Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 7 Jun 2021 19:03:23 +0100
From:   Matthew Wilcox <willy@infradead.org>
To:     Jann Horn <jannh@google.com>
Cc:     Linux-MM <linux-mm@kvack.org>, Zi Yan <ziy@nvidia.com>,
        Peter Xu <peterx@redhat.com>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
        Andrew Morton <akpm@linux-foundation.org>,
        chinwen.chang@mediatek.com,
        kernel list <linux-kernel@vger.kernel.org>,
        syzkaller-bugs <syzkaller-bugs@googlegroups.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Michel Lespinasse <walken@google.com>,
        syzbot <syzbot+1f52b3a18d5633fa7f82@syzkaller.appspotmail.com>
Subject: Re: split_huge_page_to_list() races with page_mapcount() on
 migration entry in smaps code? [was: Re: [syzbot] kernel BUG in
 __page_mapcount]
Message-ID: <YL5fayfh03Wecyd7@casper.infradead.org>
References: <00000000000017977605c395a751@google.com>
 <CAG48ez0M=iwJu=Q8yUQHD-+eZDg6ZF8QCF86Sb=CN1petP=Y0Q@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAG48ez0M=iwJu=Q8yUQHD-+eZDg6ZF8QCF86Sb=CN1petP=Y0Q@mail.gmail.com>
Precedence: bulk

On Mon, Jun 07, 2021 at 07:27:23PM +0200, Jann Horn wrote:
> === Short summary ===
> I believe the issue here is a race between /proc/*/smaps and
> split_huge_page_to_list():
> 
> The codepath for /proc/*/smaps walks the pagetables and (e.g. in
> smaps_account()) calls page_mapcount() not just on pages from normal
> PTEs but also on migration entries (since commit b1d4d9e0cbd0a
> "proc/smaps: carefully handle migration entries", from Linux v3.5).
> page_mapcount() expects compound pages to be stable.
> 
> The split_huge_page_to_list() path first protects the compound page by
> locking it and replacing all its PTEs with migration entries (since
> the THP rewrite in v4.5, I think?), then does the actual splitting
> using __split_huge_page().
> 
> So there's a mismatch of expectations here:
> The smaps code expects that migration entries point to stable compound
> pages, while the THP code expects that it's okay to split a compound
> page while it has migration entries.

Will it be a colossal performance penalty if we always get the page
refcount after looking it up?  That will cause split_huge_page() to
fail to split the page if it hits this race.