2017-11-29 00:58+0100, Jan H. Schönherr: > On 11/27/2017 07:13 PM, Jim Mattson wrote: > > I don't understand the concern regarding CPUID5_ECX_INTERRUPT_BREAK. > > Even if the CPU has this feature, can't the guest bypass it by > > disabling interrupts and invoking MWAIT with bit 0 of ECX clear? > > Note, that there was this series at some point: > > [PATCH 0/4] KVM: x86: kvm_mwait_in_guest() cleanup and fixes > https://www.spinics.net/lists/kvm/msg149238.html > > That throws away most of the function. > No sure, what happened to that. Radim? I forgot about that while waiting whether its discussion would continue. Going to send v2, thanks.
