Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-13 Thread Jan Kiszka
On 2014-04-11 21:35, Marcelo Tosatti wrote: > On Fri, Apr 11, 2014 at 08:53:09PM +0200, Jan Kiszka wrote: >> On 2014-04-11 20:35, Bandan Das wrote: >>> Jan Kiszka writes: >>> On 2014-04-11 19:26, Bandan Das wrote: > Jan Kiszka writes: > >> On 2014-04-11 02:27, Bandan Das wrote: >

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Bandan Das
Jan Kiszka writes: > On 2014-04-11 20:35, Bandan Das wrote: >> Jan Kiszka writes: >> >>> On 2014-04-11 19:26, Bandan Das wrote: Jan Kiszka writes: > On 2014-04-11 02:27, Bandan Das wrote: >> Marcelo Tosatti writes: >> >>> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Ban

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Marcelo Tosatti
On Fri, Apr 11, 2014 at 08:53:09PM +0200, Jan Kiszka wrote: > On 2014-04-11 20:35, Bandan Das wrote: > > Jan Kiszka writes: > > > >> On 2014-04-11 19:26, Bandan Das wrote: > >>> Jan Kiszka writes: > >>> > On 2014-04-11 02:27, Bandan Das wrote: > > Marcelo Tosatti writes: > > >

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Bandan Das
Marcelo Tosatti writes: > On Fri, Apr 11, 2014 at 08:22:13AM +0200, Jan Kiszka wrote: >> On 2014-04-11 02:27, Bandan Das wrote: >> > Marcelo Tosatti writes: >> > >> >> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: >> >>> For single context invalidation, we fall through to global >

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Marcelo Tosatti
On Fri, Apr 11, 2014 at 08:22:13AM +0200, Jan Kiszka wrote: > On 2014-04-11 02:27, Bandan Das wrote: > > Marcelo Tosatti writes: > > > >> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: > >>> For single context invalidation, we fall through to global > >>> invalidation in handle_invep

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Marcelo Tosatti
On Fri, Apr 11, 2014 at 08:22:13AM +0200, Jan Kiszka wrote: > > But rethinking this again, I agree with you. If there's a hypervisor > > with a single context invept implmentation that does not fallback, > > this will unfortunately not work. Jan, do you agree with this ? > > A hypervisor that doe

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Jan Kiszka
On 2014-04-11 20:35, Bandan Das wrote: > Jan Kiszka writes: > >> On 2014-04-11 19:26, Bandan Das wrote: >>> Jan Kiszka writes: >>> On 2014-04-11 02:27, Bandan Das wrote: > Marcelo Tosatti writes: > >> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: >>> For singl

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Bandan Das
Jan Kiszka writes: > On 2014-04-11 19:26, Bandan Das wrote: >> Jan Kiszka writes: >> >>> On 2014-04-11 02:27, Bandan Das wrote: Marcelo Tosatti writes: > On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: >> For single context invalidation, we fall through to global

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Jan Kiszka
On 2014-04-11 19:26, Bandan Das wrote: > Jan Kiszka writes: > >> On 2014-04-11 02:27, Bandan Das wrote: >>> Marcelo Tosatti writes: >>> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: > For single context invalidation, we fall through to global > invalidation in handle_i

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-11 Thread Bandan Das
Jan Kiszka writes: > On 2014-04-11 02:27, Bandan Das wrote: >> Marcelo Tosatti writes: >> >>> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: For single context invalidation, we fall through to global invalidation in handle_invept() except for one case - when the oper

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-10 Thread Jan Kiszka
On 2014-04-11 02:27, Bandan Das wrote: > Marcelo Tosatti writes: > >> On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: >>> For single context invalidation, we fall through to global >>> invalidation in handle_invept() except for one case - when >>> the operand supplied by L1 is differe

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-10 Thread Bandan Das
Marcelo Tosatti writes: > On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: >> For single context invalidation, we fall through to global >> invalidation in handle_invept() except for one case - when >> the operand supplied by L1 is different from what we have in >> vmcs12. However, typ

Re: [PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-04-10 Thread Marcelo Tosatti
On Mon, Mar 31, 2014 at 05:00:23PM -0400, Bandan Das wrote: > For single context invalidation, we fall through to global > invalidation in handle_invept() except for one case - when > the operand supplied by L1 is different from what we have in > vmcs12. However, typically hypervisors will only cal

[PATCH v2 1/3] KVM: nVMX: Don't advertise single context invalidation for invept

2014-03-31 Thread Bandan Das
For single context invalidation, we fall through to global invalidation in handle_invept() except for one case - when the operand supplied by L1 is different from what we have in vmcs12. However, typically hypervisors will only call invept for the currently loaded eptp, so the condition will never