mm, oom: get rid of signal_struct::oom_victims
After "oom: keep mm of the killed task available" we can safely detect
an oom victim by checking task->signal->oom_mm so we do not need the
signal_struct counter anymore so let's get rid of it.
This alone wouldn't be sufficient for nommu archs because
exit_oom_victim doesn't hide the process from the oom killer anymore.
We can, however, mark the mm with a MMF flag in __mmput. We can reuse
MMF_OOM_REAPED and rename it to a more generic MMF_OOM_SKIP.
Link: http://lkml.kernel.org/r/1472119394-11342-6-git-send-email-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 17946e5..b61357d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -58,6 +58,11 @@
return p->signal->oom_flag_origin;
}
+static inline bool tsk_is_oom_victim(struct task_struct * tsk)
+{
+ return tsk->signal->oom_mm;
+}
+
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c4b5883..af07213 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -524,7 +524,7 @@
#define MMF_HAS_UPROBES 19 /* has uprobes */
#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */
-#define MMF_OOM_REAPED 21 /* mm has been already reaped */
+#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
@@ -672,7 +672,6 @@
atomic_t sigcnt;
atomic_t live;
int nr_threads;
- atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */
struct list_head thread_head;
wait_queue_head_t wait_chldexit; /* for wait4() */
diff --git a/kernel/fork.c b/kernel/fork.c
index 5650e35..9a8ec66 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -862,6 +862,7 @@
}
if (mm->binfmt)
module_put(mm->binfmt->module);
+ set_bit(MMF_OOM_SKIP, &mm->flags);
mmdrop(mm);
}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f16ec08..e2a2c35 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -186,7 +186,7 @@
*/
adj = (long)p->signal->oom_score_adj;
if (adj == OOM_SCORE_ADJ_MIN ||
- test_bit(MMF_OOM_REAPED, &p->mm->flags) ||
+ test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
in_vfork(p)) {
task_unlock(p);
return 0;
@@ -296,11 +296,11 @@
/*
* This task already has access to memory reserves and is being killed.
* Don't allow any other task to have access to the reserves unless
- * the task has MMF_OOM_REAPED because chances that it would release
+ * the task has MMF_OOM_SKIP because chances that it would release
* any memory is quite low.
*/
- if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) {
- if (test_bit(MMF_OOM_REAPED, &task->signal->oom_mm->flags))
+ if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
+ if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
goto next;
goto abort;
}
@@ -572,7 +572,7 @@
* 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_REAPED, &mm->flags);
+ set_bit(MMF_OOM_SKIP, &mm->flags);
/* Drop a reference taken by wake_oom_reaper */
put_task_struct(tsk);
@@ -654,8 +654,6 @@
if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
- atomic_inc(&tsk->signal->oom_victims);
-
/* oom_mm is bound to the signal struct life time. */
if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm))
atomic_inc(&tsk->signal->oom_mm->mm_count);
@@ -677,7 +675,6 @@
{
if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
- atomic_dec(&tsk->signal->oom_victims);
if (!atomic_dec_return(&oom_victims))
wake_up_all(&oom_victims_wait);
@@ -769,7 +766,7 @@
* This task has already been drained by the oom reaper so there are
* only small chances it will free some more
*/
- if (test_bit(MMF_OOM_REAPED, &mm->flags))
+ if (test_bit(MMF_OOM_SKIP, &mm->flags))
return false;
if (atomic_read(&mm->mm_users) <= 1)
@@ -906,7 +903,7 @@
* killer to guarantee OOM forward progress.
*/
can_oom_reap = false;
- set_bit(MMF_OOM_REAPED, &mm->flags);
+ set_bit(MMF_OOM_SKIP, &mm->flags);
pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
task_pid_nr(victim), victim->comm,
task_pid_nr(p), p->comm);
