Re: Worst case performance of up()
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: 2006-12-08 04:11:20
On Fri, 2006-12-08 at 13:33 +1100, Paul Mackerras wrote:
Benjamin Herrenschmidt writes:quoted
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.