Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Dave Hansen <dave.hansen@intel.com>
To: Minchan Kim <minchan@kernel.org>, Michal Hocko <mhocko@kernel.org>
Cc: Jann Horn <jannh@google.com>, Linux-MM <linux-mm@kvack.org>,
	kernel list <linux-kernel@vger.kernel.org>,
	Daniel Colascione <dancol@google.com>,
	"Joel Fernandes (Google)" <joel@joelfernandes.org>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: interaction of MADV_PAGEOUT with CoW anonymous mappings?
Date: Thu, 12 Mar 2020 13:26:16 -0700
Message-ID: <501cce5b-005a-f559-7c5b-f574d1d65deb@intel.com> (raw)
In-Reply-To: <20200312201602.GA68817@google.com>

On 3/12/20 1:16 PM, Minchan Kim wrote:
> On Thu, Mar 12, 2020 at 09:22:48AM +0100, Michal Hocko wrote:
> I't likde to wait Jann's reply since Dave gave his opinion about the vulnerability.
> https://lore.kernel.org/linux-mm/cf95db88-968d-fee5-1c15-10d024c09d8a@intel.com/
> Jann, could you give your insigh about that practically it's possible?

FWIW, just checking for mapcount>=1 seems like a pretty sane fix to me.
 I went looking at doing it another way, but Michal was quite correct.
We'd probably end up having to special-case something underneath
shrink_page_list().

> A real dumb question to understand vulnerability:
> 
> The attacker would be able to trigger heavy memory consumption so that he
> could make paging them out without MADV_PAGEOUT. I know MADV_PAGEOUT makes
> it easier but he still could do without MADV_PAGEOUT.
> What makes difference here?

Causing memory pressure is quite a bit more disruptive than
MADV_PAGEOUT.  It's a much more blunt instrument and is likely to result
in a lot of collateral damage and a lot of I/O.

MADV_PAGEOUT is *surgical*.  You can target one very specific page if,
for instance, you think that your victim is reading it in a way that is
vulnerable.  You can also do it with zero I/O (after the initial pageout).

> To clarify how MADV_PAGEWORK works:
> If other process has accessed the page so that his page table has access
> bit marked, MADV_PAGEOUT couldn't page it out.

The attacker doesn't need to get the victim to get a major fault, it
just needs to induce *a* fault.  I actually did an experiment to see how
this would work in practice.

1. Allocate some memory(), touch it
2. fork()
3. In the parent: Loop reading the memory
4. In the child: loop running MADV_PAGEOUT

The pages stayed in the swap cache and the parent reading the memory saw
a constant stream of faults.


  reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-10 18:08 Jann Horn
2020-03-10 18:48 ` Michal Hocko
2020-03-10 19:11   ` Jann Horn
2020-03-10 21:09     ` Michal Hocko
2020-03-10 22:48       ` Dave Hansen
2020-03-11  8:45         ` Michal Hocko
2020-03-11 22:02           ` Minchan Kim
2020-03-11 23:53           ` Shakeel Butt
2020-03-12  0:18             ` Minchan Kim
2020-03-12  2:03               ` Daniel Colascione
2020-03-12 15:15                 ` Shakeel Butt
2020-03-10 20:19   ` Daniel Colascione
2020-03-10 21:40     ` Jann Horn
2020-03-10 21:52       ` Daniel Colascione
2020-03-10 22:14 ` Minchan Kim
2020-03-12  8:22 ` Michal Hocko
2020-03-12 15:40   ` Vlastimil Babka
2020-03-12 20:16   ` Minchan Kim
2020-03-12 20:26     ` Dave Hansen [this message]
2020-03-12 20:41     ` Michal Hocko
2020-03-13  2:08       ` Minchan Kim
2020-03-13  8:05         ` Michal Hocko
2020-03-13 20:59           ` Minchan Kim
2020-03-16  9:20             ` Michal Hocko
2020-03-17  1:43               ` Minchan Kim
2020-03-17  7:12                 ` Michal Hocko
2020-03-17 15:00                   ` Minchan Kim
2020-03-17 15:58                     ` Michal Hocko
2020-03-17 17:20                       ` Minchan Kim
2020-03-12 21:41     ` Dave Hansen
2020-03-13  2:00       ` Minchan Kim
2020-03-13 16:59         ` Dave Hansen
2020-03-13 21:13           ` Minchan Kim
2020-03-12 23:29     ` Jann Horn

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=501cce5b-005a-f559-7c5b-f574d1d65deb@intel.com \
    --to=dave.hansen@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dancol@google.com \
    --cc=jannh@google.com \
    --cc=joel@joelfernandes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=minchan@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git