From mboxrd@z Thu Jan  1 00:00:00 1970
From: Alex Williamson <alex.williamson@redhat.com>
Subject: Re: PCI assignement with nvidia K1: RmInitAdapter failed
Date: Wed, 10 Jul 2013 09:25:32 -0600
Message-ID: <1373469932.2602.330.camel@ul30vt.home>
References: <20130709111810.yrgakqxj4wgwkgw0@www.imp.polymtl.ca>
	 <20130709121545.a00mic44fksswk84@www.imp.polymtl.ca>
	 <1373392372.2602.273.camel@ul30vt.home>
	 <20130710145431.ojut19m4ys84w0cc@www.imp.polymtl.ca>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: kvm@vger.kernel.org
To: Guillaume Thouvenin <guillaume.thouvenin@polymtl.ca>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:7444 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754210Ab3GJPZl (ORCPT <rfc822;kvm@vger.kernel.org>);
	Wed, 10 Jul 2013 11:25:41 -0400
In-Reply-To: <20130710145431.ojut19m4ys84w0cc@www.imp.polymtl.ca>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Wed, 2013-07-10 at 14:54 +0200, Guillaume Thouvenin wrote:
> Alex Williamson <alex.williamson@redhat.com> a =C3=A9crit :
>=20
> > Are you sure that nvidia-smi is relevant to the K1/K2 devices?  Doe=
s it
> > work on the host?
>=20
> Yes it works on the host and I have some information like power=20
> consumption, temperature of the GPU, etc...
>=20
> > Are
> > there other tests you can do to check whether the device is otherwi=
se
> > available?
>=20
> I also tried to start an X server but I got the same error reported i=
n=20
> the syslog:  [  435.745673] NVRM: RmInitAdapter failed! (0x26:0x38:11=
70)
>   [  435.745695] NVRM: rm_init_adapter(0) failed
>=20
> And in the xorg.log I have:
>=20
>=20
>   [   423.624] (=3D=3D) NVIDIA(0): Depth 24, (=3D=3D) framebuffer bpp=
 32
>   [   423.624] (=3D=3D) NVIDIA(0): RGB weight 888
>   [   423.624] (=3D=3D) NVIDIA(0): Default visual is TrueColor
>   [   423.624] (=3D=3D) NVIDIA(0): Using gamma correction (1.0, 1.0, =
1.0)
>   [   423.624] (**) NVIDIA(0): Option "NoLogo" "true"
>   [   423.624] (**) NVIDIA(0): Option "UseDisplayDevice" "none"
>   [   423.624] (**) NVIDIA(0): Enabling 2D acceleration
>   [   423.624] (**) NVIDIA(0): Option "UseDisplayDevice" set to "none=
";=20
> enabling NoScanout
>   [   423.624] (**) NVIDIA(0):     mode
>   [   435.746] (EE) NVIDIA(0): Failed to initialize the NVIDIA GPU at=
=20
> PCI:0:3:0.  Please
>   [   435.746] (EE) NVIDIA(0):     check your system's kernel log for=
=20
> additional error
>   [   435.746] (EE) NVIDIA(0):     messages and refer to Chapter 8:=20
> Common Problems in the
>   [   435.746] (EE) NVIDIA(0):     README for additional information.
>   [   435.746] (EE) NVIDIA(0): Failed to initialize the NVIDIA graphi=
cs device!
>   [   435.746] (EE) NVIDIA(0): Failing initialization of X screen 0

AFAICT, rm_init_adapter is in the binary blob part of the nvidia driver=
,
so we can't simply check the code to see what's wrong.  Google finds
this:

http://forums.gentoo.org/viewtopic-t-961110.html?sid=3D0a60d40ba001f7bb=
e799bb16b2921cac

That was of course on bare metal, but note that the IOMMU prevented som=
e
accesses and the solution was to disable the IOMMU.  Of course we can't
disable the IOMMU in this case.  Do you see any IOMMU faults in dmesg o=
n
the host around this error?  Does nouveau work?  Thanks,

Alex