From patchwork Fri Dec 30 14:58:21 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Rafael J. Wysocki" X-Patchwork-Id: 9492223 X-Patchwork-Delegate: rjw@sisk.pl Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 4451E60417 for ; Fri, 30 Dec 2016 15:02:56 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 3201A1FF8F for ; Fri, 30 Dec 2016 15:02:56 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 231B8223B2; Fri, 30 Dec 2016 15:02:56 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 978C31FF8F for ; Fri, 30 Dec 2016 15:02:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754246AbcL3PCy (ORCPT ); Fri, 30 Dec 2016 10:02:54 -0500 Received: from cloudserver094114.home.net.pl ([79.96.170.134]:52910 "EHLO cloudserver094114.home.net.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753902AbcL3PCx (ORCPT ); Fri, 30 Dec 2016 10:02:53 -0500 Received: from adkt146.ipv4.supernova.orange.pl (79.184.253.146) (HELO aspire.rjw.lan) by serwer1319399.home.pl (79.96.170.134) with SMTP (IdeaSmtpServer 0.81.1) id 637cdcaa3e7c55ad; Fri, 30 Dec 2016 16:02:53 +0100 From: "Rafael J. Wysocki" To: Linux PM Cc: Srinivas Pandruvada , LKML Subject: [PATCH 3/3] cpufreq: intel_pstate: Always keep all limits settings in sync Date: Fri, 30 Dec 2016 15:58:21 +0100 Message-ID: <2349114.gCZGRj0iOf@aspire.rjw.lan> User-Agent: KMail/4.14.10 (Linux/4.10.0-rc1+; KDE/4.14.9; x86_64; ; ) In-Reply-To: <5344750.TOCWYON8QY@aspire.rjw.lan> References: <5344750.TOCWYON8QY@aspire.rjw.lan> MIME-Version: 1.0 Sender: linux-pm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Rafael J. Wysocki Make intel_pstate update per-logical-CPU limits when the global settings are changed to ensure that they are always in sync and users will not see confusing values in per-logical-CPU sysfs attributes. This also fixes the problem that setting the "no_turbo" global attribute to 1 in the "passive" mode (ie. when intel_pstate acts as a regular cpufreq driver) when scaling_governor is set to "performance" has no effect. Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-pm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Index: linux-pm/drivers/cpufreq/intel_pstate.c =================================================================== --- linux-pm.orig/drivers/cpufreq/intel_pstate.c +++ linux-pm/drivers/cpufreq/intel_pstate.c @@ -857,13 +857,13 @@ static struct freq_attr *hwp_cpufreq_att NULL, }; -static void intel_pstate_hwp_set(const struct cpumask *cpumask) +static void intel_pstate_hwp_set(struct cpufreq_policy *policy) { int min, hw_min, max, hw_max, cpu, range, adj_range; struct perf_limits *perf_limits = limits; u64 value, cap; - for_each_cpu(cpu, cpumask) { + for_each_cpu(cpu, policy->cpus) { int max_perf_pct, min_perf_pct; struct cpudata *cpu_data = all_cpu_data[cpu]; s16 epp; @@ -949,7 +949,7 @@ skip_epp: static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) { if (hwp_active) - intel_pstate_hwp_set(policy->cpus); + intel_pstate_hwp_set(policy); return 0; } @@ -984,11 +984,12 @@ static int intel_pstate_resume(struct cp return ret; } -static void intel_pstate_hwp_set_online_cpus(void) +static void intel_pstate_update_policies(void) { - get_online_cpus(); - intel_pstate_hwp_set(cpu_online_mask); - put_online_cpus(); + int cpu; + + for_each_possible_cpu(cpu) + cpufreq_update_policy(cpu); } /************************** debugfs begin ************************/ @@ -1109,11 +1110,10 @@ static ssize_t store_no_turbo(struct kob limits->no_turbo = clamp_t(int, input, 0, 1); - if (hwp_active) - intel_pstate_hwp_set_online_cpus(); - mutex_unlock(&intel_pstate_limits_lock); + intel_pstate_update_policies(); + return count; } @@ -1138,11 +1138,10 @@ static ssize_t store_max_perf_pct(struct limits->max_perf_pct); limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); - if (hwp_active) - intel_pstate_hwp_set_online_cpus(); - mutex_unlock(&intel_pstate_limits_lock); + intel_pstate_update_policies(); + return count; } @@ -1167,11 +1166,10 @@ static ssize_t store_min_perf_pct(struct limits->min_perf_pct); limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); - if (hwp_active) - intel_pstate_hwp_set_online_cpus(); - mutex_unlock(&intel_pstate_limits_lock); + intel_pstate_update_policies(); + return count; }