On 16/03/16 13:31, Jan Beulich wrote: > > That said, I now wonder anyway why this is a per-vCPU mask > instead of a per-pCPU one: There's no need for every vCPU in > the system to have its own afaics.
If every vcpu makes a viridian hypercall at the same time, Xen would end up clobbering same mask while trying to serve the hypercalls. ~Andrew _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel