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 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4C6BEC433F5 for ; Fri, 29 Oct 2021 16:07:53 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id E0152610EA for ; Fri, 29 Oct 2021 16:07:52 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org E0152610EA Authentication-Results: mail.kernel.org; dmarc=fail (p=reject dis=none) header.from=google.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kvack.org Received: by kanga.kvack.org (Postfix) id 2DA566B0071; Fri, 29 Oct 2021 12:07:52 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 289F2940007; Fri, 29 Oct 2021 12:07:52 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 104666B0073; Fri, 29 Oct 2021 12:07:52 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0253.hostedemail.com [216.40.44.253]) by kanga.kvack.org (Postfix) with ESMTP id DCD3E6B0071 for ; Fri, 29 Oct 2021 12:07:51 -0400 (EDT) Received: from smtpin30.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 6F94318479C82 for ; Fri, 29 Oct 2021 16:07:51 +0000 (UTC) X-FDA: 78749955942.30.3F60E72 Received: from mail-yb1-f173.google.com (mail-yb1-f173.google.com [209.85.219.173]) by imf03.hostedemail.com (Postfix) with ESMTP id 14FE730000A4 for ; Fri, 29 Oct 2021 16:07:45 +0000 (UTC) Received: by mail-yb1-f173.google.com with SMTP id a129so12319385yba.10 for ; Fri, 29 Oct 2021 09:07:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=ErSQ5CrQeSkmLUbZHQvgt43whunrTwbaNcEcHojj/F0=; b=r13mojvJ6IxO/MNCwqjQIRl2GnGDxLpJDNBQ3Jf8Txoh9BXENinQKzMfyhu2t+R34Q XaYNUIOISw7NVtii3HqpVPoYUstJaeOIWGm4Pj4x05NuuzDT8UGH/25/txTXbu2B8JBj Ypqx9W3CyM3Gs0InNIieqvyefufKQJ8HVmG8kxON7/IT8O4hH/OIyikQnw/X9sXTsfVj ZhhxqXJFk8HyTyk8paxVtgpt1YUowPq1Kf3IwB2JHg42qzYi91mH+vEtZg3DkJOHoVxC Io8KK/VSaIWIT2snrGuPBQXCMo0miHT6J7R9Y6ztme3aNVbIj9g5V5mRx5G1yvcvX0iN Slcg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=ErSQ5CrQeSkmLUbZHQvgt43whunrTwbaNcEcHojj/F0=; b=3wq+1baHKYx/xC2zWCNH7zEWOpfD8+Jhk4AKwHwF9YeLgWN71TF/ptEUIdreVmb8nF XrWzB3+WAs9k/HHr/lPb6JMU7L/tush+t963olH1X3EHkW8xxqMllg6jVBkEvdkLKBIT FyK3GaiqmaSdDh9hm9Ya4z0SVBGwrBOB9OpXpc0skZ3Pi9+lDryN2bzsp+9mFVzQreDx qMLdJ9hwZYLTLNBtW6TGX2hdwxzAbL14qn+WdILIOO/+eo7a8LwVfPsyAzZJ4xR//3eN VZkMbtUOLXqMn3DPZYh0GtLQUB+4yeSnFFkI09qEZNTErUjyMyikLqC25IxSCBYTWnwD ISFg== X-Gm-Message-State: AOAM53177BeRPKcybRS8KaTYgNB1Q90sEYDFgvM8OZt4Or4cmz3ce3RX p3JXzfrXNNsKhV8vf4pSbkBXZe3eFuALy4x2yV/IVA== X-Google-Smtp-Source: ABdhPJyFooqk3QJhmp9xEqMlJWlYya+dgKhKFj39pBOPgPsVPxI0OQtOdHjIYjwZ9h/nmENxRVtkMKSYNvX1hUyq2xc= X-Received: by 2002:a25:b3c7:: with SMTP id x7mr2296339ybf.34.1635523670005; Fri, 29 Oct 2021 09:07:50 -0700 (PDT) MIME-Version: 1.0 References: <20211022014658.263508-1-surenb@google.com> In-Reply-To: From: Suren Baghdasaryan Date: Fri, 29 Oct 2021 09:07:39 -0700 Message-ID: Subject: Re: [PATCH 1/1] mm: prevent a race between process_mrelease and exit_mmap To: Michal Hocko Cc: Andrew Morton , David Rientjes , Matthew Wilcox , Johannes Weiner , Roman Gushchin , Rik van Riel , Minchan Kim , Christian Brauner , Christoph Hellwig , Oleg Nesterov , David Hildenbrand , Jann Horn , Shakeel Butt , Andy Lutomirski , Christian Brauner , Florian Weimer , Jan Engelhardt , Linux API , linux-mm , LKML , kernel-team , "Kirill A. Shutemov" , Andrea Arcangeli Content-Type: text/plain; charset="UTF-8" X-Rspamd-Server: rspam02 X-Rspamd-Queue-Id: 14FE730000A4 X-Stat-Signature: qe69e9ikq5k5m6cxrouczumnmf8mmhym Authentication-Results: imf03.hostedemail.com; dkim=pass header.d=google.com header.s=20210112 header.b=r13mojvJ; dmarc=pass (policy=reject) header.from=google.com; spf=pass (imf03.hostedemail.com: domain of surenb@google.com designates 209.85.219.173 as permitted sender) smtp.mailfrom=surenb@google.com X-HE-Tag: 1635523665-420321 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 Fri, Oct 29, 2021 at 6:03 AM Michal Hocko wrote: > > On Wed 27-10-21 09:08:21, Suren Baghdasaryan wrote: > > On Fri, Oct 22, 2021 at 10:38 AM Suren Baghdasaryan wrote: > > > > > > On Fri, Oct 22, 2021 at 1:03 AM Michal Hocko wrote: > > > > > > > > On Thu 21-10-21 18:46:58, Suren Baghdasaryan wrote: > > > > > Race between process_mrelease and exit_mmap, where free_pgtables is > > > > > called while __oom_reap_task_mm is in progress, leads to kernel crash > > > > > during