1 files changed, 164 insertions, 240 deletions

diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6b9865c786ba..52569b27b426 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
+#include <linux/energy_model.h>
 
 #include <trace/events/thermal.h>
 
@@ -38,19 +39,6 @@
  */
 
 /**
- * struct freq_table - frequency table along with power entries
- * @frequency:	frequency in KHz
- * @power:	power in mW
- *
- * This structure is built when the cooling device registers and helps
- * in translating frequency to power and vice versa.
- */
-struct freq_table {
-	u32 frequency;
-	u32 power;
-};
-
-/**
  * struct time_in_idle - Idle time stats
  * @time: previous reading of the absolute time that this cpu was idle
  * @timestamp: wall time of the last invocation of get_cpu_idle_time_us()
@@ -69,7 +57,7 @@ struct time_in_idle {
  *	cooling	devices.
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
- * @freq_table: Freq table in descending order of frequencies
+ * @em: Reference on the Energy Model of the device
  * @cdev: thermal_cooling_device pointer to keep track of the
  *	registered cooling device.
  * @policy: cpufreq policy.
@@ -84,7 +72,7 @@ struct cpufreq_cooling_device {
 	u32 last_load;
 	unsigned int cpufreq_state;
 	unsigned int max_level;
-	struct freq_table *freq_table;	/* In descending order */
+	struct em_perf_domain *em;
 	struct cpufreq_policy *policy;
 	struct list_head node;
 	struct time_in_idle *idle_time;
@@ -95,8 +83,7 @@ static DEFINE_IDA(cpufreq_ida);
 static DEFINE_MUTEX(cooling_list_lock);
 static LIST_HEAD(cpufreq_cdev_list);
 
-/* Below code defines functions to be used for cpufreq as cooling device */
-
+#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
 /**
  * get_level: Find the level for a particular frequency
  * @cpufreq_cdev: cpufreq_cdev for which the property is required
@@ -107,114 +94,40 @@ static LIST_HEAD(cpufreq_cdev_list);
 static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 			       unsigned int freq)
 {
-	struct freq_table *freq_table = cpufreq_cdev->freq_table;
-	unsigned long level;
+	int i;
 
-	for (level = 1; level <= cpufreq_cdev->max_level; level++)
-		if (freq > freq_table[level].frequency)
+	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
+		if (freq > cpufreq_cdev->em->table[i].frequency)
 			break;
-
-	return level - 1;
-}
-
-/**
- * update_freq_table() - Update the freq table with power numbers
- * @cpufreq_cdev:	the cpufreq cooling device in which to update the table
- * @capacitance: dynamic power coefficient for these cpus
- *
- * Update the freq table with power numbers.  This table will be used in
- * cpu_power_to_freq() and cpu_freq_to_power() to convert between power and
- * frequency efficiently.  Power is stored in mW, frequency in KHz.  The
- * resulting table is in descending order.
- *
- * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
- * or -ENOMEM if we run out of memory.
- */
-static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev,
-			     u32 capacitance)
-{
-	struct freq_table *freq_table = cpufreq_cdev->freq_table;
-	struct dev_pm_opp *opp;
-	struct device *dev = NULL;
-	int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i;
-
-	dev = get_cpu_device(cpu);
-	if (unlikely(!dev)) {
-		pr_warn("No cpu device for cpu %d\n", cpu);
-		return -ENODEV;
 	}
 
-	num_opps = dev_pm_opp_get_opp_count(dev);
-	if (num_opps < 0)
-		return num_opps;
-
-	/*
-	 * The cpufreq table is also built from the OPP table and so the count
-	 * should match.
-	 */
-	if (num_opps != cpufreq_cdev->max_level + 1) {
-		dev_warn(dev, "Number of OPPs not matching with max_levels\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i <= cpufreq_cdev->max_level; i++) {
-		unsigned long freq = freq_table[i].frequency * 1000;
-		u32 freq_mhz = freq_table[i].frequency / 1000;
-		u64 power;
-		u32 voltage_mv;
-
-		/*
-		 * Find ceil frequency as 'freq' may be slightly lower than OPP
-		 * freq due to truncation while converting to kHz.
-		 */
-		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
-		if (IS_ERR(opp)) {
-			dev_err(dev, "failed to get opp for %lu frequency\n",
-				freq);
-			return -EINVAL;
-		}
-
-		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
-		dev_pm_opp_put(opp);
-
-		/*
-		 * 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);
-
-		/* power is stored in mW */
-		freq_table[i].power = power;
-	}
-
-	return 0;
+	return cpufreq_cdev->max_level - i - 1;
 }
 
 static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 freq)
 {
 	int i;
-	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i <= cpufreq_cdev->max_level; i++)
-		if (freq > freq_table[i].frequency)
+	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
+		if (freq > cpufreq_cdev->em->table[i].frequency)
 			break;
+	}
 
-	return freq_table[i - 1].power;
+	return cpufreq_cdev->em->table[i + 1].power;
 }
 
 static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 power)
 {
 	int i;
-	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i <= cpufreq_cdev->max_level; i++)
-		if (power > freq_table[i].power)
+	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
+		if (power > cpufreq_cdev->em->table[i].power)
 			break;
+	}
 
