From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757163Ab2HJRIp (ORCPT ); Fri, 10 Aug 2012 13:08:45 -0400 Received: from bente.schedom-europe.net ([193.109.184.68]:46200 "EHLO bente.schedom-europe.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752770Ab2HJRIo (ORCPT ); Fri, 10 Aug 2012 13:08:44 -0400 Message-ID: <50254019.1030304@telenet.be> Date: Fri, 10 Aug 2012 19:08:41 +0200 From: Janpieter Sollie User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111124 Thunderbird/8.0 MIME-Version: 1.0 To: linux-kernel@vger.kernel.org Subject: Re: POI: nvidia forcedeth phy id not present References: <50243237.9040704@telenet.be> <50244458.5040906@telenet.be> In-Reply-To: <50244458.5040906@telenet.be> X-Enigmail-Version: 1.3.3 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org A primary concern seems to be solved (4k frame size). However, it is not really a patch yet, just a dirty workaround (just replaced ETH_DATA_LEN with a value 4000, my switch is limited to 4k) 486c486 < #define NV_PKTLIMIT_1_ETH_DATA_LEN /* hard limit not known */ --- > #define NV_PKTLIMIT_1 4000 /* hard limit not known */ I will try to improve the MTU detection in driver, but it can take some time before I really understand what each function does. I do not know if this workaround forces a value to the 'initiated' phy, or just forces a wrong MTU to be used on standard nvidia cards. the results are worth considering: dd -if=//server/share of=/dev/null went from 91 to 112 mbps (and this is no file cache, the pc has 2gb ram (>50% used by GUI) and the source file is 30 ...) any help developing a patch may be useful. Is there some documentation about this driver module?