Merge remote-tracking branch 'stable/linux-5.15.y' into rpi-5.15.y

[platform/kernel/linux-rpi.git] / mm / oom_kill.c

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bfa9e34..262f752 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -635,7 +635,7 @@ done:
         */
        set_bit(MMF_OOM_SKIP, &mm->flags);
 
-       /* Drop a reference taken by wake_oom_reaper */
+       /* Drop a reference taken by queue_oom_reaper */
        put_task_struct(tsk);
 }
 
@@ -645,12 +645,12 @@ static int oom_reaper(void *unused)
                struct task_struct *tsk = NULL;
 
                wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
-               spin_lock(&oom_reaper_lock);
+               spin_lock_irq(&oom_reaper_lock);
                if (oom_reaper_list != NULL) {
                        tsk = oom_reaper_list;
                        oom_reaper_list = tsk->oom_reaper_list;
                }
-               spin_unlock(&oom_reaper_lock);
+               spin_unlock_irq(&oom_reaper_lock);
 
                if (tsk)
                        oom_reap_task(tsk);
@@ -659,22 +659,48 @@ static int oom_reaper(void *unused)
        return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct timer_list *timer)
 {
-       /* mm is already queued? */
-       if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
-               return;
+       struct task_struct *tsk = container_of(timer, struct task_struct,
+                       oom_reaper_timer);
+       struct mm_struct *mm = tsk->signal->oom_mm;
+       unsigned long flags;
 
-       get_task_struct(tsk);
+       /* The victim managed to terminate on its own - see exit_mmap */
+       if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
+               put_task_struct(tsk);
+               return;
+       }
 
-       spin_lock(&oom_reaper_lock);
+       spin_lock_irqsave(&oom_reaper_lock, flags);
        tsk->oom_reaper_list = oom_reaper_list;
        oom_reaper_list = tsk;
-       spin_unlock(&oom_reaper_lock);
+       spin_unlock_irqrestore(&oom_reaper_lock, flags);
        trace_wake_reaper(tsk->pid);
        wake_up(&oom_reaper_wait);
 }
 
+/*
+ * Give the OOM victim time to exit naturally before invoking the oom_reaping.
+ * The timers timeout is arbitrary... the longer it is, the longer the worst
+ * case scenario for the OOM can take. If it is too small, the oom_reaper can
+ * get in the way and release resources needed by the process exit path.
+ * e.g. The futex robust list can sit in Anon|Private memory that gets reaped
+ * before the exit path is able to wake the futex waiters.
+ */
+#define OOM_REAPER_DELAY (2*HZ)
+static void queue_oom_reaper(struct task_struct *tsk)
+{
+       /* mm is already queued? */
+       if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
+               return;
+
+       get_task_struct(tsk);
+       timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0);
+       tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY;
+       add_timer(&tsk->oom_reaper_timer);
+}
+
 static int __init oom_init(void)
 {
        oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -682,7 +708,7 @@ static int __init oom_init(void)
 }
 subsys_initcall(oom_init)
 #else
-static inline void wake_oom_reaper(struct task_struct *tsk)
+static inline void queue_oom_reaper(struct task_struct *tsk)
 {
 }
 #endif /* CONFIG_MMU */
@@ -933,7 +959,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
        rcu_read_unlock();
 
        if (can_oom_reap)
-               wake_oom_reaper(victim);
+               queue_oom_reaper(victim);
 
        mmdrop(mm);
        put_task_struct(victim);
@@ -969,7 +995,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
        task_lock(victim);
        if (task_will_free_mem(victim)) {
                mark_oom_victim(victim);
-               wake_oom_reaper(victim);
+               queue_oom_reaper(victim);
                task_unlock(victim);
                put_task_struct(victim);
                return;
@@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *oc)
         */
        if (task_will_free_mem(current)) {
                mark_oom_victim(current);
-               wake_oom_reaper(current);
+               queue_oom_reaper(current);
                return true;
        }