From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755436Ab2DKJ6f (ORCPT ); Wed, 11 Apr 2012 05:58:35 -0400 Received: from mail.secomea.com ([130.226.208.142]:1117 "EHLO mail.secomea.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752846Ab2DKJ6e (ORCPT ); Wed, 11 Apr 2012 05:58:34 -0400 X-Greylist: delayed 507 seconds by postgrey-1.27 at vger.kernel.org; Wed, 11 Apr 2012 05:58:34 EDT Message-ID: <4F8553BF.6030303@secomea.com> Date: Wed, 11 Apr 2012 11:49:51 +0200 From: =?ISO-8859-1?Q?Svenning_S=F8rensen?= User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:11.0) Gecko/20120327 Thunderbird/11.0.1 MIME-Version: 1.0 To: Francois Romieu CC: Bjarke Istrup Pedersen , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, Andreas Mohr Subject: Re: via-rhine: Problem with lost link after a while References: <20120410204249.GA26627@electric-eye.fr.zoreil.com> <20120410225534.GA28480@electric-eye.fr.zoreil.com> In-Reply-To: <20120410225534.GA28480@electric-eye.fr.zoreil.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 11-04-2012 00:55, Francois Romieu wrote: > Bjarke Istrup Pedersen : > > [...] >> Great, I'll try a 3.4-rc2 kernel, and see how it runs. >> >> The thread I was talking about earlier is here: >> http://lists.soekris.com/pipermail/soekris-tech/2012-April/018318.html >> Is there any of the changes he has there, that makes sense in the new >> driver you wrote ? > (I did not write a new driver) > > Regarding Svenning's patch: > - the wmb in alloc_rbufs may help rhine_reset_task(). > - one should probably add one in rhine_rx() as well. > - rhine_start_tx() is supposed to stop queueing when there is no room left. > I'm curious to know if the "Tx descriptor busy" test triggered. > - the rmb() in rhine_tx() will not make a difference for a single core but > it's a good reminder that I should not have forgotten to propagate the > xmit / Tx completion fix back from the r8169 driver to the via-rhine one > (sigh) > > mmiowb is probably missing. I doubt it hits hard right now. > > I have not checked if MMIO flushes are missing. Actually I need some sleep. > Regarding the "Tx descriptor busy" test: no, I didn't see it trigger, I just put it there just in case because I suspected there could be a race due to the lock-free tx path. But I'm glad if you're confident that it can't happen :) Svenning