21 files changed, 858 insertions, 358 deletions

diff --git a/Documentation/devicetree/bindings/thermal/armada-thermal.txt b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
new file mode 100644
index 000000000000..fff93d5f92de
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
@@ -0,0 +1,22 @@
+* Marvell Armada 370/XP thermal management
+
+Required properties:
+
+- compatible:	Should be set to one of the following:
+		marvell,armada370-thermal
+		marvell,armadaxp-thermal
+
+- reg:		Device's register space.
+		Two entries are expected, see the examples below.
+		The first one is required for the sensor register;
+		the second one is required for the control register
+		to be used for sensor initialization (a.k.a. calibration).
+
+Example:
+
+	thermal@d0018300 {
+		compatible = "marvell,armada370-thermal";
+                reg = <0xd0018300 0x4
+		       0xd0018304 0x4>;
+		status = "okay";
+	};
diff --git a/Documentation/thermal/exynos_thermal_emulation b/Documentation/thermal/exynos_thermal_emulation
index b73bbfb697bb..36a3e79c1203 100644
--- a/Documentation/thermal/exynos_thermal_emulation
+++ b/Documentation/thermal/exynos_thermal_emulation
@@ -13,11 +13,11 @@ Thermal emulation mode supports software debug for TMU's operation. User can set
 manually with software code and TMU will read current temperature from user value not from
 sensor's value.
 
-Enabling CONFIG_EXYNOS_THERMAL_EMUL option will make this support in available.
-When it's enabled, sysfs node will be created under
-/sys/bus/platform/devices/'exynos device name'/ with name of 'emulation'.
+Enabling CONFIG_THERMAL_EMULATION option will make this support available.
+When it's enabled, sysfs node will be created as
+/sys/devices/virtual/thermal/thermal_zone'zone id'/emul_temp.
 
-The sysfs node, 'emulation', will contain value 0 for the initial state. When you input any
+The sysfs node, 'emul_node', will contain value 0 for the initial state. When you input any
 temperature you want to update to sysfs node, it automatically enable emulation mode and
 current temperature will be changed into it.
 (Exynos also supports user changable delay time which would be used to delay of
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index 6859661c9d31..a71bd5b90fe8 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -31,15 +31,17 @@ temperature) and throttle appropriate devices.
 1. thermal sysfs driver interface functions
 
 1.1 thermal zone device interface
-1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *name,
+1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *type,
 		int trips, int mask, void *devdata,
-		struct thermal_zone_device_ops *ops)
+		struct thermal_zone_device_ops *ops,
+		const struct thermal_zone_params *tzp,
+		int passive_delay, int polling_delay))
 
     This interface function adds a new thermal zone device (sensor) to
     /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
     thermal cooling devices registered at the same time.
 
-    name: the thermal zone name.
+    type: the thermal zone type.
     trips: the total number of trip points this thermal zone supports.
     mask: Bit string: If 'n'th bit is set, then trip point 'n' is writeable.
     devdata: device private data
@@ -57,6 +59,12 @@ temperature) and throttle appropriate devices.
 			will be fired.
 	.set_emul_temp: set the emulation temperature which helps in debugging
 			different threshold temperature points.
+    tzp: thermal zone platform parameters.
+    passive_delay: number of milliseconds to wait between polls when
+	performing passive cooling.
+    polling_delay: number of milliseconds to wait between polls when checking
+	whether trip points have been crossed (0 for interrupt driven systems).
+
 
 1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
@@ -265,6 +273,10 @@ emul_temp
 	Unit: millidegree Celsius
 	WO, Optional
 
+	  WARNING: Be careful while enabling this option on production systems,
+	  because userland can easily disable the thermal policy by simply
+	  flooding this sysfs node with low temperature values.
+
 *****************************
 * Cooling device attributes *
 *****************************
@@ -363,7 +375,7 @@ This function returns the thermal_instance corresponding to a given
 {thermal_zone, cooling_device, trip_point} combination. Returns NULL
 if such an instance does not exist.
 
