Re: [PATCH] KVM: VMX: blocked-by-sti must not defer NMI injections

2010-05-12 Thread Marcelo Tosatti
On Tue, May 11, 2010 at 03:16:46PM +0200, Jan Kiszka wrote: > As the processor may not consider GUEST_INTR_STATE_STI as a reason for > blocking NMI, it could return immediately with EXIT_REASON_NMI_WINDOW > when we asked for it. But as we consider this state as NMI-blocking, we > can run into an en

Re: [PATCH] KVM: VMX: blocked-by-sti must not defer NMI injections

2010-05-11 Thread Gleb Natapov
On Tue, May 11, 2010 at 03:16:46PM +0200, Jan Kiszka wrote: > As the processor may not consider GUEST_INTR_STATE_STI as a reason for > blocking NMI, it could return immediately with EXIT_REASON_NMI_WINDOW > when we asked for it. But as we consider this state as NMI-blocking, we > can run into an en

[PATCH] KVM: VMX: blocked-by-sti must not defer NMI injections

2010-05-11 Thread Jan Kiszka
As the processor may not consider GUEST_INTR_STATE_STI as a reason for blocking NMI, it could return immediately with EXIT_REASON_NMI_WINDOW when we asked for it. But as we consider this state as NMI-blocking, we can run into an endless loop. Resolve this by allowing NMI injection if just GUEST_IN