@@ -36,8 +36,162 @@ the user. The registration APIs returns the cooling device pointer.
np: pointer to the cooling device device tree node
clip_cpus: cpumask of cpus where the frequency constraints will happen.
-1.1.3 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
+1.1.3 struct thermal_cooling_device *cpufreq_power_cooling_register(
+ const struct cpumask *clip_cpus, u32 capacitance,
+ get_static_t plat_static_func)
+
+Similar to cpufreq_cooling_register, this function registers a cpufreq
+cooling device. Using this function, the cooling device will
+implement the power extensions by using a simple cpu power model. The
+cpus must have registered their OPPs using the OPP library.
+
+The additional parameters are needed for the power model (See 2. Power
+models). "capacitance" is the dynamic power coefficient (See 2.1
+Dynamic power). "plat_static_func" is a function to calculate the
+static power consumed by these cpus (See 2.2 Static power).
+
+1.1.4 struct thermal_cooling_device *of_cpufreq_power_cooling_register(
+ struct device_node *np, const struct cpumask *clip_cpus, u32 capacitance,
+ get_static_t plat_static_func)
+
+Similar to cpufreq_power_cooling_register, this function register a
+cpufreq cooling device with power extensions using the device tree
+information supplied by the np parameter.
+
+1.1.5 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
This interface function unregisters the "thermal-cpufreq-%x" cooling device.
cdev: Cooling device pointer which has to be unregistered.
+
+2. Power models
+
+The power API registration functions provide a simple power model for
+CPUs. The current power is calculated as dynamic + (optionally)
+static power. This power model requires that the operating-points of
+the CPUs are registered using the kernel's opp library and the
+`cpufreq_frequency_table` is assigned to the `struct device` of the
+cpu. If you are using CONFIG_CPUFREQ_DT then the
+`cpufreq_frequency_table` should already be assigned to the cpu
+device.
+
+The `plat_static_func` parameter of `cpufreq_power_cooling_register()`
+and `of_cpufreq_power_cooling_register()` is optional. If you don't
+provide it, only dynamic power will be considered.
+
+2.1 Dynamic power
+
+The dynamic power consumption of a processor depends on many factors.
+For a given processor implementation the primary factors are:
+
+- The time the processor spends running, consuming dynamic power, as
+ compared to the time in idle states where dynamic consumption is
+ negligible. Herein we refer to this as 'utilisation'.
+- The voltage and frequency levels as a result of DVFS. The DVFS
+ level is a dominant factor governing power consumption.
+- In running time the 'execution' behaviour (instruction types, memory
+ access patterns and so forth) causes, in most cases, a second order
+ variation. In pathological cases this variation can be significant,
+ but typically it is of a much lesser impact than the factors above.
+
+A high level dynamic power consumption model may then be represented as:
+
+Pdyn = f(run) * Voltage^2 * Frequency * Utilisation
+
+f(run) here represents the described execution behaviour and its
+result has a units of Watts/Hz/Volt^2 (this often expressed in
+mW/MHz/uVolt^2)
+
+The detailed behaviour for f(run) could be modelled on-line. However,
+in practice, such an on-line model has dependencies on a number of
+implementation specific processor support and characterisation
+factors. Therefore, in initial implementation that contribution is
+represented as a constant coefficient. This is a simplification
+consistent with the relative contribution to overall power variation.
+
+In this simplified representation our model becomes:
+
+Pdyn = Capacitance * Voltage^2 * Frequency * Utilisation
+
+Where `capacitance` is a constant that represents an indicative
+running time dynamic power coefficient in fundamental units of
+mW/MHz/uVolt^2. Typical values for mobile CPUs might lie in range
+from 100 to 500. For reference, the approximate values for the SoC in
+ARM's Juno Development Platform are 530 for the Cortex-A57 cluster and
+140 for the Cortex-A53 cluster.
+
+
+2.2 Static power
+
+Static leakage power consumption depends on a number of factors. For a
+given circuit implementation the primary factors are:
+
+- Time the circuit spends in each 'power state'
+- Temperature
+- Operating voltage
+- Process grade
+
+The time the circuit spends in each 'power state' for a given
+evaluation period at first order means OFF or ON. However,
+'retention' states can also be supported that reduce power during
+inactive periods without loss of context.