-5.3:notify_thermal_framework:
+5.3:thermal_notify_framework:
 This function handles the trip events from sensor drivers. It starts
 throttling the cooling devices according to the policy configured.
 For CRITICAL and HOT trip points, this notifies the respective drivers,
@@ -375,11 +387,3 @@ platform data is provided, this uses the step_wise throttling policy.
 This function serves as an arbitrator to set the state of a cooling
 device. It sets the cooling device to the deepest cooling state if
 possible.
-
-5.5:thermal_register_governor:
-This function lets the various thermal governors to register themselves
-with the Thermal framework. At run time, depending on a zone's platform
-data, a particular governor is used for throttling.
-
-5.6:thermal_unregister_governor:
-This function unregisters a governor from the thermal framework.
diff --git a/MAINTAINERS b/MAINTAINERS
index 5f5c895e6621..3d7782b9f90d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8029,11 +8029,14 @@ F:	arch/xtensa/
 
 THERMAL
 M:      Zhang Rui <rui.zhang@intel.com>
+M:      Eduardo Valentin <eduardo.valentin@ti.com>
 L:      linux-pm@vger.kernel.org
 T:      git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
+Q:      https://patchwork.kernel.org/project/linux-pm/list/
 S:      Supported
 F:      drivers/thermal/
 F:      include/linux/thermal.h
+F:      include/linux/cpu_cooling.h
 
 THINGM BLINK(1) USB RGB LED DRIVER
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index a764f165b589..5e3c02554d99 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -67,15 +67,16 @@ config THERMAL_GOV_USER_SPACE
 	  Enable this to let the user space manage the platform thermals.
 
 config CPU_THERMAL
-	tristate "generic cpu cooling support"
+	bool "generic cpu cooling support"
 	depends on CPU_FREQ
 	select CPU_FREQ_TABLE
 	help
 	  This implements the generic cpu cooling mechanism through frequency
-	  reduction, cpu hotplug and any other ways of reducing temperature. An
-	  ACPI version of this already exists(drivers/acpi/processor_thermal.c).
+	  reduction. An ACPI version of this already exists
+	  (drivers/acpi/processor_thermal.c).
 	  This will be useful for platforms using the generic thermal interface
 	  and not the ACPI interface.
+
 	  If you want this support, you should say Y here.
 
 config THERMAL_EMULATION
@@ -86,6 +87,10 @@ config THERMAL_EMULATION
 	  user can manually input temperature and test the different trip
 	  threshold behaviour for simulation purpose.
 
+	  WARNING: Be careful while enabling this option on production systems,
+	  because userland can easily disable the thermal policy by simply
+	  flooding this sysfs node with low temperature values.
+
 config SPEAR_THERMAL
 	bool "SPEAr thermal sensor driver"
 	depends on PLAT_SPEAR
@@ -117,15 +122,6 @@ config EXYNOS_THERMAL
 	  If you say yes here you get support for TMU (Thermal Management
 	  Unit) on SAMSUNG EXYNOS series of SoC.
 
-config EXYNOS_THERMAL_EMUL
-	bool "EXYNOS TMU emulation mode support"
-	depends on EXYNOS_THERMAL
-	help
-	  Exynos 4412 and 4414 and 5 series has emulation mode on TMU.
-	  Enable this option will be make sysfs node in exynos thermal platform
-	  device directory to support emulation mode. With emulation mode sysfs
-	  node, you can manually input temperature to TMU for simulation purpose.
-
 config DOVE_THERMAL
 	tristate "Temperature sensor on Marvell Dove SoCs"
 	depends on ARCH_DOVE
@@ -144,6 +140,14 @@ config DB8500_THERMAL
 	  created. Cooling devices can be bound to the trip points to cool this
 	  thermal zone if trip points reached.
 
