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

Conflicts:
	drivers/thermal/cpu_cooling.c

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";
+	};

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.
+Enabling CONFIG_THERMAL_EMULATION option will make this support available.
-When it's enabled, sysfs node will be created under
+When it's enabled, sysfs node will be created as
-/sys/bus/platform/devices/'exynos device name'/ with name of 'emulation'.
+/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

Documentation/thermal/sysfs-api.txt

@@ -265,6 +265,10 @@ 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 *
 *****************************
@@ -375,11 +379,3 @@ 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.

drivers/thermal/Kconfig

@@ -67,7 +67,7 @@ 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
@@ -86,6 +86,10 @@ 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 +121,6 @@ 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 +139,14 @@ 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

drivers/thermal/Makefile

@@ -3,14 +3,15 @@
 #
 
 obj-$(CONFIG_THERMAL)		+= thermal_sys.o
+thermal_sys-y			+= thermal_core.o
 
 # governors
-obj-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
+thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
-obj-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
+thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
-obj-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
+thermal_sys-$(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
 

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");

drivers/thermal/cpu_cooling.c

@@ -108,6 +108,105 @@ static int is_cpufreq_valid(int cpu)
 	return !cpufreq_get_policy(&policy, cpu);
 }
 
+enum cpufreq_cooling_property {
+	GET_LEVEL,
+	GET_FREQ,
+	GET_MAXL,
+};
+
+/*
+ * 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.
+*/
+static int get_property(unsigned int cpu, unsigned long input,
+	unsigned int* output, enum cpufreq_cooling_property property)
+{
+	int i, j;
+	unsigned long max_level = 0, level;
+	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 -EINVAL;
+
+	
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		/* ignore invalid entries */
+		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
+			continue;
+
+		/* 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);
+
+		freq = table[i].frequency;
+		max_level++;
+	}
+
+	/* get max level */
+	if (property == GET_MAXL) {
+		*output = (unsigned int)max_level;
+		return 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;
+
+		/* 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 -EINVAL;
+}
+
+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(cpufreq_cooling_get_level);
+
 /**
  * get_cpu_frequency - get the absolute value of frequency from level.
  * @cpu: cpu for which frequency is fetched.
@@ -116,46 +215,13 @@ static int is_cpufreq_valid(int cpu)
  */
 static unsigned int get_cpu_frequency(unsigned int cpu, unsigned long level)
 {
-	int ret = 0, i = 0;
+	int ret = 0;
-	unsigned long level_index;
+	unsigned int freq;
-	bool descend = false;
-	struct cpufreq_frequency_table *table =
-					cpufreq_frequency_get_table(cpu);
-	if (!table)
-		return ret;
 
-	while (table[i].frequency != CPUFREQ_TABLE_END) {
+	ret = get_property(cpu, level, &freq, GET_FREQ);
-		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
+	if (ret)
-			continue;
+		return 0;
-
+	return freq;
-		/*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;
-		}
-
-		/*return if level matched and table in descending order*/
-		if (descend && i == level)
-			return table[i].frequency;
-		i++;
-	}
-	i--;
-
-	if (level > i || descend)
-		return ret;
-	level_index = i - level;
-
-	/*Scan the table in reverse order and match the level*/
-	while (i >= 0) {
-		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
-			continue;
-		/*return if level matched*/
-		if (i == level_index)
-			return table[i].frequency;
-		i--;
-	}
-	return ret;
 }
 
 /**
@@ -237,29 +303,17 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
 	struct cpumask *mask = &cpufreq_device->allowed_cpus;
 	unsigned int cpu;
-	struct cpufreq_frequency_table *table;
 	unsigned long count = 0;
-	int i = 0;
+	int ret;
 
 	cpu = cpumask_any(mask);
-	table = cpufreq_frequency_get_table(cpu);
-	if (!table) {
-		*state = 0;
-		return 0;
-	}
 
-	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
+	ret = get_property(cpu, 0, (unsigned int *)&count, GET_MAXL);
-		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
-			continue;
-		count++;
-	}
 
-	if (count > 0) {
+	if (count > 0)
-		*state = --count;
+		*state = count;
-		return 0;
-	}
 
-	return -EINVAL;
+	return ret;
 }
 
 /**

drivers/thermal/exynos_thermal.c

@@ -39,8 +39,6 @@
 #include <linux/cpu_cooling.h>
 #include <linux/of.h>
 
-#include <plat/cpu.h>
-
 /* Exynos generic registers */
 #define EXYNOS_TMU_REG_TRIMINFO		0x0
 #define EXYNOS_TMU_REG_CONTROL		0x20
@@ -100,13 +98,13 @@
 #define IDLE_INTERVAL 10000
 #define MCELSIUS	1000
 
-#ifdef CONFIG_EXYNOS_THERMAL_EMUL
+#ifdef CONFIG_THERMAL_EMULATION
 #define EXYNOS_EMUL_TIME	0x57F0
 #define EXYNOS_EMUL_TIME_SHIFT	16
 #define EXYNOS_EMUL_DATA_SHIFT	8
 #define EXYNOS_EMUL_DATA_MASK	0xFF
 #define EXYNOS_EMUL_ENABLE	0x1
-#endif /* CONFIG_EXYNOS_THERMAL_EMUL */
+#endif /* CONFIG_THERMAL_EMULATION */
 
 /* CPU Zone information */
 #define PANIC_ZONE      4
@@ -145,6 +143,7 @@ struct	thermal_cooling_conf {
 struct thermal_sensor_conf {
 	char name[SENSOR_NAME_LEN];
 	int (*read_temperature)(void *data);
+	int (*write_emul_temp)(void *drv_data, unsigned long temp);
 	struct thermal_trip_point_conf trip_data;
 	struct thermal_cooling_conf cooling_data;
 	void *private_data;
@@ -242,26 +241,6 @@ static int exynos_get_crit_temp(struct thermal_zone_device *thermal,
 	return ret;
 }
 
-static int exynos_get_frequency_level(unsigned int cpu, unsigned int freq)
-{
-	int i = 0, ret = -EINVAL;
-	struct cpufreq_frequency_table *table = NULL;
-#ifdef CONFIG_CPU_FREQ
-	table = cpufreq_frequency_get_table(cpu);
-#endif
-	if (!table)
-		return ret;
-
-	while (table[i].frequency != CPUFREQ_TABLE_END) {
-		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
-			continue;
-		if (table[i].frequency == freq)
-			return i;
-		i++;
-	}
-	return ret;
-}
-
 /* Bind callback functions for thermal zone */
 static int exynos_bind(struct thermal_zone_device *thermal,
 			struct thermal_cooling_device *cdev)
@@ -288,8 +267,8 @@ static int exynos_bind(struct thermal_zone_device *thermal,
 	/* Bind the thermal zone to the cpufreq cooling device */
 	for (i = 0; i < tab_size; i++) {
 		clip_data = (struct freq_clip_table *)&(tab_ptr[i]);
-		level = exynos_get_frequency_level(0, clip_data->freq_clip_max);
+		level = cpufreq_cooling_get_level(0, clip_data->freq_clip_max);
-		if (level < 0)
+		if (level == THERMAL_CSTATE_INVALID)
 			return 0;
 		switch (GET_ZONE(i)) {
 		case MONITOR_ZONE:
@@ -369,6 +348,23 @@ static int exynos_get_temp(struct thermal_zone_device *thermal,
 	return 0;
 }
 
