On Fri, Jul 11, 2014 at 08:30:59PM +, Tian, Kevin wrote:
> > From: Konrad Rzeszutek Wilk [mailto:konrad.wilk at oracle.com]
> > Sent: Friday, July 11, 2014 12:42 PM
> >
> > On Fri, Jul 11, 2014 at 08:29:56AM +0200, Daniel Vetter wrote:
> > > On Thu, Jul 10, 2014 at 09:08:24PM +, Tian,
> From: Konrad Rzeszutek Wilk [mailto:konrad.wilk at oracle.com]
> Sent: Friday, July 11, 2014 12:42 PM
>
> On Fri, Jul 11, 2014 at 08:29:56AM +0200, Daniel Vetter wrote:
> > On Thu, Jul 10, 2014 at 09:08:24PM +, Tian, Kevin wrote:
> > > actually I'm curious whether it's still necessary to
On Fri, Jul 11, 2014 at 08:29:56AM +0200, Daniel Vetter wrote:
> On Thu, Jul 10, 2014 at 09:08:24PM +, Tian, Kevin wrote:
> > actually I'm curious whether it's still necessary to __detect__ PCH. Could
> > we assume a 1:1 mapping between GPU and PCH, e.g. BDW already hard
> > code the
On Thu, Jul 10, 2014 at 09:08:24PM +, Tian, Kevin wrote:
> actually I'm curious whether it's still necessary to __detect__ PCH. Could
> we assume a 1:1 mapping between GPU and PCH, e.g. BDW already hard
> code the knowledge:
>
> } else if (IS_BROADWELL(dev)) {
>
> From: Daniel Vetter
> Sent: Monday, July 07, 2014 11:40 AM
>
> On Mon, Jul 07, 2014 at 07:58:30PM +0200, Paolo Bonzini wrote:
> > Il 07/07/2014 19:54, Daniel Vetter ha scritto:
> > >On Mon, Jul 07, 2014 at 04:57:45PM +0200, Paolo Bonzini wrote:
> > >>Il 07/07/2014 16:49, Daniel Vetter ha
On Mon, Jul 07, 2014 at 07:58:30PM +0200, Paolo Bonzini wrote:
> Il 07/07/2014 19:54, Daniel Vetter ha scritto:
> >On Mon, Jul 07, 2014 at 04:57:45PM +0200, Paolo Bonzini wrote:
> >>Il 07/07/2014 16:49, Daniel Vetter ha scritto:
> >>>So the correct fix to forward intel gpus to guests is indeed to
Il 07/07/2014 19:54, Daniel Vetter ha scritto:
> On Mon, Jul 07, 2014 at 04:57:45PM +0200, Paolo Bonzini wrote:
>> Il 07/07/2014 16:49, Daniel Vetter ha scritto:
>>> So the correct fix to forward intel gpus to guests is indeed to somehow
>>> fake the pch pci ids since the driver really needs them.
On Mon, Jul 07, 2014 at 04:57:45PM +0200, Paolo Bonzini wrote:
> Il 07/07/2014 16:49, Daniel Vetter ha scritto:
> >So the correct fix to forward intel gpus to guests is indeed to somehow
> >fake the pch pci ids since the driver really needs them. Gross design, but
> >that's how the hardware works.
Il 07/07/2014 16:49, Daniel Vetter ha scritto:
> So the correct fix to forward intel gpus to guests is indeed to somehow
> fake the pch pci ids since the driver really needs them. Gross design, but
> that's how the hardware works.
A way that could work for virtualization is this: if you find the
On Wed, Jun 25, 2014 at 10:28:21AM +0800, Chen, Tiejun wrote:
> On 2014/6/24 10:59, Zhenyu Wang wrote:
> >On 2014.06.19 17:53:51 +0800, Tiejun Chen wrote:
> >>Originally the reason to probe ISA bridge instead of Dev31:Fun0
> >>is to make graphics device passthrough work easy for VMM, that
> >>only
On Wed, Jun 25, 2014 at 08:48:32AM +0200, Paolo Bonzini wrote:
> It is only slightly better, but the right solution is to fix the driver.
> There is absolutely zero reason why a graphics driver should know about the
> vendor/device ids of the PCH.