+config ARMADA_THERMAL
+	tristate "Armada 370/XP thermal management"
+	depends on ARCH_MVEBU
+	depends on OF
+	help
+	  Enable this option if you want to have support for thermal management
+	  controller present in Armada 370 and Armada XP SoC.
+
 config DB8500_CPUFREQ_COOLING
 	tristate "DB8500 cpufreq cooling"
 	depends on ARCH_U8500
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index d3a2b38c31e8..c054d410ac3f 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -3,14 +3,15 @@
 #
 
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
+thermal_sys-y			+= thermal_core.o
 
 # governors
-obj-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
-obj-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
-obj-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
+thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
+thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
+thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
 
 # cpufreq cooling
-obj-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
+thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 
 # platform thermal drivers
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
@@ -19,6 +20,7 @@ obj-$(CONFIG_KIRKWOOD_THERMAL)  += kirkwood_thermal.o
 obj-$(CONFIG_EXYNOS_THERMAL)	+= exynos_thermal.o
 obj-$(CONFIG_DOVE_THERMAL)  	+= dove_thermal.o
 obj-$(CONFIG_DB8500_THERMAL)	+= db8500_thermal.o
+obj-$(CONFIG_ARMADA_THERMAL)	+= armada_thermal.o
 obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
 
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
new file mode 100644
index 000000000000..5b4d75fd7b49
--- /dev/null
+++ b/drivers/thermal/armada_thermal.c
@@ -0,0 +1,232 @@
+/*
+ * Marvell Armada 370/XP thermal sensor driver
+ *
+ * Copyright (C) 2013 Marvell
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/thermal.h>
+
+#define THERMAL_VALID_OFFSET		9
+#define THERMAL_VALID_MASK		0x1
+#define THERMAL_TEMP_OFFSET		10
+#define THERMAL_TEMP_MASK		0x1ff
+
+/* Thermal Manager Control and Status Register */
+#define PMU_TDC0_SW_RST_MASK		(0x1 << 1)
+#define PMU_TM_DISABLE_OFFS		0
+#define PMU_TM_DISABLE_MASK		(0x1 << PMU_TM_DISABLE_OFFS)
+#define PMU_TDC0_REF_CAL_CNT_OFFS	11
+#define PMU_TDC0_REF_CAL_CNT_MASK	(0x1ff << PMU_TDC0_REF_CAL_CNT_OFFS)
+#define PMU_TDC0_OTF_CAL_MASK		(0x1 << 30)
+#define PMU_TDC0_START_CAL_MASK		(0x1 << 25)
+
+struct armada_thermal_ops;
+
+/* Marvell EBU Thermal Sensor Dev Structure */
+struct armada_thermal_priv {
+	void __iomem *sensor;
+	void __iomem *control;
+	struct armada_thermal_ops *ops;
+};
+
+struct armada_thermal_ops {
+	/* Initialize the sensor */
+	void (*init_sensor)(struct armada_thermal_priv *);
+
+	/* Test for a valid sensor value (optional) */
+	bool (*is_valid)(struct armada_thermal_priv *);
+};
+
+static void armadaxp_init_sensor(struct armada_thermal_priv *priv)
+{
+	unsigned long reg;
+
+	reg = readl_relaxed(priv->control);
+	reg |= PMU_TDC0_OTF_CAL_MASK;
+	writel(reg, priv->control);
+
+	/* Reference calibration value */
+	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
+	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
+	writel(reg, priv->control);
+
+	/* Reset the sensor */
+	reg = readl_relaxed(priv->control);
+	writel((reg | PMU_TDC0_SW_RST_MASK), priv->control);
+
+	writel(reg, priv->control);
+
+	/* Enable the sensor */
+	reg = readl_relaxed(priv->sensor);
+	reg &= ~PMU_TM_DISABLE_MASK;
+	writel(reg, priv->sensor);
+}
+
+static void armada370_init_sensor(struct armada_thermal_priv *priv)
+{
+	unsigned long reg;
+
+	reg = readl_relaxed(priv->control);
+	reg |= PMU_TDC0_OTF_CAL_MASK;
+	writel(reg, priv->control);
+
+	/* Reference calibration value */
+	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
+	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
+	writel(reg, priv->control);
+
+	reg &= ~PMU_TDC0_START_CAL_MASK;
+	writel(reg, priv->control);
+
+	mdelay(10);
+}
+
+static bool armada_is_valid(struct armada_thermal_priv *priv)
+{
+	unsigned long reg = readl_relaxed(priv->sensor);
+
+	return (reg >> THERMAL_VALID_OFFSET) & THERMAL_VALID_MASK;
+}
+
+static int armada_get_temp(struct thermal_zone_device *thermal,
+			  unsigned long *temp)
+{
+	struct armada_thermal_priv *priv = thermal->devdata;
+	unsigned long reg;
+
+	/* Valid check */
