On Mon, Jun 11, 2007 at 07:20:59AM +0200, Thomas Gleixner wrote:
> On Mon, 2007-06-11 at 09:26 +0900, Paul Mundt wrote:
> >
> > There are two paths here depending on hlt/nohlt setting, we need to have
> > tick_nohz_stop_sched_tick() for the TIF_POLLING_NRFLAG case, too.
>
> Do you really want to r
On Mon, 2007-06-11 at 09:26 +0900, Paul Mundt wrote:
>
> There are two paths here depending on hlt/nohlt setting, we need to have
> tick_nohz_stop_sched_tick() for the TIF_POLLING_NRFLAG case, too.
Do you really want to run through that in every loop iteration ? If you
have nohlt, then nohz is rat
On Sun, Jun 10, 2007 at 09:43:59AM -, Thomas Gleixner wrote:
> Index: linux-2.6.22-rc4-mm/arch/sh/kernel/process.c
> ===
> --- linux-2.6.22-rc4-mm.orig/arch/sh/kernel/process.c 2007-06-10
> 10:44:38.0 +0200
> +++ linux-2.6
The cpuidle patches moved the tick nohz handling from irq_exit into
the inner idle loop. The change is correct as it covers non interrupt
based wakeups (e.g DMA) as well, but the move was only done for i386
and breaks ARM,SH and SPARC64.
Fix it up.
Signed-off-by: Thomas Gleixner <[EMAIL PROTECTE
4 matches
Mail list logo
