slab: link memcg caches of the same kind into a list

Sometimes, we need to iterate over all memcg copies of a particular root
kmem cache.  Currently, we use memcg_cache_params->memcg_caches array for
that, because it contains all existing memcg caches.

However, it's a bad practice to keep all caches, including those that
belong to offline cgroups, in this array, because it will be growing
beyond any bounds then.  I'm going to wipe away dead caches from it to
save space.  To still be able to perform iterations over all memcg caches
of the same kind, let us link them into a list.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 37 insertions, 33 deletions

diff --git a/mm/slab.c b/mm/slab.c
index 65b5dcb6f671..7894017bc160 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3708,8 +3708,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
 	int ret;
-	struct kmem_cache *c = NULL;
-	int i = 0;
+	struct kmem_cache *c;
 
 	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
 
@@ -3719,12 +3718,10 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 	if ((ret < 0) || !is_root_cache(cachep))
 		return ret;
 
-	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(cachep, i);
-		if (c)
-			/* return value determined by the parent cache only */
-			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
+	lockdep_assert_held(&slab_mutex);
+	for_each_memcg_cache(c, cachep) {
+		/* return value determined by the root cache only */
+		__do_tune_cpucache(c, limit, batchcount, shared, gfp);
 	}
 
 	return ret;
diff --git a/mm/slab.h b/mm/slab.h
index 53a623f85931..0a56d76ac0e9 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -163,6 +163,18 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * Iterate over all memcg caches of the given root cache. The caller must hold
+ * slab_mutex.
+ */
+#define for_each_memcg_cache(iter, root) \
+	list_for_each_entry(iter, &(root)->memcg_params.list, \
+			    memcg_params.list)
+
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \
+				 memcg_params.list)
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return s->memcg_params.is_root_cache;
@@ -241,6 +253,11 @@ extern void slab_init_memcg_params(struct kmem_cache *);
 
 #else /* !CONFIG_MEMCG_KMEM */
 
+#define for_each_memcg_cache(iter, root) \
+	for ((void)(iter), (void)(root); 0; )
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	for ((void)(iter), (void)(tmp), (void)(root); 0; )
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 7cc32cf126ef..989784bd88be 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -109,6 +109,7 @@ static inline int kmem_cache_sanity_check(const char *name, size_t size)
 void slab_init_memcg_params(struct kmem_cache *s)
 {
 	s->memcg_params.is_root_cache = true;
+	INIT_LIST_HEAD(&s->memcg_params.list);
 	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
 }
 
@@ -449,6 +450,7 @@ static int do_kmem_cache_shutdown(struct kmem_cache *s,
 						lockdep_is_held(&slab_mutex));
 		BUG_ON(arr->entries[idx] != s);
 		arr->entries[idx] = NULL;
+		list_del(&s->memcg_params.list);
 	}
 #endif
 	list_move(&s->list, release);
@@ -529,6 +531,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 	}
 
+	list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
+
 	/*
 	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
@@ -581,11 +585,13 @@ void slab_kmem_cache_release(struct kmem_cache *s)
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	int i;
+	struct kmem_cache *c, *c2;
 	LIST_HEAD(release);
 	bool need_rcu_barrier = false;
 	bool busy = false;
 
+	BUG_ON(!is_root_cache(s));
+
 	get_online_cpus();
 	get_online_mems();
 
@@ -595,10 +601,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
-	for_each_memcg_cache_index(i) {
-		struct kmem_cache *c = cache_from_memcg_idx(s, i);
-
-		if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
+	for_each_memcg_cache_safe(c, c2, s) {
+		if (do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
 			busy = true;
 	}
 
@@ -932,16 +936,11 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 {
 	struct kmem_cache *c;
 	struct slabinfo sinfo;
-	int i;
 
 	if (!is_root_cache(s))
 		return;
 
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(s, i);
-		if (!c)
-			continue;
-
+	for_each_memcg_cache(c, s) {
 		memset(&sinfo, 0, sizeof(sinfo));
 		get_slabinfo(c, &sinfo);
 
diff --git a/mm/slub.c b/mm/slub.c
index 75d55fdfe3a1..1e5a4636cb23 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3636,13 +3636,10 @@ struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s;
+	struct kmem_cache *s, *c;
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
-		int i;
-		struct kmem_cache *c;
-
 		s->refcount++;
 
 		/*
@@ -3652,10 +3649,7 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 		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;
+		for_each_memcg_cache(c, s) {
 			c->object_size = s->object_size;
 			c->inuse = max_t(int, c->inuse,
 					 ALIGN(size, sizeof(void *)));
@@ -4921,7 +4915,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 	err = attribute->store(s, buf, len);
 #ifdef CONFIG_MEMCG_KMEM
 	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-		int i;
+		struct kmem_cache *c;
 
 		mutex_lock(&slab_mutex);
 		if (s->max_attr_size < len)
@@ -4944,11 +4938,8 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		 * directly either failed or succeeded, in which case we loop
 		 * through the descendants with best-effort propagation.
 		 */
-		for_each_memcg_cache_index(i) {
-			struct kmem_cache *c = cache_from_memcg_idx(s, i);
-			if (c)
-				attribute->store(c, buf, len);
-		}
+		for_each_memcg_cache(c, s)
+			attribute->store(c, buf, len);
 		mutex_unlock(&slab_mutex);
 	}
 #endif