Merge tag 'pm-5.3-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These modify the Intel RAPL driver to allow it to use an MMIO
  interface to the hardware, make the int340X thermal driver provide
  such an interface for it, add Intel Ice Lake CPU IDs to the RAPL
  driver (these changes depend on the previously merged x86 arch
  changes), update cpufreq to use the PM QoS framework for managing the
  min and max frequency limits, and add update the imx-cpufreq-dt
  cpufreq driver to support i.MX8MN.

  Specifics:

   - Add MMIO interface support to the Intel RAPL power capping driver
     and update the int340X thermal driver to provide a RAPL MMIO
     interface (Zhang Rui, Stephen Rothwell).

   - Add Intel Ice Lake CPU IDs to the RAPL driver (Zhang Rui, Rajneesh
     Bhardwaj).

   - Make cpufreq use the PM QoS framework (instead of notifiers) for
     managing the min and max frequency constraints (Viresh Kumar).

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

* tag 'pm-5.3-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (27 commits)
  cpufreq: Make cpufreq_generic_init() return void
  intel_rapl: need linux/cpuhotplug.h for enum cpuhp_state
  powercap/rapl: Add Ice Lake NNPI support to RAPL driver
  powercap/intel_rapl: add support for ICX-D
  powercap/intel_rapl: add support for ICX
  powercap/intel_rapl: add support for IceLake desktop
  intel_rapl: Fix module autoloading issue
  int340X/processor_thermal_device: add support for MMIO RAPL
  intel_rapl: support two power limits for every RAPL domain
  intel_rapl: support 64 bit register
  intel_rapl: abstract RAPL common code
  intel_rapl: cleanup hardcoded MSR access
  intel_rapl: cleanup some functions
  intel_rapl: abstract register access operations
  intel_rapl: abstract register address
  intel_rapl: introduce struct rapl_if_private
  intel_rapl: introduce intel_rapl.h
  intel_rapl: remove hardcoded register index
  intel_rapl: use reg instead of msr
  cpufreq: imx-cpufreq-dt: Add i.MX8MN support
  ...

Documentation/power/pm_qos_interface.rst

@@ -129,7 +129,7 @@ int dev_pm_qos_remove_request(handle):
   and call the notification trees if the target was changed as a result of
   removing the request.
 
-s32 dev_pm_qos_read_value(device):
+s32 dev_pm_qos_read_value(device, type):
   Returns the aggregated value for a given device's constraints list.
 
 enum pm_qos_flags_status dev_pm_qos_flags(device, mask)
@@ -176,12 +176,14 @@ Notification mechanisms:
 
 The per-device PM QoS framework has a per-device notification tree.
 
-int dev_pm_qos_add_notifier(device, notifier):
-  Adds a notification callback function for the device.
+int dev_pm_qos_add_notifier(device, notifier, type):
+  Adds a notification callback function for the device for a particular request
+  type.
+
   The callback is called when the aggregated value of the device constraints list
-  is changed (for resume latency device PM QoS only).
+  is changed.
 
-int dev_pm_qos_remove_notifier(device, notifier):
+int dev_pm_qos_remove_notifier(device, notifier, type):
   Removes the notification callback function for the device.
 
 

MAINTAINERS

@@ -12840,6 +12840,7 @@ F:	drivers/base/power/
 F:	include/linux/pm.h
 F:	include/linux/pm_*
 F:	include/linux/powercap.h
+F:	include/linux/intel_rapl.h
 F:	drivers/powercap/
 F:	kernel/configs/nopm.config
 

drivers/base/power/domain.c

@@ -1536,7 +1536,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
 	else
-		dev_pm_qos_add_notifier(dev, &gpd_data->nb);
+		dev_pm_qos_add_notifier(dev, &gpd_data->nb,
+					DEV_PM_QOS_RESUME_LATENCY);
 
 	return ret;
 }
@@ -1569,7 +1570,8 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
 	pdd = dev->power.subsys_data->domain_data;
 	gpd_data = to_gpd_data(pdd);
-	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
+	dev_pm_qos_remove_notifier(dev, &gpd_data->nb,
+				   DEV_PM_QOS_RESUME_LATENCY);
 
 	genpd_lock(genpd);
 
@@ -1597,7 +1599,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
  out:
 	genpd_unlock(genpd);
-	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
+	dev_pm_qos_add_notifier(dev, &gpd_data->nb, DEV_PM_QOS_RESUME_LATENCY);
 
 	return ret;
 }

drivers/base/power/domain_governor.c

@@ -33,7 +33,7 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
 		 * take its current PM QoS constraint (that's the only thing
 		 * known at this point anyway).
 		 */
-		constraint_ns = dev_pm_qos_read_value(dev);
+		constraint_ns = dev_pm_qos_read_value(dev, DEV_PM_QOS_RESUME_LATENCY);
 		constraint_ns *= NSEC_PER_USEC;
 	}
 
@@ -66,7 +66,7 @@ static bool default_suspend_ok(struct device *dev)
 	td->constraint_changed = false;
 	td->cached_suspend_ok = false;
 	td->effective_constraint_ns = 0;
-	constraint_ns = __dev_pm_qos_read_value(dev);
+	constraint_ns = __dev_pm_qos_resume_latency(dev);
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 

drivers/base/power/qos.c

@@ -90,29 +90,49 @@ enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask)
 EXPORT_SYMBOL_GPL(dev_pm_qos_flags);
 
 /**
- * __dev_pm_qos_read_value - Get PM QoS constraint for a given device.
+ * __dev_pm_qos_resume_latency - Get resume latency constraint for a given device.
  * @dev: Device to get the PM QoS constraint value for.
  *
  * This routine must be called with dev->power.lock held.
  */
-s32 __dev_pm_qos_read_value(struct device *dev)
+s32 __dev_pm_qos_resume_latency(struct device *dev)
 {
 	lockdep_assert_held(&dev->power.lock);
 
-	return dev_pm_qos_raw_read_value(dev);
+	return dev_pm_qos_raw_resume_latency(dev);
 }
 
 /**
  * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked).
  * @dev: Device to get the PM QoS constraint value for.
+ * @type: QoS request type.
  */
-s32 dev_pm_qos_read_value(struct device *dev)
+s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type)
 {
+	struct dev_pm_qos *qos = dev->power.qos;
 	unsigned long flags;
 	s32 ret;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
-	ret = __dev_pm_qos_read_value(dev);
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
+			: pm_qos_read_value(&qos->resume_latency);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
+			: pm_qos_read_value(&qos->min_frequency);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
+			: pm_qos_read_value(&qos->max_frequency);
+		break;
+	default:
+		WARN_ON(1);
+		ret = 0;
+	}
+
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
 	return ret;
@@ -149,6 +169,14 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 			req->dev->power.set_latency_tolerance(req->dev, value);
 		}
 		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = pm_qos_update_target(&qos->min_frequency,
+					   &req->data.pnode, action, value);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = pm_qos_update_target(&qos->max_frequency,
+					   &req->data.pnode, action, value);
+		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -177,12 +205,11 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	if (!qos)
 		return -ENOMEM;
 
