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=-0.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_PASS,URIBL_BLOCKED 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 123E3C433F5 for ; Mon, 10 Sep 2018 08:55:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id BF4A220865 for ; Mon, 10 Sep 2018 08:55:52 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org BF4A220865 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727811AbeIJNsu (ORCPT ); Mon, 10 Sep 2018 09:48:50 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:49704 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726505AbeIJNsu (ORCPT ); Mon, 10 Sep 2018 09:48:50 -0400 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.rdu2.redhat.com [10.11.54.6]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 36A2D2637B; Mon, 10 Sep 2018 08:55:49 +0000 (UTC) Received: from [10.36.117.149] (ovpn-117-149.ams2.redhat.com [10.36.117.149]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 4A2882166BA3; Mon, 10 Sep 2018 08:55:48 +0000 (UTC) Subject: Re: [RFC] pipe: prevent compiler reordering in pipe_poll To: Eric Wong , Al Viro Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org References: <20180824225431.tpaxuck7idgnj3b7@dcvr> From: Paolo Bonzini Openpgp: preference=signencrypt Autocrypt: addr=pbonzini@redhat.com; prefer-encrypt=mutual; keydata= xsEhBFRCcBIBDqDGsz4K0zZun3jh+U6Z9wNGLKQ0kSFyjN38gMqU1SfP+TUNQepFHb/Gc0E2 CxXPkIBTvYY+ZPkoTh5xF9oS1jqI8iRLzouzF8yXs3QjQIZ2SfuCxSVwlV65jotcjD2FTN04 hVopm9llFijNZpVIOGUTqzM4U55sdsCcZUluWM6x4HSOdw5F5Utxfp1wOjD/v92Lrax0hjiX DResHSt48q+8FrZzY+AUbkUS+Jm34qjswdrgsC5uxeVcLkBgWLmov2kMaMROT0YmFY6A3m1S P/kXmHDXxhe23gKb3dgwxUTpENDBGcfEzrzilWueOeUWiOcWuFOed/C3SyijBx3Av/lbCsHU Vx6pMycNTdzU1BuAroB+Y3mNEuW56Yd44jlInzG2UOwt9XjjdKkJZ1g0P9dwptwLEgTEd3Fo UdhAQyRXGYO8oROiuh+RZ1lXp6AQ4ZjoyH8WLfTLf5g1EKCTc4C1sy1vQSdzIRu3rBIjAvnC tGZADei1IExLqB3uzXKzZ1BZ+Z8hnt2og9hb7H0y8diYfEk2w3R7wEr+Ehk5NQsT2MPI2QBd wEv1/Aj1DgUHZAHzG1QN9S8wNWQ6K9DqHZTBnI1hUlkp22zCSHK/6FwUCuYp1zcAEQEAAc0f UGFvbG8gQm9uemluaSA8Ym9uemluaUBnbnUub3JnPsLBTQQTAQIAIwUCVEJ7AwIbAwcLCQgH AwIBBhUIAgkKCwQWAgMBAh4BAheAAAoJEH4VEAzNNmmxNcwOniaZVLsuy1lW/ntYCA0Caz0i sHpmecK8aWlvL9wpQCk4GlOX9L1emyYXZPmzIYB0IRqmSzAlZxi+A2qm9XOxs5gJ2xqMEXX5 FMtUH3kpkWWJeLqe7z0EoQdUI4EG988uv/tdZyqjUn2XJE+K01x7r3MkUSFz/HZKZiCvYuze VlS0NTYdUt5jBXualvAwNKfxEkrxeHjxgdFHjYWhjflahY7TNRmuqPM/Lx7wAuyoDjlYNE40 Z+Kun4/KjMbjgpcF4Nf3PJQR8qXI6p3so2qsSn91tY7DFSJO6v2HwFJkC2jU95wxfNmTEUZc znXahYbVOwCDJRuPrE5GKFd/XJU9u5hNtr/uYipHij01WXal2cce1S5mn1/HuM1yo1u8xdHy IupCd57EWI948e8BlhpujUCU2tzOb2iYS0kpmJ9/oLVZrOcSZCcCl2P0AaCAsj59z2kwQS9D du0WxUs8waso0Qq6tDEHo8yLCOJDzSz4oojTtWe4zsulVnWV+wu70AioemAT8S6JOtlu60C5 dHgQUD1Tp+ReXpDKXmjbASJx4otvW0qah3o6JaqO79tbDqIvncu3tewwp6c85uZd48JnIOh3 utBAu684nJakbbvZUGikJfxd887ATQRUQnHuAQgAx4dxXO6/Zun0eVYOnr5GRl76+2UrAAem Vv9Yfn2PbDIbxXqLff7oyVJIkw4WdhQIIvvtu5zH24iYjmdfbg8iWpP7NqxUQRUZJEWbx2CR wkMHtOmzQiQ2tSLjKh/cHeyFH68xjeLcinR7jXMrHQK+UCEw6jqi1oeZzGvfmxarUmS0uRuf fAb589AJW50kkQK9VD/9QC2FJISSUDnRC0PawGSZDXhmvITJMdD4TjYrePYhSY4uuIV02v02 8TVAaYbIhxvDY0hUQE4r8ZbGRLn52bEzaIPgl1p/adKfeOUeMReg/CkyzQpmyB1TSk8lDMxQ zCYHXAzwnGi8WU9iuE1P0wARAQABwsEzBBgBAgAJBQJUQnHuAhsMAAoJEH4VEAzNNmmxp1EO oJy0uZggJm7gZKeJ7iUpeX4eqUtqelUw6gU2daz2hE/jsxsTbC/w5piHmk1H1VWDKEM4bQBT uiJ0bfo55SWsUNN+c9hhIX+Y8LEe22izK3w7mRpvGcg+/ZRG4DEMHLP6JVsv5GMpoYwYOmHn plOzCXHvmdlW0i6SrMsBDl9rw4AtIa6bRwWLim1lQ6EM3PWifPrWSUPrPcw4OLSwFk0CPqC4 HYv/7ZnASVkR5EERFF3+6iaaVi5OgBd81F1TCvCX2BEyIDRZLJNvX3TOd5FEN+lIrl26xecz 876SvcOb5SL5SKg9/rCBufdPSjojkGFWGziHiFaYhbuI2E+NfWLJtd+ZvWAAV+O0d8vFFSvr iy9enJ8kxJwhC0ECbSKFY+W1eTIhMD3aeAKY90drozWEyHhENf4l/V+Ja5vOnW+gCDQkGt2Y 1lJAPPSIqZKvHzGShdh8DduC0U3xYkfbGAUvbxeepjgzp0uEnBXfPTy09JGpgWbg0w91GyfT /ujKaGd4vxG2Ei+MMNDmS1SMx7wu0evvQ5kT9NPzyq8R2GIhVSiAd2jioGuTjX6AZCFv3ToO 53DliFMkVTecLptsXaesuUHgL9dKIfvpm+rNXRn9wAwGjk0X/A== Message-ID: <817dd145-fba5-d5e8-26b8-746b9bab4dd9@redhat.com> Date: Mon, 10 Sep 2018 10:55:47 