[patch 3/4] Rework secondary SMT thread setup at boot

[Nathan Lynch]

On Fri, 2004-07-30 at 16:46, nathanl at austin.ibm.com wrote:
> Our (ab)use of cpu_possible_map in setup_system to start secondary SMT
> threads bothers me.  Mark such threads in cpu_possible_map during
> early boot; let RTAS tell us which present cpus are still offline
> later so we can start them.
>
> I'm not totally sure about this one, it might be better to set up
> cpu_sibling_map in prom_hold_cpus and use that in setup_system.

To clarify this last comment:  is it safe to assume we have the
query-cpu-stopped-state RTAS call (which is used by query_cpu_stopped())
available on all SMT systems?  I suppose if we're relying on the
platform having start-cpu it's ok to assume it has
query-cpu-stopped-state... or not?

Nathan


** Sent via the linuxppc64-dev mail list. See http://lists.linuxppc.org/