lkml.org 
[lkml]   [2008]   [Mar]   [14]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
/
FromLen Brown <>
SubjectRe: [linux-pm] [PATCH] cpuidle: avoid singing capacitors
DateFri, 14 Mar 2008 00:13:58 -0400
On Thursday 13 March 2008, Andi Kleen wrote:
> On Thu, Mar 13, 2008 at 09:10:48AM +0100, Pavel Machek wrote:
> > Hi!
> > 
> > > > > USB keeps processor out of C3 in many cases.
> > > > 
> > > > I figured that was the case. But I did not see any difference in powertop.
> > > 
> > > Modern Intel mobile processors have a feature called "C2 popup"
> > > that allows the processor to retire DMA from C3 without
> > > breaking into C0.  Instead the processor pops up to C2
> > > where the cache snoop can allow the DMA to retire --
> > > then it returns to C3, all transparent to software.
> > 
> > Does that mean we should go to C3 on modern intels, even with
> > busmaster going on, so that cpu can keep going C2..C3..C2 as needed?

That decision has already been made for us.
BM_STS has been made a no-op on recent processors.
It reports bus activity only for a small sub-set of
south-bridge devices.  Otherwise it tells us there
is none and that we should proceed into C3.

> C3 is still more expensive power wise to enter, so entering C3 just
> to let it immediately go back to C2 for bus mastering would be likely
> still a loss over staying at C2.

The newer the processor, the less exposed we area to this scenario.

cheers,
-Len


\
 
 \ /
  Last update: 2008-03-14 05:17    [from the cache]
©2003-2008