On 03.07.2013, at 19:44, Scott Wood wrote:
> On 07/03/2013 12:23:16 PM, Alexander Graf wrote:
>> On 03.07.2013, at 19:18, Scott Wood wrote:
>> > On 07/03/2013 07:42:36 AM, Mihai Caraman wrote:
>> >> Increase FPU laziness by calling kvmppc_load_guest_fp() just before
>> >> returning to guest instead of each sched in. Without this improvement
>> >> an interrupt may also claim floting point corrupting guest state.
>> >> Signed-off-by: Mihai Caraman <mihai.caraman@xxxxxxxxxxxxx>
>> >> ---
>> >> arch/powerpc/kvm/booke.c | 1 +
>> >> arch/powerpc/kvm/e500mc.c | 2 --
>> >> 2 files changed, 1 insertions(+), 2 deletions(-)
>> >> diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
>> >> index 113961f..3cae2e3 100644
>> >> --- a/arch/powerpc/kvm/booke.c
>> >> +++ b/arch/powerpc/kvm/booke.c
>> >> @@ -1204,6 +1204,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
>> >> r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
>> >> } else {
>> >> kvmppc_lazy_ee_enable();
>> >> + kvmppc_load_guest_fp(vcpu);
>> >> }
>> >
>> > This should go before the kvmppc_lazy_ee_enable().
>> Why? What difference does that make? We're running with interrupts disabled here, right?
>
> Yes, and we want to minimize the code we run where we have interrupts disabled but the lazy ee state says they're enabled. So kvmppc_lazy_ee_enable() should be the last thing we do before entering asm code.
>
> See http://patchwork.ozlabs.org/patch/249565/
Ah, cool. So we should add a comment saying that this should be the last thing before entering asm code then :). That way we make sure nobody else repeats the same mistake.
Alex
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
