On Mon, Apr 26, 2010 at 01:46:26PM -0400, Glauber Costa wrote:
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch userspace to recognize it.
And if we ever add a new cpuid bit in the
On Tue, Apr 27, 2010 at 10:30:48AM -0300, Marcelo Tosatti wrote:
On Mon, Apr 26, 2010 at 01:46:26PM -0400, Glauber Costa wrote:
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch
On Tue, Apr 27, 2010 at 10:30:48AM -0300, Marcelo Tosatti wrote:
On Mon, Apr 26, 2010 at 01:46:26PM -0400, Glauber Costa wrote:
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch
On 04/26/2010 08:46 PM, Glauber Costa wrote:
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch userspace to recognize it.
And if we ever add a new cpuid bit in the future, we have to
On Tue, Apr 27, 2010 at 09:12:47PM +0300, Avi Kivity wrote:
On 04/26/2010 08:46 PM, Glauber Costa wrote:
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch userspace to recognize it.
On 04/27/2010 10:09 PM, Glauber Costa wrote:
Hmm. We already have an API to get cpuid bits:
KVM_GET_SUPPORTED_CPUID2. The nice thing about it is that it will
mean -cpu host will work out of the box.
Ok, from what I understand, KVM_GET_CPUID2 gets a set of features, and tells
userspace
Since we're changing the msrs kvmclock uses, we have to communicate
that to the guest, through cpuid. We can add a new KVM_CAP to the
hypervisor, and then patch userspace to recognize it.
And if we ever add a new cpuid bit in the future, we have to do that again,
which create some complexity and