+
+Note: The visibility of state entries to the OS can vary, according to
+platform specifics, and this can then impact the accuracy of a model
+based on OS state information alone. It might be possible in some
+cases to extract more accurate information from system resources.
+
+The temperature, operating voltage and process 'grade' (slow to fast)
+of the circuit are all significant factors in static leakage power
+consumption. All of these have complex relationships to static power.
+
+Circuit implementation specific factors include the chosen silicon
+process as well as the type, number and size of transistors in both
+the logic gates and any RAM elements included.
+
+The static power consumption modelling must take into account the
+power managed regions that are implemented. Taking the example of an
+ARM processor cluster, the modelling would take into account whether
+each CPU can be powered OFF separately or if only a single power
+region is implemented for the complete cluster.
+
+In one view, there are others, a static power consumption model can
+then start from a set of reference values for each power managed
+region (e.g. CPU, Cluster/L2) in each state (e.g. ON, OFF) at an
+arbitrary process grade, voltage and temperature point. These values
+are then scaled for all of the following: the time in each state, the
+process grade, the current temperature and the operating voltage.
+However, since both implementation specific and complex relationships
+dominate the estimate, the appropriate interface to the model from the
+cpu cooling device is to provide a function callback that calculates
+the static power in this platform. When registering the cpu cooling
+device pass a function pointer that follows the `get_static_t`
+prototype:
+
+ int plat_get_static(cpumask_t *cpumask, int interval,
+ unsigned long voltage, u32 &power);
+
+`cpumask` is the cpumask of the cpus involved in the calculation.
+`voltage` is the voltage at which they are operating. The function
+should calculate the average static power for the last `interval`
+milliseconds. It returns 0 on success, -E* on error. If it
+succeeds, it should store the static power in `power`. Reading the
+temperature of the cpus described by `cpumask` is left for
+plat_get_static() to do as the platform knows best which thermal
+sensor is closest to the cpu.
+
+If `plat_static_func` is NULL, static power is considered to be
+negligible for this platform and only dynamic power is considered.
+
+The platform specific callback can then use any combination of tables
+and/or equations to permute the estimated value. Process grade
+information is not passed to the model since access to such data, from
+on-chip measurement capability or manufacture time data, is platform
+specific.
+
+Note: the significance of static power for CPUs in comparison to
+dynamic power is highly dependent on implementation. Given the
+potential complexity in implementation, the importance and accuracy of
+its inclusion when using cpu cooling devices should be assessed on a
+case by case basis.
+
@@ -26,6 +26,7 @@
#include <linux/thermal.h>
#include <linux/cpufreq.h>
#include <linux/err.h>
+#include <linux/pm_opp.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/cpu_cooling.h>
@@ -45,6 +46,19 @@
*/
/**
+ * struct power_table - frequency to power conversion
+ * @frequency: frequency in KHz
+ * @power: power in mW
+ *
+ * This structure is built when the cooling device registers and helps
+ * in translating frequency to power and viceversa.
+ */
+struct power_table {
+ u32 frequency;
+ u32 power;
+};
+
+/**
* struct cpufreq_cooling_device - data for cooling device with cpufreq
* @id: unique integer value corresponding to each cpufreq_cooling_device
* registered.
@@ -58,6 +72,15 @@
* cpufreq frequencies.
* @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
* @node: list_head to link all cpufreq_cooling_device together.
+ * @last_load: load measured by the latest call to cpufreq_get_actual_power()
+ * @time_in_idle: previous reading of the absolute time that this cpu was idle
+ * @time_in_idle_timestamp: wall time of the last invocation of
+ * get_cpu_idle_time_us()
+ * @dyn_power_table: array of struct power_table for frequency to power
+ * conversion, sorted in ascending order.
+ * @dyn_power_table_entries: number of entries in the @dyn_power_table array
+ * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered
+ * @plat_get_static_power: callback to calculate the static power
*
* This structure is required for keeping information of each registered
* cpufreq_cooling_device.
