The MMF_OOM_SKIP bit is used to indicate weather a mm_struct can not be
invalided or has already been invalided. exit_mmap currently calls
__oom_reap_task_mm unconditionally despite the fact that the oom reaper
may have already called this.
Add a check for the MMF_OOM_SKIP bit being set in exit_mmap to avoid
unnessary calls to the invalidate code.
A slight race can occur on the MMF_OOM_SKIP bit that will still allow
this to run twice. My testing has shown an ~66% decrease in double calls
to _oom_reap_task_mm.
Fixes: 27ae357fa82b ("mm, oom: fix concurrent munlock and oom reaper unmap, v3")
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Signed-off-by: Nico Pache <npache@xxxxxxxxxx>
---
mm/mmap.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index a2968669fd4e..b867f408dacd 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3113,7 +3113,8 @@ void exit_mmap(struct mm_struct *mm)
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
- if (unlikely(mm_is_oom_victim(mm))) {
+ if (unlikely(mm_is_oom_victim(mm)) &&
+ !test_bit(MMF_OOM_SKIP, &mm->flags)) {
/*
* Manually reap the mm to free as much memory as possible.
* Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
--
2.35.1
