1 files changed, 136 insertions, 224 deletions

diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index ad09e51ffae4..f65f0d109fc8 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -4,6 +4,8 @@
  *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
  *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
  *
+ *  Copyright (C) 2014  Viresh Kumar <viresh.kumar@linaro.org>
+ *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -28,6 +30,20 @@
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 
+/*
+ * Cooling state <-> CPUFreq frequency
+ *
+ * Cooling states are translated to frequencies throughout this driver and this
+ * is the relation between them.
+ *
+ * Highest cooling state corresponds to lowest possible frequency.
+ *
+ * i.e.
+ *	level 0 --> 1st Max Freq
+ *	level 1 --> 2nd Max Freq
+ *	...
+ */
+
 /**
  * struct cpufreq_cooling_device - data for cooling device with cpufreq
  * @id: unique integer value corresponding to each cpufreq_cooling_device
@@ -38,25 +54,27 @@
  *	cooling	devices.
  * @cpufreq_val: integer value representing the absolute value of the clipped
  *	frequency.
+ * @max_level: maximum cooling level. One less than total number of valid
+ *	cpufreq frequencies.
  * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
+ * @node: list_head to link all cpufreq_cooling_device together.
  *
- * This structure is required for keeping information of each
- * cpufreq_cooling_device registered. In order to prevent corruption of this a
- * mutex lock cooling_cpufreq_lock is used.
+ * This structure is required for keeping information of each registered
+ * cpufreq_cooling_device.
  */
 struct cpufreq_cooling_device {
 	int id;
 	struct thermal_cooling_device *cool_dev;
 	unsigned int cpufreq_state;
 	unsigned int cpufreq_val;
+	unsigned int max_level;
+	unsigned int *freq_table;	/* In descending order */
 	struct cpumask allowed_cpus;
 	struct list_head node;
 };
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
 
-static unsigned int cpufreq_dev_count;
-
 static LIST_HEAD(cpufreq_dev_list);
 
 /**
@@ -98,120 +116,30 @@ 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 frequency transitioning capability.
- * @cpu: cpu for which check is needed.
+ * get_level: Find the level for a particular frequency
+ * @cpufreq_dev: cpufreq_dev for which the property is required
+ * @freq: Frequency
  *
- * 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.
+ * Return: level on success, THERMAL_CSTATE_INVALID on error.
  */
-static int is_cpufreq_valid(int cpu)
+static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev,
+			       unsigned int freq)
 {
-	struct cpufreq_policy policy;
-
-	return !cpufreq_get_policy(&policy, cpu);
-}
-
-enum cpufreq_cooling_property {
-	GET_LEVEL,
-	GET_FREQ,
-	GET_MAXL,
-};
-
-/**
- * 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 int get_property(unsigned int cpu, unsigned long input,
-			unsigned int *output,
-			enum cpufreq_cooling_property property)
-{
-	int i;
-	unsigned long max_level = 0, level = 0;
-	unsigned int freq = CPUFREQ_ENTRY_INVALID;
-	int descend = -1;
-	struct cpufreq_frequency_table *pos, *table =
-					cpufreq_frequency_get_table(cpu);
-
-	if (!output)
-		return -EINVAL;
-
-	if (!table)
-		return -EINVAL;
-
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* get the frequency order */
-		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
-			descend = freq > pos->frequency;
-
-		freq = pos->frequency;
-		max_level++;
-	}
-
-	/* No valid cpu frequency entry */
-	if (max_level == 0)
-		return -EINVAL;
+	unsigned long level;
 
-	/* max_level is an index, not a counter */
-	max_level--;
+	for (level = 0; level <= cpufreq_dev->max_level; level++) {
+		if (freq == cpufreq_dev->freq_table[level])
+			return level;
 
-	/* get max level */
-	if (property == GET_MAXL) {
-		*output = (unsigned int)max_level;
-		return 0;
+		if (freq > cpufreq_dev->freq_table[level])
+			break;
 	}
 
