[PATCH] NO_IDLE_HZ implementation for PPC64

[Benjamin Herrenschmidt]

> Aren't other exceptions possible when a CPU is in its idle loop? If not,
> then yes we can insert a call to start_hz_timer only in do_IRQ.

Nothign that matters imho.. You can probably get machine checks or
system reset, but I wouldn't even try to replay ticks in those as they
aren't synchronized with the rest (not blocked by MSR:EE). No, you
really only should care about External Interrupts, Decrementer
Interrupts and Performance Monitor interrupts (yah, forgot about those).

> BTW, in the patch that I had sent, I had got the calculation of next_dec
> (in stop_hz_timer) wrong. I had considered that tb_last_stamp is ahead of 
> jiffies, which is not correct. So the modified code should be something like 
> below:

Why not just call the decrementer interrupt ? It should replay
already...

Ben.