+	if (priv->ops->is_valid && !priv->ops->is_valid(priv)) {
+		dev_err(&thermal->device,
+			"Temperature sensor reading not valid\n");
+		return -EIO;
+	}
+
+	reg = readl_relaxed(priv->sensor);
+	reg = (reg >> THERMAL_TEMP_OFFSET) & THERMAL_TEMP_MASK;
+	*temp = (3153000000UL - (10000000UL*reg)) / 13825;
+	return 0;
+}
+
+static struct thermal_zone_device_ops ops = {
+	.get_temp = armada_get_temp,
+};
+
+static const struct armada_thermal_ops armadaxp_ops = {
+	.init_sensor = armadaxp_init_sensor,
+};
+
+static const struct armada_thermal_ops armada370_ops = {
+	.is_valid = armada_is_valid,
+	.init_sensor = armada370_init_sensor,
+};
+
+static const struct of_device_id armada_thermal_id_table[] = {
+	{
+		.compatible = "marvell,armadaxp-thermal",
+		.data       = &armadaxp_ops,
+	},
+	{
+		.compatible = "marvell,armada370-thermal",
+		.data       = &armada370_ops,
+	},
+	{
+		/* sentinel */
+	},
+};
+MODULE_DEVICE_TABLE(of, armada_thermal_id_table);
+
+static int armada_thermal_probe(struct platform_device *pdev)
+{
+	struct thermal_zone_device *thermal;
+	const struct of_device_id *match;
+	struct armada_thermal_priv *priv;
+	struct resource *res;
+
+	match = of_match_device(armada_thermal_id_table, &pdev->dev);
+	if (!match)
+		return -ENODEV;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get platform resource\n");
+		return -ENODEV;
+	}
+
+	priv->sensor = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->sensor))
+		return PTR_ERR(priv->sensor);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get platform resource\n");
+		return -ENODEV;
+	}
+
+	priv->control = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->control))
+		return PTR_ERR(priv->control);
+
+	priv->ops = (struct armada_thermal_ops *)match->data;
+	priv->ops->init_sensor(priv);
+
+	thermal = thermal_zone_device_register("armada_thermal", 0, 0,
+					       priv, &ops, NULL, 0, 0);
+	if (IS_ERR(thermal)) {
+		dev_err(&pdev->dev,
+			"Failed to register thermal zone device\n");
+		return PTR_ERR(thermal);
+	}
+
+	platform_set_drvdata(pdev, thermal);
+
+	return 0;
+}
+
+static int armada_thermal_exit(struct platform_device *pdev)
+{
+	struct thermal_zone_device *armada_thermal =
+		platform_get_drvdata(pdev);
+
+	thermal_zone_device_unregister(armada_thermal);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver armada_thermal_driver = {
+	.probe = armada_thermal_probe,
+	.remove = armada_thermal_exit,
+	.driver = {
+		.name = "armada_thermal",
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(armada_thermal_id_table),
+	},
+};
+
+module_platform_driver(armada_thermal_driver);
+
+MODULE_AUTHOR("Ezequiel Garcia <ezequiel.garcia@free-electrons.com>");
+MODULE_DESCRIPTION("Armada 370/XP thermal driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 8dc44cbb3e09..c94bf2e5de62 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -20,10 +20,8 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/thermal.h>
-#include <linux/platform_device.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -31,21 +29,19 @@
 #include <linux/cpu_cooling.h>
 
 /**
- * struct cpufreq_cooling_device
+ * 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 the
- *	egistered cooling device.
+ * @cool_dev: thermal_cooling_device pointer to keep track of the
+ *	registered cooling device.
  * @cpufreq_state: integer value representing the current state of cpufreq
  *	cooling	devices.
  * @cpufreq_val: integer value representing the absolute value of the clipped
  *	frequency.
  * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
- * @node: list_head to link all cpufreq_cooling_device together.
  *
  * This structure is required for keeping information of each
- * cpufreq_cooling_device registered as a list whose head is represented by
- * cooling_cpufreq_list. In order to prevent corruption of this list a
+ * cpufreq_cooling_device registered. In order to prevent corruption of this a
  * mutex lock cooling_cpufreq_lock is used.
  */
 struct cpufreq_cooling_device {
@@ -54,9 +50,7 @@ struct cpufreq_cooling_device {
 	unsigned int cpufreq_state;
 	unsigned int cpufreq_val;
 	struct cpumask allowed_cpus;
-	struct list_head node;
 };
-static LIST_HEAD(cooling_cpufreq_list);
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
 
