From patchwork Fri Aug 20 02:40:05 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srinivas Pandruvada X-Patchwork-Id: 501227 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BA9C0C4338F for ; Fri, 20 Aug 2021 02:40:28 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 90AAB610CB for ; Fri, 20 Aug 2021 02:40:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237643AbhHTClE (ORCPT ); Thu, 19 Aug 2021 22:41:04 -0400 Received: from mga11.intel.com ([192.55.52.93]:28085 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237269AbhHTClE (ORCPT ); Thu, 19 Aug 2021 22:41:04 -0400 X-IronPort-AV: E=McAfee;i="6200,9189,10081"; a="213577046" X-IronPort-AV: E=Sophos;i="5.84,336,1620716400"; d="scan'208";a="213577046" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Aug 2021 19:40:27 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.84,336,1620716400"; d="scan'208";a="532781071" Received: from spandruv-desk.jf.intel.com ([10.54.75.21]) by fmsmga002.fm.intel.com with ESMTP; 19 Aug 2021 19:40:27 -0700 From: Srinivas Pandruvada To: rui.zhang@intel.com, daniel.lezcano@linaro.org, rjw@rjwysocki.net, viresh.kumar@linaro.org, lenb@kernel.org Cc: linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, Srinivas Pandruvada Subject: [PATCH 1/2] thermal: intel: Allow processing of HWP interrupt Date: Thu, 19 Aug 2021 19:40:05 -0700 Message-Id: <20210820024006.2347720-1-srinivas.pandruvada@linux.intel.com> X-Mailer: git-send-email 2.31.1 MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org Add a weak function to process HWP (Hardware P-states) notifications and move updating HWP_STATUS MSR to this function. This allows HWP interrupts to be processed by the intel_pstate driver in HWP mode by overriding the implementation. Signed-off-by: Srinivas Pandruvada --- drivers/thermal/intel/therm_throt.c | 7 ++++++- drivers/thermal/intel/thermal_interrupt.h | 3 +++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/intel/therm_throt.c b/drivers/thermal/intel/therm_throt.c index 99abdc03c44c..dab7e8fb1059 100644 --- a/drivers/thermal/intel/therm_throt.c +++ b/drivers/thermal/intel/therm_throt.c @@ -569,13 +569,18 @@ static void notify_thresholds(__u64 msr_val) platform_thermal_notify(msr_val); } +void __weak notify_hwp_interrupt(void) +{ + wrmsrl_safe(MSR_HWP_STATUS, 0); +} + /* Thermal transition interrupt handler */ void intel_thermal_interrupt(void) { __u64 msr_val; if (static_cpu_has(X86_FEATURE_HWP)) - wrmsrl_safe(MSR_HWP_STATUS, 0); + notify_hwp_interrupt(); rdmsrl(MSR_IA32_THERM_STATUS, msr_val); diff --git a/drivers/thermal/intel/thermal_interrupt.h b/drivers/thermal/intel/thermal_interrupt.h index 53f427bb58dc..01e7bed2ffc7 100644 --- a/drivers/thermal/intel/thermal_interrupt.h +++ b/drivers/thermal/intel/thermal_interrupt.h @@ -12,4 +12,7 @@ extern int (*platform_thermal_notify)(__u64 msr_val); * callback has rate control */ extern bool (*platform_thermal_package_rate_control)(void); +/* Handle HWP interrupt */ +extern void notify_hwp_interrupt(void); + #endif /* _INTEL_THERMAL_INTERRUPT_H */ From patchwork Fri Aug 20 02:40:06 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srinivas Pandruvada X-Patchwork-Id: 500755 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5BC70C4320A for ; Fri, 20 Aug 2021 02:40:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 34E986103A for ; Fri, 20 Aug 2021 02:40:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237726AbhHTClE (ORCPT ); Thu, 19 Aug 2021 22:41:04 -0400 Received: from mga11.intel.com ([192.55.52.93]:28085 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237372AbhHTClE (ORCPT ); Thu, 19 Aug 2021 22:41:04 -0400 X-IronPort-AV: E=McAfee;i="6200,9189,10081"; a="213577047" X-IronPort-AV: E=Sophos;i="5.84,336,1620716400"; d="scan'208";a="213577047" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Aug 2021 19:40:27 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.84,336,1620716400"; d="scan'208";a="532781073" Received: from spandruv-desk.jf.intel.com ([10.54.75.21]) by fmsmga002.fm.intel.com with ESMTP; 19 Aug 2021 19:40:27 -0700 From: Srinivas Pandruvada To: rui.zhang@intel.com, daniel.lezcano@linaro.org, rjw@rjwysocki.net, viresh.kumar@linaro.org, lenb@kernel.org Cc: linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, Srinivas Pandruvada Subject: [PATCH 2/2] cpufreq: intel_pstate: Process HWP Guaranteed change notification Date: Thu, 19 Aug 2021 19:40:06 -0700 Message-Id: <20210820024006.2347720-2-srinivas.pandruvada@linux.intel.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210820024006.2347720-1-srinivas.pandruvada@linux.intel.com> References: <20210820024006.2347720-1-srinivas.pandruvada@linux.intel.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org It is possible that HWP guaranteed ratio is changed in response to change in power and thermal limits. For example when Intel Speed Select performance profile is changed or there is change in TDP, hardware can send notifications. It is possible that the guaranteed ratio is increased. This creates an issue when turbo is disabled, as the old limits set in MSR_HWP_REQUEST are still lower and hardware will clip to older limits. This change enables HWP interrupt and process HWP interrupts. When guaranteed is changed, calls cpufreq_update_policy() so that driver callbacks are called to update to new HWP limits. This callback is called from a delayed workqueue of 10ms to avoid frequent updates. Signed-off-by: Srinivas Pandruvada --- drivers/cpufreq/intel_pstate.c | 39 ++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index bb4549959b11..0fd2375c1f1e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -32,6 +32,7 @@ #include #include #include +#include "../drivers/thermal/intel/thermal_interrupt.h" #define INTEL_PSTATE_SAMPLING_INTERVAL (10 * NSEC_PER_MSEC) @@ -219,6 +220,7 @@ struct global_params { * @sched_flags: Store scheduler flags for possible cross CPU update * @hwp_boost_min: Last HWP boosted min performance * @suspended: Whether or not the driver has been suspended. + * @hwp_notify_work: workqueue for HWP notifications. * * This structure stores per CPU instance data for all CPUs. */ @@ -257,6 +259,7 @@ struct cpudata { unsigned int sched_flags; u32 hwp_boost_min; bool suspended; + struct delayed_work hwp_notify_work; }; static struct cpudata **all_cpu_data; @@ -1625,6 +1628,40 @@ static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void) /************************** sysfs end ************************/ +static void intel_pstate_notify_work(struct work_struct *work) +{ + mutex_lock(&intel_pstate_driver_lock); + cpufreq_update_policy(smp_processor_id()); + wrmsrl(MSR_HWP_STATUS, 0); + mutex_unlock(&intel_pstate_driver_lock); +} + +void notify_hwp_interrupt(void) +{ + unsigned int this_cpu = smp_processor_id(); + struct cpudata *cpudata; + u64 value; + + if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) + return; + + rdmsrl(MSR_HWP_STATUS, value); + if (!(value & 0x01)) + return; + + cpudata = all_cpu_data[this_cpu]; + schedule_delayed_work_on(this_cpu, &cpudata->hwp_notify_work, msecs_to_jiffies(10)); +} + +static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) +{ + /* Enable HWP notification interrupt for guaranteed performance change */ + if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { + INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); + wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); + } +} + static void intel_pstate_hwp_enable(struct cpudata *cpudata) { /* First disable HWP notification interrupt as we don't process them */ @@ -1634,6 +1671,8 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); if (cpudata->epp_default == -EINVAL) cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); + + intel_pstate_enable_hwp_interrupt(cpudata); } static int atom_get_min_pstate(void)