1 files changed, 411 insertions, 88 deletions

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3f3cd97d3fd..d31c4bacc6a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -19,6 +19,7 @@
 #include <asm/tlbflush.h>
 #include <asm/page.h>
 #include <linux/memcontrol.h>
+#include <trace/events/kmem.h>
 
 #include "slab.h"
 
@@ -28,8 +29,7 @@ DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
-				   size_t size)
+static int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	struct kmem_cache *s = NULL;
 
@@ -55,27 +55,22 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			continue;
 		}
 
-		/*
-		 * For simplicity, we won't check this in the list of memcg
-		 * caches. We have control over memcg naming, and if there
-		 * aren't duplicates in the global list, there won't be any
-		 * duplicates in the memcg lists as well.
-		 */
-		if (!memcg && !strcmp(s->name, name)) {
+#if !defined(CONFIG_SLUB)
+		if (!strcmp(s->name, name)) {
 			pr_err("%s (%s): Cache name already exists.\n",
 			       __func__, name);
 			dump_stack();
 			s = NULL;
 			return -EINVAL;
 		}
+#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
-					  const char *name, size_t size)
+static inline int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	return 0;
 }
@@ -136,6 +131,45 @@ unsigned long calculate_alignment(unsigned long flags,
 	return ALIGN(align, sizeof(void *));
 }
 
+static struct kmem_cache *
+do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align,
+		     unsigned long flags, void (*ctor)(void *),
+		     struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct kmem_cache *s;
+	int err;
+
+	err = -ENOMEM;
+	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
+	if (!s)
+		goto out;
+
+	s->name = name;
+	s->object_size = object_size;
+	s->size = size;
+	s->align = align;
+	s->ctor = ctor;
+
+	err = memcg_alloc_cache_params(memcg, s, root_cache);
+	if (err)
+		goto out_free_cache;
+
+	err = __kmem_cache_create(s, flags);
+	if (err)
+		goto out_free_cache;
+
+	s->refcount = 1;
+	list_add(&s->list, &slab_caches);
+out:
+	if (err)
+		return ERR_PTR(err);
+	return s;
+
+out_free_cache:
+	memcg_free_cache_params(s);
+	kfree(s);
+	goto out;
+}
 
 /*
  * kmem_cache_create - Create a cache.
@@ -161,20 +195,22 @@ unsigned long calculate_alignment(unsigned long flags,
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
  */
-
 struct kmem_cache *
-kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
-			size_t align, unsigned long flags, void (*ctor)(void *),
-			struct kmem_cache *parent_cache)
+kmem_cache_create(const char *name, size_t size, size_t align,
+		  unsigned long flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s = NULL;
-	int err = 0;
+	struct kmem_cache *s;
+	char *cache_name;
+	int err;
 
 	get_online_cpus();
+	get_online_mems();
+
 	mutex_lock(&slab_mutex);
 
-	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
-		goto out_locked;
+	err = kmem_cache_sanity_check(name, size);
+	if (err)
+		goto out_unlock;
 
 	/*
 	 * Some allocators will constraint the set of valid flags to a subset
@@ -184,47 +220,31 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
+	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 = calculate_alignment(flags, align, size);
-		s->ctor = ctor;
-
-		if (memcg_register_cache(memcg, s, parent_cache)) {
-			kmem_cache_free(kmem_cache, s);
-			err = -ENOMEM;
-			goto out_locked;
-		}
+		goto out_unlock;
 
-		s->name = kstrdup(name, GFP_KERNEL);
-		if (!s->name) {
-			kmem_cache_free(kmem_cache, s);
-			err = -ENOMEM;
-			goto out_locked;
-		}
-
-		err = __kmem_cache_create(s, flags);
-		if (!err) {
-			s->refcount = 1;
-			list_add(&s->list, &slab_caches);
-			memcg_cache_list_add(memcg, s);
-		} else {
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		}
-	} else
+	cache_name = kstrdup(name, GFP_KERNEL);
+	if (!cache_name) {
 		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	s = do_kmem_cache_create(cache_name, size, size,
+				 calculate_alignment(flags, align, size),
+				 flags, ctor, NULL, NULL);
+	if (IS_ERR(s)) {
+		err = PTR_ERR(s);
+		kfree(cache_name);
+	}
 
