qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Qemu-devel] Intel IOMMU guest emulation and vfio-pci passthrough


From: Martin Hicks
Subject: [Qemu-devel] Intel IOMMU guest emulation and vfio-pci passthrough
Date: Wed, 18 Nov 2015 13:50:32 -0500


Hi,

I've been looking at PCI passthrough using vfio-pci and hoping that it can use the Intel IOMMU emulation in the guest to pin-pages in an on-demand nature, rather than pinning the entire guest memory as vfio-pci does now.  Unfortunately vfio-pci and the intel iommu virtualization don't seem to play nicely together.

One problem is math overflow in vfio_listener_region_add() where a type=iommu add is requested for size == 1<<64 after the call to vfio_initfn().

If I try to fix this, I'm not sure what the call to vfio_listener_region_add for the entire iommu space (0 -> 1<<64) should actually do.  Should it just skip this region add?

Or maybe the vfio code doesn't handle virtualized real IOMMUs?  The comment in vfio_listener_region_add() makes me wonder:

         *
         * FIXME: For VFIO iommu types which have KVM acceleration to
         * avoid bouncing all map/unmaps through qemu this way, this
         * would be the right place to wire that up (tell the KVM
         * device emulation the VFIO iommu handles to use).
         */

mh

--
Martin Hicks P.Eng.      |         address@hidden
Bork Consulting Inc.     |   +1 (613) 266-2296

reply via email to

[Prev in Thread] Current Thread [Next in Thread]