[PATCH] oom, oom_reaper: do not enqueue same task twice

[Tetsuo Handa]

Arkadiusz reported that enabling memcg's group oom killing causes
strange memcg statistics where there is no task in a memcg despite
the number of tasks in that memcg is not 0. It turned out that there
is a bug in wake_oom_reaper() which allows enqueuing same task twice
which makes impossible to decrease the number of tasks in that memcg
due to a refcount leak.

This bug existed since the OOM reaper became invokable from
task_will_free_mem(current) path in out_of_memory() in Linux 4.7,
but memcg's group oom killing made it easier to trigger this bug by
calling wake_oom_reaper() on the same task from one out_of_memory()
request.

Fix this bug using an approach used by commit 855b018325737f76
("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task").
Since task_will_free_mem(p) == false if p->mm == NULL, we can assume that
p->mm != NULL when wake_oom_reaper() is called from task_will_free_mem()
paths. As a side effect of this patch, this patch also avoids enqueuing
multiple threads sharing memory via task_will_free_mem(current) path.

Signed-off-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Reported-by: Arkadiusz MiÅ?kiewicz <a.miskiewicz@xxxxxxxxx>
Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head")
---
 mm/oom_kill.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f0e8cd9..457f240 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -505,14 +505,6 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	bool ret = true;
 
-	/*
-	 * Tell all users of get_user/copy_from_user etc... that the content
-	 * is no longer stable. No barriers really needed because unmapping
-	 * should imply barriers already and the reader would hit a page fault
-	 * if it stumbled over a reaped memory.
-	 */
-	set_bit(MMF_UNSTABLE, &mm->flags);
-
 	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
 		if (!can_madv_dontneed_vma(vma))
 			continue;
@@ -645,10 +637,15 @@ static int oom_reaper(void *unused)
 	return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct task_struct *tsk, struct mm_struct *mm)
 {
-	/* tsk is already queued? */
-	if (tsk == oom_reaper_list || tsk->oom_reaper_list)
+	/*
+	 * Tell all users of get_user/copy_from_user etc... that the content
+	 * is no longer stable. No barriers really needed because unmapping
+	 * should imply barriers already and the reader would hit a page fault
+	 * if it stumbled over a reaped memory.
+	 */
+	if (test_and_set_bit(MMF_UNSTABLE, &mm->flags))
 		return;
 
 	get_task_struct(tsk);
@@ -668,7 +665,8 @@ static int __init oom_init(void)
 }
 subsys_initcall(oom_init)
 #else
-static inline void wake_oom_reaper(struct task_struct *tsk)
+static inline void wake_oom_reaper(struct task_struct *tsk,
+				   struct mm_struct *mm)
 {
 }
 #endif /* CONFIG_MMU */
@@ -915,7 +913,7 @@ static void __oom_kill_process(struct task_struct *victim)
 	rcu_read_unlock();
 
 	if (can_oom_reap)
-		wake_oom_reaper(victim);
+		wake_oom_reaper(victim, mm);
 
 	mmdrop(mm);
 	put_task_struct(victim);
@@ -955,7 +953,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	task_lock(p);
 	if (task_will_free_mem(p)) {
 		mark_oom_victim(p);
-		wake_oom_reaper(p);
+		wake_oom_reaper(p, p->mm);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -1085,7 +1083,7 @@ bool out_of_memory(struct oom_control *oc)
 	 */
 	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		wake_oom_reaper(current);
+		wake_oom_reaper(current, current->mm);
 		return true;
 	}
 
-- 
1.8.3.1