XenGT GPU virtualization

XenGT GPU virtualization

[bharat gohil]

[-- Attachment #1.1: Type: text/plain, Size: 457 bytes --]

Hello

I am new to GPU and GPU virtualization and found that xen support intel GPU
virtualization using XenGT.
I want to know,
1) What are the critical GPU command pass from xen to Dom0?
2) How the Dom0 mediator or xen validate the GPU command which is passed
from domU GPU driver?
3) If one of the domU guest send bad(malicious) command to GPU which led
GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?

-- 
Regards,
Bharat Gohil

[-- Attachment #1.2: Type: text/html, Size: 725 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Konrad Rzeszutek Wilk]

On Wed, Jan 18, 2017 at 06:51:02PM +0530, bharat gohil wrote:
> Hello

Hey!

CC-ing one of the XenGT folks who I hope can help you.
> 
> I am new to GPU and GPU virtualization and found that xen support intel GPU
> virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is passed
> from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which led
> GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
> 
> -- 
> Regards,
> Bharat Gohil

> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[anshul makkar]

[-- Attachment #1.1: Type: text/plain, Size: 805 bytes --]



On 18/01/17 13:21, bharat gohil wrote:
> Hello
>
> I am new to GPU and GPU virtualization and found that xen support 
> intel GPU virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is 
> passed from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which 
> led GPU to bad state. Can Dom0 mediator or xen prevents this kind of 
> scenario?
As far as I know, there is know mediation to check for the commands. Xen 
does audit the target address space, but not GPU commands.
>
> -- 
> Regards,
> Bharat Gohil
>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


[-- Attachment #1.2: Type: text/html, Size: 2214 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Paul Durrant]

[-- Attachment #1.1: Type: text/plain, Size: 1195 bytes --]

No, that’s not correct. The GPU commands are whitelisted and only the commands that can be audited are handled.

  Paul

From: Xen-devel [mailto:xen-devel-bounces@lists.xen.org] On Behalf Of anshul makkar
Sent: 20 February 2017 15:16
To: bharat gohil <ghl.bhrt@gmail.com>; xen-devel@lists.xenproject.org
Subject: Re: [Xen-devel] XenGT GPU virtualization




On 18/01/17 13:21, bharat gohil wrote:
Hello

I am new to GPU and GPU virtualization and found that xen support intel GPU virtualization using XenGT.
I want to know,
1) What are the critical GPU command pass from xen to Dom0?
2) How the Dom0 mediator or xen validate the GPU command which is passed from domU GPU driver?
3) If one of the domU guest send bad(malicious) command to GPU which led GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
As far as I know, there is know mediation to check for the commands. Xen does audit the target address space, but not GPU commands.


--
Regards,
Bharat Gohil





_______________________________________________

Xen-devel mailing list

Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>

https://lists.xen.org/xen-devel


[-- Attachment #1.2: Type: text/html, Size: 45846 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[bharat gohil]

[-- Attachment #1.1: Type: text/plain, Size: 1608 bytes --]

Thanks paul and anshul

Can you guys point out source code which is audit the GPU command?

Thanks
Bharat

On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant <Paul.Durrant@citrix.com>
wrote:

> No, that’s not correct. The GPU commands are whitelisted and only the
> commands that can be audited are handled.
>
>
>
>   Paul
>
>
>
> *From:* Xen-devel [mailto:xen-devel-bounces@lists.xen.org] *On Behalf Of *anshul
> makkar
> *Sent:* 20 February 2017 15:16
> *To:* bharat gohil <ghl.bhrt@gmail.com>; xen-devel@lists.xenproject.org
> *Subject:* Re: [Xen-devel] XenGT GPU virtualization
>
>
>
>
>
>
>
> On 18/01/17 13:21, bharat gohil wrote:
>
> Hello
>
>
>
> I am new to GPU and GPU virtualization and found that xen support intel
> GPU virtualization using XenGT.
>
> I want to know,
>
> 1) What are the critical GPU command pass from xen to Dom0?
>
> 2) How the Dom0 mediator or xen validate the GPU command which is passed
> from domU GPU driver?
>
> 3) If one of the domU guest send bad(malicious) command to GPU which led
> GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
>
> As far as I know, there is know mediation to check for the commands. Xen
> does audit the target address space, but not GPU commands.
>
>
>
> --
>
> Regards,
>
> Bharat Gohil
>
>
>
>
>
>
> _______________________________________________
>
> Xen-devel mailing list
>
> Xen-devel@lists.xen.org
>
> https://lists.xen.org/xen-devel
>
>
>



