From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-8.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,MENTIONS_GIT_HOSTING, SPF_HELO_NONE,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3A9B8C433DF for ; Thu, 20 Aug 2020 11:42:59 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 092B02076E for ; Thu, 20 Aug 2020 11:42:58 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 092B02076E Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=suse.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 9564B8D001B; Thu, 20 Aug 2020 07:42:58 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 92E138D0001; Thu, 20 Aug 2020 07:42:58 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 86A568D001B; Thu, 20 Aug 2020 07:42:58 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0170.hostedemail.com [216.40.44.170]) by kanga.kvack.org (Postfix) with ESMTP id 722558D0001 for ; Thu, 20 Aug 2020 07:42:58 -0400 (EDT) Received: from smtpin03.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay04.hostedemail.com (Postfix) with ESMTP id 3292A1DE6 for ; Thu, 20 Aug 2020 11:42:58 +0000 (UTC) X-FDA: 77170760436.03.card28_5d13e8227030 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin03.hostedemail.com (Postfix) with ESMTP id 046FA28A4E8 for ; Thu, 20 Aug 2020 11:42:57 +0000 (UTC) X-HE-Tag: card28_5d13e8227030 X-Filterd-Recvd-Size: 4685 Received: from mx2.suse.de (mx2.suse.de [195.135.220.15]) by imf32.hostedemail.com (Postfix) with ESMTP for ; Thu, 20 Aug 2020 11:42:57 +0000 (UTC) X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.221.27]) by mx2.suse.de (Postfix) with ESMTP id 53FB8B18A; Thu, 20 Aug 2020 11:43:23 +0000 (UTC) Date: Thu, 20 Aug 2020 13:42:45 +0200 From: Michal Hocko To: Christian Brauner Cc: Oleg Nesterov , Suren Baghdasaryan , mingo@kernel.org, peterz@infradead.org, tglx@linutronix.de, esyr@redhat.com, christian@kellner.me, areber@redhat.com, shakeelb@google.com, cyphar@cyphar.com, adobriyan@gmail.com, akpm@linux-foundation.org, ebiederm@xmission.com, gladkov.alexey@gmail.com, walken@google.com, daniel.m.jordan@oracle.com, avagin@gmail.com, bernd.edlinger@hotmail.de, john.johansen@canonical.com, laoar.shao@gmail.com, timmurray@google.com, minchan@kernel.org, kernel-team@android.com, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH 1/1] mm, oom_adj: don't loop through tasks in __set_oom_adj when not necessary Message-ID: <20200820114245.GH5033@dhcp22.suse.cz> References: <20200820002053.1424000-1-surenb@google.com> <20200820105555.GA4546@redhat.com> <20200820111349.GE5033@dhcp22.suse.cz> <20200820113023.rjxque4jveo4nj5o@wittgenstein> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20200820113023.rjxque4jveo4nj5o@wittgenstein> X-Rspamd-Queue-Id: 046FA28A4E8 X-Spamd-Result: default: False [0.00 / 100.00] X-Rspamd-Server: rspam01 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On Thu 20-08-20 13:30:23, Christian Brauner wrote: > On Thu, Aug 20, 2020 at 01:13:49PM +0200, Michal Hocko wrote: > > On Thu 20-08-20 12:55:56, Oleg Nesterov wrote: > > > On 08/19, Suren Baghdasaryan wrote: > > > > > > > > Since the combination of CLONE_VM and !CLONE_SIGHAND is rarely > > > > used the additional mutex lock in that path of the clone() syscall should > > > > not affect its overall performance. Clearing the MMF_PROC_SHARED flag > > > > (when the last process sharing the mm exits) is left out of this patch to > > > > keep it simple and because it is believed that this threading model is > > > > rare. > > > > > > vfork() ? > > > > Could you be more specific? > > vfork() implies CLONE_VM but !CLONE_THREAD. The way this patch is > written the mutex lock will be taken every time you do a vfork(). OK, I see. We definietely do not want to impact vfork so we likely have to check for CLONE_VFORK as well. Ohh, well our clone flags are really clear as mud. > (It's honestly also debatable whether it's that rare. For one, userspace > stuff I maintain uses it too (see [1]). > [1]: https://github.com/lxc/lxc/blob/9d3b7c97f0443adc9f0b0438437657ab42f5a1c3/src/lxc/start.c#L1676 > ) > > > > > > > --- a/kernel/fork.c > > > > +++ b/kernel/fork.c > > > > @@ -1403,6 +1403,15 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) > > > > if (clone_flags & CLONE_VM) { > > > > mmget(oldmm); > > > > mm = oldmm; > > > > + if (!(clone_flags & CLONE_SIGHAND)) { > > > > > > I agree with Christian, you need CLONE_THREAD > > > > This was my suggestion to Suren, likely because I've misrememberd which > > clone flag is responsible for the signal delivery. But now, after double > > checking we do explicitly disallow CLONE_SIGHAND && !CLONE_VM. So > > CLONE_THREAD is the right thing to check. > > > > > > + /* We need to synchronize with __set_oom_adj */ > > > > + mutex_lock(&oom_adj_lock); > > > > + set_bit(MMF_PROC_SHARED, &mm->flags); > > > > + /* Update the values in case they were changed after copy_signal */ > > > > + tsk->signal->oom_score_adj = current->signal->oom_score_adj; > > > > + tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; > > > > + mutex_unlock(&oom_adj_lock); > > > > > > I don't understand how this can close the race with __set_oom_adj... > > > > > > What if __set_oom_adj() is called right after mutex_unlock() ? It will see > > > MMF_PROC_SHARED, but for_each_process() won't find the new child until > > > copy_process() does list_add_tail_rcu(&p->tasks, &init_task.tasks) ? > > > > Good point. Then we will have to move this thing there. > > I was toying with moving this into sm like: > > static inline copy_oom_score(unsigned long flags, struct task_struct *tsk) > > trying to rely on set_bit() and test_bit() in copy_mm() being atomic and > then calling it where Oleg said after the point of no return. No objections. -- Michal Hocko SUSE Labs