@@ -71,6 +94,13 @@ struct cpufreq_cooling_device {
unsigned int *freq_table; /* In descending order */
struct cpumask allowed_cpus;
struct list_head node;
+ u32 last_load;
+ u64 *time_in_idle;
+ u64 *time_in_idle_timestamp;
+ struct power_table *dyn_power_table;
+ int dyn_power_table_entries;
+ struct device *cpu_dev;
+ get_static_t plat_get_static_power;
};
static DEFINE_IDR(cpufreq_idr);
static DEFINE_MUTEX(cooling_cpufreq_lock);
@@ -167,6 +197,39 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
}
EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
+static void update_cpu_device(int cpu)
+{
+ struct cpufreq_cooling_device *cpufreq_dev;
+
+ mutex_lock(&cooling_cpufreq_lock);
+ list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+ if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
+ cpufreq_dev->cpu_dev = get_cpu_device(cpu);
+ if (!cpufreq_dev->cpu_dev) {
+ dev_warn(&cpufreq_dev->cool_dev->device,
+ "No cpu device for new policy cpu %d\n",
+ cpu);
+ }
+ break;
+ }
+ }
+ mutex_unlock(&cooling_cpufreq_lock);
+}
+
+static void remove_cpu_device(int cpu)
+{
+ struct cpufreq_cooling_device *cpufreq_dev;
+
+ mutex_lock(&cooling_cpufreq_lock);
+ list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+ if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
+ cpufreq_dev->cpu_dev = NULL;
+ break;
+ }
+ }
+ mutex_unlock(&cooling_cpufreq_lock);
+}
+
/**
* cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
* @nb: struct notifier_block * with callback info.
@@ -186,23 +249,240 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
unsigned long max_freq = 0;
struct cpufreq_cooling_device *cpufreq_dev;
- if (event != CPUFREQ_ADJUST)
- return 0;
+ switch (event) {
- mutex_lock(&cooling_cpufreq_lock);
- list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
- if (!cpumask_test_cpu(policy->cpu,
- &cpufreq_dev->allowed_cpus))
+ case CPUFREQ_ADJUST:
+ mutex_lock(&cooling_cpufreq_lock);
+ list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+ if (!cpumask_test_cpu(policy->cpu,
+ &cpufreq_dev->allowed_cpus))
+ continue;
+
+ max_freq = cpufreq_dev->cpufreq_val;
+
+ if (policy->max != max_freq)
+ cpufreq_verify_within_limits(policy, 0,
+ max_freq);
+ }
+ mutex_unlock(&cooling_cpufreq_lock);
+ break;
+
+ case CPUFREQ_CREATE_POLICY:
+ update_cpu_device(policy->cpu);
+ break;
+ case CPUFREQ_REMOVE_POLICY:
+ remove_cpu_device(policy->cpu);
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+
+ return NOTIFY_OK;
+}
+
+/**
+ * build_dyn_power_table() - create a dynamic power to frequency table
+ * @cpufreq_device: the cpufreq cooling device in which to store the table
+ * @capacitance: dynamic power coefficient for these cpus
+ *
+ * Build a dynamic power to frequency table for this cpu and store it
+ * in @cpufreq_device. This table will be used in cpu_power_to_freq() and
+ * cpu_freq_to_power() to convert between power and frequency
+ * efficiently. Power is stored in mW, frequency in KHz. The
+ * resulting table is in ascending order.
+ *
+ * Return: 0 on success, -E* on error.
+ */
+static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
+ u32 capacitance)
+{
+ struct power_table *power_table;
+ struct dev_pm_opp *opp;
+ struct device *dev = NULL;
+ int num_opps = 0, cpu, i, ret = 0;
+ unsigned long freq;
+
+ rcu_read_lock();
+
+ for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+ dev = get_cpu_device(cpu);
+ if (!dev) {
+ dev_warn(&cpufreq_device->cool_dev->device,
+ "No cpu device for cpu %d\n", cpu);
continue;
+ }
- max_freq = cpufreq_dev->cpufreq_val;
+ num_opps = dev_pm_opp_get_opp_count(dev);
+ if (num_opps > 0) {
+ break;
+ } else if (num_opps < 0) {
+ ret = num_opps;
+ goto unlock;
+ }
+ }
- if (policy->max != max_freq)
- cpufreq_verify_within_limits(policy, 0, max_freq);
+ if (num_opps == 0) {
+ ret = -EINVAL;
+ goto unlock;
}
- mutex_unlock(&cooling_cpufreq_lock);
- return 0;
+ power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
+
+ for (freq = 0, i = 0;
+ opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
+ freq++, i++) {
+ u32 freq_mhz, voltage_mv;
+ u64 power;
+
+ freq_mhz = freq / 1000000;
+ voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+
+ /*
+ * Do the multiplication with MHz and millivolt so as
+ * to not overflow.
