From: Andrew Cooper <andrew.cooper3@citrix.com>
To: speck@linutronix.de
Subject: [MODERATED] Re: LVI
Date: Tue, 19 Nov 2019 18:22:09 +0000 [thread overview]
Message-ID: <59d8550a-a217-7d30-9b44-e6a31cb4addf@citrix.com> (raw)
In-Reply-To: <20191119174008.7dbymix2eo4mrv57@treble>
[-- Attachment #1: Type: text/plain, Size: 2018 bytes --]
On 19/11/2019 17:40, speck for Josh Poimboeuf wrote:
> Hi,
>
> What kernel changes (if any) are needed for LVI? I haven't seen any
> discussion here.
>
> The last I heard, the official CRD was Dec 10, but was likely to move to
> March.
>
> For the uninitiated, LVI is a reverse MDS/L1TF:
>
> 1) Victim puts secret data in CPU buffer or L1. Alternatively,
> attacker puts address of secret data in CPU buffer or L1.
>
> 2) Attacker gets victim to fault or assist on a load. (Note that an
> assist gives a much bigger speculation window - it can be triggered
> if a page Accessed bit needs updating)
>
> 3) While waiting for the fault/assist to complete, victim speculatively
> reads CPU buffer or L1 to get data (or address) from step 1.
>
> 4) Victim gadgets expose the data via the usual L1 side channel.
I'd phrase this slightly differently, e.g. "Attacker puts something
deliberate in a CPU buffer or L1".
It doesn't have to be a secret, or an address of a secret. In the case
of ret hijacking, it is just the address of a disclosure gadget to
speculate to.
The important point of LVI is that a victim load ends up speculatively
using an attacker-chosen value.
> To protect the kernel, we'd presumably need to look for places where
> users can trigger a faulting/assisting load. For example,
> copy_from_user().
>
> copy_from_user() has an LFENCE between the access_ok() check and the
> actual copy to protect against Spectre v1. What if we move that LFENCE
> to *after* the copy? I think that would protect against both Spectre v1
> and LVI.
>
> Thoughts?
The lfence before protects from speculating into copy_from_user() with a
bad pointer. This protection is still necessary.
An lfence afterwards would be necessary to prevent (speculatively)
returning to calling context with bad data.
On current Intel parts, stac/clac have lfence semantics, but I don't
recall if this is intended to be relied upon in future parts.
~Andrew
next prev parent reply other threads:[~2019-11-19 18:22 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-19 17:40 [MODERATED] LVI Josh Poimboeuf
2019-11-19 17:51 ` [MODERATED] LVI Andrew Cooper
2019-11-19 18:27 ` Josh Poimboeuf
2019-11-19 19:26 ` Andrew Cooper
2019-11-20 9:52 ` Paolo Bonzini
2019-11-19 18:12 ` Greg KH
2019-11-19 18:21 ` Josh Poimboeuf
2019-11-19 18:46 ` Greg KH
2019-11-19 18:21 ` Paolo Bonzini
2019-11-19 18:22 ` Andrew Cooper [this message]
2019-11-19 18:27 ` Josh Poimboeuf
2019-11-19 18:36 ` Luck, Tony
2019-11-20 17:02 ` Greg KH
2019-11-19 18:39 ` Andrew Cooper
2019-11-19 21:00 ` Josh Poimboeuf
2019-11-19 21:03 ` Josh Poimboeuf
2019-11-20 14:11 ` Andrew Cooper
2019-11-20 8:04 ` Peter Zijlstra
2019-11-20 9:49 ` Andrew Cooper
2019-11-20 17:13 ` Josh Poimboeuf
2019-11-20 17:25 ` Greg KH
2019-11-20 17:29 ` Tyler Hicks
2019-11-20 17:30 ` Andrew Cooper
2019-11-20 17:46 ` Greg KH
2019-11-20 19:09 ` Peter Zijlstra
2019-11-20 19:19 ` Greg KH
2019-11-21 0:50 ` LVI Thomas Gleixner
2019-11-21 13:45 ` [MODERATED] LVI Greg KH
2019-11-26 0:54 ` Andi Kleen
2019-11-26 10:37 ` Greg KH
2019-11-26 18:23 ` Andi Kleen
2019-11-27 7:38 ` Greg KH
2019-11-26 10:55 ` Paolo Bonzini
2019-11-26 18:28 ` Andi Kleen
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=59d8550a-a217-7d30-9b44-e6a31cb4addf@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=speck@linutronix.de \
/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).