From: David Woodhouse <dwmw2@infradead.org>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Dave Hansen <dave.hansen@intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linuxfoundation.org>,
x86@kernel.org, Borislav Petkov <bp@alien8.de>,
Tim Chen <tim.c.chen@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>,
Greg KH <gregkh@linuxfoundation.org>,
Andy Lutomirski <luto@kernel.org>,
Arjan Van De Ven <arjan.van.de.ven@intel.com>
Subject: Re: [patch RFC 5/5] x86/speculation: Add basic speculation control code
Date: Wed, 10 Jan 2018 12:09:34 +0000 [thread overview]
Message-ID: <1515586174.22302.126.camel@infradead.org> (raw)
In-Reply-To: <20180110120158.GB9706@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 977 bytes --]
On Wed, 2018-01-10 at 13:01 +0100, Andrea Arcangeli wrote:
>
> > On all current hardware, if you only set IBRS when you exit a guest,
> > then you are not protecting yourself from userspace at all. IBRS acts
> > as a *barrier* in all current hardware.
>
> Kernel memory is 100% protected if you set only IBRS at vmexit.
>
> Once IBRS is set, there's no way any userland (nor host nor guest) can
> attack the kernel memory through spectre variant#2.
That is not consistent with the documentation I've seen, which Intel
have so far utterly failed to publish AFAICT.
"a near indirect jump/call/return may be affected by code in a less privileged
prediction mode that executed AFTER IBRS mode was last written with a value of 1"
The kernel is only protected from branch targets set in userspace
*BEFORE* the IBRS mode was last set to 1. If you set it to 1, then
leave it like that while you run userspace and then kernel code again,
you are not protected.
[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 5213 bytes --]
next prev parent reply other threads:[~2018-01-10 12:09 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-10 1:06 [patch RFC 0/5] x86/spectre_v2: Initial integration of IBRS into the spectre_v2 mechanics Thomas Gleixner
2018-01-10 1:06 ` [patch RFC 1/5] x86/CPU: Sync CPU feature flags late Thomas Gleixner
2018-01-10 1:37 ` Dave Hansen
2018-01-10 1:39 ` Van De Ven, Arjan
2018-01-10 1:47 ` Thomas Gleixner
2018-01-10 2:57 ` Andy Lutomirski
2018-01-10 11:02 ` Thomas Gleixner
2018-01-10 1:44 ` Thomas Gleixner
2018-01-10 6:20 ` Ingo Molnar
2018-01-10 11:33 ` Borislav Petkov
2018-01-10 12:38 ` Thomas Gleixner
2018-01-10 1:06 ` [patch RFC 2/5] x86/spectre: Simplify spectre code a bit Thomas Gleixner
2018-01-10 6:22 ` Ingo Molnar
2018-01-10 1:06 ` [patch RFC 3/5] x86/spectre: Prepare for IBRS selection Thomas Gleixner
2018-01-10 1:51 ` Dave Hansen
2018-01-10 1:06 ` [patch RFC 4/5] x86/cpufeatures: Detect Speculation control feature Thomas Gleixner
2018-01-10 6:32 ` Ingo Molnar
2018-01-10 11:06 ` Thomas Gleixner
2018-01-10 1:06 ` [patch RFC 5/5] x86/speculation: Add basic speculation control code Thomas Gleixner
2018-01-10 2:02 ` Dave Hansen
2018-01-10 4:11 ` Justin Forbes
2018-01-10 9:22 ` Peter Zijlstra
2018-01-10 9:27 ` David Woodhouse
2018-01-10 10:03 ` Peter Zijlstra
2018-01-10 11:22 ` David Woodhouse
2018-01-10 11:41 ` Thomas Gleixner
2018-01-10 11:45 ` Peter Zijlstra
2018-01-10 11:54 ` Andrea Arcangeli
2018-01-10 11:58 ` David Woodhouse
2018-01-10 12:01 ` Andrea Arcangeli
2018-01-10 12:07 ` Andrea Arcangeli
2018-01-10 12:12 ` David Woodhouse
2018-01-10 12:20 ` Andrea Arcangeli
2018-01-10 12:27 ` Andrea Arcangeli
2018-01-10 13:42 ` Van De Ven, Arjan
2018-01-10 12:09 ` David Woodhouse [this message]
2018-01-10 12:17 ` Andrea Arcangeli
2018-01-10 12:29 ` David Woodhouse
2018-01-10 12:41 ` Andrea Arcangeli
2018-01-10 12:47 ` Jiri Kosina
2018-01-10 12:51 ` David Woodhouse
2018-01-10 13:02 ` Andrea Arcangeli
2018-01-10 13:05 ` Andrea Arcangeli
2018-01-10 13:10 ` Andrea Arcangeli
2018-01-10 13:12 ` Andrea Arcangeli
2018-01-10 12:57 ` Andrea Arcangeli
2018-01-10 13:07 ` David Woodhouse
2018-01-10 13:45 ` Van De Ven, Arjan
2018-01-10 13:52 ` Andrea Arcangeli
2018-01-10 13:53 ` Van De Ven, Arjan
2018-01-10 21:35 ` Tim Chen
2018-01-10 22:13 ` Andrea Arcangeli
2018-01-10 13:46 ` Thomas Gleixner
2018-01-10 13:51 ` Van De Ven, Arjan
2018-01-10 13:53 ` Thomas Gleixner
2018-01-10 13:58 ` David Woodhouse
2018-01-10 14:10 ` Andrea Arcangeli
2018-01-10 14:14 ` Van De Ven, Arjan
2018-01-10 14:59 ` Dave Hansen
2018-01-10 15:13 ` Andrea Arcangeli
2018-01-10 15:24 ` David Woodhouse
2018-01-10 15:47 ` Andrea Arcangeli
2018-01-10 15:56 ` David Woodhouse
2018-01-10 13:10 ` Jiri Kosina
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=1515586174.22302.126.camel@infradead.org \
--to=dwmw2@infradead.org \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=arjan.van.de.ven@intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@intel.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linuxfoundation.org \
--cc=x86@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
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
all inboxes | Powered by JetHome®