memcg: add rwsem to synchronize against memcg_caches arrays relocation

We need a stable value of memcg_nr_cache_ids in kmem_cache_create()
(memcg_alloc_cache_params() wants it for root caches), where we only
hold the slab_mutex and no memcg-related locks.  As a result, we have to
update memcg_nr_cache_ids under the slab_mutex, which we can only take
on the slab's side (see memcg_update_array_size).  This looks awkward
and will become even worse when per-memcg list_lru is introduced, which
also wants stable access to memcg_nr_cache_ids.

To get rid of this dependency between the memcg_nr_cache_ids and the
slab_mutex, this patch introduces a special rwsem.  The rwsem is held
for writing during memcg_caches arrays relocation and memcg_nr_cache_ids
updates.  Therefore one can take it for reading to get a stable access
to memcg_caches arrays and/or memcg_nr_cache_ids.

Currently the semaphore is taken for reading only from
kmem_cache_create, right before taking the slab_mutex, so right now
there's no much point in using rwsem instead of mutex.  However, once
list_lru is made per-memcg it will allow list_lru initializations to
proceed concurrently.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
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: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 33 insertions, 17 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2607c91230af..dbc4baa3619c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -399,6 +399,8 @@ static inline void sock_release_memcg(struct sock *sk)
 extern struct static_key memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
+extern void memcg_get_cache_ids(void);
+extern void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
@@ -434,8 +436,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-void memcg_update_array_size(int num_groups);
-
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
@@ -569,6 +569,14 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
+static inline void memcg_get_cache_ids(void)
+{
+}
+
+static inline void memcg_put_cache_ids(void)
+{
+}
+
 static inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8608fa543b84..6706e5fa5ac0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -544,6 +544,19 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 static DEFINE_IDA(memcg_cache_ida);
 int memcg_nr_cache_ids;
 
+/* Protects memcg_nr_cache_ids */
+static DECLARE_RWSEM(memcg_cache_ids_sem);
+
+void memcg_get_cache_ids(void)
+{
+	down_read(&memcg_cache_ids_sem);
+}
+
+void memcg_put_cache_ids(void)
+{
+	up_read(&memcg_cache_ids_sem);
+}
+
 /*
  * MIN_SIZE is different than 1, because we would like to avoid going through
  * the alloc/free process all the time. In a small machine, 4 kmem-limited
@@ -2549,6 +2562,7 @@ static int memcg_alloc_cache_id(void)
 	 * There's no space for the new id in memcg_caches arrays,
 	 * so we have to grow them.
 	 */
+	down_write(&memcg_cache_ids_sem);
 
 	size = 2 * (id + 1);
 	if (size < MEMCG_CACHES_MIN_SIZE)
@@ -2557,6 +2571,11 @@ static int memcg_alloc_cache_id(void)
 		size = MEMCG_CACHES_MAX_SIZE;
 
 	err = memcg_update_all_caches(size);
+	if (!err)
+		memcg_nr_cache_ids = size;
+
+	up_write(&memcg_cache_ids_sem);
+
 	if (err) {
 		ida_simple_remove(&memcg_cache_ida, id);
 		return err;
@@ -2569,16 +2588,6 @@ static void memcg_free_cache_id(int id)
 	ida_simple_remove(&memcg_cache_ida, id);
 }
 
-/*
- * We should update the current array size iff all caches updates succeed. This
- * can only be done from the slab side. The slab mutex needs to be held when
- * calling this.
- */
-void memcg_update_array_size(int num)
-{
-	memcg_nr_cache_ids = num;
-}
-
 struct memcg_kmem_cache_create_work {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *cachep;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f8899eedab68..23f5fcde6043 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -169,8 +169,8 @@ int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
 	int ret = 0;
-	mutex_lock(&slab_mutex);
 
+	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
 		if (!is_root_cache(s))
 			continue;
@@ -181,11 +181,8 @@ int memcg_update_all_caches(int num_memcgs)
 		 * up to this point in an updated state.
 		 */
 		if (ret)
-			goto out;
+			break;
 	}
-
-	memcg_update_array_size(num_memcgs);
-out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
@@ -369,6 +366,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 
 	get_online_cpus();
 	get_online_mems();
+	memcg_get_cache_ids();
 
 	mutex_lock(&slab_mutex);
 
@@ -407,6 +405,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
+	memcg_put_cache_ids();
 	put_online_mems();
 	put_online_cpus();