-- 
Regards,
Bharat Gohil
Sr.Software Engineer
bharat.gohil@harman.com
+919427054633

[-- Attachment #1.2: Type: text/html, Size: 7614 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Paul Durrant]

[-- Attachment #1.1: Type: text/plain, Size: 2252 bytes --]

Hi,

  I’m not actually sure where the latest public release of the xengt code is. Perhaps someone from Intel can comment?

  Otherwise, if you grab the source ISOs from xenserver.org you can look in the SRPM for xengt. The xengt kernel module is responsible for auditing the servicing the GPU commands from guests.

  Cheers,

  Paul


From: bharat gohil [mailto:ghl.bhrt@gmail.com]
Sent: 23 February 2017 12:30
To: Paul Durrant <Paul.Durrant@citrix.com>
Cc: Anshul Makkar <anshul.makkar@citrix.com>; xen-devel@lists.xenproject.org
Subject: Re: [Xen-devel] XenGT GPU virtualization

Thanks paul and anshul
Can you guys point out source code which is audit the GPU command?

Thanks
Bharat

On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant <Paul.Durrant@citrix.com<mailto:Paul.Durrant@citrix.com>> wrote:
No, that’s not correct. The GPU commands are whitelisted and only the commands that can be audited are handled.

  Paul

From: Xen-devel [mailto:xen-devel-bounces@lists.xen.org<mailto:xen-devel-bounces@lists.xen.org>] On Behalf Of anshul makkar
Sent: 20 February 2017 15:16
To: bharat gohil <ghl.bhrt@gmail.com<mailto:ghl.bhrt@gmail.com>>; xen-devel@lists.xenproject.org<mailto:xen-devel@lists.xenproject.org>
Subject: Re: [Xen-devel] XenGT GPU virtualization




On 18/01/17 13:21, bharat gohil wrote:
Hello

I am new to GPU and GPU virtualization and found that xen support intel GPU virtualization using XenGT.
I want to know,
1) What are the critical GPU command pass from xen to Dom0?
2) How the Dom0 mediator or xen validate the GPU command which is passed from domU GPU driver?
3) If one of the domU guest send bad(malicious) command to GPU which led GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
As far as I know, there is know mediation to check for the commands. Xen does audit the target address space, but not GPU commands.

--
Regards,
Bharat Gohil




_______________________________________________

Xen-devel mailing list

Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>

https://lists.xen.org/xen-devel




--
Regards,
Bharat Gohil
Sr.Software Engineer
bharat.gohil@harman.com<mailto:bharat.gohil@harman.com>
+919427054633

[-- Attachment #1.2: Type: text/html, Size: 53791 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Haozhong Zhang]

Cc'ed to the mailing list of Intel graphic virtualization

On 01/18/17 18:51 +0530, bharat gohil wrote:
> Hello
> 
> I am new to GPU and GPU virtualization and found that xen support intel GPU
> virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is passed
> from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which led
> GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
> 
> -- 
> Regards,
> Bharat Gohil

> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Haozhong Zhang]

