On Thu, Mar 05, 2015 at 08:52:49PM +0900, Peter Maydell wrote:

On 5 March 2015 at 20:04, Catalin Marinas [off-list ref] wrote:

quoted

On Thu, Mar 05, 2015 at 11:12:22AM +0100, Paolo Bonzini wrote:

quoted

On 04/03/2015 18:28, Catalin Marinas wrote:

quoted

quoted

quoted

Can you add that property to the device tree for PCI devices too?

Yes but not with mainline yet:

http://thread.gmane.org/gmane.linux.kernel.iommu/8935

We can add the property at the PCI host bridge level (with the drawback
that it covers all the PCI devices), like here:

Even covering all PCI devices is not enough if we want to support device
assignment of PCI host devices.

Can we not have another PCI bridge node in the DT for the host device
assignments?

I'd hate to have to do that. PCI should be entirely probeable
given that we tell the guest where the host bridge is, that's
one of its advantages.

I didn't say a DT node per device, the DT doesn't know what PCI devices
are available (otherwise it defeats the idea of probing). But we need to
tell the OS where the host bridge is via DT.

So the guest would be told about two host bridges: one for real devices
and another for virtual devices. These can have different coherency
properties.

-- 
Catalin