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 S933213AbcHaLMW (ORCPT <rfc822;w@1wt.eu>);
        Wed, 31 Aug 2016 07:12:22 -0400
Received: from mx1.redhat.com ([209.132.183.28]:33778 "EHLO mx1.redhat.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1758851AbcHaLMS (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Wed, 31 Aug 2016 07:12:18 -0400
Subject: Re: RFC: Petition Intel/AMD to add POPF_IF insn
To: Paolo Bonzini <pbonzini@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>
 <CALCETrXZpbzF=HUVNvOZjhF+DGYA1viYdDa_aaBVHJVQb=6eGA@mail.gmail.com>
 <CA+55aFyv2tj1YQH3Ga4oAkNEZgsT2+KmuU_MYqN0aUUtkBygrQ@mail.gmail.com>
 <1686aa11-152d-9416-34dd-17820de7a7b6@redhat.com>
 <CA+55aFxWeVBjZeDUS3-hLjG-CuzRYfxsrMaQxxG_KH02ttZ5Dg@mail.gmail.com>
 <f91d4c19-688b-ff13-8905-377c0f5cea77@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: Denys Vlasenko <dvlasenk@redhat.com>
Message-ID: <fea16f6c-8afc-a694-cd76-c385308e1f9b@redhat.com>
Date: Wed, 31 Aug 2016 13:12:00 +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: <f91d4c19-688b-ff13-8905-377c0f5cea77@redhat.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit
X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.38]); Wed, 31 Aug 2016 11:12:05 +0000 (UTC)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 08/19/2016 12:54 PM, Paolo Bonzini wrote:
> On 18/08/2016 19:24, Linus Torvalds wrote:
>>>> I didn't do CPL0 tests yet. Realized that cli/sti can be tested in userspace
>>>> if we set iopl(3) first.
>> Yes, but it might not be the same. So the timings could be very
>> different from a cpl0 case.
>
> FWIW I recently measured around 20 cycles for a popf as well on
> Haswell-EP and CPL=0 (that was for commit f2485b3e0c6c, "KVM: x86: use
> guest_exit_irqoff", 2016-07-01).

Thanks for confirmation.

I revisited benchmarking of the

	if (flags & X86_EFLAGS_IF)
		native_irq_enable();

patch. In "make -j20" kernel compiles on a 8-way (HT) CPU, it shows some ~5 second
improvement during ~16 minute compile. That's 0.5% speedup. It's ok, but not
something to bee too excited.

80 e6 02                and    $0x2,%dh
74 01                   je     ffffffff810101ae <intel_pt_handle_vmx+0x3e>
fb                      sti

41 f6 86 91 00 00 00 02 testb  $0x2,0x91(%r14)
74 01                   je     ffffffff81013ce7 <math_error+0x77>
fb                      sti

f6 83 91 00 00 00 02    testb  $0x2,0x91(%rbx)
74 01                   je     ffffffff81013efa <do_int3+0xba>
fb                      sti

41 f7 c4 00 02 00 00    test   $0x200,%r12d
74 01                   je     ffffffff8101615d <oops_end+0x5d>
fb                      sti

Here we trade 20-cycle POPF for either 4-cycle STI, or a branch (which is either
~1 cycle if predicted, or ~20 cycles if mispredicted). The disassembly of
vmlinux shows that gcc generates these asm patterns:

I still think a dedicated instruction for a conditional STI is worth asking for.

Along the lines of "If bit 9 in the r/m argument is set, then STI, else nothing".

What do people from CPU companies say?