WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

Re: [Xen-devel] collecting info on platforms with VT-d BIOS problems

To: "Kay, Allen M" <allen.m.kay@xxxxxxxxx>
Subject: Re: [Xen-devel] collecting info on platforms with VT-d BIOS problems
From: Sander Eikelenboom <linux@xxxxxxxxxxxxxx>
Date: Mon, 25 Jan 2010 17:26:44 +0100
Cc: "'xen-devel@xxxxxxxxxxxxxxxxxxx'" <xen-devel@xxxxxxxxxxxxxxxxxxx>, "Han, Weidong" <weidong.han@xxxxxxxxx>
Delivery-date: Mon, 25 Jan 2010 08:27:41 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <987664A83D2D224EAE907B061CE93D530C8A3D08@xxxxxxxxxxxxxxxxxxxxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Organization: Eikelenboom IT services
References: <987664A83D2D224EAE907B061CE93D530C8A3D08@xxxxxxxxxxxxxxxxxxxxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Hello Allen,

My problem before Weidongs workarounds was that VT-D would be switched off due 
to RMRR base address > end address when using a pci-e graphics card which 
disables the IGD on my platform (Q45 chipset).
Since his workarounds this doesn't happen anymore though one warning remains.

So there are to issues:
- RMRR address range not in reserved memory base = 7f000000 end = 7effffff; 
iommu_inclusive_mapping=1 parameter may be needed.
- And as you see if it was included this RMRR is still invalid because the base 
address > end address (which was previously the cause that xen switched off 
vt-d alltogether, but this error isn't reported separately anymore)

I have attached:
- xm info output, that should satisfy (c)
- serial log booting with and without iommu_inclusive_mapping=1 option, this 
should satisfy (d)
- output lspci -vvvknn

Ad (a):
- Asus P5Q-EM DO
- Q45 intel chipset
- Q9400 intel processor
- Ati Radeon HD 4850 GPU

Ad (b):
- bios version (latest available): P5Q-EM DO 1102 BIOS, date 2009/06/05


Regards,

Sander





Saturday, January 23, 2010, 1:22:08 AM, you wrote:

> We would like to collect information on platforms that have problem with VT-d 
> PCI device passthrough using non-IGD PCI devices.  Note that IGD (integrated 
> display device) device passthrough code is still being worked on.

> If you have encountered  VT-d problems on a particular platform using latest 
> xen-unstable, please provide the following information so that we can work 
> with OEM's to get their BIOS's fixed:

>     (a) Platform details (OEM, Product/Model#,  Other identifying info)
>     (b) BIOS version/number
>     (c) Version of Xen with which failure is seen (if not the latest 
> xen-unstable)
>     (d) Specific error/failure details such as serial log

> Thanks!

> Allen






-- 
Best regards,
 Sander                            mailto:linux@xxxxxxxxxxxxxx

Attachment: lspci-vtd.txt
Description: Text document

Attachment: xen-serial-log.txt
Description: Text document

Attachment: xen-serial-log-iommu_inclusive_mapping.txt
Description: Text document

Attachment: xm-info-vtd.txt
Description: Text document

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel