From: Jann Horn <jannh@google.com>
To: pasha.tatashin@soleen.com
Cc: oleksandr@natalenko.name, linux-doc@vger.kernel.org,
kernel list <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
timofey.titovets@synesis.ru, Matthew Wilcox <willy@infradead.org>,
Daniel Gruss <daniel@gruss.cc>
Subject: Re: [PATCH V3] KSM: allow dedup all tasks memory
Date: Tue, 13 Nov 2018 21:26:51 +0100 [thread overview]
Message-ID: <CAG48ez29kArZTU=MgsVxWbuTZZ+sCrxeQ3FkDKpmQnj_MZ5hTg@mail.gmail.com> (raw)
In-Reply-To: <20181113175930.3g65rlhbaimstq7g@soleen.tm1wkky2jk1uhgkn0ivaxijq1c.bx.internal.cloudapp.net>
+cc Daniel Gruss
On Tue, Nov 13, 2018 at 6:59 PM Pavel Tatashin
<pasha.tatashin@soleen.com> wrote:
> On 18-11-13 15:23:50, Oleksandr Natalenko wrote:
> > Hi.
> >
> > > Yep. However, so far, it requires an application to explicitly opt in
> > > to this behavior, so it's not all that bad. Your patch would remove
> > > the requirement for application opt-in, which, in my opinion, makes
> > > this way worse and reduces the number of applications for which this
> > > is acceptable.
> >
> > The default is to maintain the old behaviour, so unless the explicit
> > decision is made by the administrator, no extra risk is imposed.
>
> The new interface would be more tolerable if it honored MADV_UNMERGEABLE:
>
> KSM default on: merge everything except when MADV_UNMERGEABLE is
> excplicitly set.
>
> KSM default off: merge only when MADV_MERGEABLE is set.
>
> The proposed change won't honor MADV_UNMERGEABLE, meaning that
> application programmers won't have a way to prevent sensitive data to be
> every merged. So, I think, we should keep allow an explicit opt-out
> option for applications.
>
> >
> > > As far as I know, basically nobody is using KSM at this point. There
> > > are blog posts from several cloud providers about these security risks
> > > that explicitly state that they're not using memory deduplication.
> >
> > I tend to disagree here. Based on both what my company does and what UKSM
> > users do, memory dedup is a desired option (note "option" word here, not the
> > default choice).
>
> Lightweight containers is a use case for KSM: when many VMs share the
> same small kernel. KSM is used in production by large cloud vendors.
Wait, what? Can you name specific ones? Nowadays, enabling KSM for
untrusted VMs seems like a terrible idea to me, security-wise.
Google says at <https://cloud.google.com/blog/products/gcp/7-ways-we-harden-our-kvm-hypervisor-at-google-cloud-security-in-plaintext>:
"Compute Engine and Container Engine are not vulnerable to this kind
of attack, since they do not use KSM."
An AWS employee says at
<https://forums.aws.amazon.com/thread.jspa?threadID=238519&tstart=0&messageID=739485#739485>:
"memory de-duplication is not enabled by Amazon EC2's hypervisor"
In my opinion, KSM is fundamentally insecure for systems hosting
multiple VMs that don't trust each other. I don't think anyone writes
cryptographic software under the assumption that an attacker will be
given the ability to query whether a given page of data exists
anywhere else on the system.
next prev parent reply other threads:[~2018-11-13 20:27 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <<CAG48ez0ZprqUYGZFxcrY6U3Dnwt77q1NJXzzpsn1XNkRuXVppw@mail.gmail.com>
2018-11-13 14:23 ` [PATCH V3] KSM: allow dedup all tasks memory Oleksandr Natalenko
2018-11-13 17:59 ` Pavel Tatashin
2018-11-13 18:17 ` Timofey Titovets
2018-11-13 18:35 ` Pavel Tatashin
2018-11-13 18:54 ` Timofey Titovets
2018-11-13 19:16 ` Pavel Tatashin
2018-11-13 22:40 ` Timofey Titovets
2018-11-13 22:53 ` Pavel Tatashin
2018-11-13 23:07 ` Timofey Titovets
2018-11-13 20:26 ` Jann Horn [this message]
2018-11-13 22:35 ` Pavel Tatashin
2018-11-13 18:20 Timofey Titovets
[not found] <<20181112231344.7161-1-timofey.titovets@synesis.ru>
2018-11-13 11:06 ` Oleksandr Natalenko
2018-11-13 11:56 ` Timofey Titovets
2018-11-13 16:33 ` Oleksandr Natalenko
2018-11-13 17:10 ` Timofey Titovets
2018-11-13 17:27 ` Oleksandr Natalenko
2018-11-13 17:44 ` Timofey Titovets
-- strict thread matches above, loose matches on Subject: below --
2018-11-12 23:13 Timofey Titovets
2018-11-13 1:49 ` Matthew Wilcox
2018-11-13 11:25 ` Timofey Titovets
2018-11-13 2:25 ` Pavel Tatashin
2018-11-13 11:40 ` Timofey Titovets
2018-11-13 18:42 ` Pavel Tatashin
2018-11-13 22:55 ` Timofey Titovets
2018-11-13 11:57 ` Jann Horn
2018-11-13 12:58 ` Timofey Titovets
2018-11-13 13:25 ` 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='CAG48ez29kArZTU=MgsVxWbuTZZ+sCrxeQ3FkDKpmQnj_MZ5hTg@mail.gmail.com' \
--to=jannh@google.com \
--cc=daniel@gruss.cc \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=oleksandr@natalenko.name \
--cc=pasha.tatashin@soleen.com \
--cc=timofey.titovets@synesis.ru \
--cc=willy@infradead.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).