-	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	n = kzalloc(3 * sizeof(*n), GFP_KERNEL);
 	if (!n) {
 		kfree(qos);
 		return -ENOMEM;
 	}
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
 
 	c = &qos->resume_latency;
 	plist_head_init(&c->list);
@@ -191,6 +218,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
+	BLOCKING_INIT_NOTIFIER_HEAD(n);
 
 	c = &qos->latency_tolerance;
 	plist_head_init(&c->list);
@@ -199,6 +227,24 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 
+	c = &qos->min_frequency;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
+	c->default_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
+	c->type = PM_QOS_MAX;
+	c->notifiers = ++n;
+	BLOCKING_INIT_NOTIFIER_HEAD(n);
+
+	c = &qos->max_frequency;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
+	c->default_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
+	c->type = PM_QOS_MIN;
+	c->notifiers = ++n;
+	BLOCKING_INIT_NOTIFIER_HEAD(n);
+
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -252,11 +298,25 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
 		memset(req, 0, sizeof(*req));
 	}
+
 	c = &qos->latency_tolerance;
 	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
 		memset(req, 0, sizeof(*req));
 	}
+
+	c = &qos->min_frequency;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
+	c = &qos->max_frequency;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -368,6 +428,8 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
+	case DEV_PM_QOS_MIN_FREQUENCY:
+	case DEV_PM_QOS_MAX_FREQUENCY:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -467,6 +529,7 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
  *
  * @dev: target device for the constraint
  * @notifier: notifier block managed by caller.
+ * @type: request type.
  *
  * Will register the notifier into a notification chain that gets called
  * upon changes to the target value for the device.
@@ -474,7 +537,8 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
  * If the device's constraints object doesn't exist when this routine is called,
  * it will be created (or error code will be returned if that fails).
  */
-int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
+int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier,
+			    enum dev_pm_qos_req_type type)
 {
 	int ret = 0;
 
@@ -485,10 +549,28 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
 	else if (!dev->power.qos)
 		ret = dev_pm_qos_constraints_allocate(dev);
 
-	if (!ret)
+	if (ret)
+		goto unlock;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
 		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
 						       notifier);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = blocking_notifier_chain_register(dev->power.qos->min_frequency.notifiers,
+						       notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = blocking_notifier_chain_register(dev->power.qos->max_frequency.notifiers,
+						       notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
 
+unlock:
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
@@ -500,24 +582,44 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier);
  *
  * @dev: target device for the constraint
  * @notifier: notifier block to be removed.
+ * @type: request type.
  *
  * Will remove the notifier from the notification chain that gets called
  * upon changes to the target value.
  */
 int dev_pm_qos_remove_notifier(struct device *dev,
-			       struct notifier_block *notifier)
+			       struct notifier_block *notifier,
+			       enum dev_pm_qos_req_type type)
 {
-	int retval = 0;
+	int ret = 0;
 
 	mutex_lock(&dev_pm_qos_mtx);
 
 	/* Silently return if the constraints object is not present. */
-	if (!IS_ERR_OR_NULL(dev->power.qos))
-		retval = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
-							    notifier);
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		goto unlock;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
+							 notifier);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = blocking_notifier_chain_unregister(dev->power.qos->min_frequency.notifiers,
+							 notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = blocking_notifier_chain_unregister(dev->power.qos->max_frequency.notifiers,
+							 notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
 
+unlock:
 	mutex_unlock(&dev_pm_qos_mtx);
-	return retval;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
 
@@ -577,6 +679,9 @@ static void __dev_pm_qos_drop_user_request(struct device *dev,
 		req = dev->power.qos->flags_req;
 		dev->power.qos->flags_req = NULL;
 		break;
+	default:
+		WARN_ON(1);
+		return;
 	}
 	__dev_pm_qos_remove_request(req);
 	kfree(req);

drivers/base/power/runtime.c

@@ -275,7 +275,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
-	else if (__dev_pm_qos_read_value(dev) == 0)
+	else if (__dev_pm_qos_resume_latency(dev) == 0)
 		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;

drivers/cpufreq/bmips-cpufreq.c

@@ -131,23 +131,18 @@ static int bmips_cpufreq_exit(struct cpufreq_policy *policy)
 static int bmips_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
-	int ret;
 
 	freq_table = bmips_cpufreq_get_freq_table(policy);
 	if (IS_ERR(freq_table)) {
-		ret = PTR_ERR(freq_table);
-		pr_err("%s: couldn't determine frequency table (%d).\n",
-			BMIPS_CPUFREQ_NAME, ret);
-		return ret;
+		pr_err("%s: couldn't determine frequency table (%ld).\n",
+			BMIPS_CPUFREQ_NAME, PTR_ERR(freq_table));
+		return PTR_ERR(freq_table);
 	}
 
-	ret = cpufreq_generic_init(policy, freq_table, TRANSITION_LATENCY);
-	if (ret)
-		bmips_cpufreq_exit(policy);
-	else
-		pr_info("%s: registered\n", BMIPS_CPUFREQ_NAME);
+	cpufreq_generic_init(policy, freq_table, TRANSITION_LATENCY);
+	pr_info("%s: registered\n", BMIPS_CPUFREQ_NAME);
 
-	return ret;
+	return 0;
 }
 
 static struct cpufreq_driver bmips_cpufreq_driver = {

drivers/cpufreq/cpufreq.c

@@ -23,6 +23,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
@@ -158,7 +159,7 @@ EXPORT_SYMBOL_GPL(arch_set_freq_scale);
  * - set policies transition latency
  * - policy->cpus with all possible CPUs
  */
-int cpufreq_generic_init(struct cpufreq_policy *policy,
+void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency)
 {
@@ -170,8 +171,6 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 	 * share the clock and voltage and clock.
 	 */
 	cpumask_setall(policy->cpus);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
@@ -714,23 +713,15 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 static ssize_t store_##file_name					\
 (struct cpufreq_policy *policy, const char *buf, size_t count)		\
 {									\
-	int ret, temp;							\
-	struct cpufreq_policy new_policy;				\
+	unsigned long val;						\
+	int ret;							\
 									\
-	memcpy(&new_policy, policy, sizeof(*policy));			\
-	new_policy.min = policy->user_policy.min;			\
-	new_policy.max = policy->user_policy.max;			\
-									\
-	ret = sscanf(buf, "%u", &new_policy.object);			\
+	ret = sscanf(buf, "%lu", &val);					\
 	if (ret != 1)							\
 		return -EINVAL;						\
 									\
-	temp = new_policy.object;					\
-	ret = cpufreq_set_policy(policy, &new_policy);		\
-	if (!ret)							\
-		policy->user_policy.object = temp;			\
-									\
-	return ret ? ret : count;					\
+	ret = dev_pm_qos_update_request(policy->object##_freq_req, val);\
+	return ret >= 0 ? count : ret;					\
 }
 
 store_one(scaling_min_freq, min);
@@ -996,7 +987,7 @@ static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
 
-	if (!dev)
+	if (unlikely(!dev))
 		return;
 
 	if (cpumask_test_and_set_cpu(cpu, policy->real_cpus))
@@ -1112,17 +1103,18 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 	return ret;
 }
 
-static void refresh_frequency_limits(struct cpufreq_policy *policy)
+void refresh_frequency_limits(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy new_policy = *policy;
-
-	pr_debug("updating policy for CPU %u\n", policy->cpu);
+	struct cpufreq_policy new_policy;
 
-	new_policy.min = policy->user_policy.min;
-	new_policy.max = policy->user_policy.max;
+	if (!policy_is_inactive(policy)) {
+		new_policy = *policy;
+		pr_debug("updating policy for CPU %u\n", policy->cpu);
 
-	cpufreq_set_policy(policy, &new_policy);
+		cpufreq_set_policy(policy, &new_policy);
+	}
 }
+EXPORT_SYMBOL(refresh_frequency_limits);
 
 static void handle_update(struct work_struct *work)
 {
@@ -1130,14 +1122,60 @@ static void handle_update(struct work_struct *work)
 		container_of(work, struct cpufreq_policy, update);
 
 	pr_debug("handle_update for cpu %u called\n", policy->cpu);
+	down_write(&policy->rwsem);
 	refresh_frequency_limits(policy);
+	up_write(&policy->rwsem);
+}
+
+static int cpufreq_notifier_min(struct notifier_block *nb, unsigned long freq,
+				void *data)
+{
+	struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_min);
+
+	schedule_work(&policy->update);
+	return 0;
+}
+
+static int cpufreq_notifier_max(struct notifier_block *nb, unsigned long freq,
+				void *data)
+{
+	struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_max);
+
+	schedule_work(&policy->update);
+	return 0;
+}
+
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+{
+	struct kobject *kobj;
+	struct completion *cmp;
+
+	down_write(&policy->rwsem);
+	cpufreq_stats_free_table(policy);
+	kobj = &policy->kobj;
+	cmp = &policy->kobj_unregister;
+	up_write(&policy->rwsem);
+	kobject_put(kobj);
+
+	/*
+	 * We need to make sure that the underlying kobj is
+	 * actually not referenced anymore by anybody before we
+	 * proceed with unloading.
+	 */
+	pr_debug("waiting for dropping of refcount\n");
+	wait_for_completion(cmp);
+	pr_debug("wait complete\n");
 }
 
 static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
+	struct device *dev = get_cpu_device(cpu);
 	int ret;
 
