From: Josh Poimboeuf <jpoimboe@redhat.com>
To: speck@linutronix.de
Subject: [MODERATED] Re: [patch V5 09/14] MDS basics 9
Date: Fri, 1 Mar 2019 10:40:22 -0600 [thread overview]
Message-ID: <20190301164022.uxpvtuzwlfdylqri@treble> (raw)
In-Reply-To: <alpine.DEB.2.21.1903011650460.1638@nanos.tec.linutronix.de>
On Fri, Mar 01, 2019 at 05:03:39PM +0100, speck for Thomas Gleixner wrote:
> On Fri, 1 Mar 2019, speck for Josh Poimboeuf wrote:
> > On Wed, Feb 27, 2019 at 04:09:48PM +0100, speck for Thomas Gleixner wrote:
> > > Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
> > > From: Thomas Gleixner <tglx@linutronix.de>
> > >
> > > Add a static key which controls the invocation of the CPU buffer clear
> > > mechanism on idle entry. This is independent of other MDS mitigations
> > > because the idle entry invocation to mitigate the potential leakage due to
> > > store buffer repartitioning is only necessary on SMT systems.
> > >
> > > Add the actual invocations to the different halt/mwait variants which
> > > covers all usage sites. mwaitx is not patched as it's not available on
> > > Intel CPUs.
> > >
> > > The buffer clear is only invoked before entering the C-State to prevent
> > > that stale data from the idling CPU is spilled to the Hyper-Thread sibling
> > > after the Store buffer got repartitioned and all entries are available to
> > > the non idle sibling.
> >
> > Andrea brought up a good question privately -- this patch mitigates
> > MSBDS for HT, but HT will still be susceptible to the other two MDS
> > issues. So what's the point? It seems this patch only protects people
> > who don't care about MDS in the first place.
>
> Indeed for most CPU models it's pointless.
>
> The ones which are only affected by MSBDS are Atom Silvermont/Airmont which
> are all single threaded and the XEON PHIs.
>
> For XEON PHI it actually makes sense because XEON PHI does not have L1TF
> either.
>
> But yes, for everything else it's just window dressing.
Makes sense. I didn't realize that some CPUs were affected by MSBDS and
not other MDSes.
Can you add that justification to the documentation and/or patch
description?
--
Josh
next prev parent reply other threads:[~2019-03-01 16:40 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-27 15:09 [patch V5 00/14] MDS basics 0 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 01/14] MDS basics 1 Thomas Gleixner
2019-02-28 13:08 ` Thomas Gleixner
2019-02-27 15:09 ` [patch V5 02/14] MDS basics 2 Thomas Gleixner
2019-02-28 13:55 ` [MODERATED] " Josh Poimboeuf
2019-02-28 14:09 ` Thomas Gleixner
2019-02-28 20:23 ` [MODERATED] " Josh Poimboeuf
2019-03-01 16:04 ` Thomas Gleixner
2019-02-27 15:09 ` [patch V5 03/14] MDS basics 3 Thomas Gleixner
2019-02-27 16:34 ` [MODERATED] " Greg KH
2019-02-27 15:09 ` [patch V5 04/14] MDS basics 4 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 05/14] MDS basics 5 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 06/14] MDS basics 6 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 07/14] MDS basics 7 Thomas Gleixner
2019-02-27 17:07 ` [MODERATED] " Greg KH
2019-02-27 15:09 ` [patch V5 08/14] MDS basics 8 Thomas Gleixner
2019-02-28 8:11 ` [MODERATED] " Greg KH
2019-02-27 15:09 ` [patch V5 09/14] MDS basics 9 Thomas Gleixner
2019-03-01 14:04 ` [MODERATED] " Josh Poimboeuf
2019-03-01 16:03 ` Thomas Gleixner
2019-03-01 16:40 ` Josh Poimboeuf [this message]
2019-03-01 18:39 ` [MODERATED] " Josh Poimboeuf
2019-03-01 19:15 ` Thomas Gleixner
2019-03-01 22:38 ` [MODERATED] " Andrea Arcangeli
2019-03-01 22:58 ` Thomas Gleixner
2019-03-02 19:22 ` [MODERATED] Re: [SPAM] " Dave Hansen
2019-03-02 20:39 ` Thomas Gleixner
2019-02-27 15:09 ` [patch V5 10/14] MDS basics 10 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 11/14] MDS basics 11 Thomas Gleixner
2019-02-27 15:09 ` [patch V5 12/14] MDS basics 12 Thomas Gleixner
2019-03-01 22:00 ` [MODERATED] " mark gross
2019-02-27 15:09 ` [patch V5 13/14] MDS basics 13 Thomas Gleixner
2019-03-01 22:04 ` [MODERATED] " mark gross
2019-02-27 15:09 ` [patch V5 14/14] MDS basics 14 Thomas Gleixner
2019-02-27 17:49 ` Thomas Gleixner
2019-02-27 16:26 ` [MODERATED] Re: [patch V5 00/14] MDS basics 0 Linus Torvalds
2019-02-27 17:51 ` Thomas Gleixner
2019-02-27 18:13 ` Thomas Gleixner
2019-02-27 19:50 ` [MODERATED] " Linus Torvalds
2019-02-27 20:05 ` Thomas Gleixner
2019-02-27 21:04 ` Thomas Gleixner
2019-02-28 1:04 ` [MODERATED] " Josh Poimboeuf
2019-02-27 23:06 ` mark gross
2019-02-28 6:58 ` Thomas Gleixner
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=20190301164022.uxpvtuzwlfdylqri@treble \
--to=jpoimboe@redhat.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).