Messages in this thread | | | Date | Wed, 3 Dec 2008 10:03:04 +0100 | From | Joerg Roedel <> | Subject | Re: [PATCH 0/12] Factor VT-d KVM functions into a generic API (with multiple device assignment support) |
| |
On Tue, Dec 02, 2008 at 11:53:02PM -0800, Greg KH wrote: > On Wed, Dec 03, 2008 at 08:50:49AM +0100, Joerg Roedel wrote: > > On Tue, Dec 02, 2008 at 07:44:05PM -0800, Greg KH wrote: > > > On Tue, Dec 02, 2008 at 02:01:11PM +0100, Joerg Roedel wrote: > > > > Hi, > > > > > > > > this patch series makes the current KVM device passthrough code generic > > > > enough so that other IOMMU implementation can also plug into this code. > > > > It works by factoring the functions Vt-d code exports to KVM into a > > > > generic interface which allows different backends. > > > > > > > > This is the second version of the patchset. The most important change to > > > > the previous version is that this patchset was rebased to the improved > > > > API from Han Weidong which supports multiple devices per IOMMU domain. > > > > > > > > For completeness, this series also includes the patches from Han with > > > > some cleanups. So this patchset can be applied on current avi/master > > > > tree. > > > > > > Have you tried porting any of the current iommu controllers to this new > > > framework to see if it works properly for them? > > > > It works currently for VT-d. I also port it to AMD IOMMU currently. With > > some extensions (offset for start address, flags and size limitation) it > > is also suitable for IOMMUs like GART or similar ones. > > What about the Calgary chipset?
Calgary is quite similar to GART (there is something like the aperture and a linear single-level pagetable). So with the before mentioned extensions it is also suitable for Calgary.
Joerg
| |