+	if (!dev)
+		return NULL;
+
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
 		return NULL;
@@ -1154,7 +1192,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
 				   cpufreq_global_kobject, "policy%u", cpu);
 	if (ret) {
-		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		dev_err(dev, "%s: failed to init policy->kobj: %d\n", __func__, ret);
 		/*
 		 * The entire policy object will be freed below, but the extra
 		 * memory allocated for the kobject name needs to be freed by
@@ -1164,6 +1202,25 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 		goto err_free_real_cpus;
 	}
 
+	policy->nb_min.notifier_call = cpufreq_notifier_min;
+	policy->nb_max.notifier_call = cpufreq_notifier_max;
+
+	ret = dev_pm_qos_add_notifier(dev, &policy->nb_min,
+				      DEV_PM_QOS_MIN_FREQUENCY);
+	if (ret) {
+		dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n",
+			ret, cpumask_pr_args(policy->cpus));
+		goto err_kobj_remove;
+	}
+
+	ret = dev_pm_qos_add_notifier(dev, &policy->nb_max,
+				      DEV_PM_QOS_MAX_FREQUENCY);
+	if (ret) {
+		dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n",
+			ret, cpumask_pr_args(policy->cpus));
+		goto err_min_qos_notifier;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1174,6 +1231,11 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	policy->cpu = cpu;
 	return policy;
 
+err_min_qos_notifier:
+	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
+				   DEV_PM_QOS_MIN_FREQUENCY);
+err_kobj_remove:
+	cpufreq_policy_put_kobj(policy);
 err_free_real_cpus:
 	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
@@ -1186,30 +1248,9 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
-{
-	struct kobject *kobj;
-	struct completion *cmp;
-
-	down_write(&policy->rwsem);
-	cpufreq_stats_free_table(policy);
-	kobj = &policy->kobj;
-	cmp = &policy->kobj_unregister;
-	up_write(&policy->rwsem);
-	kobject_put(kobj);
-
-	/*
-	 * We need to make sure that the underlying kobj is
-	 * actually not referenced anymore by anybody before we
-	 * proceed with unloading.
-	 */
-	pr_debug("waiting for dropping of refcount\n");
-	wait_for_completion(cmp);
-	pr_debug("wait complete\n");
-}
-
 static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
+	struct device *dev = get_cpu_device(policy->cpu);
 	unsigned long flags;
 	int cpu;
 
@@ -1221,6 +1262,14 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	dev_pm_qos_remove_notifier(dev, &policy->nb_max,
+				   DEV_PM_QOS_MAX_FREQUENCY);
+	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
+				   DEV_PM_QOS_MIN_FREQUENCY);
+	dev_pm_qos_remove_request(policy->max_freq_req);
+	dev_pm_qos_remove_request(policy->min_freq_req);
+	kfree(policy->min_freq_req);
+
 	cpufreq_policy_put_kobj(policy);
 	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
@@ -1298,16 +1347,50 @@ static int cpufreq_online(unsigned int cpu)
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
 	if (new_policy) {
-		policy->user_policy.min = policy->min;
-		policy->user_policy.max = policy->max;
+		struct device *dev = get_cpu_device(cpu);
 
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
 			add_cpu_dev_symlink(policy, j);
 		}
-	} else {
-		policy->min = policy->user_policy.min;
-		policy->max = policy->user_policy.max;
+
+		policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req),
+					       GFP_KERNEL);
+		if (!policy->min_freq_req)
+			goto out_destroy_policy;
+
+		ret = dev_pm_qos_add_request(dev, policy->min_freq_req,
+					     DEV_PM_QOS_MIN_FREQUENCY,
+					     policy->min);
+		if (ret < 0) {
+			/*
+			 * So we don't call dev_pm_qos_remove_request() for an
+			 * uninitialized request.
+			 */
+			kfree(policy->min_freq_req);
+			policy->min_freq_req = NULL;
+
+			dev_err(dev, "Failed to add min-freq constraint (%d)\n",
+				ret);
+			goto out_destroy_policy;
+		}
+
+		/*
+		 * This must be initialized right here to avoid calling
+		 * dev_pm_qos_remove_request() on uninitialized request in case
+		 * of errors.
+		 */
+		policy->max_freq_req = policy->min_freq_req + 1;
+
+		ret = dev_pm_qos_add_request(dev, policy->max_freq_req,
+					     DEV_PM_QOS_MAX_FREQUENCY,
+					     policy->max);
+		if (ret < 0) {
+			policy->max_freq_req = NULL;
+			dev_err(dev, "Failed to add max-freq constraint (%d)\n",
+				ret);
+			goto out_destroy_policy;
+		}
 	}
 
 	if (cpufreq_driver->get && has_target()) {
@@ -2280,6 +2363,7 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	int ret;
 
 	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
@@ -2288,17 +2372,21 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
 	/*
-	* This check works well when we store new min/max freq attributes,
-	* because new_policy is a copy of policy with one field updated.
-	*/
-	if (new_policy->min > new_policy->max)
-		return -EINVAL;
+	 * PM QoS framework collects all the requests from users and provide us
+	 * the final aggregated value here.
+	 */
+	new_policy->min = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MIN_FREQUENCY);
+	new_policy->max = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MAX_FREQUENCY);
 
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		return ret;
 
+	/*
+	 * The notifier-chain shall be removed once all the users of
+	 * CPUFREQ_ADJUST are moved to use the QoS framework.
+	 */
 	/* adjust if necessary - all reasons */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_ADJUST, new_policy);
@@ -2377,10 +2465,9 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
  * @cpu: CPU to re-evaluate the policy for.
  *
  * 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.
+ * cpufreq_set_policy() to re-apply the min and max limits, 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)
 {
@@ -2440,10 +2527,9 @@ static int cpufreq_boost_set_sw(int state)
 			break;
 		}
 
-		down_write(&policy->rwsem);
-		policy->user_policy.max = policy->max;
-		cpufreq_governor_limits(policy);
-		up_write(&policy->rwsem);
+		ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max);
+		if (ret)
+			break;
 	}
 
 	return ret;

drivers/cpufreq/davinci-cpufreq.c

@@ -90,7 +90,8 @@ static int davinci_cpu_init(struct cpufreq_policy *policy)
 	 * Setting the latency to 2000 us to accommodate addition of drivers
 	 * to pre/post change notification list.
 	 */
-	return cpufreq_generic_init(policy, freq_table, 2000 * 1000);
+	cpufreq_generic_init(policy, freq_table, 2000 * 1000);
+	return 0;
 }
 
 static struct cpufreq_driver davinci_driver = {

drivers/cpufreq/imx-cpufreq-dt.c

@@ -44,10 +44,11 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev)
 	 * According to datasheet minimum speed grading is not supported for
 	 * consumer parts so clamp to 1 to avoid warning for "no OPPs"
 	 *
-	 * Applies to 8mq and 8mm.
+	 * Applies to i.MX8M series SoCs.
 	 */
 	if (mkt_segment == 0 && speed_grade == 0 && (
 			of_machine_is_compatible("fsl,imx8mm") ||
+			of_machine_is_compatible("fsl,imx8mn") ||
 			of_machine_is_compatible("fsl,imx8mq")))
 		speed_grade = 1;
 

drivers/cpufreq/imx6q-cpufreq.c

@@ -190,14 +190,12 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
-	int ret;
-
 	policy->clk = clks[ARM].clk;
-	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
+	cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
 	dev_pm_opp_of_register_em(policy->cpus);
 
