From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1754551AbZBPVpr@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1754551AbZBPVpr (ORCPT <rfc822;w@1wt.eu>);
	Mon, 16 Feb 2009 16:45:47 -0500
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751233AbZBPVpi
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Mon, 16 Feb 2009 16:45:38 -0500
Received: from bombadil.infradead.org ([18.85.46.34]:35419 "EHLO
	bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750727AbZBPVpi (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 16 Feb 2009 16:45:38 -0500
Subject: Re: Q: smp.c && barriers (Was: [PATCH 1/4] generic-smp: remove
 single ipi fallback for smp_call_function_many())
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Oleg Nesterov <oleg@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>,
       Suresh Siddha <suresh.b.siddha@intel.com>,
       Linus Torvalds <torvalds@linux-foundation.org>,
       Nick Piggin <npiggin@suse.de>,
       "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
       Ingo Molnar <mingo@elte.hu>, Rusty Russell <rusty@rustcorp.com.au>,
       Steven Rostedt <rostedt@goodmis.org>, linux-kernel@vger.kernel.org
In-Reply-To: <20090216213205.GA9098@redhat.com>
References: <20090216163847.431174825@chello.nl>
	 <20090216164114.433430761@chello.nl> <20090216204902.GA6924@redhat.com>
	 <1234818201.30178.386.camel@laptop>  <20090216213205.GA9098@redhat.com>
Content-Type: text/plain
Date: Mon, 16 Feb 2009 22:45:04 +0100
Message-Id: <1234820704.30178.396.camel@laptop>
Mime-Version: 1.0
X-Mailer: Evolution 2.25.90 
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 Mon, 2009-02-16 at 22:32 +0100, Oleg Nesterov wrote:
> > I was about to write a response, but found it to be a justification for
> > the read_barrier_depends() at the end of the loop.
> 
> I forgot to mention I don't understand the read_barrier_depends() at the
> end of the loop as well ;)

Suppose cpu0 adds to csd to cpu1:


 cpu0:                 cpu1:

add entry1
mb();
send ipi
                      run ipi handler
                      read_barrier_depends()
                      while (!list_empty())    [A]
                        do foo

add entry2
mb();
[no ipi -- we still observe entry1]

                        remove foo
                        read_barrier_depends()
                      while (!list_empty())      [B]


The read_barrier_depends() matches the mb() on the other cpu, without
which the 'new' entry might not be observed.

So it turns out the initial one is needed as well.