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

Pull thermal management updates from Zhang Rui:
 "Specifics:

   - enhance Thermal Framework with several new capabilities:

       * use power estimates
       * compute weights with relative integers instead of percentages
       * allow governors to have private data in thermal zones
       * export thermal zone parameters through sysfs

     Thanks to the ARM thermal team (Javi, Punit, KP).

   - introduce a new thermal governor: power allocator.  First in kernel
     closed loop PI(D) controller for thermal control.  Thanks to ARM
     thermal team.

   - enhance OF thermal to allow thermal zones to have sustainable power
     HW specification.  Thanks to Punit.

   - introduce thermal driver for Intel Quark SoC x1000platform.  Thanks
     to Ong, Boon Leong.

   - introduce QPNP PMIC temperature alarm driver.  Thanks to Ivan T. I.

   - introduce thermal driver for Hisilicon hi6220.  Thanks to
     kongxinwei.

   - enhance Exynos thermal driver to handle Exynos5433 TMU.  Thanks to
     Chanwoo C.

   - TI thermal driver now has a better implementation for EOCZ bit.
     From Pavel M.

   - add id for Skylake processors in int340x processor thermal driver.

   - a couple of small fixes and cleanups."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux: (36 commits)
  thermal: hisilicon: add new hisilicon thermal sensor driver
  dt-bindings: Document the hi6220 thermal sensor bindings
  thermal: of-thermal: add support for reading coefficients property
  thermal: support slope and offset coefficients
  thermal: power_allocator: round the division when divvying up power
  thermal: exynos: Add the support for Exynos5433 TMU
  thermal: cpu_cooling: Fix power calculation when CPUs are offline
  thermal: cpu_cooling: Remove cpu_dev update on policy CPU update
  thermal: export thermal_zone_parameters to sysfs
  thermal: cpu_cooling: Check memory allocation of power_table
  ti-soc-thermal: request temperature periodically if hw can't do that itself
  ti-soc-thermal: implement eocz bit to make driver useful on omap3
  cleanup ti-soc-thermal
  thermal: remove stale THERMAL_POWER_ACTOR select
  thermal: Default OF created trip points to writable
  thermal: core: Add Kconfig option to enable writable trips
  thermal: x86_pkg_temp: drop const for thermal_zone_parameters
  of: thermal: Introduce sustainable power for a thermal zone
  thermal: add trace events to the power allocator governor
  thermal: introduce the Power Allocator governor
  ...

25 files changed, 3620 insertions, 533 deletions

diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d24fa1964eb8..6d4e44ea74ac 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -800,7 +800,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result =
 					thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result =
 					thermal_zone_unbind_cooling_device
@@ -824,7 +825,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 			if (bind)
 				result = thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 					(thermal, trip, cdev);
@@ -841,7 +843,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result = thermal_zone_bind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,
 						 cdev, THERMAL_NO_LIMIT,
-						 THERMAL_NO_LIMIT);
+						 THERMAL_NO_LIMIT,
+						 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 594c918b553d..1ef02daddb60 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -372,7 +372,8 @@ static int acerhdf_bind(struct thermal_zone_device *thermal,
 		return 0;
 
 	if (thermal_zone_bind_cooling_device(thermal, 0, cdev,
-			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT)) {
+			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+			THERMAL_WEIGHT_DEFAULT)) {
 		pr_err("error binding cooling dev\n");
 		return -EINVAL;
 	}
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index af40db0df58e..118938ee8552 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -42,6 +42,17 @@ config THERMAL_OF
 	  Say 'Y' here if you need to build thermal infrastructure
 	  based on device tree.
 
+config THERMAL_WRITABLE_TRIPS
+	bool "Enable writable trip points"
+	help
+	  This option allows the system integrator to choose whether
+	  trip temperatures can be changed from userspace. The
+	  writable trips need to be specified when setting up the
+	  thermal zone but the choice here takes precedence.
+
+	  Say 'Y' here if you would like to allow userspace tools to
+	  change trip temperatures.
+
 choice
 	prompt "Default Thermal governor"
 	default THERMAL_DEFAULT_GOV_STEP_WISE
@@ -71,6 +82,14 @@ config THERMAL_DEFAULT_GOV_USER_SPACE
 	  Select this if you want to let the user space manage the
 	  platform thermals.
 
