From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Lameter Subject: [ofa-general] Re: [patch 02/10] emm: notifier logic Date: Sun, 6 Apr 2008 22:48:56 -0700 (PDT) Message-ID: References: <20080404223048.374852899@sgi.com> <20080404223131.469710551@sgi.com> <20080405005759.GH14784@duo.random> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Return-path: In-Reply-To: <20080405005759.GH14784@duo.random> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: general-bounces@lists.openfabrics.org Errors-To: general-bounces@lists.openfabrics.org To: Andrea Arcangeli Cc: Peter Zijlstra , kvm-devel@lists.sourceforge.net, steiner@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Robin Holt , general@lists.openfabrics.org, "Paul E. McKenney" List-Id: linux-mm.kvack.org 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. So a memory fence / barrier is needed to guarantee that the contents pointed to are fetched after the pointer.