From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: memory barrier question
Date: Wed, 22 Sep 2010 11:41:44 -0700
Message-ID: <20100922184144.GA11741@linux.vnet.ibm.com>
References: <20100919152638.GF3060@linux.vnet.ibm.com>
 <E1OxQIg-0005Nw-WE@pomaz-ex.szeredi.hu>
 <20100919215909.GG3060@linux.vnet.ibm.com>
 <1284944316.2957.795.camel@mulgrave.site>
 <20100920012915.GI3060@linux.vnet.ibm.com>
 <E1OxioY-0006nd-M9@pomaz-ex.szeredi.hu>
 <20100920182504.GD2408@linux.vnet.ibm.com>
 <4C97C366.80206@orcon.net.nz>
 <20100920204055.GJ2408@linux.vnet.ibm.com>
 <20100921145910.GA3358@linux.vnet.ibm.com>
Reply-To: paulmck@linux.vnet.ibm.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-arch-owner@vger.kernel.org>
Received: from e5.ny.us.ibm.com ([32.97.182.145]:47591 "EHLO e5.ny.us.ibm.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754246Ab0IVSly (ORCPT <rfc822;linux-arch@vger.kernel.org>);
	Wed, 22 Sep 2010 14:41:54 -0400
Content-Disposition: inline
In-Reply-To: <20100921145910.GA3358@linux.vnet.ibm.com>
Sender: linux-arch-owner@vger.kernel.org
List-ID: <linux-arch.vger.kernel.org>
To: Michael Cree <mcree@orcon.net.nz>
Cc: Miklos Szeredi <miklos@szeredi.hu>, James.Bottomley@HansenPartnership.com, benh@kernel.crashing.org, dhowells@redhat.com, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org

On Tue, Sep 21, 2010 at 07:59:10AM -0700, Paul E. McKenney wrote:
> On Mon, Sep 20, 2010 at 01:40:55PM -0700, Paul E. McKenney wrote:
> > On Tue, Sep 21, 2010 at 08:26:14AM +1200, Michael Cree wrote:
> > > On 21/09/10 06:25, Paul E. McKenney wrote:
> > > >But do we really care about Alpha anymore?  (I can see it now... The
> > > >Alpha portion of the kernel tree moves to staging...)
> > > 
> > > I do.
> > > 
> > > Sent from my Compaq Alpha XP1000 :-)
> > 
> > In that case, an smp_read_barrier_depends() or rcu_dereference() is
> > also required...
> 
> Wait a minute...  I finally got a chance to look up the system.  This
> system has only a single Alpha CPU, right?
> 
> If so, just build a UP kernel and be happy.  No need to worry about
> any of these SMP issues.
> 
> So, an alternative proposal -- support only UP kernels on Alpha.  ;-)

And there do seem to be some SMP Alpha systems still in use:

	http://www.alphalinux.org/wiki/index.php/User:Armin76/HW_list

							Thanx, Paul