XCI: can we get to the demo state?

XCI: can we get to the demo state?

[Phung Te Ha]

Hello XCI developers,

I have a HP6930, downloaded xenclient from the git. And by following the instruction in HOWTO, I could get xenclient boot up fine. I try then to start a guest using xenvm.readme as template and nothing shows on the screen for the guest, although xenops shows 2 doms running.

Can you point me to how to start a guest. And also, is the tree downloaded from git enough to arrive to what was shown in the demo video:

http://www.citrix.com/tv/#video/423

Thank you.

Phung-Te

Re: XCI: can we get to the demo state?

[Vincent Hanquez]

Phung Te Ha wrote:
> Hello XCI developers,
>
> I have a HP6930, downloaded xenclient from the git. And by following the instruction in HOWTO, I could get xenclient boot up fine. I try then to start a guest using xenvm.readme as template and nothing shows on the screen for the guest, although xenops shows 2 doms running.
>
> Can you point me to how to start a guest. And also, is the tree downloaded from git enough to arrive to what was shown in the demo video:
>
> http://www.citrix.com/tv/#video/423
>
> Thank you.
>
> Phung-Te

Hi Phung-Te,

The demo contains few bytes from citrix that are not available, however 
you can definitely have the graphics of your VM if you have VT-d 
available and enabled. At this point you just need to set at the end of 
your xenvm config:

pci = 0,bind,PCIBUSID_OF_YOUR_GRAPHIC_CARD

usually with an intel card this end up beeing:

pci = 0,bind,0000:00:02.0

-- 
Vincent

RE: XCI: can we get to the demo state?

[Tim Moore]

Hi Vincent,

I have not had a success with the 2.6.27 XCI kernel due to a number of issues (I think with support for my hardware).

Intel Core i7 920 on Intel DX58SO (latest Intel BIOS)

Success with build.git after the dev team fixed..

XCI Kernel fails to boot: 2 reasons

Randomly stops and freezes after initialising the 1st core on the processor (keyboard lockup / total machine lockup) have to hard reset to try again...

If it passes this point, kernel then continues to load all processor cores, and upto SATA controller (AHCI Mode). The driver loads the disk sd(..) and then the system reboots - no messages - I think just before initrc is started.

I have no RS232 on this board, so am waiting for a 1394 adapter for laptop before I can debug further... 

Any pointers to getting further would help; I can't even get the point of trying pass-through for vga!

Cheers,
Tim


-----Original Message-----
From: xen-devel-bounces@lists.xensource.com [mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of Vincent Hanquez
Sent: 10 August 2009 14:20
To: Phung Te Ha
Cc: xen-devel@lists.xensource.com
Subject: Re: [Xen-devel] XCI: can we get to the demo state?

Phung Te Ha wrote:
> Hello XCI developers,
>
> I have a HP6930, downloaded xenclient from the git. And by following the instruction in HOWTO, I could get xenclient boot up fine. I try then to start a guest using xenvm.readme as template and nothing shows on the screen for the guest, although xenops shows 2 doms running.
>
> Can you point me to how to start a guest. And also, is the tree downloaded from git enough to arrive to what was shown in the demo video:
>
> http://www.citrix.com/tv/#video/423
>
> Thank you.
>
> Phung-Te

Hi Phung-Te,

The demo contains few bytes from citrix that are not available, however 
you can definitely have the graphics of your VM if you have VT-d 
available and enabled. At this point you just need to set at the end of 
your xenvm config:

pci = 0,bind,PCIBUSID_OF_YOUR_GRAPHIC_CARD

usually with an intel card this end up beeing:

pci = 0,bind,0000:00:02.0

-- 
Vincent

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

Re: XCI: can we get to the demo state?

[Vincent Hanquez]

Tim Moore wrote:
> Hi Vincent,
>
> I have not had a success with the 2.6.27 XCI kernel due to a number of issues (I think with support for my hardware).
>
> Intel Core i7 920 on Intel DX58SO (latest Intel BIOS)
>
> Success with build.git after the dev team fixed..
>
> XCI Kernel fails to boot: 2 reasons
>
> Randomly stops and freezes after initialising the 1st core on the processor (keyboard lockup / total machine lockup) have to hard reset to try again...
>
> If it passes this point, kernel then continues to load all processor cores, and upto SATA controller (AHCI Mode). The driver loads the disk sd(..) and then the system reboots - no messages - I think just before initrc is started.
>
> I have no RS232 on this board, so am waiting for a 1394 adapter for laptop before I can debug further... 
>
> Any pointers to getting further would help; I can't even get the point of trying pass-through for vga!
>   
are you able to boot with normal xen-unstable and the 2.6.27 ?

Did you try to tweak acpi or smp in your dom0 (or xen) command line ?
you can try to set nosmp, acpi=0, maxcpus=1 to see if it helps (see xen 
documentation for the xen equivalents).

-- 
Vincent

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 1955 bytes --]

Hi Vincent,

I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.

On both machines, I got the samething, the guest run as shown by xenops
list_domains:

 id |  state |    cpu_time |                                 uuid
 0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
 1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002

But nothing shows on the screen.

I checked the logs and found in xenops dmesg:

...
(XEN) Intel VT-d Snoop Control not supported.
(XEN) Intel VT-d DMA Passthrough not supported.
(XEN) Intel VT-d Queued Invalidation not supported.
(XEN) Intel VT-d Interrupt Remapping not supported.
(XEN) I/O virtualisation enabled
(XEN) I/O virtualisation for PV guests disabled


And when the guest is started:

...
 _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
ffff828bfff56000
(XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = faddf7
(XEN)     root_entry = ffff83007e0ce000
(XEN)     root_entry[0] = 7e066001
(XEN)     context = ffff83007e066000
(XEN)     context[10] = 201_7da02001
(XEN)     l3 = ffff83007da02000
(XEN)     l3_index = 3e
(XEN)     l3[3e] = 0
(XEN)     l3[3e] not present
(XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
(XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
(XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
(XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000 REASON
5 iommu->reg = ffff828bfff56000
(XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = faddf7
(XEN)     root_entry = ffff83007e0ce000
(XEN)     root_entry[0] = 7e066001
(XEN)     context = ffff83007e066000
...

Do you think these 2 machines have enough of VT-d features to get the
graphics passed-through?
Do you have a preferred desktop board, known to work for graphisc
passed-through?

Thank you very much.

Phung-Te

[-- Attachment #1.2: Type: text/html, Size: 2156 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Vincent Hanquez]

Phung Te Ha wrote:
> Hi Vincent,
>
> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>
> On both machines, I got the samething, the guest run as shown by 
> xenops list_domains:
>
>  id |  state |    cpu_time |                                 uuid
>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>
> But nothing shows on the screen.
>
> I checked the logs and found in xenops dmesg:
>
> ...
> (XEN) Intel VT-d Snoop Control not supported.
> (XEN) Intel VT-d DMA Passthrough not supported.
> (XEN) Intel VT-d Queued Invalidation not supported.
> (XEN) Intel VT-d Interrupt Remapping not supported.
> (XEN) I/O virtualisation enabled
> (XEN) I/O virtualisation for PV guests disabled
>
>
> And when the guest is started:
>
> ...
>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg = 
> ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = 
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> (XEN)     context[10] = 201_7da02001
> (XEN)     l3 = ffff83007da02000
> (XEN)     l3_index = 3e
> (XEN)     l3[3e] = 0
> (XEN)     l3[3e] not present
> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000 
> REASON 5 iommu->reg = ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = 
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> ...
>
> Do you think these 2 machines have enough of VT-d features to get the 
> graphics passed-through?
> Do you have a preferred desktop board, known to work for graphisc 
> passed-through?
I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have 
any idea, what this previous errors means ?

thanks,
-- 
Vincent

RE: XCI: can we get to the demo state?

[Ross Philipson]

Yeah, these occur when the iommu context for the device in question (in this case your iGfx card) has been torn down but the card is still active (still attempting DMA). The code in xen to perform an function level resets (FLR) on the devices takes care of the vast majority of these but there still remain one or two that occur even thought the FLR has been done. This issue was never resolved but these few remaining faults don't seem to cause a problem. So you are experiencing a hang as the vm starts I take it. Is the vtd fault trace the last thing you see? Are you passing anything else through?

Thanks
Ross

-----Original Message-----
From: Vincent Hanquez 
Sent: Friday, August 14, 2009 7:05 AM
To: Phung Te Ha
Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
Subject: Re: [Xen-devel] XCI: can we get to the demo state?

