Re: RFC: PCI devices passthrough on Arm design proposal

[Oleksandr <olekstysh@gmail.com>]

On 18.07.20 14:24, Julien Grall wrote:

Hello Julien

>
>
> On 17/07/2020 20:17, Oleksandr wrote:
>> I would like to clarify regarding an IOMMU driver changes which 
>> should be done to support PCI pass-through properly.
>>
>> Design document mentions about SMMU, but Xen also supports IPMMU-VMSA 
>> (under tech preview now). It would be really nice if the required 
>> support is extended to that kind of IOMMU as well.
>>
>> May I clarify what should be implemented in the Xen driver in order 
>> to support PCI pass-through feature on Arm? 
>
> I would expect callbacks to:
>     - add a PCI device
>     - remove a PCI device
>     - assign a PCI device
>     - deassign a PCI device
>
> AFAICT, they are already existing. So it is a matter of plumbing. This 
> would then be up to the driver to configure the IOMMU correctly.


Got it.

>
>> Should the IOMMU H/W be "PCI-aware" for that purpose?
>
> The only requirement is that your PCI devices are behind an IOMMU :). 
> Other than that the IOMMU can mostly be configured the same way as you 
> would do for the non-PCI devices. 

That's good.


> The main difference would be how you find the master ID.
>
> I am aware that on some platforms, the masterID may be shared between 
> multiple PCI devices. In that case, we would need to have a way to 
> assign all the devices to the same guest (maybe using group?).

Or just prevent these devices from being assigned to different guests? 
During assigning a device to newly created guest check whether masterID 
is already in use for any existing guests and deny operation in such a 
case.


-- 
Regards,

Oleksandr Tyshchenko