@@ -70,6 +64,11 @@ static struct cpufreq_cooling_device *notify_device;
  * get_idr - function to get a unique id.
  * @idr: struct idr * handle used to create a id.
  * @id: int * value generated by this function.
+ *
+ * This function will populate @id with an unique
+ * id, using the idr API.
+ *
+ * Return: 0 on success, an error code on failure.
  */
 static int get_idr(struct idr *idr, int *id)
 {
@@ -81,6 +80,7 @@ static int get_idr(struct idr *idr, int *id)
 	if (unlikely(ret < 0))
 		return ret;
 	*id = ret;
+
 	return 0;
 }
 
@@ -99,63 +99,162 @@ static void release_idr(struct idr *idr, int id)
 /* Below code defines functions to be used for cpufreq as cooling device */
 
 /**
- * is_cpufreq_valid - function to check if a cpu has frequency transition policy.
+ * is_cpufreq_valid - function to check frequency transitioning capability.
  * @cpu: cpu for which check is needed.
+ *
+ * This function will check the current state of the system if
+ * it is capable of changing the frequency for a given @cpu.
+ *
+ * Return: 0 if the system is not currently capable of changing
+ * the frequency of given cpu. !0 in case the frequency is changeable.
  */
 static int is_cpufreq_valid(int cpu)
 {
 	struct cpufreq_policy policy;
+
 	return !cpufreq_get_policy(&policy, cpu);
 }
 
+enum cpufreq_cooling_property {
+	GET_LEVEL,
+	GET_FREQ,
+	GET_MAXL,
+};
+
 /**
- * get_cpu_frequency - get the absolute value of frequency from level.
- * @cpu: cpu for which frequency is fetched.
- * @level: level of frequency, equals cooling state of cpu cooling device
- *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
+ * get_property - fetch a property of interest for a give cpu.
+ * @cpu: cpu for which the property is required
+ * @input: query parameter
+ * @output: query return
+ * @property: type of query (frequency, level, max level)
+ *
+ * This is the common function to
+ * 1. get maximum cpu cooling states
+ * 2. translate frequency to cooling state
+ * 3. translate cooling state to frequency
+ * Note that the code may be not in good shape
+ * but it is written in this way in order to:
+ * a) reduce duplicate code as most of the code can be shared.
+ * b) make sure the logic is consistent when translating between
+ *    cooling states and frequencies.
+ *
+ * Return: 0 on success, -EINVAL when invalid parameters are passed.
  */
-static unsigned int get_cpu_frequency(unsigned int cpu, unsigned long level)
+static int get_property(unsigned int cpu, unsigned long input,
+			unsigned int *output,
+			enum cpufreq_cooling_property property)
 {
-	int ret = 0, i = 0;
-	unsigned long level_index;
-	bool descend = false;
+	int i, j;
+	unsigned long max_level = 0, level = 0;
+	unsigned int freq = CPUFREQ_ENTRY_INVALID;
+	int descend = -1;
 	struct cpufreq_frequency_table *table =
 					cpufreq_frequency_get_table(cpu);
+
+	if (!output)
+		return -EINVAL;
+
 	if (!table)
-		return ret;
+		return -EINVAL;
 
-	while (table[i].frequency != CPUFREQ_TABLE_END) {
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		/* ignore invalid entries */
 		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
 			continue;
 
-		/*check if table in ascending or descending order*/
-		if ((table[i + 1].frequency != CPUFREQ_TABLE_END) &&
-			(table[i + 1].frequency < table[i].frequency)
-			&& !descend) {
-			descend = true;
-		}
+		/* ignore duplicate entry */
+		if (freq == table[i].frequency)
+			continue;
+
+		/* get the frequency order */
+		if (freq != CPUFREQ_ENTRY_INVALID && descend != -1)
+			descend = !!(freq > table[i].frequency);
 
