From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chen Yu Subject: Re: [PATCH 1/2][RFC v3] ACPI throttling: Disable the MSR T-state if enabled after resumed Date: Mon, 13 Feb 2017 10:17:55 +0800 Message-ID: <20170213021755.GA22608@yu-desktop-1.sh.intel.com> References: <1fd9d91c7cbdd314ebb6e65264f57f430dfb89ca.1486483294.git.yu.c.chen@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mga05.intel.com ([192.55.52.43]:8892 "EHLO mga05.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751229AbdBMCS0 (ORCPT ); Sun, 12 Feb 2017 21:18:26 -0500 Content-Disposition: inline In-Reply-To: <1fd9d91c7cbdd314ebb6e65264f57f430dfb89ca.1486483294.git.yu.c.chen@intel.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: linux-pm@vger.kernel.org Cc: inux-kernel@vger.kernel.org, Len Brown , "Rafael J. Wysocki" , Pavel Machek , Matthew Garrett , Zhang Rui , Ingo Molnar On Wed, Feb 08, 2017 at 12:23:16AM +0800, Chen Yu wrote: > Previously a bug was reported that on certain Broadwell > platform, after resumed from S3, the CPU is running at > an anomalously low speed, due to the BIOS has enabled the > MSR throttling across S3. The solution to this was to introduce > a quirk framework to save/restore tstate MSR register around > suspend/resume, in Commit 7a9c2dd08ead ("x86/pm: > Introduce quirk framework to save/restore extra MSR > registers around suspend/resume"). > > There are three problems here: > 1. More and more reports show that other platforms also > encountered the same issue, so the quirk list might > be endless. > 2. Each CPUs should take the save/restore operation into > consideration, rather than the nonboot CPU alone. > 3. Normally ACPI T-state re-evaluation is done on resume, > however there is no _TSS on the bogus platform, thus > above re-evaluation code does not run on that machine. > > Solution: > This patch is based on the fact that, we generally should not > expect the system to come back from resume with throttling > enabled, but leverage the OS components to deal with it, > such as thermal event. So we simply clear the MSR T-state > and print the warning if it is found to be enabled after > resumed back. > > Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=90041 > Reported-by: Kadir > Suggested-by: Len Brown > Cc: Len Brown > Cc: "Rafael J. Wysocki" > Cc: Pavel Machek > Cc: Matthew Garrett > Cc: Zhang Rui > Cc: Ingo Molnar > Cc: linux-pm@vger.kernel.org > Signed-off-by: Chen Yu > --- Please ignore this patch for now, need to do more test on this. Thanks, Yu