Phung Te Ha wrote:
> Hi Vincent,
>
> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>
> On both machines, I got the samething, the guest run as shown by 
> xenops list_domains:
>
>  id |  state |    cpu_time |                                 uuid
>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>
> But nothing shows on the screen.
>
> I checked the logs and found in xenops dmesg:
>
> ...
> (XEN) Intel VT-d Snoop Control not supported.
> (XEN) Intel VT-d DMA Passthrough not supported.
> (XEN) Intel VT-d Queued Invalidation not supported.
> (XEN) Intel VT-d Interrupt Remapping not supported.
> (XEN) I/O virtualisation enabled
> (XEN) I/O virtualisation for PV guests disabled
>
>
> And when the guest is started:
>
> ...
>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg = 
> ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = 
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> (XEN)     context[10] = 201_7da02001
> (XEN)     l3 = ffff83007da02000
> (XEN)     l3_index = 3e
> (XEN)     l3[3e] = 0
> (XEN)     l3[3e] not present
> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000 
> REASON 5 iommu->reg = ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn = 
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> ...
>
> Do you think these 2 machines have enough of VT-d features to get the 
> graphics passed-through?
> Do you have a preferred desktop board, known to work for graphisc 
> passed-through?
I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have 
any idea, what this previous errors means ?

thanks,
-- 
Vincent

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 3819 bytes --]

Hello all,

The only thing I passed through was the graphics controller.
After starting the guest, the system is still there running, xenops
list_domains shows 2 doms running, but nothing from the guest is showing.

The board I am using is the Intel DQ35OJ and the graphics controller is the
onboard one. Same operation has also been done on a HP6930p, same result.
Can you publish the list of hardware you guys are using, MB, graphics
board..., the config that most likely to get a graphics controller passed
through.

Thank you.

Phung-Te

On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson
<Ross.Philipson@citrix.com>wrote:

> Yeah, these occur when the iommu context for the device in question (in
> this case your iGfx card) has been torn down but the card is still active
> (still attempting DMA). The code in xen to perform an function level resets
> (FLR) on the devices takes care of the vast majority of these but there
> still remain one or two that occur even thought the FLR has been done. This
> issue was never resolved but these few remaining faults don't seem to cause
> a problem. So you are experiencing a hang as the vm starts I take it. Is the
> vtd fault trace the last thing you see? Are you passing anything else
> through?
>
> Thanks
> Ross
>
> -----Original Message-----
> From: Vincent Hanquez
> Sent: Friday, August 14, 2009 7:05 AM
> To: Phung Te Ha
> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
> Phung Te Ha wrote:
> > Hi Vincent,
> >
> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >
> > On both machines, I got the samething, the guest run as shown by
> > xenops list_domains:
> >
> >  id |  state |    cpu_time |                                 uuid
> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >
> > But nothing shows on the screen.
> >
> > I checked the logs and found in xenops dmesg:
> >
> > ...
> > (XEN) Intel VT-d Snoop Control not supported.
> > (XEN) Intel VT-d DMA Passthrough not supported.
> > (XEN) Intel VT-d Queued Invalidation not supported.
> > (XEN) Intel VT-d Interrupt Remapping not supported.
> > (XEN) I/O virtualisation enabled
> > (XEN) I/O virtualisation for PV guests disabled
> >
> >
> > And when the guest is started:
> >
> > ...
> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> > ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > (XEN)     context[10] = 201_7da02001
> > (XEN)     l3 = ffff83007da02000
> > (XEN)     l3_index = 3e
> > (XEN)     l3[3e] = 0
> > (XEN)     l3[3e] not present
> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> > REASON 5 iommu->reg = ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > ...
> >
> > Do you think these 2 machines have enough of VT-d features to get the
> > graphics passed-through?
> > Do you have a preferred desktop board, known to work for graphisc
> > passed-through?
> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> any idea, what this previous errors means ?
>
> thanks,
> --
> Vincent
>

[-- Attachment #1.2: Type: text/html, Size: 4682 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

RE: XCI: can we get to the demo state?

[Ross Philipson]

[-- Attachment #1.1: Type: text/plain, Size: 4270 bytes --]

Well we don't have a official list we can push but we run on the same HP 6930p you have all the time. We have also had it running on Intel Q35 systems. So in general it should work on these systems.

Thanks
Ross

From: Phung Te Ha [mailto:phungte@gmail.com]
Sent: Friday, August 14, 2009 11:32 AM
To: Ross Philipson
Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
Subject: Re: [Xen-devel] XCI: can we get to the demo state?

Hello all,

The only thing I passed through was the graphics controller.
After starting the guest, the system is still there running, xenops list_domains shows 2 doms running, but nothing from the guest is showing.

The board I am using is the Intel DQ35OJ and the graphics controller is the onboard one. Same operation has also been done on a HP6930p, same result. Can you publish the list of hardware you guys are using, MB, graphics board..., the config that most likely to get a graphics controller passed through.

Thank you.

Phung-Te
On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com<mailto:Ross.Philipson@citrix.com>> wrote:
Yeah, these occur when the iommu context for the device in question (in this case your iGfx card) has been torn down but the card is still active (still attempting DMA). The code in xen to perform an function level resets (FLR) on the devices takes care of the vast majority of these but there still remain one or two that occur even thought the FLR has been done. This issue was never resolved but these few remaining faults don't seem to cause a problem. So you are experiencing a hang as the vm starts I take it. Is the vtd fault trace the last thing you see? Are you passing anything else through?

Thanks
Ross

-----Original Message-----
From: Vincent Hanquez
Sent: Friday, August 14, 2009 7:05 AM
To: Phung Te Ha
Cc: xen-devel@lists.xensource.com<mailto:xen-devel@lists.xensource.com>; Ross Philipson; Kamala Narasimhan
Subject: Re: [Xen-devel] XCI: can we get to the demo state?
Phung Te Ha wrote:
> Hi Vincent,
>
> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>
> On both machines, I got the samething, the guest run as shown by
> xenops list_domains:
>
>  id |  state |    cpu_time |                                 uuid
>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>
> But nothing shows on the screen.
>
> I checked the logs and found in xenops dmesg:
>
> ...
> (XEN) Intel VT-d Snoop Control not supported.
> (XEN) Intel VT-d DMA Passthrough not supported.
> (XEN) Intel VT-d Queued Invalidation not supported.
> (XEN) Intel VT-d Interrupt Remapping not supported.
> (XEN) I/O virtualisation enabled
> (XEN) I/O virtualisation for PV guests disabled
>
>
> And when the guest is started:
>
> ...
>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> (XEN)     context[10] = 201_7da02001
> (XEN)     l3 = ffff83007da02000
> (XEN)     l3_index = 3e
> (XEN)     l3[3e] = 0
> (XEN)     l3[3e] not present
> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> REASON 5 iommu->reg = ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> ...
>
> Do you think these 2 machines have enough of VT-d features to get the
> graphics passed-through?
> Do you have a preferred desktop board, known to work for graphisc
> passed-through?
I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
any idea, what this previous errors means ?

thanks,
--
Vincent


[-- Attachment #1.2: Type: text/html, Size: 8094 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 4712 bytes --]

Do you pass the graphics controller through? Which guest are you using? Do
you mind publish your config file?

Thank you.

Phung-Te

On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson
<Ross.Philipson@citrix.com>wrote:

>  Well we don’t have a official list we can push but we run on the same HP
> 6930p you have all the time. We have also had it running on Intel Q35
> systems. So in general it should work on these systems.
>
>
>
> Thanks
>
> Ross
>
>
>
> *From:* Phung Te Ha [mailto:phungte@gmail.com]
> *Sent:* Friday, August 14, 2009 11:32 AM
> *To:* Ross Philipson
> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>
> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Hello all,
>
> The only thing I passed through was the graphics controller.
> After starting the guest, the system is still there running, xenops
> list_domains shows 2 doms running, but nothing from the guest is showing.
>
> The board I am using is the Intel DQ35OJ and the graphics controller is the
> onboard one. Same operation has also been done on a HP6930p, same result.
> Can you publish the list of hardware you guys are using, MB, graphics
> board..., the config that most likely to get a graphics controller passed
> through.
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com>
> wrote:
>
> Yeah, these occur when the iommu context for the device in question (in
> this case your iGfx card) has been torn down but the card is still active
> (still attempting DMA). The code in xen to perform an function level resets
> (FLR) on the devices takes care of the vast majority of these but there
> still remain one or two that occur even thought the FLR has been done. This
> issue was never resolved but these few remaining faults don't seem to cause
> a problem. So you are experiencing a hang as the vm starts I take it. Is the
> vtd fault trace the last thing you see? Are you passing anything else
> through?
>
> Thanks
> Ross
>
>
> -----Original Message-----
> From: Vincent Hanquez
> Sent: Friday, August 14, 2009 7:05 AM
> To: Phung Te Ha
>
> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
> Phung Te Ha wrote:
> > Hi Vincent,
> >
> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >
> > On both machines, I got the samething, the guest run as shown by
> > xenops list_domains:
> >
> >  id |  state |    cpu_time |                                 uuid
> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >
> > But nothing shows on the screen.
> >
> > I checked the logs and found in xenops dmesg:
> >
> > ...
> > (XEN) Intel VT-d Snoop Control not supported.
> > (XEN) Intel VT-d DMA Passthrough not supported.
> > (XEN) Intel VT-d Queued Invalidation not supported.
> > (XEN) Intel VT-d Interrupt Remapping not supported.
> > (XEN) I/O virtualisation enabled
> > (XEN) I/O virtualisation for PV guests disabled
> >
> >
> > And when the guest is started:
> >
> > ...
> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> > ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > (XEN)     context[10] = 201_7da02001
> > (XEN)     l3 = ffff83007da02000
> > (XEN)     l3_index = 3e
> > (XEN)     l3[3e] = 0
> > (XEN)     l3[3e] not present
> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> > REASON 5 iommu->reg = ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > ...
> >
> > Do you think these 2 machines have enough of VT-d features to get the
> > graphics passed-through?
> > Do you have a preferred desktop board, known to work for graphisc
> > passed-through?
> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> any idea, what this previous errors means ?
>
> thanks,
> --
> Vincent
>
>
>

[-- Attachment #1.2: Type: text/html, Size: 6620 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

RE: XCI: can we get to the demo state?

