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 daniel.lezcano@linaro.org Acked-by: Quentin Perret qperret@google.com Signed-off-by: Lukasz Luba lukasz.luba@arm.com --- drivers/thermal/cpufreq_cooling.c | 12 ++--- include/linux/energy_model.h | 86 +++++++++++++++++-------------- kernel/power/energy_model.c | 44 ++++++++-------- kernel/sched/topology.c | 20 +++---- 4 files changed, 84 insertions(+), 78 deletions(-)

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index e297e135c031..ad8971e26538 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -333,18 +333,18 @@ static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev, return false;

policy = cpufreq_cdev->policy; - if (!cpumask_equal(policy->related_cpus, to_cpumask(em->cpus))) { + if (!cpumask_equal(policy->related_cpus, em_span_cpus(em))) { pr_err("The span of pd %*pbl is misaligned with cpufreq policy %*pbl\n", - cpumask_pr_args(to_cpumask(em->cpus)), + cpumask_pr_args(em_span_cpus(em)), cpumask_pr_args(policy->related_cpus)); return false; }

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); + if (em_pd_nr_perf_states(em) != nr_levels) { + pr_err("The number of performance states in pd %*pbl (%u) doesn't match the number of cooling levels (%u)\n", + cpumask_pr_args(em_span_cpus(em)), + em_pd_nr_perf_states(em), nr_levels); return false; }

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index ade6486a3382..fe336a9eb5d4 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -10,13 +10,13 @@ #include <linux/types.h>

/** - * em_cap_state - Capacity state of a performance domain + * 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 * @cost: The cost coefficient associated with this level, used during * energy calculation. Equal to: power * max_frequency / frequency */ -struct em_cap_state { +struct em_perf_state { unsigned long frequency; unsigned long power; unsigned long cost; @@ -24,8 +24,8 @@ struct em_cap_state {

/** * em_perf_domain - Performance domain - * @table: List of capacity states, in ascending order - * @nr_cap_states: Number of capacity states + * @table: List of performance states, in ascending order + * @nr_perf_states: Number of performance states * @cpus: Cpumask covering the CPUs of the domain * * A "performance domain" represents a group of CPUs whose performance is @@ -34,22 +34,27 @@ struct em_cap_state { * CPUFreq policies. */ struct em_perf_domain { - struct em_cap_state *table; - int nr_cap_states; + struct em_perf_state *table; + int nr_perf_states; unsigned long cpus[]; };

+#define em_span_cpus(em) (to_cpumask((em)->cpus)) + #ifdef CONFIG_ENERGY_MODEL #define EM_CPU_MAX_POWER 0xFFFF

struct em_data_callback { /** - * active_power() - Provide power at the next capacity state of a CPU - * @power : Active power at the capacity state in mW (modified) - * @freq : Frequency at the capacity state in kHz (modified) + * active_power() - Provide power at the next performance state of + * a CPU + * @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 * - * active_power() must find the lowest capacity state of 'cpu' above + * active_power() must find the lowest performance state of 'cpu' above * 'freq' and update 'power' and 'freq' to the matching active power * and frequency. * @@ -80,46 +85,46 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { unsigned long freq, scale_cpu; - struct em_cap_state *cs; + struct em_perf_state *ps; int i, cpu;

/* - * In order to predict the capacity state, map the utilization of the - * most utilized CPU of the performance domain to a requested frequency, - * like schedutil. + * In order to predict the performance state, map the utilization of + * the most utilized CPU of the performance domain to a requested + * frequency, like schedutil. */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); - cs = &pd->table[pd->nr_cap_states - 1]; - freq = map_util_freq(max_util, cs->frequency, scale_cpu); + ps = &pd->table[pd->nr_perf_states - 1]; + freq = map_util_freq(max_util, ps->frequency, scale_cpu);

/* - * Find the lowest capacity state of the Energy Model above the + * Find the lowest performance state of the Energy Model above the * requested frequency. */ - for (i = 0; i < pd->nr_cap_states; i++) { - cs = &pd->table[i]; - if (cs->frequency >= freq) + for (i = 0; i < pd->nr_perf_states; i++) { + ps = &pd->table[i]; + if (ps->frequency >= freq) break; }

