Re: [PATCH 2/2] turn off kvmclock when resetting cpu

[Glauber Costa <glommer@redhat.com>]

On Wed, May 05, 2010 at 06:34:22PM +0300, Avi Kivity wrote:
> On 05/05/2010 06:24 PM, Glauber Costa wrote:
> >On Wed, May 05, 2010 at 10:26:43AM +0300, Avi Kivity wrote:
> >
> >>>+    msr_data.info.nmsrs = n;
> >>>+
> >>>+    return kvm_vcpu_ioctl(env, KVM_SET_MSRS,&msr_data);
> >>>+}
> >>>+
> >>>+
> >>How about a different approach?  Query the supported MSRs
> >>(KVM_GET_MSR_LIST or thereabout) and reset them (with special cases
> >>for the TSC, and the old clock MSRs when the new ones are present)?
> >I didn't went that route because I was unsure that every one of them
> >would be resetable by writing 0 on it.
> 
> There are probably others.  We should reset them correctly anyway.
> 
> It's probably done by generic qemu code so it works.
> 
> >And if we are going to special case the most part of it, then there
> >is no point in doing it.
> >
> >If you think it is doable to special case just the tsc, then I am fine.
> 
> I think if we have the following sequence
> 
>   clear all msrs
>   qemu reset
>   kvm specific msr reset
> 
> Then we'd be fine.
> 
> Oh, and tsc needs to be reset to 0 as well - it isn't a special case.
This means a guest running on a perfectly synchronized tsc host
will not see a sync tsc. Simply because we can't possible
reset all tscs at the same time.