[Ross Philipson]

[-- Attachment #1.1: Type: text/plain, Size: 5232 bytes --]

Yes, I am passing the graphics through. I am using an HP 6930p at the moment. I am using Windows Vista as the VM I am passing the graphics through to and using Windows XP in a second VM that I am using VNC for. I attached the xenvm config files I happen to be using right now. Note that my Vista install is not a vhd but rather installed on a partition on disk.

Ross

From: Phung Te Ha [mailto:phungte@gmail.com]
Sent: Friday, August 14, 2009 4:18 PM
To: Ross Philipson
Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
Subject: Re: [Xen-devel] XCI: can we get to the demo state?

Do you pass the graphics controller through? Which guest are you using? Do you mind publish your config file?

Thank you.

Phung-Te
On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <Ross.Philipson@citrix.com<mailto:Ross.Philipson@citrix.com>> wrote:

Well we don't have a official list we can push but we run on the same HP 6930p you have all the time. We have also had it running on Intel Q35 systems. So in general it should work on these systems.



Thanks

Ross



From: Phung Te Ha [mailto:phungte@gmail.com<mailto:phungte@gmail.com>]
Sent: Friday, August 14, 2009 11:32 AM
To: Ross Philipson
Cc: Vincent Hanquez; xen-devel@lists.xensource.com<mailto:xen-devel@lists.xensource.com>; Kamala Narasimhan

Subject: Re: [Xen-devel] XCI: can we get to the demo state?



Hello all,

The only thing I passed through was the graphics controller.
After starting the guest, the system is still there running, xenops list_domains shows 2 doms running, but nothing from the guest is showing.

The board I am using is the Intel DQ35OJ and the graphics controller is the onboard one. Same operation has also been done on a HP6930p, same result. Can you publish the list of hardware you guys are using, MB, graphics board..., the config that most likely to get a graphics controller passed through.

Thank you.

Phung-Te

On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com<mailto:Ross.Philipson@citrix.com>> wrote:

Yeah, these occur when the iommu context for the device in question (in this case your iGfx card) has been torn down but the card is still active (still attempting DMA). The code in xen to perform an function level resets (FLR) on the devices takes care of the vast majority of these but there still remain one or two that occur even thought the FLR has been done. This issue was never resolved but these few remaining faults don't seem to cause a problem. So you are experiencing a hang as the vm starts I take it. Is the vtd fault trace the last thing you see? Are you passing anything else through?

Thanks
Ross

-----Original Message-----
From: Vincent Hanquez
Sent: Friday, August 14, 2009 7:05 AM
To: Phung Te Ha

Cc: xen-devel@lists.xensource.com<mailto:xen-devel@lists.xensource.com>; Ross Philipson; Kamala Narasimhan
Subject: Re: [Xen-devel] XCI: can we get to the demo state?

Phung Te Ha wrote:
> Hi Vincent,
>
> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>
> On both machines, I got the samething, the guest run as shown by
> xenops list_domains:
>
>  id |  state |    cpu_time |                                 uuid
>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>
> But nothing shows on the screen.
>
> I checked the logs and found in xenops dmesg:
>
> ...
> (XEN) Intel VT-d Snoop Control not supported.
> (XEN) Intel VT-d DMA Passthrough not supported.
> (XEN) Intel VT-d Queued Invalidation not supported.
> (XEN) Intel VT-d Interrupt Remapping not supported.
> (XEN) I/O virtualisation enabled
> (XEN) I/O virtualisation for PV guests disabled
>
>
> And when the guest is started:
>
> ...
>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> (XEN)     context[10] = 201_7da02001
> (XEN)     l3 = ffff83007da02000
> (XEN)     l3_index = 3e
> (XEN)     l3[3e] = 0
> (XEN)     l3[3e] not present
> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> REASON 5 iommu->reg = ffff828bfff56000
> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> faddf7
> (XEN)     root_entry = ffff83007e0ce000
> (XEN)     root_entry[0] = 7e066001
> (XEN)     context = ffff83007e066000
> ...
>
> Do you think these 2 machines have enough of VT-d features to get the
> graphics passed-through?
> Do you have a preferred desktop board, known to work for graphisc
> passed-through?
I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
any idea, what this previous errors means ?

thanks,
--
Vincent




[-- Attachment #1.2: Type: text/html, Size: 10168 bytes --]

[-- Attachment #2: svm --]
[-- Type: application/octet-stream, Size: 613 bytes --]

uuid = da77e8b6-2ad8-49d1-8bb3-21df90c86131

debug = true
hvm = true
pae = true
acpi = true
apic = true
nx = true

#disk = /dev/xenclient/storage/winxp_dev.vhd:vhd:hda:w:disk
disk = /storage/winxp_dev.vhd:vhd:hda:w:disk
disk = /root/Image_090813_1238.iso:file:hdd:r:cdrom

memory = 256
videoram = 8

vif = bridge=xenbr0

#serial = tcp:10.204.4.73:7204

vnc = -1
# This is the slot number it needs to be between 1 and 4
# 1 is usally the PVM
#extra-hvm = dom0-input=2
#extra-hvm = intel=
#extra-hvm = std-vga=

extra-hvm = vga=std
extra-hvm = vnc=0.0.0.0:1
extra-hvm = usbdevice=tablet

#pci = 0,bind,0000:00:1b.0

[-- Attachment #3: pvm --]
[-- Type: application/octet-stream, Size: 481 bytes --]

uuid = 00000000-0000-0000-0000-000000000001

debug = true
hvm = true
pae = true
acpi = true
apic = true
nx = true

smbios-pt = true
acpi-pt = true
diskinfo-pt = true
oem-features = 1

power-management = 2

#serial = tcp:10.204.4.73:7204

vif = bridge=xenbr0

disk = /dev/sda:phy:hda:w:disk

memory = 1200

vnc = -1
extra-hvm = dom0-input=1
extra-hvm = vga-passthrough=

pci = 0,bind,0000:00:02.0
#pci = 0,bind,0000:00:1b.0
#pci = 0,bind,0000:02:00.0

[-- Attachment #4: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 5552 bytes --]

Thank you Ross, I am working on it and will update.

On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson
<Ross.Philipson@citrix.com>wrote:

>  Yes, I am passing the graphics through. I am using an HP 6930p at the
> moment. I am using Windows Vista as the VM I am passing the graphics through
> to and using Windows XP in a second VM that I am using VNC for. I attached
> the xenvm config files I happen to be using right now. Note that my Vista
> install is not a vhd but rather installed on a partition on disk.
>
>
>
> Ross
>
>
>
> *From:* Phung Te Ha [mailto:phungte@gmail.com]
> *Sent:* Friday, August 14, 2009 4:18 PM
>
> *To:* Ross Philipson
> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Do you pass the graphics controller through? Which guest are you using? Do
> you mind publish your config file?
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <
> Ross.Philipson@citrix.com> wrote:
>
> Well we don’t have a official list we can push but we run on the same HP
> 6930p you have all the time. We have also had it running on Intel Q35
> systems. So in general it should work on these systems.
>
>
>
> Thanks
>
> Ross
>
>
>
> *From:* Phung Te Ha [mailto:phungte@gmail.com]
> *Sent:* Friday, August 14, 2009 11:32 AM
> *To:* Ross Philipson
> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>
>
> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Hello all,
>
> The only thing I passed through was the graphics controller.
> After starting the guest, the system is still there running, xenops
> list_domains shows 2 doms running, but nothing from the guest is showing.
>
> The board I am using is the Intel DQ35OJ and the graphics controller is the
> onboard one. Same operation has also been done on a HP6930p, same result.
> Can you publish the list of hardware you guys are using, MB, graphics
> board..., the config that most likely to get a graphics controller passed
> through.
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com>
> wrote:
>
> Yeah, these occur when the iommu context for the device in question (in
> this case your iGfx card) has been torn down but the card is still active
> (still attempting DMA). The code in xen to perform an function level resets
> (FLR) on the devices takes care of the vast majority of these but there
> still remain one or two that occur even thought the FLR has been done. This
> issue was never resolved but these few remaining faults don't seem to cause
> a problem. So you are experiencing a hang as the vm starts I take it. Is the
> vtd fault trace the last thing you see? Are you passing anything else
> through?
>
> Thanks
> Ross
>
>
> -----Original Message-----
> From: Vincent Hanquez
> Sent: Friday, August 14, 2009 7:05 AM
> To: Phung Te Ha
>
> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
> Phung Te Ha wrote:
> > Hi Vincent,
> >
> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >
> > On both machines, I got the samething, the guest run as shown by
> > xenops list_domains:
> >
> >  id |  state |    cpu_time |                                 uuid
> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >
> > But nothing shows on the screen.
> >
> > I checked the logs and found in xenops dmesg:
> >
> > ...
> > (XEN) Intel VT-d Snoop Control not supported.
> > (XEN) Intel VT-d DMA Passthrough not supported.
> > (XEN) Intel VT-d Queued Invalidation not supported.
> > (XEN) Intel VT-d Interrupt Remapping not supported.
> > (XEN) I/O virtualisation enabled
> > (XEN) I/O virtualisation for PV guests disabled
> >
> >
> > And when the guest is started:
> >
> > ...
> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> > ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > (XEN)     context[10] = 201_7da02001
> > (XEN)     l3 = ffff83007da02000
> > (XEN)     l3_index = 3e
> > (XEN)     l3[3e] = 0
> > (XEN)     l3[3e] not present
> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> > REASON 5 iommu->reg = ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > ...
> >
> > Do you think these 2 machines have enough of VT-d features to get the
> > graphics passed-through?
> > Do you have a preferred desktop board, known to work for graphisc
> > passed-through?
> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> any idea, what this previous errors means ?
>
> thanks,
> --
> Vincent
>
>
>
>
>

