linux-kernel - Re: [PATCH 3/3] mm/mincore: provide mapped status when cached status is not allowed

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: <e1478ab8-e009-9bdd-3866-f319bd7259a0@suse.cz>
Date:   Fri, 1 Feb 2019 10:27:38 +0100
From:   Vlastimil Babka <vbabka@...e.cz>
To:     Michal Hocko <mhocko@...nel.org>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        linux-api@...r.kernel.org, Peter Zijlstra <peterz@...radead.org>,
        Greg KH <gregkh@...uxfoundation.org>,
        Jann Horn <jannh@...gle.com>, Jiri Kosina <jikos@...nel.org>,
        Dominique Martinet <asmadeus@...ewreck.org>,
        Andy Lutomirski <luto@...capital.net>,
        Dave Chinner <david@...morbit.com>,
        Kevin Easton <kevin@...rana.org>,
        Matthew Wilcox <willy@...radead.org>,
        Cyril Hrubis <chrubis@...e.cz>, Tejun Heo <tj@...nel.org>,
        "Kirill A . Shutemov" <kirill@...temov.name>,
        Daniel Gruss <daniel@...ss.cc>, Jiri Kosina <jkosina@...e.cz>,
        Josh Snyder <joshs@...flix.com>
Subject: Re: [PATCH 3/3] mm/mincore: provide mapped status when cached status
 is not allowed

On 2/1/19 10:11 AM, Michal Hocko wrote:
> On Fri 01-02-19 10:04:23, Vlastimil Babka wrote:
>> The side channel exists anyway as long as process can e.g. check if
>> its rss shrinked, and I doubt we are going to remove that possibility.
> 
> Well, but rss update will not tell you that the page has been faulted in
> which is the most interesting part.

Sure, but the patch doesn't add back that capability neither. It allows
to recognize page being reclaimed, and I argue you can infer that from
rss change as well. That change is mentioned in the last paragraph in
changelog, and I thought "add a hard to evaluate side channel" in your
reply referred to that. It doesn't add back the "original" side channel
to detect somebody else accessed a page.

> You shouldn't be able to sniff on
> /proc/$vicimt/smaps as an attacker.