Summary of LPC guest MSI discussion in Santa Fe

[Joerg Roedel]

On Thu, Nov 10, 2016 at 01:14:42AM +0100, Auger Eric wrote:
> Besides above problematic, I started to prototype the sysfs API. A first
> issue I face is the reserved regions become global to the iommu instead
> of characterizing the iommu_domain, ie. the "reserved_regions" attribute
> file sits below an iommu instance (~
> /sys/class/iommu/dmar0/intel-iommu/reserved_regions ||
> /sys/class/iommu/arm-smmu0/arm-smmu/reserved_regions).
> 
> MSI reserved window can be considered global to the IOMMU. However PCIe
> host bridge P2P regions rather are per iommu-domain.
> 
> Do you confirm the attribute file should contain both global reserved
> regions and all per iommu_domain reserved regions?
> 
> Thoughts?

This information is best attached to the sysfs-representation of
iommu-groups. The file should then contain the superset of all reserved
regions of the devices the group contains. This makes it usable later to
also describe RMRR/Unity-mapped regions on x86 there and make them
assignable to guests as well.


	Joerg