linux-kernel - Re: [PATCH 4/5] mm: Do early cow for pinned pages during fork() for ptes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <24037577-0b96-4d8c-9487-8e788fbc29eb@nvidia.com>
Date:   Mon, 21 Sep 2020 17:08:39 -0700
From:   John Hubbard <jhubbard@...dia.com>
To:     Jann Horn <jannh@...gle.com>
CC:     Peter Xu <peterx@...hat.com>, Linux-MM <linux-mm@...ck.org>,
        kernel list <linux-kernel@...r.kernel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Michal Hocko <mhocko@...e.com>,
        "Kirill Shutemov" <kirill@...temov.name>,
        Oleg Nesterov <oleg@...hat.com>,
        "Kirill Tkhai" <ktkhai@...tuozzo.com>,
        Hugh Dickins <hughd@...gle.com>,
        "Leon Romanovsky" <leonro@...dia.com>, Jan Kara <jack@...e.cz>,
        Christoph Hellwig <hch@....de>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Andrea Arcangeli <aarcange@...hat.com>
Subject: Re: [PATCH 4/5] mm: Do early cow for pinned pages during fork() for
 ptes

On 9/21/20 3:27 PM, Jann Horn wrote:
> On Tue, Sep 22, 2020 at 12:18 AM John Hubbard <jhubbard@...dia.com> wrote:
>> On 9/21/20 2:55 PM, Jann Horn wrote:
>>> On Mon, Sep 21, 2020 at 11:20 PM Peter Xu <peterx@...hat.com> wrote:
>> ...
> Ah... the documentation you linked implies that FOLL_WRITE should more
> or less imply FOLL_PIN? I didn't realize that.
> 

hmmm, that does seem like a pretty close approximation. It's certainly
true that if we were only doing reads, and also never marking pages
dirty, that the file system writeback code would be OK.

For completeness we should add: even just reading a page is still a
problem, if one also marks the page as dirty (which is inconsistent and
wrong, but still). That's because the file system code can then break,
during writeback in particular.


thanks,
-- 
John Hubbard
NVIDIA