-	if (property == GET_FREQ)
-		level = descend ? input : (max_level - input);
-
-	i = 0;
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* now we have a valid frequency entry */
-		freq = pos->frequency;
-
-		if (property == GET_LEVEL && (unsigned int)input == freq) {
-			/* get level by frequency */
-			*output = descend ? i : (max_level - i);
-			return 0;
-		}
-		if (property == GET_FREQ && level == i) {
-			/* get frequency by level */
-			*output = freq;
-			return 0;
-		}
-		i++;
-	}
-
-	return -EINVAL;
+	return THERMAL_CSTATE_INVALID;
 }
 
 /**
- * cpufreq_cooling_get_level - for a give cpu, return the cooling level.
+ * cpufreq_cooling_get_level - for a given cpu, return the cooling level.
  * @cpu: cpu for which the level is required
  * @freq: the frequency of interest
  *
@@ -223,77 +151,21 @@ static int get_property(unsigned int cpu, unsigned long input,
  */
 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;
-}
-
-/**
- * cpufreq_apply_cooling - function to apply frequency clipping.
- * @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 int cpuid, clip_freq;
-	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 */
-	if (cpufreq_device->cpufreq_state == cooling_state)
-		return 0;
-
-	clip_freq = get_cpu_frequency(cpu, cooling_state);
-	if (!clip_freq)
-		return -EINVAL;
-
-	cpufreq_device->cpufreq_state = cooling_state;
-	cpufreq_device->cpufreq_val = clip_freq;
+	struct cpufreq_cooling_device *cpufreq_dev;
 
-	for_each_cpu(cpuid, mask) {
-		if (is_cpufreq_valid(cpuid))
-			cpufreq_update_policy(cpuid);
+	mutex_lock(&cooling_cpufreq_lock);
+	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+		if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
+			mutex_unlock(&cooling_cpufreq_lock);
+			return get_level(cpufreq_dev, freq);
+		}
 	}
+	mutex_unlock(&cooling_cpufreq_lock);
 
-	return 0;
+	pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu);
+	return THERMAL_CSTATE_INVALID;
 }
+EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
 
 /**
  * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
@@ -323,11 +195,6 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 					&cpufreq_dev->allowed_cpus))
 			continue;
 
-		if (!cpufreq_dev->cpufreq_val)
-			cpufreq_dev->cpufreq_val = get_cpu_frequency(
-					cpumask_any(&cpufreq_dev->allowed_cpus),
-					cpufreq_dev->cpufreq_state);
-
 		max_freq = cpufreq_dev->cpufreq_val;
 
 		if (policy->max != max_freq)
@@ -354,19 +221,9 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
-	struct cpumask *mask = &cpufreq_device->allowed_cpus;
-	unsigned int cpu;
-	unsigned int count = 0;
-	int ret;
-
-	cpu = cpumask_any(mask);
-
-	ret = get_property(cpu, 0, &count, GET_MAXL);
 
-	if (count > 0)
-		*state = count;
-
-	return ret;
+	*state = cpufreq_device->max_level;
+	return 0;
 }
 
 /**
@@ -403,8 +260,24 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	unsigned int cpu = cpumask_any(&cpufreq_device->allowed_cpus);
+	unsigned int clip_freq;
+
+	/* Request state should be less than max_level */
+	if (WARN_ON(state > cpufreq_device->max_level))
+		return -EINVAL;
+
+	/* Check if the old cooling action is same as new cooling action */
+	if (cpufreq_device->cpufreq_state == state)
+		return 0;
 
-	return cpufreq_apply_cooling(cpufreq_device, state);
+	clip_freq = cpufreq_device->freq_table[state];
+	cpufreq_device->cpufreq_state = state;
+	cpufreq_device->cpufreq_val = clip_freq;
+
+	cpufreq_update_policy(cpu);
+
+	return 0;
 }
 
 /* Bind cpufreq callbacks to thermal cooling device ops */
@@ -419,10 +292,25 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
 	.notifier_call = cpufreq_thermal_notifier,
 };
 
