Has anyone successfully passed through the Intel HDA device (1f:3) to a guest without exposing it to the LOM NIC (1f:6) that they carelessly left in the same IOMMU group?
Hacking the pcie_acs_override patch to ignore the test for non-PCIe devices seems create separate iommu groups for the Intel HDA Audio device and the Intel NIC, although at what cost to stability and security?