-		/*return if level matched and table in descending order*/
-		if (descend && i == level)
-			return table[i].frequency;
-		i++;
+		freq = table[i].frequency;
+		max_level++;
 	}
-	i--;
 
-	if (level > i || descend)
-		return ret;
-	level_index = i - level;
+	/* get max level */
+	if (property == GET_MAXL) {
+		*output = (unsigned int)max_level;
+		return 0;
+	}
 
-	/*Scan the table in reverse order and match the level*/
-	while (i >= 0) {
+	if (property == GET_FREQ)
+		level = descend ? input : (max_level - input - 1);
+
+	for (i = 0, j = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		/* ignore invalid entry */
 		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
 			continue;
-		/*return if level matched*/
-		if (i == level_index)
-			return table[i].frequency;
-		i--;
+
+		/* ignore duplicate entry */
+		if (freq == table[i].frequency)
+			continue;
+
+		/* now we have a valid frequency entry */
+		freq = table[i].frequency;
+
+		if (property == GET_LEVEL && (unsigned int)input == freq) {
+			/* get level by frequency */
+			*output = descend ? j : (max_level - j - 1);
+			return 0;
+		}
+		if (property == GET_FREQ && level == j) {
+			/* get frequency by level */
+			*output = freq;
+			return 0;
+		}
+		j++;
 	}
-	return ret;
+
+	return -EINVAL;
+}
+
+/**
+ * cpufreq_cooling_get_level - for a give 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)
+{
+	unsigned int val;
+
+	if (get_property(cpu, (unsigned long)freq, &val, GET_LEVEL))
+		return THERMAL_CSTATE_INVALID;
+
+	return (unsigned long)val;
+}
+EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
+
+/**
+ * get_cpu_frequency - get the absolute value of frequency from level.
+ * @cpu: cpu for which frequency is fetched.
+ * @level: cooling level
+ *
+ * This function matches cooling level with frequency. Based on a cooling level
+ * of frequency, equals cooling state of cpu cooling device, it will return
+ * the corresponding frequency.
+ *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
+ *
+ * Return: 0 on error, the corresponding frequency otherwise.
+ */
+static unsigned int get_cpu_frequency(unsigned int cpu, unsigned long level)
+{
+	int ret = 0;
+	unsigned int freq;
+
+	ret = get_property(cpu, level, &freq, GET_FREQ);
+	if (ret)
+		return 0;
+
+	return freq;
 }
 
 /**
@@ -163,13 +262,19 @@ static unsigned int get_cpu_frequency(unsigned int cpu, unsigned long level)
  * @cpufreq_device: cpufreq_cooling_device pointer containing frequency
  *	clipping data.
  * @cooling_state: value of the cooling state.
+ *
+ * Function used to make sure the cpufreq layer is aware of current thermal
+ * limits. The limits are applied by updating the cpufreq policy.
+ *
+ * Return: 0 on success, an error code otherwise (-EINVAL in case wrong
+ * cooling state).
  */
 static int cpufreq_apply_cooling(struct cpufreq_cooling_device *cpufreq_device,
-				unsigned long cooling_state)
+				 unsigned long cooling_state)
 {
 	unsigned int cpuid, clip_freq;
-	struct cpumask *maskPtr = &cpufreq_device->allowed_cpus;
-	unsigned int cpu = cpumask_any(maskPtr);
+	struct cpumask *mask = &cpufreq_device->allowed_cpus;
+	unsigned int cpu = cpumask_any(mask);
 
 
 	/* Check if the old cooling action is same as new cooling action */
@@ -184,7 +289,7 @@ static int cpufreq_apply_cooling(struct cpufreq_cooling_device *cpufreq_device,
 	cpufreq_device->cpufreq_val = clip_freq;
 	notify_device = cpufreq_device;
 
