Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux

Pull thermal management updates from Zhang Rui:

 - Improve thermal cpu_cooling interaction with cpufreq core.

   The cpu_cooling driver is designed to use CPU frequency scaling to
   avoid high thermal states for a platform. But it wasn't glued really
   well with cpufreq core.

   For example clipped-cpus is copied from the policy structure and its
   much better to use the policy->cpus (or related_cpus) fields directly
   as they may have got updated. Not that things were broken before this
   series, but they can be optimized a bit more.

   This series tries to improve interactions between cpufreq core and
   cpu_cooling driver and does some fixes/cleanups to the cpu_cooling
   driver. (Viresh Kumar)

 - A couple of fixes and cleanups in thermal core and imx, hisilicon,
   bcm_2835, int340x thermal drivers. (Arvind Yadav, Dan Carpenter,
   Sumeet Pawnikar, Srinivas Pandruvada, Willy WOLFF)

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux: (24 commits)
  thermal: bcm2835: fix an error code in probe()
  thermal: hisilicon: Handle return value of clk_prepare_enable
  thermal: imx: Handle return value of clk_prepare_enable
  thermal: int340x: check for sensor when PTYP is missing
  Thermal/int340x: Fix few typos and kernel-doc style
  thermal: fix source code documentation for parameters
  thermal: cpu_cooling: Replace kmalloc with kmalloc_array
  thermal: cpu_cooling: Rearrange struct cpufreq_cooling_device
  thermal: cpu_cooling: 'freq' can't be zero in cpufreq_state2power()
  thermal: cpu_cooling: don't store cpu_dev in cpufreq_cdev
  thermal: cpu_cooling: get_level() can't fail
  thermal: cpu_cooling: create structure for idle time stats
  thermal: cpu_cooling: merge frequency and power tables
  thermal: cpu_cooling: get rid of 'allowed_cpus'
  thermal: cpu_cooling: OPPs are registered for all CPUs
  thermal: cpu_cooling: store cpufreq policy
  cpufreq: create cpufreq_table_count_valid_entries()
  thermal: cpu_cooling: use cpufreq_policy to register cooling device
  thermal: cpu_cooling: get rid of a variable in cpufreq_set_cur_state()
  thermal: cpu_cooling: remove cpufreq_cooling_get_level()
  ...

18 files changed, 342 insertions, 419 deletions

diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 418042201e6d..ea6d62547b10 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -540,7 +540,7 @@ static void bL_cpufreq_ready(struct cpufreq_policy *policy)
 				     &power_coefficient);
 
 		cdev[cur_cluster] = of_cpufreq_power_cooling_register(np,
-				policy->related_cpus, power_coefficient, NULL);
+				policy, power_coefficient, NULL);
 		if (IS_ERR(cdev[cur_cluster])) {
 			dev_err(cpu_dev,
 				"running cpufreq without cooling device: %ld\n",
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index c943787d761e..fef3c2160691 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -326,7 +326,7 @@ static void cpufreq_ready(struct cpufreq_policy *policy)
 				     &power_coefficient);
 
 		priv->cdev = of_cpufreq_power_cooling_register(np,
-				policy->related_cpus, power_coefficient, NULL);
+				policy, power_coefficient, NULL);
 		if (IS_ERR(priv->cdev)) {
 			dev_err(priv->cpu_dev,
 				"running cpufreq without cooling device: %ld\n",
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index d362739a71f3..e75880eb037d 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -170,11 +170,10 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	unsigned int i = 0, count = 0, ret = -ENOMEM;
 	struct cpufreq_stats *stats;
 	unsigned int alloc_size;
-	struct cpufreq_frequency_table *pos, *table;
+	struct cpufreq_frequency_table *pos;
 
-	/* We need cpufreq table for creating stats table */
-	table = policy->freq_table;
-	if (unlikely(!table))
+	count = cpufreq_table_count_valid_entries(policy);
+	if (!count)
 		return;
 
 	/* stats already initialized */
@@ -185,10 +184,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	if (!stats)
 		return;
 
-	/* Find total allocation size */
-	cpufreq_for_each_valid_entry(pos, table)
-		count++;
-
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
 	alloc_size += count * count * sizeof(int);
@@ -205,7 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stats->max_state = count;
 
 	/* Find valid-unique entries */
-	cpufreq_for_each_valid_entry(pos, table)
+	cpufreq_for_each_valid_entry(pos, policy->freq_table)
 		if (freq_table_get_index(stats, pos->frequency) == -1)
 			stats->freq_table[i++] = pos->frequency;
 
diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c
index 3575b82210ba..4ee0431579c1 100644
--- a/drivers/cpufreq/dbx500-cpufreq.c
+++ b/drivers/cpufreq/dbx500-cpufreq.c
@@ -43,7 +43,7 @@ static int dbx500_cpufreq_exit(struct cpufreq_policy *policy)
 
 static void dbx500_cpufreq_ready(struct cpufreq_policy *policy)
 {
-	cdev = cpufreq_cooling_register(policy->cpus);
+	cdev = cpufreq_cooling_register(policy);
 	if (IS_ERR(cdev))
 		pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev));
 	else
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index fd1886faf33a..f9f00fb4bc3a 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -320,9 +320,7 @@ static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
 		of_property_read_u32(np, DYNAMIC_POWER, &capacitance);
 
 		info->cdev = of_cpufreq_power_cooling_register(np,
-						policy->related_cpus,
-						capacitance,
-						NULL);
+						policy, capacitance, NULL);
 
 		if (IS_ERR(info->cdev)) {
 			dev_err(info->cpu_dev,
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index e2ea433a5f9c..4ada55b8856e 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -278,8 +278,7 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
 	struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
 
 	if (of_find_property(np, "#cooling-cells", NULL)) {
-		cpud->cdev = of_cpufreq_cooling_register(np,
-							 policy->related_cpus);
+		cpud->cdev = of_cpufreq_cooling_register(np, policy);
 
 		if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) {
 			pr_err("cpu%d is not running as cooling device: %ld\n",
diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
index 0ecf80890c84..e6863c841662 100644
--- a/drivers/thermal/broadcom/bcm2835_thermal.c
+++ b/drivers/thermal/broadcom/bcm2835_thermal.c
@@ -245,7 +245,6 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 		 */
 		err = tz->ops->get_trip_temp(tz, 0, &trip_temp);
 		if (err < 0) {
-			err = PTR_ERR(tz);
 			dev_err(&pdev->dev,
 				"Not able to read trip_temp: %d\n",
 				err);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 69d0f430b2d1..908a8014cf76 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -49,40 +49,45 @@
  */
 
