From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S932385AbbEZNk7 (ORCPT <rfc822;w@1wt.eu>);
	Tue, 26 May 2015 09:40:59 -0400
Received: from mail-oi0-f42.google.com ([209.85.218.42]:34207 "EHLO
	mail-oi0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1755096AbbEZNkz (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Tue, 26 May 2015 09:40:55 -0400
MIME-Version: 1.0
In-Reply-To: <20150526101548.GL3644@twins.programming.kicks-ass.net>
References: <20150522132905.416122812@infradead.org>
	<20150522133135.447912500@infradead.org>
	<CABPqkBSpmMUOhK4oAVVDYctwizyi5mSm=o+A4XmtivZAq-Z5HA@mail.gmail.com>
	<20150526101548.GL3644@twins.programming.kicks-ass.net>
Date: Tue, 26 May 2015 04:47:11 -0700
Message-ID: <CABPqkBSnJmnF-v1JXC2Wj0Qw1q+wa8WY3krVFWVP8VPix2se=w@mail.gmail.com>
Subject: Re: [PATCH v2 02/11] perf/x86: Improve HT workaround GP counter constraint
From: Stephane Eranian <eranian@google.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>, Vince Weaver <vincent.weaver@maine.edu>,
        Jiri Olsa <jolsa@redhat.com>, "Liang, Kan" <kan.liang@intel.com>,
        LKML <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, May 26, 2015 at 3:15 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> Please trim your email.
>
> On Tue, May 26, 2015 at 02:37:52AM -0700, Stephane Eranian wrote:
>> > @@ -822,8 +830,24 @@ int x86_schedule_events(struct cpu_hw_ev
>> >
>> >         /* slow path */
>> >         if (i != n) {
>> > +               int gpmax = x86_pmu.num_counters;
>> > +
>> > +               /*
>> > +                * Do not allow scheduling of more than half the available
>> > +                * generic counters.
>> > +                *
>> > +                * This helps avoid counter starvation of sibling thread by
>> > +                * ensuring at most half the counters cannot be in exclusive
>> > +                * mode. There is no designated counters for the limits. Any
>> > +                * N/2 counters can be used. This helps with events with
>> > +                * specific counter constraints.
>> > +                */
>> > +               if (is_ht_workaround_enabled() && !cpuc->is_fake &&
>> > +                   READ_ONCE(cpuc->excl_cntrs->exclusive_present))
>> > +                       gpmax /= 2;
>> > +
>> What I don't like about this part is that this is a hack to work around a bug
>> on some limited Intel CPUs and yet it is in the middle of generic x86 code.
>> I understand it will be inoperative on AMD PMU and is not used by Intel
>> uncore. On KNC or P6, you will not have is_ht_workaround_enabled().
>> Could this be made a x86_pmu callback? x86_pmu.counter_limit()?
>
> It'll be slower though. You get an indirect function call in there.
>
> But sure we can clean that up later if you like; there's other things
> needing to be fixed here first.
>
> I'm going to overhaul the whole get/put constraints stuff first.

Ok, I think it would be good to balance to number of get/put. It would
avoid the confusion. Is that what you are thinking about?