[-- Attachment #1.2: Type: text/html, Size: 8403 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Tom Rotenberg]

I think that the "hanging" problem happens, when you try to
pass-through, both the 00:02.0, and the 00:02.1 (at-least that's what
happened to me in the past), so i guess that because you are just
passing through 00:02.0, you don't get this problem...

Can you try to pass-through 00:02.1 also, and see if it happens to you?

On Sat, Aug 15, 2009 at 12:15 AM, Ross
Philipson<Ross.Philipson@citrix.com> wrote:
> Yes, I am passing the graphics through. I am using an HP 6930p at the
> moment. I am using Windows Vista as the VM I am passing the graphics through
> to and using Windows XP in a second VM that I am using VNC for. I attached
> the xenvm config files I happen to be using right now. Note that my Vista
> install is not a vhd but rather installed on a partition on disk.
>
>
>
> Ross
>
>
>
> From: Phung Te Ha [mailto:phungte@gmail.com]
> Sent: Friday, August 14, 2009 4:18 PM
>
> To: Ross Philipson
> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Do you pass the graphics controller through? Which guest are you using? Do
> you mind publish your config file?
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <Ross.Philipson@citrix.com>
> wrote:
>
> Well we don’t have a official list we can push but we run on the same HP
> 6930p you have all the time. We have also had it running on Intel Q35
> systems. So in general it should work on these systems.
>
>
>
> Thanks
>
> Ross
>
>
>
> From: Phung Te Ha [mailto:phungte@gmail.com]
> Sent: Friday, August 14, 2009 11:32 AM
> To: Ross Philipson
> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Hello all,
>
> The only thing I passed through was the graphics controller.
> After starting the guest, the system is still there running, xenops
> list_domains shows 2 doms running, but nothing from the guest is showing.
>
> The board I am using is the Intel DQ35OJ and the graphics controller is the
> onboard one. Same operation has also been done on a HP6930p, same result.
> Can you publish the list of hardware you guys are using, MB, graphics
> board..., the config that most likely to get a graphics controller passed
> through.
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com>
> wrote:
>
> Yeah, these occur when the iommu context for the device in question (in this
> case your iGfx card) has been torn down but the card is still active (still
> attempting DMA). The code in xen to perform an function level resets (FLR)
> on the devices takes care of the vast majority of these but there still
> remain one or two that occur even thought the FLR has been done. This issue
> was never resolved but these few remaining faults don't seem to cause a
> problem. So you are experiencing a hang as the vm starts I take it. Is the
> vtd fault trace the last thing you see? Are you passing anything else
> through?
>
> Thanks
> Ross
>
> -----Original Message-----
> From: Vincent Hanquez
> Sent: Friday, August 14, 2009 7:05 AM
> To: Phung Te Ha
>
> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
> Phung Te Ha wrote:
>> Hi Vincent,
>>
>> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
>> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>>
>> On both machines, I got the samething, the guest run as shown by
>> xenops list_domains:
>>
>>  id |  state |    cpu_time |                                 uuid
>>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>>
>> But nothing shows on the screen.
>>
>> I checked the logs and found in xenops dmesg:
>>
>> ...
>> (XEN) Intel VT-d Snoop Control not supported.
>> (XEN) Intel VT-d DMA Passthrough not supported.
>> (XEN) Intel VT-d Queued Invalidation not supported.
>> (XEN) Intel VT-d Interrupt Remapping not supported.
>> (XEN) I/O virtualisation enabled
>> (XEN) I/O virtualisation for PV guests disabled
>>
>>
>> And when the guest is started:
>>
>> ...
>>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
>> ffff828bfff56000
>> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>> faddf7
>> (XEN)     root_entry = ffff83007e0ce000
>> (XEN)     root_entry[0] = 7e066001
>> (XEN)     context = ffff83007e066000
>> (XEN)     context[10] = 201_7da02001
>> (XEN)     l3 = ffff83007da02000
>> (XEN)     l3_index = 3e
>> (XEN)     l3[3e] = 0
>> (XEN)     l3[3e] not present
>> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
>> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
>> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
>> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
>> REASON 5 iommu->reg = ffff828bfff56000
>> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>> faddf7
>> (XEN)     root_entry = ffff83007e0ce000
>> (XEN)     root_entry[0] = 7e066001
>> (XEN)     context = ffff83007e066000
>> ...
>>
>> Do you think these 2 machines have enough of VT-d features to get the
>> graphics passed-through?
>> Do you have a preferred desktop board, known to work for graphisc
>> passed-through?
> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> any idea, what this previous errors means ?
>
> thanks,
> --
> Vincent
>
>
>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
>
>

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 6103 bytes --]

Hi all,

Thanks to your helps, I could see vista come up from a DVD installation with
the graphics controller passed-through. The machine I am using is HP6930p.
The config is Ross', just changed the disk from:

disk = /dev/sda:phy:hda:w:disk

to

disk = /dev/sr0:phy:hdd:r:cdrom

I also have vista on the disk at /dev/sda1. But since I use the same disk to
boot xenclient, when I start the guest, giving /dev/sda as disk, grub wants
to boot xenclient again, instead of vista.

So now I am building a xenclient_usb config, and leave /dev/sda to vista
only.

Will update.

Phung-Te


On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson
<Ross.Philipson@citrix.com>wrote:

>  Yes, I am passing the graphics through. I am using an HP 6930p at the
> moment. I am using Windows Vista as the VM I am passing the graphics through
> to and using Windows XP in a second VM that I am using VNC for. I attached
> the xenvm config files I happen to be using right now. Note that my Vista
> install is not a vhd but rather installed on a partition on disk.
>
>
>
> Ross
>
>
>
> *From:* Phung Te Ha [mailto:phungte@gmail.com]
> *Sent:* Friday, August 14, 2009 4:18 PM
>
> *To:* Ross Philipson
> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Do you pass the graphics controller through? Which guest are you using? Do
> you mind publish your config file?
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <
> Ross.Philipson@citrix.com> wrote:
>
> Well we don’t have a official list we can push but we run on the same HP
> 6930p you have all the time. We have also had it running on Intel Q35
> systems. So in general it should work on these systems.
>
>
>
> Thanks
>
> Ross
>
>
>
> *From:* Phung Te Ha [mailto:phungte@gmail.com]
> *Sent:* Friday, August 14, 2009 11:32 AM
> *To:* Ross Philipson
> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>
>
> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>
>
>
> Hello all,
>
> The only thing I passed through was the graphics controller.
> After starting the guest, the system is still there running, xenops
> list_domains shows 2 doms running, but nothing from the guest is showing.
>
> The board I am using is the Intel DQ35OJ and the graphics controller is the
> onboard one. Same operation has also been done on a HP6930p, same result.
> Can you publish the list of hardware you guys are using, MB, graphics
> board..., the config that most likely to get a graphics controller passed
> through.
>
> Thank you.
>
> Phung-Te
>
> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <Ross.Philipson@citrix.com>
> wrote:
>
> Yeah, these occur when the iommu context for the device in question (in
> this case your iGfx card) has been torn down but the card is still active
> (still attempting DMA). The code in xen to perform an function level resets
> (FLR) on the devices takes care of the vast majority of these but there
> still remain one or two that occur even thought the FLR has been done. This
> issue was never resolved but these few remaining faults don't seem to cause
> a problem. So you are experiencing a hang as the vm starts I take it. Is the
> vtd fault trace the last thing you see? Are you passing anything else
> through?
>
> Thanks
> Ross
>
>
> -----Original Message-----
> From: Vincent Hanquez
> Sent: Friday, August 14, 2009 7:05 AM
> To: Phung Te Ha
>
> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>
> Phung Te Ha wrote:
> > Hi Vincent,
> >
> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >
> > On both machines, I got the samething, the guest run as shown by
> > xenops list_domains:
> >
> >  id |  state |    cpu_time |                                 uuid
> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >
> > But nothing shows on the screen.
> >
> > I checked the logs and found in xenops dmesg:
> >
> > ...
> > (XEN) Intel VT-d Snoop Control not supported.
> > (XEN) Intel VT-d DMA Passthrough not supported.
> > (XEN) Intel VT-d Queued Invalidation not supported.
> > (XEN) Intel VT-d Interrupt Remapping not supported.
> > (XEN) I/O virtualisation enabled
> > (XEN) I/O virtualisation for PV guests disabled
> >
> >
> > And when the guest is started:
> >
> > ...
> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> > ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > (XEN)     context[10] = 201_7da02001
> > (XEN)     l3 = ffff83007da02000
> > (XEN)     l3_index = 3e
> > (XEN)     l3[3e] = 0
> > (XEN)     l3[3e] not present
> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> > REASON 5 iommu->reg = ffff828bfff56000
> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> > faddf7
> > (XEN)     root_entry = ffff83007e0ce000
> > (XEN)     root_entry[0] = 7e066001
> > (XEN)     context = ffff83007e066000
> > ...
> >
> > Do you think these 2 machines have enough of VT-d features to get the
> > graphics passed-through?
> > Do you have a preferred desktop board, known to work for graphisc
> > passed-through?
> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> any idea, what this previous errors means ?
>
> thanks,
> --
> Vincent
>
>
>
>
>