-	return ret;
+	return 0;
 }
 
 static struct cpufreq_driver imx6q_cpufreq_driver = {

drivers/cpufreq/intel_pstate.c

@@ -898,7 +898,6 @@ static void intel_pstate_update_policies(void)
 static void intel_pstate_update_max_freq(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
-	struct cpufreq_policy new_policy;
 	struct cpudata *cpudata;
 
 	if (!policy)
@@ -908,11 +907,7 @@ static void intel_pstate_update_max_freq(unsigned int cpu)
 	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
 			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
 
-	memcpy(&new_policy, policy, sizeof(*policy));
-	new_policy.max = min(policy->user_policy.max, policy->cpuinfo.max_freq);
-	new_policy.min = min(policy->user_policy.min, new_policy.max);
-
-	cpufreq_set_policy(policy, &new_policy);
+	refresh_frequency_limits(policy);
 
 	cpufreq_cpu_release(policy);
 }

drivers/cpufreq/kirkwood-cpufreq.c

@@ -85,7 +85,8 @@ static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
 /* Module init and exit code */
 static int kirkwood_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, kirkwood_freq_table, 5000);
+	cpufreq_generic_init(policy, kirkwood_freq_table, 5000);
+	return 0;
 }
 
 static struct cpufreq_driver kirkwood_cpufreq_driver = {

drivers/cpufreq/loongson1-cpufreq.c

@@ -81,7 +81,7 @@ static int ls1x_cpufreq_init(struct cpufreq_policy *policy)
 	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	struct cpufreq_frequency_table *freq_tbl;
 	unsigned int pll_freq, freq;
-	int steps, i, ret;
+	int steps, i;
 
 	pll_freq = clk_get_rate(cpufreq->pll_clk) / 1000;
 
@@ -103,11 +103,9 @@ static int ls1x_cpufreq_init(struct cpufreq_policy *policy)
 	freq_tbl[i].frequency = CPUFREQ_TABLE_END;
 
 	policy->clk = cpufreq->clk;
-	ret = cpufreq_generic_init(policy, freq_tbl, 0);
-	if (ret)
-		kfree(freq_tbl);
+	cpufreq_generic_init(policy, freq_tbl, 0);
 
-	return ret;
+	return 0;
 }
 
 static int ls1x_cpufreq_exit(struct cpufreq_policy *policy)

drivers/cpufreq/loongson2_cpufreq.c

@@ -95,7 +95,8 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	policy->clk = cpuclk;
-	return cpufreq_generic_init(policy, &loongson2_clockmod_table[0], 0);
+	cpufreq_generic_init(policy, &loongson2_clockmod_table[0], 0);
+	return 0;
 }
 
 static int loongson2_cpufreq_exit(struct cpufreq_policy *policy)

drivers/cpufreq/maple-cpufreq.c

@@ -140,7 +140,8 @@ static unsigned int maple_cpufreq_get_speed(unsigned int cpu)
 
 static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, maple_cpu_freqs, 12000);
+	cpufreq_generic_init(policy, maple_cpu_freqs, 12000);
+	return 0;
 }
 
 static struct cpufreq_driver maple_cpufreq_driver = {

drivers/cpufreq/omap-cpufreq.c

@@ -122,23 +122,18 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 			dev_err(mpu_dev,
 				"%s: cpu%d: failed creating freq table[%d]\n",
 				__func__, policy->cpu, result);
-			goto fail;
+			clk_put(policy->clk);
+			return result;
 		}
 	}
 
 	atomic_inc_return(&freq_table_users);
 
 	/* FIXME: what's the actual transition time? */
-	result = cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	if (!result) {
-		dev_pm_opp_of_register_em(policy->cpus);
-		return 0;
-	}
+	cpufreq_generic_init(policy, freq_table, 300 * 1000);
+	dev_pm_opp_of_register_em(policy->cpus);
 
-	freq_table_free();
-fail:
-	clk_put(policy->clk);
-	return result;
+	return 0;
 }
 
 static int omap_cpu_exit(struct cpufreq_policy *policy)

drivers/cpufreq/pasemi-cpufreq.c

@@ -196,7 +196,8 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cur = pas_freqs[cur_astate].frequency;
 	ppc_proc_freq = policy->cur * 1000ul;
 
-	return cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency());
+	cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency());
+	return 0;
 
 out_unmap_sdcpwr:
 	iounmap(sdcpwr_mapbase);

drivers/cpufreq/pmac32-cpufreq.c

@@ -372,7 +372,8 @@ static int pmac_cpufreq_target(	struct cpufreq_policy *policy,
 
 static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, pmac_cpu_freqs, transition_latency);
+	cpufreq_generic_init(policy, pmac_cpu_freqs, transition_latency);
+	return 0;
 }
 
 static u32 read_gpio(struct device_node *np)

drivers/cpufreq/pmac64-cpufreq.c

@@ -321,7 +321,8 @@ static unsigned int g5_cpufreq_get_speed(unsigned int cpu)
 
 static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, g5_cpu_freqs, transition_latency);
+	cpufreq_generic_init(policy, g5_cpu_freqs, transition_latency);
+	return 0;
 }
 
 static struct cpufreq_driver g5_cpufreq_driver = {

drivers/cpufreq/s3c2416-cpufreq.c

@@ -447,21 +447,16 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 	/* Datasheet says PLL stabalisation time must be at least 300us,
 	 * so but add some fudge. (reference in LOCKCON0 register description)
 	 */
-	ret = cpufreq_generic_init(policy, s3c_freq->freq_table,
+	cpufreq_generic_init(policy, s3c_freq->freq_table,
 			(500 * 1000) + s3c_freq->regulator_latency);
-	if (ret)
-		goto err_freq_table;
-
 	register_reboot_notifier(&s3c2416_cpufreq_reboot_notifier);
 
 	return 0;
 
-err_freq_table:
 #ifdef CONFIG_ARM_S3C2416_CPUFREQ_VCORESCALE
-	regulator_put(s3c_freq->vddarm);
 err_vddarm:
-#endif
 	clk_put(s3c_freq->armclk);
+#endif
 err_armclk:
 	clk_put(s3c_freq->hclk);
 err_hclk:

drivers/cpufreq/s3c64xx-cpufreq.c

@@ -144,7 +144,6 @@ static void s3c64xx_cpufreq_config_regulator(void)
 
 static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
-	int ret;
 	struct cpufreq_frequency_table *freq;
 
 	if (policy->cpu != 0)
@@ -165,8 +164,7 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 #ifdef CONFIG_REGULATOR
 	vddarm = regulator_get(NULL, "vddarm");
 	if (IS_ERR(vddarm)) {
-		ret = PTR_ERR(vddarm);
-		pr_err("Failed to obtain VDDARM: %d\n", ret);
+		pr_err("Failed to obtain VDDARM: %ld\n", PTR_ERR(vddarm));
 		pr_err("Only frequency scaling available\n");
 		vddarm = NULL;
 	} else {
@@ -196,16 +194,9 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 	 * the PLLs, which we don't currently) is ~300us worst case,
 	 * but add some fudge.
 	 */
-	ret = cpufreq_generic_init(policy, s3c64xx_freq_table,
+	cpufreq_generic_init(policy, s3c64xx_freq_table,
 			(500 * 1000) + regulator_latency);
-	if (ret != 0) {
-		pr_err("Failed to configure frequency table: %d\n",
-		       ret);
-		regulator_put(vddarm);
-		clk_put(policy->clk);
-	}
-
-	return ret;
+	return 0;
 }
 
 static struct cpufreq_driver s3c64xx_cpufreq_driver = {

drivers/cpufreq/s5pv210-cpufreq.c

@@ -541,7 +541,8 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy)
 	s5pv210_dram_conf[1].freq = clk_get_rate(dmc1_clk);
 