/* - * The capacity of a CPU in the domain at that capacity state (cs) + * The capacity of a CPU in the domain at the performance state (ps) * can be computed as: * - * cs->freq * scale_cpu - * cs->cap = -------------------- (1) + * ps->freq * scale_cpu + * ps->cap = -------------------- (1) * cpu_max_freq * * So, ignoring the costs of idle states (which are not available in - * the EM), the energy consumed by this CPU at that capacity state is - * estimated as: + * the EM), the energy consumed by this CPU at that performance state + * is estimated as: * - * cs->power * cpu_util + * ps->power * cpu_util * cpu_nrg = -------------------- (2) - * cs->cap + * ps->cap * - * since 'cpu_util / cs->cap' represents its percentage of busy time. + * since 'cpu_util / ps->cap' represents its percentage of busy time. * * NOTE: Although the result of this computation actually is in * units of power, it can be manipulated as an energy value @@ -129,34 +134,35 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product * of two terms: * - * cs->power * cpu_max_freq cpu_util + * ps->power * cpu_max_freq cpu_util * cpu_nrg = ------------------------ * --------- (3) - * cs->freq scale_cpu + * ps->freq scale_cpu * - * The first term is static, and is stored in the em_cap_state struct - * as 'cs->cost'. + * The first term is static, and is stored in the em_perf_state struct + * as 'ps->cost'. * * Since all CPUs of the domain have the same micro-architecture, they - * share the same 'cs->cost', and the same CPU capacity. Hence, the + * share the same 'ps->cost', and the same CPU capacity. Hence, the * total energy of the domain (which is the simple sum of the energy of * all of its CPUs) can be factorized as: * - * cs->cost * \Sum cpu_util + * ps->cost * \Sum cpu_util * pd_nrg = ------------------------ (4) * scale_cpu */ - return cs->cost * sum_util / scale_cpu; + return ps->cost * sum_util / scale_cpu; }

/** - * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain + * em_pd_nr_perf_states() - Get the number of performance states of a perf. + * domain * @pd : performance domain for which this must be done * - * Return: the number of capacity states in the performance domain table + * Return: the number of performance states in the performance domain table */ -static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { - return pd->nr_cap_states; + return pd->nr_perf_states; }

#else @@ -177,7 +183,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, { return 0; } -static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { return 0; } 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 8344757bba6e..0a411df05fb3 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -282,10 +282,10 @@ 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; }

@@ -323,26 +323,26 @@ 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; @@ -394,15 +394,15 @@ 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;

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 qperret@google.com Signed-off-by: Lukasz Luba lukasz.luba@arm.com --- 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(-)

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 9cd8f0adacae..5b75829a915d 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1047,9 +1047,8 @@ 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; @@ -1057,10 +1056,6 @@ 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; @@ -1128,6 +1123,6 @@ 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;

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 daniel.lezcano@linaro.org Acked-by: Quentin Perret qperret@google.com Signed-off-by: Lukasz Luba lukasz.luba@arm.com --- include/linux/energy_model.h | 11 ++++++++--- kernel/sched/fair.c | 2 +- 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 3aaa0bc43429..a0aff705b535 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 538ba5d94e99..c28f1de43f5e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6489,7 +6489,7 @@ 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); }

/*

The Energy Model framework supports not only CPU devices. Drop the CPU specific interface with cpumask and add struct device. Add also a return value, user might use it. This new interface provides easy way to create a simple Energy Model, which then might be used by e.g. thermal subsystem.

Acked-by: Daniel Lezcano daniel.lezcano@linaro.org Signed-off-by: Lukasz Luba lukasz.luba@arm.com --- drivers/cpufreq/cpufreq-dt.c | 2 +- drivers/cpufreq/imx6q-cpufreq.c | 2 +- drivers/cpufreq/mediatek-cpufreq.c | 2 +- drivers/cpufreq/omap-cpufreq.c | 2 +- drivers/cpufreq/qcom-cpufreq-hw.c | 2 +- drivers/cpufreq/scpi-cpufreq.c | 2 +- drivers/cpufreq/vexpress-spc-cpufreq.c | 2 +- drivers/opp/of.c | 71 ++++++++++++++++---------- include/linux/pm_opp.h | 15 +++++- 9 files changed, 65 insertions(+), 35 deletions(-)

diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 26fe8dfb9ce6..f9f03fd49b83 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -275,7 +275,7 @@ static int cpufreq_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = transition_latency; policy->dvfs_possible_from_any_cpu = true;

- dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(cpu_dev, policy->cpus);

return 0;

diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index fdb2ffffbd15..ef7b34c1fd2b 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -193,7 +193,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy) policy->clk = clks[ARM].clk; cpufreq_generic_init(policy, freq_table, transition_latency); policy->suspend_freq = max_freq; - dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(cpu_dev, policy->cpus);

return 0; } diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 0c98dd08273d..7d1212c9b7c8 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -448,7 +448,7 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy) policy->driver_data = info; policy->clk = info->cpu_clk;

- dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(info->cpu_dev, policy->cpus);

return 0; } diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index 8d14b42a8c6f..3694bb030df3 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -131,7 +131,7 @@ static int omap_cpu_init(struct cpufreq_policy *policy)

/* FIXME: what's the actual transition time? */ cpufreq_generic_init(policy, freq_table, 300 * 1000); - dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(mpu_dev, policy->cpus);

return 0; } diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index fc92a8842e25..0a04b6f03b9a 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -238,7 +238,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) goto error; }

- dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(cpu_dev, policy->cpus);

policy->fast_switch_possible = true;

diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index 20d1f85d5f5a..b0f5388b8854 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -167,7 +167,7 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)

policy->fast_switch_possible = false;

- dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(cpu_dev, policy->cpus);

return 0;

diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index 83c85d3d67e3..4e8b1dee7c9a 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -450,7 +450,7 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy) policy->freq_table = freq_table[cur_cluster]; policy->cpuinfo.transition_latency = 1000000; /* 1 ms */

- dev_pm_opp_of_register_em(policy->cpus); + dev_pm_opp_of_register_em(cpu_dev, policy->cpus);

if (is_bL_switching_enabled()) per_cpu(cpu_last_req_freq, policy->cpu) = diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 5b75829a915d..4500ce46d476 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1036,18 +1036,18 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);

/* * Callback function provided to the Energy Model framework upon registration. - * This computes the power estimated by @CPU at @kHz if it is the frequency + * This computes the power estimated by @dev at @kHz if it is the frequency * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled * frequency and @mW to the associated power. The power is estimated as - * P = C * V^2 * f with C being the CPU's capacitance and V and f respectively - * the voltage and frequency of the OPP. + * P = C * V^2 * f with C being the device's capacitance and V and f + * respectively the voltage and frequency of the OPP. * - * Returns -ENODEV if the CPU device cannot be found, -EINVAL if the power - * calculation failed because of missing parameters, 0 otherwise. + * Returns -EINVAL if the power calculation failed because of missing + * parameters, 0 otherwise. */ -static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, - struct device *cpu_dev) +static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz, + struct device *dev) { struct dev_pm_opp *opp; struct device_node *np; @@ -1056,7 +1056,7 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, u64 tmp; int ret;

- np = of_node_get(cpu_dev->of_node); + np = of_node_get(dev->of_node); if (!np) return -EINVAL;

@@ -1066,7 +1066,7 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz, return -EINVAL;

Hz = *kHz * 1000; - opp = dev_pm_opp_find_freq_ceil(cpu_dev, &Hz); + opp = dev_pm_opp_find_freq_ceil(dev, &Hz); if (IS_ERR(opp)) return -EINVAL;

@@ -1086,30 +1086,38 @@ static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,

/** * dev_pm_opp_of_register_em() - Attempt to register an Energy Model - * @cpus : CPUs for which an Energy Model has to be registered + * @dev : Device for which an Energy Model has to be registered + * @cpus : CPUs for which an Energy Model has to be registered. For + * other type of devices it should be set to NULL. * * This checks whether the "dynamic-power-coefficient" devicetree property has * been specified, and tries to register an Energy Model with it if it has. + * Having this property means the voltages are known for OPPs and the EM + * might be calculated. */ -void dev_pm_opp_of_register_em(struct cpumask *cpus) +int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus) { - struct em_data_callback em_cb = EM_DATA_CB(_get_cpu_power); - int ret, nr_opp, cpu = cpumask_first(cpus); - struct device *cpu_dev; + struct em_data_callback em_cb = EM_DATA_CB(_get_power); struct device_node *np; + int ret, nr_opp; u32 cap;

- cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) - return; + if (IS_ERR_OR_NULL(dev)) { + ret = -EINVAL; + goto failed; + }

- nr_opp = dev_pm_opp_get_opp_count(cpu_dev); - if (nr_opp <= 0) - return; + nr_opp = dev_pm_opp_get_opp_count(dev); + if (nr_opp <= 0) { + ret = -EINVAL; + goto failed; + }

- np = of_node_get(cpu_dev->of_node); - if (!np) - return; + np = of_node_get(dev->of_node); + if (!np) { + ret = -EINVAL; + goto failed; + }

/* * Register an EM only if the 'dynamic-power-coefficient' property is @@ -1120,9 +1128,20 @@ void dev_pm_opp_of_register_em(struct cpumask *cpus) */ ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap); of_node_put(np); - if (ret || !cap) - return; + if (ret || !cap) { + dev_dbg(dev, "Couldn't find proper 'dynamic-power-coefficient' in DT\n"); + ret = -EINVAL; + goto failed; + }

- em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, cpus); + ret = em_dev_register_perf_domain(dev, nr_opp, &em_cb, cpus); + if (ret) + goto failed; + + return 0; + +failed: + dev_dbg(dev, "Couldn't register Energy Model %d\n", ret); + return ret; } EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em); diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 747861816f4f..8df8b82054e5 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -11,6 +11,7 @@ #ifndef __LINUX_OPP_H__ #define __LINUX_OPP_H__

+#include <linux/energy_model.h> #include <linux/err.h> #include <linux/notifier.h>

@@ -360,7 +361,11 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); -void dev_pm_opp_of_register_em(struct cpumask *cpus); +int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus); +static inline void dev_pm_opp_of_unregister_em(struct device *dev) +{ + em_dev_unregister_perf_domain(dev); +} #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -400,7 +405,13 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) return NULL; }

-static inline void dev_pm_opp_of_register_em(struct cpumask *cpus) +static inline int dev_pm_opp_of_register_em(struct device *dev, + struct cpumask *cpus) +{ + return -ENOTSUPP; +} + +static inline void dev_pm_opp_of_unregister_em(struct device *dev) { }