+config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR
+	bool "power_allocator"
+	select THERMAL_GOV_POWER_ALLOCATOR
+	help
+	  Select this if you want to control temperature based on
+	  system and device power allocation. This governor can only
+	  operate on cooling devices that implement the power API.
+
 endchoice
 
 config THERMAL_GOV_FAIR_SHARE
@@ -99,6 +118,12 @@ config THERMAL_GOV_USER_SPACE
 	help
 	  Enable this to let the user space manage the platform thermals.
 
+config THERMAL_GOV_POWER_ALLOCATOR
+	bool "Power allocator thermal governor"
+	help
+	  Enable this to manage platform thermals by dynamically
+	  allocating and limiting power to devices.
+
 config CPU_THERMAL
 	bool "generic cpu cooling support"
 	depends on CPU_FREQ
@@ -136,6 +161,14 @@ config THERMAL_EMULATION
 	  because userland can easily disable the thermal policy by simply
 	  flooding this sysfs node with low temperature values.
 
+config HISI_THERMAL
+	tristate "Hisilicon thermal driver"
+	depends on ARCH_HISI && CPU_THERMAL && OF
+	help
+	  Enable this to plug hisilicon's thermal sensor driver into the Linux
+	  thermal framework. cpufreq is used as the cooling device to throttle
+	  CPUs when the passive trip is crossed.
+
 config IMX_THERMAL
 	tristate "Temperature sensor driver for Freescale i.MX SoCs"
 	depends on CPU_THERMAL
@@ -249,9 +282,20 @@ config X86_PKG_TEMP_THERMAL
 	  two trip points which can be set by user to get notifications via thermal
 	  notification methods.
 
+config INTEL_SOC_DTS_IOSF_CORE
+	tristate
+	depends on X86
+	select IOSF_MBI
+	help
+	  This is becoming a common feature for Intel SoCs to expose the additional
+	  digital temperature sensors (DTSs) using side band interface (IOSF). This
+	  implements the common set of helper functions to register, get temperature
+	  and get/set thresholds on DTSs.
+
 config INTEL_SOC_DTS_THERMAL
 	tristate "Intel SoCs DTS thermal driver"
-	depends on X86 && IOSF_MBI
+	depends on X86
+	select INTEL_SOC_DTS_IOSF_CORE
 	help
 	  Enable this to register Intel SoCs (e.g. Bay Trail) platform digital
 	  temperature sensor (DTS). These SoCs have two additional DTSs in
@@ -261,12 +305,23 @@ config INTEL_SOC_DTS_THERMAL
 	  notification methods.The other trip is a critical trip point, which
 	  was set by the driver based on the TJ MAX temperature.
 
+config INTEL_QUARK_DTS_THERMAL
+	tristate "Intel Quark DTS thermal driver"
+	depends on X86_INTEL_QUARK
+	help
+	  Enable this to register Intel Quark SoC (e.g. X1000) platform digital
+	  temperature sensor (DTS). For X1000 SoC, it has one on-die DTS.
+	  The DTS will be registered as a thermal zone. There are two trip points:
+	  hot & critical. The critical trip point default value is set by
+	  underlying BIOS/Firmware.
+
 config INT340X_THERMAL
 	tristate "ACPI INT340X thermal drivers"
 	depends on X86 && ACPI
 	select THERMAL_GOV_USER_SPACE
 	select ACPI_THERMAL_REL
 	select ACPI_FAN
+	select INTEL_SOC_DTS_IOSF_CORE
 	help
 	  Newer laptops and tablets that use ACPI may have thermal sensors and
 	  other devices with thermal control capabilities outside the core
@@ -299,4 +354,15 @@ depends on ARCH_STI && OF
 source "drivers/thermal/st/Kconfig"
 endmenu
 
+config QCOM_SPMI_TEMP_ALARM
+	tristate "Qualcomm SPMI PMIC Temperature Alarm"
+	depends on OF && SPMI && IIO
+	select REGMAP_SPMI
+	help
+	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
+	  PMIC devices. It shows up in sysfs as a thermal sensor with multiple
+	  trip points. The temperature reported by the thermal sensor reflects the
+	  real time die temperature if an ADC is present or an estimate of the
+	  temperature based upon the over temperature stage value.
+
 endif
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index fa0dc486790f..535dfee1496f 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -14,6 +14,7 @@ thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
 thermal_sys-$(CONFIG_THERMAL_GOV_BANG_BANG)	+= gov_bang_bang.o
 thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
 thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
+thermal_sys-$(CONFIG_THERMAL_GOV_POWER_ALLOCATOR)	+= power_allocator.o
 
 # cpufreq cooling
 thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
@@ -22,6 +23,7 @@ thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
 