+ */
+ power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv;
+ do_div(power, 1000000000);
+
+ /* frequency is stored in power_table in KHz */
+ power_table[i].frequency = freq / 1000;
+
+ /* power is stored in mW */
+ power_table[i].power = power;
+ }
+
+ if (i == 0) {
+ ret = PTR_ERR(opp);
+ goto unlock;
+ }
+
+ cpufreq_device->cpu_dev = dev;
+ cpufreq_device->dyn_power_table = power_table;
+ cpufreq_device->dyn_power_table_entries = i;
+
+unlock:
+ rcu_read_unlock();
+ return ret;
+}
+
+static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device,
+ u32 freq)
+{
+ int i;
+ struct power_table *pt = cpufreq_device->dyn_power_table;
+
+ for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+ if (freq < pt[i].frequency)
+ break;
+
+ return pt[i - 1].power;
+}
+
+static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
+ u32 power)
+{
+ int i;
+ struct power_table *pt = cpufreq_device->dyn_power_table;
+
+ for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+ if (power < pt[i].power)
+ break;
+
+ return pt[i - 1].frequency;
+}
+
+/**
+ * get_load() - get load for a cpu since last updated
+ * @cpufreq_device: &struct cpufreq_cooling_device for this cpu
+ * @cpu: cpu number
+ *
+ * Return: The average load of cpu @cpu in percentage since this
+ * function was last called.
+ */
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
+{
+ u32 load;
+ u64 now, now_idle, delta_time, delta_idle;
+
+ now_idle = get_cpu_idle_time(cpu, &now, 0);
+ delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
+ delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+
+ if (delta_time <= delta_idle)
+ load = 0;
+ else
+ load = div64_u64(100 * (delta_time - delta_idle), delta_time);
+
+ cpufreq_device->time_in_idle[cpu] = now_idle;
+ cpufreq_device->time_in_idle_timestamp[cpu] = now;
+
+ return load;
+}
+
+/**
+ * get_static_power() - calculate the static power consumed by the cpus
+ * @cpufreq_device: struct &cpufreq_cooling_device for this cpu cdev
+ * @tz: thermal zone device in which we're operating
+ * @freq: frequency in KHz
+ * @power: pointer in which to store the calculated static power
+ *
+ * Calculate the static power consumed by the cpus described by
+ * @cpu_actor running at frequency @freq. This function relies on a
+ * platform specific function that should have been provided when the
+ * actor was registered. If it wasn't, the static power is assumed to
+ * be negligible. The calculated static power is stored in @power.
+ *
+ * Return: 0 on success, -E* on failure.
+ */
+static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
+ struct thermal_zone_device *tz, unsigned long freq,
+ u32 *power)
+{
+ struct dev_pm_opp *opp;
+ unsigned long voltage;
+ struct cpumask *cpumask = &cpufreq_device->allowed_cpus;
+ unsigned long freq_hz = freq * 1000;
+
+ if (!cpufreq_device->plat_get_static_power ||
+ !cpufreq_device->cpu_dev) {
+ *power = 0;
+ return 0;
+ }
+
+ rcu_read_lock();
+
+ opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
+ true);
+ voltage = dev_pm_opp_get_voltage(opp);
+
+ rcu_read_unlock();
+
+ if (voltage == 0) {
+ dev_warn_ratelimited(cpufreq_device->cpu_dev,
+ "Failed to get voltage for frequency %lu: %ld\n",
+ freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+ return -EINVAL;
+ }
+
+ return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay,
+ voltage, power);
+}
+
+/**
+ * get_dynamic_power() - calculate the dynamic power
+ * @cpufreq_device: &cpufreq_cooling_device for this cdev
+ * @freq: current frequency
+ *
+ * Return: the dynamic power consumed by the cpus described by
+ * @cpufreq_device.
+ */
+static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
+ unsigned long freq)
+{
+ u32 raw_cpu_power;
+
+ raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq);
+ return (raw_cpu_power * cpufreq_device->last_load) / 100;
}
/* cpufreq cooling device callback functions are defined below */
@@ -280,8 +560,169 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
return 0;
}
+/**
+ * cpufreq_get_requested_power() - get the current power
+ * @cdev: &thermal_cooling_device pointer
+ * @tz: a valid thermal zone device pointer
+ * @power: pointer in which to store the resulting power
+ *
+ * Calculate the current power consumption of the cpus in milliwatts
+ * and store it in @power. This function should actually calculate
+ * the requested power, but it's hard to get the frequency that
+ * cpufreq would have assigned if there were no thermal limits.