[-- Attachment #1.2: Type: text/html, Size: 9025 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 6420 bytes --]

Hi Tom,

It does hang for me too.

Phung-Te

On Sat, Aug 15, 2009 at 10:38 AM, Tom Rotenberg <tom.rotenberg@gmail.com>wrote:

> I think that the "hanging" problem happens, when you try to
> pass-through, both the 00:02.0, and the 00:02.1 (at-least that's what
> happened to me in the past), so i guess that because you are just
> passing through 00:02.0, you don't get this problem...
>
> Can you try to pass-through 00:02.1 also, and see if it happens to you?
>
> On Sat, Aug 15, 2009 at 12:15 AM, Ross
> Philipson<Ross.Philipson@citrix.com> wrote:
> > Yes, I am passing the graphics through. I am using an HP 6930p at the
> > moment. I am using Windows Vista as the VM I am passing the graphics
> through
> > to and using Windows XP in a second VM that I am using VNC for. I
> attached
> > the xenvm config files I happen to be using right now. Note that my Vista
> > install is not a vhd but rather installed on a partition on disk.
> >
> >
> >
> > Ross
> >
> >
> >
> > From: Phung Te Ha [mailto:phungte@gmail.com]
> > Sent: Friday, August 14, 2009 4:18 PM
> >
> > To: Ross Philipson
> > Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> > Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >
> >
> >
> > Do you pass the graphics controller through? Which guest are you using?
> Do
> > you mind publish your config file?
> >
> > Thank you.
> >
> > Phung-Te
> >
> > On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <
> Ross.Philipson@citrix.com>
> > wrote:
> >
> > Well we don’t have a official list we can push but we run on the same HP
> > 6930p you have all the time. We have also had it running on Intel Q35
> > systems. So in general it should work on these systems.
> >
> >
> >
> > Thanks
> >
> > Ross
> >
> >
> >
> > From: Phung Te Ha [mailto:phungte@gmail.com]
> > Sent: Friday, August 14, 2009 11:32 AM
> > To: Ross Philipson
> > Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> >
> > Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >
> >
> >
> > Hello all,
> >
> > The only thing I passed through was the graphics controller.
> > After starting the guest, the system is still there running, xenops
> > list_domains shows 2 doms running, but nothing from the guest is showing.
> >
> > The board I am using is the Intel DQ35OJ and the graphics controller is
> the
> > onboard one. Same operation has also been done on a HP6930p, same result.
> > Can you publish the list of hardware you guys are using, MB, graphics
> > board..., the config that most likely to get a graphics controller passed
> > through.
> >
> > Thank you.
> >
> > Phung-Te
> >
> > On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <
> Ross.Philipson@citrix.com>
> > wrote:
> >
> > Yeah, these occur when the iommu context for the device in question (in
> this
> > case your iGfx card) has been torn down but the card is still active
> (still
> > attempting DMA). The code in xen to perform an function level resets
> (FLR)
> > on the devices takes care of the vast majority of these but there still
> > remain one or two that occur even thought the FLR has been done. This
> issue
> > was never resolved but these few remaining faults don't seem to cause a
> > problem. So you are experiencing a hang as the vm starts I take it. Is
> the
> > vtd fault trace the last thing you see? Are you passing anything else
> > through?
> >
> > Thanks
> > Ross
> >
> > -----Original Message-----
> > From: Vincent Hanquez
> > Sent: Friday, August 14, 2009 7:05 AM
> > To: Phung Te Ha
> >
> > Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> > Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >
> > Phung Te Ha wrote:
> >> Hi Vincent,
> >>
> >> I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
> >> on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >>
> >> On both machines, I got the samething, the guest run as shown by
> >> xenops list_domains:
> >>
> >>  id |  state |    cpu_time |                                 uuid
> >>  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >>  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >>
> >> But nothing shows on the screen.
> >>
> >> I checked the logs and found in xenops dmesg:
> >>
> >> ...
> >> (XEN) Intel VT-d Snoop Control not supported.
> >> (XEN) Intel VT-d DMA Passthrough not supported.
> >> (XEN) Intel VT-d Queued Invalidation not supported.
> >> (XEN) Intel VT-d Interrupt Remapping not supported.
> >> (XEN) I/O virtualisation enabled
> >> (XEN) I/O virtualisation for PV guests disabled
> >>
> >>
> >> And when the guest is started:
> >>
> >> ...
> >>  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> >> ffff828bfff56000
> >> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> >> faddf7
> >> (XEN)     root_entry = ffff83007e0ce000
> >> (XEN)     root_entry[0] = 7e066001
> >> (XEN)     context = ffff83007e066000
> >> (XEN)     context[10] = 201_7da02001
> >> (XEN)     l3 = ffff83007da02000
> >> (XEN)     l3_index = 3e
> >> (XEN)     l3[3e] = 0
> >> (XEN)     l3[3e] not present
> >> (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
> >> (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> >> (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> >> (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> >> REASON 5 iommu->reg = ffff828bfff56000
> >> (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> >> faddf7
> >> (XEN)     root_entry = ffff83007e0ce000
> >> (XEN)     root_entry[0] = 7e066001
> >> (XEN)     context = ffff83007e066000
> >> ...
> >>
> >> Do you think these 2 machines have enough of VT-d features to get the
> >> graphics passed-through?
> >> Do you have a preferred desktop board, known to work for graphisc
> >> passed-through?
> > I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
> > any idea, what this previous errors means ?
> >
> > thanks,
> > --
> > Vincent
> >
> >
> >
> >
> >
> > _______________________________________________
> > Xen-devel mailing list
> > Xen-devel@lists.xensource.com
> > http://lists.xensource.com/xen-devel
> >
> >
>

[-- Attachment #1.2: Type: text/html, Size: 8299 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 6776 bytes --]

Hi all,

I tried and gave up on building a xenclient_usb.config, the build broke at
quite many places. So I use file as disk:

disk = /mnt/3/vista_image.bin:file:hda:w:disk

first started a vista installation from DVD, then continued on, setup the
network, download the graphics driver from hp.com, and aero showed after
reboot!!!

Thanks for your help.

Phung-Te

On Mon, Aug 17, 2009 at 12:09 PM, Phung Te Ha <phungte@gmail.com> wrote:

> Hi all,
>
> Thanks to your helps, I could see vista come up from a DVD installation
> with the graphics controller passed-through. The machine I am using is
> HP6930p. The config is Ross', just changed the disk from:
>
> disk = /dev/sda:phy:hda:w:disk
>
> to
>
> disk = /dev/sr0:phy:hdd:r:cdrom
>
> I also have vista on the disk at /dev/sda1. But since I use the same disk
> to boot xenclient, when I start the guest, giving /dev/sda as disk, grub
> wants to boot xenclient again, instead of vista.
>
> So now I am building a xenclient_usb config, and leave /dev/sda to vista
> only.
>
> Will update.
>
> Phung-Te
>
>
>
> On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson <Ross.Philipson@citrix.com
> > wrote:
>
>>  Yes, I am passing the graphics through. I am using an HP 6930p at the
>> moment. I am using Windows Vista as the VM I am passing the graphics through
>> to and using Windows XP in a second VM that I am using VNC for. I attached
>> the xenvm config files I happen to be using right now. Note that my Vista
>> install is not a vhd but rather installed on a partition on disk.
>>
>>
>>
>> Ross
>>
>>
>>
>> *From:* Phung Te Ha [mailto:phungte@gmail.com]
>> *Sent:* Friday, August 14, 2009 4:18 PM
>>
>> *To:* Ross Philipson
>> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>>
>>
>>
>> Do you pass the graphics controller through? Which guest are you using? Do
>> you mind publish your config file?
>>
>> Thank you.
>>
>> Phung-Te
>>
>> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <
>> Ross.Philipson@citrix.com> wrote:
>>
>> Well we don’t have a official list we can push but we run on the same HP
>> 6930p you have all the time. We have also had it running on Intel Q35
>> systems. So in general it should work on these systems.
>>
>>
>>
>> Thanks
>>
>> Ross
>>
>>
>>
>> *From:* Phung Te Ha [mailto:phungte@gmail.com]
>> *Sent:* Friday, August 14, 2009 11:32 AM
>> *To:* Ross Philipson
>> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>>
>>
>> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>>
>>
>>
>> Hello all,
>>
>> The only thing I passed through was the graphics controller.
>> After starting the guest, the system is still there running, xenops
>> list_domains shows 2 doms running, but nothing from the guest is showing.
>>
>> The board I am using is the Intel DQ35OJ and the graphics controller is
>> the onboard one. Same operation has also been done on a HP6930p, same
>> result. Can you publish the list of hardware you guys are using, MB,
>> graphics board..., the config that most likely to get a graphics controller
>> passed through.
>>
>> Thank you.
>>
>> Phung-Te
>>
>> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <
>> Ross.Philipson@citrix.com> wrote:
>>
>> Yeah, these occur when the iommu context for the device in question (in
>> this case your iGfx card) has been torn down but the card is still active
>> (still attempting DMA). The code in xen to perform an function level resets
>> (FLR) on the devices takes care of the vast majority of these but there
>> still remain one or two that occur even thought the FLR has been done. This
>> issue was never resolved but these few remaining faults don't seem to cause
>> a problem. So you are experiencing a hang as the vm starts I take it. Is the
>> vtd fault trace the last thing you see? Are you passing anything else
>> through?
>>
>> Thanks
>> Ross
>>
>>
>> -----Original Message-----
>> From: Vincent Hanquez
>> Sent: Friday, August 14, 2009 7:05 AM
>> To: Phung Te Ha
>>
>> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>>
>> Phung Te Ha wrote:
>> > Hi Vincent,
>> >
>> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
>> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>> >
>> > On both machines, I got the samething, the guest run as shown by
>> > xenops list_domains:
>> >
>> >  id |  state |    cpu_time |                                 uuid
>> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>> >
>> > But nothing shows on the screen.
>> >
>> > I checked the logs and found in xenops dmesg:
>> >
>> > ...
>> > (XEN) Intel VT-d Snoop Control not supported.
>> > (XEN) Intel VT-d DMA Passthrough not supported.
>> > (XEN) Intel VT-d Queued Invalidation not supported.
>> > (XEN) Intel VT-d Interrupt Remapping not supported.
>> > (XEN) I/O virtualisation enabled
>> > (XEN) I/O virtualisation for PV guests disabled
>> >
>> >
>> > And when the guest is started:
>> >
>> > ...
>> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
>> > ffff828bfff56000
>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>> > faddf7
>> > (XEN)     root_entry = ffff83007e0ce000
>> > (XEN)     root_entry[0] = 7e066001
>> > (XEN)     context = ffff83007e066000
>> > (XEN)     context[10] = 201_7da02001
>> > (XEN)     l3 = ffff83007da02000
>> > (XEN)     l3_index = 3e
>> > (XEN)     l3[3e] = 0
>> > (XEN)     l3[3e] not present
>> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg = ffff828bfff56000
>> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
>> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
>> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
>> > REASON 5 iommu->reg = ffff828bfff56000
>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>> > faddf7
>> > (XEN)     root_entry = ffff83007e0ce000
>> > (XEN)     root_entry[0] = 7e066001
>> > (XEN)     context = ffff83007e066000
>> > ...
>> >
>> > Do you think these 2 machines have enough of VT-d features to get the
>> > graphics passed-through?
>> > Do you have a preferred desktop board, known to work for graphisc
>> > passed-through?
>> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
>> any idea, what this previous errors means ?
>>
>> thanks,
>> --
>> Vincent
>>
>>
>>
>>
>>
>
>

[-- Attachment #1.2: Type: text/html, Size: 9850 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Tom Rotenberg]

Did the Aero worked for you on the nVidia/ATI or on the Intel IGD?

On Wed, Aug 19, 2009 at 12:17 AM, Phung Te Ha<phungte@gmail.com> wrote:
> Hi all,
>
> I tried and gave up on building a xenclient_usb.config, the build broke at
> quite many places. So I use file as disk:
>
> disk = /mnt/3/vista_image.bin:file:hda:w:disk
>
> first started a vista installation from DVD, then continued on, setup the
> network, download the graphics driver from hp.com, and aero showed after
> reboot!!!
>
> Thanks for your help.
>
> Phung-Te
>
> On Mon, Aug 17, 2009 at 12:09 PM, Phung Te Ha <phungte@gmail.com> wrote:
>>
>> Hi all,
>>
>> Thanks to your helps, I could see vista come up from a DVD installation
>> with the graphics controller passed-through. The machine I am using is
>> HP6930p. The config is Ross', just changed the disk from:
>>
>> disk = /dev/sda:phy:hda:w:disk
>>
>> to
>>
>> disk = /dev/sr0:phy:hdd:r:cdrom
>>
>> I also have vista on the disk at /dev/sda1. But since I use the same disk
>> to boot xenclient, when I start the guest, giving /dev/sda as disk, grub
>> wants to boot xenclient again, instead of vista.
>>
>> So now I am building a xenclient_usb config, and leave /dev/sda to vista
>> only.
>>
>> Will update.
>>
>> Phung-Te
>>
>>
>> On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson
>> <Ross.Philipson@citrix.com> wrote:
>>>
>>> Yes, I am passing the graphics through. I am using an HP 6930p at the
>>> moment. I am using Windows Vista as the VM I am passing the graphics through
>>> to and using Windows XP in a second VM that I am using VNC for. I attached
>>> the xenvm config files I happen to be using right now. Note that my Vista
>>> install is not a vhd but rather installed on a partition on disk.
>>>
>>>
>>>
>>> Ross
>>>
>>>
>>>
>>> From: Phung Te Ha [mailto:phungte@gmail.com]
>>> Sent: Friday, August 14, 2009 4:18 PM
>>>
>>> To: Ross Philipson
>>> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>>
>>>
>>> Do you pass the graphics controller through? Which guest are you using?
>>> Do you mind publish your config file?
>>>
>>> Thank you.
>>>
>>> Phung-Te
>>>
>>> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson
>>> <Ross.Philipson@citrix.com> wrote:
>>>
>>> Well we don’t have a official list we can push but we run on the same HP
>>> 6930p you have all the time. We have also had it running on Intel Q35
>>> systems. So in general it should work on these systems.
>>>
>>>
>>>
>>> Thanks
>>>
>>> Ross
>>>
>>>
>>>
>>> From: Phung Te Ha [mailto:phungte@gmail.com]
>>> Sent: Friday, August 14, 2009 11:32 AM
>>> To: Ross Philipson
>>> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>>>
>>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>>
>>>
>>> Hello all,
>>>
>>> The only thing I passed through was the graphics controller.
>>> After starting the guest, the system is still there running, xenops
>>> list_domains shows 2 doms running, but nothing from the guest is showing.
>>>
>>> The board I am using is the Intel DQ35OJ and the graphics controller is
>>> the onboard one. Same operation has also been done on a HP6930p, same
>>> result. Can you publish the list of hardware you guys are using, MB,
>>> graphics board..., the config that most likely to get a graphics controller
>>> passed through.
>>>
>>> Thank you.
>>>
>>> Phung-Te
>>>
>>> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson
>>> <Ross.Philipson@citrix.com> wrote:
>>>
>>> Yeah, these occur when the iommu context for the device in question (in
>>> this case your iGfx card) has been torn down but the card is still active
>>> (still attempting DMA). The code in xen to perform an function level resets
>>> (FLR) on the devices takes care of the vast majority of these but there
>>> still remain one or two that occur even thought the FLR has been done. This
>>> issue was never resolved but these few remaining faults don't seem to cause
>>> a problem. So you are experiencing a hang as the vm starts I take it. Is the
>>> vtd fault trace the last thing you see? Are you passing anything else
>>> through?
>>>
>>> Thanks
>>> Ross
>>>
>>> -----Original Message-----
>>> From: Vincent Hanquez
>>> Sent: Friday, August 14, 2009 7:05 AM
>>> To: Phung Te Ha
>>>
>>> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
>>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>> Phung Te Ha wrote:
>>> > Hi Vincent,
>>> >
>>> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
>>> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>>> >
>>> > On both machines, I got the samething, the guest run as shown by
>>> > xenops list_domains:
>>> >
>>> >  id |  state |    cpu_time |                                 uuid
>>> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>>> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>>> >
>>> > But nothing shows on the screen.
>>> >
>>> > I checked the logs and found in xenops dmesg:
>>> >
>>> > ...
>>> > (XEN) Intel VT-d Snoop Control not supported.
>>> > (XEN) Intel VT-d DMA Passthrough not supported.
>>> > (XEN) Intel VT-d Queued Invalidation not supported.
>>> > (XEN) Intel VT-d Interrupt Remapping not supported.
>>> > (XEN) I/O virtualisation enabled
>>> > (XEN) I/O virtualisation for PV guests disabled
>>> >
>>> >
>>> > And when the guest is started:
>>> >
>>> > ...
>>> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
>>> > ffff828bfff56000
>>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>>> > faddf7
>>> > (XEN)     root_entry = ffff83007e0ce000
>>> > (XEN)     root_entry[0] = 7e066001
>>> > (XEN)     context = ffff83007e066000
>>> > (XEN)     context[10] = 201_7da02001
>>> > (XEN)     l3 = ffff83007da02000
>>> > (XEN)     l3_index = 3e
>>> > (XEN)     l3[3e] = 0
>>> > (XEN)     l3[3e] not present
>>> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg =
>>> > ffff828bfff56000
>>> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
>>> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
>>> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
>>> > REASON 5 iommu->reg = ffff828bfff56000
>>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>>> > faddf7
>>> > (XEN)     root_entry = ffff83007e0ce000
>>> > (XEN)     root_entry[0] = 7e066001
>>> > (XEN)     context = ffff83007e066000
>>> > ...
>>> >
>>> > Do you think these 2 machines have enough of VT-d features to get the
>>> > graphics passed-through?
>>> > Do you have a preferred desktop board, known to work for graphisc
>>> > passed-through?
>>> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
>>> any idea, what this previous errors means ?
>>>
>>> thanks,
>>> --
>>> Vincent
>>>
>>>
>>>
>>>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
>
>