 /**
- * struct power_table - frequency to power conversion
+ * struct freq_table - frequency table along with power entries
  * @frequency:	frequency in KHz
  * @power:	power in mW
  *
  * This structure is built when the cooling device registers and helps
- * in translating frequency to power and viceversa.
+ * in translating frequency to power and vice versa.
  */
-struct power_table {
+struct freq_table {
 	u32 frequency;
 	u32 power;
 };
 
 /**
+ * struct time_in_idle - Idle time stats
+ * @time: previous reading of the absolute time that this cpu was idle
+ * @timestamp: wall time of the last invocation of get_cpu_idle_time_us()
+ */
+struct time_in_idle {
+	u64 time;
+	u64 timestamp;
+};
+
+/**
  * struct cpufreq_cooling_device - data for cooling device with cpufreq
  * @id: unique integer value corresponding to each cpufreq_cooling_device
  *	registered.
- * @cool_dev: thermal_cooling_device pointer to keep track of the
- *	registered cooling device.
+ * @last_load: load measured by the latest call to cpufreq_get_requested_power()
  * @cpufreq_state: integer value representing the current state of cpufreq
  *	cooling	devices.
  * @clipped_freq: integer value representing the absolute value of the clipped
  *	frequency.
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
- * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
+ * @freq_table: Freq table in descending order of frequencies
+ * @cdev: thermal_cooling_device pointer to keep track of the
+ *	registered cooling device.
+ * @policy: cpufreq policy.
  * @node: list_head to link all cpufreq_cooling_device together.
- * @last_load: load measured by the latest call to cpufreq_get_requested_power()
- * @time_in_idle: previous reading of the absolute time that this cpu was idle
- * @time_in_idle_timestamp: wall time of the last invocation of
- *	get_cpu_idle_time_us()
- * @dyn_power_table: array of struct power_table for frequency to power
- *	conversion, sorted in ascending order.
- * @dyn_power_table_entries: number of entries in the @dyn_power_table array
- * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered
+ * @idle_time: idle time stats
  * @plat_get_static_power: callback to calculate the static power
  *
  * This structure is required for keeping information of each registered
@@ -90,81 +95,45 @@ struct power_table {
  */
 struct cpufreq_cooling_device {
 	int id;
-	struct thermal_cooling_device *cool_dev;
+	u32 last_load;
 	unsigned int cpufreq_state;
 	unsigned int clipped_freq;
 	unsigned int max_level;
-	unsigned int *freq_table;	/* In descending order */
-	struct cpumask allowed_cpus;
+	struct freq_table *freq_table;	/* In descending order */
+	struct thermal_cooling_device *cdev;
+	struct cpufreq_policy *policy;
 	struct list_head node;
-	u32 last_load;
-	u64 *time_in_idle;
-	u64 *time_in_idle_timestamp;
-	struct power_table *dyn_power_table;
-	int dyn_power_table_entries;
-	struct device *cpu_dev;
+	struct time_in_idle *idle_time;
 	get_static_t plat_get_static_power;
 };
-static DEFINE_IDA(cpufreq_ida);
 
+static DEFINE_IDA(cpufreq_ida);
 static DEFINE_MUTEX(cooling_list_lock);
-static LIST_HEAD(cpufreq_dev_list);
+static LIST_HEAD(cpufreq_cdev_list);
 
 /* Below code defines functions to be used for cpufreq as cooling device */
 
 /**
  * get_level: Find the level for a particular frequency
- * @cpufreq_dev: cpufreq_dev for which the property is required
+ * @cpufreq_cdev: cpufreq_cdev for which the property is required
  * @freq: Frequency
  *
- * Return: level on success, THERMAL_CSTATE_INVALID on error.
+ * Return: level corresponding to the frequency.
  */
-static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev,
+static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 			       unsigned int freq)
 {
+	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 	unsigned long level;
 
-	for (level = 0; level <= cpufreq_dev->max_level; level++) {
-		if (freq == cpufreq_dev->freq_table[level])
-			return level;
-
-		if (freq > cpufreq_dev->freq_table[level])
+	for (level = 1; level <= cpufreq_cdev->max_level; level++)
+		if (freq > freq_table[level].frequency)
 			break;
-	}
 
-	return THERMAL_CSTATE_INVALID;
+	return level - 1;
 }
 
 /**
- * cpufreq_cooling_get_level - for a given cpu, return the cooling level.
- * @cpu: cpu for which the level is required
- * @freq: the frequency of interest
- *
- * This function will match the cooling level corresponding to the
- * requested @freq and return it.
- *
- * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID
- * otherwise.
- */
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
-{
-	struct cpufreq_cooling_device *cpufreq_dev;
-
-	mutex_lock(&cooling_list_lock);
-	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-		if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
-			mutex_unlock(&cooling_list_lock);
-			return get_level(cpufreq_dev, freq);
-		}
-	}
-	mutex_unlock(&cooling_list_lock);
-
-	pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu);
-	return THERMAL_CSTATE_INVALID;
-}
-EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
-
-/**
  * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
  * @nb:	struct notifier_block * with callback info.
  * @event: value showing cpufreq event for which this function invoked.
@@ -181,14 +150,18 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 {
 	struct cpufreq_policy *policy = data;
 	unsigned long clipped_freq;
-	struct cpufreq_cooling_device *cpufreq_dev;
+	struct cpufreq_cooling_device *cpufreq_cdev;
 
 	if (event != CPUFREQ_ADJUST)
 		return NOTIFY_DONE;
 
 	mutex_lock(&cooling_list_lock);
-	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-		if (!cpumask_test_cpu(policy->cpu, &cpufreq_dev->allowed_cpus))
+	list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) {
+		/*
+		 * A new copy of the policy is sent to the notifier and can't
+		 * compare that directly.
+		 */
+		if (policy->cpu != cpufreq_cdev->policy->cpu)
 			continue;
 
