1 files changed, 89 insertions, 62 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 25f14ad8f81..2b1ce697fc4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -210,21 +210,22 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 #ifdef CONFIG_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
-static void sysfs_slab_remove(struct kmem_cache *);
 static void memcg_propagate_slab_attrs(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
-
 static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
 {
 #ifdef CONFIG_SLUB_STATS
-	__this_cpu_inc(s->cpu_slab->stat[si]);
+	/*
+	 * The rmw is racy on a preemptible kernel but this is acceptable, so
+	 * avoid this_cpu_add()'s irq-disable overhead.
+	 */
+	raw_cpu_inc(s->cpu_slab->stat[si]);
 #endif
 }
 
@@ -1348,11 +1349,12 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	page = alloc_slab_page(alloc_gfp, node, oo);
 	if (unlikely(!page)) {
 		oo = s->min;
+		alloc_gfp = flags;
 		/*
 		 * Allocation may have failed due to fragmentation.
 		 * Try a lower order alloc if possible
 		 */
-		page = alloc_slab_page(flags, node, oo);
+		page = alloc_slab_page(alloc_gfp, node, oo);
 
 		if (page)
 			stat(s, ORDER_FALLBACK);
@@ -1362,7 +1364,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
 		int pages = 1 << oo_order(oo);
 
-		kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
+		kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node);
 
 		/*
 		 * Objects from caches that have a constructor don't get
@@ -1684,8 +1686,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 		return NULL;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
-		zonelist = node_zonelist(slab_node(), flags);
+		cpuset_mems_cookie = read_mems_allowed_begin();
+		zonelist = node_zonelist(mempolicy_slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
 
@@ -1696,19 +1698,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
 					/*
-					 * Return the object even if
-					 * put_mems_allowed indicated that
-					 * the cpuset mems_allowed was
-					 * updated in parallel. It's a
-					 * harmless race between the alloc
-					 * and the cpuset update.
+					 * Don't check read_mems_allowed_retry()
+					 * here - if mems_allowed was updated in
+					 * parallel, that was a harmless race
+					 * between allocation and the cpuset
+					 * update
 					 */
-					put_mems_allowed(cpuset_mems_cookie);
 					return object;
 				}
 			}
 		}
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
@@ -3235,23 +3235,7 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 
 int __kmem_cache_shutdown(struct kmem_cache *s)
 {
-	int rc = kmem_cache_close(s);
-
-	if (!rc) {
-		/*
-		 * We do the same lock strategy around sysfs_slab_add, see
-		 * __kmem_cache_create. Because this is pretty much the last
-		 * operation we do and the lock will be released shortly after
-		 * that in slab_common.c, we could just move sysfs_slab_remove
-		 * to a later point in common code. We should do that when we
-		 * have a common sysfs framework for all allocators.
-		 */
-		mutex_unlock(&slab_mutex);
-		sysfs_slab_remove(s);
-		mutex_lock(&slab_mutex);
-	}
-
-	return rc;
+	return kmem_cache_close(s);
 }
 
 /********************************************************************
@@ -3686,6 +3670,9 @@ 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;
 
@@ -3698,9 +3685,8 @@ static int slab_unmergeable(struct kmem_cache *s)
 	return 0;
 }
 
-static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
-		size_t align, unsigned long flags, const char *name,
-		void (*ctor)(void *))
+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;
 
@@ -3723,7 +3709,7 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
 			continue;
 
 		if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME))
-				continue;
+			continue;
 		/*
 		 * Check if alignment is compatible.
 		 * Courtesy of Adrian Drzewiecki
@@ -3734,23 +3720,24 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
-		if (!cache_match_memcg(s, memcg))
-			continue;
-
 		return s;
 	}
 	return NULL;
 }
 
 struct kmem_cache *
-__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
-		   size_t align, unsigned long flags, void (*ctor)(void *))
+__kmem_cache_alias(const char *name, size_t size, size_t align,
+		   unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
 
