Re: [RFC][PATCH v2 4/7] taskstats: Add per task steal timeaccounting

[Peter Zijlstra]

On Tue, 2010-11-16 at 18:38 +0200, Avi Kivity wrote:
> On 11/16/2010 05:45 PM, Peter Zijlstra wrote:
> >
> >>> In fact, kvm seems to already have these tracepoints: kvm_exit/kvm_entry
> >>> and it has a separate excplicit hypercall tracepoint as well:
> >>> kvm_hypercall.
> >> But the kvm tracepoints are used when Linux is the hypervisor, no? For our
> >> situation that would be a tracepoint in z/VM - or the equivalent. This is
> >> out of scope of this patch.
> > Ah crud, you might be right.. Avi could a kvm guest generate events on
> > vcpu enter/exit?
> 
> No.  Hypercalls are voluntary and known, but most exits are involuntary 
> and unknown to the guest.  Any memory access can generate a page fault, 
> and any host interrupt will exit the guest.

Right, but we could not make the guest jump to a special stub on vcpu
enter? I guess we could simply because we have the hypervisor under
control.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/