On Sep 1, 2008, at 4:22 PM, Avi Kivity wrote:
Alexander Graf wrote:
This is completely implementation specific. So for now this is 100%
AMD only code.
Also I don't really like Intel's design for VMX and while making
nested VMX work might not be _that_ hard, getting it fast would
probably require a lot of work and hacks.
I've thought of introducing a third, hypercall based, virtualization
extension and exposing that. We could then optimize it to the hilts.
The advantages of this are that we can live migrate across vendors,
and of course we have great freedom in the implementation. The
disadvantage is that a lot of thought needs to go into the design in
order to accommodate future changes in both the host and guest.
Not only that, but we'd also only enable running KVM inside the VM for
now. With real vendor specific extensions passed through you could run
a 3rd party hypervisor, which is what I think is the really
interesting use case.
Alex
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