+/* Get temperature callback functions for thermal zone */
+static int exynos_set_emul_temp(struct thermal_zone_device *thermal,
+						unsigned long temp)
+{
+	void *data;
+	int ret = -EINVAL;
+
+	if (!th_zone->sensor_conf) {
+		pr_info("Temperature sensor not initialised\n");
+		return -EINVAL;
+	}
+	data = th_zone->sensor_conf->private_data;
+	if (th_zone->sensor_conf->write_emul_temp)
+		ret = th_zone->sensor_conf->write_emul_temp(data, temp);
+	return ret;
+}
+
 /* Get the temperature trend */
 static int exynos_get_trend(struct thermal_zone_device *thermal,
 			int trip, enum thermal_trend *trend)
@@ -392,6 +388,7 @@ static struct thermal_zone_device_ops const exynos_dev_ops = {
 	.bind = exynos_bind,
 	.unbind = exynos_unbind,
 	.get_temp = exynos_get_temp,
+	.set_emul_temp = exynos_set_emul_temp,
 	.get_trend = exynos_get_trend,
 	.get_mode = exynos_get_mode,
 	.set_mode = exynos_set_mode,
@@ -714,6 +711,47 @@ static int exynos_tmu_read(struct exynos_tmu_data *data)
 	return temp;
 }
 
+#ifdef CONFIG_THERMAL_EMULATION
+static int exynos_tmu_set_emulation(void *drv_data, unsigned long temp)
+{
+	struct exynos_tmu_data *data = drv_data;
+	unsigned int reg;
+	int ret = -EINVAL;
+
+	if (data->soc == SOC_ARCH_EXYNOS4210)
+		goto out;
+
+	if (temp && temp < MCELSIUS)
+		goto out;
+
+	mutex_lock(&data->lock);
+	clk_enable(data->clk);
+
+	reg = readl(data->base + EXYNOS_EMUL_CON);
+
+	if (temp) {
+		temp /= MCELSIUS;
+
+		reg = (EXYNOS_EMUL_TIME << EXYNOS_EMUL_TIME_SHIFT) |
+			(temp_to_code(data, temp)
+			 << EXYNOS_EMUL_DATA_SHIFT) | EXYNOS_EMUL_ENABLE;
+	} else {
+		reg &= ~EXYNOS_EMUL_ENABLE;
+	}
+
+	writel(reg, data->base + EXYNOS_EMUL_CON);
+
+	clk_disable(data->clk);
+	mutex_unlock(&data->lock);
+	return 0;
+out:
+	return ret;
+}
+#else
+static int exynos_tmu_set_emulation(void *drv_data,	unsigned long temp)
+	{ return -EINVAL; }
+#endif/*CONFIG_THERMAL_EMULATION*/
+
 static void exynos_tmu_work(struct work_struct *work)
 {
 	struct exynos_tmu_data *data = container_of(work,
@@ -747,6 +785,7 @@ static irqreturn_t exynos_tmu_irq(int irq, void *id)
 static struct thermal_sensor_conf exynos_sensor_conf = {
 	.name			= "exynos-therm",
 	.read_temperature	= (int (*)(void *))exynos_tmu_read,
+	.write_emul_temp	= exynos_tmu_set_emulation,
 };
 
 #if defined(CONFIG_CPU_EXYNOS4210)
@@ -853,93 +892,6 @@ static inline struct  exynos_tmu_platform_data *exynos_get_driver_data(
 			platform_get_device_id(pdev)->driver_data;
 }
 
