[PATCH v2] mm: memcg/slab: fix memory leak at non-root kmem_cache destroy

[Muchun Song]

If the kmem_cache refcount is greater than one, we should not
mark the root kmem_cache as dying. If we mark the root kmem_cache
dying incorrectly, the non-root kmem_cache can never be destroyed.
It resulted in memory leak when memcg was destroyed. We can use the
following steps to reproduce.

  1) Use kmem_cache_create() to create a new kmem_cache named A.
  2) Coincidentally, the kmem_cache A is an alias for kmem_cache B,
     so the refcount of B is just increased.
  3) Use kmem_cache_destroy() to destroy the kmem_cache A, just
     decrease the B's refcount but mark the B as dying.
  4) Create a new memory cgroup and alloc memory from the kmem_cache
     B. It leads to create a non-root kmem_cache for allocating memory.
  5) When destroy the memory cgroup created in the step 4), the
     non-root kmem_cache can never be destroyed.

If we repeat steps 4) and 5), this will cause a lot of memory leak.
So only when refcount reach zero, we mark the root kmem_cache as dying.

Fixes: 92ee383f6daa ("mm: fix race between kmem_cache destroy, create and deactivate")
Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
---

changelog in v2:
 1) Fix a confusing typo in the commit log.
 2) Remove flush_memcg_workqueue() for !CONFIG_MEMCG_KMEM.
 3) Introduce a new helper memcg_set_kmem_cache_dying() to fix a race
    condition between flush_memcg_workqueue() and slab_unmergeable(). 

 mm/slab_common.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 47 insertions(+), 7 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8c1ffbf7de45..c4958116e3fd 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -258,6 +258,11 @@ static void memcg_unlink_cache(struct kmem_cache *s)
 		list_del(&s->memcg_params.kmem_caches_node);
 	}
 }
+
+static inline bool memcg_kmem_cache_dying(struct kmem_cache *s)
+{
+	return is_root_cache(s) && s->memcg_params.dying;
+}
 #else
 static inline int init_memcg_params(struct kmem_cache *s,
 				    struct kmem_cache *root_cache)
@@ -272,6 +277,11 @@ static inline void destroy_memcg_params(struct kmem_cache *s)
 static inline void memcg_unlink_cache(struct kmem_cache *s)
 {
 }
+
+static inline bool memcg_kmem_cache_dying(struct kmem_cache *s)
+{
+	return false;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 /*
@@ -326,6 +336,13 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (s->refcount < 0)
 		return 1;
 
+	/*
+	 * If the kmem_cache is dying. We should also skip this
+	 * kmem_cache.
+	 */
+	if (memcg_kmem_cache_dying(s))
+		return 1;
+
 	return 0;
 }
 
@@ -886,12 +903,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 	return 0;
 }
 
-static void flush_memcg_workqueue(struct kmem_cache *s)
+static void memcg_set_kmem_cache_dying(struct kmem_cache *s)
 {
 	spin_lock_irq(&memcg_kmem_wq_lock);
 	s->memcg_params.dying = true;
 	spin_unlock_irq(&memcg_kmem_wq_lock);
+}
 
+static void flush_memcg_workqueue(struct kmem_cache *s)
+{
 	/*
 	 * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
 	 * sure all registered rcu callbacks have been invoked.
@@ -923,10 +943,6 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	return 0;
 }
-
-static inline void flush_memcg_workqueue(struct kmem_cache *s)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
@@ -944,8 +960,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
-	flush_memcg_workqueue(s);
-
 	get_online_cpus();
 	get_online_mems();
 
@@ -955,6 +969,32 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
+#ifdef CONFIG_MEMCG_KMEM
+	memcg_set_kmem_cache_dying(s);
+
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+
+	flush_memcg_workqueue(s);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+
+	if (WARN(s->refcount,
+		 "kmem_cache_destroy %s: Slab cache is still referenced\n",
+		 s->name)) {
+		/*
+		 * Reset the dying flag setted by memcg_set_kmem_cache_dying().
+		 */
+		s->memcg_params.dying = false;
+		goto out_unlock;
+	}
+#endif
+
 	err = shutdown_memcg_caches(s);
 	if (!err)
 		err = shutdown_cache(s);
-- 
2.11.0