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 S1754085AbcHSCJP (ORCPT <rfc822;w@1wt.eu>);
        Thu, 18 Aug 2016 22:09:15 -0400
Received: from mail-wm0-f41.google.com ([74.125.82.41]:35366 "EHLO
        mail-wm0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1753237AbcHSCI7 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 18 Aug 2016 22:08:59 -0400
Subject: Re: RFC: Petition Intel/AMD to add POPF_IF insn
To: Denys Vlasenko <dvlasenk@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>
References: <f2d39812-8e2b-ed32-398f-8bb32bd20c7f@redhat.com>
 <CA+55aFy0zq5h7zXcL7KNZuhvVHUZvA__U4ztJvP_WTCN+dub2g@mail.gmail.com>
 <8de26c33-5597-bf00-2ac5-d265ba01d0d4@redhat.com>
 <CA+55aFwmxwQBkyDjombS4cy1q=a_buhmDjDnaa8rdC8ZDaDYEA@mail.gmail.com>
 <CALCETrXOuomfta==NmAu3WEsgj69t+-Vi0pwtM0_MHRjn=v_tw@mail.gmail.com>
 <d1c78779-b885-8e3e-a87a-a586b18423fc@redhat.com>
 <CA+55aFyrwdH1ege_rcHp9JDAcwGoqDcCrYHGTBU2HFjXgSJN5w@mail.gmail.com>
 <CA+55aFwfEzVCdeVdK6hUO4s_yy-wisPmQhtYbNUr4hFuRm8NkQ@mail.gmail.com>
 <CA+55aFw=nt9+Jk2O2cuYaTJ7qLoO3Gjv=tUH6bwjFFTg=sNHfQ@mail.gmail.com>
 <CA+55aFyf9UAhQp48YCtqNnvSs_tC3W51uCb00nMND7ZG8KQexA@mail.gmail.com>
 <1ae46402-4cd0-6afc-3dd3-e155ec59f64e@redhat.com>
 <5174a3b9-7f48-49f4-c59f-0fa234b68b17@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>,
        Sara Sharon <sara.sharon@intel.com>,
        Dan Williams <dan.j.williams@intel.com>,
        =?UTF-8?Q?Christian_K=c3=b6nig?= <christian.koenig@amd.com>,
        Vinod Koul <vinod.koul@intel.com>,
        Alex Deucher <alexander.deucher@amd.com>,
        Johannes Berg <johannes.berg@intel.com>,
        "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
        Andy Lutomirski <luto@kernel.org>,
        the arch/x86 maintainers <x86@kernel.org>,
        Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
        Adrian Hunter <adrian.hunter@intel.com>
From: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <0ad8824d-7e4a-6c72-43e0-9ecf7a43f86e@redhat.com>
Date: Thu, 18 Aug 2016 19:22:16 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
 Thunderbird/45.2.0
MIME-Version: 1.0
In-Reply-To: <5174a3b9-7f48-49f4-c59f-0fa234b68b17@redhat.com>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org



On 18/08/2016 14:18, Denys Vlasenko wrote:
> 
> -     2,588,839,023      branches                  #  977.555
> M/sec                    ( +-  0.02% )
> +     2,599,319,615      branches                  # 1046.786
> M/sec                    ( +-  0.04% )
> -         3,620,273      branch-misses             #    0.14% of all
> branches          ( +-  0.67% )
> +         3,577,771      branch-misses             #    0.14% of all
> branches          ( +-  0.69% )
> -       2.648799072 seconds time
> elapsed                                          ( +-  0.24% )
> +       2.487452268 seconds time
> elapsed                                          ( +-  0.31% )
> 
> Good, we run more insns/cycle, as expected. However, a bit more branches.

Can you see where the missed branches are?  Assuming branch misses are
the case where IF=0, perhaps there are a few places that can be changed
to spin_lock/unlock_irq or local_irq_disable/enable.

Paolo