Merge tag 'pm-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These include a rework of the main suspend-to-idle code flow (related
  to the handling of spurious wakeups), a switch over of several users
  of cpufreq notifiers to QoS-based limits, a new devfreq driver for
  Tegra20, a new cpuidle driver and governor for virtualized guests, an
  extension of the wakeup sources framework to expose wakeup sources as
  device objects in sysfs, and more.

  Specifics:

   - Rework the main suspend-to-idle control flow to avoid repeating
     "noirq" device resume and suspend operations in case of spurious
     wakeups from the ACPI EC and decouple the ACPI EC wakeups support
     from the LPS0 _DSM support (Rafael Wysocki).

   - Extend the wakeup sources framework to expose wakeup sources as
     device objects in sysfs (Tri Vo, Stephen Boyd).

   - Expose system suspend statistics in sysfs (Kalesh Singh).

   - Introduce a new haltpoll cpuidle driver and a new matching governor
     for virtualized guests wanting to do guest-side polling in the idle
     loop (Marcelo Tosatti, Joao Martins, Wanpeng Li, Stephen Rothwell).

   - Fix the menu and teo cpuidle governors to allow the scheduler tick
     to be stopped if PM QoS is used to limit the CPU idle state exit
     latency in some cases (Rafael Wysocki).

   - Increase the resolution of the play_idle() argument to microseconds
     for more fine-grained injection of CPU idle cycles (Daniel
     Lezcano).

   - Switch over some users of cpuidle notifiers to the new QoS-based
     frequency limits and drop the CPUFREQ_ADJUST and CPUFREQ_NOTIFY
     policy notifier events (Viresh Kumar).

   - Add new cpufreq driver based on nvmem for sun50i (Yangtao Li).

   - Add support for MT8183 and MT8516 to the mediatek cpufreq driver
     (Andrew-sh.Cheng, Fabien Parent).

   - Add i.MX8MN support to the imx-cpufreq-dt cpufreq driver (Anson
     Huang).

   - Add qcs404 to cpufreq-dt-platdev blacklist (Jorge Ramirez-Ortiz).

   - Update the qcom cpufreq driver (among other things, to make it
     easier to extend and to use kryo cpufreq for other nvmem-based
     SoCs) and add qcs404 support to it (Niklas Cassel, Douglas
     RAILLARD, Sibi Sankar, Sricharan R).

   - Fix assorted issues and make assorted minor improvements in the
     cpufreq code (Colin Ian King, Douglas RAILLARD, Florian Fainelli,
     Gustavo Silva, Hariprasad Kelam).

   - Add new devfreq driver for NVidia Tegra20 (Dmitry Osipenko, Arnd
     Bergmann).

   - Add new Exynos PPMU events to devfreq events and extend that
     mechanism (Lukasz Luba).

   - Fix and clean up the exynos-bus devfreq driver (Kamil Konieczny).

   - Improve devfreq documentation and governor code, fix spelling typos
     in devfreq (Ezequiel Garcia, Krzysztof Kozlowski, Leonard Crestez,
     MyungJoo Ham, Gaël PORTAY).

   - Add regulators enable and disable to the OPP (operating performance
     points) framework (Kamil Konieczny).

   - Update the OPP framework to support multiple opp-suspend properties
     (Anson Huang).

   - Fix assorted issues and make assorted minor improvements in the OPP
     code (Niklas Cassel, Viresh Kumar, Yue Hu).

   - Clean up the generic power domains (genpd) framework (Ulf Hansson).

   - Clean up assorted pieces of power management code and documentation
     (Akinobu Mita, Amit Kucheria, Chuhong Yuan).

   - Update the pm-graph tool to version 5.5 including multiple fixes
     and improvements (Todd Brandt).

   - Update the cpupower utility (Benjamin Weis, Geert Uytterhoeven,
     Sébastien Szymanski)"

* tag 'pm-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (126 commits)
  cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available
  cpuidle-haltpoll: do not set an owner to allow modunload
  cpuidle-haltpoll: return -ENODEV on modinit failure
  cpuidle-haltpoll: set haltpoll as preferred governor
  cpuidle: allow governor switch on cpuidle_register_driver()
  PM: runtime: Documentation: add runtime_status ABI document
  pm-graph: make setVal unbuffered again for python2 and python3
  powercap: idle_inject: Use higher resolution for idle injection
  cpuidle: play_idle: Increase the resolution to usec
  cpuidle-haltpoll: vcpu hotplug support
  cpufreq: Add qcs404 to cpufreq-dt-platdev blacklist
  cpufreq: qcom: Add support for qcs404 on nvmem driver
  cpufreq: qcom: Refactor the driver to make it easier to extend
  cpufreq: qcom: Re-organise kryo cpufreq to use it for other nvmem based qcom socs
  dt-bindings: opp: Add qcom-opp bindings with properties needed for CPR
  dt-bindings: opp: qcom-nvmem: Support pstates provided by a power domain
  Documentation: cpufreq: Update policy notifier documentation
  cpufreq: Remove CPUFREQ_ADJUST and CPUFREQ_NOTIFY policy notifier events
  PM / Domains: Verify PM domain type in dev_pm_genpd_set_performance_state()
  PM / Domains: Simplify genpd_lookup_dev()
  ...

