On 02/17/2017 03:28 AM, Jan Beulich wrote:
On 16.02.17 at 18:31, <boris.ostrov...@oracle.com> wrote:
On 02/16/2017 11:59 AM, Jan Beulich wrote:
Also this new model basically limits the opportunity to change the
mode to the case where no guest at all is running, iiuc. Previously
this would have been possible with any number of guests running,
as long as none of them actually used the vPMU.
I don't think much changed. The only difference is that for PV guests we
bump vpmu_count at VCPU creation as opposed to during the hypercall.
And HVM guests always incremented the count during vcpu_initialise().
True, so my earlier statement needs to be limited to PV guests.
Which I think is still OK: as long as we promised a guest (via
CPUID/vpmu_mode at the time of guest creation) that PMU is available we
shouldn't be able to take it away by changing vpmu_mode, whether or not
the guest is actually using it.
-boris
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
