Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <97a04805-120c-abc1-4e34-01cfdc5ef8fb@redhat.com>
Date:   Wed, 13 Apr 2022 12:00:25 -0400
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.5.0
Subject: Re: [PATCH v8] oom_kill.c: futex: Don't OOM reap the VMA containing
 the robust_list_head
Content-Language: en-US
To:     Michal Hocko <mhocko@suse.com>
Cc:     Joel Savitz <jsavitz@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>, linux-mm@kvack.org,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Rafael Aquini <aquini@redhat.com>,
        Waiman Long <longman@redhat.com>, Baoquan He <bhe@redhat.com>,
        Christoph von Recklinghausen <crecklin@redhat.com>,
        Don Dutile <ddutile@redhat.com>,
        "Herton R . Krzesinski" <herton@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Ingo Molnar <mingo@redhat.com>,
        Darren Hart <dvhart@infradead.org>, stable@kernel.org,
        Thomas Gleixner <tglx@linutronix.de>
References: <20220408032809.3696798-1-npache@redhat.com>
 <20220408081549.GM2731@worktop.programming.kicks-ass.net>
 <ee07a31c-c514-4a88-599f-14a30e93f32e@redhat.com> <87k0bzk7e5.ffs@tglx>
 <CAL1p7m4ukBQdQihkeSTjGHTM+HAF-GVf=QSnNPhRmetC213ANg@mail.gmail.com>
 <87sfqni77s.ffs@tglx> <YlPPRrGrX2ECe8QY@dhcp22.suse.cz> <87wnfwf4e5.ffs@tglx>
 <YlPv8elVxqa4XZnd@dhcp22.suse.cz>
From:   Nico Pache <npache@redhat.com>
In-Reply-To: <YlPv8elVxqa4XZnd@dhcp22.suse.cz>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 7ec38194f8e1..be6d65ead7ec 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -632,7 +632,7 @@ static void oom_reap_task(struct task_struct *tsk)
>  	 */
>  	set_bit(MMF_OOM_SKIP, &mm->flags);
>  
> -	/* Drop a reference taken by wake_oom_reaper */
> +	/* Drop a reference taken by queue_oom_repaer */
>  	put_task_struct(tsk);
>  }
>  
> @@ -644,12 +644,12 @@ 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);
> @@ -658,22 +658,50 @@ static int oom_reaper(void *unused)
>  	return 0;
>  }
>  
> -static void wake_oom_reaper(struct task_struct *tsk)
> +static void wake_oom_reaper_fn(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 OOM victims some head room to exit themselves. If they do not exit
> + * on their own the oom reaper is invoked.
> + * The timeout is basically arbitrary and there is no best value to use.
> + * The longer it will be the longer the worst case scenario OOM can
> + * take. The smaller the timeout the more likely the oom_reaper can get
> + * into the way and release resources which could be needed during the
> + * exit path - e.g. futex robust lists can sit in the anonymous memory
> + * which could be reaped and the exit path won't be able to let waiters
> + * know the holding task has terminated.
> + */
> +#define OOM_REAPER_DELAY (2*HZ)
> +static void queue_oom_repaer(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_fn, 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");
> @@ -681,7 +709,7 @@ 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_repaer(struct task_struct *tsk)
>  {
>  }
>  #endif /* CONFIG_MMU */
> @@ -932,7 +960,7 @@ 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_repaer(victim);
>  
>  	mmdrop(mm);
>  	put_task_struct(victim);
> @@ -968,7 +996,7 @@ 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_repaer(victim);
>  		task_unlock(victim);
>  		put_task_struct(victim);
>  		return;
> @@ -1067,7 +1095,7 @@ bool out_of_memory(struct oom_control *oc)
>  	 */
>  	if (task_will_free_mem(current)) {
>  		mark_oom_victim(current);
> -		wake_oom_reaper(current);
> +		queue_oom_repaer(current);
>  		return true;
>  	}

Thanks for the code Michal-- It does seem to fix our issue! I will post it after
I finish running it through a few more test cases, and our internal testing suites.

Cheers,
-- Nico