1 files changed, 26 insertions, 84 deletions

diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 4c5db59a619b..391f39776c6a 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
@@ -66,8 +67,6 @@ struct time_in_idle {
  * @last_load: load measured by the latest call to cpufreq_get_requested_power()
  * @cpufreq_state: integer value representing the current state of cpufreq
  *	cooling	devices.
- * @clipped_freq: integer value representing the absolute value of the clipped
- *	frequency.
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
  * @freq_table: Freq table in descending order of frequencies
@@ -84,12 +83,12 @@ struct cpufreq_cooling_device {
 	int id;
 	u32 last_load;
 	unsigned int cpufreq_state;
-	unsigned int clipped_freq;
 	unsigned int max_level;
 	struct freq_table *freq_table;	/* In descending order */
 	struct cpufreq_policy *policy;
 	struct list_head node;
 	struct time_in_idle *idle_time;
+	struct dev_pm_qos_request qos_req;
 };
 
 static DEFINE_IDA(cpufreq_ida);
@@ -119,59 +118,6 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 
 /**
- * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
- * @nb:	struct notifier_block * with callback info.
- * @event: value showing cpufreq event for which this function invoked.
- * @data: callback-specific data
- *
- * Callback to hijack the notification on cpufreq policy transition.
- * Every time there is a change in policy, we will intercept and
- * update the cpufreq policy with thermal constraints.
- *
- * Return: 0 (success)
- */
-static int cpufreq_thermal_notifier(struct notifier_block *nb,
-				    unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	unsigned long clipped_freq;
-	struct cpufreq_cooling_device *cpufreq_cdev;
-
-	if (event != CPUFREQ_ADJUST)
-		return NOTIFY_DONE;
-
-	mutex_lock(&cooling_list_lock);
-	list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) {
-		/*
-		 * A new copy of the policy is sent to the notifier and can't
-		 * compare that directly.
-		 */
-		if (policy->cpu != cpufreq_cdev->policy->cpu)
-			continue;
-
-		/*
-		 * policy->max is the maximum allowed frequency defined by user
-		 * and clipped_freq is the maximum that thermal constraints
-		 * allow.
-		 *
-		 * If clipped_freq is lower than policy->max, then we need to
-		 * readjust policy->max.
-		 *
-		 * But, if clipped_freq is greater than policy->max, we don't
-		 * need to do anything.
-		 */
-		clipped_freq = cpufreq_cdev->clipped_freq;
-
-		if (policy->max > clipped_freq)
-			cpufreq_verify_within_limits(policy, 0, clipped_freq);
-		break;
-	}
-	mutex_unlock(&cooling_list_lock);
-
-	return NOTIFY_OK;
-}
-
-/**
  * update_freq_table() - Update the freq table with power numbers
  * @cpufreq_cdev:	the cpufreq cooling device in which to update the table
  * @capacitance: dynamic power coefficient for these cpus
@@ -374,7 +320,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
 	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
-	unsigned int clip_freq;
 
 	/* Request state should be less than max_level */
 	if (WARN_ON(state > cpufreq_cdev->max_level))
@@ -384,13 +329,10 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	if (cpufreq_cdev->cpufreq_state == state)
 		return 0;
 
-	clip_freq = cpufreq_cdev->freq_table[state].frequency;
 	cpufreq_cdev->cpufreq_state = state;
-	cpufreq_cdev->clipped_freq = clip_freq;
-
-	cpufreq_update_policy(cpufreq_cdev->policy->cpu);
 
-	return 0;
+	return dev_pm_qos_update_request(&cpufreq_cdev->qos_req,
+				cpufreq_cdev->freq_table[state].frequency);
 }
 
 /**
@@ -554,11 +496,6 @@ static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
 	.power2state		= cpufreq_power2state,
 };
 
-/* Notifier for cpufreq policy change */
-static struct notifier_block thermal_cpufreq_notifier_block = {
-	.notifier_call = cpufreq_thermal_notifier,
-};
-
 static unsigned int find_next_max(struct cpufreq_frequency_table *table,
 				  unsigned int prev_max)
 {
@@ -596,9 +533,16 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	unsigned int freq, i, num_cpus;
+	struct device *dev;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
-	bool first;
+
+	dev = get_cpu_device(policy->cpu);
+	if (unlikely(!dev)) {
+		pr_warn("No cpu device for cpu %d\n", policy->cpu);
+		return ERR_PTR(-ENODEV);
+	}
+
 
 	if (IS_ERR_OR_NULL(policy)) {
 		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
@@ -671,25 +615,29 @@ __cpufreq_cooling_register(struct device_node *np,
 		cooling_ops = &cpufreq_cooling_ops;
 	}
 
+	ret = dev_pm_qos_add_request(dev, &cpufreq_cdev->qos_req,
+				     DEV_PM_QOS_MAX_FREQUENCY,
+				     cpufreq_cdev->freq_table[0].frequency);
+	if (ret < 0) {
+		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
+		       ret);
+		cdev = ERR_PTR(ret);
+		goto remove_ida;
+	}
+
 	cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev,
 						  cooling_ops);
 	if (IS_ERR(cdev))
-		goto remove_ida;
-
-	cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency;
+		goto remove_qos_req;
 
 	mutex_lock(&cooling_list_lock);
-	/* Register the notifier for first cpufreq cooling device */
-	first = list_empty(&cpufreq_cdev_list);
 	list_add(&cpufreq_cdev->node, &cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
-	if (first)
-		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
-					  CPUFREQ_POLICY_NOTIFIER);
-
 	return cdev;
 
+remove_qos_req:
+	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_table:
@@ -777,7 +725,6 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	struct cpufreq_cooling_device *cpufreq_cdev;
-	bool last;
 
 	if (!cdev)
 		return;
@@ -786,15 +733,10 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	mutex_lock(&cooling_list_lock);
 	list_del(&cpufreq_cdev->node);
-	/* Unregister the notifier for the last cpufreq cooling device */
-	last = list_empty(&cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
-	if (last)
-		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
-					    CPUFREQ_POLICY_NOTIFIER);
-
 	thermal_cooling_device_unregister(cdev);
+	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 	kfree(cpufreq_cdev->idle_time);
 	kfree(cpufreq_cdev->freq_table);