mm: fix oom_kill event handling

commit fe6bdfc8e1e131720abbe77a2eb990c94c9024cb upstream.

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>
[fllinden@amazon.com: backport to 4.14, minor contextual changes]
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c7876eadd206dbdfde5290f433666a3c7a6ee1b7..b5cd86e320ff38a093293ecfd8e7e0b47481bb75 100644 (file)
--- 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_NR_MEMORY_EVENTS,
 };
 
@@ -706,11 +707,8 @@ 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();
 }
 
@@ -721,6 +719,21 @@ 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
@@ -742,6 +755,11 @@ 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 bool mem_cgroup_low(struct mem_cgroup *root,
                                  struct mem_cgroup *memcg)
 {

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 31972189a8274ac5afa3191f974afd2349ac8409..ef6d996a920aa4d726c7dee8fd328917902b11b2 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3648,7 +3648,8 @@ 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;
 }
 
@@ -5320,7 +5321,8 @@ 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 6482d743c5c88d3df2505a54383a7bb513d2321b..6f1bed2111226662a1342772db50c07f3d224029 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -917,7 +917,7 @@ 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