 		/*
@@ -202,7 +175,7 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 		 * But, if clipped_freq is greater than policy->max, we don't
 		 * need to do anything.
 		 */
-		clipped_freq = cpufreq_dev->clipped_freq;
+		clipped_freq = cpufreq_cdev->clipped_freq;
 
 		if (policy->max > clipped_freq)
 			cpufreq_verify_within_limits(policy, 0, clipped_freq);
@@ -214,63 +187,63 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 }
 
 /**
- * build_dyn_power_table() - create a dynamic power to frequency table
- * @cpufreq_device:	the cpufreq cooling device in which to store the table
+ * update_freq_table() - Update the freq table with power numbers
+ * @cpufreq_cdev:	the cpufreq cooling device in which to update the table
  * @capacitance: dynamic power coefficient for these cpus
  *
- * Build a dynamic power to frequency table for this cpu and store it
- * in @cpufreq_device.  This table will be used in cpu_power_to_freq() and
- * cpu_freq_to_power() to convert between power and frequency
- * efficiently.  Power is stored in mW, frequency in KHz.  The
- * resulting table is in ascending order.
+ * Update the freq table with power numbers.  This table will be used in
+ * cpu_power_to_freq() and cpu_freq_to_power() to convert between power and
+ * frequency efficiently.  Power is stored in mW, frequency in KHz.  The
+ * resulting table is in descending order.
  *
  * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
- * -ENOMEM if we run out of memory or -EAGAIN if an OPP was
- * added/enabled while the function was executing.
+ * or -ENOMEM if we run out of memory.
  */
-static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
-				 u32 capacitance)
+static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev,
+			     u32 capacitance)
 {
-	struct power_table *power_table;
+	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 	struct dev_pm_opp *opp;
 	struct device *dev = NULL;
-	int num_opps = 0, cpu, i, ret = 0;
-	unsigned long freq;
-
-	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
-		dev = get_cpu_device(cpu);
-		if (!dev) {
-			dev_warn(&cpufreq_device->cool_dev->device,
-				 "No cpu device for cpu %d\n", cpu);
-			continue;
-		}
+	int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i;
 
-		num_opps = dev_pm_opp_get_opp_count(dev);
-		if (num_opps > 0)
-			break;
-		else if (num_opps < 0)
-			return num_opps;
+	dev = get_cpu_device(cpu);
+	if (unlikely(!dev)) {
+		dev_warn(&cpufreq_cdev->cdev->device,
+			 "No cpu device for cpu %d\n", cpu);
+		return -ENODEV;
 	}
 
-	if (num_opps == 0)
-		return -EINVAL;
+	num_opps = dev_pm_opp_get_opp_count(dev);
+	if (num_opps < 0)
+		return num_opps;
 
-	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
-	if (!power_table)
-		return -ENOMEM;
+	/*
+	 * The cpufreq table is also built from the OPP table and so the count
+	 * should match.
+	 */
+	if (num_opps != cpufreq_cdev->max_level + 1) {
+		dev_warn(dev, "Number of OPPs not matching with max_levels\n");
+		return -EINVAL;
+	}
 
-	for (freq = 0, i = 0;
-	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
-	     freq++, i++) {
-		u32 freq_mhz, voltage_mv;
+	for (i = 0; i <= cpufreq_cdev->max_level; i++) {
+		unsigned long freq = freq_table[i].frequency * 1000;
+		u32 freq_mhz = freq_table[i].frequency / 1000;
 		u64 power;
+		u32 voltage_mv;
 
-		if (i >= num_opps) {
-			ret = -EAGAIN;
-			goto free_power_table;
+		/*
+		 * Find ceil frequency as 'freq' may be slightly lower than OPP
+		 * freq due to truncation while converting to kHz.
+		 */
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+		if (IS_ERR(opp)) {
+			dev_err(dev, "failed to get opp for %lu frequency\n",
+				freq);
+			return -EINVAL;
 		}
 
-		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
 		dev_pm_opp_put(opp);
 
@@ -281,89 +254,73 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv;
 		do_div(power, 1000000000);
 
-		/* frequency is stored in power_table in KHz */
-		power_table[i].frequency = freq / 1000;
-
 		/* power is stored in mW */
-		power_table[i].power = power;
+		freq_table[i].power = power;
 	}
 
-	if (i != num_opps) {
-		ret = PTR_ERR(opp);
-		goto free_power_table;
-	}
-
-	cpufreq_device->cpu_dev = dev;
-	cpufreq_device->dyn_power_table = power_table;
-	cpufreq_device->dyn_power_table_entries = i;
-
 	return 0;
-
-free_power_table:
-	kfree(power_table);
-
-	return ret;
 }
 
-static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device,
+static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 freq)
 {
 	int i;
-	struct power_table *pt = cpufreq_device->dyn_power_table;
+	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
-		if (freq < pt[i].frequency)
+	for (i = 1; i <= cpufreq_cdev->max_level; i++)
+		if (freq > freq_table[i].frequency)
 			break;
 
-	return pt[i - 1].power;
+	return freq_table[i - 1].power;
 }
 
-static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
+static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 power)
 {
 	int i;
-	struct power_table *pt = cpufreq_device->dyn_power_table;
+	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
-		if (power < pt[i].power)
+	for (i = 1; i <= cpufreq_cdev->max_level; i++)
+		if (power > freq_table[i].power)
 			break;
 
-	return pt[i - 1].frequency;
+	return freq_table[i - 1].frequency;
 }
 
 /**
  * get_load() - get load for a cpu since last updated
- * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
+ * @cpufreq_cdev:	&struct cpufreq_cooling_device for this cpu
  * @cpu:	cpu number
- * @cpu_idx:	index of the cpu in cpufreq_device->allowed_cpus
+ * @cpu_idx:	index of the cpu in time_in_idle*
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
-static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu,
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
 		    int cpu_idx)
 {
 	u32 load;
 	u64 now, now_idle, delta_time, delta_idle;
+	struct time_in_idle *idle_time = &cpufreq_cdev->idle_time[cpu_idx];
 
 	now_idle = get_cpu_idle_time(cpu, &now, 0);
-	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx];
-	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx];
+	delta_idle = now_idle - idle_time->time;
+	delta_time = now - idle_time->timestamp;
 
 	if (delta_time <= delta_idle)
 		load = 0;
 	else
 		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
 
