memcg: convert mem_cgroup->under_oom from atomic_t to int

memcg->under_oom tracks whether the memcg is under OOM conditions and is
an atomic_t counter managed with mem_cgroup_[un]mark_under_oom().  While
atomic_t appears to be simple synchronization-wise, when used as a
synchronization construct like here, it's trickier and more error-prone
due to weak memory ordering rules, especially around atomic_read(), and
false sense of security.

For example, both non-trivial read sites of memcg->under_oom are a bit
problematic although not being actually broken.

* mem_cgroup_oom_register_event()

  It isn't explicit what guarantees the memory ordering between event
  addition and memcg->under_oom check.  This isn't broken only because
  memcg_oom_lock is used for both event list and memcg->oom_lock.

* memcg_oom_recover()

  The lockless test doesn't have any explanation why this would be
  safe.

mem_cgroup_[un]mark_under_oom() are very cold paths and there's no point
in avoiding locking memcg_oom_lock there.  This patch converts
memcg->under_oom from atomic_t to int, puts their modifications under
memcg_oom_lock and documents why the lockless test in
memcg_oom_recover() is safe.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 21 insertions, 8 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6a5f5d59f7d7..e65f7b0131d3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -285,8 +285,9 @@ struct mem_cgroup {
 	 */
 	bool use_hierarchy;
 
+	/* protected by memcg_oom_lock */
 	bool		oom_lock;
-	atomic_t	under_oom;
+	int		under_oom;
 
 	int	swappiness;
 	/* OOM-Killer disable */
@@ -1809,8 +1810,10 @@ static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *iter;
 
+	spin_lock(&memcg_oom_lock);
 	for_each_mem_cgroup_tree(iter, memcg)
-		atomic_inc(&iter->under_oom);
+		iter->under_oom++;
+	spin_unlock(&memcg_oom_lock);
 }
 
 static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
@@ -1819,11 +1822,13 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
 
 	/*
 	 * When a new child is created while the hierarchy is under oom,
-	 * mem_cgroup_oom_lock() may not be called. We have to use
-	 * atomic_add_unless() here.
+	 * mem_cgroup_oom_lock() may not be called. Watch for underflow.
 	 */
+	spin_lock(&memcg_oom_lock);
 	for_each_mem_cgroup_tree(iter, memcg)
-		atomic_add_unless(&iter->under_oom, -1, 0);
+		if (iter->under_oom > 0)
+			iter->under_oom--;
+	spin_unlock(&memcg_oom_lock);
 }
 
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
@@ -1851,7 +1856,15 @@ static int memcg_oom_wake_function(wait_queue_t *wait,
 
 static void memcg_oom_recover(struct mem_cgroup *memcg)
 {
-	if (memcg && atomic_read(&memcg->under_oom))
+	/*
+	 * For the following lockless ->under_oom test, the only required
+	 * guarantee is that it must see the state asserted by an OOM when
+	 * this function is called as a result of userland actions
+	 * triggered by the notification of the OOM.  This is trivially
+	 * achieved by invoking mem_cgroup_mark_under_oom() before
+	 * triggering notification.
+	 */
+	if (memcg && memcg->under_oom)
 		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
 }
 
@@ -3860,7 +3873,7 @@ static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
 	list_add(&event->list, &memcg->oom_notify);
 
 	/* already in OOM ? */
-	if (atomic_read(&memcg->under_oom))
+	if (memcg->under_oom)
 		eventfd_signal(eventfd, 1);
 	spin_unlock(&memcg_oom_lock);
 
@@ -3889,7 +3902,7 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf));
 
 	seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
-	seq_printf(sf, "under_oom %d\n", (bool)atomic_read(&memcg->under_oom));
+	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
 	return 0;
 }