From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753118Ab2GPQIO (ORCPT ); Mon, 16 Jul 2012 12:08:14 -0400 Received: from out3-smtp.messagingengine.com ([66.111.4.27]:40135 "EHLO out3-smtp.messagingengine.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752867Ab2GPQIL (ORCPT ); Mon, 16 Jul 2012 12:08:11 -0400 X-Sasl-enc: tLm4Nf7mN60g8tqgeu1vOnVOblAuoM5zFNSjxKOhe759 1342454890 Date: Mon, 16 Jul 2012 13:08:07 -0300 From: Henrique de Moraes Holschuh To: Ben Hutchings Cc: "Dave, Tushar N" , Joe Jin , "e1000-devel@lists.sf.net" , "netdev@vger.kernel.org" , "linux-kernel@vger.kernel.org" Subject: Re: 82571EB: Detected Hardware Unit Hang Message-ID: <20120716160807.GB1765@khazad-dum.debian.net> References: <4FFE6BB9.4060106@oracle.com> <061C8A8601E8EE4CA8D8FD6990CEA891274F033B@ORSMSX102.amr.corp.intel.com> <4FFE787B.9050201@oracle.com> <061C8A8601E8EE4CA8D8FD6990CEA891274F0ACC@ORSMSX102.amr.corp.intel.com> <4FFF61BD.1060604@oracle.com> <061C8A8601E8EE4CA8D8FD6990CEA891274F11FF@ORSMSX102.amr.corp.intel.com> <4FFFA532.1030208@oracle.com> <061C8A8601E8EE4CA8D8FD6990CEA891274F2354@ORSMSX102.amr.corp.intel.com> <20120715133510.GA5484@khazad-dum.debian.net> <1342453645.2523.17.camel@bwh-desktop.uk.solarflarecom.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1342453645.2523.17.camel@bwh-desktop.uk.solarflarecom.com> X-GPG-Fingerprint: 1024D/1CDB0FE3 5422 5C61 F6B7 06FB 7E04 3738 EE25 DE3F 1CDB 0FE3 User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 16 Jul 2012, Ben Hutchings wrote: > On Sun, 2012-07-15 at 10:35 -0300, Henrique de Moraes Holschuh wrote: > > On Sun, 15 Jul 2012, Dave, Tushar N wrote: > > > Somehow setting max payload to 256 from BIOS does not set this value for all devices. I believe this is a BIOS bug. > > > > And preferably, Linux should complain about it. Since we know it is going > > to cause problems, and since we know it does happen, we should be raising a > > ruckus about it in the kernel log (and probably fixing it to min(path) while > > at it)... > > > > Is this something that should be raised as a feature request with the > > PCI/PCIe subsystem? > > The feature is there, but we ended up with: > > commit 5f39e6705faade2e89d119958a8c51b9b6e2c53c > Author: Jon Mason > Date: Mon Oct 3 09:50:20 2011 -0500 > > PCI: Disable MPS configuration by default > > But you are welcome to share use of the fixup_mpss_256() quirk. Meh. I'd be happy with a warning if MPSS decreases when walking up to the tree root... i.e. a warning if any child has a MPSS larger than the parent. -- "One disk to rule them all, One disk to find them. One disk to bring them all and in the darkness grind them. In the Land of Redmond where the shadows lie." -- The Silicon Valley Tarot Henrique Holschuh