From d87ddcdb2daab79085efe71a8f547aebb5ca9b05 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 23 Jul 2020 21:15:27 -0700 Subject: [PATCH] mm: memcg/slab: fix memory leak at non-root kmem_cache destroy commit d38a2b7a9c939e6d7329ab92b96559ccebf7b135 upstream. 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 Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Vlastimil Babka Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Shakeel Butt Cc: Link: http://lkml.kernel.org/r/20200716165103.83462-1-songmuchun@bytedance.com Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- mm/slab_common.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index 3dbf693527dd..a94b9981eb17 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -311,6 +311,14 @@ int slab_unmergeable(struct kmem_cache *s) if (s->refcount < 0) return 1; +#ifdef CONFIG_MEMCG_KMEM + /* + * Skip the dying kmem_cache. + */ + if (s->memcg_params.dying) + return 1; +#endif + return 0; } @@ -841,12 +849,15 @@ 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) +{ /* * SLUB deactivates the kmem_caches through call_rcu_sched. Make * sure all registered rcu callbacks have been invoked. @@ -867,10 +878,6 @@ 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) @@ -888,8 +895,6 @@ void kmem_cache_destroy(struct kmem_cache *s) if (unlikely(!s)) return; - flush_memcg_workqueue(s); - get_online_cpus(); get_online_mems(); @@ -899,6 +904,22 @@ 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); +#endif + err = shutdown_memcg_caches(s); if (!err) err = shutdown_cache(s);