From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751467AbeFEDsH (ORCPT ); Mon, 4 Jun 2018 23:48:07 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:56026 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751342AbeFEDsF (ORCPT ); Mon, 4 Jun 2018 23:48:05 -0400 From: Stewart Smith To: Michael Ellerman , "Gautham R. Shenoy" , "Rafael J. Wysocki" , Daniel Lezcano , Michael Neuling , Vaidyanathan Srinivasan , Shilpasri G Bhat , Akshay Adiga , Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, "Gautham R. Shenoy" Subject: Re: [PATCH] cpuidle:powernv: Make the snooze timeout dynamic. In-Reply-To: <87fu22bxlf.fsf@concordia.ellerman.id.au> References: <1527768909-32637-1-git-send-email-ego@linux.vnet.ibm.com> <87fu22bxlf.fsf@concordia.ellerman.id.au> Date: Tue, 05 Jun 2018 13:47:55 +1000 MIME-Version: 1.0 Content-Type: text/plain X-TM-AS-GCONF: 00 x-cbid: 18060503-0004-0000-0000-0000143F1418 X-IBM-SpamModules-Scores: X-IBM-SpamModules-Versions: BY=3.00009131; HX=3.00000241; KW=3.00000007; PH=3.00000004; SC=3.00000265; SDB=6.01042477; UDB=6.00533813; IPR=6.00821607; MB=3.00021468; MTD=3.00000008; XFM=3.00000015; UTC=2018-06-05 03:48:03 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 18060503-0005-0000-0000-000087914BE3 Message-Id: <87k1rd28t0.fsf@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2018-06-05_01:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 malwarescore=0 suspectscore=1 phishscore=0 bulkscore=0 spamscore=0 clxscore=1011 lowpriorityscore=0 mlxscore=0 impostorscore=0 mlxlogscore=638 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1805220000 definitions=main-1806050045 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Michael Ellerman writes: > "Gautham R. Shenoy" writes: > >> From: "Gautham R. Shenoy" >> >> The commit 78eaa10f027c ("cpuidle: powernv/pseries: Auto-promotion of >> snooze to deeper idle state") introduced a timeout for the snooze idle >> state so that it could be eventually be promoted to a deeper idle >> state. The snooze timeout value is static and set to the target >> residency of the next idle state, which would train the cpuidle >> governor to pick the next idle state eventually. >> >> The unfortunate side-effect of this is that if the next idle state(s) >> is disabled, the CPU will forever remain in snooze, despite the fact >> that the system is completely idle, and other deeper idle states are >> available. > > That sounds like a bug, I'll add? > > Fixes: 78eaa10f027c ("cpuidle: powernv/pseries: Auto-promotion of snooze to deeper idle state") > Cc: stable@vger.kernel.org # v4.2+ Yes, it's a bug - we had a customer bug because we lacked this that meant we had to do firmware changes rather than just tweaking what stop states were used. -- Stewart Smith OPAL Architect, IBM.