Worst case performance of up()

[Benjamin Herrenschmidt]

On Fri, 2006-12-08 at 13:33 +1100, Paul Mackerras wrote:
> Benjamin Herrenschmidt writes:
> 
> > Paul, do you reckon the best solution here is to clear ppc_md.power_save
> > when detecting an SMP powermac ? (Or the flush-on-lock property)
> 
> Yes, that sounds good.  It would let us get rid of the runtime cpu
> feature check in idle_6xx.c too.

We would have to do something about users flippin powersave_nap tho...

Ben.