-	cpufreq_device->time_in_idle[cpu_idx] = now_idle;
-	cpufreq_device->time_in_idle_timestamp[cpu_idx] = now;
+	idle_time->time = now_idle;
+	idle_time->timestamp = now;
 
 	return load;
 }
 
 /**
  * get_static_power() - calculate the static power consumed by the cpus
- * @cpufreq_device:	struct &cpufreq_cooling_device for this cpu cdev
+ * @cpufreq_cdev:	struct &cpufreq_cooling_device for this cpu cdev
  * @tz:		thermal zone device in which we're operating
  * @freq:	frequency in KHz
  * @power:	pointer in which to store the calculated static power
@@ -376,26 +333,28 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu,
  *
  * Return: 0 on success, -E* on failure.
  */
-static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
+static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev,
 			    struct thermal_zone_device *tz, unsigned long freq,
 			    u32 *power)
 {
 	struct dev_pm_opp *opp;
 	unsigned long voltage;
-	struct cpumask *cpumask = &cpufreq_device->allowed_cpus;
+	struct cpufreq_policy *policy = cpufreq_cdev->policy;
+	struct cpumask *cpumask = policy->related_cpus;
 	unsigned long freq_hz = freq * 1000;
+	struct device *dev;
 
-	if (!cpufreq_device->plat_get_static_power ||
-	    !cpufreq_device->cpu_dev) {
+	if (!cpufreq_cdev->plat_get_static_power) {
 		*power = 0;
 		return 0;
 	}
 
-	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
-					 true);
+	dev = get_cpu_device(policy->cpu);
+	WARN_ON(!dev);
+
+	opp = dev_pm_opp_find_freq_exact(dev, freq_hz, true);
 	if (IS_ERR(opp)) {
-		dev_warn_ratelimited(cpufreq_device->cpu_dev,
-				     "Failed to find OPP for frequency %lu: %ld\n",
+		dev_warn_ratelimited(dev, "Failed to find OPP for frequency %lu: %ld\n",
 				     freq_hz, PTR_ERR(opp));
 		return -EINVAL;
 	}
@@ -404,31 +363,30 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
 	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
-		dev_err_ratelimited(cpufreq_device->cpu_dev,
-				    "Failed to get voltage for frequency %lu\n",
+		dev_err_ratelimited(dev, "Failed to get voltage for frequency %lu\n",
 				    freq_hz);
 		return -EINVAL;
 	}
 
-	return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay,
-						     voltage, power);
+	return cpufreq_cdev->plat_get_static_power(cpumask, tz->passive_delay,
+						  voltage, power);
 }
 
 /**
  * get_dynamic_power() - calculate the dynamic power
- * @cpufreq_device:	&cpufreq_cooling_device for this cdev
+ * @cpufreq_cdev:	&cpufreq_cooling_device for this cdev
  * @freq:	current frequency
  *
  * Return: the dynamic power consumed by the cpus described by
- * @cpufreq_device.
+ * @cpufreq_cdev.
  */
-static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
+static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
 			     unsigned long freq)
 {
 	u32 raw_cpu_power;
 
-	raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq);
-	return (raw_cpu_power * cpufreq_device->last_load) / 100;
+	raw_cpu_power = cpu_freq_to_power(cpufreq_cdev, freq);
+	return (raw_cpu_power * cpufreq_cdev->last_load) / 100;
 }
 
 /* cpufreq cooling device callback functions are defined below */
@@ -446,9 +404,9 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
 static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 
-	*state = cpufreq_device->max_level;
+	*state = cpufreq_cdev->max_level;
 	return 0;
 }
 
@@ -465,9 +423,9 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 
-	*state = cpufreq_device->cpufreq_state;
+	*state = cpufreq_cdev->cpufreq_state;
 
 	return 0;
 }
@@ -485,23 +443,22 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
 static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
-	unsigned int cpu = cpumask_any(&cpufreq_device->allowed_cpus);
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 	unsigned int clip_freq;
 
 	/* Request state should be less than max_level */
-	if (WARN_ON(state > cpufreq_device->max_level))
+	if (WARN_ON(state > cpufreq_cdev->max_level))
 		return -EINVAL;
 
 	/* Check if the old cooling action is same as new cooling action */
-	if (cpufreq_device->cpufreq_state == state)
+	if (cpufreq_cdev->cpufreq_state == state)
 		return 0;
 
-	clip_freq = cpufreq_device->freq_table[state];
-	cpufreq_device->cpufreq_state = state;
-	cpufreq_device->clipped_freq = clip_freq;
+	clip_freq = cpufreq_cdev->freq_table[state].frequency;
+	cpufreq_cdev->cpufreq_state = state;
+	cpufreq_cdev->clipped_freq = clip_freq;
 
-	cpufreq_update_policy(cpu);
+	cpufreq_update_policy(cpufreq_cdev->policy->cpu);
 
 	return 0;
 }
@@ -536,33 +493,23 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 	unsigned long freq;
 	int i = 0, cpu, ret;
 	u32 static_power, dynamic_power, total_load = 0;
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+	struct cpufreq_policy *policy = cpufreq_cdev->policy;
 	u32 *load_cpu = NULL;
 
-	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
-
-	/*
-	 * All the CPUs are offline, thus the requested power by
-	 * the cdev is 0
-	 */
-	if (cpu >= nr_cpu_ids) {
-		*power = 0;
-		return 0;
-	}
-
-	freq = cpufreq_quick_get(cpu);
+	freq = cpufreq_quick_get(policy->cpu);
 
 	if (trace_thermal_power_cpu_get_power_enabled()) {
-		u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus);
+		u32 ncpus = cpumask_weight(policy->related_cpus);
 
 		load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL);
 	}
 
-	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+	for_each_cpu(cpu, policy->related_cpus) {
 		u32 load;
 
 		if (cpu_online(cpu))
-			load = get_load(cpufreq_device, cpu, i);
+			load = get_load(cpufreq_cdev, cpu, i);
 		else
 			load = 0;
 