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 7864 bytes --]

That's on the Intel controller.

Phung-Te

On Tue, Aug 18, 2009 at 2:28 PM, Tom Rotenberg <tom.rotenberg@gmail.com>wrote:

> Did the Aero worked for you on the nVidia/ATI or on the Intel IGD?
>
> On Wed, Aug 19, 2009 at 12:17 AM, Phung Te Ha<phungte@gmail.com> wrote:
> > Hi all,
> >
> > I tried and gave up on building a xenclient_usb.config, the build broke
> at
> > quite many places. So I use file as disk:
> >
> > disk = /mnt/3/vista_image.bin:file:hda:w:disk
> >
> > first started a vista installation from DVD, then continued on, setup the
> > network, download the graphics driver from hp.com, and aero showed after
> > reboot!!!
> >
> > Thanks for your help.
> >
> > Phung-Te
> >
> > On Mon, Aug 17, 2009 at 12:09 PM, Phung Te Ha <phungte@gmail.com> wrote:
> >>
> >> Hi all,
> >>
> >> Thanks to your helps, I could see vista come up from a DVD installation
> >> with the graphics controller passed-through. The machine I am using is
> >> HP6930p. The config is Ross', just changed the disk from:
> >>
> >> disk = /dev/sda:phy:hda:w:disk
> >>
> >> to
> >>
> >> disk = /dev/sr0:phy:hdd:r:cdrom
> >>
> >> I also have vista on the disk at /dev/sda1. But since I use the same
> disk
> >> to boot xenclient, when I start the guest, giving /dev/sda as disk, grub
> >> wants to boot xenclient again, instead of vista.
> >>
> >> So now I am building a xenclient_usb config, and leave /dev/sda to vista
> >> only.
> >>
> >> Will update.
> >>
> >> Phung-Te
> >>
> >>
> >> On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson
> >> <Ross.Philipson@citrix.com> wrote:
> >>>
> >>> Yes, I am passing the graphics through. I am using an HP 6930p at the
> >>> moment. I am using Windows Vista as the VM I am passing the graphics
> through
> >>> to and using Windows XP in a second VM that I am using VNC for. I
> attached
> >>> the xenvm config files I happen to be using right now. Note that my
> Vista
> >>> install is not a vhd but rather installed on a partition on disk.
> >>>
> >>>
> >>>
> >>> Ross
> >>>
> >>>
> >>>
> >>> From: Phung Te Ha [mailto:phungte@gmail.com]
> >>> Sent: Friday, August 14, 2009 4:18 PM
> >>>
> >>> To: Ross Philipson
> >>> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> >>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >>>
> >>>
> >>>
> >>> Do you pass the graphics controller through? Which guest are you using?
> >>> Do you mind publish your config file?
> >>>
> >>> Thank you.
> >>>
> >>> Phung-Te
> >>>
> >>> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson
> >>> <Ross.Philipson@citrix.com> wrote:
> >>>
> >>> Well we don’t have a official list we can push but we run on the same
> HP
> >>> 6930p you have all the time. We have also had it running on Intel Q35
> >>> systems. So in general it should work on these systems.
> >>>
> >>>
> >>>
> >>> Thanks
> >>>
> >>> Ross
> >>>
> >>>
> >>>
> >>> From: Phung Te Ha [mailto:phungte@gmail.com]
> >>> Sent: Friday, August 14, 2009 11:32 AM
> >>> To: Ross Philipson
> >>> Cc: Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
> >>>
> >>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >>>
> >>>
> >>>
> >>> Hello all,
> >>>
> >>> The only thing I passed through was the graphics controller.
> >>> After starting the guest, the system is still there running, xenops
> >>> list_domains shows 2 doms running, but nothing from the guest is
> showing.
> >>>
> >>> The board I am using is the Intel DQ35OJ and the graphics controller is
> >>> the onboard one. Same operation has also been done on a HP6930p, same
> >>> result. Can you publish the list of hardware you guys are using, MB,
> >>> graphics board..., the config that most likely to get a graphics
> controller
> >>> passed through.
> >>>
> >>> Thank you.
> >>>
> >>> Phung-Te
> >>>
> >>> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson
> >>> <Ross.Philipson@citrix.com> wrote:
> >>>
> >>> Yeah, these occur when the iommu context for the device in question (in
> >>> this case your iGfx card) has been torn down but the card is still
> active
> >>> (still attempting DMA). The code in xen to perform an function level
> resets
> >>> (FLR) on the devices takes care of the vast majority of these but there
> >>> still remain one or two that occur even thought the FLR has been done.
> This
> >>> issue was never resolved but these few remaining faults don't seem to
> cause
> >>> a problem. So you are experiencing a hang as the vm starts I take it.
> Is the
> >>> vtd fault trace the last thing you see? Are you passing anything else
> >>> through?
> >>>
> >>> Thanks
> >>> Ross
> >>>
> >>> -----Original Message-----
> >>> From: Vincent Hanquez
> >>> Sent: Friday, August 14, 2009 7:05 AM
> >>> To: Phung Te Ha
> >>>
> >>> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
> >>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
> >>>
> >>> Phung Te Ha wrote:
> >>> > Hi Vincent,
> >>> >
> >>> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the
> config
> >>> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
> >>> >
> >>> > On both machines, I got the samething, the guest run as shown by
> >>> > xenops list_domains:
> >>> >
> >>> >  id |  state |    cpu_time |                                 uuid
> >>> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
> >>> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
> >>> >
> >>> > But nothing shows on the screen.
> >>> >
> >>> > I checked the logs and found in xenops dmesg:
> >>> >
> >>> > ...
> >>> > (XEN) Intel VT-d Snoop Control not supported.
> >>> > (XEN) Intel VT-d DMA Passthrough not supported.
> >>> > (XEN) Intel VT-d Queued Invalidation not supported.
> >>> > (XEN) Intel VT-d Interrupt Remapping not supported.
> >>> > (XEN) I/O virtualisation enabled
> >>> > (XEN) I/O virtualisation for PV guests disabled
> >>> >
> >>> >
> >>> > And when the guest is started:
> >>> >
> >>> > ...
> >>> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
> >>> > ffff828bfff56000
> >>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> >>> > faddf7
> >>> > (XEN)     root_entry = ffff83007e0ce000
> >>> > (XEN)     root_entry[0] = 7e066001
> >>> > (XEN)     context = ffff83007e066000
> >>> > (XEN)     context[10] = 201_7da02001
> >>> > (XEN)     l3 = ffff83007da02000
> >>> > (XEN)     l3_index = 3e
> >>> > (XEN)     l3[3e] = 0
> >>> > (XEN)     l3[3e] not present
> >>> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg =
> >>> > ffff828bfff56000
> >>> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
> >>> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
> >>> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
> >>> > REASON 5 iommu->reg = ffff828bfff56000
> >>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
> >>> > faddf7
> >>> > (XEN)     root_entry = ffff83007e0ce000
> >>> > (XEN)     root_entry[0] = 7e066001
> >>> > (XEN)     context = ffff83007e066000
> >>> > ...
> >>> >
> >>> > Do you think these 2 machines have enough of VT-d features to get the
> >>> > graphics passed-through?
> >>> > Do you have a preferred desktop board, known to work for graphisc
> >>> > passed-through?
> >>> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you
> have
> >>> any idea, what this previous errors means ?
> >>>
> >>> thanks,
> >>> --
> >>> Vincent
> >>>
> >>>
> >>>
> >>>
> >
> >
> > _______________________________________________
> > Xen-devel mailing list
> > Xen-devel@lists.xensource.com
> > http://lists.xensource.com/xen-devel
> >
> >
>

[-- Attachment #1.2: Type: text/html, Size: 11120 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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

Re: XCI: can we get to the demo state?