-out_locked:
+out_unlock:
 	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
 	put_online_cpus();
 
 	if (err) {
-
 		if (flags & SLAB_PANIC)
 			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
 				name, err);
@@ -233,54 +253,148 @@ out_locked:
 				name, err);
 			dump_stack();
 		}
-
 		return NULL;
 	}
+	return s;
+}
+EXPORT_SYMBOL(kmem_cache_create);
+
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * memcg_create_kmem_cache - Create a cache for a memory cgroup.
+ * @memcg: The memory cgroup the new cache is for.
+ * @root_cache: The parent of the new cache.
+ * @memcg_name: The name of the memory cgroup (used for naming the new cache).
+ *
+ * This function attempts to create a kmem cache that will serve allocation
+ * requests going from @memcg to @root_cache. The new cache inherits properties
+ * from its parent.
+ */
+struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
+					   struct kmem_cache *root_cache,
+					   const char *memcg_name)
+{
+	struct kmem_cache *s = NULL;
+	char *cache_name;
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+
+	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
+			       memcg_cache_id(memcg), memcg_name);
+	if (!cache_name)
+		goto out_unlock;
+
+	s = do_kmem_cache_create(cache_name, root_cache->object_size,
+				 root_cache->size, root_cache->align,
+				 root_cache->flags, root_cache->ctor,
+				 memcg, root_cache);
+	if (IS_ERR(s)) {
+		kfree(cache_name);
+		s = NULL;
+	}
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
 
 	return s;
 }
 
-struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
-		  unsigned long flags, void (*ctor)(void *))
+static int memcg_cleanup_cache_params(struct kmem_cache *s)
+{
+	int rc;
+
+	if (!s->memcg_params ||
+	    !s->memcg_params->is_root_cache)
+		return 0;
+
+	mutex_unlock(&slab_mutex);
+	rc = __memcg_cleanup_cache_params(s);
+	mutex_lock(&slab_mutex);
+
+	return rc;
+}
+#else
+static int memcg_cleanup_cache_params(struct kmem_cache *s)
 {
-	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
+	return 0;
 }
-EXPORT_SYMBOL(kmem_cache_create);
+#endif /* CONFIG_MEMCG_KMEM */
 
-void kmem_cache_destroy(struct kmem_cache *s)
+void slab_kmem_cache_release(struct kmem_cache *s)
 {
-	/* Destroy all the children caches if we aren't a memcg cache */
-	kmem_cache_destroy_memcg_children(s);
+	kfree(s->name);
+	kmem_cache_free(kmem_cache, s);
+}
 
+void kmem_cache_destroy(struct kmem_cache *s)
+{
 	get_online_cpus();
+	get_online_mems();
+
 	mutex_lock(&slab_mutex);
+
 	s->refcount--;
-	if (!s->refcount) {
-		list_del(&s->list);
-
-		if (!__kmem_cache_shutdown(s)) {
-			mutex_unlock(&slab_mutex);
-			if (s->flags & SLAB_DESTROY_BY_RCU)
-				rcu_barrier();
-
-			memcg_release_cache(s);
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		} else {
-			list_add(&s->list, &slab_caches);
-			mutex_unlock(&slab_mutex);
-			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
-				s->name);
-			dump_stack();
-		}
-	} else {
-		mutex_unlock(&slab_mutex);
+	if (s->refcount)
+		goto out_unlock;
+
+	if (memcg_cleanup_cache_params(s) != 0)
+		goto out_unlock;
+
+	if (__kmem_cache_shutdown(s) != 0) {
+		printk(KERN_ERR "kmem_cache_destroy %s: "
+		       "Slab cache still has objects\n", s->name);
+		dump_stack();
+		goto out_unlock;
 	}
+
+	list_del(&s->list);
+
+	mutex_unlock(&slab_mutex);
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		rcu_barrier();
+
+	memcg_free_cache_params(s);
+#ifdef SLAB_SUPPORTS_SYSFS
+	sysfs_slab_remove(s);
+#else
+	slab_kmem_cache_release(s);
+#endif
+	goto out;
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+out:
+	put_online_mems();
 	put_online_cpus();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
+/**
+ * kmem_cache_shrink - Shrink a cache.
+ * @cachep: The cache to shrink.
+ *
+ * Releases as many slabs as possible for a cache.
+ * To help debugging, a zero exit status indicates all slabs were released.
+ */
+int kmem_cache_shrink(struct kmem_cache *cachep)
+{
+	int ret;
+
+	get_online_cpus();
+	get_online_mems();
+	ret = __kmem_cache_shrink(cachep);
+	put_online_mems();
+	put_online_cpus();
+	return ret;
+}
+EXPORT_SYMBOL(kmem_cache_shrink);
+
 int slab_is_available(void)
 {
 	return slab_state >= UP;
@@ -299,7 +413,7 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
-		panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
+		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
 					name, size, err);
 
 	s->refcount = -1;	/* Exempt from merging for now */
@@ -319,10 +433,218 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 	return s;
 }
 
+struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_caches);
+
+#ifdef CONFIG_ZONE_DMA
+struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_dma_caches);
+#endif
+
+/*
+ * 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;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ */
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+{
+	int index;
+
+	if (unlikely(size > KMALLOC_MAX_SIZE)) {
+		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
+		return NULL;
+	}
+
+	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 & GFP_DMA)))
+		return kmalloc_dma_caches[index];
+
+#endif
+	return kmalloc_caches[index];
+}
+
+/*
+ * Create the kmalloc array. Some of the regular kmalloc arrays
+ * may already have been created because they were needed to
+ * enable allocations for slab creation.
+ */
+void __init create_kmalloc_caches(unsigned long flags)
+{
+	int i;
+
+	/*
+	 * 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;
+
+	}
+
+	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;
+	}
+	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+		if (!kmalloc_caches[i]) {
+			kmalloc_caches[i] = create_kmalloc_cache(NULL,
+							1 << i, flags);
+		}
+
+		/*
+		 * Caches that are not of the two-to-the-power-of size.
+		 * These have to be created immediately after the
+		 * earlier power of two caches
+		 */
+		if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
+			kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
+
+		if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
+			kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
+	}
+
+	/* Kmalloc array is now usable */
+	slab_state = UP;
+
+	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+		struct kmem_cache *s = kmalloc_caches[i];
+		char *n;
+
+		if (s) {
+			n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
+
+			BUG_ON(!n);
+			s->name = n;
+		}
+	}
+
+#ifdef CONFIG_ZONE_DMA
+	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+		struct kmem_cache *s = kmalloc_caches[i];
+
+		if (s) {
+			int size = kmalloc_size(i);
+			char *n = kasprintf(GFP_NOWAIT,
+				 "dma-kmalloc-%d", size);
+
+			BUG_ON(!n);
+			kmalloc_dma_caches[i] = create_kmalloc_cache(n,
+				size, SLAB_CACHE_DMA | flags);
+		}
+	}
+#endif
+}
 #endif /* !CONFIG_SLOB */
 
+/*
+ * To avoid unnecessary overhead, we pass through large allocation requests
+ * directly to the page allocator. We use __GFP_COMP, because we will need to
+ * know the allocation order to free the pages properly in kfree.
+ */
+void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret;
+	struct page *page;
+
+	flags |= __GFP_COMP;
+	page = alloc_kmem_pages(flags, order);
+	ret = page ? page_address(page) : NULL;
+	kmemleak_alloc(ret, size, 1, flags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order);
+
+#ifdef CONFIG_TRACING
+void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret = kmalloc_order(size, flags, order);
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order_trace);
+#endif
 
 #ifdef CONFIG_SLABINFO
+
+#ifdef CONFIG_SLAB
+#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
+#else
+#define SLABINFO_RIGHTS S_IRUSR
+#endif
+
 void print_slabinfo_header(struct seq_file *m)
 {
 	/*
@@ -357,12 +679,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	return seq_list_start(&slab_caches, *pos);
 }
 
-static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+void *slab_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	return seq_list_next(p, &slab_caches, pos);
 }
 
-static void s_stop(struct seq_file *m, void *p)
+void slab_stop(struct seq_file *m, void *p)
 {
 	mutex_unlock(&slab_mutex);
 }
@@ -378,7 +700,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 		return;
 
 	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(s, i);
+		c = cache_from_memcg_idx(s, i);
 		if (!c)
 			continue;
 
@@ -439,8 +761,8 @@ static int s_show(struct seq_file *m, void *p)
  */
 static const struct seq_operations slabinfo_op = {
 	.start = s_start,
-	.next = s_next,
-	.stop = s_stop,
+	.next = slab_next,
+	.stop = slab_stop,
 	.show = s_show,
 };
 
@@ -459,7 +781,8 @@ static const struct file_operations proc_slabinfo_operations = {
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
+	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
+						&proc_slabinfo_operations);
 	return 0;
 }
 module_init(slab_proc_init);