-	return freq_table[i - 1].frequency;
+	return cpufreq_cdev->em->table[i + 1].frequency;
 }
 
 /**
@@ -265,76 +178,6 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
 	return (raw_cpu_power * cpufreq_cdev->last_load) / 100;
 }
 
-/* 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_cdev = cdev->devdata;
-
-	*state = cpufreq_cdev->max_level;
-	return 0;
-}
-
-/**
- * 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)
-{
-	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
-
-	*state = cpufreq_cdev->cpufreq_state;
-
-	return 0;
-}
-
-/**
- * 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)
-{
-	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
-
-	/* Request state should be less than max_level */
-	if (WARN_ON(state > cpufreq_cdev->max_level))
-		return -EINVAL;
-
-	/* Check if the old cooling action is same as new cooling action */
-	if (cpufreq_cdev->cpufreq_state == state)
-		return 0;
-
-	cpufreq_cdev->cpufreq_state = state;
-
-	return freq_qos_update_request(&cpufreq_cdev->qos_req,
-				cpufreq_cdev->freq_table[state].frequency);
-}
-
 /**
  * cpufreq_get_requested_power() - get the current power
  * @cdev:	&thermal_cooling_device pointer
@@ -425,7 +268,7 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 			       struct thermal_zone_device *tz,
 			       unsigned long state, u32 *power)
 {
-	unsigned int freq, num_cpus;
+	unsigned int freq, num_cpus, idx;
 	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 
 	/* Request state should be less than max_level */
@@ -434,7 +277,8 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 
 	num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus);
 
-	freq = cpufreq_cdev->freq_table[state].frequency;
+	idx = cpufreq_cdev->max_level - state;
+	freq = cpufreq_cdev->em->table[idx].frequency;
 	*power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus;
 
 	return 0;
@@ -479,43 +323,142 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
 	return 0;
 }
 
-/* Bind cpufreq callbacks to thermal cooling device ops */
+static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev,
+			      struct em_perf_domain *em) {
+	struct cpufreq_policy *policy;
+	unsigned int nr_levels;
 
-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,
-};
+	if (!em)
+		return false;
 
-static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
-	.get_max_state		= cpufreq_get_max_state,
-	.get_cur_state		= cpufreq_get_cur_state,
-	.set_cur_state		= cpufreq_set_cur_state,
-	.get_requested_power	= cpufreq_get_requested_power,
-	.state2power		= cpufreq_state2power,
-	.power2state		= cpufreq_power2state,
-};
+	policy = cpufreq_cdev->policy;
+	if (!cpumask_equal(policy->related_cpus, to_cpumask(em->cpus))) {
+		pr_err("The span of pd %*pbl is misaligned with cpufreq policy %*pbl\n",
+			cpumask_pr_args(to_cpumask(em->cpus)),
+			cpumask_pr_args(policy->related_cpus));
+		return false;
+	}
 
-static unsigned int find_next_max(struct cpufreq_frequency_table *table,
-				  unsigned int prev_max)
+	nr_levels = cpufreq_cdev->max_level + 1;
+	if (em->nr_cap_states != nr_levels) {
+		pr_err("The number of cap states in pd %*pbl (%u) doesn't match the number of cooling levels (%u)\n",
+			cpumask_pr_args(to_cpumask(em->cpus)),
+			em->nr_cap_states, nr_levels);
+		return false;
+	}
+
+	return true;
+}
+#endif /* CONFIG_THERMAL_GOV_POWER_ALLOCATOR */
+
+static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev,
+				   unsigned long state)
 {
-	struct cpufreq_frequency_table *pos;
-	unsigned int max = 0;
+	struct cpufreq_policy *policy;
+	unsigned long idx;
 
-	cpufreq_for_each_valid_entry(pos, table) {
-		if (pos->frequency > max && pos->frequency < prev_max)
-			max = pos->frequency;
+#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
+	/* Use the Energy Model table if available */
+	if (cpufreq_cdev->em) {
+		idx = cpufreq_cdev->max_level - state;
+		return cpufreq_cdev->em->table[idx].frequency;
 	}
+#endif
+
+	/* Otherwise, fallback on the CPUFreq table */
+	policy = cpufreq_cdev->policy;
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
+		idx = cpufreq_cdev->max_level - state;
+	else
+		idx = state;
+
+	return policy->freq_table[idx].frequency;
+}
+
+/* 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_cdev = cdev->devdata;
+
+	*state = cpufreq_cdev->max_level;
+	return 0;
+}
+
+/**
+ * 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)
+{
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
 
