[PATCH] oom, oom_reaper: Try to reap tasks which skip regular OOM killer path

[Michal Hocko]

If either the current task is already killed or PF_EXITING or a selected
task is PF_EXITING then the oom killer is suppressed and so is the oom
reaper. This patch adds try_oom_reaper which checks the given task
and queues it for the oom reaper if that is safe to be done meaning
that the task doesn't share the mm with an alive process.

This might help to release the memory pressure while the task tries to
exit.

Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>
---
 mm/oom_kill.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 64 insertions(+), 18 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1c2b7a82f0c4..2f637728b12a 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -412,6 +412,25 @@ bool oom_killer_disabled __read_mostly;
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 
+/*
+ * task->mm can be NULL if the task is the exited group leader.  So to
+ * determine whether the task is using a particular mm, we examine all the
+ * task's threads: if one of those is using this mm then this task was also
+ * using it.
+ */
+static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
+{
+	struct task_struct *t;
+
+	for_each_thread(p, t) {
+		struct mm_struct *t_mm = READ_ONCE(t->mm);
+		if (t_mm)
+			return t_mm == mm;
+	}
+	return false;
+}
+
+
 #ifdef CONFIG_MMU
 /*
  * OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -563,6 +582,45 @@ static void wake_oom_reaper(struct task_struct *tsk)
 	wake_up(&oom_reaper_wait);
 }
 
+/* Check if we can reap the given task. This has to be called with stable
+ * tsk->mm
+ */
+static void try_oom_reaper(struct task_struct *tsk)
+{
+	struct mm_struct *mm = tsk->mm;
+	bool can_oom_reap = true;
+	struct task_struct *p;
+
+	if (!mm)
+		return;
+
+	/*
+	 * There might be other threads/processes which are either not
+	 * dying or even not killable.
+	 */
+	if (atomic_read(&mm->mm_users) > 1) {
+		rcu_read_lock();
+		for_each_process(p) {
+			if (!process_shares_mm(p, mm))
+				continue;
+			if (same_thread_group(p, tsk))
+				continue;
+			/*
+			 * other process sharing the mm is not dying so we cannot
+			 * simply reap the address space.
+			 */
+			if (!fatal_signal_pending(p) || !task_will_free_mem(p)) {
+				can_oom_reap = false;
+				break;
+			}
+		}
+		rcu_read_unlock();
+	}
+
+	if (can_oom_reap)
+		wake_oom_reaper(tsk);
+}
+
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -575,6 +633,10 @@ static int __init oom_init(void)
 }
 subsys_initcall(oom_init)
 #else
+static void try_oom_reaper(struct task_struct *tsk)
+{
+}
+
 static void wake_oom_reaper(struct task_struct *tsk)
 {
 }
@@ -653,24 +715,6 @@ void oom_killer_enable(void)
 }
 
 /*
- * task->mm can be NULL if the task is the exited group leader.  So to
- * determine whether the task is using a particular mm, we examine all the
- * task's threads: if one of those is using this mm then this task was also
- * using it.
- */
-static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
-{
-	struct task_struct *t;
-
-	for_each_thread(p, t) {
-		struct mm_struct *t_mm = READ_ONCE(t->mm);
-		if (t_mm)
-			return t_mm == mm;
-	}
-	return false;
-}
-
-/*
  * Must be called while holding a reference to p, which will be released upon
  * returning.
  */
@@ -694,6 +738,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	task_lock(p);
 	if (p->mm && task_will_free_mem(p)) {
 		mark_oom_victim(p);
+		try_oom_reaper(p);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -873,6 +918,7 @@ bool out_of_memory(struct oom_control *oc)
 	if (current->mm &&
 	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
 		mark_oom_victim(current);
+		try_oom_reaper(current);
 		return true;
 	}
 
-- 
2.7.0

-- 
Michal Hocko
SUSE Labs