oom: task->mm == NULL doesn't mean the memory was freed

exit_mm() sets ->mm == NULL then it does mmput()->exit_mmap() which
frees the memory.

However select_bad_process() checks ->mm != NULL before TIF_MEMDIE,
so it continues to kill other tasks even if we have the oom-killed
task freeing its memory.

Change select_bad_process() to check ->mm after TIF_MEMDIE, but skip
the tasks which have already passed exit_notify() to ensure a zombie
with TIF_MEMDIE set can't block oom-killer. Alternatively we could
probably clear TIF_MEMDIE after exit_mmap().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Oleg Nesterov 2011-07-30 16:35:02 +02:00 committed by Linus Torvalds
parent cfe22345ad
commit c027a474a6

View File

@ -303,7 +303,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
do_each_thread(g, p) { do_each_thread(g, p) {
unsigned int points; unsigned int points;
if (!p->mm) if (p->exit_state)
continue; continue;
if (oom_unkillable_task(p, mem, nodemask)) if (oom_unkillable_task(p, mem, nodemask))
continue; continue;
@ -319,6 +319,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
*/ */
if (test_tsk_thread_flag(p, TIF_MEMDIE)) if (test_tsk_thread_flag(p, TIF_MEMDIE))
return ERR_PTR(-1UL); return ERR_PTR(-1UL);
if (!p->mm)
continue;
if (p->flags & PF_EXITING) { if (p->flags & PF_EXITING) {
/* /*