From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: Soft-Lockup/Race in networking in 2.6.31-rc1+195 ( possibly?caused by netem) Date: Sat, 4 Jul 2009 08:36:46 +0200 Message-ID: <20090704063646.GA3410@ami.dom.local> References: <20090703120301.GD4847@ff.dom.local> <20090703.132220.57384838.davem@davemloft.net> <20090703225640.GA3639@ami.dom.local> <20090703.185553.218218176.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: andres@anarazel.de, arun@linux.vnet.ibm.com, tglx@linutronix.de, shemminger@vyatta.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org To: David Miller Return-path: Content-Disposition: inline In-Reply-To: <20090703.185553.218218176.davem@davemloft.net> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Fri, Jul 03, 2009 at 06:55:53PM -0700, David Miller wrote: > From: Jarek Poplawski > Date: Sat, 4 Jul 2009 00:56:40 +0200 > > > On Fri, Jul 03, 2009 at 01:22:20PM -0700, David Miller wrote: > >> Well, if you look at that commit the bisect pointed to Jarek, it is a > >> change which starts causing a situation which never happened before. > >> Namely, timers added on one cpu can be migrated and fire on another. > >> > >> So this could be exposing races in the networking that technically > >> always existed. > > > > I'm not sure I get your point; could you give some example? > > Actually, I've suspected races in timers code. > > Let's say that a particular networking timer always gets > re-added on the cpu where the timer fires. > > In that case, beforehand, no inter-cpu races could possibly > be tested. But with the new timer code, such races could > now be potentially triggered. Maybe I still miss something, but even if it were possible, lockdep should have reported such things long ago. Jarek P.