pte_offset_map_lock call. oom-reaper avoids this race by setting > > > > > MMF_OOM_VICTIM flag and causing exit_mmap to take and release > > > > > mmap_write_lock, blocking it until oom-reaper releases mmap_read_lock. > > > > > Reusing MMF_OOM_VICTIM for process_mrelease would be the simplest way to > > > > > fix this race, however that would be considered a hack. Fix this race > > > > > by elevating mm->mm_users and preventing exit_mmap from executing until > > > > > process_mrelease is finished. Patch slightly refactors the code to adapt > > > > > for a possible mmget_not_zero failure. > > > > > This fix has considerable negative impact on process_mrelease performance > > > > > and will likely need later optimization. > > > > > > > > I am not sure there is any promise that process_mrelease will run in > > > > parallel with the exiting process. In fact the primary purpose of this > > > > syscall is to provide a reliable way to oom kill from user space. If you > > > > want to optimize process exit resp. its exit_mmap part then you should > > > > be using other means. So I would be careful calling this a regression. > > > > > > > > I do agree that taking the reference count is the right approach here. I > > > > was wrong previously [1] when saying that pinning the mm struct is > > > > sufficient. I have completely forgot about the subtle sync in exit_mmap. > > > > One way we can approach that would be to take exclusive mmap_sem > > > > throughout the exit_mmap unconditionally. > > > > > > I agree, that would probably be the cleanest way. > > > > > > > There was a push back against > > > > that though so arguments would have to be re-evaluated. > > > > > > I'll review that discussion to better understand the reasons for the > > > push back. Thanks for the link. > > > > Adding Kirill and Andrea. > > > > I had some time to dig some more. The latency increase is definitely > > coming due to process_mrelease calling the last mmput and exit_aio is > > especially problematic. So, currently process_mrelease not only > > releases memory but does more, including waiting for io to finish. > > Well, I still do not see why that is a problem. This syscall is meant to > release the address space not to do it fast. It's the same problem for a userspace memory reaper as for the oom-reaper. The goal is to release the memory of the victim and to quickly move on to the next one if needed. > > > Unconditional mmap_write_lock around free_pgtables in exit_mmap seems > > to me the most semantically correct way forward and the pushback is on > > the basis of regressing performance of the exit path. I would like to > > measure that regression to confirm this. I don't have access to a big > > machine but will ask someone in another Google team to try the test > > Michal wrote here > > https://lore.kernel.org/all/20170725142626.GJ26723@dhcp22.suse.cz/ on > > a server with and without a custom patch. > > Well, I do not remember all the details of the discussion but I believe > a rather large part of that discussion was a bit misled. The exist > path - and the last mmput in particular - shouldn't trigger mmap_sem > contention. There are only rare cases where somebody can race and take a > lock then (e.g. proc interfaces taking the lock before mmget_notzero). > Certainly not something to optimize for and I believe a correct and > robust code should have a preference. As we can see a lack of proper > synchronization has led to 2 very similar problem nobody revealed during > review because the code is just too tricky. I totally agree that this locking is tricky and mmap_sem contention should be very rare in the exit_mmap path and not worth optimizing. > > Btw. the above code will not really tell you much on a larger machine > unless you manage to trigger mmap_sem contection. Otherwise you are > measuring the mmap_sem writelock fast path and that should be really > within a noise comparing to the whole address space destruction time. If > that is not the case then we have a real problem with the locking... My understanding of that discussion is that the concern was that even taking uncontended mmap_sem writelock would regress the exit path. That was what I wanted to confirm. Am I misreading it? Thanks, Suren. > -- > Michal Hocko > SUSE Labs