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 S1754778AbaIWIND (ORCPT <rfc822;w@1wt.eu>);
	Tue, 23 Sep 2014 04:13:03 -0400
Received: from bombadil.infradead.org ([198.137.202.9]:50216 "EHLO
	bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1754125AbaIWIM6 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Tue, 23 Sep 2014 04:12:58 -0400
Date: Tue, 23 Sep 2014 10:12:46 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Pranith Kumar <bobby.prani@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        "maintainer:X86 ARCHITECTURE..." <x86@kernel.org>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        "open list:X86 ARCHITECTURE..." <linux-kernel@vger.kernel.org>
Subject: Re: [RFC PATCH] x86: Use volatile semantics for atomic_set()
Message-ID: <20140923081246.GB3312@worktop.programming.kicks-ass.net>
References: <1411414762-32366-1-git-send-email-bobby.prani@gmail.com>
 <20140922200806.GC3128@worktop.programming.kicks-ass.net>
 <CAJhHMCC7RKE9GE3fGx0pnNoZHL0r_MOPMPwCjjNNbnC6i0G=BA@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAJhHMCC7RKE9GE3fGx0pnNoZHL0r_MOPMPwCjjNNbnC6i0G=BA@mail.gmail.com>
User-Agent: Mutt/1.5.22.1 (2013-10-16)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Sep 22, 2014 at 05:42:16PM -0400, Pranith Kumar wrote:
> On Mon, Sep 22, 2014 at 4:08 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > On Mon, Sep 22, 2014 at 03:39:21PM -0400, Pranith Kumar wrote:
> >> All the atomic operations have volatile semantics to prevent compiler
> >> reordering. Enforce the same semantics for atomic_set() too.
> >
> > To what point? atomic_set() is typically not what you expect it to
> > anyhow.
> 
> This is the only atomic operation which allows compiler reordering. I
> am not sure why this exception was made. Any ideas as to why we do
> this?

Because it typically doesn't matter. And you should never use
atomic_set() where it does matter.