+ * Instead, we calculate the current power on the assumption that the
+ * immediate future will look like the immediate past.
+ *
+ * We use the current frequency and the average load since this
+ * function was last called. In reality, there could have been
+ * multiple opps since this function was last called and that affects
+ * the load calculation. While it's not perfectly accurate, this
+ * simplification is good enough and works. REVISIT this, as more
+ * complex code may be needed if experiments show that it's not
+ * accurate enough.
+ *
+ * Return: 0 on success, -E* if getting the static power failed.
+ */
+static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
+ struct thermal_zone_device *tz,
+ u32 *power)
+{
+ unsigned long freq;
+ int cpu, ret;
+ u32 static_power, dynamic_power, total_load = 0;
+ struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+ freq = cpufreq_quick_get(cpumask_any(&cpufreq_device->allowed_cpus));
+
+ for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+ u32 load;
+
+ if (cpu_online(cpu))
+ load = get_load(cpufreq_device, cpu);
+ else
+ load = 0;
+
+ total_load += load;
+ }
+
+ cpufreq_device->last_load = total_load;
+
+ dynamic_power = get_dynamic_power(cpufreq_device, freq);
+ ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+ if (ret)
+ return ret;
+
+ *power = static_power + dynamic_power;
+ return 0;
+}
+
+/**
+ * cpufreq_state2power() - convert a cpu cdev state to power consumed
+ * @cdev: &thermal_cooling_device pointer
+ * @tz: a valid thermal zone device pointer
+ * @state: cooling device state to be converted
+ * @power: pointer in which to store the resulting power
+ *
+ * Convert cooling device state @state into power consumption in
+ * milliwatts assuming 100% load. Store the calculated power in
+ * @power.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device state could not
+ * be converted into a frequency or other -E* if there was an error
+ * when calculating the static power.
+ */
+static int cpufreq_state2power(struct thermal_cooling_device *cdev,
+ struct thermal_zone_device *tz,
+ unsigned long state, u32 *power)
+{
+ unsigned int freq, num_cpus;
+ cpumask_t cpumask;
+ u32 static_power, dynamic_power;
+ int ret;
+ struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+ cpumask_and(&cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask);
+ num_cpus = cpumask_weight(&cpumask);
+
+ /* None of our cpus are online, so no power */
+ if (num_cpus == 0) {
+ *power = 0;
+ return 0;
+ }
+
+ freq = cpufreq_device->freq_table[state];
+ if (!freq)
+ return -EINVAL;
+
+ dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus;
+ ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+ if (ret)
+ return ret;
+
+ *power = static_power + dynamic_power;
+ return 0;
+}
+
+/**
+ * cpufreq_power2state() - convert power to a cooling device state
+ * @cdev: &thermal_cooling_device pointer
+ * @tz: a valid thermal zone device pointer
+ * @power: power in milliwatts to be converted
+ * @state: pointer in which to store the resulting state
+ *
+ * Calculate a cooling device state for the cpus described by @cdev
+ * that would allow them to consume at most @power mW and store it in
+ * @state. Note that this calculation depends on external factors
+ * such as the cpu load or the current static power. Calling this
+ * function with the same power as input can yield different cooling
+ * device states depending on those external factors.
+ *
+ * Return: 0 on success, -ENODEV if no cpus are online or -EINVAL if
+ * the calculated frequency could not be converted to a valid state.
+ * The latter should not happen unless the frequencies available to
+ * cpufreq have changed since the initialization of the cpu cooling
+ * device.