-	s = find_mergeable(memcg, size, align, flags, name, ctor);
+	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
+		int i;
+		struct kmem_cache *c;
+
 		s->refcount++;
+
 		/*
 		 * Adjust the object sizes so that we clear
 		 * the complete object on kzalloc.
@@ -3758,6 +3745,15 @@ __kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
 		s->object_size = max(s->object_size, (int)size);
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 
+		for_each_memcg_cache_index(i) {
+			c = cache_from_memcg_idx(s, i);
+			if (!c)
+				continue;
+			c->object_size = s->object_size;
+			c->inuse = max_t(int, c->inuse,
+					 ALIGN(size, sizeof(void *)));
+		}
+
 		if (sysfs_slab_alias(s, name)) {
 			s->refcount--;
 			s = NULL;
@@ -3780,10 +3776,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 		return 0;
 
 	memcg_propagate_slab_attrs(s);
-	mutex_unlock(&slab_mutex);
 	err = sysfs_slab_add(s);
-	mutex_lock(&slab_mutex);
-
 	if (err)
 		kmem_cache_close(s);
 
@@ -5058,15 +5051,18 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 #ifdef CONFIG_MEMCG_KMEM
 	int i;
 	char *buffer = NULL;
+	struct kmem_cache *root_cache;
 
-	if (!is_root_cache(s))
+	if (is_root_cache(s))
 		return;
 
+	root_cache = s->memcg_params->root_cache;
+
 	/*
 	 * This mean this cache had no attribute written. Therefore, no point
 	 * in copying default values around
 	 */
-	if (!s->max_attr_size)
+	if (!root_cache->max_attr_size)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
@@ -5088,7 +5084,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		 */
 		if (buffer)
 			buf = buffer;
-		else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
 			buf = mbuf;
 		else {
 			buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5097,7 +5093,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(s->memcg_params->root_cache, buf);
+		attr->show(root_cache, buf);
 		attr->store(s, buf, strlen(buf));
 	}
 
@@ -5106,6 +5102,11 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 #endif
 }
 
+static void kmem_cache_release(struct kobject *k)
+{
+	slab_kmem_cache_release(to_slab(k));
+}
+
 static const struct sysfs_ops slab_sysfs_ops = {
 	.show = slab_attr_show,
 	.store = slab_attr_store,
@@ -5113,6 +5114,7 @@ static const struct sysfs_ops slab_sysfs_ops = {
 
 static struct kobj_type slab_ktype = {
 	.sysfs_ops = &slab_sysfs_ops,
+	.release = kmem_cache_release,
 };
 
 static int uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -5130,6 +5132,15 @@ static const struct kset_uevent_ops slab_uevent_ops = {
 
 static struct kset *slab_kset;
 
+static inline struct kset *cache_kset(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+	if (!is_root_cache(s))
+		return s->memcg_params->root_cache->memcg_kset;
+#endif
+	return slab_kset;
+}
+
 #define ID_STR_LENGTH 64
 
 /* Create a unique string id for a slab cache:
@@ -5195,29 +5206,42 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		name = create_unique_id(s);
 	}
 
-	s->kobj.kset = slab_kset;
+	s->kobj.kset = cache_kset(s);
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
-	if (err) {
-		kobject_put(&s->kobj);
-		return err;
-	}
+	if (err)
+		goto out_put_kobj;
 
 	err = sysfs_create_group(&s->kobj, &slab_attr_group);
-	if (err) {
-		kobject_del(&s->kobj);
-		kobject_put(&s->kobj);
-		return err;
+	if (err)
+		goto out_del_kobj;
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (is_root_cache(s)) {
+		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
+		if (!s->memcg_kset) {
+			err = -ENOMEM;
+			goto out_del_kobj;
+		}
 	}
+#endif
+
 	kobject_uevent(&s->kobj, KOBJ_ADD);
 	if (!unmergeable) {
 		/* Setup first alias */
 		sysfs_slab_alias(s, s->name);
-		kfree(name);
 	}
-	return 0;
+out:
+	if (!unmergeable)
+		kfree(name);
+	return err;
+out_del_kobj:
+	kobject_del(&s->kobj);
+out_put_kobj:
+	kobject_put(&s->kobj);
+	goto out;
 }
 
-static void sysfs_slab_remove(struct kmem_cache *s)
+void sysfs_slab_remove(struct kmem_cache *s)
 {
 	if (slab_state < FULL)
 		/*
@@ -5226,6 +5250,9 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 		 */
 		return;
 
+#ifdef CONFIG_MEMCG_KMEM
+	kset_unregister(s->memcg_kset);
+#endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
 	kobject_del(&s->kobj);
 	kobject_put(&s->kobj);