From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754142AbYDGGGi (ORCPT ); Mon, 7 Apr 2008 02:06:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751989AbYDGGGa (ORCPT ); Mon, 7 Apr 2008 02:06:30 -0400 Received: from host36-195-149-62.serverdedicati.aruba.it ([62.149.195.36]:54441 "EHLO mx.cpushare.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751749AbYDGGG3 (ORCPT ); Mon, 7 Apr 2008 02:06:29 -0400 Date: Mon, 7 Apr 2008 08:06:02 +0200 From: Andrea Arcangeli To: Christoph Lameter Cc: Robin Holt , "Paul E. McKenney" , kvm-devel@lists.sourceforge.net, Peter Zijlstra , general@lists.openfabrics.org, steiner@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [patch 02/10] emm: notifier logic Message-ID: <20080407060602.GE9309@duo.random> References: <20080404223048.374852899@sgi.com> <20080404223131.469710551@sgi.com> <20080405005759.GH14784@duo.random> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sun, Apr 06, 2008 at 10:48:56PM -0700, Christoph Lameter wrote: > On Sat, 5 Apr 2008, Andrea Arcangeli wrote: > > > > + rcu_assign_pointer(mm->emm_notifier, e); > > > + mm_unlock(mm); > > > > My mm_lock solution makes all rcu serialization an unnecessary > > overhead so you should remove it like I already did in #v11. If it > > wasn't the case, then mm_lock wouldn't be a definitive fix for the > > race. > > There still could be junk in the cache of one cpu. If you just read the > new pointer but use the earlier content pointed to then you have a > problem. There can't be junk, spinlocks provides semantics of proper memory barriers, just like rcu, so it's entirely superflous. There could be junk only if any of the mmu_notifier_* methods would be invoked _outside_ the i_mmap_lock and _outside_ the anon_vma and outside the mmap_sem, that is never the case of course. > So a memory fence / barrier is needed to guarantee that the contents > pointed to are fetched after the pointer. It's not needed... if you were right we could never possibly run a list_for_each inside any spinlock protected critical section and we'd always need to use the _rcu version instead. The _rcu version is needed only when the list walk happens outside the spinlock critical section of course (rcu = no spinlock cacheline exlusive write operation in the read side, here the read side takes the spinlock big time).