From 521b512b157a1315ff2bf11c11ab184c79515aea Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:47 +0100 Subject: PM / EM: change naming convention from 'capacity' to 'performance' The Energy Model uses concept of performance domain and capacity states in order to calculate power used by CPUs. Change naming convention from capacity to performance state would enable wider usage in future, e.g. upcoming support for other devices other than CPUs. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 44 ++++++++++++++++++++++---------------------- kernel/sched/topology.c | 20 ++++++++++---------- 2 files changed, 32 insertions(+), 32 deletions(-) (limited to 'kernel') diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 0a9326f5f421..9892d548a0fa 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -27,18 +27,18 @@ static DEFINE_MUTEX(em_pd_mutex); #ifdef CONFIG_DEBUG_FS static struct dentry *rootdir; -static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd) +static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd) { struct dentry *d; char name[24]; - snprintf(name, sizeof(name), "cs:%lu", cs->frequency); + snprintf(name, sizeof(name), "ps:%lu", ps->frequency); - /* Create per-cs directory */ + /* Create per-ps directory */ d = debugfs_create_dir(name, pd); - debugfs_create_ulong("frequency", 0444, d, &cs->frequency); - debugfs_create_ulong("power", 0444, d, &cs->power); - debugfs_create_ulong("cost", 0444, d, &cs->cost); + debugfs_create_ulong("frequency", 0444, d, &ps->frequency); + debugfs_create_ulong("power", 0444, d, &ps->power); + debugfs_create_ulong("cost", 0444, d, &ps->cost); } static int em_debug_cpus_show(struct seq_file *s, void *unused) @@ -62,9 +62,9 @@ static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops); - /* Create a sub-directory for each capacity state */ - for (i = 0; i < pd->nr_cap_states; i++) - em_debug_create_cs(&pd->table[i], d); + /* Create a sub-directory for each performance state */ + for (i = 0; i < pd->nr_perf_states; i++) + em_debug_create_ps(&pd->table[i], d); } static int __init em_debug_init(void) @@ -84,7 +84,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, unsigned long opp_eff, prev_opp_eff = ULONG_MAX; unsigned long power, freq, prev_freq = 0; int i, ret, cpu = cpumask_first(span); - struct em_cap_state *table; + struct em_perf_state *table; struct em_perf_domain *pd; u64 fmax; @@ -99,26 +99,26 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, if (!table) goto free_pd; - /* Build the list of capacity states for this performance domain */ + /* Build the list of performance states for this performance domain */ for (i = 0, freq = 0; i < nr_states; i++, freq++) { /* * active_power() is a driver callback which ceils 'freq' to - * lowest capacity state of 'cpu' above 'freq' and updates + * lowest performance state of 'cpu' above 'freq' and updates * 'power' and 'freq' accordingly. */ ret = cb->active_power(&power, &freq, cpu); if (ret) { - pr_err("pd%d: invalid cap. state: %d\n", cpu, ret); - goto free_cs_table; + pr_err("pd%d: invalid perf. state: %d\n", cpu, ret); + goto free_ps_table; } /* * We expect the driver callback to increase the frequency for - * higher capacity states. + * higher performance states. */ if (freq <= prev_freq) { pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq); - goto free_cs_table; + goto free_ps_table; } /* @@ -127,7 +127,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, */ if (!power || power > EM_CPU_MAX_POWER) { pr_err("pd%d: invalid power: %lu\n", cpu, power); - goto free_cs_table; + goto free_ps_table; } table[i].power = power; @@ -141,12 +141,12 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, */ opp_eff = freq / power; if (opp_eff >= prev_opp_eff) - pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n", + pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n", cpu, i, i - 1); prev_opp_eff = opp_eff; } - /* Compute the cost of each capacity_state. */ + /* Compute the cost of each performance state. */ fmax = (u64) table[nr_states - 1].frequency; for (i = 0; i < nr_states; i++) { table[i].cost = div64_u64(fmax * table[i].power, @@ -154,14 +154,14 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, } pd->table = table; - pd->nr_cap_states = nr_states; + pd->nr_perf_states = nr_states; cpumask_copy(to_cpumask(pd->cpus), span); em_debug_create_pd(pd, cpu); return pd; -free_cs_table: +free_ps_table: