From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andreas Herrmann Subject: Re: Linux 2.6.39-rc3 Date: Fri, 15 Apr 2011 16:49:30 +0200 Message-ID: <20110415144930.GB4883@alberich.amd.com> References: <20110412184433.GF19819@8bytes.org> <20110413064609.GA18777@elte.hu> <20110413172147.GI19819@8bytes.org> <4DA5F62F.3030504@kernel.org> <4DA654D6.2060103@zytor.com> <20110414085624.GC18463@8bytes.org> <20110414210932.GG18463@8bytes.org> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: Alex Deucher Cc: Joerg Roedel , "H. Peter Anvin" , Yinghai Lu , Ingo Molnar , Linus Torvalds , Linux Kernel Mailing List , dri-devel@lists.freedesktop.org, Thomas Gleixner , Tejun Heo List-Id: dri-devel@lists.freedesktop.org On Thu, Apr 14, 2011 at 05:34:46PM -0400, Alex Deucher wrote: > On Thu, Apr 14, 2011 at 5:09 PM, Joerg Roedel wrote= : > > On Thu, Apr 14, 2011 at 10:28:43AM -0400, Alex Deucher wrote: > >> On Thu, Apr 14, 2011 at 4:56 AM, Joerg Roedel wr= ote: > >> > And this makes a difference, with this change on-top of -rc3 the= box boots > >> > fine. So there seems to be some dependency between the GART base= and the GTT > >> > base even when they are in different address spaces. > >> > > >> > Alex, can you comment on this? > >> > >> As Dave said, they are completely different addresses spaces. =A0Y= ou > >> could put the GPU aperture at 0 if you wanted (in fact we do on so= me > >> chips). =A0Perhaps there's some strange interaction with the nb ga= rt > >> since the nb gart on that chipset was designed to be used for grap= hics > >> and the rs780/880 can be configured to use an agp aperture. > >> Unfortunately, I'm not that familiar with the nb gart. > > > > Actually, the nb gart is part of the cpu. It is part of the cpu nor= th > > bridge and can translate io and cpu accesses. In fact, it is a rema= pper > > of physical memory addresses. >=20 > I know what it's for. In the IGP graphics chip is also part of the > north bridge, but it may not be related at all. >=20 > > > > The problem seems to be related to specific gpu chips. On another > > notebook with an hd3000 card gtt and the nb gart aperture are both = on > > 0xa0000000 too but the box works fine. I havn't tested with an hd50= 00 > > yet. The failing notebook has an hd4200 mobility. >=20 > What exact model is the hd3000? Is it IGP GPU or a discrete GPU? I= t > it's an IGP, it's identical to the hd4200 programming-wise. BTW, first of all the other notebook had a different CPU (it's family 0fh and Joerg's is family 10h). So different CPUs different GARTs different issues ;-) (Furthermore for CPU family 0fh reporting of GartTblWalk errors is already switched off in arch/x86/kernel/cpu/mcheck/mce.c.) Andreas