 # platform thermal drivers
+obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM)	+= qcom-spmi-temp-alarm.o
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
 obj-$(CONFIG_ROCKCHIP_THERMAL)	+= rockchip_thermal.o
 obj-$(CONFIG_RCAR_THERMAL)	+= rcar_thermal.o
@@ -34,8 +36,11 @@ obj-$(CONFIG_IMX_THERMAL)	+= imx_thermal.o
 obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
 obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
+obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE)	+= intel_soc_dts_iosf.o
 obj-$(CONFIG_INTEL_SOC_DTS_THERMAL)	+= intel_soc_dts_thermal.o
+obj-$(CONFIG_INTEL_QUARK_DTS_THERMAL)	+= intel_quark_dts_thermal.o
 obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/
 obj-$(CONFIG_INT340X_THERMAL)  += int340x_thermal/
 obj-$(CONFIG_ST_THERMAL)	+= st/
 obj-$(CONFIG_TEGRA_SOCTHERM)	+= tegra_soctherm.o
+obj-$(CONFIG_HISI_THERMAL)     += hisi_thermal.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index f65f0d109fc8..6509c61b9648 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -26,10 +26,13 @@
 #include <linux/thermal.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 
+#include <trace/events/thermal.h>
+
 /*
  * Cooling state <-> CPUFreq frequency
  *
@@ -45,6 +48,19 @@
  */
 
 /**
+ * struct power_table - frequency to power conversion
+ * @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.
+ */
+struct power_table {
+	u32 frequency;
+	u32 power;
+};
+
+/**
  * struct cpufreq_cooling_device - data for cooling device with cpufreq
  * @id: unique integer value corresponding to each cpufreq_cooling_device
  *	registered.
@@ -58,6 +74,15 @@
  *	cpufreq frequencies.
  * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
  * @node: list_head to link all cpufreq_cooling_device together.
+ * @last_load: load measured by the latest call to cpufreq_get_actual_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
+ * @plat_get_static_power: callback to calculate the static power
  *
  * This structure is required for keeping information of each registered
  * cpufreq_cooling_device.
@@ -71,6 +96,13 @@ struct cpufreq_cooling_device {
 	unsigned int *freq_table;	/* In descending order */
 	struct cpumask allowed_cpus;
 	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;
+	get_static_t plat_get_static_power;
 };
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
@@ -186,23 +218,237 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 	unsigned long max_freq = 0;
 	struct cpufreq_cooling_device *cpufreq_dev;
 
-	if (event != CPUFREQ_ADJUST)
-		return 0;
+	switch (event) {
 
-	mutex_lock(&cooling_cpufreq_lock);
-	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-		if (!cpumask_test_cpu(policy->cpu,
-					&cpufreq_dev->allowed_cpus))
+	case CPUFREQ_ADJUST:
+		mutex_lock(&cooling_cpufreq_lock);
+		list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+			if (!cpumask_test_cpu(policy->cpu,
+					      &cpufreq_dev->allowed_cpus))
+				continue;
+
+			max_freq = cpufreq_dev->cpufreq_val;
+
+			if (policy->max != max_freq)
+				cpufreq_verify_within_limits(policy, 0,
+							     max_freq);
+		}
+		mutex_unlock(&cooling_cpufreq_lock);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+/**
+ * build_dyn_power_table() - create a dynamic power to frequency table
+ * @cpufreq_device:	the cpufreq cooling device in which to store 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.
+ *
+ * Return: 0 on success, -E* on error.
+ */
+static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
+				 u32 capacitance)
+{
+	struct power_table *power_table;
+	struct dev_pm_opp *opp;
+	struct device *dev = NULL;
+	int num_opps = 0, cpu, i, ret = 0;
+	unsigned long freq;
+
+	rcu_read_lock();
+
+	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;
+		}
+
+		num_opps = dev_pm_opp_get_opp_count(dev);
+		if (num_opps > 0) {
+			break;
+		} else if (num_opps < 0) {
+			ret = num_opps;
+			goto unlock;
+		}
+	}
 
-		max_freq = cpufreq_dev->cpufreq_val;
+	if (num_opps == 0) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
-		if (policy->max != max_freq)
-			cpufreq_verify_within_limits(policy, 0, max_freq);
+	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
+	if (!power_table) {
+		ret = -ENOMEM;
+		goto unlock;
 	}
-	mutex_unlock(&cooling_cpufreq_lock);
 
