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
  ...

32 files changed, 989 insertions, 676 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 33c30c1e6a30..b063bc41b0a9 100644
--- a/drivers/base/power/domain.c
+++ b/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;
 }
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 3838045c9277..daa8c7689f7e 100644
--- a/drivers/base/power/domain_governor.c
+++ b/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);
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 6c91f8df1d59..6c90fd7e2ff8 100644
--- a/drivers/base/power/qos.c
+++ b/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);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 952a1e7057c7..b75335508d2c 100644
--- a/drivers/base/power/runtime.c
+++ b/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;
diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c
index 56a4ebbf00e0..f7c23fa468f0 100644
--- a/drivers/cpufreq/bmips-cpufreq.c
+++ b/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 = {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0a9f675f2af4..8dda62367816 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/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 @@ err_free_policy:
 	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;
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 3de48ae60c29..297d23cad8b5 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/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 = {
diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c
index b54fd26ea7df..4f85f3112784 100644
--- a/drivers/cpufreq/imx-cpufreq-dt.c
+++ b/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.
 	 */