From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756687Ab1BCR5g (ORCPT ); Thu, 3 Feb 2011 12:57:36 -0500 Received: from s15228384.onlinehome-server.info ([87.106.30.177]:38148 "EHLO mail.x86-64.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756675Ab1BCR5f (ORCPT ); Thu, 3 Feb 2011 12:57:35 -0500 Date: Thu, 3 Feb 2011 18:58:45 +0100 From: Borislav Petkov To: Markus Trippelsdorf Cc: "linux-edac@vger.kernel.org" , Doug Thompson , "linux-kernel@vger.kernel.org" Subject: Re: [EDAC-AMD64] Display correct RAM sizes in ganged mode on F10 CPUs Message-ID: <20110203175845.GC26261@aftab> References: <20110129211531.GA1874@gentoo.trippels.de> <20110201185114.GD8418@aftab> <20110201192752.GA1589@gentoo.trippels.de> <20110203151721.GD24755@aftab> <20110203155951.GA1594@gentoo.trippels.de> <20110203163600.GA26261@aftab> <20110203164203.GB1594@gentoo.trippels.de> <20110203170932.GB26261@aftab> <20110203172539.GA1581@gentoo.trippels.de> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20110203172539.GA1581@gentoo.trippels.de> 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 Thu, Feb 03, 2011 at 12:25:39PM -0500, Markus Trippelsdorf wrote: > Looks good, many thanks Boris. > > EDAC amd64: F10h detected (node 0). > EDAC MC: DCT0 chip selects: > EDAC amd64: MC: 0: 1024MB 1: 1024MB > EDAC amd64: MC: 2: 1024MB 3: 1024MB > EDAC amd64: MC: 4: 0MB 5: 0MB > EDAC amd64: MC: 6: 0MB 7: 0MB > EDAC MC: DCT1 chip selects: > EDAC amd64: MC: 0: 1024MB 1: 1024MB > EDAC amd64: MC: 2: 1024MB 3: 1024MB > EDAC amd64: MC: 4: 0MB 5: 0MB > EDAC amd64: MC: 6: 0MB 7: 0MB Ok thanks, will add your Tested-by: too. > BTW another thing, while I have your attention: > > cat /sys/devices/system/edac/mc/mc0/csrow0/edac_mode > prints "S4ECD4ED" aka Chipkill on my system. > But I'm using a revision C Phenom that only supports a x4 symbol size, > while the Kingston ECC DIMMs have a width of x8. So according to > table 77 (page 174) of the "BIOS and Kernel Developer’s Guide" the > system is actually running in SECDED mode and does not provide Chipkill. Yeah, that table needs to be implemented for proper csrow->edac_mode assignment. I'll try to get it done soon. Thanks. -- Regards/Gruss, Boris. Advanced Micro Devices GmbH Einsteinring 24, 85609 Dornach General Managers: Alberto Bozzo, Andrew Bowd Registration: Dornach, Gemeinde Aschheim, Landkreis Muenchen Registergericht Muenchen, HRB Nr. 43632