nodelists to node
  slab: Common name for the per node structures
  ...

1 files changed, 40 insertions, 181 deletions

diff --git a/mm/slub.c b/mm/slub.c
index a0206df88ab..57707f01bcf 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1006,7 +1006,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
 	 * dilemma by deferring the increment of the count during
 	 * bootstrap (see early_kmem_cache_node_alloc).
 	 */
-	if (n) {
+	if (likely(n)) {
 		atomic_long_inc(&n->nr_slabs);
 		atomic_long_add(objects, &n->total_objects);
 	}
@@ -1494,7 +1494,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
  */
 static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
-		int mode)
+		int mode, int *objects)
 {
 	void *freelist;
 	unsigned long counters;
@@ -1508,6 +1508,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
 	freelist = page->freelist;
 	counters = page->counters;
 	new.counters = counters;
+	*objects = new.objects - new.inuse;
 	if (mode) {
 		new.inuse = page->objects;
 		new.freelist = NULL;
@@ -1529,7 +1530,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
 	return freelist;
 }
 
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
 static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
 
 /*
@@ -1540,6 +1541,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 {
 	struct page *page, *page2;
 	void *object = NULL;
+	int available = 0;
+	int objects;
 
 	/*
 	 * Racy check. If we mistakenly see no partial slabs then we
@@ -1553,22 +1556,21 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 	spin_lock(&n->list_lock);
 	list_for_each_entry_safe(page, page2, &n->partial, lru) {
 		void *t;
-		int available;
 
 		if (!pfmemalloc_match(page, flags))
 			continue;
 
-		t = acquire_slab(s, n, page, object == NULL);
+		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
 			break;
 
+		available += objects;
 		if (!object) {
 			c->page = page;
 			stat(s, ALLOC_FROM_PARTIAL);
 			object = t;
-			available =  page->objects - page->inuse;
 		} else {
-			available = put_cpu_partial(s, page, 0);
+			put_cpu_partial(s, page, 0);
 			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
@@ -1947,7 +1949,7 @@ 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.
  */
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 {
 	struct page *oldpage;
 	int pages;
@@ -1985,7 +1987,6 @@ static 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);
-	return pobjects;
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
@@ -2042,7 +2043,7 @@ static void flush_all(struct kmem_cache *s)
 static inline int node_match(struct page *page, int node)
 {
 #ifdef CONFIG_NUMA
-	if (node != NUMA_NO_NODE && page_to_nid(page) != node)
+	if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node))
 		return 0;
 #endif
 	return 1;
@@ -2332,13 +2333,18 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 
 	s = memcg_kmem_get_cache(s, gfpflags);
 redo:
-
 	/*
 	 * Must read kmem_cache cpu data via this cpu ptr. Preemption is
 	 * enabled. We may switch back and forth between cpus while
 	 * reading from one cpu area. That does not matter as long
 	 * as we end up on the original cpu again when doing the cmpxchg.
+	 *
+	 * Preemption is disabled for the retrieval of the tid because that
+	 * must occur from the current processor. We cannot allow rescheduling
+	 * on a different processor between the determination of the pointer
+	 * and the retrieval of the tid.
 	 */
+	preempt_disable();
 	c = __this_cpu_ptr(s->cpu_slab);
 
 	/*
@@ -2348,7 +2354,7 @@ redo:
 	 * linked list in between.
 	 */
 	tid = c->tid;
-	barrier();
+	preempt_enable();
 
 	object = c->freelist;
 	page = c->page;
@@ -2595,10 +2601,11 @@ redo:
 	 * data is retrieved via this pointer. If we are on the same cpu
 	 * during the cmpxchg then the free will succedd.
 	 */
+	preempt_disable();
 	c = __this_cpu_ptr(s->cpu_slab);
 
 	tid = c->tid;
-	barrier();
+	preempt_enable();
 
 	if (likely(page == c->page)) {
 		set_freepointer(s, object, c->freelist);
@@ -2776,7 +2783,7 @@ init_kmem_cache_node(struct kmem_cache_node *n)
 static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 {
 	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
-			SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
+			KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu));
 
