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 S1757951Ab0JSVcy (ORCPT <rfc822;w@1wt.eu>);
	Tue, 19 Oct 2010 17:32:54 -0400
Received: from mx1.redhat.com ([209.132.183.28]:48962 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1757872Ab0JSVcx (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 19 Oct 2010 17:32:53 -0400
Date: Tue, 19 Oct 2010 17:32:26 -0400
From: Jason Baron <jbaron@redhat.com>
To: David Daney <ddaney@caviumnetworks.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Koki Sanagi <sanagi.koki@jp.fujitsu.com>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@elte.hu>,
        Frederic Weisbecker <fweisbec@gmail.com>, nhorman@tuxdriver.com,
        scott.a.mcmillan@intel.com, laijs@cn.fujitsu.com,
        "H. Peter Anvin" <hpa@zytor.com>, LKML <linux-kernel@vger.kernel.org>,
        eric.dumazet@gmail.com, kaneshige.kenji@jp.fujitsu.com,
        David Miller <davem@davemloft.net>, izumi.taku@jp.fujitsu.com,
        kosaki.motohiro@jp.fujitsu.com,
        Heiko Carstens <heiko.carstens@de.ibm.com>,
        "Luck, Tony" <tony.luck@intel.com>
Subject: Re: [PATCH] tracing: Cleanup the convoluted softirq tracepoints
Message-ID: <20101019213225.GB2855@redhat.com>
References: <1287398936.29097.1548.camel@twins>
 <4CBD79CF.2060706@jp.fujitsu.com>
 <alpine.LFD.2.00.1010191428560.6815@localhost6.localdomain6>
 <20101019132236.GA19197@Krystal>
 <alpine.LFD.2.00.1010191524160.6815@localhost6.localdomain6>
 <1287496495.16971.372.camel@gandalf.stny.rr.com>
 <alpine.LFD.2.00.1010191558250.6815@localhost6.localdomain6>
 <20101019142820.GA14520@Krystal>
 <alpine.LFD.2.00.1010191842270.6815@localhost6.localdomain6>
 <4CBE0AC6.3040402@caviumnetworks.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <4CBE0AC6.3040402@caviumnetworks.com>
User-Agent: Mutt/1.5.20 (2010-07-18)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, Oct 19, 2010 at 02:16:54PM -0700, David Daney wrote:
> On 10/19/2010 12:49 PM, Thomas Gleixner wrote:
> [...]
> >So that saves _TWO_ bytes of text and replaces:
> >
> >-  1e:	83 3d 00 00 00 00 00 	cmpl   $0x0,0x0(%rip)        # 25<test+0x25>
> >-  25:	74 4d                	je     74<test+0x74>
> >+  1e:	e9 00 00 00 00       	jmpq   23<test+0x23>
> >+  23:	eb 4d                	jmp    72<test+0x72>
> >
> >So it trades a conditional vs. two jumps ? WTF ??
> >
> >I thought that jumplabel magic was supposed to get rid of the jump
> >over the tracing code ? In fact it adds another jump. Whatfor ?
> 
> The 'asm goto' construct in GCC-4.5 is deficient in this area.
> 
> GCC assumes that all exit paths from an 'asm goto' are equally
> likely, so the tracing (or dynamic printk etc.) code is assumed to
> be hot and is emitted inline.  Since they are inline like this,
> there are all these jumps around them and they pollute the I-Cache.
> 
> I was looking at fixing it, but I think a true general purpose fix
> would require enhancing GCC's grammar to allow specifying of the
> 'likelyness' of each exit path from 'asm goto'.
> 
> David Daney
> 

right, the next step is adding support for hot/cold labels, so the
tracing code will be annotaed with a 'cold' label. Thus, not adding the
'jmp' above on line '23', and in fact moving the tracing code
out-of-line. Maybe I haven't been clear on this.

thanks,

-Jason