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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5F7CEECAAD3 for ; Mon, 5 Sep 2022 14:35:19 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id BDCD6801E5; Mon, 5 Sep 2022 10:35:18 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id B8D308D0076; Mon, 5 Sep 2022 10:35:18 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id A55D7801E5; Mon, 5 Sep 2022 10:35:18 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0017.hostedemail.com [216.40.44.17]) by kanga.kvack.org (Postfix) with ESMTP id 955B78D0076 for ; Mon, 5 Sep 2022 10:35:18 -0400 (EDT) Received: from smtpin04.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay06.hostedemail.com (Postfix) with ESMTP id 76629AC47E for ; Mon, 5 Sep 2022 14:35:18 +0000 (UTC) X-FDA: 79878279516.04.7126FAB Received: from out30-44.freemail.mail.aliyun.com (out30-44.freemail.mail.aliyun.com [115.124.30.44]) by imf18.hostedemail.com (Postfix) with ESMTP id 2A8BC1C005B for ; Mon, 5 Sep 2022 14:35:14 +0000 (UTC) X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R981e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046059;MF=baolin.wang@linux.alibaba.com;NM=1;PH=DS;RN=10;SR=0;TI=SMTPD_---0VOUw8Ef_1662388503; Received: from 30.32.67.179(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0VOUw8Ef_1662388503) by smtp.aliyun-inc.com; Mon, 05 Sep 2022 22:35:09 +0800 Message-ID: <9f098ff0-26d7-477c-13fa-cb878981e1ac@linux.alibaba.com> Date: Mon, 5 Sep 2022 22:35:13 +0800 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Thunderbird/91.13.0 Subject: Re: [PATCH] mm: gup: fix the fast GUP race against THP collapse To: David Hildenbrand , John Hubbard , Yang Shi , peterx@redhat.com, kirill.shutemov@linux.intel.com, jgg@nvidia.com, hughd@google.com, akpm@linux-foundation.org Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org References: <20220901222707.477402-1-shy828301@gmail.com> <0c9d9774-77dd-fd93-b5b6-fc63f3d01b7f@linux.alibaba.com> <383fec21-9801-9b60-7570-856da2133ea9@redhat.com> From: Baolin Wang In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit ARC-Authentication-Results: i=1; imf18.hostedemail.com; dkim=none; spf=pass (imf18.hostedemail.com: domain of baolin.wang@linux.alibaba.com designates 115.124.30.44 as permitted sender) smtp.mailfrom=baolin.wang@linux.alibaba.com; dmarc=pass (policy=none) header.from=alibaba.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1662388518; a=rsa-sha256; cv=none; b=4eMcMrIf1IQYkInLc7w1iycQUi9C/MGSNWUJXcW9U0FPChJb98PQEyXQXIRX/q74QM8G30 kUH9yNhv3N2bs5C8Qf49KGM9HaQlSEKobNxLOOXMbJkwguF7pe3VK8i1GPsx1EZq4z/Q63 ZONY24Sk9mj2tBIp4jkcE/7fhj+u2l8= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1662388518; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=iqpmGl368/JUl7QwijV5Hdfvh0Y+7yPw+f0mzxm8dBo=; b=kfltpyzgLsAj786X6TaPjdFyk9y5qt6ki+oXZq/BRjyZtHFaTe020LkcYDrlkFSDcVL9C8 NUG0LxfjJnTWIvsdvLniAcgTxY2wHfe5pQ6kcxLHjwpTfiYCfJHGbEH9Sh2Q+uU8EEjqEi ycAtQKc+zNrVflznTH1ICxKCsDbWA5I= X-Rspam-User: Authentication-Results: imf18.hostedemail.com; dkim=none; spf=pass (imf18.hostedemail.com: domain of baolin.wang@linux.alibaba.com designates 115.124.30.44 as permitted sender) smtp.mailfrom=baolin.wang@linux.alibaba.com; dmarc=pass (policy=none) header.from=alibaba.com X-Rspamd-Server: rspam08 X-Rspamd-Queue-Id: 2A8BC1C005B X-Stat-Signature: rq7nsn9r94hpuifsina1xdoutptico9n X-HE-Tag: 1662388514-581100 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 9/5/2022 7:11 PM, David Hildenbrand wrote: > On 05.09.22 12:24, David Hildenbrand wrote: >> On 05.09.22 12:16, Baolin Wang wrote: >>> >>> >>> On 9/5/2022 3:59 PM, David Hildenbrand wrote: >>>> On 05.09.22 00:29, John Hubbard wrote: >>>>> On 9/1/22 15:27, Yang Shi wrote: >>>>>> Since general RCU GUP fast was introduced in commit 2667f50e8b81 >>>>>> ("mm: >>>>>> introduce a general RCU get_user_pages_fast()"), a TLB flush is no >>>>>> longer >>>>>> sufficient to handle concurrent GUP-fast in all cases, it only >>>>>> handles >>>>>> traditional IPI-based GUP-fast correctly.  On architectures that send >>>>>> an IPI broadcast on TLB flush, it works as expected.  But on the >>>>>> architectures that do not use IPI to broadcast TLB flush, it may have >>>>>> the below race: >>>>>> >>>>>>       CPU A                                          CPU B >>>>>> THP collapse                                     fast GUP >>>>>>                                                  gup_pmd_range() <-- >>>>>> see valid pmd >>>>>>                                                      gup_pte_range() >>>>>> <-- work on pte >>>>>> pmdp_collapse_flush() <-- clear pmd and flush >>>>>> __collapse_huge_page_isolate() >>>>>>        check page pinned <-- before GUP bump refcount >>>>>>                                                          pin the page >>>>>>                                                          