-	return max;
+	*state = cpufreq_cdev->cpufreq_state;
+
+	return 0;
 }
 
 /**
+ * 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)
+{
+	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+
+	/* Request state should be less than max_level */
+	if (WARN_ON(state > cpufreq_cdev->max_level))
+		return -EINVAL;
+
+	/* Check if the old cooling action is same as new cooling action */
+	if (cpufreq_cdev->cpufreq_state == state)
+		return 0;
+
+	cpufreq_cdev->cpufreq_state = state;
+
+	return freq_qos_update_request(&cpufreq_cdev->qos_req,
+				get_state_freq(cpufreq_cdev, state));
+}
+
+/* Bind cpufreq callbacks to thermal cooling device 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,
+};
+
+/**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
  * @np: a valid struct device_node to the cooling device device tree node
  * @policy: cpufreq policy
  * Normally this should be same as cpufreq policy->related_cpus.
- * @capacitance: dynamic power coefficient for these cpus
+ * @em: Energy Model of the cpufreq policy
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -527,12 +470,13 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  */
 static struct thermal_cooling_device *
 __cpufreq_cooling_register(struct device_node *np,
-			struct cpufreq_policy *policy, u32 capacitance)
+			struct cpufreq_policy *policy,
+			struct em_perf_domain *em)
 {
 	struct thermal_cooling_device *cdev;
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	unsigned int freq, i, num_cpus;
+	unsigned int i, num_cpus;
 	struct device *dev;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
@@ -573,51 +517,36 @@ __cpufreq_cooling_register(struct device_node *np,
 	/* max_level is an index, not a counter */
 	cpufreq_cdev->max_level = i - 1;
 
-	cpufreq_cdev->freq_table = kmalloc_array(i,
-					sizeof(*cpufreq_cdev->freq_table),
-					GFP_KERNEL);
-	if (!cpufreq_cdev->freq_table) {
-		cdev = ERR_PTR(-ENOMEM);
-		goto free_idle_time;
-	}
-
 	ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
 		cdev = ERR_PTR(ret);
-		goto free_table;
+		goto free_idle_time;
 	}
 	cpufreq_cdev->id = ret;
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
 		 cpufreq_cdev->id);
 
-	/* Fill freq-table in descending order of frequencies */
-	for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) {
-		freq = find_next_max(policy->freq_table, freq);
-		cpufreq_cdev->freq_table[i].frequency = freq;
-
-		/* Warn for duplicate entries */
-		if (!freq)
-			pr_warn("%s: table has duplicate entries\n", __func__);
-		else
-			pr_debug("%s: freq:%u KHz\n", __func__, freq);
-	}
-
-	if (capacitance) {
-		ret = update_freq_table(cpufreq_cdev, capacitance);
-		if (ret) {
-			cdev = ERR_PTR(ret);
-			goto remove_ida;
-		}
-
-		cooling_ops = &cpufreq_power_cooling_ops;
-	} else {
-		cooling_ops = &cpufreq_cooling_ops;
+	cooling_ops = &cpufreq_cooling_ops;
+
+#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
+	if (em_is_sane(cpufreq_cdev, em)) {
+		cpufreq_cdev->em = em;
+		cooling_ops->get_requested_power = cpufreq_get_requested_power;
+		cooling_ops->state2power = cpufreq_state2power;
+		cooling_ops->power2state = cpufreq_power2state;
+	} else
+#endif
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED) {
+		pr_err("%s: unsorted frequency tables are not supported\n",
+		       __func__);
+		cdev = ERR_PTR(-EINVAL);
+		goto remove_ida;
 	}
 
 	ret = freq_qos_add_request(&policy->constraints,
 				   &cpufreq_cdev->qos_req, FREQ_QOS_MAX,
-				   cpufreq_cdev->freq_table[0].frequency);
+				   get_state_freq(cpufreq_cdev, 0));
 	if (ret < 0) {
 		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
 		       ret);
@@ -640,8 +569,6 @@ remove_qos_req:
 	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
-free_table:
-	kfree(cpufreq_cdev->freq_table);
 free_idle_time:
 	kfree(cpufreq_cdev->idle_time);
 free_cdev:
@@ -663,7 +590,7 @@ free_cdev:
 struct thermal_cooling_device *
 cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
-	return __cpufreq_cooling_register(NULL, policy, 0);
+	return __cpufreq_cooling_register(NULL, policy, NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
@@ -691,7 +618,6 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
 	struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
 	struct thermal_cooling_device *cdev = NULL;
-	u32 capacitance = 0;
 
 	if (!np) {
 		pr_err("cpu_cooling: OF node not available for cpu%d\n",
@@ -700,10 +626,9 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy)
 	}
 
 	if (of_find_property(np, "#cooling-cells", NULL)) {
-		of_property_read_u32(np, "dynamic-power-coefficient",
-				     &capacitance);
+		struct em_perf_domain *em = em_cpu_get(policy->cpu);
 
-		cdev = __cpufreq_cooling_register(np, policy, capacitance);
+		cdev = __cpufreq_cooling_register(np, policy, em);
 		if (IS_ERR(cdev)) {
 			pr_err("cpu_cooling: cpu%d failed to register as cooling device: %ld\n",
 			       policy->cpu, PTR_ERR(cdev));
@@ -739,7 +664,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 	kfree(cpufreq_cdev->idle_time);
-	kfree(cpufreq_cdev->freq_table);
 	kfree(cpufreq_cdev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);