 	policy->suspend_freq = SLEEP_FREQ;
-	return cpufreq_generic_init(policy, s5pv210_freq_table, 40000);
+	cpufreq_generic_init(policy, s5pv210_freq_table, 40000);
+	return 0;
 
 out_dmc1:
 	clk_put(dmc0_clk);

drivers/cpufreq/sa1100-cpufreq.c

@@ -181,7 +181,8 @@ static int sa1100_target(struct cpufreq_policy *policy, unsigned int ppcr)
 
 static int __init sa1100_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, sa11x0_freq_table, 0);
+	cpufreq_generic_init(policy, sa11x0_freq_table, 0);
+	return 0;
 }
 
 static struct cpufreq_driver sa1100_driver __refdata = {

drivers/cpufreq/sa1110-cpufreq.c

@@ -303,7 +303,8 @@ static int sa1110_target(struct cpufreq_policy *policy, unsigned int ppcr)
 
 static int __init sa1110_cpu_init(struct cpufreq_policy *policy)
 {
-	return cpufreq_generic_init(policy, sa11x0_freq_table, 0);
+	cpufreq_generic_init(policy, sa11x0_freq_table, 0);
+	return 0;
 }
 
 /* sa1110_driver needs __refdata because it must remain after init registers

drivers/cpufreq/spear-cpufreq.c

@@ -153,8 +153,9 @@ static int spear_cpufreq_target(struct cpufreq_policy *policy,
 static int spear_cpufreq_init(struct cpufreq_policy *policy)
 {
 	policy->clk = spear_cpufreq.clk;
-	return cpufreq_generic_init(policy, spear_cpufreq.freq_tbl,
+	cpufreq_generic_init(policy, spear_cpufreq.freq_tbl,
 			spear_cpufreq.transition_latency);
+	return 0;
 }
 
 static struct cpufreq_driver spear_cpufreq_driver = {

drivers/cpufreq/tegra20-cpufreq.c

@@ -118,17 +118,11 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 static int tegra_cpu_init(struct cpufreq_policy *policy)
 {
 	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
-	int ret;
 
 	clk_prepare_enable(cpufreq->cpu_clk);
 
 	/* FIXME: what's the actual transition time? */
-	ret = cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	if (ret) {
-		clk_disable_unprepare(cpufreq->cpu_clk);
-		return ret;
-	}
-
+	cpufreq_generic_init(policy, freq_table, 300 * 1000);
 	policy->clk = cpufreq->cpu_clk;
 	policy->suspend_freq = freq_table[0].frequency;
 	return 0;

drivers/cpuidle/governor.c

@@ -110,7 +110,7 @@ int cpuidle_governor_latency_req(unsigned int cpu)
 {
 	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	struct device *device = get_cpu_device(cpu);
-	int device_req = dev_pm_qos_raw_read_value(device);
+	int device_req = dev_pm_qos_raw_resume_latency(device);
 
 	return device_req < global_req ? device_req : global_req;
 }

drivers/powercap/Kconfig

@@ -16,14 +16,17 @@ menuconfig POWERCAP
 
 if POWERCAP
 # Client driver configurations go here.
+config INTEL_RAPL_CORE
+	tristate
+
 config INTEL_RAPL
-	tristate "Intel RAPL Support"
+	tristate "Intel RAPL Support via MSR Interface"
 	depends on X86 && IOSF_MBI
-	default n
+	select INTEL_RAPL_CORE
 	---help---
 	  This enables support for the Intel Running Average Power Limit (RAPL)
-	  technology which allows power limits to be enforced and monitored on
-	  modern Intel processors (Sandy Bridge and later).
+	  technology via MSR interface, which allows power limits to be enforced
+	  and monitored on modern Intel processors (Sandy Bridge and later).
 
 	  In RAPL, the platform level settings are divided into domains for
 	  fine grained control. These domains include processor package, DRAM

drivers/powercap/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
-obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o
+obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o
 obj-$(CONFIG_IDLE_INJECT) += idle_inject.o

drivers/powercap/intel_rapl_msr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Running Average Power Limit (RAPL) Driver via MSR interface
+ * Copyright (c) 2019, Intel Corporation.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/log2.h>
+#include <linux/bitmap.h>
+#include <linux/delay.h>
+#include <linux/sysfs.h>
+#include <linux/cpu.h>
+#include <linux/powercap.h>
+#include <linux/suspend.h>
+#include <linux/intel_rapl.h>
+#include <linux/processor.h>
+#include <linux/platform_device.h>
+
+#include <asm/iosf_mbi.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+
+/* Local defines */
+#define MSR_PLATFORM_POWER_LIMIT	0x0000065C
+
+/* private data for RAPL MSR Interface */
+static struct rapl_if_priv rapl_msr_priv = {
+	.reg_unit = MSR_RAPL_POWER_UNIT,
+	.regs[RAPL_DOMAIN_PACKAGE] = {
+		MSR_PKG_POWER_LIMIT, MSR_PKG_ENERGY_STATUS, MSR_PKG_PERF_STATUS, 0, MSR_PKG_POWER_INFO },
+	.regs[RAPL_DOMAIN_PP0] = {
+		MSR_PP0_POWER_LIMIT, MSR_PP0_ENERGY_STATUS, 0, MSR_PP0_POLICY, 0 },
+	.regs[RAPL_DOMAIN_PP1] = {
+		MSR_PP1_POWER_LIMIT, MSR_PP1_ENERGY_STATUS, 0, MSR_PP1_POLICY, 0 },
+	.regs[RAPL_DOMAIN_DRAM] = {
+		MSR_DRAM_POWER_LIMIT, MSR_DRAM_ENERGY_STATUS, MSR_DRAM_PERF_STATUS, 0, MSR_DRAM_POWER_INFO },
+	.regs[RAPL_DOMAIN_PLATFORM] = {
+		MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0},
+	.limits[RAPL_DOMAIN_PACKAGE] = 2,
+};
+
+/* Handles CPU hotplug on multi-socket systems.
+ * If a CPU goes online as the first CPU of the physical package
+ * we add the RAPL package to the system. Similarly, when the last
+ * CPU of the package is removed, we remove the RAPL package and its
+ * associated domains. Cooling devices are handled accordingly at
+ * per-domain level.
+ */
+static int rapl_cpu_online(unsigned int cpu)
+{
+	struct rapl_package *rp;
+
+	rp = rapl_find_package_domain(cpu, &rapl_msr_priv);
+	if (!rp) {
+		rp = rapl_add_package(cpu, &rapl_msr_priv);
+		if (IS_ERR(rp))
+			return PTR_ERR(rp);
+	}
+	cpumask_set_cpu(cpu, &rp->cpumask);
+	return 0;
+}
+
+static int rapl_cpu_down_prep(unsigned int cpu)
+{
+	struct rapl_package *rp;
+	int lead_cpu;
+
+	rp = rapl_find_package_domain(cpu, &rapl_msr_priv);
+	if (!rp)
+		return 0;
+
+	cpumask_clear_cpu(cpu, &rp->cpumask);
+	lead_cpu = cpumask_first(&rp->cpumask);
+	if (lead_cpu >= nr_cpu_ids)
+		rapl_remove_package(rp);
+	else if (rp->lead_cpu == cpu)
+		rp->lead_cpu = lead_cpu;
+	return 0;
+}
+
+static int rapl_msr_read_raw(int cpu, struct reg_action *ra)
+{
+	u32 msr = (u32)ra->reg;
+
+	if (rdmsrl_safe_on_cpu(cpu, msr, &ra->value)) {
+		pr_debug("failed to read msr 0x%x on cpu %d\n", msr, cpu);
+		return -EIO;
+	}
+	ra->value &= ra->mask;
+	return 0;
+}
+
+static void rapl_msr_update_func(void *info)
+{
+	struct reg_action *ra = info;
+	u32 msr = (u32)ra->reg;
+	u64 val;
+
+	ra->err = rdmsrl_safe(msr, &val);
+	if (ra->err)
+		return;
+
+	val &= ~ra->mask;
+	val |= ra->value;
+
+	ra->err = wrmsrl_safe(msr, val);
+}
+
+static int rapl_msr_write_raw(int cpu, struct reg_action *ra)
+{
+	int ret;
+
+	ret = smp_call_function_single(cpu, rapl_msr_update_func, ra, 1);
+	if (WARN_ON_ONCE(ret))
+		return ret;
+
+	return ra->err;
+}
+
+static int rapl_msr_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	rapl_msr_priv.read_raw = rapl_msr_read_raw;
+	rapl_msr_priv.write_raw = rapl_msr_write_raw;
+
+	rapl_msr_priv.control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
+	if (IS_ERR(rapl_msr_priv.control_type)) {
+		pr_debug("failed to register powercap control_type.\n");
+		return PTR_ERR(rapl_msr_priv.control_type);
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online",
+				rapl_cpu_online, rapl_cpu_down_prep);
+	if (ret < 0)
+		goto out;
+	rapl_msr_priv.pcap_rapl_online = ret;
+
+	/* Don't bail out if PSys is not supported */
+	rapl_add_platform_domain(&rapl_msr_priv);
+
+	return 0;
+
+out:
+	if (ret)
+		powercap_unregister_control_type(rapl_msr_priv.control_type);
+	return ret;
+}
+
+static int rapl_msr_remove(struct platform_device *pdev)
+{
+	cpuhp_remove_state(rapl_msr_priv.pcap_rapl_online);
+	rapl_remove_platform_domain(&rapl_msr_priv);
+	powercap_unregister_control_type(rapl_msr_priv.control_type);
+	return 0;
+}
+
+static const struct platform_device_id rapl_msr_ids[] = {
+	{ .name = "intel_rapl_msr", },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, rapl_msr_ids);
+
+static struct platform_driver intel_rapl_msr_driver = {
+	.probe = rapl_msr_probe,
+	.remove = rapl_msr_remove,
+	.id_table = rapl_msr_ids,
+	.driver = {
+		.name = "intel_rapl_msr",
+	},
+};
+
+module_platform_driver(intel_rapl_msr_driver);
+
+MODULE_DESCRIPTION("Driver for Intel RAPL (Running Average Power Limit) control via MSR interface");
+MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>");
+MODULE_LICENSE("GPL v2");

