From: Peter Zijlstra <peterz@infradead.org>
To: Stephane Eranian <eranian@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
"mingo@elte.hu" <mingo@elte.hu>,
"ak@linux.intel.com" <ak@linux.intel.com>,
Jiri Olsa <jolsa@redhat.com>,
"Yan, Zheng" <zheng.z.yan@intel.com>,
Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Subject: Re: [PATCH 5/9] perf/x86: implement cross-HT corruption bug workaround
Date: Thu, 5 Jun 2014 16:31:40 +0200 [thread overview]
Message-ID: <20140605143140.GN6758@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <CABPqkBQ9_HWN-LbwoxqDY52gHjevA_8fSoYbcv=wp04Rtp2ESg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1035 bytes --]
On Thu, Jun 05, 2014 at 04:26:38PM +0200, Stephane Eranian wrote:
> On Thu, Jun 5, 2014 at 4:21 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > We could limit each cpu to num_counters/2 exclusive slots. That'll still
> > be painful with some constrained events I imagine, but in general that
> > should 'work' I suppose.
>
> That is probably the easiest solution, just modify the dynamic constraint
> mask some more. Have not yet tried it.
Right, see what happens :-)
> The repatriation of the leaked count is not so easy either. Need to IPI
> the other HT. There may be some restrictions as to when we can
> safely do this.
Yes, that'll be 'interesting'. You typically cannot do things like
smp_function_call() from IRQ/NMI context. Which leaves you to
asynchonous IPIs.
I suppose the easiest way is to simply push the count out to the right
event when you reprogram the sibling. And maybe kick it every so often
to force do this just in case the PMU doesn't get reprogrammed a lot.
Still tricky.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
next prev parent reply other threads:[~2014-06-05 14:31 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-04 21:34 [PATCH 0/9] perf/x86: implement HT counter corruption workaround Stephane Eranian
2014-06-04 21:34 ` [PATCH 1/9] perf,x86: rename er_flags to flags Stephane Eranian
2014-06-04 21:34 ` [PATCH 2/9] pref/x86: vectorize cpuc->kfree_on_online Stephane Eranian
2014-06-04 21:34 ` [PATCH 3/9] perf/x86: add 3 new scheduling callbacks Stephane Eranian
2014-06-04 21:34 ` [PATCH 4/9] perf/x86: add cross-HT counter exclusion infrastructure Stephane Eranian
2014-06-05 7:47 ` Peter Zijlstra
2014-06-05 10:51 ` Stephane Eranian
2014-06-05 8:04 ` Peter Zijlstra
2014-06-05 13:36 ` Maria Dimakopoulou
2014-06-05 8:29 ` Peter Zijlstra
2014-06-05 21:33 ` Andi Kleen
2014-06-05 21:38 ` Stephane Eranian
2014-06-10 11:53 ` Stephane Eranian
2014-06-10 12:26 ` Peter Zijlstra
2014-06-04 21:34 ` [PATCH 5/9] perf/x86: implement cross-HT corruption bug workaround Stephane Eranian
2014-06-05 13:38 ` Peter Zijlstra
2014-06-05 13:42 ` Peter Zijlstra
2014-06-05 13:48 ` Peter Zijlstra
2014-06-05 14:01 ` Maria Dimakopoulou
2014-06-05 14:04 ` Borislav Petkov
2014-06-05 14:11 ` Peter Zijlstra
2014-06-05 14:14 ` Peter Zijlstra
2014-06-05 14:24 ` Maria Dimakopoulou
2014-06-05 14:04 ` Peter Zijlstra
2014-06-05 14:15 ` Stephane Eranian
2014-06-05 14:21 ` Peter Zijlstra
2014-06-05 14:26 ` Stephane Eranian
2014-06-05 14:31 ` Peter Zijlstra [this message]
2014-06-05 15:31 ` Stephane Eranian
2014-06-04 21:34 ` [PATCH 6/9] perf/x86: enforce HT bug workaround for SNB/IVB/HSW Stephane Eranian
2014-06-04 21:34 ` [PATCH 7/9] perf/x86: enforce HT bug workaround with PEBS " Stephane Eranian
2014-06-04 21:34 ` [PATCH 8/9] perf/x86: fix intel_get_event_constraints() for dynamic constraints Stephane Eranian
2014-06-04 21:34 ` [PATCH 9/9] perf/x86: add syfs entry to disable HT bug workaround Stephane Eranian
2014-06-05 8:32 ` Matt Fleming
2014-06-05 9:29 ` Stephane Eranian
2014-06-05 10:01 ` Matt Fleming
2014-06-05 10:19 ` Stephane Eranian
2014-06-05 11:16 ` Matt Fleming
2014-06-05 12:02 ` Stephane Eranian
2014-06-05 13:27 ` Borislav Petkov
2014-06-05 13:42 ` Stephane Eranian
2014-06-05 14:03 ` Borislav Petkov
2014-06-05 14:45 ` Maria Dimakopoulou
2014-06-05 15:17 ` Borislav Petkov
2014-06-05 16:39 ` Maria Dimakopoulou
2014-06-05 16:47 ` Stephane Eranian
2014-06-05 16:52 ` Borislav Petkov
2014-06-05 18:00 ` Maria Dimakopoulou
2014-06-05 23:29 ` Andi Kleen
2014-06-06 8:28 ` Matt Fleming
2014-06-05 12:50 ` Peter Zijlstra
2014-06-05 12:55 ` Stephane Eranian
2014-06-05 12:59 ` Peter Zijlstra
2014-06-05 13:16 ` Stephane Eranian
2014-06-05 13:26 ` Peter Zijlstra
2014-06-05 13:19 ` Peter Zijlstra
2014-06-05 13:26 ` Stephane Eranian
2014-06-04 22:28 ` [PATCH 0/9] perf/x86: implement HT counter corruption workaround Andi Kleen
2014-06-05 12:45 ` Stephane Eranian
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=20140605143140.GN6758@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=maria.n.dimakopoulou@gmail.com \
--cc=mingo@elte.hu \
--cc=zheng.z.yan@intel.com \
/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