Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
Date:   Fri, 22 Apr 2022 17:38:44 +0200
From:   Michal Hocko <mhocko@suse.com>
To:     Nico Pache <npache@redhat.com>
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        David Rientjes <rientjes@google.com>,
        Andrea Arcangeli <aarcange@redhat.com>
Subject: Re: [RFC 3/3] exit: Check for MMF_OOM_SKIP in exit_mmap
Message-ID: <YmLMBDkHmcjf9Nem@dhcp22.suse.cz>
References: <20220421190533.1601879-1-npache@redhat.com>
 <20220421190533.1601879-4-npache@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220421190533.1601879-4-npache@redhat.com>
Precedence: bulk

On Thu 21-04-22 15:05:33, Nico Pache wrote:
> The MMF_OOM_SKIP bit is used to indicate weather a mm_struct can not be
> invalided or has already been invalided. exit_mmap currently calls
> __oom_reap_task_mm unconditionally despite the fact that the oom reaper
> may have already called this.
> 
> Add a check for the MMF_OOM_SKIP bit being set in exit_mmap to avoid
> unnessary calls to the invalidate code.

Why do we care about this?
 
> A slight race can occur on the MMF_OOM_SKIP bit that will still allow
> this to run twice. My testing has shown an ~66% decrease in double calls
> to _oom_reap_task_mm.
> 
> Fixes: 27ae357fa82b ("mm, oom: fix concurrent munlock and oom reaper unmap, v3")

I do not see this would be fixing anything.

> Cc: David Rientjes <rientjes@google.com>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Andrea Arcangeli <aarcange@redhat.com>
> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>  mm/mmap.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/mm/mmap.c b/mm/mmap.c
> index a2968669fd4e..b867f408dacd 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -3113,7 +3113,8 @@ void exit_mmap(struct mm_struct *mm)
>  	/* mm's last user has gone, and its about to be pulled down */
>  	mmu_notifier_release(mm);
>  
> -	if (unlikely(mm_is_oom_victim(mm))) {
> +	if (unlikely(mm_is_oom_victim(mm)) &&
> +			!test_bit(MMF_OOM_SKIP, &mm->flags)) {
>  		/*
>  		 * Manually reap the mm to free as much memory as possible.
>  		 * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
> -- 
> 2.35.1

-- 
Michal Hocko
SUSE Labs