 	/*
 	 * Must align to double word boundary for the double cmpxchg
@@ -2983,7 +2990,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		s->allocflags |= __GFP_COMP;
 
 	if (s->flags & SLAB_CACHE_DMA)
-		s->allocflags |= SLUB_DMA;
+		s->allocflags |= GFP_DMA;
 
 	if (s->flags & SLAB_RECLAIM_ACCOUNT)
 		s->allocflags |= __GFP_RECLAIMABLE;
@@ -3175,13 +3182,6 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
-EXPORT_SYMBOL(kmalloc_caches);
-
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
-#endif
-
 static int __init setup_slub_min_order(char *str)
 {
 	get_option(&str, &slub_min_order);
@@ -3218,73 +3218,15 @@ static int __init setup_slub_nomerge(char *str)
 
 __setup("slub_nomerge", setup_slub_nomerge);
 
-/*
- * Conversion table for small slabs sizes / 8 to the index in the
- * kmalloc array. This is necessary for slabs < 192 since we have non power
- * of two cache sizes there. The size of larger slabs can be determined using
- * fls.
- */
-static s8 size_index[24] = {
-	3,	/* 8 */
-	4,	/* 16 */
-	5,	/* 24 */
-	5,	/* 32 */
-	6,	/* 40 */
-	6,	/* 48 */
-	6,	/* 56 */
-	6,	/* 64 */
-	1,	/* 72 */
-	1,	/* 80 */
-	1,	/* 88 */
-	1,	/* 96 */
-	7,	/* 104 */
-	7,	/* 112 */
-	7,	/* 120 */
-	7,	/* 128 */
-	2,	/* 136 */
-	2,	/* 144 */
-	2,	/* 152 */
-	2,	/* 160 */
-	2,	/* 168 */
-	2,	/* 176 */
-	2,	/* 184 */
-	2	/* 192 */
-};
-
-static inline int size_index_elem(size_t bytes)
-{
-	return (bytes - 1) / 8;
-}
-
-static struct kmem_cache *get_slab(size_t size, gfp_t flags)
-{
-	int index;
-
-	if (size <= 192) {
-		if (!size)
-			return ZERO_SIZE_PTR;
-
-		index = size_index[size_index_elem(size)];
-	} else
-		index = fls(size - 1);
-
-#ifdef CONFIG_ZONE_DMA
-	if (unlikely((flags & SLUB_DMA)))
-		return kmalloc_dma_caches[index];
-
-#endif
-	return kmalloc_caches[index];
-}
-
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE))
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
 		return kmalloc_large(size, flags);
 
-	s = get_slab(size, flags);
+	s = kmalloc_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3317,7 +3259,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE)) {
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, flags, node);
 
 		trace_kmalloc_node(_RET_IP_, ret,
@@ -3327,7 +3269,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 		return ret;
 	}
 
-	s = get_slab(size, flags);
+	s = kmalloc_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3620,6 +3562,12 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 
 	memcpy(s, static_cache, kmem_cache->object_size);
 
+	/*
+	 * This runs very early, and only the boot processor is supposed to be
+	 * up.  Even if it weren't true, IRQs are not up so we couldn't fire
+	 * 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);
 		struct page *p;
@@ -3642,8 +3590,6 @@ void __init kmem_cache_init(void)
 {
 	static __initdata struct kmem_cache boot_kmem_cache,
 		boot_kmem_cache_node;
-	int i;
-	int caches = 2;
 
 	if (debug_guardpage_minorder())
 		slub_max_order = 0;
@@ -3674,103 +3620,16 @@ void __init kmem_cache_init(void)
 	kmem_cache_node = bootstrap(&boot_kmem_cache_node);
 