[Phung Te Ha]

[-- Attachment #1.1: Type: text/plain, Size: 7498 bytes --]

Hello Ross, hello Vincent,

I am looking around the source tree, and trying to see how from the current
xci, the demo could be done.

Do you mind give some pointers how that was done?

Do the 2 guests both have the graphics passthrough to them? But then how to
keep the one in the background happy and how to pop back its context when we
want to bring it back into foreground?

Thank you.

Phung-Te


On Tue, Aug 18, 2009 at 2:17 PM, Phung Te Ha <phungte@gmail.com> wrote:

> Hi all,
>
> I tried and gave up on building a xenclient_usb.config, the build broke at
> quite many places. So I use file as disk:
>
> disk = /mnt/3/vista_image.bin:file:hda:w:disk
>
> first started a vista installation from DVD, then continued on, setup the
> network, download the graphics driver from hp.com, and aero showed after
> reboot!!!
>
> Thanks for your help.
>
> Phung-Te
>
>
> On Mon, Aug 17, 2009 at 12:09 PM, Phung Te Ha <phungte@gmail.com> wrote:
>
>> Hi all,
>>
>> Thanks to your helps, I could see vista come up from a DVD installation
>> with the graphics controller passed-through. The machine I am using is
>> HP6930p. The config is Ross', just changed the disk from:
>>
>> disk = /dev/sda:phy:hda:w:disk
>>
>> to
>>
>> disk = /dev/sr0:phy:hdd:r:cdrom
>>
>> I also have vista on the disk at /dev/sda1. But since I use the same disk
>> to boot xenclient, when I start the guest, giving /dev/sda as disk, grub
>> wants to boot xenclient again, instead of vista.
>>
>> So now I am building a xenclient_usb config, and leave /dev/sda to vista
>> only.
>>
>> Will update.
>>
>> Phung-Te
>>
>>
>>
>> On Fri, Aug 14, 2009 at 2:15 PM, Ross Philipson <
>> Ross.Philipson@citrix.com> wrote:
>>
>>>  Yes, I am passing the graphics through. I am using an HP 6930p at the
>>> moment. I am using Windows Vista as the VM I am passing the graphics through
>>> to and using Windows XP in a second VM that I am using VNC for. I attached
>>> the xenvm config files I happen to be using right now. Note that my Vista
>>> install is not a vhd but rather installed on a partition on disk.
>>>
>>>
>>>
>>> Ross
>>>
>>>
>>>
>>> *From:* Phung Te Ha [mailto:phungte@gmail.com]
>>> *Sent:* Friday, August 14, 2009 4:18 PM
>>>
>>> *To:* Ross Philipson
>>> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>>> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>>
>>>
>>> Do you pass the graphics controller through? Which guest are you using?
>>> Do you mind publish your config file?
>>>
>>> Thank you.
>>>
>>> Phung-Te
>>>
>>> On Fri, Aug 14, 2009 at 11:08 AM, Ross Philipson <
>>> Ross.Philipson@citrix.com> wrote:
>>>
>>> Well we don’t have a official list we can push but we run on the same HP
>>> 6930p you have all the time. We have also had it running on Intel Q35
>>> systems. So in general it should work on these systems.
>>>
>>>
>>>
>>> Thanks
>>>
>>> Ross
>>>
>>>
>>>
>>> *From:* Phung Te Ha [mailto:phungte@gmail.com]
>>> *Sent:* Friday, August 14, 2009 11:32 AM
>>> *To:* Ross Philipson
>>> *Cc:* Vincent Hanquez; xen-devel@lists.xensource.com; Kamala Narasimhan
>>>
>>>
>>> *Subject:* Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>>
>>>
>>> Hello all,
>>>
>>> The only thing I passed through was the graphics controller.
>>> After starting the guest, the system is still there running, xenops
>>> list_domains shows 2 doms running, but nothing from the guest is showing.
>>>
>>> The board I am using is the Intel DQ35OJ and the graphics controller is
>>> the onboard one. Same operation has also been done on a HP6930p, same
>>> result. Can you publish the list of hardware you guys are using, MB,
>>> graphics board..., the config that most likely to get a graphics controller
>>> passed through.
>>>
>>> Thank you.
>>>
>>> Phung-Te
>>>
>>> On Fri, Aug 14, 2009 at 7:13 AM, Ross Philipson <
>>> Ross.Philipson@citrix.com> wrote:
>>>
>>> Yeah, these occur when the iommu context for the device in question (in
>>> this case your iGfx card) has been torn down but the card is still active
>>> (still attempting DMA). The code in xen to perform an function level resets
>>> (FLR) on the devices takes care of the vast majority of these but there
>>> still remain one or two that occur even thought the FLR has been done. This
>>> issue was never resolved but these few remaining faults don't seem to cause
>>> a problem. So you are experiencing a hang as the vm starts I take it. Is the
>>> vtd fault trace the last thing you see? Are you passing anything else
>>> through?
>>>
>>> Thanks
>>> Ross
>>>
>>>
>>> -----Original Message-----
>>> From: Vincent Hanquez
>>> Sent: Friday, August 14, 2009 7:05 AM
>>> To: Phung Te Ha
>>>
>>> Cc: xen-devel@lists.xensource.com; Ross Philipson; Kamala Narasimhan
>>> Subject: Re: [Xen-devel] XCI: can we get to the demo state?
>>>
>>> Phung Te Ha wrote:
>>> > Hi Vincent,
>>> >
>>> > I tried your suggestion, adding pci = 0,bind,0000:00:02.0 in the config
>>> > on 2 different machines, the HP6930 and on an Intel MB DQ35OJ.
>>> >
>>> > On both machines, I got the samething, the guest run as shown by
>>> > xenops list_domains:
>>> >
>>> >  id |  state |    cpu_time |                                 uuid
>>> >  0 |     R  | 54203470658 | 00000000-0000-0000-0000-000000000000
>>> >  1 |    B H | 12214238864 | 00000000-0000-0000-0000-000000000002
>>> >
>>> > But nothing shows on the screen.
>>> >
>>> > I checked the logs and found in xenops dmesg:
>>> >
>>> > ...
>>> > (XEN) Intel VT-d Snoop Control not supported.
>>> > (XEN) Intel VT-d DMA Passthrough not supported.
>>> > (XEN) Intel VT-d Queued Invalidation not supported.
>>> > (XEN) Intel VT-d Interrupt Remapping not supported.
>>> > (XEN) I/O virtualisation enabled
>>> > (XEN) I/O virtualisation for PV guests disabled
>>> >
>>> >
>>> > And when the guest is started:
>>> >
>>> > ...
>>> >  _fault:DMA Write: 0:2.0 addr faddf7000 REASON 5 iommu->reg =
>>> > ffff828bfff56000
>>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>>> > faddf7
>>> > (XEN)     root_entry = ffff83007e0ce000
>>> > (XEN)     root_entry[0] = 7e066001
>>> > (XEN)     context = ffff83007e066000
>>> > (XEN)     context[10] = 201_7da02001
>>> > (XEN)     l3 = ffff83007da02000
>>> > (XEN)     l3_index = 3e
>>> > (XEN)     l3[3e] = 0
>>> > (XEN)     l3[3e] not present
>>> > (XEN) [VT-D]iommu.c:722: iommu_page_fault: iommu->reg =
>>> ffff828bfff56000
>>> > (XEN) [VT-D]iommu.c:691: iommu_fault_status: Fault Overflow
>>> > (XEN) [VT-D]iommu.c:694: iommu_fault_status: Primary Pending Fault
>>> > (XEN) [VT-D]iommu.c:676: iommu_fault:DMA Write: 0:2.0 addr faddf7000
>>> > REASON 5 iommu->reg = ffff828bfff56000
>>> > (XEN) print_vtd_entries: iommu = ffff83007dcfb320 bdf = 0:2:0 gmfn =
>>> > faddf7
>>> > (XEN)     root_entry = ffff83007e0ce000
>>> > (XEN)     root_entry[0] = 7e066001
>>> > (XEN)     context = ffff83007e066000
>>> > ...
>>> >
>>> > Do you think these 2 machines have enough of VT-d features to get the
>>> > graphics passed-through?
>>> > Do you have a preferred desktop board, known to work for graphisc
>>> > passed-through?
>>> I'm not really familiar with thoses VT-d errors. Kamala/Ross do you have
>>> any idea, what this previous errors means ?
>>>
>>> thanks,
>>> --
>>> Vincent
>>>
>>>
>>>
>>>
>>>
>>
>>
>

[-- Attachment #1.2: Type: text/html, Size: 10716 bytes --]

[-- Attachment #2: Type: text/plain, Size: 138 bytes --]

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