drivers/thermal/intel/int340x_thermal/Kconfig

@@ -40,4 +40,10 @@ config INT3406_THERMAL
 	  brightness in order to address a thermal condition or to reduce
 	  power consumed by display device.
 
+config PROC_THERMAL_MMIO_RAPL
+	bool
+	depends on 64BIT
+	depends on POWERCAP
+	select INTEL_RAPL_CORE
+	default y
 endif

drivers/thermal/intel/int340x_thermal/processor_thermal_device.c

@@ -11,6 +11,8 @@
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
 #include <linux/thermal.h>
+#include <linux/cpuhotplug.h>
+#include <linux/intel_rapl.h>
 #include "int340x_thermal_zone.h"
 #include "../intel_soc_dts_iosf.h"
 
@@ -37,6 +39,8 @@
 /* GeminiLake thermal reporting device */
 #define PCI_DEVICE_ID_PROC_GLK_THERMAL	0x318C
 
+#define DRV_NAME "proc_thermal"
+
 struct power_config {
 	u32	index;
 	u32	min_uw;
@@ -52,6 +56,7 @@ struct proc_thermal_device {
 	struct power_config power_limits[2];
 	struct int34x_thermal_zone *int340x_zone;
 	struct intel_soc_dts_sensors *soc_dts;
+	void __iomem *mmio_base;
 };
 
 enum proc_thermal_emum_mode_type {
@@ -60,6 +65,12 @@ enum proc_thermal_emum_mode_type {
 	PROC_THERMAL_PLATFORM_DEV
 };
 
+struct rapl_mmio_regs {
+	u64 reg_unit;
+	u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
+	int limits[RAPL_DOMAIN_MAX];
+};
+
 /*
  * We can have only one type of enumeration, PCI or Platform,
  * not both. So we don't need instance specific data.
@@ -367,8 +378,151 @@ static irqreturn_t proc_thermal_pci_msi_irq(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_PROC_THERMAL_MMIO_RAPL
+
+#define MCHBAR 0
+
+/* RAPL Support via MMIO interface */
+static struct rapl_if_priv rapl_mmio_priv;
+
+static int rapl_mmio_cpu_online(unsigned int cpu)
+{
+	struct rapl_package *rp;
+
+	/* mmio rapl supports package 0 only for now */
+	if (topology_physical_package_id(cpu))
+		return 0;
+
+	rp = rapl_find_package_domain(cpu, &rapl_mmio_priv);
+	if (!rp) {
+		rp = rapl_add_package(cpu, &rapl_mmio_priv);
+		if (IS_ERR(rp))
+			return PTR_ERR(rp);
+	}
+	cpumask_set_cpu(cpu, &rp->cpumask);
+	return 0;
+}
+
+static int rapl_mmio_cpu_down_prep(unsigned int cpu)
+{
+	struct rapl_package *rp;
+	int lead_cpu;
+
+	rp = rapl_find_package_domain(cpu, &rapl_mmio_priv);
+	if (!rp)
+		return 0;
+
+	cpumask_clear_cpu(cpu, &rp->cpumask);
+	lead_cpu = cpumask_first(&rp->cpumask);
+	if (lead_cpu >= nr_cpu_ids)
+		rapl_remove_package(rp);
+	else if (rp->lead_cpu == cpu)
+		rp->lead_cpu = lead_cpu;
+	return 0;
+}
+
+static int rapl_mmio_read_raw(int cpu, struct reg_action *ra)
+{
+	if (!ra->reg)
+		return -EINVAL;
+
+	ra->value = readq((void __iomem *)ra->reg);
+	ra->value &= ra->mask;
+	return 0;
+}
+
+static int rapl_mmio_write_raw(int cpu, struct reg_action *ra)
+{
+	u64 val;
+
+	if (!ra->reg)
+		return -EINVAL;
+
+	val = readq((void __iomem *)ra->reg);
+	val &= ~ra->mask;
+	val |= ra->value;
+	writeq(val, (void __iomem *)ra->reg);
+	return 0;
+}
+
+static int proc_thermal_rapl_add(struct pci_dev *pdev,
+				 struct proc_thermal_device *proc_priv,
+				 struct rapl_mmio_regs *rapl_regs)
+{
+	enum rapl_domain_reg_id reg;
+	enum rapl_domain_type domain;
+	int ret;
+
+	if (!rapl_regs)
+		return 0;
+
+	ret = pcim_iomap_regions(pdev, 1 << MCHBAR, DRV_NAME);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot reserve PCI memory region\n");
+		return -ENOMEM;
+	}
+
+	proc_priv->mmio_base = pcim_iomap_table(pdev)[MCHBAR];
+
+	for (domain = RAPL_DOMAIN_PACKAGE; domain < RAPL_DOMAIN_MAX; domain++) {
+		for (reg = RAPL_DOMAIN_REG_LIMIT; reg < RAPL_DOMAIN_REG_MAX; reg++)
+			if (rapl_regs->regs[domain][reg])
+				rapl_mmio_priv.regs[domain][reg] =
+						(u64)proc_priv->mmio_base +
+						rapl_regs->regs[domain][reg];
+		rapl_mmio_priv.limits[domain] = rapl_regs->limits[domain];
+	}
+	rapl_mmio_priv.reg_unit = (u64)proc_priv->mmio_base + rapl_regs->reg_unit;
+
+	rapl_mmio_priv.read_raw = rapl_mmio_read_raw;
+	rapl_mmio_priv.write_raw = rapl_mmio_write_raw;
+
+	rapl_mmio_priv.control_type = powercap_register_control_type(NULL, "intel-rapl-mmio", NULL);
+	if (IS_ERR(rapl_mmio_priv.control_type)) {
+		pr_debug("failed to register powercap control_type.\n");
+		return PTR_ERR(rapl_mmio_priv.control_type);
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online",
+				rapl_mmio_cpu_online, rapl_mmio_cpu_down_prep);
+	if (ret < 0) {
+		powercap_unregister_control_type(rapl_mmio_priv.control_type);
+		return ret;
+	}
+	rapl_mmio_priv.pcap_rapl_online = ret;
+
+	return 0;
+}
+
+static void proc_thermal_rapl_remove(void)
+{
+	cpuhp_remove_state(rapl_mmio_priv.pcap_rapl_online);
+	powercap_unregister_control_type(rapl_mmio_priv.control_type);
+}
+
+static const struct rapl_mmio_regs rapl_mmio_hsw = {
+	.reg_unit = 0x5938,
+	.regs[RAPL_DOMAIN_PACKAGE] = { 0x59a0, 0x593c, 0x58f0, 0, 0x5930},
+	.regs[RAPL_DOMAIN_DRAM] = { 0x58e0, 0x58e8, 0x58ec, 0, 0},
+	.limits[RAPL_DOMAIN_PACKAGE] = 2,
+	.limits[RAPL_DOMAIN_DRAM] = 2,
+};
+
+#else
+
+static int proc_thermal_rapl_add(struct pci_dev *pdev,
+				 struct proc_thermal_device *proc_priv,
+				 struct rapl_mmio_regs *rapl_regs)
+{
+	return 0;
+}
+static void proc_thermal_rapl_remove(void) {}
+static const struct rapl_mmio_regs rapl_mmio_hsw;
+
+#endif /* CONFIG_MMIO_RAPL */
+
 static int  proc_thermal_pci_probe(struct pci_dev *pdev,
-				   const struct pci_device_id *unused)
+				   const struct pci_device_id *id)
 {
 	struct proc_thermal_device *proc_priv;
 	int ret;
@@ -378,15 +532,21 @@ static int  proc_thermal_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
-	ret = pci_enable_device(pdev);
+	ret = pcim_enable_device(pdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "error: could not enable device\n");
 		return ret;
 	}
 
