Re: Use of barriers in pvclock ABI

[Jeremy Fitzhardinge]

Glauber Costa wrote:
> Okay for guest vcpu, but what about physical cpus?
>
> IIRC, the checks are there, and so strict, to account for the
> possiblity of the vcpu to be migrated to another cpu in the middle of
> the
> clock reading.
>   

That's fine.  As part of rescheduling a vcpu on a new pcpu, the clock 
record will be updated with the new cpu's parameters, but that update 
will be complete by the time the vcpu gets rescheduled.  The version 
check and loop still needs to be there, but it will never see an 
inconsistent (partially updated) clock record.

   J
--
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/