-#ifdef CONFIG_EXYNOS_THERMAL_EMUL
-static ssize_t exynos_tmu_emulation_show(struct device *dev,
-					 struct device_attribute *attr,
-					 char *buf)
-{
-	struct platform_device *pdev = container_of(dev,
-					struct platform_device, dev);
-	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	unsigned int reg;
-	u8 temp_code;
-	int temp = 0;
-
-	if (data->soc == SOC_ARCH_EXYNOS4210)
-		goto out;
-
-	mutex_lock(&data->lock);
-	clk_enable(data->clk);
-	reg = readl(data->base + EXYNOS_EMUL_CON);
-	clk_disable(data->clk);
-	mutex_unlock(&data->lock);
-
-	if (reg & EXYNOS_EMUL_ENABLE) {
-		reg >>= EXYNOS_EMUL_DATA_SHIFT;
-		temp_code = reg & EXYNOS_EMUL_DATA_MASK;
-		temp = code_to_temp(data, temp_code);
-	}
-out:
-	return sprintf(buf, "%d\n", temp * MCELSIUS);
-}
-
-static ssize_t exynos_tmu_emulation_store(struct device *dev,
-					struct device_attribute *attr,
-					const char *buf, size_t count)
-{
-	struct platform_device *pdev = container_of(dev,
-					struct platform_device, dev);
-	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	unsigned int reg;
-	int temp;
-
-	if (data->soc == SOC_ARCH_EXYNOS4210)
-		goto out;
-
-	if (!sscanf(buf, "%d\n", &temp) || temp < 0)
-		return -EINVAL;
-
-	mutex_lock(&data->lock);
-	clk_enable(data->clk);
-
-	reg = readl(data->base + EXYNOS_EMUL_CON);
-
-	if (temp) {
-		/* Both CELSIUS and MCELSIUS type are available for input */
-		if (temp > MCELSIUS)
-			temp /= MCELSIUS;
-
-		reg = (EXYNOS_EMUL_TIME << EXYNOS_EMUL_TIME_SHIFT) |
-			(temp_to_code(data, (temp / MCELSIUS))
-			 << EXYNOS_EMUL_DATA_SHIFT) | EXYNOS_EMUL_ENABLE;
-	} else {
-		reg &= ~EXYNOS_EMUL_ENABLE;
-	}
-
-	writel(reg, data->base + EXYNOS_EMUL_CON);
-
-	clk_disable(data->clk);
-	mutex_unlock(&data->lock);
-
-out:
-	return count;
-}
-
-static DEVICE_ATTR(emulation, 0644, exynos_tmu_emulation_show,
-					exynos_tmu_emulation_store);
-static int create_emulation_sysfs(struct device *dev)
-{
-	return device_create_file(dev, &dev_attr_emulation);
-}
-static void remove_emulation_sysfs(struct device *dev)
-{
-	device_remove_file(dev, &dev_attr_emulation);
-}
-#else
-static inline int create_emulation_sysfs(struct device *dev) { return 0; }
-static inline void remove_emulation_sysfs(struct device *dev) {}
-#endif
-
 static int exynos_tmu_probe(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data;
@@ -1039,10 +991,6 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
-	ret = create_emulation_sysfs(&pdev->dev);
-	if (ret)
-		dev_err(&pdev->dev, "Failed to create emulation mode sysfs node\n");
-
 	return 0;
 err_clk:
 	platform_set_drvdata(pdev, NULL);
@@ -1054,8 +1002,6 @@ static int exynos_tmu_remove(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
 
-	remove_emulation_sysfs(&pdev->dev);
-
 	exynos_tmu_control(pdev, false);
 
 	exynos_unregister_thermal();

drivers/thermal/fair_share.c

@@ -22,9 +22,6 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
 #include <linux/thermal.h>
 
 #include "thermal_core.h"
@@ -111,23 +108,15 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 static struct thermal_governor thermal_gov_fair_share = {
 	.name		= "fair_share",
 	.throttle	= fair_share_throttle,
-	.owner		= THIS_MODULE,
 };
 
-static int __init thermal_gov_fair_share_init(void)
+int thermal_gov_fair_share_register(void)
 {
 	return thermal_register_governor(&thermal_gov_fair_share);
 }
 
-static void __exit thermal_gov_fair_share_exit(void)
+void thermal_gov_fair_share_unregister(void)
 {
 	thermal_unregister_governor(&thermal_gov_fair_share);
 }
 
-/* This should load after thermal framework */
-fs_initcall(thermal_gov_fair_share_init);
-module_exit(thermal_gov_fair_share_exit);
-
-MODULE_AUTHOR("Durgadoss R");
-MODULE_DESCRIPTION("A simple weight based thermal throttling governor");
-MODULE_LICENSE("GPL");

drivers/thermal/rcar_thermal.c

@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -377,6 +378,9 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	spin_lock_init(&common->lock);
 	common->dev = dev;
 