Cc'ed to the mailing list of Intel graphic virtualization

On 02/23/17 12:36 +0000, Paul Durrant wrote:
> Hi,
> 
>   I’m not actually sure where the latest public release of the xengt code is. Perhaps someone from Intel can comment?
> 
>   Otherwise, if you grab the source ISOs from xenserver.org you can look in the SRPM for xengt. The xengt kernel module is responsible for auditing the servicing the GPU commands from guests.
> 
>   Cheers,
> 
>   Paul
> 
> 
> From: bharat gohil [mailto:ghl.bhrt@gmail.com]
> Sent: 23 February 2017 12:30
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Anshul Makkar <anshul.makkar@citrix.com>; xen-devel@lists.xenproject.org
> Subject: Re: [Xen-devel] XenGT GPU virtualization
> 
> Thanks paul and anshul
> Can you guys point out source code which is audit the GPU command?
> 
> Thanks
> Bharat
> 
> On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant <Paul.Durrant@citrix.com<mailto:Paul.Durrant@citrix.com>> wrote:
> No, that’s not correct. The GPU commands are whitelisted and only the commands that can be audited are handled.
> 
>   Paul
> 
> From: Xen-devel [mailto:xen-devel-bounces@lists.xen.org<mailto:xen-devel-bounces@lists.xen.org>] On Behalf Of anshul makkar
> Sent: 20 February 2017 15:16
> To: bharat gohil <ghl.bhrt@gmail.com<mailto:ghl.bhrt@gmail.com>>; xen-devel@lists.xenproject.org<mailto:xen-devel@lists.xenproject.org>
> Subject: Re: [Xen-devel] XenGT GPU virtualization
> 
> 
> 
> 
> On 18/01/17 13:21, bharat gohil wrote:
> Hello
> 
> I am new to GPU and GPU virtualization and found that xen support intel GPU virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is passed from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which led GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
> As far as I know, there is know mediation to check for the commands. Xen does audit the target address space, but not GPU commands.
> 
> --
> Regards,
> Bharat Gohil
> 
> 
> 
> 
> _______________________________________________
> 
> Xen-devel mailing list
> 
> Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>
> 
> https://lists.xen.org/xen-devel
> 
> 
> 
> 
> --
> Regards,
> Bharat Gohil
> Sr.Software Engineer
> bharat.gohil@harman.com<mailto:bharat.gohil@harman.com>
> +919427054633

> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Haozhong Zhang]

Cc'ed to the mailing list of Intel graphic virtualization                                        
                                                                                       
[Sorry for the spam. The last cc failed as I didn't subscribe to igvt-g@lists.01.org] 

On 01/18/17 18:51 +0530, bharat gohil wrote:
> Hello
> 
> I am new to GPU and GPU virtualization and found that xen support intel GPU
> virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is passed
> from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which led
> GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
> 
> -- 
> Regards,
> Bharat Gohil

> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: XenGT GPU virtualization

[Haozhong Zhang]

Cc'ed to the mailing list of Intel graphic virtualization

[Sorry for the spam. The last cc failed as I didn't subscribe to igvt-g@lists.01.org]  

On 02/23/17 12:36 +0000, Paul Durrant wrote:
> Hi,
> 
>   I’m not actually sure where the latest public release of the xengt code is. Perhaps someone from Intel can comment?
> 
>   Otherwise, if you grab the source ISOs from xenserver.org you can look in the SRPM for xengt. The xengt kernel module is responsible for auditing the servicing the GPU commands from guests.
> 
>   Cheers,
> 
>   Paul
> 
> 
> From: bharat gohil [mailto:ghl.bhrt@gmail.com]
> Sent: 23 February 2017 12:30
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Anshul Makkar <anshul.makkar@citrix.com>; xen-devel@lists.xenproject.org
> Subject: Re: [Xen-devel] XenGT GPU virtualization
> 
> Thanks paul and anshul
> Can you guys point out source code which is audit the GPU command?
> 
> Thanks
> Bharat
> 
> On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant <Paul.Durrant@citrix.com<mailto:Paul.Durrant@citrix.com>> wrote:
> No, that’s not correct. The GPU commands are whitelisted and only the commands that can be audited are handled.
> 
>   Paul
> 
> From: Xen-devel [mailto:xen-devel-bounces@lists.xen.org<mailto:xen-devel-bounces@lists.xen.org>] On Behalf Of anshul makkar
> Sent: 20 February 2017 15:16
> To: bharat gohil <ghl.bhrt@gmail.com<mailto:ghl.bhrt@gmail.com>>; xen-devel@lists.xenproject.org<mailto:xen-devel@lists.xenproject.org>
> Subject: Re: [Xen-devel] XenGT GPU virtualization
> 
> 
> 
> 
> On 18/01/17 13:21, bharat gohil wrote:
> Hello
> 
> I am new to GPU and GPU virtualization and found that xen support intel GPU virtualization using XenGT.
> I want to know,
> 1) What are the critical GPU command pass from xen to Dom0?
> 2) How the Dom0 mediator or xen validate the GPU command which is passed from domU GPU driver?
> 3) If one of the domU guest send bad(malicious) command to GPU which led GPU to bad state. Can Dom0 mediator or xen prevents this kind of scenario?
> As far as I know, there is know mediation to check for the commands. Xen does audit the target address space, but not GPU commands.
> 
> --
> Regards,
> Bharat Gohil
> 
> 
> 
> 
> _______________________________________________
> 
> Xen-devel mailing list
> 
> Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>
> 
> https://lists.xen.org/xen-devel
> 
> 
> 
> 
> --
> Regards,
> Bharat Gohil
> Sr.Software Engineer
> bharat.gohil@harman.com<mailto:bharat.gohil@harman.com>
> +919427054633

> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [iGVT-g] XenGT GPU virtualization

[Wang, Hongbo]

Intel XenGT has another maillist " igvt-g@lists.01.org" to discuss Intel GPU
virtualization questions, including XenGT and KVMGT. Feel free to subscribe.

Right now, we have two version GVT-g, "old architecture" vs "new
architecture for upstream"
Old architecture:
  - The codes are maintained off-tree, support both XenGT and KVMGT.
  - Our latest code is 2016Q3 version in Oct'16, 2016Q4 version is coming
   soon due to some open bugs.
  - 2016Q3 release blog:
   https://01.org/igvt-g/blogs/wangbo85/2016/intel-gvt-g-iso-public-release-q32016 
  - Repo  Kernel: https://github.com/01org/igvtg-kernel 
         Xen: https://github.com/01org/igvtg-xen 
         QEMU: https://github.com/01org/igvtg-qemu 


New architecture for upstream:
  - KVMGT version with new VFIO interface have been upstreamed into
   kernel 4.10. You can see the code from kernel 4.10, or from our own 
   GVT-g repo which hosts latest code and bug fixing.
  - Repo Kernel:   https://github.com/01org/gvt-linux.git 
        QEMU:  git://git.qemu.org/qemu.git 
  - XenGT code upstream is ongoing, not upstreamed. So you can't see
   those code yet. We already have a workable XenGT version for upstream,
   may share the code after interface polishing.

More details about two versions, please refer to below introduction blog:
https://01.org/igvt-g/blogs/wangbo85/2017/gvt-g-upstream-status-update-were-transition-phase 


Best regards.
Hongbo
Tel: +86-21-6116 7445
MP: +86-1364 1793 689
Mail: hongbo.wang@intel.com

