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=-8.1 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,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 B7815C2D0A8 for ; Wed, 23 Sep 2020 13:10:52 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id D57A921BE5 for ; Wed, 23 Sep 2020 13:10:51 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="G2p3F7Jw" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org D57A921BE5 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 04ADA6B0003; Wed, 23 Sep 2020 09:10:51 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 020196B0055; Wed, 23 Sep 2020 09:10:50 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id E506B6B005A; Wed, 23 Sep 2020 09:10:50 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0011.hostedemail.com [216.40.44.11]) by kanga.kvack.org (Postfix) with ESMTP id D0DEB6B0003 for ; Wed, 23 Sep 2020 09:10:50 -0400 (EDT) Received: from smtpin19.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay01.hostedemail.com (Postfix) with ESMTP id 917B4180AD804 for ; Wed, 23 Sep 2020 13:10:50 +0000 (UTC) X-FDA: 77294361060.19.trail86_0015dc027156 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin19.hostedemail.com (Postfix) with ESMTP id 689B71ACEBC for ; Wed, 23 Sep 2020 13:10:50 +0000 (UTC) X-HE-Tag: trail86_0015dc027156 X-Filterd-Recvd-Size: 11788 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [216.205.24.124]) by imf14.hostedemail.com (Postfix) with ESMTP for ; Wed, 23 Sep 2020 13:10:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1600866649; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: in-reply-to:in-reply-to:references:references; bh=W5rV3Uet75F/qzjENYEH62H02or+L/mJaAH6PnzXKX8=; b=G2p3F7JwCOwj9q4Vx59QJ9tTHqH1mLjtjUmn6rhJ24HEvg8esBiOkvgnWDWGXOWhd1dc+g srOF8FsOB4CGlRcxIh9ytLKRrfeENcn0F9kes2eepyFVcGfVlnV16r4mYXY4ShwMjBRrhh YJXmjq1xCvZqliLPfipUmsVeNVxMi4M= Received: from mail-qt1-f197.google.com (mail-qt1-f197.google.com [209.85.160.197]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-65-NPw7cELeNh-cP_gV1I3z5Q-1; Wed, 23 Sep 2020 09:10:47 -0400 X-MC-Unique: NPw7cELeNh-cP_gV1I3z5Q-1 Received: by mail-qt1-f197.google.com with SMTP id f5so19197515qtk.11 for ; Wed, 23 Sep 2020 06:10:47 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:date:from:to:cc:subject:message-id:references :mime-version:content-disposition:in-reply-to; bh=W5rV3Uet75F/qzjENYEH62H02or+L/mJaAH6PnzXKX8=; b=s4c4OOfraZhIA54MP/lOeTo2xQNyG1iMsnM10qH6B9unMeghPJNWw6S3GgGySSJcU5 r3RzA2ZWuVRgQuPf2pcqMK2Jav4s1MIlYpSMjP/Ny+JjdwrCJtVovZ+pYvebOB8OSUmE +3u0vQa3mxL5gCtf4Ao+JBjDzZIUvdYZu90dG2U2Bl1s1OjwEt76yyj+hPfASnoYIRHC C5OMQ/W7fp7EBsiqBdrSgcBq89BEcXAnqNm9EqHe8jIdHTbGMVALid1YNUghNiCf7eJw y+7bt1DeDz+/w+4xksGZyGpNJrfO7sIpmBO2xDqaRMUV32M3952yFkWtlbsAq2+NJ2SU /SIw== X-Gm-Message-State: AOAM531gKOVLm4Eh1LMynregGnrVS0uw6wE+3WVqGRmPDCa2QxGASM/U xezaaMlybIRwY6WeqafwtfAD3Z/lODXVKG4Gz7k25Yia3lGxSKHBia5x/uAuhOjIWZxTuZn63I2 DDylagNWnJQI= X-Received: by 2002:ac8:3f23:: with SMTP id c32mr9778673qtk.102.1600866646949; Wed, 23 Sep 2020 06:10:46 -0700 (PDT) X-Google-Smtp-Source: ABdhPJxERnC1XgxlM4YhveNHIg2JOcQXKyxlQXpCDyWKQ1MGMLIuBozPcP450B4H8SSbwdChMVRZzg== X-Received: by 2002:ac8:3f23:: with SMTP id c32mr9778624qtk.102.1600866646437; Wed, 23 Sep 2020 06:10:46 -0700 (PDT) Received: from xz-x1 (bras-vprn-toroon474qw-lp130-11-70-53-122-15.dsl.bell.ca. [70.53.122.15]) by smtp.gmail.com with ESMTPSA id v30sm15091090qtj.52.2020.09.23.06.10.44 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 23 Sep 2020 06:10:45 -0700 (PDT) Date: Wed, 23 Sep 2020 09:10:43 -0400 From: Peter Xu To: Jason Gunthorpe Cc: John Hubbard , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton , Jan Kara , Michal Hocko , Kirill Tkhai , Kirill Shutemov , Hugh Dickins , Christoph Hellwig , Andrea Arcangeli , Oleg Nesterov , Leon Romanovsky , Linus Torvalds , Jann Horn Subject: Re: [PATCH 1/5] mm: Introduce mm_struct.has_pinned Message-ID: <20200923131043.GA59978@xz-x1> References: <20200921211744.24758-1-peterx@redhat.com> <20200921211744.24758-2-peterx@redhat.com> <224908c1-5d0f-8e01-baa9-94ec2374971f@nvidia.com> <20200922151736.GD19098@xz-x1> <20200922161046.GB731578@ziepe.ca> <20200922175415.GI19098@xz-x1> <20200922191116.GK8409@ziepe.ca> <20200923002735.GN19098@xz-x1> MIME-Version: 1.0 In-Reply-To: <20200923002735.GN19098@xz-x1> Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=peterx@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=utf-8 Content-Disposition: inline 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 Tue, Sep 22, 2020 at 08:27:35PM -0400, Peter Xu wrote: > On Tue, Sep 22, 2020 at 04:11:16PM -0300, Jason Gunthorpe wrote: > > On Tue, Sep 22, 2020 at 01:54:15PM -0400, Peter Xu wrote: > > > diff --git a/mm/memory.c b/mm/memory.c > > > index 8f3521be80ca..6591f3f33299 100644 > > > +++ b/mm/memory.c > > > @@ -888,8 +888,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, > > > * Because we'll need to release the locks before doing cow, > > > * pass this work to upper layer. > > > */ > > > - if (READ_ONCE(src_mm->has_pinned) && wp && > > > - page_maybe_dma_pinned(page)) { > > > + if (wp && page_maybe_dma_pinned(page) && > > > + READ_ONCE(src_mm->has_pinned)) { > > > /* We've got the page already; we're safe */ > > > data->cow_old_page = page; > > > data->cow_oldpte = *src_pte; > > > > > > I can also add some more comment to emphasize this. > > > > It is not just that, but the ptep_set_wrprotect() has to be done > > earlier. > > Now I understand your point, I think.. So I guess it's not only about > has_pinned, but it should be a race between the fast-gup and the fork() code, > even if has_pinned is always set. > > > > > Otherwise it races like: > > > > pin_user_pages_fast() fork() > > atomic_set(has_pinned, 1); > > [..] > > atomic_read(page->_refcount) //false > > // skipped atomic_read(has_pinned) > > atomic_add(page->_refcount) > > ordered check write protect() > > ordered set write protect() > > > > And now have a write protect on a DMA pinned page, which is the > > invarient we are trying to create. > > > > The best algorithm I've thought of is something like: > > > > pte_map_lock() > > if (page) { > > if (wp) { > > ptep_set_wrprotect() > > /* Order with try_grab_compound_head(), either we see > > * page_maybe_dma_pinned(), or they see the wrprotect */ > > get_page(); > > Is this get_page() a must to be after ptep_set_wrprotect() explicitly? IIUC > what we need is to order ptep_set_wrprotect() and page_maybe_dma_pinned() here. > E.g., would a "mb()" work? > > Another thing is, do we need similar thing for e.g. gup_pte_range(), so that > to guarantee ordering of try_grab_compound_head() and the pte change check? > > > > > if (page_maybe_dma_pinned() && READ_ONCE(src_mm->has_pinned)) { > > put_page(); > > ptep_clear_wrprotect() > > > > // do copy > > return > > } > > } else { > > get_page(); > > } > > page_dup_rmap() > > pte_unmap_lock() > > > > Then the do_wp_page() path would have to detect that the page is not > > write protected under the pte lock inside the fault handler and just > > do nothing. > > Yes, iiuc do_wp_page() should be able to handle spurious write page faults like > this already, as below: > > vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); > spin_lock(vmf->ptl); > ... > if (vmf->flags & FAULT_FLAG_WRITE) { > if (!pte_write(entry)) > return