On 04/02/12 14:02, Tony Luck wrote:
x86 halt() causes processor to go to C1 state (which is often not the
deepest). But other than that it seems similar to what you are describing.
OK - then Konrad's suggestion of using "safe_halt()" here rather than
"halt()" would work for ia64.
I originally didn't want to use safe_halt() because the CPU will wake up
on an unmasked HW interrupt unlike halt(). But I guess we are not
supposed to get any such interrupts when we are off-lining a CPU so
safe_halt() should be OK.
Thanks.
-boris
_______________________________________________
linux-pm mailing list
linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/linux-pm
