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=-2.2 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,UNPARSEABLE_RELAY,USER_AGENT_SANE_1 autolearn=no 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 38CE8C43215 for ; Mon, 25 Nov 2019 19:33:55 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 9DED720748 for ; Mon, 25 Nov 2019 19:33:54 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 9DED720748 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 1C66C6B027A; Mon, 25 Nov 2019 14:33:54 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 177636B027B; Mon, 25 Nov 2019 14:33:54 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 08DA36B027C; Mon, 25 Nov 2019 14:33:54 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0144.hostedemail.com [216.40.44.144]) by kanga.kvack.org (Postfix) with ESMTP id E30B16B027A for ; Mon, 25 Nov 2019 14:33:53 -0500 (EST) Received: from smtpin14.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with SMTP id 7CDA65837 for ; Mon, 25 Nov 2019 19:33:53 +0000 (UTC) X-FDA: 76195799946.14.care21_3eeabb583992a X-HE-Tag: care21_3eeabb583992a X-Filterd-Recvd-Size: 5804 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) by imf17.hostedemail.com (Postfix) with ESMTP for ; Mon, 25 Nov 2019 19:33:52 +0000 (UTC) X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R601e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04420;MF=yang.shi@linux.alibaba.com;NM=1;PH=DS;RN=8;SR=0;TI=SMTPD_---0Tj5FL5p_1574710425; Received: from US-143344MP.local(mailfrom:yang.shi@linux.alibaba.com fp:SMTPD_---0Tj5FL5p_1574710425) by smtp.aliyun-inc.com(127.0.0.1); Tue, 26 Nov 2019 03:33:49 +0800 Subject: Re: [RFC PATCH] mm: shmem: allow split THP when truncating THP partially To: "Kirill A. Shutemov" Cc: hughd@google.com, kirill.shutemov@linux.intel.com, aarcange@redhat.com, akpm@linux-foundation.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org References: <1574471132-55639-1-git-send-email-yang.shi@linux.alibaba.com> <20191125093611.hlamtyo4hvefwibi@box> <3a35da3a-dff0-a8ca-8269-3018fff8f21b@linux.alibaba.com> <20191125183350.5gmcln6t3ofszbsy@box> From: Yang Shi Message-ID: <9a68b929-2f84-083d-0ac8-2ceb3eab8785@linux.alibaba.com> Date: Mon, 25 Nov 2019 11:33:41 -0800 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:52.0) Gecko/20100101 Thunderbird/52.7.0 MIME-Version: 1.0 In-Reply-To: <20191125183350.5gmcln6t3ofszbsy@box> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: quoted-printable 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 11/25/19 10:33 AM, Kirill A. Shutemov wrote: > On Mon, Nov 25, 2019 at 10:24:38AM -0800, Yang Shi wrote: >> >> On 11/25/19 1:36 AM, Kirill A. Shutemov wrote: >>> On Sat, Nov 23, 2019 at 09:05:32AM +0800, Yang Shi wrote: >>>> Currently when truncating shmem file, if the range is partial of THP >>>> (start or end is in the middle of THP), the pages actually will just= get >>>> cleared rather than being freed unless the range cover the whole THP= . >>>> Even though all the subpages are truncated (randomly or sequentially= ), >>>> the THP may still be kept in page cache. This might be fine for som= e >>>> usecases which prefer preserving THP. >>>> >>>> But, when doing balloon inflation in QEMU, QEMU actually does hole p= unch >>>> or MADV_DONTNEED in base page size granulairty if hugetlbfs is not u= sed. >>>> So, when using shmem THP as memory backend QEMU inflation actually d= oesn't >>>> work as expected since it doesn't free memory. But, the inflation >>>> usecase really needs get the memory freed. Anonymous THP will not g= et >>>> freed right away too but it will be freed eventually when all subpag= es are >>>> unmapped, but shmem THP would still stay in page cache. >>>> >>>> To protect the usecases which may prefer preserving THP, introduce a >>>> new fallocate mode: FALLOC_FL_SPLIT_HPAGE, which means spltting THP = is >>>> preferred behavior if truncating partial THP. This mode just makes >>>> sense to tmpfs for the time being. >>> We need to clarify interaction with khugepaged. This implementation >>> doesn't do anything to prevent khugepaged from collapsing the range b= ack >>> to THP just after the split. >> Yes, it doesn't. Will clarify this in the commit log. > Okay, but I'm not sure that documention alone will be enough. We need > proper design. Maybe we could try to hold inode lock with read during collapse_file().=20 The shmem fallocate does acquire inode lock with write, this should be=20 able to synchronize hole punch and khugepaged. And, shmem just needs=20 hold inode lock for llseek and fallocate, I'm supposed they are should=20 be called not that frequently to have impact on khugepaged. The llseek=20 might be often, but it should be quite fast. However, they might get=20 blocked by khugepaged. It sounds safe to hold a rwsem during collapsing THP. Or we could set VM_NOHUGEPAGE in shmem inode's flag with hole punch and=20 clear it after truncate, then check the flag before doing collapse in=20 khugepaged. khugepaged should not need hold the inode lock during=20 collapse since it could be released after the flag is checked. > >>>> @@ -976,8 +1022,31 @@ static void shmem_undo_range(struct inode *ino= de, loff_t lstart, loff_t lend, >>>> } >>>> unlock_page(page); >>>> } >>>> +rescan_split: >>>> pagevec_remove_exceptionals(&pvec); >>>> pagevec_release(&pvec); >>>> + >>>> + if (split && PageTransCompound(page)) { >>>> + /* The THP may get freed under us */ >>>> + if (!get_page_unless_zero(compound_head(page))) >>>> + goto rescan_out; >>>> + >>>> + lock_page(page); >>>> + >>>> + /* >>>> + * The extra pins from page cache lookup have been >>>> + * released by pagevec_release(). >>>> + */ >>>> + if (!split_huge_page(page)) { >>>> + unlock_page(page); >>>> + put_page(page); >>>> + /* Re-look up page cache from current index */ >>>> + goto again; >>>> + } >>>> + unlock_page(page); >>>> + put_page(page); >>>> + } >>>> +rescan_out: >>>> index++; >>>> } >>> Doing get_page_unless_zero() just after you've dropped the pin for th= e >>> page looks very suboptimal. >> If I don't drop the pins the THP can't be split. And, there might be m= ore >> than one pins from find_get_entries() if I read the code correctly. Fo= r >> example, truncate 8K length in the middle of THP, the THP's refcount w= ould >> get bumpped twice since=C2=A0 two sub pages would be returned. > Pin the page before pagevec_release() and avoid get_page_unless_zero(). > > Current code is buggy. You need to check that the page is still belong = to > the file after speculative lookup. Yes, I missed this point. Thanks for the suggestion. >