Messages in this thread | | | Date | Wed, 20 Nov 2013 17:59:21 +0100 | From | Peter Zijlstra <> | Subject | Re: [PATCH 3/7] idle, thermal, acpi: Remove home grown idle implementations |
| |
On Wed, Nov 20, 2013 at 08:40:49AM -0800, Arjan van de Ven wrote: > On 11/20/2013 8:04 AM, Peter Zijlstra wrote: > >This does not fully preseve existing behaviour in that the generic > >idle cycle function calls into the normal cpuidle governed idle > >routines and should thus respect things like QoS parameters and the > >like. > > > NAK on the powerclamp side. > > powerclamp MUST NOT do that.... > it is needed to go to the deepest state no matter what > (this is for when your system is overheating. there is not a lot of choice > here... alternative is an emergency reset that the hardware does for safety)
Then its a worse broken piece of shit than I thought it was.
The only way to do what you want is to pretty much do stop_machine().
There's no guarantee your current FIFO-50 tasks will ever get to run.
Also, since when does Intel hardware do emergency resets on thermal events? It used to force throttle stuff.
| |