All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: speck@linutronix.de
Subject: [MODERATED] Re: [patch 4/8] MDS basics 4
Date: Tue, 19 Feb 2019 17:17:49 +0100	[thread overview]
Message-ID: <20190219161749.GB32494@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20190219160913.GU16922@tassilo.jf.intel.com>

On Tue, Feb 19, 2019 at 08:09:13AM -0800, speck for Andi Kleen wrote:
> On Tue, Feb 19, 2019 at 03:07:59PM +0100, speck for Thomas Gleixner wrote:
> > On Tue, 19 Feb 2019, speck for Thomas Gleixner wrote:
> > > On Tue, 19 Feb 2019, speck for Andrew Cooper wrote:
> > > 
> > > > On 19/02/2019 12:44, speck for Thomas Gleixner wrote:
> > > > > Subject: [patch 4/8] x86/speculation/mds: Conditionaly 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.
> > > > >
> > > > > Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> > > > 
> > > > Unfortunately, clearing is needed on the exit from idle as well as the
> > > > entry.
> > > > 
> > > > This only impacts the store buffer (MSBDS, previously PSF) because it
> > > > gets statically re-partitioned when a thread comes in and out of idle.
> > > > 
> > > > >From the point of view of the thread going idle, when going idle my half
> > > > of the store buffers get given to the other thread and potentially leak
> > > > my secrets, whereas when coming out of idle, the other threads store
> > > > buffers get split with me, potentially leaking their secrets.
> > > 
> > > Duh, indeed. Easy enough to fix.
> > 
> > Delta patch below. Stupid me even mentioned the repartioning on both sides
> > in the changelog.
> 
> It's not needed.

But will the part of the store buffer that gets repartitioned not
contain state of the other sibling?

If it can see our data after we go idle; why can't we see its data when
we come out of idle?

  reply	other threads:[~2019-02-19 16:17 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-19 12:44 [patch 0/8] MDS basics 0 Thomas Gleixner
2019-02-19 12:44 ` [patch 1/8] MDS basics 1 Thomas Gleixner
2019-02-19 14:00   ` [MODERATED] " Borislav Petkov
2019-02-19 12:44 ` [patch 2/8] MDS basics 2 Thomas Gleixner
2019-02-19 12:44 ` [patch 3/8] MDS basics 3 Thomas Gleixner
2019-02-19 16:04   ` [MODERATED] " Andi Kleen
2019-02-19 21:44     ` Thomas Gleixner
2019-02-19 22:13       ` Thomas Gleixner
2019-02-20 16:59       ` [MODERATED] " Andi Kleen
2019-02-20 21:28         ` Thomas Gleixner
2019-02-19 12:44 ` [patch 4/8] MDS basics 4 Thomas Gleixner
2019-02-19 13:54   ` [MODERATED] " Andrew Cooper
2019-02-19 14:02     ` Thomas Gleixner
2019-02-19 14:07       ` Thomas Gleixner
2019-02-19 16:09         ` [MODERATED] " Andi Kleen
2019-02-19 16:17           ` Peter Zijlstra [this message]
2019-02-19 17:16       ` Thomas Gleixner
2019-02-19 16:08     ` [MODERATED] " Andi Kleen
2019-02-19 16:23       ` Andrew Cooper
2019-02-19 16:07   ` Andi Kleen
2019-02-19 18:29     ` Thomas Gleixner
2019-02-19 12:44 ` [patch 5/8] MDS basics 5 Thomas Gleixner
2019-02-19 15:07   ` Thomas Gleixner
2019-02-19 16:13     ` [MODERATED] " Andi Kleen
2019-02-19 17:37       ` Thomas Gleixner
2019-02-20  0:05         ` Thomas Gleixner
2019-02-19 16:03   ` [MODERATED] " Andi Kleen
2019-02-19 17:40     ` Thomas Gleixner
2019-02-19 17:44       ` [MODERATED] " Andrew Cooper
2019-02-19 17:52         ` Thomas Gleixner
2019-02-19 12:44 ` [patch 6/8] MDS basics 6 Thomas Gleixner
2019-02-19 12:44 ` [patch 7/8] MDS basics 7 Thomas Gleixner
2019-02-19 12:44 ` [patch 8/8] MDS basics 8 Thomas Gleixner
2019-02-19 14:17   ` [MODERATED] " Greg KH
2019-02-19 14:22     ` Thomas Gleixner
2019-02-19 17:27   ` [MODERATED] " Andrew Cooper
2019-02-19 14:03 ` [MODERATED] Re: [patch 0/8] MDS basics 0 Andrew Cooper
2019-02-19 14:09   ` Thomas Gleixner
2019-02-19 14:10   ` [MODERATED] " Tyler Hicks
2019-02-19 15:56 ` Andi Kleen
2019-02-19 17:42   ` Thomas Gleixner
2019-02-21 16:14 ` [MODERATED] Encrypted Message Jon Masters

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=20190219161749.GB32494@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.