-	for_each_cpu(cpuid, maskPtr) {
+	for_each_cpu(cpuid, mask) {
 		if (is_cpufreq_valid(cpuid))
 			cpufreq_update_policy(cpuid);
 	}
@@ -199,9 +304,15 @@ static int cpufreq_apply_cooling(struct cpufreq_cooling_device *cpufreq_device,
  * @nb:	struct notifier_block * with callback info.
  * @event: value showing cpufreq event for which this function invoked.
  * @data: callback-specific data
+ *
+ * Callback to highjack the notification on cpufreq policy transition.
+ * Every time there is a change in policy, we will intercept and
+ * update the cpufreq policy with thermal constraints.
+ *
+ * Return: 0 (success)
  */
 static int cpufreq_thermal_notifier(struct notifier_block *nb,
-					unsigned long event, void *data)
+				    unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
 	unsigned long max_freq = 0;
@@ -212,7 +323,7 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 	if (cpumask_test_cpu(policy->cpu, &notify_device->allowed_cpus))
 		max_freq = notify_device->cpufreq_val;
 
-	/* Never exceed user_policy.max*/
+	/* Never exceed user_policy.max */
 	if (max_freq > policy->user_policy.max)
 		max_freq = policy->user_policy.max;
 
@@ -222,50 +333,46 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 	return 0;
 }
 
-/*
- * cpufreq cooling device callback functions are defined below
- */
+/* cpufreq cooling device callback functions are defined below */
 
 /**
  * cpufreq_get_max_state - callback function to get the max cooling state.
  * @cdev: thermal cooling device pointer.
  * @state: fill this variable with the max cooling state.
+ *
+ * Callback for the thermal cooling device to return the cpufreq
+ * max cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
  */
 static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
-	struct cpumask *maskPtr = &cpufreq_device->allowed_cpus;
+	struct cpumask *mask = &cpufreq_device->allowed_cpus;
 	unsigned int cpu;
-	struct cpufreq_frequency_table *table;
-	unsigned long count = 0;
-	int i = 0;
-
-	cpu = cpumask_any(maskPtr);
-	table = cpufreq_frequency_get_table(cpu);
-	if (!table) {
-		*state = 0;
-		return 0;
-	}
+	unsigned int count = 0;
+	int ret;
 
-	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
-		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
-			continue;
-		count++;
-	}
+	cpu = cpumask_any(mask);
 
-	if (count > 0) {
-		*state = --count;
-		return 0;
-	}
+	ret = get_property(cpu, 0, &count, GET_MAXL);
 
-	return -EINVAL;
+	if (count > 0)
+		*state = count;
+
+	return ret;
 }
 
 /**
  * cpufreq_get_cur_state - callback function to get the current cooling state.
  * @cdev: thermal cooling device pointer.
  * @state: fill this variable with the current cooling state.
+ *
+ * Callback for the thermal cooling device to return the cpufreq
+ * current cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
  */
 static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
@@ -273,6 +380,7 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
 
 	*state = cpufreq_device->cpufreq_state;
+
 	return 0;
 }
 
@@ -280,6 +388,11 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
  * cpufreq_set_cur_state - callback function to set the current cooling state.
  * @cdev: thermal cooling device pointer.
  * @state: set this variable to the current cooling state.
+ *
+ * Callback for the thermal cooling device to change the cpufreq
+ * current cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
  */
 static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
@@ -304,9 +417,16 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ *
+ * This interface function registers the cpufreq cooling device with the name
+ * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
+ * cooling devices.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
  */
-struct thermal_cooling_device *cpufreq_cooling_register(
-	const struct cpumask *clip_cpus)
+struct thermal_cooling_device *
+cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev = NULL;
@@ -315,9 +435,9 @@ struct thermal_cooling_device *cpufreq_cooling_register(
 	int ret = 0, i;
 	struct cpufreq_policy policy;
 
-	/*Verify that all the clip cpus have same freq_min, freq_max limit*/
+	/* Verify that all the clip cpus have same freq_min, freq_max limit */
 	for_each_cpu(i, clip_cpus) {
-		/*continue if cpufreq policy not found and not return error*/
+		/* continue if cpufreq policy not found and not return error */
 		if (!cpufreq_get_policy(&policy, i))
 			continue;
 		if (min == 0 && max == 0) {