-	return 0;
+	for (freq = 0, i = 0;
+	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
+	     freq++, i++) {
+		u32 freq_mhz, voltage_mv;
+		u64 power;
+
+		freq_mhz = freq / 1000000;
+		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+
+		/*
+		 * Do the multiplication with MHz and millivolt so as
+		 * to not overflow.
+		 */
+		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;
+	}
+
+	if (i == 0) {
+		ret = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	cpufreq_device->cpu_dev = dev;
+	cpufreq_device->dyn_power_table = power_table;
+	cpufreq_device->dyn_power_table_entries = i;
+
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+
+static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 freq)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (freq < pt[i].frequency)
+			break;
+
+	return pt[i - 1].power;
+}
+
+static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 power)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (power < pt[i].power)
+			break;
+
+	return pt[i - 1].frequency;
+}
+
+/**
+ * get_load() - get load for a cpu since last updated
+ * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
+ * @cpu:	cpu number
+ *
+ * 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)
+{
+	u32 load;
+	u64 now, now_idle, delta_time, delta_idle;
+
+	now_idle = get_cpu_idle_time(cpu, &now, 0);
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+
+	if (delta_time <= delta_idle)
+		load = 0;
+	else
+		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
+
+	cpufreq_device->time_in_idle[cpu] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+
+	return load;
+}
+
+/**
+ * get_static_power() - calculate the static power consumed by the cpus
+ * @cpufreq_device:	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
+ *
+ * Calculate the static power consumed by the cpus described by
+ * @cpu_actor running at frequency @freq.  This function relies on a
+ * platform specific function that should have been provided when the
+ * actor was registered.  If it wasn't, the static power is assumed to
+ * be negligible.  The calculated static power is stored in @power.
+ *
+ * Return: 0 on success, -E* on failure.
+ */
+static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
+			    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;
+	unsigned long freq_hz = freq * 1000;
+
+	if (!cpufreq_device->plat_get_static_power ||
+	    !cpufreq_device->cpu_dev) {
+		*power = 0;
+		return 0;
+	}
+
+	rcu_read_lock();
+
+	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
+					 true);
+	voltage = dev_pm_opp_get_voltage(opp);
+
+	rcu_read_unlock();
+
+	if (voltage == 0) {
+		dev_warn_ratelimited(cpufreq_device->cpu_dev,
+				     "Failed to get voltage for frequency %lu: %ld\n",
+				     freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		return -EINVAL;
+	}
+
+	return cpufreq_device->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
+ * @freq:	current frequency
+ *
+ * Return: the dynamic power consumed by the cpus described by
+ * @cpufreq_device.
+ */
+static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
+			     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;
 }
 
 /* cpufreq cooling device callback functions are defined below */
@@ -280,8 +526,205 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	return 0;
 }
 