> -----Original Message-----
> From: iGVT-g [mailto:igvt-g-bounces@lists.01.org] On Behalf Of Haozhong
> Zhang
> Sent: Friday, February 24, 2017 9:43 AM
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: xen-devel@lists.xenproject.org; 'bharat gohil' <ghl.bhrt@gmail.com>;
> igvt-g@lists.01.org
> Subject: Re: [iGVT-g] [Xen-devel] XenGT GPU virtualization
> 
> Cc'ed to the mailing list of Intel graphic virtualization
> 
> [Sorry for the spam. The last cc failed as I didn't subscribe to
> igvt-g@lists.01.org]
> 
> On 02/23/17 12:36 +0000, Paul Durrant wrote:
> > Hi,
> >
> >   I’m not actually sure where the latest public release of the xengt code
> is. Perhaps someone from Intel can comment?
> >
> >   Otherwise, if you grab the source ISOs from xenserver.org you can look
> in the SRPM for xengt. The xengt kernel module is responsible for auditing
> the servicing the GPU commands from guests.
> >
> >   Cheers,
> >
> >   Paul
> >
> >
> > From: bharat gohil [mailto:ghl.bhrt@gmail.com]
> > Sent: 23 February 2017 12:30
> > To: Paul Durrant <Paul.Durrant@citrix.com>
> > Cc: Anshul Makkar <anshul.makkar@citrix.com>;
> xen-devel@lists.xenproject.org
> > Subject: Re: [Xen-devel] XenGT GPU virtualization
> >
> > Thanks paul and anshul
> > Can you guys point out source code which is audit the GPU command?
> >
> > Thanks
> > Bharat
> >
> > On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant
> <Paul.Durrant@citrix.com<mailto:Paul.Durrant@citrix.com>> wrote:
> > No, that’s not correct. The GPU commands are whitelisted and only the
> commands that can be audited are handled.
> >
> >   Paul
> >
> > From: Xen-devel
> [mailto:xen-devel-bounces@lists.xen.org<mailto:xen-devel-bounces@lists.x
> en.org>] On Behalf Of anshul makkar
> > Sent: 20 February 2017 15:16
> > To: bharat gohil <ghl.bhrt@gmail.com<mailto:ghl.bhrt@gmail.com>>;
> xen-devel@lists.xenproject.org<mailto:xen-devel@lists.xenproject.org>
> > Subject: Re: [Xen-devel] XenGT GPU virtualization
> >
> >
> >
> >
> > On 18/01/17 13:21, bharat gohil wrote:
> > Hello
> >
> > I am new to GPU and GPU virtualization and found that xen support intel
> GPU virtualization using XenGT.
> > I want to know,
> > 1) What are the critical GPU command pass from xen to Dom0?
> > 2) How the Dom0 mediator or xen validate the GPU command which is
> passed from domU GPU driver?
> > 3) If one of the domU guest send bad(malicious) command to GPU which
> led GPU to bad state. Can Dom0 mediator or xen prevents this kind of
> scenario?
> > As far as I know, there is know mediation to check for the commands. Xen
> does audit the target address space, but not GPU commands.
> >
> > --
> > Regards,
> > Bharat Gohil
> >
> >
> >
> >
> > _______________________________________________
> >
> > Xen-devel mailing list
> >
> > Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>
> >
> > https://lists.xen.org/xen-devel
> >
> >
> >
> >
> > --
> > Regards,
> > Bharat Gohil
> > Sr.Software Engineer
> > bharat.gohil@harman.com<mailto:bharat.gohil@harman.com>
> > +919427054633
> 
> > _______________________________________________
> > Xen-devel mailing list
> > Xen-devel@lists.xen.org
> > https://lists.xen.org/xen-devel
> 
> _______________________________________________
> iGVT-g mailing list
> iGVT-g@lists.01.org
> https://lists.01.org/mailman/listinfo/igvt-g
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [iGVT-g] XenGT GPU virtualization

[bharat gohil]

[-- Attachment #1.1: Type: text/plain, Size: 5517 bytes --]

Thanks Wang

I will keep eye on XenGT release for those code.

Regards,
Bharat

On Fri, Feb 24, 2017 at 7:55 AM, Wang, Hongbo <hongbo.wang@intel.com> wrote:

> Intel XenGT has another maillist " igvt-g@lists.01.org" to discuss Intel
> GPU
> virtualization questions, including XenGT and KVMGT. Feel free to
> subscribe.
>
> Right now, we have two version GVT-g, "old architecture" vs "new
> architecture for upstream"
> Old architecture:
>   - The codes are maintained off-tree, support both XenGT and KVMGT.
>   - Our latest code is 2016Q3 version in Oct'16, 2016Q4 version is coming
>    soon due to some open bugs.
>   - 2016Q3 release blog:
>    https://01.org/igvt-g/blogs/wangbo85/2016/intel-gvt-g-iso-
> public-release-q32016
>   - Repo  Kernel: https://github.com/01org/igvtg-kernel
>          Xen: https://github.com/01org/igvtg-xen
>          QEMU: https://github.com/01org/igvtg-qemu
>
>
> New architecture for upstream:
>   - KVMGT version with new VFIO interface have been upstreamed into
>    kernel 4.10. You can see the code from kernel 4.10, or from our own
>    GVT-g repo which hosts latest code and bug fixing.
>   - Repo Kernel:   https://github.com/01org/gvt-linux.git
>         QEMU:  git://git.qemu.org/qemu.git
>   - XenGT code upstream is ongoing, not upstreamed. So you can't see
>    those code yet. We already have a workable XenGT version for upstream,
>    may share the code after interface polishing.
>
> More details about two versions, please refer to below introduction blog:
> https://01.org/igvt-g/blogs/wangbo85/2017/gvt-g-upstream-
> status-update-were-transition-phase
>
>
> Best regards.
> Hongbo
> Tel: +86-21-6116 7445
> MP: +86-1364 1793 689
> Mail: hongbo.wang@intel.com
>
> > -----Original Message-----
> > From: iGVT-g [mailto:igvt-g-bounces@lists.01.org] On Behalf Of Haozhong
> > Zhang
> > Sent: Friday, February 24, 2017 9:43 AM
> > To: Paul Durrant <Paul.Durrant@citrix.com>
> > Cc: xen-devel@lists.xenproject.org; 'bharat gohil' <ghl.bhrt@gmail.com>;
> > igvt-g@lists.01.org
> > Subject: Re: [iGVT-g] [Xen-devel] XenGT GPU virtualization
> >
> > Cc'ed to the mailing list of Intel graphic virtualization
> >
> > [Sorry for the spam. The last cc failed as I didn't subscribe to
> > igvt-g@lists.01.org]
> >
> > On 02/23/17 12:36 +0000, Paul Durrant wrote:
> > > Hi,
> > >
> > >   I’m not actually sure where the latest public release of the xengt
> code
> > is. Perhaps someone from Intel can comment?
> > >
> > >   Otherwise, if you grab the source ISOs from xenserver.org you can
> look
> > in the SRPM for xengt. The xengt kernel module is responsible for
> auditing
> > the servicing the GPU commands from guests.
> > >
> > >   Cheers,
> > >
> > >   Paul
> > >
> > >
> > > From: bharat gohil [mailto:ghl.bhrt@gmail.com]
> > > Sent: 23 February 2017 12:30
> > > To: Paul Durrant <Paul.Durrant@citrix.com>
> > > Cc: Anshul Makkar <anshul.makkar@citrix.com>;
> > xen-devel@lists.xenproject.org
> > > Subject: Re: [Xen-devel] XenGT GPU virtualization
> > >
> > > Thanks paul and anshul
> > > Can you guys point out source code which is audit the GPU command?
> > >
> > > Thanks
> > > Bharat
> > >
> > > On Mon, Feb 20, 2017 at 9:01 PM, Paul Durrant
> > <Paul.Durrant@citrix.com<mailto:Paul.Durrant@citrix.com>> wrote:
> > > No, that’s not correct. The GPU commands are whitelisted and only the
> > commands that can be audited are handled.
> > >
> > >   Paul
> > >
> > > From: Xen-devel
> > [mailto:xen-devel-bounces@lists.xen.org<mailto:xen-devel-bounces@lists.x
> > en.org>] On Behalf Of anshul makkar
> > > Sent: 20 February 2017 15:16
> > > To: bharat gohil <ghl.bhrt@gmail.com<mailto:ghl.bhrt@gmail.com>>;
> > xen-devel@lists.xenproject.org<mailto:xen-devel@lists.xenproject.org>
> > > Subject: Re: [Xen-devel] XenGT GPU virtualization
> > >
> > >
> > >
> > >
> > > On 18/01/17 13:21, bharat gohil wrote:
> > > Hello
> > >
> > > I am new to GPU and GPU virtualization and found that xen support intel
> > GPU virtualization using XenGT.
> > > I want to know,
> > > 1) What are the critical GPU command pass from xen to Dom0?
> > > 2) How the Dom0 mediator or xen validate the GPU command which is
> > passed from domU GPU driver?
> > > 3) If one of the domU guest send bad(malicious) command to GPU which
> > led GPU to bad state. Can Dom0 mediator or xen prevents this kind of
> > scenario?
> > > As far as I know, there is know mediation to check for the commands.
> Xen
> > does audit the target address space, but not GPU commands.
> > >
> > > --
> > > Regards,
> > > Bharat Gohil
> > >
> > >
> > >
> > >
> > > _______________________________________________
> > >
> > > Xen-devel mailing list
> > >
> > > Xen-devel@lists.xen.org<mailto:Xen-devel@lists.xen.org>
> > >
> > > https://lists.xen.org/xen-devel
> > >
> > >
> > >
> > >
> > > --
> > > Regards,
> > > Bharat Gohil
> > > Sr.Software Engineer
> > > bharat.gohil@harman.com<mailto:bharat.gohil@harman.com>
> > > +919427054633
> >
> > > _______________________________________________
> > > Xen-devel mailing list
> > > Xen-devel@lists.xen.org
> > > https://lists.xen.org/xen-devel
> >
> > _______________________________________________
> > iGVT-g mailing list
> > iGVT-g@lists.01.org
> > https://lists.01.org/mailman/listinfo/igvt-g
>