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
 	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (irq) {
 		int ret;
@@ -419,12 +423,15 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 		priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 		if (!priv) {
 			dev_err(dev, "Could not allocate priv\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto error_unregister;
 		}
 
 		priv->base = devm_ioremap_resource(dev, res);
-		if (IS_ERR(priv->base))
+		if (IS_ERR(priv->base)) {
-			return PTR_ERR(priv->base);
+			ret = PTR_ERR(priv->base);
+			goto error_unregister;
+		}
 
 		priv->common = common;
 		priv->id = i;
@@ -443,10 +450,10 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 			goto error_unregister;
 		}
 
-		list_move_tail(&priv->list, &common->head);
-
 		if (rcar_has_irq_support(priv))
 			rcar_thermal_irq_enable(priv);
+
+		list_move_tail(&priv->list, &common->head);
 	}
 
 	platform_set_drvdata(pdev, common);
@@ -456,8 +463,14 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	return 0;
 
 error_unregister:
-	rcar_thermal_for_each_priv(priv, common)
+	rcar_thermal_for_each_priv(priv, common) {
 		thermal_zone_device_unregister(priv->zone);
+		if (rcar_has_irq_support(priv))
+			rcar_thermal_irq_disable(priv);
+	}
+
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 
 	return ret;
 }
@@ -465,13 +478,20 @@ error_unregister:
 static int rcar_thermal_remove(struct platform_device *pdev)
 {
 	struct rcar_thermal_common *common = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
 	struct rcar_thermal_priv *priv;
 
-	rcar_thermal_for_each_priv(priv, common)
+	rcar_thermal_for_each_priv(priv, common) {
 		thermal_zone_device_unregister(priv->zone);
+		if (rcar_has_irq_support(priv))
+			rcar_thermal_irq_disable(priv);
+	}
 
 	platform_set_drvdata(pdev, NULL);
 
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
 	return 0;
 }
 

drivers/thermal/step_wise.c

@@ -22,9 +22,6 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
 #include <linux/thermal.h>
 
 #include "thermal_core.h"
@@ -59,9 +56,12 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 
 	switch (trend) {
 	case THERMAL_TREND_RAISING:
-		if (throttle)
+		if (throttle) {
 			cur_state = cur_state < instance->upper ?
 				    (cur_state + 1) : instance->upper;
+			if (cur_state < instance->lower)
+				cur_state = instance->lower;
+		}
 		break;
 	case THERMAL_TREND_RAISE_FULL:
 		if (throttle)
@@ -71,8 +71,11 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 		if (cur_state == instance->lower) {
 			if (!throttle)
 				cur_state = -1;
-		} else
+		} else {
 			cur_state -= 1;
+			if (cur_state > instance->upper)
+				cur_state = instance->upper;
+		}
 		break;
 	case THERMAL_TREND_DROP_FULL:
 		if (cur_state == instance->lower) {
@@ -180,23 +183,14 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip)
 static struct thermal_governor thermal_gov_step_wise = {
 	.name		= "step_wise",
 	.throttle	= step_wise_throttle,
-	.owner		= THIS_MODULE,
 };
 
-static int __init thermal_gov_step_wise_init(void)
+int thermal_gov_step_wise_register(void)
 {
 	return thermal_register_governor(&thermal_gov_step_wise);
 }
 