@@ -573,19 +520,19 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 		i++;
 	}
 
-	cpufreq_device->last_load = total_load;
+	cpufreq_cdev->last_load = total_load;
 
-	dynamic_power = get_dynamic_power(cpufreq_device, freq);
-	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	dynamic_power = get_dynamic_power(cpufreq_cdev, freq);
+	ret = get_static_power(cpufreq_cdev, tz, freq, &static_power);
 	if (ret) {
 		kfree(load_cpu);
 		return ret;
 	}
 
 	if (load_cpu) {
-		trace_thermal_power_cpu_get_power(
-			&cpufreq_device->allowed_cpus,
-			freq, load_cpu, i, dynamic_power, static_power);
+		trace_thermal_power_cpu_get_power(policy->related_cpus, freq,
+						  load_cpu, i, dynamic_power,
+						  static_power);
 
 		kfree(load_cpu);
 	}
@@ -614,38 +561,23 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 			       unsigned long state, u32 *power)
 {
 	unsigned int freq, num_cpus;
-	cpumask_var_t cpumask;
 	u32 static_power, dynamic_power;
 	int ret;
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
-
-	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
-		return -ENOMEM;
-
-	cpumask_and(cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask);
-	num_cpus = cpumask_weight(cpumask);
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 
-	/* None of our cpus are online, so no power */
-	if (num_cpus == 0) {
-		*power = 0;
-		ret = 0;
-		goto out;
-	}
+	/* Request state should be less than max_level */
+	if (WARN_ON(state > cpufreq_cdev->max_level))
+		return -EINVAL;
 
-	freq = cpufreq_device->freq_table[state];
-	if (!freq) {
-		ret = -EINVAL;
-		goto out;
-	}
+	num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus);
 
-	dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus;
-	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	freq = cpufreq_cdev->freq_table[state].frequency;
+	dynamic_power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus;
+	ret = get_static_power(cpufreq_cdev, tz, freq, &static_power);
 	if (ret)
-		goto out;
+		return ret;
 
 	*power = static_power + dynamic_power;
-out:
-	free_cpumask_var(cpumask);
 	return ret;
 }
 
@@ -673,39 +605,27 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
 			       struct thermal_zone_device *tz, u32 power,
 			       unsigned long *state)
 {
-	unsigned int cpu, cur_freq, target_freq;
+	unsigned int cur_freq, target_freq;
 	int ret;
 	s32 dyn_power;
 	u32 last_load, normalised_power, static_power;
-	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+	struct cpufreq_policy *policy = cpufreq_cdev->policy;
 
-	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
-
-	/* None of our cpus are online */
-	if (cpu >= nr_cpu_ids)
-		return -ENODEV;
-
-	cur_freq = cpufreq_quick_get(cpu);
-	ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power);
+	cur_freq = cpufreq_quick_get(policy->cpu);
+	ret = get_static_power(cpufreq_cdev, tz, cur_freq, &static_power);
 	if (ret)
 		return ret;
 
 	dyn_power = power - static_power;
 	dyn_power = dyn_power > 0 ? dyn_power : 0;
-	last_load = cpufreq_device->last_load ?: 1;
+	last_load = cpufreq_cdev->last_load ?: 1;
 	normalised_power = (dyn_power * 100) / last_load;
-	target_freq = cpu_power_to_freq(cpufreq_device, normalised_power);
+	target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power);
 
-	*state = cpufreq_cooling_get_level(cpu, target_freq);
-	if (*state == THERMAL_CSTATE_INVALID) {
-		dev_err_ratelimited(&cdev->device,
-				    "Failed to convert %dKHz for cpu %d into a cdev state\n",
-				    target_freq, cpu);
-		return -EINVAL;
-	}
-
-	trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus,
-				      target_freq, *state, power);
+	*state = get_level(cpufreq_cdev, target_freq);
+	trace_thermal_power_cpu_limit(policy->related_cpus, target_freq, *state,
+				      power);
 	return 0;
 }
 
@@ -748,7 +668,7 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
 /**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
  * @np: a valid struct device_node to the cooling device device tree node
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  * Normally this should be same as cpufreq policy->related_cpus.
  * @capacitance: dynamic power coefficient for these cpus
  * @plat_static_func: function to calculate the static power consumed by these
@@ -764,102 +684,68 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  */
 static struct thermal_cooling_device *
 __cpufreq_cooling_register(struct device_node *np,
-			const struct cpumask *clip_cpus, u32 capacitance,
+			struct cpufreq_policy *policy, u32 capacitance,
 			get_static_t plat_static_func)
 {
-	struct cpufreq_policy *policy;
-	struct thermal_cooling_device *cool_dev;
-	struct cpufreq_cooling_device *cpufreq_dev;
+	struct thermal_cooling_device *cdev;
+	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	struct cpufreq_frequency_table *pos, *table;
-	cpumask_var_t temp_mask;
 	unsigned int freq, i, num_cpus;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
 	bool first;
 
-	if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL))
-		return ERR_PTR(-ENOMEM);
-
-	cpumask_and(temp_mask, clip_cpus, cpu_online_mask);
-	policy = cpufreq_cpu_get(cpumask_first(temp_mask));
-	if (!policy) {
-		pr_debug("%s: CPUFreq policy not found\n", __func__);
-		cool_dev = ERR_PTR(-EPROBE_DEFER);
-		goto free_cpumask;
+	if (IS_ERR_OR_NULL(policy)) {
+		pr_err("%s: cpufreq policy isn't valid: %p", __func__, policy);
+		return ERR_PTR(-EINVAL);
 	}
 
