From 03049269de433cb5fe2859be9ae4469ceb1163ed Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:33 -0700 Subject: [PATCH] mm, oom_reaper: implement OOM victims queuing wake_oom_reaper has allowed only 1 oom victim to be queued. The main reason for that was the simplicity as other solutions would require some way of queuing. The current approach is racy and that was deemed sufficient as the oom_reaper is considered a best effort approach to help with oom handling when the OOM victim cannot terminate in a reasonable time. The race could lead to missing an oom victim which can get stuck out_of_memory wake_oom_reaper cmpxchg // OK oom_reaper oom_reap_task __oom_reap_task oom_victim terminates atomic_inc_not_zero // fail out_of_memory wake_oom_reaper cmpxchg // fails task_to_reap = NULL This race requires 2 OOM invocations in a short time period which is not very likely but certainly not impossible. E.g. the original victim might have not released a lot of memory for some reason. The situation would improve considerably if wake_oom_reaper used a more robust queuing. This is what this patch implements. This means adding oom_reaper_list list_head into task_struct (eat a hole before embeded thread_struct for that purpose) and a oom_reaper_lock spinlock for queuing synchronization. wake_oom_reaper will then add the task on the queue and oom_reaper will dequeue it. Signed-off-by: Michal Hocko Cc: Vladimir Davydov Cc: Andrea Argangeli Cc: David Rientjes Cc: Hugh Dickins Cc: Johannes Weiner Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ mm/oom_kill.c | 36 +++++++++++++++++++----------------- 2 files changed, 22 insertions(+), 17 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 478b41de7f7d..788f223f8f8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1849,6 +1849,9 @@ struct task_struct { unsigned long task_state_change; #endif int pagefault_disabled; +#ifdef CONFIG_MMU + struct list_head oom_reaper_list; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 30a60991173a..f6d4ae9f1c69 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -418,8 +418,10 @@ bool oom_killer_disabled __read_mostly; * victim (if that is possible) to help the OOM killer to move on. */ static struct task_struct *oom_reaper_th; -static struct task_struct *task_to_reap; static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); +static LIST_HEAD(oom_reaper_list); +static DEFINE_SPINLOCK(oom_reaper_lock); + static bool __oom_reap_task(struct task_struct *tsk) { @@ -524,12 +526,20 @@ static void oom_reap_task(struct task_struct *tsk) static int oom_reaper(void *unused) { while (true) { - struct task_struct *tsk; + struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, - (tsk = READ_ONCE(task_to_reap))); - oom_reap_task(tsk); - WRITE_ONCE(task_to_reap, NULL); + (!list_empty(&oom_reaper_list))); + spin_lock(&oom_reaper_lock); + if (!list_empty(&oom_reaper_list)) { + tsk = list_first_entry(&oom_reaper_list, + struct task_struct, oom_reaper_list); + list_del(&tsk->oom_reaper_list); + } + spin_unlock(&oom_reaper_lock); + + if (tsk) + oom_reap_task(tsk); } return 0; @@ -537,23 +547,15 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - struct task_struct *old_tsk; - if (!oom_reaper_th) return; get_task_struct(tsk); - /* - * Make sure that only a single mm is ever queued for the reaper - * because multiple are not necessary and the operation might be - * disruptive so better reduce it to the bare minimum. - */ - old_tsk = cmpxchg(&task_to_reap, NULL, tsk); - if (!old_tsk) - wake_up(&oom_reaper_wait); - else - put_task_struct(tsk); + spin_lock(&oom_reaper_lock); + list_add(&tsk->oom_reaper_list, &oom_reaper_list); + spin_unlock(&oom_reaper_lock); + wake_up(&oom_reaper_wait); } static int __init oom_init(void)