-static void __exit thermal_gov_step_wise_exit(void)
+void thermal_gov_step_wise_unregister(void)
 {
 	thermal_unregister_governor(&thermal_gov_step_wise);
 }
-
-/* This should load after thermal framework */
-fs_initcall(thermal_gov_step_wise_init);
-module_exit(thermal_gov_step_wise_exit);
-
-MODULE_AUTHOR("Durgadoss R");
-MODULE_DESCRIPTION("A step-by-step thermal throttling governor");
-MODULE_LICENSE("GPL");

drivers/thermal/thermal_core.c

@@ -99,7 +99,6 @@ int thermal_register_governor(struct thermal_governor *governor)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(thermal_register_governor);
 
 void thermal_unregister_governor(struct thermal_governor *governor)
 {
@@ -127,7 +126,6 @@ exit:
 	mutex_unlock(&thermal_governor_lock);
 	return;
 }
-EXPORT_SYMBOL_GPL(thermal_unregister_governor);
 
 static int get_idr(struct idr *idr, struct mutex *lock, int *id)
 {
@@ -1858,30 +1856,69 @@ static inline int genetlink_init(void) { return 0; }
 static inline void genetlink_exit(void) {}
 #endif /* !CONFIG_NET */
 
+static int __init thermal_register_governors(void)
+{
+	int result;
+
+	result = thermal_gov_step_wise_register();
+	if (result)
+		return result;
+
+	result = thermal_gov_fair_share_register();
+	if (result)
+		return result;
+
+	return thermal_gov_user_space_register();
+}
+
+static void thermal_unregister_governors(void)
+{
+	thermal_gov_step_wise_unregister();
+	thermal_gov_fair_share_unregister();
+	thermal_gov_user_space_unregister();
+}
+
 static int __init thermal_init(void)
 {
-	int result = 0;
+	int result;
+
+	result = thermal_register_governors();
+	if (result)
+		goto error;
 
 	result = class_register(&thermal_class);
-	if (result) {
+	if (result)
-		idr_destroy(&thermal_tz_idr);
+		goto unregister_governors;
-		idr_destroy(&thermal_cdev_idr);
+
-		mutex_destroy(&thermal_idr_lock);
-		mutex_destroy(&thermal_list_lock);
-		return result;
-	}
 	result = genetlink_init();
+	if (result)
+		goto unregister_class;
+
+	return 0;
+
+unregister_governors:
+	thermal_unregister_governors();
+unregister_class:
+	class_unregister(&thermal_class);
+error:
+	idr_destroy(&thermal_tz_idr);
+	idr_destroy(&thermal_cdev_idr);
+	mutex_destroy(&thermal_idr_lock);
+	mutex_destroy(&thermal_list_lock);
+	mutex_destroy(&thermal_governor_lock);
 	return result;
 }
 
 static void __exit thermal_exit(void)
 {
+	genetlink_exit();
 	class_unregister(&thermal_class);
+	thermal_unregister_governors();
 	idr_destroy(&thermal_tz_idr);
 	idr_destroy(&thermal_cdev_idr);
 	mutex_destroy(&thermal_idr_lock);
 	mutex_destroy(&thermal_list_lock);
-	genetlink_exit();
+	mutex_destroy(&thermal_governor_lock);
 }
 
 fs_initcall(thermal_init);

drivers/thermal/thermal_core.h

@@ -50,4 +50,31 @@ struct thermal_instance {
 	struct list_head cdev_node; /* node in cdev->thermal_instances */
 };
 
+int thermal_register_governor(struct thermal_governor *);
+void thermal_unregister_governor(struct thermal_governor *);
+
+#ifdef CONFIG_THERMAL_GOV_STEP_WISE
+int thermal_gov_step_wise_register(void);
+void thermal_gov_step_wise_unregister(void);
+#else
+static inline int thermal_gov_step_wise_register(void) { return 0; }
+static inline void thermal_gov_step_wise_unregister(void) {}
+#endif /* CONFIG_THERMAL_GOV_STEP_WISE */
+
+#ifdef CONFIG_THERMAL_GOV_FAIR_SHARE
+int thermal_gov_fair_share_register(void);
+void thermal_gov_fair_share_unregister(void);
+#else
+static inline int thermal_gov_fair_share_register(void) { return 0; }
+static inline void thermal_gov_fair_share_unregister(void) {}
+#endif /* CONFIG_THERMAL_GOV_FAIR_SHARE */
+
+#ifdef CONFIG_THERMAL_GOV_USER_SPACE
+int thermal_gov_user_space_register(void);
+void thermal_gov_user_space_unregister(void);
+#else
+static inline int thermal_gov_user_space_register(void) { return 0; }
+static inline void thermal_gov_user_space_unregister(void) {}
+#endif /* CONFIG_THERMAL_GOV_USER_SPACE */
+
 #endif /* __THERMAL_CORE_H__ */

drivers/thermal/user_space.c

@@ -22,9 +22,6 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
 #include <linux/thermal.h>
 
