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

[Avi Kivity]

On 11/16/2010 06:56 PM, Avi Kivity wrote:
> On 11/16/2010 06:43 PM, Peter Zijlstra wrote:
> > > 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.
>
> No, some entries inject an interrupt or exception, so the next rip 
> value is unknown (without doing a lot of extra slow calculations).

Also, consider an exit within the stub (if the stub is paged out, for 
example).

--
error compiling committee.c: too many arguments to function

--
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/