+ */
+static int cpufreq_power2state(struct thermal_cooling_device *cdev,
+ struct thermal_zone_device *tz, u32 power,
+ unsigned long *state)
+{
+ unsigned int cpu, cur_freq, target_freq;
+ int ret;
+ s32 dyn_power;
+ u32 last_load, normalised_power, static_power;
+ struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+ cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
+
+ /* None of our cpus are online */
+ if (cpu >= nr_cpu_ids)
+ return -ENODEV;
+
+ cur_freq = cpufreq_quick_get(cpu);
+ ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power);
+ if (ret)
+ return ret;
+
+ dyn_power = power - static_power;
+ dyn_power = dyn_power > 0 ? dyn_power : 0;
+ last_load = cpufreq_device->last_load ?: 1;
+ normalised_power = (dyn_power * 100) / last_load;
+ target_freq = cpu_power_to_freq(cpufreq_device, normalised_power);
+
+ *state = cpufreq_cooling_get_level(cpu, target_freq);
+ if (*state == THERMAL_CSTATE_INVALID) {
+ dev_warn_ratelimited(&cdev->device,
+ "Failed to convert %dKHz for cpu %d into a cdev state\n",
+ target_freq, cpu);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/* Bind cpufreq callbacks to thermal cooling device ops */
-static struct thermal_cooling_device_ops const cpufreq_cooling_ops = {
+static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
.get_max_state = cpufreq_get_max_state,
.get_cur_state = cpufreq_get_cur_state,
.set_cur_state = cpufreq_set_cur_state,
@@ -311,6 +752,9 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
* @np: a valid struct device_node to the cooling device device tree node
* @clip_cpus: cpumask of cpus where the frequency constraints will happen.
* Normally this should be same as cpufreq policy->related_cpus.
+ * @capacitance: dynamic power coefficient for these cpus
+ * @plat_static_func: function to calculate the static power consumed by these
+ * cpus (optional)
*
* This interface function registers the cpufreq cooling device with the name
* "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -322,13 +766,14 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
*/
static struct thermal_cooling_device *
__cpufreq_cooling_register(struct device_node *np,
- const struct cpumask *clip_cpus)
+ const struct cpumask *clip_cpus, u32 capacitance,
+ get_static_t plat_static_func)
{
struct thermal_cooling_device *cool_dev;
struct cpufreq_cooling_device *cpufreq_dev;
char dev_name[THERMAL_NAME_LENGTH];
struct cpufreq_frequency_table *pos, *table;
- unsigned int freq, i;
+ unsigned int freq, i, num_cpus;
int ret;
table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
@@ -341,6 +786,23 @@ __cpufreq_cooling_register(struct device_node *np,
if (!cpufreq_dev)
return ERR_PTR(-ENOMEM);
+ num_cpus = cpumask_weight(clip_cpus);
+ cpufreq_dev->time_in_idle = kcalloc(num_cpus,
+ sizeof(*cpufreq_dev->time_in_idle),
+ GFP_KERNEL);
+ if (!cpufreq_dev->time_in_idle) {
+ cool_dev = ERR_PTR(-ENOMEM);
+ goto free_cdev;
+ }
+
+ cpufreq_dev->time_in_idle_timestamp =
+ kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp),
+ GFP_KERNEL);
+ if (!cpufreq_dev->time_in_idle_timestamp) {
+ cool_dev = ERR_PTR(-ENOMEM);
+ goto free_time_in_idle;
+ }
+
/* Find max levels */
cpufreq_for_each_valid_entry(pos, table)
cpufreq_dev->max_level++;
@@ -349,7 +811,7 @@ __cpufreq_cooling_register(struct device_node *np,
cpufreq_dev->max_level, GFP_KERNEL);
if (!cpufreq_dev->freq_table) {
cool_dev = ERR_PTR(-ENOMEM);
- goto free_cdev;
+ goto free_time_in_idle_timestamp;
}
/* max_level is an index, not a counter */
@@ -357,6 +819,20 @@ __cpufreq_cooling_register(struct device_node *np,
cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
+ if (capacitance) {
+ cpufreq_cooling_ops.get_requested_power =
+ cpufreq_get_requested_power;
+ cpufreq_cooling_ops.state2power = cpufreq_state2power;
+ cpufreq_cooling_ops.power2state = cpufreq_power2state;
+ cpufreq_dev->plat_get_static_power = plat_static_func;
+
+ ret = build_dyn_power_table(cpufreq_dev, capacitance);
+ if (ret) {
+ cool_dev = ERR_PTR(ret);
+ goto free_table;
+ }
+ }
+
ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
if (ret) {
cool_dev = ERR_PTR(ret);
@@ -402,6 +878,10 @@ remove_idr:
release_idr(&cpufreq_idr, cpufreq_dev->id);
free_table:
kfree(cpufreq_dev->freq_table);
+free_time_in_idle_timestamp:
+ kfree(cpufreq_dev->time_in_idle_timestamp);
+free_time_in_idle:
+ kfree(cpufreq_dev->time_in_idle);
free_cdev:
kfree(cpufreq_dev);
@@ -422,7 +902,7 @@ free_cdev:
struct thermal_cooling_device *
cpufreq_cooling_register(const struct cpumask *clip_cpus)
{