check PTE >>>>>> <-- >>>>>> no change >>>>>> __collapse_huge_page_copy() >>>>>>        copy data to huge page >>>>>>        ptep_clear() >>>>>> install huge pmd for the huge page >>>>>>                                                          return the >>>>>> stale page >>>>>> discard the stale page >>>>> >>>>> Hi Yang, >>>>> >>>>> Thanks for taking the trouble to write down these notes. I always >>>>> forget which race we are dealing with, and this is a great help. :) >>>>> >>>>> More... >>>>> >>>>>> >>>>>> The race could be fixed by checking whether PMD is changed or not >>>>>> after >>>>>> taking the page pin in fast GUP, just like what it does for PTE. >>>>>> If the >>>>>> PMD is changed it means there may be parallel THP collapse, so GUP >>>>>> should back off. >>>>>> >>>>>> Also update the stale comment about serializing against fast GUP in >>>>>> khugepaged. >>>>>> >>>>>> Fixes: 2667f50e8b81 ("mm: introduce a general RCU >>>>>> get_user_pages_fast()") >>>>>> Signed-off-by: Yang Shi >>>>>> --- >>>>>>     mm/gup.c        | 30 ++++++++++++++++++++++++------ >>>>>>     mm/khugepaged.c | 10 ++++++---- >>>>>>     2 files changed, 30 insertions(+), 10 deletions(-) >>>>>> >>>>>> diff --git a/mm/gup.c b/mm/gup.c >>>>>> index f3fc1f08d90c..4365b2811269 100644 >>>>>> --- a/mm/gup.c >>>>>> +++ b/mm/gup.c >>>>>> @@ -2380,8 +2380,9 @@ static void __maybe_unused undo_dev_pagemap(int >>>>>> *nr, int nr_start, >>>>>>     } >>>>>>     #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL >>>>>> -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned >>>>>> long end, >>>>>> -             unsigned int flags, struct page **pages, int *nr) >>>>>> +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, >>>>>> +             unsigned long end, unsigned int flags, >>>>>> +             struct page **pages, int *nr) >>>>>>     { >>>>>>         struct dev_pagemap *pgmap = NULL; >>>>>>         int nr_start = *nr, ret = 0; >>>>>> @@ -2423,7 +2424,23 @@ static int gup_pte_range(pmd_t pmd, unsigned >>>>>> long addr, unsigned long end, >>>>>>                 goto pte_unmap; >>>>>>             } >>>>>> -        if (unlikely(pte_val(pte) != pte_val(*ptep))) { >>>>>> +        /* >>>>>> +         * THP collapse conceptually does: >>>>>> +         *   1. Clear and flush PMD >>>>>> +         *   2. Check the base page refcount >>>>>> +         *   3. Copy data to huge page >>>>>> +         *   4. Clear PTE >>>>>> +         *   5. Discard the base page >>>>>> +         * >>>>>> +         * So fast GUP may race with THP collapse then pin and >>>>>> +         * return an old page since TLB flush is no longer >>>>>> sufficient >>>>>> +         * to serialize against fast GUP. >>>>>> +         * >>>>>> +         * Check PMD, if it is changed just back off since it >>>>>> +         * means there may be parallel THP collapse. >>>>>> +         */ >>>>> >>>>> As I mentioned in the other thread, it would be a nice touch to move >>>>> such discussion into the comment header. >>>>> >>>>>> +        if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || >>>>>> +            unlikely(pte_val(pte) != pte_val(*ptep))) { >>>>> >>>>> >>>>> That should be READ_ONCE() for the *pmdp and *ptep reads. Because this >>>>> whole lockless house of cards may fall apart if we try reading the >>>>> page table values without READ_ONCE(). >>>> >>>> I came to the conclusion that the implicit memory barrier when grabbing >>>> a reference on the page is sufficient such that we don't need READ_ONCE >>>> here. >>> >>> IMHO the compiler may optimize the code 'pte_val(*ptep)' to be always >>> get from a register, then we can get an old value if other thread did >>> set_pte(). I am not sure how the implicit memory barrier can pervent the >>> compiler optimization? Please correct me if I missed something. >> >> IIUC, an memory barrier always implies a compiler barrier. >> > > To clarify what I mean, Documentation/atomic_t.txt documents > > NOTE: when the atomic RmW ops are fully ordered, they should also imply > a compiler barrier. Right, I agree. That means the complier can not optimize the order of the 'pte_val(*ptep)', however what I am confusing is that the complier can still save the value of *ptep into a register or stack instead of reloading from memory? A similar issue in commit d6c1f098f2a7 ("mm/swap_state: fix a data race in swapin_nr_pages"). --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -509,10 +509,11 @@ static unsigned long swapin_nr_pages(unsigned long offset) return 1; hits = atomic_xchg(&swapin_readahead_hits, 0); - pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages, + pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, + max_pages, atomic_read(&last_readahead_pages)); if (!hits) - prev_offset = offset; + WRITE_ONCE(prev_offset, offset); atomic_set(&last_readahead_pages, pages); return pages;