diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index dfd23245f778..eb0d87f32bc7 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -31,6 +31,7 @@ #include #include #include +#include #include @@ -48,19 +49,6 @@ * ... */ -/** - * 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 @@ -82,7 +70,7 @@ struct time_in_idle { * frequency. * @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. @@ -98,7 +86,7 @@ struct cpufreq_cooling_device { unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; - struct freq_table *freq_table; /* In descending order */ + struct em_perf_domain *em; struct thermal_cooling_device *cdev; struct cpufreq_policy *policy; struct list_head node; @@ -111,26 +99,6 @@ static LIST_HEAD(cpufreq_cdev_list); /* Below code defines functions to be used for cpufreq as cooling device */ -/** - * get_level: Find the level for a particular frequency - * @cpufreq_cdev: cpufreq_cdev for which the property is required - * @freq: Frequency - * - * Return: level corresponding to the frequency. - */ -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; - - for (level = 1; level <= cpufreq_cdev->max_level; level++) - if (freq > freq_table[level].frequency) - break; - - return level - 1; -} - /** * cpufreq_thermal_notifier - notifier callback for cpufreq policy change. * @nb: struct notifier_block * with callback info. @@ -184,105 +152,52 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, return NOTIFY_OK; } +#ifdef CONFIG_ENERGY_MODEL /** - * 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 + * get_level: Find the level for a particular frequency + * @cpufreq_cdev: cpufreq_cdev for which the property is required + * @freq: Frequency * - * 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. + * Return: level corresponding to the frequency. */ -static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev, - u32 capacitance) +static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, + unsigned int freq) { - 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; + int i; - dev = get_cpu_device(cpu); - if (unlikely(!dev)) { - dev_warn(&cpufreq_cdev->cdev->device, - "No cpu device for cpu %d\n", cpu); - return -ENODEV; + for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) { + if (freq > cpufreq_cdev->em->table[i].frequency) + break; } - 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; } /** @@ -332,6 +247,7 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev, raw_cpu_power = cpu_freq_to_power(cpufreq_cdev, freq); return (raw_cpu_power * cpufreq_cdev->last_load) / 100; } +#endif /* cpufreq cooling device callback functions are defined below */ @@ -374,6 +290,30 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev, return 0; } +static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev, + unsigned long state) +{ + struct cpufreq_policy *policy; + unsigned long idx; + +#ifdef CONFIG_ENERGY_MODEL + /* 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_set_cur_state - callback function to set the current cooling state. * @cdev: thermal cooling device pointer. @@ -398,7 +338,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, if (cpufreq_cdev->cpufreq_state == state) return 0; - clip_freq = cpufreq_cdev->freq_table[state].frequency; + clip_freq = get_state_freq(cpufreq_cdev, state); cpufreq_cdev->cpufreq_state = state; cpufreq_cdev->clipped_freq = clip_freq; @@ -407,6 +347,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, return 0; } +#ifdef CONFIG_ENERGY_MODEL /** * cpufreq_get_requested_power() - get the current power * @cdev: &thermal_cooling_device pointer @@ -497,7 +438,7 @@ 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 */ @@ -506,7 +447,8 @@ 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; @@ -553,14 +495,6 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, return 0; } -/* 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, -}; - static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { .get_max_state = cpufreq_get_max_state, .get_cur_state = cpufreq_get_cur_state, @@ -569,32 +503,27 @@ static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { .state2power = cpufreq_state2power, .power2state = cpufreq_power2state, }; +#endif + +/* 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, +}; /* Notifier for cpufreq policy change */ 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 * @policy: cpufreq policy * Normally this should be same as cpufreq policy->related_cpus. - * @capacitance: dynamic power coefficient for these cpus + * @try_model: true if a power model should be used * * This interface function registers the cpufreq cooling device with the name * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq @@ -606,12 +535,12 @@ 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, bool try_model) { 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; int ret; struct thermal_cooling_device_ops *cooling_ops; bool first; @@ -645,54 +574,36 @@ __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; - } +#ifdef CONFIG_ENERGY_MODEL + if (try_model) { + struct em_perf_domain *em = em_cpu_get(policy->cpu); + + if (!em || !cpumask_equal(policy->cpus, to_cpumask(em->cpus))) { + cdev = ERR_PTR(-EINVAL); + goto free_idle_time; + } + cpufreq_cdev->em = em; + cooling_ops = &cpufreq_power_cooling_ops; + } else +#endif + cooling_ops = &cpufreq_cooling_ops; 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; - } - cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev, cooling_ops); if (IS_ERR(cdev)) goto remove_ida; - cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency; + cpufreq_cdev->clipped_freq = get_state_freq(cpufreq_cdev, 0); cpufreq_cdev->cdev = cdev; mutex_lock(&cooling_list_lock); @@ -709,8 +620,6 @@ __cpufreq_cooling_register(struct device_node *np, 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: @@ -732,7 +641,7 @@ __cpufreq_cooling_register(struct device_node *np, struct thermal_cooling_device * cpufreq_cooling_register(struct cpufreq_policy *policy) { - return __cpufreq_cooling_register(NULL, policy, 0); + return __cpufreq_cooling_register(NULL, policy, false); } EXPORT_SYMBOL_GPL(cpufreq_cooling_register); @@ -760,7 +669,6 @@ 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", @@ -769,10 +677,7 @@ 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); - - cdev = __cpufreq_cooling_register(np, policy, capacitance); + cdev = __cpufreq_cooling_register(np, policy, true); if (IS_ERR(cdev)) { pr_err("cpu_cooling: cpu%d is not running as cooling device: %ld\n", policy->cpu, PTR_ERR(cdev)); @@ -814,7 +719,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) thermal_cooling_device_unregister(cpufreq_cdev->cdev); 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);