From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752112Ab1BCUi6 (ORCPT ); Thu, 3 Feb 2011 15:38:58 -0500 Received: from rcsinet10.oracle.com ([148.87.113.121]:62458 "EHLO rcsinet10.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751640Ab1BCUi5 (ORCPT ); Thu, 3 Feb 2011 15:38:57 -0500 Message-ID: <4D4B1214.20603@kernel.org> Date: Thu, 03 Feb 2011 12:37:40 -0800 From: Yinghai Lu User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.16) Gecko/20101125 SUSE/3.0.11 Thunderbird/3.0.11 MIME-Version: 1.0 To: Andrew Morton CC: Ingo Molnar , David Miller , "H. Peter Anvin" , Benjamin Herrenschmidt , "linux-kernel@vger.kernel.org" Subject: Re: [PATCH - resend] memblock: Don't adjust size in memblock_find_base() References: <4D1BD928.50701@zytor.com> <4D1BE615.4000700@zytor.com> <20101230090648.GB7306@elte.hu> <20101230102815.GA29822@elte.hu> <20101230103002.GA30020@elte.hu> <20110105134434.GA22816@elte.hu> <4D43615B.9060203@kernel.org> <20110203122505.8369330f.akpm@linux-foundation.org> In-Reply-To: <20110203122505.8369330f.akpm@linux-foundation.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Source-IP: acsmt353.oracle.com [141.146.40.153] X-Auth-Type: Internal IP X-CT-RefId: str=0001.0A090201.4D4B1249.027A,ss=1,fgs=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/03/2011 12:25 PM, Andrew Morton wrote: > On Fri, 28 Jan 2011 16:37:47 -0800 > Yinghai Lu wrote: > >> >> While applying patch to use memblock to find aperture for 64bit x86. >> Ingo found system with 1g + force_iommu >> >>> No AGP bridge found >>> Node 0: aperture @ 38000000 size 32 MB >>> Aperture pointing to e820 RAM. Ignoring. >>> Your BIOS doesn't leave a aperture memory hole >>> Please enable the IOMMU option in the BIOS setup >>> This costs you 64 MB of RAM >>> Cannot allocate aperture memory hole (0,65536K) > > I'm trying to work out if we should backport this fix into earlier > kernels and as is often the case, I wasn't given enough information. > > What are the end-user visible effects of this? The kernel cannot use > the AGP bridge? 64MB of RAM wasted? Something else? that is needed for further cleanup memblock with x86. http://git.kernel.org/?p=linux/kernel/git/tip/linux-2.6-tip.git;a=shortlog;h=refs/heads/x86/bootmem but it triggers another old bug in core memblock on one Ingo test machine. (with 1g ram but have iommu forced set for debug) end-user is not supposed to have this conf. Thanks Yinghai