From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932849AbXJRXS0 (ORCPT ); Thu, 18 Oct 2007 19:18:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758923AbXJRXST (ORCPT ); Thu, 18 Oct 2007 19:18:19 -0400 Received: from gate.crashing.org ([63.228.1.57]:55155 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752870AbXJRXSS (ORCPT ); Thu, 18 Oct 2007 19:18:18 -0400 Subject: Re: [PATCH] synchronize_irq needs a barrier From: Benjamin Herrenschmidt Reply-To: benh@kernel.crashing.org To: Linus Torvalds Cc: Herbert Xu , akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org In-Reply-To: References: <1192745137.7367.40.camel@pasglop> Content-Type: text/plain Date: Fri, 19 Oct 2007 09:17:29 +1000 Message-Id: <1192749449.7367.51.camel@pasglop> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2007-10-18 at 15:52 -0700, Linus Torvalds wrote: > > On Fri, 19 Oct 2007, Benjamin Herrenschmidt wrote: > > > > The barrier would guarantee that ioc->active (and in fact the write to > > the chip too above) are globally visible > > No, it doesn't really guarantee that. > > The thing is, there is no such thing as "globally visible". > > There is a "ordering of visibility wrt CPU's", but it's not global, it's > quite potentially per-CPU. So a barrier on one CPU doesn't guarantee > anything at all without a barrier on the *other* CPU. > > That said, the interrupt handling itself contains various barriers on the > CPU's that receive interrupts, thanks to the spinlocking. But I do agree > with Herbert that adding a "smb_mb()" is certainly in no way "obviously > correct", because it doesn't talk about what the other side does wrt > barriers and that word in memory. I agree and you can see that in fact, we don't have enough barrier on the other side since spin_unlock doesn't prevent subsequent loads from crossing a previous store... I wonder if that's worth trying to address, adding a barrier in handle_IRQ_event for example, or we can continue ignoring the barrier and let some drivers do their own fixes in fancy ways. Ben.