Re: [PATCH 2/8] mm,oom_reaper: Reduce find_lock_task_mm() usage.

[Michal Hocko <mhocko@suse.cz>]

On Sun 03-07-16 11:37:33, Tetsuo Handa wrote:
> >From 3be379c6b42a0901cd81fb2c743e321b6fbdec5b Mon Sep 17 00:00:00 2001
> From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
> Date: Sat, 2 Jul 2016 22:55:17 +0900
> Subject: [PATCH 2/8] mm,oom_reaper: Reduce find_lock_task_mm() usage.
> 
> Since holding mm_struct with elevated mm_count for a second is harmless,
> we can determine mm_struct and hold it upon entry of oom_reap_task().
> This patch has no functional change. Future patch in this series will
> eliminate find_lock_task_mm() usage from the OOM reaper.

OK, this seems to reduce the code size and makes the code more readable.

> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/oom_kill.c | 79 ++++++++++++++++++++++++++++-------------------------------
>  1 file changed, 37 insertions(+), 42 deletions(-)
> 
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 16340f2..76c765e 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -451,12 +451,10 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
>  static struct task_struct *oom_reaper_list;
>  static DEFINE_SPINLOCK(oom_reaper_lock);
>  
> -static bool __oom_reap_task(struct task_struct *tsk)
> +static bool __oom_reap_task(struct task_struct *tsk, struct mm_struct *mm)
>  {
>  	struct mmu_gather tlb;
>  	struct vm_area_struct *vma;
> -	struct mm_struct *mm = NULL;
> -	struct task_struct *p;
>  	struct zap_details details = {.check_swap_entries = true,
>  				      .ignore_dirty = true};
>  	bool ret = true;
> @@ -477,22 +475,9 @@ static bool __oom_reap_task(struct task_struct *tsk)
>  	 */
>  	mutex_lock(&oom_lock);
>  
> -	/*
> -	 * Make sure we find the associated mm_struct even when the particular
> -	 * thread has already terminated and cleared its mm.
> -	 * We might have race with exit path so consider our work done if there
> -	 * is no mm.
> -	 */
> -	p = find_lock_task_mm(tsk);
> -	if (!p)
> -		goto unlock_oom;
> -	mm = p->mm;
> -	atomic_inc(&mm->mm_count);
> -	task_unlock(p);
> -
>  	if (!down_read_trylock(&mm->mmap_sem)) {
>  		ret = false;
> -		goto mm_drop;
> +		goto unlock_oom;
>  	}
>  
>  	/*
> @@ -502,7 +487,7 @@ static bool __oom_reap_task(struct task_struct *tsk)
>  	 */
>  	if (!mmget_not_zero(mm)) {
>  		up_read(&mm->mmap_sem);
> -		goto mm_drop;
> +		goto unlock_oom;
>  	}
>  
>  	tlb_gather_mmu(&tlb, mm, 0, -1);
> @@ -550,8 +535,6 @@ static bool __oom_reap_task(struct task_struct *tsk)
>  	 * put the oom_reaper out of the way.
>  	 */
>  	mmput_async(mm);
> -mm_drop:
> -	mmdrop(mm);
>  unlock_oom:
>  	mutex_unlock(&oom_lock);
>  	return ret;
> @@ -561,36 +544,45 @@ unlock_oom:
>  static void oom_reap_task(struct task_struct *tsk)
>  {
>  	int attempts = 0;
> +	struct mm_struct *mm = NULL;
> +	struct task_struct *p = find_lock_task_mm(tsk);
> +
> +	/*
> +	 * Make sure we find the associated mm_struct even when the particular
> +	 * thread has already terminated and cleared its mm.
> +	 * We might have race with exit path so consider our work done if there
> +	 * is no mm.
> +	 */
> +	if (!p)
> +		goto done;
> +	mm = p->mm;
> +	atomic_inc(&mm->mm_count);
> +	task_unlock(p);
>  
>  	/* Retry the down_read_trylock(mmap_sem) a few times */
> -	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk))
> +	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk, mm))
>  		schedule_timeout_idle(HZ/10);
>  
> -	if (attempts > MAX_OOM_REAP_RETRIES) {
> -		struct task_struct *p;
> +	if (attempts <= MAX_OOM_REAP_RETRIES)
> +		goto done;
>  
> -		pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
> -				task_pid_nr(tsk), tsk->comm);
> +	pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
> +		task_pid_nr(tsk), tsk->comm);
>  
> -		/*
> -		 * If we've already tried to reap this task in the past and
> -		 * failed it probably doesn't make much sense to try yet again
> -		 * so hide the mm from the oom killer so that it can move on
> -		 * to another task with a different mm struct.
> -		 */
> -		p = find_lock_task_mm(tsk);
> -		if (p) {
> -			if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &p->mm->flags)) {
> -				pr_info("oom_reaper: giving up pid:%d (%s)\n",
> -						task_pid_nr(tsk), tsk->comm);
> -				set_bit(MMF_OOM_REAPED, &p->mm->flags);
> -			}
> -			task_unlock(p);
> -		}
> -
> -		debug_show_all_locks();
> +	/*
> +	 * If we've already tried to reap this task in the past and
> +	 * failed it probably doesn't make much sense to try yet again
> +	 * so hide the mm from the oom killer so that it can move on
> +	 * to another task with a different mm struct.
> +	 */
> +	if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &mm->flags)) {
> +		pr_info("oom_reaper: giving up pid:%d (%s)\n",
> +			task_pid_nr(tsk), tsk->comm);
> +		set_bit(MMF_OOM_REAPED, &mm->flags);
>  	}
> +	debug_show_all_locks();
>  
> +done:
>  	/*
>  	 * Clear TIF_MEMDIE because the task shouldn't be sitting on a
>  	 * reasonably reclaimable memory anymore or it is not a good candidate
> @@ -602,6 +594,9 @@ static void oom_reap_task(struct task_struct *tsk)
>  
>  	/* Drop a reference taken by wake_oom_reaper */
>  	put_task_struct(tsk);
> +	/* Drop a reference taken above. */
> +	if (mm)
> +		mmdrop(mm);
>  }
>  
>  static int oom_reaper(void *unused)
> -- 
> 1.8.3.1

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>