 	ret = proc_thermal_add(&pdev->dev, &proc_priv);
+	if (ret)
+		return ret;
+
+	ret = proc_thermal_rapl_add(pdev, proc_priv,
+				(struct rapl_mmio_regs *)id->driver_data);
 	if (ret) {
-		pci_disable_device(pdev);
+		dev_err(&pdev->dev, "failed to add RAPL MMIO interface\n");
+		proc_thermal_remove(proc_priv);
 		return ret;
 	}
 
@@ -439,8 +599,8 @@ static void  proc_thermal_pci_remove(struct pci_dev *pdev)
 			pci_disable_msi(pdev);
 		}
 	}
+	proc_thermal_rapl_remove();
 	proc_thermal_remove(proc_priv);
-	pci_disable_device(pdev);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -462,7 +622,8 @@ static SIMPLE_DEV_PM_OPS(proc_thermal_pm, NULL, proc_thermal_resume);
 static const struct pci_device_id proc_thermal_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BDW_THERMAL)},
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_HSB_THERMAL)},
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_SKL_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_SKL_THERMAL),
+		.driver_data = (kernel_ulong_t)&rapl_mmio_hsw, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BSW_THERMAL)},
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXT0_THERMAL)},
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXT1_THERMAL)},
@@ -477,7 +638,7 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
 MODULE_DEVICE_TABLE(pci, proc_thermal_pci_ids);
 
 static struct pci_driver proc_thermal_pci_driver = {
-	.name		= "proc_thermal",
+	.name		= DRV_NAME,
 	.probe		= proc_thermal_pci_probe,
 	.remove		= proc_thermal_pci_remove,
 	.id_table	= proc_thermal_pci_ids,

include/linux/cpufreq.h

@@ -47,11 +47,6 @@ struct cpufreq_cpuinfo {
 	unsigned int		transition_latency;
 };
 
-struct cpufreq_user_policy {
-	unsigned int		min;    /* in kHz */
-	unsigned int		max;    /* in kHz */
-};
-
 struct cpufreq_policy {
 	/* CPUs sharing clock, require sw coordination */
 	cpumask_var_t		cpus;	/* Online CPUs only */
@@ -81,7 +76,8 @@ struct cpufreq_policy {
 	struct work_struct	update; /* if update_policy() needs to be
 					 * called, but you're in IRQ context */
 
-	struct cpufreq_user_policy user_policy;
+	struct dev_pm_qos_request *min_freq_req;
+	struct dev_pm_qos_request *max_freq_req;
 	struct cpufreq_frequency_table	*freq_table;
 	enum cpufreq_table_sorting freq_table_sorted;
 
@@ -144,6 +140,9 @@ struct cpufreq_policy {
 
 	/* Pointer to the cooling device if used for thermal mitigation */
 	struct thermal_cooling_device *cdev;
+
+	struct notifier_block nb_min;
+	struct notifier_block nb_max;
 };
 
 struct cpufreq_freqs {
@@ -201,6 +200,7 @@ void cpufreq_cpu_release(struct cpufreq_policy *policy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
 int cpufreq_set_policy(struct cpufreq_policy *policy,
 		       struct cpufreq_policy *new_policy);
+void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
@@ -992,7 +992,7 @@ extern struct freq_attr *cpufreq_generic_attr[];
 int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy);
 
 unsigned int cpufreq_generic_get(unsigned int cpu);
-int cpufreq_generic_init(struct cpufreq_policy *policy,
+void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
 #endif /* _LINUX_CPUFREQ_H */

