slab: link memcg kmem_caches on their associated memory cgroup

With kmem cgroup support enabled, kmem_caches can be created and
destroyed frequently and a great number of near empty kmem_caches can
accumulate if there are a lot of transient cgroups and the system is not
under memory pressure.  When memory reclaim starts under such
conditions, it can lead to consecutive deactivation and destruction of
many kmem_caches, easily hundreds of thousands on moderately large
systems, exposing scalability issues in the current slab management
code.  This is one of the patches to address the issue.

While a memcg kmem_cache is listed on its root cache's ->children list,
there is no direct way to iterate all kmem_caches which are assocaited
with a memory cgroup.  The only way to iterate them is walking all
caches while filtering out caches which don't match, which would be most
of them.

This makes memcg destruction operations O(N^2) where N is the total
number of slab caches which can be huge.  This combined with the
synchronous RCU operations can tie up a CPU and affect the whole machine
for many hours when memory reclaim triggers offlining and destruction of
the stale memcgs.

This patch adds mem_cgroup->kmem_caches list which goes through
memcg_cache_params->kmem_caches_node of all kmem_caches which are
associated with the memcg.  All memcg specific iterations, including
stat file access, are updated to use the new list instead.

Link: http://lkml.kernel.org/r/20170117235411.9408-6-tj@kernel.org
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Jay Vana <jsvana@fb.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 36 insertions, 10 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b822e158b319..834d641dfa8c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2837,6 +2837,7 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
+	INIT_LIST_HEAD(&memcg->kmem_caches);
 
 	return 0;
 }
@@ -4002,9 +4003,9 @@ static struct cftype mem_cgroup_legacy_files[] = {
 #ifdef CONFIG_SLABINFO
 	{
 		.name = "kmem.slabinfo",
-		.seq_start = slab_start,
-		.seq_next = slab_next,
-		.seq_stop = slab_stop,
+		.seq_start = memcg_slab_start,
+		.seq_next = memcg_slab_next,
+		.seq_stop = memcg_slab_stop,
 		.seq_show = memcg_slab_show,
 	},
 #endif
diff --git a/mm/slab.h b/mm/slab.h
index 3ed3336883ed..a08f01016a3f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -494,6 +494,9 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
+void *memcg_slab_start(struct seq_file *m, loff_t *pos);
+void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
+void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index c3885032dbce..c3bbeddaeaaf 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -154,6 +154,7 @@ static int init_memcg_params(struct kmem_cache *s,
 		s->memcg_params.root_cache = root_cache;
 		s->memcg_params.memcg = memcg;
 		INIT_LIST_HEAD(&s->memcg_params.children_node);
+		INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
 		return 0;
 	}
 
@@ -224,6 +225,7 @@ int memcg_update_all_caches(int num_memcgs)
 static void unlink_memcg_cache(struct kmem_cache *s)
 {
 	list_del(&s->memcg_params.children_node);
+	list_del(&s->memcg_params.kmem_caches_node);
 }
 #else
 static inline int init_memcg_params(struct kmem_cache *s,
@@ -596,6 +598,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 
 	list_add(&s->memcg_params.children_node,
 		 &root_cache->memcg_params.children);
+	list_add(&s->memcg_params.kmem_caches_node, &memcg->kmem_caches);
 
 	/*
 	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
@@ -651,9 +654,8 @@ void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 	get_online_mems();
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry_safe(s, s2, &slab_caches, list) {
-		if (is_root_cache(s) || s->memcg_params.memcg != memcg)
-			continue;
+	list_for_each_entry_safe(s, s2, &memcg->kmem_caches,
+				 memcg_params.kmem_caches_node) {
 		/*
 		 * The cgroup is about to be freed and therefore has no charges
 		 * left. Hence, all its caches must be empty by now.
@@ -1201,15 +1203,35 @@ static int slab_show(struct seq_file *m, void *p)
 }
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
+void *memcg_slab_start(struct seq_file *m, loff_t *pos)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	mutex_lock(&slab_mutex);
+	return seq_list_start(&memcg->kmem_caches, *pos);
+}
+
+void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	return seq_list_next(p, &memcg->kmem_caches, pos);
+}
+
+void memcg_slab_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&slab_mutex);
+}
+
 int memcg_slab_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct kmem_cache *s = list_entry(p, struct kmem_cache,
+					  memcg_params.kmem_caches_node);
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
 
-	if (p == slab_caches.next)
+	if (p == memcg->kmem_caches.next)
 		print_slabinfo_header(m);
-	if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
-		cache_show(s, m);
+	cache_show(s, m);
 	return 0;
 }
 #endif