-	table = policy->freq_table;
-	if (!table) {
-		pr_debug("%s: CPUFreq table not found\n", __func__);
-		cool_dev = ERR_PTR(-ENODEV);
-		goto put_policy;
+	i = cpufreq_table_count_valid_entries(policy);
+	if (!i) {
+		pr_debug("%s: CPUFreq table not found or has no valid entries\n",
+			 __func__);
+		return ERR_PTR(-ENODEV);
 	}
 
-	cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL);
-	if (!cpufreq_dev) {
-		cool_dev = ERR_PTR(-ENOMEM);
-		goto put_policy;
-	}
+	cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL);
+	if (!cpufreq_cdev)
+		return ERR_PTR(-ENOMEM);
 
-	num_cpus = cpumask_weight(clip_cpus);
-	cpufreq_dev->time_in_idle = kcalloc(num_cpus,
-					    sizeof(*cpufreq_dev->time_in_idle),
-					    GFP_KERNEL);
-	if (!cpufreq_dev->time_in_idle) {
-		cool_dev = ERR_PTR(-ENOMEM);
+	cpufreq_cdev->policy = policy;
+	num_cpus = cpumask_weight(policy->related_cpus);
+	cpufreq_cdev->idle_time = kcalloc(num_cpus,
+					 sizeof(*cpufreq_cdev->idle_time),
+					 GFP_KERNEL);
+	if (!cpufreq_cdev->idle_time) {
+		cdev = ERR_PTR(-ENOMEM);
 		goto free_cdev;
 	}
 
-	cpufreq_dev->time_in_idle_timestamp =
-		kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp),
-			GFP_KERNEL);
-	if (!cpufreq_dev->time_in_idle_timestamp) {
-		cool_dev = ERR_PTR(-ENOMEM);
-		goto free_time_in_idle;
-	}
-
-	/* Find max levels */
-	cpufreq_for_each_valid_entry(pos, table)
-		cpufreq_dev->max_level++;
-
-	cpufreq_dev->freq_table = kmalloc(sizeof(*cpufreq_dev->freq_table) *
-					  cpufreq_dev->max_level, GFP_KERNEL);
-	if (!cpufreq_dev->freq_table) {
-		cool_dev = ERR_PTR(-ENOMEM);
-		goto free_time_in_idle_timestamp;
-	}
-
 	/* max_level is an index, not a counter */
-	cpufreq_dev->max_level--;
-
-	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
-
-	if (capacitance) {
-		cpufreq_dev->plat_get_static_power = plat_static_func;
-
-		ret = build_dyn_power_table(cpufreq_dev, capacitance);
-		if (ret) {
-			cool_dev = ERR_PTR(ret);
-			goto free_table;
-		}
-
-		cooling_ops = &cpufreq_power_cooling_ops;
-	} else {
-		cooling_ops = &cpufreq_cooling_ops;
+	cpufreq_cdev->max_level = i - 1;
+
+	cpufreq_cdev->freq_table = kmalloc_array(i,
+					sizeof(*cpufreq_cdev->freq_table),
+					GFP_KERNEL);
+	if (!cpufreq_cdev->freq_table) {
+		cdev = ERR_PTR(-ENOMEM);
+		goto free_idle_time;
 	}
 
 	ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
-		cool_dev = ERR_PTR(ret);
-		goto free_power_table;
+		cdev = ERR_PTR(ret);
+		goto free_table;
 	}
-	cpufreq_dev->id = ret;
+	cpufreq_cdev->id = ret;
+
+	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
+		 cpufreq_cdev->id);
 
 	/* Fill freq-table in descending order of frequencies */
-	for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
-		freq = find_next_max(table, freq);
-		cpufreq_dev->freq_table[i] = freq;
+	for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) {
+		freq = find_next_max(policy->freq_table, freq);
+		cpufreq_cdev->freq_table[i].frequency = freq;
 
 		/* Warn for duplicate entries */
 		if (!freq)
@@ -868,51 +754,54 @@ __cpufreq_cooling_register(struct device_node *np,
 			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
 
-	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
-		 cpufreq_dev->id);
+	if (capacitance) {
+		cpufreq_cdev->plat_get_static_power = plat_static_func;
+
+		ret = update_freq_table(cpufreq_cdev, capacitance);
+		if (ret) {
+			cdev = ERR_PTR(ret);
+			goto remove_ida;
+		}
+
+		cooling_ops = &cpufreq_power_cooling_ops;
+	} else {
+		cooling_ops = &cpufreq_cooling_ops;
+	}
 
-	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
-						      cooling_ops);
-	if (IS_ERR(cool_dev))
+	cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev,
+						  cooling_ops);
+	if (IS_ERR(cdev))
 		goto remove_ida;
 
-	cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0];
-	cpufreq_dev->cool_dev = cool_dev;
+	cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency;
+	cpufreq_cdev->cdev = cdev;
 
 	mutex_lock(&cooling_list_lock);
 	/* Register the notifier for first cpufreq cooling device */
-	first = list_empty(&cpufreq_dev_list);
-	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
+	first = list_empty(&cpufreq_cdev_list);
+	list_add(&cpufreq_cdev->node, &cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
 	if (first)
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
 
-	goto put_policy;
+	return cdev;
 
 remove_ida:
-	ida_simple_remove(&cpufreq_ida, cpufreq_dev->id);
-free_power_table:
-	kfree(cpufreq_dev->dyn_power_table);
+	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_table:
-	kfree(cpufreq_dev->freq_table);
-free_time_in_idle_timestamp:
-	kfree(cpufreq_dev->time_in_idle_timestamp);
-free_time_in_idle:
-	kfree(cpufreq_dev->time_in_idle);
+	kfree(cpufreq_cdev->freq_table);
+free_idle_time:
+	kfree(cpufreq_cdev->idle_time);
 free_cdev:
-	kfree(cpufreq_dev);
-put_policy:
-	cpufreq_cpu_put(policy);
-free_cpumask:
-	free_cpumask_var(temp_mask);
-	return cool_dev;
+	kfree(cpufreq_cdev);
+	return cdev;
 }
 
