Re: [PATCH] mm: oom: Fix race condition between oom_badness and do_exit of task

[David Rientjes]

On Wed, 7 Mar 2018, Gaurav Kohli wrote:

> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 6fd9773..5f4cc4b 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -114,9 +114,11 @@ struct task_struct *find_lock_task_mm(struct task_struct *p)
>  
>  	for_each_thread(p, t) {
>  		task_lock(t);
> +		get_task_struct(t);
>  		if (likely(t->mm))
>  			goto found;
>  		task_unlock(t);
> +		put_task_struct(t);
>  	}
>  	t = NULL;
>  found:

We hold rcu_read_lock() here, so perhaps only do get_task_struct() before 
doing rcu_read_unlock() and we have a non-NULL t?

> @@ -191,6 +193,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
>  			test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
>  			in_vfork(p)) {
>  		task_unlock(p);
> +		put_task_struct(p);
>  		return 0;
>  	}
>  
> @@ -208,7 +211,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
>  	 */
>  	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
>  		points -= (points * 3) / 100;
> -
> +	put_task_struct(p);
>  	/* Normalize to oom_score_adj units */
>  	adj *= totalpages / 1000;
>  	points += adj;

This fixes up oom_badness(), but there are other users of 
find_lock_task_mm() in the oom killer as well as other subsystems.