include/linux/intel_rapl.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Data types and headers for RAPL support
+ *
+ *  Copyright (C) 2019  Intel Corporation.
+ *
+ *  Author: Zhang Rui <rui.zhang@intel.com>
+ */
+
+#ifndef __INTEL_RAPL_H__
+#define __INTEL_RAPL_H__
+
+#include <linux/types.h>
+#include <linux/powercap.h>
+#include <linux/cpuhotplug.h>
+
+enum rapl_domain_type {
+	RAPL_DOMAIN_PACKAGE,	/* entire package/socket */
+	RAPL_DOMAIN_PP0,	/* core power plane */
+	RAPL_DOMAIN_PP1,	/* graphics uncore */
+	RAPL_DOMAIN_DRAM,	/* DRAM control_type */
+	RAPL_DOMAIN_PLATFORM,	/* PSys control_type */
+	RAPL_DOMAIN_MAX,
+};
+
+enum rapl_domain_reg_id {
+	RAPL_DOMAIN_REG_LIMIT,
+	RAPL_DOMAIN_REG_STATUS,
+	RAPL_DOMAIN_REG_PERF,
+	RAPL_DOMAIN_REG_POLICY,
+	RAPL_DOMAIN_REG_INFO,
+	RAPL_DOMAIN_REG_MAX,
+};
+
+struct rapl_package;
+
+enum rapl_primitives {
+	ENERGY_COUNTER,
+	POWER_LIMIT1,
+	POWER_LIMIT2,
+	FW_LOCK,
+
+	PL1_ENABLE,		/* power limit 1, aka long term */
+	PL1_CLAMP,		/* allow frequency to go below OS request */
+	PL2_ENABLE,		/* power limit 2, aka short term, instantaneous */
+	PL2_CLAMP,
+
+	TIME_WINDOW1,		/* long term */
+	TIME_WINDOW2,		/* short term */
+	THERMAL_SPEC_POWER,
+	MAX_POWER,
+
+	MIN_POWER,
+	MAX_TIME_WINDOW,
+	THROTTLED_TIME,
+	PRIORITY_LEVEL,
+
+	/* below are not raw primitive data */
+	AVERAGE_POWER,
+	NR_RAPL_PRIMITIVES,
+};
+
+struct rapl_domain_data {
+	u64 primitives[NR_RAPL_PRIMITIVES];
+	unsigned long timestamp;
+};
+
+#define NR_POWER_LIMITS (2)
+struct rapl_power_limit {
+	struct powercap_zone_constraint *constraint;
+	int prim_id;		/* primitive ID used to enable */
+	struct rapl_domain *domain;
+	const char *name;
+	u64 last_power_limit;
+};
+
+struct rapl_package;
+
+struct rapl_domain {
+	const char *name;
+	enum rapl_domain_type id;
+	u64 regs[RAPL_DOMAIN_REG_MAX];
+	struct powercap_zone power_zone;
+	struct rapl_domain_data rdd;
+	struct rapl_power_limit rpl[NR_POWER_LIMITS];
+	u64 attr_map;		/* track capabilities */
+	unsigned int state;
+	unsigned int domain_energy_unit;
+	struct rapl_package *rp;
+};
+
+struct reg_action {
+	u64 reg;
+	u64 mask;
+	u64 value;
+	int err;
+};
+
+/**
+ * struct rapl_if_priv: private data for different RAPL interfaces
+ * @control_type:		Each RAPL interface must have its own powercap
+ *				control type.
+ * @platform_rapl_domain:	Optional. Some RAPL interface may have platform
+ *				level RAPL control.
+ * @pcap_rapl_online:		CPU hotplug state for each RAPL interface.
+ * @reg_unit:			Register for getting energy/power/time unit.
+ * @regs:			Register sets for different RAPL Domains.
+ * @limits:			Number of power limits supported by each domain.
+ * @read_raw:			Callback for reading RAPL interface specific
+ *				registers.
+ * @write_raw:			Callback for writing RAPL interface specific
+ *				registers.
+ */
+struct rapl_if_priv {
+	struct powercap_control_type *control_type;
+	struct rapl_domain *platform_rapl_domain;
+	enum cpuhp_state pcap_rapl_online;
+	u64 reg_unit;
+	u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
+	int limits[RAPL_DOMAIN_MAX];
+	int (*read_raw)(int cpu, struct reg_action *ra);
+	int (*write_raw)(int cpu, struct reg_action *ra);
+};
+
+/* maximum rapl package domain name: package-%d-die-%d */
+#define PACKAGE_DOMAIN_NAME_LENGTH 30
+
+struct rapl_package {
+	unsigned int id;	/* logical die id, equals physical 1-die systems */
+	unsigned int nr_domains;
+	unsigned long domain_map;	/* bit map of active domains */
+	unsigned int power_unit;
+	unsigned int energy_unit;
+	unsigned int time_unit;
+	struct rapl_domain *domains;	/* array of domains, sized at runtime */
+	struct powercap_zone *power_zone;	/* keep track of parent zone */
+	unsigned long power_limit_irq;	/* keep track of package power limit
+					 * notify interrupt enable status.
+					 */
+	struct list_head plist;
+	int lead_cpu;		/* one active cpu per package for access */
+	/* Track active cpus */
+	struct cpumask cpumask;
+	char name[PACKAGE_DOMAIN_NAME_LENGTH];
+	struct rapl_if_priv *priv;
+};
+
+struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv);
+struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv);
+void rapl_remove_package(struct rapl_package *rp);
+
+int rapl_add_platform_domain(struct rapl_if_priv *priv);
+void rapl_remove_platform_domain(struct rapl_if_priv *priv);
+
+#endif /* __INTEL_RAPL_H__ */

include/linux/pm_qos.h

@@ -40,6 +40,8 @@ enum pm_qos_flags_status {
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	PM_QOS_LATENCY_ANY
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS	PM_QOS_LATENCY_ANY_NS
 #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE	0
+#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE	0
+#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE	(-1)
 #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT	(-1)
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
@@ -58,6 +60,8 @@ struct pm_qos_flags_request {
 enum dev_pm_qos_req_type {
 	DEV_PM_QOS_RESUME_LATENCY = 1,
 	DEV_PM_QOS_LATENCY_TOLERANCE,
+	DEV_PM_QOS_MIN_FREQUENCY,
+	DEV_PM_QOS_MAX_FREQUENCY,
 	DEV_PM_QOS_FLAGS,
 };
 
@@ -99,10 +103,14 @@ struct pm_qos_flags {
 struct dev_pm_qos {
 	struct pm_qos_constraints resume_latency;
 	struct pm_qos_constraints latency_tolerance;
+	struct pm_qos_constraints min_frequency;
+	struct pm_qos_constraints max_frequency;
 	struct pm_qos_flags flags;
 	struct dev_pm_qos_request *resume_latency_req;
 	struct dev_pm_qos_request *latency_tolerance_req;
 	struct dev_pm_qos_request *flags_req;
+	struct dev_pm_qos_request *min_frequency_req;
+	struct dev_pm_qos_request *max_frequency_req;
 };
 
 /* Action requested to pm_qos_update_target */
@@ -139,16 +147,18 @@ s32 pm_qos_read_value(struct pm_qos_constraints *c);
 #ifdef CONFIG_PM
 enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask);
 enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask);
-s32 __dev_pm_qos_read_value(struct device *dev);
-s32 dev_pm_qos_read_value(struct device *dev);
+s32 __dev_pm_qos_resume_latency(struct device *dev);
+s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type);
 int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 			   enum dev_pm_qos_req_type type, s32 value);
 int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value);
 int dev_pm_qos_remove_request(struct dev_pm_qos_request *req);
 int dev_pm_qos_add_notifier(struct device *dev,
-			    struct notifier_block *notifier);
+			    struct notifier_block *notifier,
+			    enum dev_pm_qos_req_type type);
 int dev_pm_qos_remove_notifier(struct device *dev,
-			       struct notifier_block *notifier);
+			       struct notifier_block *notifier,
+			       enum dev_pm_qos_req_type type);
 void dev_pm_qos_constraints_init(struct device *dev);
 void dev_pm_qos_constraints_destroy(struct device *dev);
 int dev_pm_qos_add_ancestor_request(struct device *dev,
@@ -174,7 +184,7 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev)
 	return dev->power.qos->flags_req->data.flr.flags;
 }
 
-static inline s32 dev_pm_qos_raw_read_value(struct device *dev)
+static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev)
 {
 	return IS_ERR_OR_NULL(dev->power.qos) ?
 		PM_QOS_RESUME_LATENCY_NO_CONSTRAINT :
@@ -187,10 +197,24 @@ static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
 static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev,
 							s32 mask)
 			{ return PM_QOS_FLAGS_UNDEFINED; }
-static inline s32 __dev_pm_qos_read_value(struct device *dev)
-			{ return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; }
-static inline s32 dev_pm_qos_read_value(struct device *dev)
+static inline s32 __dev_pm_qos_resume_latency(struct device *dev)
 			{ return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; }
+static inline s32 dev_pm_qos_read_value(struct device *dev,
+					enum dev_pm_qos_req_type type)
+{
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
 static inline int dev_pm_qos_add_request(struct device *dev,
 					 struct dev_pm_qos_request *req,
 					 enum dev_pm_qos_req_type type,
@@ -202,10 +226,12 @@ static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 static inline int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
 			{ return 0; }
 static inline int dev_pm_qos_add_notifier(struct device *dev,
-					  struct notifier_block *notifier)
+					  struct notifier_block *notifier,
+					  enum dev_pm_qos_req_type type)
 			{ return 0; }
 static inline int dev_pm_qos_remove_notifier(struct device *dev,
-					     struct notifier_block *notifier)
+					     struct notifier_block *notifier,
+					     enum dev_pm_qos_req_type type)
 			{ return 0; }
 static inline void dev_pm_qos_constraints_init(struct device *dev)
 {
@@ -241,7 +267,7 @@ static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
 	return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
 }
 static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
-static inline s32 dev_pm_qos_raw_read_value(struct device *dev)
+static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev)
 {
 	return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
 }