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -922,16 +811,16 @@ free_cpumask:
  * on failure, it returns a corresponding ERR_PTR().
  */
 struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL);
+	return __cpufreq_cooling_register(NULL, policy, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
 /**
  * of_cpufreq_cooling_register - function to create cpufreq cooling device.
  * @np: a valid struct device_node to the cooling device device tree node
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -943,18 +832,18 @@ EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
  */
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus, 0, NULL);
+	return __cpufreq_cooling_register(np, policy, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 
 /**
  * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
- * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @policy:		cpufreq policy
  * @capacitance:	dynamic power coefficient for these cpus
  * @plat_static_func:	function to calculate the static power consumed by these
  *			cpus (optional)
@@ -974,10 +863,10 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
  * on failure, it returns a corresponding ERR_PTR().
  */
 struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance,
 			       get_static_t plat_static_func)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus, capacitance,
+	return __cpufreq_cooling_register(NULL, policy, capacitance,
 				plat_static_func);
 }
 EXPORT_SYMBOL(cpufreq_power_cooling_register);
@@ -985,7 +874,7 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register);
 /**
  * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
  * @np:	a valid struct device_node to the cooling device device tree node
- * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy
  * @capacitance:	dynamic power coefficient for these cpus
  * @plat_static_func:	function to calculate the static power consumed by these
  *			cpus (optional)
@@ -1007,14 +896,14 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register);
  */
 struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus, capacitance,
+	return __cpufreq_cooling_register(np, policy, capacitance,
 				plat_static_func);
 }
 EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
@@ -1027,30 +916,28 @@ EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
  */
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
-	struct cpufreq_cooling_device *cpufreq_dev;
+	struct cpufreq_cooling_device *cpufreq_cdev;
 	bool last;
 
 	if (!cdev)
 		return;
 
-	cpufreq_dev = cdev->devdata;
+	cpufreq_cdev = cdev->devdata;
 
 	mutex_lock(&cooling_list_lock);
-	list_del(&cpufreq_dev->node);
+	list_del(&cpufreq_cdev->node);
 	/* Unregister the notifier for the last cpufreq cooling device */
-	last = list_empty(&cpufreq_dev_list);
+	last = list_empty(&cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
 	if (last)
 		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
 					    CPUFREQ_POLICY_NOTIFIER);
 
-	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
-	ida_simple_remove(&cpufreq_ida, cpufreq_dev->id);
-	kfree(cpufreq_dev->dyn_power_table);
-	kfree(cpufreq_dev->time_in_idle_timestamp);
-	kfree(cpufreq_dev->time_in_idle);
-	kfree(cpufreq_dev->freq_table);
-	kfree(cpufreq_dev);
+	thermal_cooling_device_unregister(cpufreq_cdev->cdev);
+	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
+	kfree(cpufreq_cdev->idle_time);
+	kfree(cpufreq_cdev->freq_table);
+	kfree(cpufreq_cdev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);
diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c
index 68bd1b569118..d3469fbc5207 100644
--- a/drivers/thermal/fair_share.c
+++ b/drivers/thermal/fair_share.c
@@ -71,6 +71,7 @@ static long get_target_state(struct thermal_zone_device *tz,
 /**
  * fair_share_throttle - throttles devices associated with the given zone
  * @tz - thermal_zone_device
+ * @trip - trip point index
  *
  * Throttling Logic: This uses three parameters to calculate the new
  * throttle state of the cooling devices associated with the given zone.
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index f6429666a1cf..9c3ce341eb97 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -397,8 +397,11 @@ static int hisi_thermal_suspend(struct device *dev)
 static int hisi_thermal_resume(struct device *dev)
 {
 	struct hisi_thermal_data *data = dev_get_drvdata(dev);
+	int ret;
 
-	clk_prepare_enable(data->clk);
+	ret = clk_prepare_enable(data->clk);
+	if (ret)
+		return ret;
 
 	data->irq_enabled = true;
 	hisi_thermal_enable_bind_irq_sensor(data);
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index fb648a45754e..4798b4b1fd77 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -88,6 +89,7 @@ static struct thermal_soc_data thermal_imx6sx_data = {
 };
 
 struct imx_thermal_data {
+	struct cpufreq_policy *policy;
 	struct thermal_zone_device *tz;
 	struct thermal_cooling_device *cdev;
 	enum thermal_device_mode mode;
@@ -525,13 +527,18 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	regmap_write(map, MISC0 + REG_SET, MISC0_REFTOP_SELBIASOFF);
 	regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
 
-	data->cdev = cpufreq_cooling_register(cpu_present_mask);
+	data->policy = cpufreq_cpu_get(0);
+	if (!data->policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return -EPROBE_DEFER;
+	}
+
+	data->cdev = cpufreq_cooling_register(data->policy);
 	if (IS_ERR(data->cdev)) {
 		ret = PTR_ERR(data->cdev);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev,
-				"failed to register cpufreq cooling device: %d\n",
-				ret);
+		dev_err(&pdev->dev,
+			"failed to register cpufreq cooling device: %d\n", ret);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -542,6 +549,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev,
 				"failed to get thermal clk: %d\n", ret);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -556,6 +564,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -571,6 +580,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 			"failed to register thermal zone device %d\n", ret);
 		clk_disable_unprepare(data->thermal_clk);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -599,6 +609,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		clk_disable_unprepare(data->thermal_clk);
 		thermal_zone_device_unregister(data->tz);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -620,6 +631,7 @@ static int imx_thermal_remove(struct platform_device *pdev)
 
 	thermal_zone_device_unregister(data->tz);
 	cpufreq_cooling_unregister(data->cdev);
+	cpufreq_cpu_put(data->policy);
 
 	return 0;
 }
@@ -648,8 +660,11 @@ static int imx_thermal_resume(struct device *dev)
 {
 	struct imx_thermal_data *data = dev_get_drvdata(dev);
 	struct regmap *map = data->tempmon;
+	int ret;
 