+/**
+ * cpufreq_get_requested_power() - get the current power
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	pointer in which to store the resulting power
+ *
+ * Calculate the current power consumption of the cpus in milliwatts
+ * and store it in @power.  This function should actually calculate
+ * the requested power, but it's hard to get the frequency that
+ * cpufreq would have assigned if there were no thermal limits.
+ * Instead, we calculate the current power on the assumption that the
+ * immediate future will look like the immediate past.
+ *
+ * We use the current frequency and the average load since this
+ * function was last called.  In reality, there could have been
+ * multiple opps since this function was last called and that affects
+ * the load calculation.  While it's not perfectly accurate, this
+ * simplification is good enough and works.  REVISIT this, as more
+ * complex code may be needed if experiments show that it's not
+ * accurate enough.
+ *
+ * Return: 0 on success, -E* if getting the static power failed.
+ */
+static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       u32 *power)
+{
+	unsigned long freq;
+	int i = 0, cpu, ret;
+	u32 static_power, dynamic_power, total_load = 0;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	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);
+
+	if (trace_thermal_power_cpu_get_power_enabled()) {
+		u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus);
+
+		load_cpu = devm_kcalloc(&cdev->device, ncpus, sizeof(*load_cpu),
+					GFP_KERNEL);
+	}
+
+	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+		u32 load;
+
+		if (cpu_online(cpu))
+			load = get_load(cpufreq_device, cpu);
+		else
+			load = 0;
+
+		total_load += load;
+		if (trace_thermal_power_cpu_limit_enabled() && load_cpu)
+			load_cpu[i] = load;
+
+		i++;
+	}
+
+	cpufreq_device->last_load = total_load;
+
+	dynamic_power = get_dynamic_power(cpufreq_device, freq);
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret) {
+		if (load_cpu)
+			devm_kfree(&cdev->device, 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);
+
+		devm_kfree(&cdev->device, load_cpu);
+	}
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_state2power() - convert a cpu cdev state to power consumed
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @state:	cooling device state to be converted
+ * @power:	pointer in which to store the resulting power
+ *
+ * Convert cooling device state @state into power consumption in
+ * milliwatts assuming 100% load.  Store the calculated power in
+ * @power.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device state could not
+ * be converted into a frequency or other -E* if there was an error
+ * when calculating the static power.
+ */
+static int cpufreq_state2power(struct thermal_cooling_device *cdev,
+			       struct thermal_zone_device *tz,
+			       unsigned long state, u32 *power)
+{
+	unsigned int freq, num_cpus;
+	cpumask_t cpumask;
+	u32 static_power, dynamic_power;
+	int ret;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	cpumask_and(&cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask);
+	num_cpus = cpumask_weight(&cpumask);
+
+	/* None of our cpus are online, so no power */
+	if (num_cpus == 0) {
+		*power = 0;
+		return 0;
+	}
+
+	freq = cpufreq_device->freq_table[state];
+	if (!freq)
+		return -EINVAL;
+
+	dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus;
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret)
+		return ret;
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_power2state() - convert power to a cooling device state
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	power in milliwatts to be converted
+ * @state:	pointer in which to store the resulting state
+ *
+ * Calculate a cooling device state for the cpus described by @cdev
+ * that would allow them to consume at most @power mW and store it in
+ * @state.  Note that this calculation depends on external factors
+ * such as the cpu load or the current static power.  Calling this
+ * function with the same power as input can yield different cooling
+ * device states depending on those external factors.
+ *
+ * Return: 0 on success, -ENODEV if no cpus are online or -EINVAL if
+ * the calculated frequency could not be converted to a valid state.
+ * The latter should not happen unless the frequencies available to
+ * cpufreq have changed since the initialization of the cpu cooling
+ * device.
+ */
+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;
+	int ret;
+	s32 dyn_power;
+	u32 last_load, normalised_power, static_power;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	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);
+	if (ret)
+		return ret;
+
+	dyn_power = power - static_power;
+	dyn_power = dyn_power > 0 ? dyn_power : 0;
+	last_load = cpufreq_device->last_load ?: 1;
+	normalised_power = (dyn_power * 100) / last_load;
+	target_freq = cpu_power_to_freq(cpufreq_device, normalised_power);
+
+	*state = cpufreq_cooling_get_level(cpu, target_freq);
+	if (*state == THERMAL_CSTATE_INVALID) {
+		dev_warn_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);
+	return 0;
+}
+
 /* Bind cpufreq callbacks to thermal cooling device ops */
-static struct thermal_cooling_device_ops const cpufreq_cooling_ops = {
+static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
 	.get_max_state = cpufreq_get_max_state,
 	.get_cur_state = cpufreq_get_cur_state,
 	.set_cur_state = cpufreq_set_cur_state,
@@ -311,6 +754,9 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  * @np: a valid struct device_node to the cooling device device tree node
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
  * 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
+ *                    cpus (optional)
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -322,13 +768,14 @@ 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)
+			const struct cpumask *clip_cpus, u32 capacitance,
+			get_static_t plat_static_func)
 {
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	struct cpufreq_frequency_table *pos, *table;
-	unsigned int freq, i;
+	unsigned int freq, i, num_cpus;
 	int ret;
 
 	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
@@ -341,6 +788,23 @@ __cpufreq_cooling_register(struct device_node *np,
 	if (!cpufreq_dev)
 		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);
+		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++;
@@ -349,7 +813,7 @@ __cpufreq_cooling_register(struct device_node *np,
 					  cpufreq_dev->max_level, GFP_KERNEL);
 	if (!cpufreq_dev->freq_table) {
 		cool_dev = ERR_PTR(-ENOMEM);
-		goto free_cdev;
+		goto free_time_in_idle_timestamp;
 	}
 
 	/* max_level is an index, not a counter */
@@ -357,6 +821,20 @@ __cpufreq_cooling_register(struct device_node *np,
 
 	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
 
+	if (capacitance) {
+		cpufreq_cooling_ops.get_requested_power =
+			cpufreq_get_requested_power;
+		cpufreq_cooling_ops.state2power = cpufreq_state2power;
+		cpufreq_cooling_ops.power2state = cpufreq_power2state;
+		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;
+		}
+	}
+
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
 		cool_dev = ERR_PTR(ret);
@@ -402,6 +880,10 @@ remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev-&g