 #include "thermal_core.h"
@@ -46,23 +43,15 @@ static int notify_user_space(struct thermal_zone_device *tz, int trip)
 static struct thermal_governor thermal_gov_user_space = {
 	.name		= "user_space",
 	.throttle	= notify_user_space,
-	.owner		= THIS_MODULE,
 };
 
-static int __init thermal_gov_user_space_init(void)
+int thermal_gov_user_space_register(void)
 {
 	return thermal_register_governor(&thermal_gov_user_space);
 }
 
-static void __exit thermal_gov_user_space_exit(void)
+void thermal_gov_user_space_unregister(void)
 {
 	thermal_unregister_governor(&thermal_gov_user_space);
 }
 
-/* This should load after thermal framework */
-fs_initcall(thermal_gov_user_space_init);
-module_exit(thermal_gov_user_space_exit);
-
-MODULE_AUTHOR("Durgadoss R");
-MODULE_DESCRIPTION("A user space Thermal notifier");
-MODULE_LICENSE("GPL");

include/linux/cpu_cooling.h

@@ -29,7 +29,7 @@
 #define CPUFREQ_COOLING_START		0
 #define CPUFREQ_COOLING_STOP		1
 
-#if defined(CONFIG_CPU_THERMAL) || defined(CONFIG_CPU_THERMAL_MODULE)
+#ifdef CONFIG_CPU_THERMAL
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen
@@ -42,6 +42,8 @@ struct thermal_cooling_device *cpufreq_cooling_register(
  * @cdev: thermal cooling device pointer.
  */
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
+
+unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int);
 #else /* !CONFIG_CPU_THERMAL */
 static inline struct thermal_cooling_device *cpufreq_cooling_register(
 	const struct cpumask *clip_cpus)
@@ -53,6 +55,11 @@ static inline void cpufreq_cooling_unregister(
 {
 	return;
 }
+static inline unsigned long cpufreq_cooling_get_level(unsigned int,
+						 unsigned int)
+{
+	return THERMAL_CSTATE_INVALID;
+}
 #endif	/* CONFIG_CPU_THERMAL */
 
 #endif /* __CPU_COOLING_H__ */

include/linux/thermal.h

@@ -33,8 +33,11 @@
 #define THERMAL_MAX_TRIPS	12
 #define THERMAL_NAME_LENGTH	20
 
+/* invalid cooling state */
+#define THERMAL_CSTATE_INVALID -1UL
+
 /* No upper/lower limit requirement */
-#define THERMAL_NO_LIMIT	-1UL
+#define THERMAL_NO_LIMIT	THERMAL_CSTATE_INVALID
 
 /* Unit conversion macros */
 #define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
@@ -184,7 +187,6 @@ struct thermal_governor {
 	char name[THERMAL_NAME_LENGTH];
 	int (*throttle)(struct thermal_zone_device *tz, int trip);
 	struct list_head	governor_list;
-	struct module		*owner;
 };
 
 /* Structure that holds binding parameters for a zone */
@@ -244,9 +246,6 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 void thermal_cdev_update(struct thermal_cooling_device *);
 void notify_thermal_framework(struct thermal_zone_device *, int);
 
-int thermal_register_governor(struct thermal_governor *);
-void thermal_unregister_governor(struct thermal_governor *);
-
 #ifdef CONFIG_NET
 extern int thermal_generate_netlink_event(struct thermal_zone_device *tz,
 						enum events event);