 	/* Now we can use the kmem_cache to allocate kmalloc slabs */
-
-	/*
-	 * Patch up the size_index table if we have strange large alignment
-	 * requirements for the kmalloc array. This is only the case for
-	 * MIPS it seems. The standard arches will not generate any code here.
-	 *
-	 * Largest permitted alignment is 256 bytes due to the way we
-	 * handle the index determination for the smaller caches.
-	 *
-	 * Make sure that nothing crazy happens if someone starts tinkering
-	 * around with ARCH_KMALLOC_MINALIGN
-	 */
-	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
-		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
-
-	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
-		int elem = size_index_elem(i);
-		if (elem >= ARRAY_SIZE(size_index))
-			break;
-		size_index[elem] = KMALLOC_SHIFT_LOW;
-	}
-
-	if (KMALLOC_MIN_SIZE == 64) {
-		/*
-		 * The 96 byte size cache is not used if the alignment
-		 * is 64 byte.
-		 */
-		for (i = 64 + 8; i <= 96; i += 8)
-			size_index[size_index_elem(i)] = 7;
-	} else if (KMALLOC_MIN_SIZE == 128) {
-		/*
-		 * The 192 byte sized cache is not used if the alignment
-		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
-		 * instead.
-		 */
-		for (i = 128 + 8; i <= 192; i += 8)
-			size_index[size_index_elem(i)] = 8;
-	}
-
-	/* Caches that are not of the two-to-the-power-of size */
-	if (KMALLOC_MIN_SIZE <= 32) {
-		kmalloc_caches[1] = create_kmalloc_cache("kmalloc-96", 96, 0);
-		caches++;
-	}
-
-	if (KMALLOC_MIN_SIZE <= 64) {
-		kmalloc_caches[2] = create_kmalloc_cache("kmalloc-192", 192, 0);
-		caches++;
-	}
-
-	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
-		kmalloc_caches[i] = create_kmalloc_cache("kmalloc", 1 << i, 0);
-		caches++;
-	}
-
-	slab_state = UP;
-
-	/* Provide the correct kmalloc names now that the caches are up */
-	if (KMALLOC_MIN_SIZE <= 32) {
-		kmalloc_caches[1]->name = kstrdup(kmalloc_caches[1]->name, GFP_NOWAIT);
-		BUG_ON(!kmalloc_caches[1]->name);
-	}
-
-	if (KMALLOC_MIN_SIZE <= 64) {
-		kmalloc_caches[2]->name = kstrdup(kmalloc_caches[2]->name, GFP_NOWAIT);
-		BUG_ON(!kmalloc_caches[2]->name);
-	}
-
-	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;
-	}
+	create_kmalloc_caches(0);
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
 #endif
 
-#ifdef CONFIG_ZONE_DMA
-	for (i = 0; i < SLUB_PAGE_SHIFT; i++) {
-		struct kmem_cache *s = kmalloc_caches[i];
-
-		if (s && s->size) {
-			char *name = kasprintf(GFP_NOWAIT,
-				 "dma-kmalloc-%d", s->object_size);
-
-			BUG_ON(!name);
-			kmalloc_dma_caches[i] = create_kmalloc_cache(name,
-				s->object_size, SLAB_CACHE_DMA);
-		}
-	}
-#endif
 	printk(KERN_INFO
-		"SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
+		"SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d,"
 		" CPUs=%d, Nodes=%d\n",
-		caches, cache_line_size(),
+		cache_line_size(),
 		slub_min_order, slub_max_order, slub_min_objects,
 		nr_cpu_ids, nr_node_ids);
 }
@@ -3933,10 +3792,10 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE))
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
 		return kmalloc_large(size, gfpflags);
 
-	s = get_slab(size, gfpflags);
+	s = kmalloc_slab(size, gfpflags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3956,7 +3815,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE)) {
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, gfpflags, node);
 
 		trace_kmalloc_node(caller, ret,
@@ -3966,7 +3825,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 		return ret;
 	}
 
-	s = get_slab(size, gfpflags);
+	s = kmalloc_slab(size, gfpflags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -4315,7 +4174,7 @@ static void resiliency_test(void)
 {
 	u8 *p;
 
-	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || SLUB_PAGE_SHIFT < 10);
+	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10);
 
 	printk(KERN_ERR "SLUB resiliency testing\n");
 	printk(KERN_ERR "-----------------------\n");