On Wed, Jun 01, 2011 at 12:34:43AM +0200, Segher Boessenkool wrote:
> There's a loop of 128 iterations of 3 insns.
>
> I'm not saying it is actually bad, just that that 50 is slightly off ;-)
That would be the TLB invalidation. On POWER7 we only need to do that
if the virtual cpu last ran on a
Sure, but that shouldn't happen with HDEC during the odd 50
instructions that it takes to enter the guest :)
It's more like 500 insns, including some ptesync, so lots of cycles
too.
I don't think its actually that bad.
There's a loop of 128 iterations of 3 insns.
I'm not saying it is actua
On May 27, 2011, at 9:07 PM, Segher Boessenkool wrote:
If HDEC expires when interrupts are off, the HDEC interrupt stays
pending until interrupts get re-enabled. I'm not sure exactly what
the conditions are that cause an HDEC interrupt to get lost, but they
seem to involve at
If HDEC expires when interrupts are off, the HDEC interrupt stays
pending until interrupts get re-enabled. I'm not sure exactly what
the conditions are that cause an HDEC interrupt to get lost, but they
seem to involve at least a partition switch.
On some CPUs, if the top bit of the decrementer
On 27.05.2011, at 22:59, Segher Boessenkool wrote:
I do the check there because I was having problems where, if the HDEC
goes negative before we do the partition switch, we would occasionally
not get the HDEC interrupt at all until the next time HDEC went
negative, ~ 8.4 secon
I do the check there because I was having problems where, if the HDEC
goes negative before we do the partition switch, we would
occasionally
not get the HDEC interrupt at all until the next time HDEC went
negative, ~ 8.4 seconds later.
Yikes - so HDEC is edge and doesn't even keep the interrup
On 27.05.2011, at 12:33, Paul Mackerras wrote:
> On Tue, May 17, 2011 at 12:17:50PM +0200, Alexander Graf wrote:
>>
>> On 16.05.2011, at 07:58, Paul Mackerras wrote:
>>
>>> I do the check there because I was having problems where, if the HDEC
>>> goes negative before we do the partition switch,
On Tue, May 17, 2011 at 12:17:50PM +0200, Alexander Graf wrote:
>
> On 16.05.2011, at 07:58, Paul Mackerras wrote:
>
> > I do the check there because I was having problems where, if the HDEC
> > goes negative before we do the partition switch, we would occasionally
> > not get the HDEC interrupt
On 16.05.2011, at 07:58, Paul Mackerras wrote:
> On Sun, May 15, 2011 at 11:58:12PM +0200, Alexander Graf wrote:
>>
>> On 11.05.2011, at 12:44, Paul Mackerras wrote:
>
>>> +#ifdef CONFIG_KVM_BOOK3S_NONHV
>>
>> I really liked how you called the .c file _pr - why call it NONHV now?
>
> I agree,
On Sun, May 15, 2011 at 11:58:12PM +0200, Alexander Graf wrote:
>
> On 11.05.2011, at 12:44, Paul Mackerras wrote:
> > +#ifdef CONFIG_KVM_BOOK3S_NONHV
>
> I really liked how you called the .c file _pr - why call it NONHV now?
I agree, CONFIG_KVM_BOOK3S_PR would be better, I'll change it.
> > d
On Thu, May 12, 2011 at 12:07:17PM +0300, Avi Kivity wrote:
> On 05/11/2011 01:44 PM, Paul Mackerras wrote:
> >--- a/include/linux/kvm.h
> >+++ b/include/linux/kvm.h
> >@@ -161,6 +161,7 @@ struct kvm_pit_config {
> > #define KVM_EXIT_NMI 16
> > #define KVM_EXIT_INTERNAL_ERROR 17
>
On 05/11/2011 01:44 PM, Paul Mackerras wrote:
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instruction
12 matches
Mail list logo