- return __cpufreq_cooling_register(NULL, clip_cpus);
+ return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL);
}
EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
@@ -446,11 +926,78 @@ of_cpufreq_cooling_register(struct device_node *np,
if (!np)
return ERR_PTR(-EINVAL);
- return __cpufreq_cooling_register(np, clip_cpus);
+ return __cpufreq_cooling_register(np, clip_cpus, 0, NULL);
}
EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
/**
+ * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @capacitance: dynamic power coefficient for these cpus
+ * @plat_static_func: function to calculate the static power consumed by these
+ * cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x". This api can support multiple
+ * instances of cpufreq cooling devices. Using this function, the
+ * cooling device will implement the power extensions by using a
+ * simple cpu power model. The cpus must have registered their OPPs
+ * using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus. If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance,
+ get_static_t plat_static_func)
+{
+ return __cpufreq_cooling_register(NULL, clip_cpus, capacitance,
+ plat_static_func);
+}
+EXPORT_SYMBOL(cpufreq_power_cooling_register);
+
+/**
+ * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @np: a valid struct device_node to the cooling device device tree node
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @capacitance: dynamic power coefficient for these cpus
+ * @plat_static_func: function to calculate the static power consumed by these
+ * cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x". This api can support multiple
+ * instances of cpufreq cooling devices. Using this API, the cpufreq
+ * cooling device will be linked to the device tree node provided.
+ * Using this function, the cooling device will implement the power
+ * extensions by using a simple cpu power model. The cpus must have
+ * registered their OPPs using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus. If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus,
+ u32 capacitance,
+ get_static_t plat_static_func)
+{
+ if (!np)
+ return ERR_PTR(-EINVAL);
+
+ return __cpufreq_cooling_register(np, clip_cpus, capacitance,
+ plat_static_func);
+}
+EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
+
+/**
* cpufreq_cooling_unregister - function to remove cpufreq cooling device.
* @cdev: thermal cooling device pointer.
*
@@ -475,6 +1022,8 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
release_idr(&cpufreq_idr, cpufreq_dev->id);
+ kfree(cpufreq_dev->time_in_idle_timestamp);
+ kfree(cpufreq_dev->time_in_idle);
kfree(cpufreq_dev->freq_table);
kfree(cpufreq_dev);
}
@@ -28,6 +28,9 @@
#include <linux/thermal.h>
#include <linux/cpumask.h>
+typedef int (*get_static_t)(cpumask_t *cpumask, int interval,
+ unsigned long voltage, u32 *power);
+
#ifdef CONFIG_CPU_THERMAL
/**
* cpufreq_cooling_register - function to create cpufreq cooling device.
@@ -36,6 +39,10 @@
struct thermal_cooling_device *
cpufreq_cooling_register(const struct cpumask *clip_cpus);
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+ u32 capacitance, get_static_t plat_static_func);
+
/**
* of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
* @np: a valid struct device_node to the cooling device device tree node.
@@ -45,6 +52,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus);
struct thermal_cooling_device *
of_cpufreq_cooling_register(struct device_node *np,
const struct cpumask *clip_cpus);
+
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus,
+ u32 capacitance,
+ get_static_t plat_static_func);
#else
static inline struct thermal_cooling_device *
of_cpufreq_cooling_register(struct device_node *np,
@@ -52,6 +65,15 @@ of_cpufreq_cooling_register(struct device_node *np,
{
return ERR_PTR(-ENOSYS);
}
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus,
+ u32 capacitance,
+ get_static_t plat_static_func)
+{
+ return NULL;
+}
#endif
/**
@@ -68,11 +90,28 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
return ERR_PTR(-ENOSYS);
}
static inline struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+ u32 capacitance, get_static_t plat_static_func)
+{
+ return NULL;
+}
+
+static inline struct thermal_cooling_device *
of_cpufreq_cooling_register(struct device_node *np,
const struct cpumask *clip_cpus)
{
return ERR_PTR(-ENOSYS);
}
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus,
+ u32 capacitance,
+ get_static_t plat_static_func)
+{
+ return NULL;
+}
+
static inline
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{