+static unsigned int find_next_max(struct cpufreq_frequency_table *table,
+				  unsigned int prev_max)
+{
+	struct cpufreq_frequency_table *pos;
+	unsigned int max = 0;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		if (pos->frequency > max && pos->frequency < prev_max)
+			max = pos->frequency;
+	}
+
+	return max;
+}
+
 /**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
  * @np: a valid struct device_node to the cooling device device tree node
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * Normally this should be same as cpufreq policy->related_cpus.
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -437,37 +325,42 @@ __cpufreq_cooling_register(struct device_node *np,
 			   const struct cpumask *clip_cpus)
 {
 	struct thermal_cooling_device *cool_dev;
-	struct cpufreq_cooling_device *cpufreq_dev = NULL;
-	unsigned int min = 0, max = 0;
+	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	int ret = 0, i;
-	struct cpufreq_policy policy;
+	struct cpufreq_frequency_table *pos, *table;
+	unsigned int freq, i;
+	int ret;
 
-	/* 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 */
-		if (!cpufreq_get_policy(&policy, i))
-			continue;
-		if (min == 0 && max == 0) {
-			min = policy.cpuinfo.min_freq;
-			max = policy.cpuinfo.max_freq;
-		} else {
-			if (min != policy.cpuinfo.min_freq ||
-			    max != policy.cpuinfo.max_freq)
-				return ERR_PTR(-EINVAL);
-		}
+	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
+	if (!table) {
+		pr_debug("%s: CPUFreq table not found\n", __func__);
+		return ERR_PTR(-EPROBE_DEFER);
 	}
-	cpufreq_dev = kzalloc(sizeof(struct cpufreq_cooling_device),
-			      GFP_KERNEL);
+
+	cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL);
 	if (!cpufreq_dev)
 		return ERR_PTR(-ENOMEM);
 
+	/* Find max levels */
+	cpufreq_for_each_valid_entry(pos, table)
+		cpufreq_dev->max_level++;
+
+	cpufreq_dev->freq_table = kmalloc(sizeof(*cpufreq_dev->freq_table) *
+					  cpufreq_dev->max_level, GFP_KERNEL);
+	if (!cpufreq_dev->freq_table) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_cdev;
+	}
+
+	/* max_level is an index, not a counter */
+	cpufreq_dev->max_level--;
+
 	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
 
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
-		kfree(cpufreq_dev);
-		return ERR_PTR(-EINVAL);
+		cool_dev = ERR_PTR(ret);
+		goto free_table;
 	}
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
@@ -475,25 +368,44 @@ __cpufreq_cooling_register(struct device_node *np,
 
 	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
 						      &cpufreq_cooling_ops);
-	if (IS_ERR(cool_dev)) {
-		release_idr(&cpufreq_idr, cpufreq_dev->id);
-		kfree(cpufreq_dev);
-		return cool_dev;
+	if (IS_ERR(cool_dev))
+		goto remove_idr;
+
+	/* Fill freq-table in descending order of frequencies */
+	for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
+		freq = find_next_max(table, freq);
+		cpufreq_dev->freq_table[i] = freq;
+
+		/* Warn for duplicate entries */
+		if (!freq)
+			pr_warn("%s: table has duplicate entries\n", __func__);
+		else
+			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
+
+	cpufreq_dev->cpufreq_val = cpufreq_dev->freq_table[0];
 	cpufreq_dev->cool_dev = cool_dev;
-	cpufreq_dev->cpufreq_state = 0;
+
 	mutex_lock(&cooling_cpufreq_lock);
 
 	/* Register the notifier for first cpufreq cooling device */
-	if (cpufreq_dev_count == 0)
+	if (list_empty(&cpufreq_dev_list))
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
-	cpufreq_dev_count++;
 	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
 
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	return cool_dev;
+
+remove_idr:
+	release_idr(&cpufreq_idr, cpufreq_dev->id);
+free_table:
+	kfree(cpufreq_dev->freq_table);
+free_cdev:
+	kfree(cpufreq_dev);
+
+	return cool_dev;
 }
 
 /**
@@ -554,16 +466,16 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	cpufreq_dev = cdev->devdata;
 	mutex_lock(&cooling_cpufreq_lock);
 	list_del(&cpufreq_dev->node);
-	cpufreq_dev_count--;
 
 	/* Unregister the notifier for the last cpufreq cooling device */
-	if (cpufreq_dev_count == 0)
+	if (list_empty(&cpufreq_dev_list))
 		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
 					    CPUFREQ_POLICY_NOTIFIER);
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->freq_table);
 	kfree(cpufreq_dev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);