mm: fix race between kmem_cache destroy, create and deactivate

The memcg kmem cache creation and deactivation (SLUB only) is
asynchronous.  If a root kmem cache is destroyed whose memcg cache is in
the process of creation or deactivation, the kernel may crash.

Example of one such crash:
	general protection fault: 0000 [#1] SMP PTI
	CPU: 1 PID: 1721 Comm: kworker/14:1 Not tainted 4.17.0-smp
	...
	Workqueue: memcg_kmem_cache kmemcg_deactivate_workfn
	RIP: 0010:has_cpu_slab
	...
	Call Trace:
	? on_each_cpu_cond
	__kmem_cache_shrink
	kmemcg_cache_deact_after_rcu
	kmemcg_deactivate_workfn
	process_one_work
	worker_thread
	kthread
	ret_from_fork+0x35/0x40

To fix this race, on root kmem cache destruction, mark the cache as
dying and flush the workqueue used for memcg kmem cache creation and
deactivation.  SLUB's memcg kmem cache deactivation also includes RCU
callback and thus make sure all previous registered RCU callbacks have
completed as well.

[shakeelb@google.com: handle the RCU callbacks for SLUB deactivation]
  Link: http://lkml.kernel.org/r/20180611192951.195727-1-shakeelb@google.com
[shakeelb@google.com: add more documentation, rename fields for readability]
  Link: http://lkml.kernel.org/r/20180522201336.196994-1-shakeelb@google.com
[akpm@linux-foundation.org: fix build, per Shakeel]
[shakeelb@google.com: v3.  Instead of refcount, flush the workqueue]
  Link: http://lkml.kernel.org/r/20180530001204.183758-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180521174116.171846-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Greg Thelen <gthelen@google.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>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 33 insertions, 1 deletions

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 4d759e1..14e3fe4 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -600,6 +600,7 @@ struct memcg_cache_params {
 			struct memcg_cache_array __rcu *memcg_caches;
 			struct list_head __root_caches_node;
 			struct list_head children;
+			bool dying;
 		};
 		struct {
 			struct mem_cgroup *memcg;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 98dcdc3..42aca26 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -136,6 +136,7 @@ void slab_init_memcg_params(struct kmem_cache *s)
 	s->memcg_params.root_cache = NULL;
 	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
 	INIT_LIST_HEAD(&s->memcg_params.children);
+	s->memcg_params.dying = false;
 }
 
 static int init_memcg_params(struct kmem_cache *s,
@@ -608,7 +609,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	 * The memory cgroup could have been offlined while the cache
 	 * creation work was pending.
 	 */
-	if (memcg->kmem_state != KMEM_ONLINE)
+	if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
 		goto out_unlock;
 
 	idx = memcg_cache_id(memcg);
@@ -712,6 +713,9 @@ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
 	    WARN_ON_ONCE(s->memcg_params.deact_fn))
 		return;
 
+	if (s->memcg_params.root_cache->memcg_params.dying)
+		return;
+
 	/* pin memcg so that @s doesn't get destroyed in the middle */
 	css_get(&s->memcg_params.memcg->css);
 
@@ -823,11 +827,36 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 		return -EBUSY;
 	return 0;
 }
+
+static void flush_memcg_workqueue(struct kmem_cache *s)
+{
+	mutex_lock(&slab_mutex);
+	s->memcg_params.dying = true;
+	mutex_unlock(&slab_mutex);
+
+	/*
+	 * SLUB deactivates the kmem_caches through call_rcu_sched. Make
+	 * sure all registered rcu callbacks have been invoked.
+	 */
+	if (IS_ENABLED(CONFIG_SLUB))
+		rcu_barrier_sched();
+
+	/*
+	 * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
+	 * deactivates the memcg kmem_caches through workqueue. Make sure all
+	 * previous workitems on workqueue are processed.
+	 */
+	flush_workqueue(memcg_kmem_cache_wq);
+}
 #else
 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 && !CONFIG_SLOB */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
@@ -845,6 +874,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
+	flush_memcg_workqueue(s);
+
 	get_online_cpus();
 	get_online_mems();