There is a very valid reason to know about the
On 2014/7/2 14:21, Michael S. Tsirkin wrote:
> On Thu, Jun 19, 2014 at 05:53:51PM +0800, Tiejun Chen wrote:
>> Originally the reason to probe ISA bridge instead of Dev31:Fun0
>> is to make graphics device passthrough work easy for VMM, that
>> only need to expose ISA bridge to let driver know the
On Thu, Jun 19, 2014 at 05:53:51PM +0800, Tiejun Chen wrote:
> Originally the reason to probe ISA bridge instead of Dev31:Fun0
> is to make graphics device passthrough work easy for VMM, that
> only need to expose ISA bridge to let driver know the real
> hardware underneath. This is a requirement
On 2014/6/30 19:18, Michael S. Tsirkin wrote:
> On Thu, Jun 19, 2014 at 05:53:51PM +0800, Tiejun Chen wrote:
>> Originally the reason to probe ISA bridge instead of Dev31:Fun0
>> is to make graphics device passthrough work easy for VMM, that
>> only need to expose ISA bridge to let driver know the
On Thu, Jun 19, 2014 at 05:53:51PM +0800, Tiejun Chen wrote:
> Originally the reason to probe ISA bridge instead of Dev31:Fun0
> is to make graphics device passthrough work easy for VMM, that
> only need to expose ISA bridge to let driver know the real
> hardware underneath. This is a requirement
Il 30/06/2014 05:13, Chen, Tiejun ha scritto:
> After I discuss internal, we think even we just set the real
> vendor/device ids to this ISA bridge at 00:1f.0, guest firmware should
> still work well with these pair of real vendor/device ids.
>
> So if you think something would conflict or be
On 2014/6/25 15:55, Paolo Bonzini wrote:
> Il 25/06/2014 09:34, Chen, Tiejun ha scritto:
>> On 2014/6/25 14:48, Paolo Bonzini wrote:
>>> Second problem. Your IGD passthrough code currently works with QEMU's
>>> PIIX4-based machine. But what happens if you try to extend it, so that
>>
>> Yes,
On 2014/6/25 14:48, Paolo Bonzini wrote:
> Il 22/06/2014 10:25, Chen, Tiejun ha scritto:
>> In qemu-upstream, as you commented we can't create this as a ISA class
>> type explicitly.
>
> Note I didn't say that QEMU doesn't like having two ISA bridges.
>
> I commented that the firmware will see two
On 2014/6/24 10:59, Zhenyu Wang wrote:
> On 2014.06.19 17:53:51 +0800, Tiejun Chen wrote:
>> Originally the reason to probe ISA bridge instead of Dev31:Fun0
>> is to make graphics device passthrough work easy for VMM, that
>> only need to expose ISA bridge to let driver know the real
>> hardware
Il 25/06/2014 09:34, Chen, Tiejun ha scritto:
> On 2014/6/25 14:48, Paolo Bonzini wrote:
>> Second problem. Your IGD passthrough code currently works with QEMU's
>> PIIX4-based machine. But what happens if you try to extend it, so that
>
> Yes, current xen machine, xenpv, is based on pii4, and
Il 22/06/2014 10:25, Chen, Tiejun ha scritto:
> In qemu-upstream, as you commented we can't create this as a ISA class
> type explicitly.
Note I didn't say that QEMU doesn't like having two ISA bridges.
I commented that the firmware will see two ISA bridges and will try to
initialize both of
On 2014.06.19 17:53:51 +0800, Tiejun Chen wrote:
> Originally the reason to probe ISA bridge instead of Dev31:Fun0
> is to make graphics device passthrough work easy for VMM, that
> only need to expose ISA bridge to let driver know the real
> hardware underneath. This is a requirement from
On 2014/6/20 20:48, Paolo Bonzini wrote:
> Il 19/06/2014 11:53, Tiejun Chen ha scritto:
>> so this mean that isa bridge is still represented with Dev31:Func0
>> like the native OS. Furthermore, currently we're pushing VGA
>> passthrough support into qemu upstream, and with some discussion,
>> we
On 2014/6/20 20:32, Daniel Vetter wrote:
> Well I have no clue about forwarding the intel gpu to virtualized
> hosts and also no idea who could review this really. There's been a
> bit a discussion around the iommu mapping forwarding and similar
No, this doesn't affect IOMMU mapping.
> topics
Just ping, any comments?
Thanks
Tiejun
On 2014/6/19 17:53, Tiejun Chen wrote:
> Originally the reason to probe ISA bridge instead of Dev31:Fun0
> is to make graphics device passthrough work easy for VMM, that
> only need to expose ISA bridge to let driver know the real
> hardware underneath.
Il 19/06/2014 11:53, Tiejun Chen ha scritto:
> so this mean that isa bridge is still represented with Dev31:Func0
> like the native OS. Furthermore, currently we're pushing VGA
> passthrough support into qemu upstream, and with some discussion,
> we wouldn't set the bridge class type and just
Well I have no clue about forwarding the intel gpu to virtualized
hosts and also no idea who could review this really. There's been a
bit a discussion around the iommu mapping forwarding and similar
topics though. So I really wonder how well our driver works in this
use case ...
-Daniel
On Fri,
Originally the reason to probe ISA bridge instead of Dev31:Fun0
is to make graphics device passthrough work easy for VMM, that
only need to expose ISA bridge to let driver know the real
hardware underneath. This is a requirement from virtualization
team. Especially in that virtualized
28 matches
Mail list logo