kfree(table); free_pd: kfree(pd); @@ -185,7 +185,7 @@ EXPORT_SYMBOL_GPL(em_cpu_get); /** * em_register_perf_domain() - Register the Energy Model of a performance domain * @span : Mask of CPUs in the performance domain - * @nr_states : Number of capacity states to register + * @nr_states : Number of performance states to register * @cb : Callback functions providing the data of the Energy Model * * Create Energy Model tables for a performance domain using the callbacks diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index ba81187bb7af..2f91d3126365 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -272,10 +272,10 @@ static void perf_domain_debug(const struct cpumask *cpu_map, printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map)); while (pd) { - printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }", + printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_pstate=%d }", cpumask_first(perf_domain_span(pd)), cpumask_pr_args(perf_domain_span(pd)), - em_pd_nr_cap_states(pd->em_pd)); + em_pd_nr_perf_states(pd->em_pd)); pd = pd->next; } @@ -313,26 +313,26 @@ static void sched_energy_set(bool has_eas) * * The complexity of the Energy Model is defined as: * - * C = nr_pd * (nr_cpus + nr_cs) + * C = nr_pd * (nr_cpus + nr_ps) * * with parameters defined as: * - nr_pd: the number of performance domains * - nr_cpus: the number of CPUs - * - nr_cs: the sum of the number of capacity states of all performance + * - nr_ps: the sum of the number of performance states of all performance * domains (for example, on a system with 2 performance domains, - * with 10 capacity states each, nr_cs = 2 * 10 = 20). + * with 10 performance states each, nr_ps = 2 * 10 = 20). * * It is generally not a good idea to use such a model in the wake-up path on * very complex platforms because of the associated scheduling overheads. The * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs - * with per-CPU DVFS and less than 8 capacity states each, for example. + * with per-CPU DVFS and less than 8 performance states each, for example. */ #define EM_MAX_COMPLEXITY 2048 extern struct cpufreq_governor schedutil_gov; static bool build_perf_domains(const struct cpumask *cpu_map) { - int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map); + int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map); struct perf_domain *pd = NULL, *tmp; int cpu = cpumask_first(cpu_map); struct root_domain *rd = cpu_rq(cpu)->rd; @@ -384,15 +384,15 @@ static bool build_perf_domains(const struct cpumask *cpu_map) pd = tmp; /* - * Count performance domains and capacity states for the + * Count performance domains and performance states for the * complexity check. */ nr_pd++; - nr_cs += em_pd_nr_cap_states(pd->em_pd); + nr_ps += em_pd_nr_perf_states(pd->em_pd); } /* Bail out if the Energy Model complexity is too high. */ - if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) { + if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) { WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n", cpumask_pr_args(cpu_map)); goto free; -- cgit v1.2.3 From 7d9895c7fbfc9c70afce7029b7de0f3f974adb88 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:48 +0100 Subject: PM / EM: introduce em_dev_register_perf_domain function Add now function in the Energy Model framework which is going to support new devices. This function will help in transition and make it smoother. For now it still checks if the cpumask is a valid pointer, which will be removed later when the new structures and infrastructure will be ready. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 13 +++++++++++-- kernel/power/energy_model.c | 40 ++++++++++++++++++++++++++++++++++------ 2 files changed, 45 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index fe336a9eb5d4..7c048df98447 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -2,6 +2,7 @@ #ifndef _LINUX_ENERGY_MODEL_H #define _LINUX_ENERGY_MODEL_H #include +#include #include #include #include @@ -42,7 +43,7 @@ struct em_perf_domain { #define em_span_cpus(em) (to_cpumask((em)->cpus)) #ifdef CONFIG_ENERGY_MODEL -#define EM_CPU_MAX_POWER 0xFFFF +#define EM_MAX_POWER 0xFFFF struct em_data_callback { /** @@ -59,7 +60,7 @@ struct em_data_callback { * and frequency. * * The power is the one of a single CPU in the domain, expressed in - * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER] + * milli-watts. It is expected to fit in the [0, EM_MAX_POWER] * range. * * Return 0 on success. @@ -71,6 +72,8 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, struct em_data_callback *cb); +int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, + struct em_data_callback *cb, cpumask_t *span); /** * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain @@ -174,6 +177,12 @@ static inline int em_register_perf_domain(cpumask_t *span, { return -EINVAL; } +static inline +int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, + struct em_data_callback *cb, cpumask_t *span) +{ + return -EINVAL; +} static inline struct em_perf_domain *em_cpu_get(int cpu) { return NULL; diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 9892d548a0fa..875b163e54ab 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -125,7 +125,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, * The power returned by active_state() is expected to be * positive, in milli-watts and to fit into 16 bits. */ - if (!power || power > EM_CPU_MAX_POWER) { + if (!power || power > EM_MAX_POWER) { pr_err("pd%d: invalid power: %lu\n", cpu, power); goto free_ps_table; } @@ -183,10 +183,13 @@ struct em_perf_domain *em_cpu_get(int cpu) EXPORT_SYMBOL_GPL(em_cpu_get); /** - * em_register_perf_domain() - Register the Energy Model of a performance domain - * @span : Mask of CPUs in the performance domain + * em_dev_register_perf_domain() - Register the Energy Model (EM) for a device + * @dev : Device for which the EM is to register * @nr_states : Number of performance states to register * @cb : Callback functions providing the data of the Energy Model + * @span : Pointer to cpumask_t, which in case of a CPU device is + * obligatory. It can be taken from i.e. 'policy->cpus'. For other + * type of devices this should be set to NULL. * * Create Energy Model tables for a performance domain using the callbacks * defined in cb. @@ -196,14 +199,14 @@ EXPORT_SYMBOL_GPL(em_cpu_get); * * Return 0 on success */ -int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, - struct em_data_callback *cb) +int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, + struct em_data_callback *cb, cpumask_t *span) { unsigned long cap, prev_cap = 0; struct em_perf_domain *pd; int cpu, ret = 0; - if (!span || !nr_states || !cb) + if (!dev || !span || !nr_states || !cb) return -EINVAL; /* @@ -255,4 +258,29 @@ unlock: return ret; } +EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); + +/** + * em_register_perf_domain() - Register the Energy Model of a performance domain + * @span : Mask of CPUs in the performance domain + * @nr_states : Number of capacity states to register + * @cb : Callback functions providing the data of the Energy Model + * + * Create Energy Model tables for a performance domain using the callbacks + * defined in cb. + * + * If multiple clients register the same performance domain, all but the first + * registration will be ignored. + * + * Return 0 on success + */ +int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, + struct em_data_callback *cb) +{ + struct device *cpu_dev; + + cpu_dev = get_cpu_device(cpumask_first(span)); + + return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span); +} EXPORT_SYMBOL_GPL(em_register_perf_domain); -- cgit v1.2.3 From d0351cc3b0f57214d157e4d589564730af2aedae Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:49 +0100 Subject: PM / EM: update callback structure and add device pointer The Energy Model framework is going to support devices other that CPUs. In order to make this happen change the callback function and add pointer to a device as an argument. Update the related users to use new function and new callback from the Energy Model. Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/scmi-cpufreq.c | 11 +++-------- drivers/opp/of.c | 9 ++------- include/linux/energy_model.h | 15 ++++++++------- kernel/power/energy_model.c | 9 +++++---- 4 files changed, 18 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 61623e2ff149..11ee24e06d12 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -103,17 +103,12 @@ scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) } static int __maybe_unused -scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, int cpu) +scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, + struct device *cpu_dev) { - struct device *cpu_dev = get_cpu_device(cpu); unsigned long Hz; int ret, domain; - if (!cpu_dev) { - pr_err("failed