Re: [Qemu-devel] [RFC 3/3] acpi-build: allocate mcfg for multiple host bridges

[Zihan Yang]

2018-05-24 1:33 GMT+08:00 Marcel Apfelbaum <address@hidden>:
>
>> * IOMMUs cannot span domains either, so bringing new domains introduces
>> the need
>>   to add a VT-d DHRD or vIOMMU per PCIe domain
>
>
> Not really, you may have PCI domains not associated to an vIOMMU. As a first
> step,
> you should not deal with it. The IOMMU can't span over multiple domains,
> yes.
>

OK, I'll leave IOMMU part at present.

>> * 64-bit space is crowded and there are no standards within QEMU for
>> placing per
>>   domain 64-bit MMIO and MMCFG ranges
>
>
> Yes, but we do have some layout for the "over 4G" area and we can continue
> building on it.

That sounds good.

>> * NUMA modeling seems to be a stronger motivation than the limitation of
>> 256 but
>>   nubmers, that each NUMA node holds its own PCI(e) sub-hierarchy
>
>
> No, the 256 devices limitation is the biggest issue we are trying to solve.

Great, the initial purpose still holds.

> You are on the right path, this discussion is meant to help you understand
> wider concerns
> and make you aware of different constrains we didn't think about.
>
> Good luck with the next version!

It is indeed very helpful. I'll try to deal with (at least most of) the issues
int v2. Thanks for your valuable reviews!

Zihan