If mm->mm_users is not incremented because it is already zero by the oom
reaper, meaning the final refcount has been dropped, do not set
MMF_OOM_SKIP prematurely.
__mmput() may not have had a chance to do exit_mmap() yet, so memory from
a previous oom victim is still mapped. __mput() naturally requires no
references on mm->mm_users to do exit_mmap().
Without this, several processes can be oom killed unnecessarily and the
oom log can show an abundance of memory available if exit_mmap() is in
progress at the time the process is skipped.
Signed-off-by: David Rientjes <rient...@google.com>
---
mm/oom_kill.c | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -531,6 +531,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk,
struct mm_struct *mm)
NULL);
}
tlb_finish_mmu(&tlb, 0, -1);
+ set_bit(MMF_OOM_SKIP, &mm->flags);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB,
file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -562,7 +563,11 @@ static void oom_reap_task(struct task_struct *tsk)
if (attempts <= MAX_OOM_REAP_RETRIES)
goto done;
-
+ /*
+ * Hide this mm from OOM killer because it cannot be reaped since
+ * mm->mmap_sem cannot be acquired.
+ */
+ set_bit(MMF_OOM_SKIP, &mm->flags);
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
@@ -570,12 +575,6 @@ static void oom_reap_task(struct task_struct *tsk)
done:
tsk->oom_reaper_list = NULL;
- /*
- * Hide this mm from OOM killer because it has been either reaped or
- * somebody can't call up_write(mmap_sem).
- */
- set_bit(MMF_OOM_SKIP, &mm->flags);
-
/* Drop a reference taken by wake_oom_reaper */
put_task_struct(tsk);
}