do_wp_page(vmf); > entry = pte_mkdirty(entry); > } > > So when spin_lock() returns: > > - When it's a real cow (not pinned pages; we write-protected it and it keeps > write-protected), we should do cow here as usual. > > - When it's a fake cow (pinned pages), the write bit should have been > recovered before the page table lock released, and we'll skip do_wp_page() > and retry the page fault immediately. > > > Ie the set/clear could be visible to the CPU and trigger a > > spurious fault, but never trigger a COW. > > > > Thus 'wp' becomes a 'lock' that prevents GUP from returning this page. > > Another question is, how about read fast-gup for pinning? Because we can't use > the write-protect mechanism to block a read gup. I remember we've discussed > similar things and iirc your point is "pinned pages should always be with > WRITE". However now I still doubt it... Because I feel like read gup is still > legal (as I mentioned previously - when device purely writes to the page and > the processor only reads from it). > > > > > Very tricky, deserves a huge comment near the ptep_clear_wrprotect() > > > > Consider the above algorithm beside the gup_fast() algorithm: > > > > if (!pte_access_permitted(pte, flags & FOLL_WRITE)) > > goto pte_unmap; > > [..] > > head = try_grab_compound_head(page, 1, flags); > > if (!head) > > goto pte_unmap; > > if (unlikely(pte_val(pte) != pte_val(*ptep))) { > > put_compound_head(head, 1, flags); > > goto pte_unmap; > > > > That last *ptep will check that the WP is not set after making > > page_maybe_dma_pinned() true. > > > > It still looks reasonable, the extra work is still just the additional > > atomic in page_maybe_dma_pinned(), just everything else has to be very > > carefully sequenced due to unlocked page table accessors. > > Tricky! I'm still thinking about some easier way but no much clue so far. > Hopefully we'll figure out something solid soon. Hmm, how about something like below? Would this be acceptable? ------8<-------- diff --git a/mm/gup.c b/mm/gup.c index 2d9019bf1773..698bc2b520ac 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2136,6 +2136,18 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; + spinlock_t *ptl = NULL; + + /* + * More strict with FOLL_PIN, otherwise it could race with fork(). The + * page table lock guarantees that fork() will capture all the pinned + * pages when dup_mm() and do proper page copy on them. + */ + if (flags & FOLL_PIN) { + ptl = pte_lockptr(mm, pmd); + if (!spin_trylock(ptl)) + return 0; + } ptem = ptep = pte_offset_map(&pmd, addr); do { @@ -2200,6 +2212,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, ret = 1; pte_unmap: + if (ptl) + spin_unlock(ptl); if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); ------8<-------- Both of the solution would fail some fast-gups that might have succeeded in the past. The latter solution might even fail more (because pmd lock should be definitely bigger than a single pte wrprotect), however afaict it's still a very, very corner case as it's fast-gup+FOLL_PIN+lockfail (and not to mention fast-gup should be allowed to fail). To confirm it can fail, I also checked up that we have only one caller of pin_user_pages_fast_only(), which is i915_gem_userptr_get_pages(). While it's: if (mm == current->mm) { pvec = kvmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (pvec) { /* defer to worker if malloc fails */ if (!i915_gem_object_is_readonly(obj)) gup_flags |= FOLL_WRITE; pinned = pin_user_pages_fast_only(obj->userptr.ptr, num_pages, gup_flags, pvec); } } So looks like it can fallback to something slow too even if purely unlucky. So looks safe so far for either solution above. -- Peter Xu