Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

1 files changed, 86 insertions, 48 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e35a886e00bc..0e626b00053b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -19,6 +19,7 @@
 
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -545,13 +546,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us);
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
 static ssize_t show_boost(struct kobject *kobj,
-				 struct attribute *attr, char *buf)
+			  struct kobj_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled);
 }
 
-static ssize_t store_boost(struct kobject *kobj, struct attribute *attr,
-				  const char *buf, size_t count)
+static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr,
+			   const char *buf, size_t count)
 {
 	int ret, enable;
 
@@ -1200,28 +1201,39 @@ static int cpufreq_online(unsigned int cpu)
 			return -ENOMEM;
 	}
 
-	cpumask_copy(policy->cpus, cpumask_of(cpu));
+	if (!new_policy && cpufreq_driver->online) {
+		ret = cpufreq_driver->online(policy);
+		if (ret) {
+			pr_debug("%s: %d: initialization failed\n", __func__,
+				 __LINE__);
+			goto out_exit_policy;
+		}
 
-	/* call driver. From then on the cpufreq must be able
-	 * to accept all calls to ->verify and ->setpolicy for this CPU
-	 */
-	ret = cpufreq_driver->init(policy);
-	if (ret) {
-		pr_debug("initialization failed\n");
-		goto out_free_policy;
-	}
+		/* Recover policy->cpus using related_cpus */
+		cpumask_copy(policy->cpus, policy->related_cpus);
+	} else {
+		cpumask_copy(policy->cpus, cpumask_of(cpu));
 
-	ret = cpufreq_table_validate_and_sort(policy);
-	if (ret)
-		goto out_exit_policy;
+		/*
+		 * Call driver. From then on the cpufreq must be able
+		 * to accept all calls to ->verify and ->setpolicy for this CPU.
+		 */
+		ret = cpufreq_driver->init(policy);
+		if (ret) {
+			pr_debug("%s: %d: initialization failed\n", __func__,
+				 __LINE__);
+			goto out_free_policy;
+		}
 
-	down_write(&policy->rwsem);
+		ret = cpufreq_table_validate_and_sort(policy);
+		if (ret)
+			goto out_exit_policy;
 
-	if (new_policy) {
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
 	}
 
+	down_write(&policy->rwsem);
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
 	 * managing offline cpus here.
@@ -1305,8 +1317,6 @@ static int cpufreq_online(unsigned int cpu)
 	if (ret) {
 		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
 		       __func__, cpu, ret);
-		/* cpufreq_policy_free() will notify based on this */
-		new_policy = false;
 		goto out_destroy_policy;
 	}
 
@@ -1318,6 +1328,10 @@ static int cpufreq_online(unsigned int cpu)
 	if (cpufreq_driver->ready)
 		cpufreq_driver->ready(policy);
 
+	if (IS_ENABLED(CONFIG_CPU_THERMAL) &&
+	    cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV)
+		policy->cdev = of_cpufreq_cooling_register(policy);
+
 	pr_debug("initialization complete\n");
 
 	return 0;
@@ -1405,6 +1419,12 @@ static int cpufreq_offline(unsigned int cpu)
 		goto unlock;
 	}
 
+	if (IS_ENABLED(CONFIG_CPU_THERMAL) &&
+	    cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) {
+		cpufreq_cooling_unregister(policy->cdev);
+		policy->cdev = NULL;
+	}
+
 	if (cpufreq_driver->stop_cpu)
 		cpufreq_driver->stop_cpu(policy);
 
@@ -1412,11 +1432,12 @@ static int cpufreq_offline(unsigned int cpu)
 		cpufreq_exit_governor(policy);
 
 	/*
-	 * Perform the ->exit() even during light-weight tear-down,
-	 * since this is a core component, and is essential for the
-	 * subsequent light-weight ->init() to succeed.
+	 * Perform the ->offline() during light-weight tear-down, as
+	 * that allows fast recovery when the CPU comes back.
 	 */
-	if (cpufreq_driver->exit) {
+	if (cpufreq_driver->offline) {
+		cpufreq_driver->offline(policy);
+	} else if (cpufreq_driver->exit) {
 		cpufreq_driver->exit(policy);
 		policy->freq_table = NULL;
 	}
@@ -1445,8 +1466,13 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	cpumask_clear_cpu(cpu, policy->real_cpus);
 	remove_cpu_dev_symlink(policy, dev);
 