-	clk_prepare_enable(data->thermal_clk);
+	ret = clk_prepare_enable(data->thermal_clk);
+	if (ret)
+		return ret;
 	/* Enabled thermal sensor after resume */
 	regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
 	regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP);
diff --git a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
index 2c2ec7666eb1..51ceb80212a7 100644
--- a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
@@ -62,8 +62,8 @@ static int acpi_thermal_rel_release(struct inode *inode, struct file *file)
  * acpi_parse_trt - Thermal Relationship Table _TRT for passive cooling
  *
  * @handle: ACPI handle of the device contains _TRT
- * @art_count: the number of valid entries resulted from parsing _TRT
- * @artp: pointer to pointer of array of art entries in parsing result
+ * @trt_count: the number of valid entries resulted from parsing _TRT
+ * @trtp: pointer to pointer of array of _TRT entries in parsing result
  * @create_dev: whether to create platform devices for target and source
  *
  */
@@ -208,7 +208,7 @@ int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp,
 		if (art->target) {
 			result = acpi_bus_get_device(art->target, &adev);
 			if (result)
-				pr_warn("Failed to get source ACPI device\n");
+				pr_warn("Failed to get target ACPI device\n");
 		}
 	}
 
diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c
index c4890c9437eb..8a7f24dd9315 100644
--- a/drivers/thermal/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3403_thermal.c
@@ -238,8 +238,16 @@ static int int3403_add(struct platform_device *pdev)
 	status = acpi_evaluate_integer(priv->adev->handle, "PTYP",
 				       NULL, &priv->type);
 	if (ACPI_FAILURE(status)) {
-		result = -EINVAL;
-		goto err;
+		unsigned long long tmp;
+
+		status = acpi_evaluate_integer(priv->adev->handle, "_TMP",
+					       NULL, &tmp);
+		if (ACPI_FAILURE(status)) {
+			result = -EINVAL;
+			goto err;
+		} else {
+			priv->type = INT3403_TYPE_SENSOR;
+		}
 	}
 
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c
index bcef2e7c4ec9..be95826631b7 100644
--- a/drivers/thermal/step_wise.c
+++ b/drivers/thermal/step_wise.c
@@ -186,8 +186,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 /**
  * step_wise_throttle - throttles devices associated with the given zone
  * @tz - thermal_zone_device
- * @trip - the trip point
- * @trip_type - type of the trip point
+ * @trip - trip point index
  *
  * Throttling Logic: This uses the trend of the thermal zone to throttle.
  * If the thermal zone is 'heating up' this throttles all the cooling
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 02790f69e26c..c211a8e4a210 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -28,6 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
 #include <linux/thermal.h>
+#include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/cpu_cooling.h>
 #include <linux/of.h>
@@ -37,6 +38,7 @@
 
 /* common data structures */
 struct ti_thermal_data {
+	struct cpufreq_policy *policy;
 	struct thermal_zone_device *ti_thermal;
 	struct thermal_zone_device *pcb_tz;
 	struct thermal_cooling_device *cool_dev;
@@ -247,15 +249,19 @@ int ti_thermal_register_cpu_cooling(struct ti_bandgap *bgp, int id)
 	if (!data)
 		return -EINVAL;
 
+	data->policy = cpufreq_cpu_get(0);
+	if (!data->policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return -EPROBE_DEFER;
+	}
+
 	/* Register cooling device */
-	data->cool_dev = cpufreq_cooling_register(cpu_present_mask);
+	data->cool_dev = cpufreq_cooling_register(data->policy);
 	if (IS_ERR(data->cool_dev)) {
 		int ret = PTR_ERR(data->cool_dev);
-
-		if (ret != -EPROBE_DEFER)
-			dev_err(bgp->dev,
-				"Failed to register cpu cooling device %d\n",
-				ret);
+		dev_err(bgp->dev, "Failed to register cpu cooling device %d\n",
+			ret);
+		cpufreq_cpu_put(data->policy);
 
 		return ret;
 	}
@@ -270,8 +276,10 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data)
+	if (data) {
 		cpufreq_cooling_unregister(data->cool_dev);
+		cpufreq_cpu_put(data->policy);
+	}
 
 	return 0;
 }
diff --git a/drivers/thermal/user_space.c b/drivers/thermal/user_space.c
index c908150c268d..8e92a06ef48a 100644
--- a/drivers/thermal/user_space.c
+++ b/drivers/thermal/user_space.c
@@ -24,12 +24,13 @@
 
 #include <linux/thermal.h>
 #include <linux/slab.h>
+
 #include "thermal_core.h"
 
 /**
  * notify_user_space - Notifies user space about thermal events
  * @tz - thermal_zone_device
- * @trip - Trip point index
+ * @trip - trip point index
  *
  * This function notifies the user space through UEvents.
  */
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index c156f5082758..d4292ebc5c8b 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -28,47 +28,49 @@
 #include <linux/thermal.h>
 #include <linux/cpumask.h>
 
+struct cpufreq_policy;
+
 typedef int (*get_static_t)(cpumask_t *cpumask, int interval,
 			    unsigned long voltage, u32 *power);
 
 #ifdef CONFIG_CPU_THERMAL
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy.
  */
 struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus);
+cpufreq_cooling_register(struct cpufreq_policy *policy);
 
 struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy,
 			       u32 capacitance, get_static_t plat_static_func);
 
 /**
  * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
  * @np: a valid struct device_node to the cooling device device tree node.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy.
  */
 #ifdef CONFIG_THERMAL_OF
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus);
+			    struct cpufreq_policy *policy);
 
 struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func);
 #else
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
@@ -82,15 +84,14 @@ of_cpufreq_power_cooling_register(struct device_node *np,
  */
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
 
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq);
 #else /* !CONFIG_CPU_THERMAL */
 static inline struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 static inline struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy,
 			       u32 capacitance, get_static_t plat_static_func)
 {
 	return NULL;
@@ -98,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
 
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
@@ -117,11 +118,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	return;
 }
-static inline
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
-{
-	return THERMAL_CSTATE_INVALID;
-}
 #endif	/* CONFIG_CPU_THERMAL */
 
 #endif /* __CPU_COOLING_H__ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 905117bd5012..f10a9b3761cd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -862,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		return -EINVAL;
 	}
 }
+
+static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos;
+	int count = 0;
+
+	if (unlikely(!policy->freq_table))
+		return 0;
+
+	cpufreq_for_each_valid_entry(pos, policy->freq_table)
+		count++;
+
+	return count;
+}
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {