From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH 3/7] idle, thermal, acpi: Remove home grown idle implementations Date: Wed, 20 Nov 2013 17:59:21 +0100 Message-ID: <20131120165921.GT16796@laptop.programming.kicks-ass.net> References: <20131120160450.072555619@infradead.org> <20131120162736.508462614@infradead.org> <528CE611.8040903@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from merlin.infradead.org ([205.233.59.134]:47419 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753953Ab3KTQ7e (ORCPT ); Wed, 20 Nov 2013 11:59:34 -0500 Content-Disposition: inline In-Reply-To: <528CE611.8040903@linux.intel.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Arjan van de Ven Cc: lenb@kernel.org, rjw@rjwysocki.net, Eliezer Tamir , Chris Leech , David Miller , rui.zhang@intel.com, jacob.jun.pan@linux.intel.com, Mike Galbraith , Ingo Molnar , hpa@zytor.com, Thomas Gleixner , linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, "Rafael J. Wysocki" 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.