-	if (cpumask_empty(policy->real_cpus))
+	if (cpumask_empty(policy->real_cpus)) {
+		/* We did light-weight exit earlier, do full tear down now */
+		if (cpufreq_driver->offline)
+			cpufreq_driver->exit(policy);
+
 		cpufreq_policy_free(policy);
+	}
 }
 
 /**
@@ -2192,12 +2218,25 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_get_policy);
 
-/*
- * policy : current policy.
- * new_policy: policy to be set.
+/**
+ * cpufreq_set_policy - Modify cpufreq policy parameters.
+ * @policy: Policy object to modify.
+ * @new_policy: New policy data.
+ *
+ * Pass @new_policy to the cpufreq driver's ->verify() callback, run the
+ * installed policy notifiers for it with the CPUFREQ_ADJUST value, pass it to
+ * the driver's ->verify() callback again and run the notifiers for it again
+ * with the CPUFREQ_NOTIFY value.  Next, copy the min and max parameters
+ * of @new_policy to @policy and either invoke the driver's ->setpolicy()
+ * callback (if present) or carry out a governor update for @policy.  That is,
+ * run the current governor's ->limits() callback (if the governor field in
+ * @new_policy points to the same object as the one in @policy) or replace the
+ * governor for @policy with the new one stored in @new_policy.
+ *
+ * The cpuinfo part of @policy is not updated by this function.
  */
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
-				struct cpufreq_policy *new_policy)
+			      struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
 	int ret;
@@ -2247,11 +2286,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (cpufreq_driver->setpolicy) {
 		policy->policy = new_policy->policy;
 		pr_debug("setting range\n");
-		return cpufreq_driver->setpolicy(new_policy);
+		return cpufreq_driver->setpolicy(policy);
 	}
 
 	if (new_policy->governor == policy->governor) {
-		pr_debug("cpufreq: governor limits update\n");
+		pr_debug("governor limits update\n");
 		cpufreq_governor_limits(policy);
 		return 0;
 	}
@@ -2272,7 +2311,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (!ret) {
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
-			pr_debug("cpufreq: governor change\n");
+			pr_debug("governor change\n");
 			sched_cpufreq_governor_change(policy, old_gov);
 			return 0;
 		}
@@ -2293,11 +2332,14 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 }
 
 /**
- *	cpufreq_update_policy - re-evaluate an existing cpufreq policy
- *	@cpu: CPU which shall be re-evaluated
+ * cpufreq_update_policy - Re-evaluate an existing cpufreq policy.
+ * @cpu: CPU to re-evaluate the policy for.
  *
- *	Useful for policy notifiers which have different necessities
- *	at different times.
+ * Update the current frequency for the cpufreq policy of @cpu and use
+ * cpufreq_set_policy() to re-apply the min and max limits saved in the
+ * user_policy sub-structure of that policy, which triggers the evaluation
+ * of policy notifiers and the cpufreq driver's ->verify() callback for the
+ * policy in question, among other things.
  */
 void cpufreq_update_policy(unsigned int cpu)
 {
@@ -2312,23 +2354,18 @@ void cpufreq_update_policy(unsigned int cpu)
 	if (policy_is_inactive(policy))
 		goto unlock;
 
-	pr_debug("updating policy for CPU %u\n", cpu);
-	memcpy(&new_policy, policy, sizeof(*policy));
-	new_policy.min = policy->user_policy.min;
-	new_policy.max = policy->user_policy.max;
-
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
-	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
-		if (cpufreq_suspended)
-			goto unlock;
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy &&
+	    (cpufreq_suspended || WARN_ON(!cpufreq_update_current_freq(policy))))
+		goto unlock;
 
-		new_policy.cur = cpufreq_update_current_freq(policy);
-		if (WARN_ON(!new_policy.cur))
-			goto unlock;
-	}
+	pr_debug("updating policy for CPU %u\n", cpu);
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.min = policy->user_policy.min;
+	new_policy.max = policy->user_policy.max;
 
 	cpufreq_set_policy(policy, &new_policy);
 
@@ -2479,7 +2516,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		    driver_data->target) ||
 	     (driver_data->setpolicy && (driver_data->target_index ||
 		    driver_data->target)) ||
-	     (!!driver_data->get_intermediate != !!driver_data->target_intermediate))
+	     (!driver_data->get_intermediate != !driver_data->target_intermediate) ||
+	     (!driver_data->online != !driver_data->offline))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);