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.9.1 MIME-Version: 1.0 In-Reply-To: <20180824225431.tpaxuck7idgnj3b7@dcvr> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.78 on 10.11.54.6 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.2]); Mon, 10 Sep 2018 08:55:49 +0000 (UTC) X-Greylist: inspected by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.2]); Mon, 10 Sep 2018 08:55:49 +0000 (UTC) for IP:'10.11.54.6' DOMAIN:'int-mx06.intmail.prod.int.rdu2.redhat.com' HELO:'smtp.corp.redhat.com' FROM:'pbonzini@redhat.com' RCPT:'' Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 25/08/2018 00:54, Eric Wong wrote: > The pipe_poll function does not use locks, and adding an entry > to the waitqueue is not guaranteed to happen before pipe->nrbufs > (or other fields) are read, leading to missed wakeups. > > Looking at Ruby CI build logs and backtraces, I've noticed > occasional instances where processes are stuck in select(2) or > ppoll(2) with a pipe. > > I don't have access to the systems where this is happening to > test/reproduce the problem, and haven't been able to reproduce > it locally on less-powerful hardware, either. However, it seems > like a problem based on similar comments in > fs/eventfd.c::eventfd_poll made by Paolo. The documentation change can be useful, but if you add a compiler barrier you should also mention why reordering at the processor level is okay. In this case, processor-level reordering is okay because (just like in fs/eventfd.c) poll_wait acts as an acquire barrier. *However* I would be surprised if the scenario (even the one in fs/eventfd.c) can actually happen, and I don't think the compiler barrier is useful; there's no reason why the compiler should think that it can hoist the reads above poll_wait. In fact, there is a big difference between READ_ONCE() and barrier() for whoever reads the code, which makes the code after your patch worse than before. READ_ONCE() means "I know I am accessing this variable outside a lock". barrier() means one of two things: 1) "I know what I am doing can trick the compiler, and I don't want that to happen"; 2) "I am synchronizing against other things happening on this CPU" such as interrupts. In this case you are not doing any of the two. Paolo > Signed-off-by: Eric Wong > Cc: Paolo Bonzini > --- > fs/pipe.c | 32 ++++++++++++++++++++++++++++++-- > 1 file changed, 30 insertions(+), 2 deletions(-) > > diff --git a/fs/pipe.c b/fs/pipe.c > index 39d6f431da83..1a904d941cf1 100644 > --- a/fs/pipe.c > +++ b/fs/pipe.c > @@ -509,7 +509,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) > } > } > > -/* No kernel lock held - fine */ > +/* No kernel lock held - fine, but a compiler barrier is required */ > static __poll_t > pipe_poll(struct file *filp, poll_table *wait) > { > @@ -519,7 +519,35 @@ pipe_poll(struct file *filp, poll_table *wait) > > poll_wait(filp, &pipe->wait, wait); > > - /* Reading only -- no need for acquiring the semaphore. */ > + /* > + * Reading only -- no need for acquiring the semaphore, but > + * we need a compiler barrier to ensure the compiler does > + * not reorder reads to pipe->nrbufs, pipe->writers, > + * pipe->readers, filp->f_version, pipe->w_counter, and > + * pipe->buffers before poll_wait to avoid missing wakeups > + * from compiler reordering. In other words, we need to > + * prevent the following situation: > + * > + * pipe_poll pipe_write > + * ----------------- ------------ > + * nrbufs = pipe->nrbufs (INVALID!) > + * > + * __pipe_lock > + * pipe->nrbufs = ++bufs; > + * __pipe_unlock > + * wake_up_interruptible_sync_poll > + * pipe->wait is empty, no wakeup > + * > + * lock pipe->wait.lock (in poll_wait) > + * __add_wait_queue > + * unlock pipe->wait.lock > + * > + * // pipe->nrbufs should be read here, NOT above > + * > + * pipe_poll returns 0 (WRONG) > + */ > + barrier(); > + > nrbufs = pipe->nrbufs; > mask = 0; > if (filp->f_mode & FMODE_READ) { >