-- 
Regards,
Bharat Gohil
Sr.Software Engineer
bharat.gohil@harman.com
+919427054633

[-- Attachment #1.2: Type: text/html, Size: 9700 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [iGVT-g] XenGT GPU virtualization

[Konrad Rzeszutek Wilk]

On Fri, Feb 24, 2017 at 02:25:27AM +0000, Wang, Hongbo wrote:
> Intel XenGT has another maillist " igvt-g@lists.01.org" to discuss Intel GPU
> virtualization questions, including XenGT and KVMGT. Feel free to subscribe.
> 
> Right now, we have two version GVT-g, "old architecture" vs "new
> architecture for upstream"
> Old architecture:
>   - The codes are maintained off-tree, support both XenGT and KVMGT.
>   - Our latest code is 2016Q3 version in Oct'16, 2016Q4 version is coming
>    soon due to some open bugs.
>   - 2016Q3 release blog:
>    https://01.org/igvt-g/blogs/wangbo85/2016/intel-gvt-g-iso-public-release-q32016 
>   - Repo  Kernel: https://github.com/01org/igvtg-kernel 
>          Xen: https://github.com/01org/igvtg-xen 
>          QEMU: https://github.com/01org/igvtg-qemu 
> 
> 
> New architecture for upstream:
>   - KVMGT version with new VFIO interface have been upstreamed into
>    kernel 4.10. You can see the code from kernel 4.10, or from our own 
>    GVT-g repo which hosts latest code and bug fixing.
>   - Repo Kernel:   https://github.com/01org/gvt-linux.git 
>         QEMU:  git://git.qemu.org/qemu.git 
>   - XenGT code upstream is ongoing, not upstreamed. So you can't see
>    those code yet. We already have a workable XenGT version for upstream,
>    may share the code after interface polishing.

Could you expand on that please? I thought the ioreq multiple
servers were the big dependency but it sounds like there is more work?

What is involved here?


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [iGVT-g] XenGT GPU virtualization

[Zhiyuan Lv]

Hi Konrad,

On Tue, Feb 28, 2017 at 10:07:18AM -0500, Konrad Rzeszutek Wilk wrote:
> On Fri, Feb 24, 2017 at 02:25:27AM +0000, Wang, Hongbo wrote:
> > Intel XenGT has another maillist " igvt-g@lists.01.org" to discuss Intel GPU
> > virtualization questions, including XenGT and KVMGT. Feel free to subscribe.
> > 
> > Right now, we have two version GVT-g, "old architecture" vs "new
> > architecture for upstream"
> > Old architecture:
> >   - The codes are maintained off-tree, support both XenGT and KVMGT.
> >   - Our latest code is 2016Q3 version in Oct'16, 2016Q4 version is coming
> >    soon due to some open bugs.
> >   - 2016Q3 release blog:
> >    https://01.org/igvt-g/blogs/wangbo85/2016/intel-gvt-g-iso-public-release-q32016 
> >   - Repo  Kernel: https://github.com/01org/igvtg-kernel 
> >          Xen: https://github.com/01org/igvtg-xen 
> >          QEMU: https://github.com/01org/igvtg-qemu 
> > 
> > 
> > New architecture for upstream:
> >   - KVMGT version with new VFIO interface have been upstreamed into
> >    kernel 4.10. You can see the code from kernel 4.10, or from our own 
> >    GVT-g repo which hosts latest code and bug fixing.
> >   - Repo Kernel:   https://github.com/01org/gvt-linux.git 
> >         QEMU:  git://git.qemu.org/qemu.git 
> >   - XenGT code upstream is ongoing, not upstreamed. So you can't see
> >    those code yet. We already have a workable XenGT version for upstream,
> >    may share the code after interface polishing.
> 
> Could you expand on that please? I thought the ioreq multiple
> servers were the big dependency but it sounds like there is more work?
> 
> What is involved here?

