mm: fix oom_kill event handling

Commit e27be240df53 ("mm: memcg: make sure memory.events is uptodate
when waking pollers") converted most of memcg event counters to
per-memcg atomics, which made them less confusing for a user.  The
"oom_kill" counter remained untouched, so now it behaves differently
than other counters (including "oom").  This adds nothing but confusion.

Let's fix this by adding the MEMCG_OOM_KILL event, and follow the
MEMCG_OOM approach.

This also removes a hack from count_memcg_event_mm(), introduced earlier
specially for the OOM_KILL counter.

[akpm@linux-foundation.org: fix for droppage of memcg-replace-mm-owner-with-mm-memcg.patch]
Link: http://lkml.kernel.org/r/20180508124637.29984-1-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 27 insertions, 7 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4f52ec755725..6c6fb116e925 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -53,6 +53,7 @@ enum memcg_memory_event {
 	MEMCG_HIGH,
 	MEMCG_MAX,
 	MEMCG_OOM,
+	MEMCG_OOM_KILL,
 	MEMCG_SWAP_MAX,
 	MEMCG_SWAP_FAIL,
 	MEMCG_NR_MEMORY_EVENTS,
@@ -720,11 +721,8 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (likely(memcg)) {
+	if (likely(memcg))
 		count_memcg_events(memcg, idx, 1);
-		if (idx == OOM_KILL)
-			cgroup_file_notify(&memcg->events_file);
-	}
 	rcu_read_unlock();
 }
 
@@ -735,6 +733,21 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 	cgroup_file_notify(&memcg->events_file);
 }
 
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+					 enum memcg_memory_event event)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (likely(memcg))
+		memcg_memory_event(memcg, event);
+	rcu_read_unlock();
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
@@ -756,6 +769,11 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 {
 }
 
+static inline void memcg_memory_event_mm(struct mm_struct *mm,
+					 enum memcg_memory_event event)
+{
+}
+
 static inline enum mem_cgroup_protection mem_cgroup_protected(
 	struct mem_cgroup *root, struct mem_cgroup *memcg)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5a3873e9d657..e6f0d5ef320a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3550,7 +3550,8 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
 
 	seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
 	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
-	seq_printf(sf, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL));
+	seq_printf(sf, "oom_kill %lu\n",
+		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
 	return 0;
 }
 
@@ -5239,7 +5240,8 @@ static int memory_events_show(struct seq_file *m, void *v)
 		   atomic_long_read(&memcg->memory_events[MEMCG_MAX]));
 	seq_printf(m, "oom %lu\n",
 		   atomic_long_read(&memcg->memory_events[MEMCG_OOM]));
-	seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL));
+	seq_printf(m, "oom_kill %lu\n",
+		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
 
 	return 0;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6694348b27e9..84081e77bc51 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -913,7 +913,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 
 	/* Raise event before sending signal: task reaper must see this */
 	count_vm_event(OOM_KILL);
-	count_memcg_event_mm(mm, OOM_KILL);
+	memcg_memory_event_mm(mm, MEMCG_OOM_KILL);
 
 	/*
 	 * We should send SIGKILL before granting access to memory reserves