to get cpu%d device\n", cpu); - return -ENODEV; - } - domain = handle->perf_ops->device_domain_id(cpu_dev); if (domain < 0) return domain; @@ -200,7 +195,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = true; - em_register_perf_domain(policy->cpus, nr_opp, &em_cb); + em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus); return 0; diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 9a5873591a40..e273f419a4bf 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1216,9 +1216,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node); * calculation failed because of missing parameters, 0 otherwise. */ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, - int cpu) + struct device *cpu_dev) { - struct device *cpu_dev; struct dev_pm_opp *opp; struct device_node *np; unsigned long mV, Hz; @@ -1226,10 +1225,6 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, u64 tmp; int ret; - cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) - return -ENODEV; - np = of_node_get(cpu_dev->of_node); if (!np) return -EINVAL; @@ -1297,6 +1292,6 @@ void dev_pm_opp_of_register_em(struct cpumask *cpus) if (ret || !cap) return; - em_register_perf_domain(cpus, nr_opp, &em_cb); + em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, cpus); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em); diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7c048df98447..7076cb22b247 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -48,24 +48,25 @@ struct em_perf_domain { struct em_data_callback { /** * active_power() - Provide power at the next performance state of - * a CPU + * a device * @power : Active power at the performance state in mW * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @cpu : CPU for which we do this operation + * @dev : Device for which we do this operation (can be a CPU) * - * active_power() must find the lowest performance state of 'cpu' above + * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power * and frequency. * - * The power is the one of a single CPU in the domain, expressed in - * milli-watts. It is expected to fit in the [0, EM_MAX_POWER] - * range. + * In case of CPUs, the power is the one of a single CPU in the domain, + * expressed in milli-watts. It is expected to fit in the + * [0, EM_MAX_POWER] range. * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, int cpu); + int (*active_power)(unsigned long *power, unsigned long *freq, + struct device *dev); }; #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 875b163e54ab..5b8a1566526a 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -78,8 +78,9 @@ core_initcall(em_debug_init); #else /* CONFIG_DEBUG_FS */ static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {} #endif -static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, - struct em_data_callback *cb) +static struct em_perf_domain * +em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, + cpumask_t *span) { unsigned long opp_eff, prev_opp_eff = ULONG_MAX; unsigned long power, freq, prev_freq = 0; @@ -106,7 +107,7 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, * lowest performance state of 'cpu' above 'freq' and updates * 'power' and 'freq' accordingly. */ - ret = cb->active_power(&power, &freq, cpu); + ret = cb->active_power(&power, &freq, dev); if (ret) { pr_err("pd%d: invalid perf. state: %d\n", cpu, ret); goto free_ps_table; @@ -237,7 +238,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, } /* Create the performance domain and add it to the Energy Model. */ - pd = em_create_pd(span, nr_states, cb); + pd = em_create_pd(dev, nr_states, cb, span); if (!pd) { ret = -EINVAL; goto unlock; -- cgit v1.2.3 From 1bc138c622959979eb547be2d3bbc6442a5c80b0 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 10 Jun 2020 11:12:23 +0100 Subject: PM / EM: add support for other devices than CPUs in Energy Model Add support for other devices than CPUs. The registration function does not require a valid cpumask pointer and is ready to handle new devices. Some of the internal structures has been reorganized in order to keep consistent view (like removing per_cpu pd pointers). Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 5 + include/linux/energy_model.h | 29 +++-- kernel/power/energy_model.c | 244 +++++++++++++++++++++++++++++-------------- 3 files changed, 194 insertions(+), 84 deletions(-) (limited to 'kernel') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..b72e6f9ad845 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -13,6 +13,7 @@ #define _DEVICE_H_ #include +#include #include #include #include @@ -559,6 +560,10 @@ struct device { struct dev_pm_info power; struct dev_pm_domain *pm_domain; +#ifdef CONFIG_ENERGY_MODEL + struct em_perf_domain *em_pd; +#endif + #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN struct irq_domain *msi_domain; #endif diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7076cb22b247..2d4689964029 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -12,8 +12,10 @@ /** * em_perf_state - Performance state of a performance domain - * @frequency: The CPU frequency in KHz, for consistency with CPUFreq - * @power: The power consumed by 1 CPU at this level, in milli-watts + * @frequency: The frequency in KHz, for consistency with CPUFreq + * @power: The power consumed at this level, in milli-watts (by 1 CPU or + by a registered device). It can be a total power: static and + dynamic. * @cost: The cost coefficient associated with this level, used during * energy calculation. Equal to: power * max_frequency / frequency */ @@ -27,12 +29,16 @@ struct em_perf_state { * em_perf_domain - Performance domain * @table: List of performance states, in ascending order * @nr_perf_states: Number of performance states - * @cpus: Cpumask covering the CPUs of the domain + * @cpus: Cpumask covering the CPUs of the domain. It's here + * for performance reasons to avoid potential cache + * misses during energy calculations in the scheduler + * and simplifies allocating/freeing that memory region. * - * A "performance domain" represents a group of CPUs whose performance is - * scaled together. All CPUs of a performance domain must have the same - * micro-architecture. Performance domains often have a 1-to-1 mapping with - * CPUFreq policies. + * In case of CPU device, a "performance domain" represents a group of CPUs + * whose performance is scaled together. All CPUs of a performance domain + * must have the same micro-architecture. Performance domains often have + * a 1-to-1 mapping with CPUFreq policies. In case of other devices the @cpus + * field is unused. */ struct em_perf_domain { struct em_perf_state *table; @@ -71,10 +77,12 @@ struct em_data_callback { #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } struct em_perf_domain *em_cpu_get(int cpu); +struct em_perf_domain *em_pd_get(struct device *dev); int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, struct em_data_callback *cb); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span); +void em_dev_unregister_perf_domain(struct device *dev); /** * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain @@ -184,10 +192,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline void em_dev_unregister_perf_domain(struct device *dev) +{ +} static inline struct em_perf_domain *em_cpu_get(int cpu) { return NULL; } +static inline struct em_perf_domain *em_pd_get(struct device *dev) +{ + return NULL; +} static inline unsigned long em_pd_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 5b8a1566526a..32d76e78f992 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Energy Model of CPUs + * Energy Model of devices * - * Copyright (c) 2018, Arm ltd. + * Copyright (c) 2018-2020, Arm ltd. * Written by: Quentin Perret, Arm ltd. + * Improvements provided by: Lukasz Luba, Arm ltd. */ #define pr_fmt(fmt) "energy_model: " fmt @@ -15,15 +16,17 @@ #include #include -/* Mapping of each CPU to the performance domain to which it belongs. */ -static DEFINE_PER_CPU(struct em_perf_domain *, em_data); - /* * Mutex serializing the registrations of performance domains and letting * callbacks defined by drivers sleep. */ static DEFINE_MUTEX(em_pd_mutex); +static bool _is_cpu_device(struct device *dev) +{ + return (dev->bus == &cpu_subsys); +} + #ifdef CONFIG_DEBUG_FS static struct dentry *rootdir; @@ -49,22 +52,30 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(em_debug_cpus); -static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) +static void em_debug_create_pd(struct device *dev) { struct dentry *d; - char name[8]; int i; - snprintf(name, sizeof(name), "pd%d", cpu); - /* Create the directory of the performance domain */ - d = debugfs_create_dir(name, rootdir); + d = debugfs_create_dir(dev_name(dev), rootdir); - debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops); + if (_is_cpu_device(dev)) + debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus, + &em_debug_cpus_fops); /* Create a sub-directory for each performance state */ - for (i = 0; i < pd->nr_perf_states; i++) - em_debug_create_ps(&pd->table[i], d); + for (i = 0; i < dev->em_pd->nr_perf_states; i++) + em_debug_create_ps(&dev->em_pd->table[i], d); + +} + +static void em_debug_remove_pd(struct device *dev) +{ + struct dentry *debug_dir; + + debug_dir = debugfs_lookup(dev_name(dev), rootdir); + debugfs_remove_recursive(debug_dir); } static int __init em_debug_init(void) @@ -76,40 +87,34 @@ static int __init em_debug_init(void) } core_initcall(em_debug_init); #else /* CONFIG_DEBUG_FS */ -static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {} +static void em_debug_create_pd(struct device *dev) {} +static void em_debug_remove_pd(struct device *dev) {} #endif -static struct em_perf_domain * -em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, - cpumask_t *span) + +static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, + int nr_states, struct em_data_callback *cb) { unsigned long opp_eff, prev_opp_eff = ULONG_MAX; unsigned long power, freq, prev_freq = 0; - int i, ret, cpu = cpumask_first(span); struct em_perf_state *table; - struct em_perf_domain *pd; + int i, ret; u64 fmax; - if (!cb->active_power) - return NULL; - - pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL); - if (!pd) - return NULL; - table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL); if (!table) - goto free_pd; + return -ENOMEM; /* Build the list of performance states for this performance domain */ for (i = 0, freq = 0; i < nr_states; i++, freq++) { /* * active_power() is a driver callback which ceils 'freq' to - * lowest performance state of 'cpu' above 'freq' and updates + * lowest performance state of 'dev' above 'freq' and updates * 'power' and 'freq' accordingly. */ ret = cb->active_power(&power, &freq, dev); if (ret) { - pr_err("pd%d: invalid perf. state: %d\n", cpu, ret); + dev_err(dev, "EM: invalid perf. state: %d\n", + ret); goto free_ps_table; } @@ -118,7 +123,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, * higher performance states. */ if (freq <= prev_freq) { - pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq); + dev_err(dev, "EM: non-increasing freq: %lu\n", + freq); goto free_ps_table; } @@ -127,7 +133,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, * positive, in milli-watts and to fit into 16 bits. */ if (!power || power > EM_MAX_POWER) { - pr_err("pd%d: invalid power: %lu\n", cpu, power); + dev_err(dev, "EM: invalid power: %lu\n", + power); goto free_ps_table; } @@ -142,8 +149,8 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, */ opp_eff = freq / power; if (opp_eff >= prev_opp_eff) - pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n", - cpu, i, i - 1); + dev_dbg(dev, "EM: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n", + i, i - 1); prev_opp_eff = opp_eff; } @@ -156,30 +163,82 @@ em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, pd->table = table; pd->nr_perf_states = nr_states; - cpumask_copy(to_cpumask(pd->cpus), span); - em_debug_create_pd(pd, cpu); - - return pd; + return 0; free_ps_table: kfree(table); -free_pd: - kfree(pd); + return -EINVAL; +} + +static int em_create_pd(struct device *dev, int nr_states, + struct em_data_callback *cb, cpumask_t *cpus) +{ + struct em_perf_domain *pd; + struct device *cpu_dev; + int cpu, ret; + + if (_is_cpu_device(dev)) { + pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL); + if (!pd) + return -ENOMEM; + + cpumask_copy(em_span_cpus(pd), cpus); + } else { + pd = kzalloc(sizeof(*pd), GFP_KERNEL); + if (!pd) + return -ENOMEM; + } + + ret = em_create_perf_table(dev, pd, nr_states, cb); + if (ret) { + kfree(pd); + return ret; + } + + if (_is_cpu_device(dev)) + for_each_cpu(cpu, cpus) { + cpu_dev = get_cpu_device(cpu); + cpu_dev->em_pd = pd; + } + + dev->em_pd = pd; + + return 0; +} + +/** + * em_pd_get() - Return the performance domain for a device + * @dev : Device to find the performance domain for + * + * Returns the performance domain to which @dev belongs, or NULL if it doesn't + * exist. + */ +struct em_perf_domain *em_pd_get(struct device *dev) +{ + if (IS_ERR_OR_NULL(dev)) + return NULL; - return NULL; + return dev->em_pd; } +EXPORT_SYMBOL_GPL(em_pd_get); /** * em_cpu_get() - Return the performance domain for a CPU * @cpu : CPU to find the performance domain for * - * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't + * Returns the performance domain to which @cpu belongs, or NULL if it doesn't * exist. */ struct em_perf_domain *em_cpu_get(int cpu) { - return READ_ONCE(per_cpu(em_data, cpu)); + struct device *cpu_dev; + + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return NULL; + + return em_pd_get(cpu_dev); } EXPORT_SYMBOL_GPL(em_cpu_get); @@ -188,7 +247,7 @@ EXPORT_SYMBOL_GPL(em_cpu_get); * @dev : Device for which the EM is to register * @nr_states : Number of performance states to register * @cb : Callback functions providing the data of the Energy Model - * @span : Pointer to cpumask_t, which in case of a CPU device is + * @cpus : Pointer to cpumask_t, which in case of a CPU device is * obligatory. It can be taken from i.e. 'policy->cpus'. For other * type of devices this should be set to NULL. * @@ -201,13 +260,12 @@ EXPORT_SYMBOL_GPL(em_cpu_get); * Return 0 on success */ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, - struct em_data_callback *cb, cpumask_t *span) + struct em_data_callback *cb, cpumask_t *cpus) { unsigned long cap, prev_cap = 0; - struct em_perf_domain *pd; - int cpu, ret = 0; + int cpu, ret; - if (!dev || !span || !nr_states || !cb) + if (!dev || !nr_states || !cb) return -EINVAL; /* @@ -216,47 +274,50 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, */ mutex_lock(&em_pd_mutex); - for_each_cpu(cpu, span) { - /* Make sure we don't register again an existing domain. */ - if (READ_ONCE(per_cpu(em_data, cpu))) { - ret = -EEXIST; - goto unlock; - } + if (dev->em_pd) { + ret = -EEXIST; + goto unlock; + } - /* - * All CPUs of a domain must have the same micro-architecture - * since they all share the same table. - */ - cap = arch_scale_cpu_capacity(cpu); - if (prev_cap && prev_cap != cap) { - pr_err("CPUs of %*pbl must have the same capacity\n", - cpumask_pr_args(span)); + if (_is_cpu_device(dev)) { + if (!cpus) { + dev_err(dev, "EM: invalid CPU mask\n"); ret = -EINVAL; goto unlock; } - prev_cap = cap; + + for_each_cpu(cpu, cpus) { + if (em_cpu_get(cpu)) { + dev_err(dev, "EM: exists for CPU%d\n", cpu); + ret = -EEXIST; + goto unlock; + } + /* + * All CPUs of a domain must have the same + * micro-architecture since they all share the same + * table. + */ + cap = arch_scale_cpu_capacity(cpu); + if (prev_cap && prev_cap != cap) { + dev_err(dev, "EM: CPUs of %*pbl must have the same capacity\n", + cpumask_pr_args(cpus)); + + ret = -EINVAL; + goto unlock; + } + prev_cap = cap; + } } - /* Create the performance domain and add it to the Energy Model. */ - pd = em_create_pd(dev, nr_states, cb, span); - if (!pd) { - ret = -EINVAL; + ret = em_create_pd(dev, nr_states, cb, cpus); + if (ret) goto unlock; - } - for_each_cpu(cpu, span) { - /* - * The per-cpu array can be read concurrently from em_cpu_get(). - * The barrier enforces the ordering needed to make sure readers - * can only access well formed em_perf_domain structs. - */ - smp_store_release(per_cpu_ptr(&em_data, cpu), pd); - } + em_debug_create_pd(dev); + dev_info(dev, "EM: created perf domain\n"); - pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span)); unlock: mutex_unlock(&em_pd_mutex); - return ret; } EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); @@ -285,3 +346,32 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span); } EXPORT_SYMBOL_GPL(em_register_perf_domain); + +/** + * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device + * @dev : Device for which the EM is registered + * + * Unregister the EM for the specified @dev (but not a CPU device). + */ +void em_dev_unregister_perf_domain(struct device *dev) +{ + if (IS_ERR_OR_NULL(dev) || !dev->em_pd) + return; + + if (_is_cpu_device(dev)) + return; + + /* + * The mutex separates all register/unregister requests and protects + * from potential clean-up/setup issues in the debugfs directories. + * The debugfs directory name is the same as device's name. + */ + mutex_lock(&em_pd_mutex); + em_debug_remove_pd(dev); + + kfree(dev->em_pd->table); + kfree(dev->em_pd); + dev->em_pd = NULL; + mutex_unlock(&em_pd_mutex); +} +EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain); -- cgit v1.2.3 From 07891f15d91317b2220a0b610a2d7e324a88105d Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:51 +0100 Subject: PM / EM: remove em_register_perf_domain Remove old function em_register_perf_domain which is no longer needed. There is em_dev_register_perf_domain that covers old use cases and new as well. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 7 ------- kernel/power/energy_model.c | 25 ------------------------- 2 files changed, 32 deletions(-) (limited to 'kernel') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 2d4689964029..0f94e871a202 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -78,8 +78,6 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); -int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, - struct em_data_callback *cb); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span); void em_dev_unregister_perf_domain(struct device *dev); @@ -181,11 +179,6 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } -static inline int em_register_perf_domain(cpumask_t *span, - unsigned int nr_states, struct em_data_callback *cb) -{ - return -EINVAL; -} static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 32d76e78f992..c1ff7fa030ab 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -322,31 +322,6 @@ unlock: } EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); -/** - * em_register_perf_domain() - Register the Energy Model of a performance domain - * @span : Mask of CPUs in the performance domain - * @nr_states : Number of capacity states to register - * @cb : Callback functions providing the data of the Energy Model - * - * Create Energy Model tables for a performance domain using the callbacks - * defined in cb. - * - * If multiple clients register the same performance domain, all but the first - * registration will be ignored. - * - * Return 0 on success - */ -int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, - struct em_data_callback *cb) -{ - struct device *cpu_dev; - - cpu_dev = get_cpu_device(cpumask_first(span)); - - return em_dev_register_perf_domain(cpu_dev, nr_states, cb, span); -} -EXPORT_SYMBOL_GPL(em_register_perf_domain); - /** * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device * @dev : Device for which the EM is registered -- cgit v1.2.3 From f0b5694791ce70dba16758c3b838d5ddc7731b02 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:52 +0100 Subject: PM / EM: change name of em_pd_energy to em_cpu_energy Energy Model framework now supports other devices than CPUs. Refactor some of the functions in order to prevent wrong usage. The old function em_pd_energy has to generic name. It must not be used without proper cpumask pointer, which is possible only for CPU devices. Thus, rename it and add proper description to warn of potential wrong usage for other devices. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 11 ++++++++--- kernel/sched/fair.c | 2 +- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 0f94e871a202..b67a51c574b9 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -83,15 +83,20 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, void em_dev_unregister_perf_domain(struct device *dev); /** - * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain + * em_cpu_energy() - Estimates the energy consumed by the CPUs of a + performance domain * @pd : performance domain for which energy has to be estimated * @max_util : highest utilization among CPUs of the domain * @sum_util : sum of the utilization of all CPUs in the domain * + * This function must be used only for CPU devices. There is no validation, + * i.e. if the EM is a CPU type and has cpumask allocated. It is called from + * the scheduler code quite frequently and that is why there is not checks. + * * Return: the sum of the energy consumed by the CPUs of the domain assuming * a capacity state satisfying the max utilization of the domain. */ -static inline unsigned long em_pd_energy(struct em_perf_domain *pd, +static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { unsigned long freq, scale_cpu; @@ -196,7 +201,7 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev) { return NULL; } -static inline unsigned long em_pd_energy(struct em_perf_domain *pd, +static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { return 0; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cbcb2f71599b..6da601c8d383 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6497,7 +6497,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) max_util = max(max_util, cpu_util); } - return em_pd_energy(pd->em_pd, max_util, sum_util); + return em_cpu_energy(pd->em_pd, max_util, sum_util); } /* -- cgit v1.2.3