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 S1755186AbbDJJNA (ORCPT <rfc822;w@1wt.eu>);
	Fri, 10 Apr 2015 05:13:00 -0400
Received: from mail-wi0-f182.google.com ([209.85.212.182]:38696 "EHLO
	mail-wi0-f182.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753326AbbDJJM5 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Fri, 10 Apr 2015 05:12:57 -0400
Date: Fri, 10 Apr 2015 11:12:53 +0200
From: Ingo Molnar <mingo@kernel.org>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
        Jason Low <jason.low2@hp.com>, Peter Zijlstra <peterz@infradead.org>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        Aswin Chandramouleeswaran <aswin@hp.com>,
        LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] mutex: Speed up mutex_spin_on_owner() by not taking the
 RCU lock
Message-ID: <20150410091252.GA27630@gmail.com>
References: <1428521960-5268-3-git-send-email-jason.low2@hp.com>
 <20150409053725.GB13871@gmail.com>
 <1428561611.3506.78.camel@j-VirtualBox>
 <20150409075311.GA4645@gmail.com>
 <CA+55aFz6KKxGVxPAbsmw9GsKJfy85P2C0EmYBrGpn+aJDjZJWw@mail.gmail.com>
 <20150409175652.GI6464@linux.vnet.ibm.com>
 <CA+55aFzXMDjQQ7jTjsPdh1RikXfgV7OCd-+13cz06MOmDBA33w@mail.gmail.com>
 <CA+55aFwZWi6ecDmVsMBQJTrgrW3GD2DaRtpiOspe=5amR1=dNg@mail.gmail.com>
 <20150409183926.GM6464@linux.vnet.ibm.com>
 <20150410090051.GA28549@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20150410090051.GA28549@gmail.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


* Ingo Molnar <mingo@kernel.org> wrote:

> 0000000000000030 <mutex_spin_on_owner.isra.4>:
>   30:	48 3b 37             	cmp    (%rdi),%rsi
>   33:	48 8d 4e 28          	lea    0x28(%rsi),%rcx
>   37:	75 4e                	jne    87 <mutex_spin_on_owner.isra.4+0x57>
>   39:	55                   	push   %rbp
>   3a:	45 31 c0             	xor    %r8d,%r8d
>   3d:	65 4c 8b 0c 25 00 00 	mov    %gs:0x0,%r9
>   44:	00 00 
>   46:	48 89 e5             	mov    %rsp,%rbp
>   49:	48 83 ec 10          	sub    $0x10,%rsp
>   4d:	eb 08                	jmp    57 <mutex_spin_on_owner.isra.4+0x27>
>   4f:	90                   	nop
>   50:	f3 90                	pause  
>   52:	48 3b 37             	cmp    (%rdi),%rsi
>   55:	75 29                	jne    80 <mutex_spin_on_owner.isra.4+0x50>
>   57:	44 89 c0             	mov    %r8d,%eax
>   5a:	90                   	nop
>   5b:	90                   	nop
>   5c:	90                   	nop
>   5d:	8b 11                	mov    (%rcx),%edx
>   5f:	90                   	nop
>   60:	90                   	nop
>   61:	90                   	nop

Yeah, so what I missed here are those nops: placeholders for the 
STAC/CLAC instructions on x86... and this is what Linus mentioned 
about the clac() overhead.

But this could be solved I think: by adding a 
copy_from_kernel_inatomic() primitive which simply leaves out the 
STAC/CLAC sequence: as these are always guaranteed to be kernel 
addresses, the SMAP fault should not be generated.

Thanks,

	Ingo