memcg: free mem_cgroup by RCU to fix oops

After fixing the GPF in mem_cgroup_lru_del_list(), three times one
machine running a similar load (moving and removing memcgs while
swapping) has oopsed in mem_cgroup_zone_nr_lru_pages(), when retrieving
memcg zone numbers for get_scan_count() for shrink_mem_cgroup_zone():
this is where a struct mem_cgroup is first accessed after being chosen
by mem_cgroup_iter().

Just what protects a struct mem_cgroup from being freed, in between
mem_cgroup_iter()'s css_get_next() and its css_tryget()? css_tryget()
fails once css->refcnt is zero with CSS_REMOVED set in flags, yes: but
what if that memory is freed and reused for something else, which sets
"refcnt" non-zero? Hmm, and scope for an indefinite freeze if refcnt is
left at zero but flags are cleared.

It's tempting to move the css_tryget() into css_get_next(), to make it
really "get" the css, but I don't think that actually solves anything:
the same difficulty in moving from css_id found to stable css remains.

But we already have rcu_read_lock() around the two, so it's easily fixed
if __mem_cgroup_free() just uses kfree_rcu() to free mem_cgroup.

However, a big struct mem_cgroup is allocated with vzalloc() instead of
kzalloc(), and we're not allowed to vfree() at interrupt time: there
doesn't appear to be a general vfree_rcu() to help with this, so roll
our own using schedule_work().  The compiler decently removes
vfree_work() and vfree_rcu() when the config doesn't need them.

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 47 insertions, 6 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d0e57a3cda18..58a08fc7414a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -230,10 +230,30 @@ struct mem_cgroup {
          * the counter to account for memory usage
          */
         struct res_counter res;
-        /*
-         * the counter to account for mem+swap usage.
-         */
-        struct res_counter memsw;
+
+        union {
+                /*
+                 * the counter to account for mem+swap usage.
+                 */
+                struct res_counter memsw;
+
+                /*
+                 * rcu_freeing is used only when freeing struct mem_cgroup,
+                 * so put it into a union to avoid wasting more memory.
+                 * It must be disjoint from the css field.  It could be
+                 * in a union with the res field, but res plays a much
+                 * larger part in mem_cgroup life than memsw, and might
+                 * be of interest, even at time of free, when debugging.
+                 * So share rcu_head with the less interesting memsw.
+                 */
+                struct rcu_head rcu_freeing;
+                /*
+                 * But when using vfree(), that cannot be done at
+                 * interrupt time, so we must then queue the work.
+                 */
+                struct work_struct work_freeing;
+        };
+
         /*
          * Per cgroup active and inactive list, similar to the
          * per zone LRU lists.
@@ -4780,6 +4800,27 @@ out_free:
 }
 
 /*
+ * Helpers for freeing a vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
+ */
+static void vfree_work(struct work_struct *work)
+{
+        struct mem_cgroup *memcg;
+
+        memcg = container_of(work, struct mem_cgroup, work_freeing);
+        vfree(memcg);
+}
+static void vfree_rcu(struct rcu_head *rcu_head)
+{
+        struct mem_cgroup *memcg;
+
+        memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+        INIT_WORK(&memcg->work_freeing, vfree_work);
+        schedule_work(&memcg->work_freeing);
+}
+
+/*
  * At destroying mem_cgroup, references from swap_cgroup can remain.
  * (scanning all at force_empty is too costly...)
  *
@@ -4802,9 +4843,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
         free_percpu(memcg->stat);
         if (sizeof(struct mem_cgroup) < PAGE_SIZE)
-                kfree(memcg);
+                kfree_rcu(memcg, rcu_freeing);
         else
-                vfree(memcg);
+                call_rcu(&memcg->rcu_freeing, vfree_rcu);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)