You mean the dom0 kernel changes for XenGT right? Basically we need to add a
hypervisor adapter for Xen to work with GVT-g device model. ioreq server code
will be part of that adapter. What Hongbo said is that internally we have such
code for XenGT working, but still need to address some opens for pushing upstream.

Besides this, XenGT has some Xen hypervisor changes as well mainly related to
IOREQ server.  That part will be pushed upstream first before dom0 kernel
upstream effort. Thanks!

Regards,
-Zhiyuan

> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> https://lists.xen.org/xen-devel

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [iGVT-g] XenGT GPU virtualization

[Konrad Rzeszutek Wilk]

On Wed, Mar 01, 2017 at 10:36:13PM +0800, Zhiyuan Lv wrote:
> Hi Konrad,
> 
> On Tue, Feb 28, 2017 at 10:07:18AM -0500, Konrad Rzeszutek Wilk wrote:
> > On Fri, Feb 24, 2017 at 02:25:27AM +0000, Wang, Hongbo wrote:
> > > Intel XenGT has another maillist " igvt-g@lists.01.org" to discuss Intel GPU
> > > virtualization questions, including XenGT and KVMGT. Feel free to subscribe.
> > > 
> > > Right now, we have two version GVT-g, "old architecture" vs "new
> > > architecture for upstream"
> > > Old architecture:
> > >   - The codes are maintained off-tree, support both XenGT and KVMGT.
> > >   - Our latest code is 2016Q3 version in Oct'16, 2016Q4 version is coming
> > >    soon due to some open bugs.
> > >   - 2016Q3 release blog:
> > >    https://01.org/igvt-g/blogs/wangbo85/2016/intel-gvt-g-iso-public-release-q32016 
> > >   - Repo  Kernel: https://github.com/01org/igvtg-kernel 
> > >          Xen: https://github.com/01org/igvtg-xen 
> > >          QEMU: https://github.com/01org/igvtg-qemu 
> > > 
> > > 
> > > New architecture for upstream:
> > >   - KVMGT version with new VFIO interface have been upstreamed into
> > >    kernel 4.10. You can see the code from kernel 4.10, or from our own 
> > >    GVT-g repo which hosts latest code and bug fixing.
> > >   - Repo Kernel:   https://github.com/01org/gvt-linux.git 
> > >         QEMU:  git://git.qemu.org/qemu.git 
> > >   - XenGT code upstream is ongoing, not upstreamed. So you can't see
> > >    those code yet. We already have a workable XenGT version for upstream,
> > >    may share the code after interface polishing.
> > 
> > Could you expand on that please? I thought the ioreq multiple
> > servers were the big dependency but it sounds like there is more work?
> > 
> > What is involved here?
> 
> You mean the dom0 kernel changes for XenGT right? Basically we need to add a

I meant in general. So that if I use upstream Linux and upstream Xen
this works out of the box.

> hypervisor adapter for Xen to work with GVT-g device model. ioreq server code
> will be part of that adapter. What Hongbo said is that internally we have such
> code for XenGT working, but still need to address some opens for pushing upstream.

'opens for pushing upstream' ?

> 
> Besides this, XenGT has some Xen hypervisor changes as well mainly related to
> IOREQ server.  That part will be pushed upstream first before dom0 kernel
> upstream effort. Thanks!

OK! Any idea when that will happen?

Thanks!

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel