memcg, slab: do not destroy children caches if parent has aliases

Currently we destroy children caches at the very beginning of
kmem_cache_destroy().  This is wrong, because the root cache will not
necessarily be destroyed in the end - if it has aliases (refcount > 0),
kmem_cache_destroy() will simply decrement its refcount and return.  In
this case, at best we will get a bunch of warnings in dmesg, like this
one:

  kmem_cache_destroy kmalloc-32:0: Slab cache still has objects
  CPU: 1 PID: 7139 Comm: modprobe Tainted: G    B   W    3.13.0+ #117
  Call Trace:
    dump_stack+0x49/0x5b
    kmem_cache_destroy+0xdf/0xf0
    kmem_cache_destroy_memcg_children+0x97/0xc0
    kmem_cache_destroy+0xf/0xf0
    xfs_mru_cache_uninit+0x21/0x30 [xfs]
    exit_xfs_fs+0x2e/0xc44 [xfs]
    SyS_delete_module+0x198/0x1f0
    system_call_fastpath+0x16/0x1b

At worst - if kmem_cache_destroy() will race with an allocation from a
memcg cache - the kernel will panic.

This patch fixes this by moving children caches destruction after the
check if the cache has aliases.  Plus, it forbids destroying a root
cache if it still has children caches, because each children cache keeps
a reference to its parent.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 57 insertions, 37 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 02d3072..b569b8b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -507,7 +507,7 @@ struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
 void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
-void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
+int __kmem_cache_destroy_memcg_children(struct kmem_cache *s);
 
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
@@ -661,10 +661,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	return cachep;
 }
-
-static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c22d8bf..29501f0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3321,15 +3321,10 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
 	schedule_work(&cachep->memcg_params->destroy);
 }
 
-void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+int __kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 {
 	struct kmem_cache *c;
-	int i;
-
-	if (!s->memcg_params)
-		return;
-	if (!s->memcg_params->is_root_cache)
-		return;
+	int i, failed = 0;
 
 	/*
 	 * If the cache is being destroyed, we trust that there is no one else
@@ -3363,8 +3358,12 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 		c->memcg_params->dead = false;
 		cancel_work_sync(&c->memcg_params->destroy);
 		kmem_cache_destroy(c);
+
+		if (cache_from_memcg_idx(s, i))
+			failed++;
 	}
 	mutex_unlock(&activate_kmem_mutex);
+	return failed;
 }
 
 static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0c2879ff..f3cfccf 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -301,39 +301,64 @@ out_unlock:
 	mutex_unlock(&slab_mutex);
 	put_online_cpus();
 }
+
+static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	int rc;
+
+	if (!s->memcg_params ||
+	    !s->memcg_params->is_root_cache)
+		return 0;
+
+	mutex_unlock(&slab_mutex);
+	rc = __kmem_cache_destroy_memcg_children(s);
+	mutex_lock(&slab_mutex);
+
+	return rc;
+}
+#else
+static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	return 0;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	/* Destroy all the children caches if we aren't a memcg cache */
-	kmem_cache_destroy_memcg_children(s);
-
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
+
 	s->refcount--;
-	if (!s->refcount) {
-		list_del(&s->list);
-		memcg_unregister_cache(s);
-
-		if (!__kmem_cache_shutdown(s)) {
-			mutex_unlock(&slab_mutex);
-			if (s->flags & SLAB_DESTROY_BY_RCU)
-				rcu_barrier();
-
-			memcg_free_cache_params(s);
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		} else {
-			list_add(&s->list, &slab_caches);
-			memcg_register_cache(s);
-			mutex_unlock(&slab_mutex);
-			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
-				s->name);
-			dump_stack();
-		}
-	} else {
-		mutex_unlock(&slab_mutex);
+	if (s->refcount)
+		goto out_unlock;
+
+	if (kmem_cache_destroy_memcg_children(s) != 0)
+		goto out_unlock;
+
+	list_del(&s->list);
+	memcg_unregister_cache(s);
+
+	if (__kmem_cache_shutdown(s) != 0) {
+		list_add(&s->list, &slab_caches);
+		memcg_register_cache(s);
+		printk(KERN_ERR "kmem_cache_destroy %s: "
+		       "Slab cache still has objects\n", s->name);
+		dump_stack();
+		goto out_unlock;
 	}
+
+	mutex_unlock(&slab_mutex);
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		rcu_barrier();
+
+	memcg_free_cache_params(s);
+	kfree(s->name);
+	kmem_cache_free(kmem_cache, s);
+	goto out_put_cpus;
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+out_put_cpus:
 	put_online_cpus();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);