diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/cpufreq.h | 14 | ||||
| -rw-r--r-- | include/linux/cpuidle.h | 9 | ||||
| -rw-r--r-- | include/linux/devfreq.h | 9 | ||||
| -rw-r--r-- | include/linux/device.h | 5 | ||||
| -rw-r--r-- | include/linux/energy_model.h | 149 | ||||
| -rw-r--r-- | include/linux/freezer.h | 14 | ||||
| -rw-r--r-- | include/linux/intel_rapl.h | 5 | ||||
| -rw-r--r-- | include/linux/pm.h | 10 | ||||
| -rw-r--r-- | include/linux/pm_domain.h | 12 | ||||
| -rw-r--r-- | include/linux/pm_opp.h | 15 |
10 files changed, 168 insertions, 74 deletions
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 3494f6763597..e62b022cb07e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -577,6 +577,20 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); +#define cpufreq_governor_init(__governor) \ +static int __init __governor##_init(void) \ +{ \ + return cpufreq_register_governor(&__governor); \ +} \ +core_initcall(__governor##_init) + +#define cpufreq_governor_exit(__governor) \ +static void __exit __governor##_exit(void) \ +{ \ + return cpufreq_unregister_governor(&__governor); \ +} \ +module_exit(__governor##_exit) + struct cpufreq_governor *cpufreq_default_governor(void); struct cpufreq_governor *cpufreq_fallback_governor(void); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index ec2ef63771f0..b65909ae4e20 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -65,10 +65,13 @@ struct cpuidle_state { * CPUs execute ->enter_s2idle with the local tick or entire timekeeping * suspended, so it must not re-enable interrupts at any point (even * temporarily) or attempt to change states of clock event devices. + * + * This callback may point to the same function as ->enter if all of + * the above requirements are met by it. */ - void (*enter_s2idle) (struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index); + int (*enter_s2idle)(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index); }; /* Idle State Flags */ diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 57e871a559a9..12782fbb4c25 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -31,6 +31,13 @@ #define DEVFREQ_PRECHANGE (0) #define DEVFREQ_POSTCHANGE (1) +/* DEVFREQ work timers */ +enum devfreq_timer { + DEVFREQ_TIMER_DEFERRABLE = 0, + DEVFREQ_TIMER_DELAYED, + DEVFREQ_TIMER_NUM, +}; + struct devfreq; struct devfreq_governor; @@ -70,6 +77,7 @@ struct devfreq_dev_status { * @initial_freq: The operating frequency when devfreq_add_device() is * called. * @polling_ms: The polling interval in ms. 0 disables polling. + * @timer: Timer type is either deferrable or delayed timer. * @target: The device should set its operating frequency at * freq or lowest-upper-than-freq value. If freq is * higher than any operable frequency, set maximum. @@ -96,6 +104,7 @@ struct devfreq_dev_status { struct devfreq_dev_profile { unsigned long initial_freq; unsigned int polling_ms; + enum devfreq_timer timer; int (*target)(struct device *dev, unsigned long *freq, u32 flags); int (*get_dev_status)(struct device *dev, diff --git a/include/linux/device.h b/include/linux/device.h index 5efed864b387..4e2e9d3a2eda 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -13,6 +13,7 @@ #define _DEVICE_H_ #include <linux/dev_printk.h> +#include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> @@ -560,6 +561,10 @@ 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 ade6486a3382..b67a51c574b9 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 <linux/cpumask.h> +#include <linux/device.h> #include <linux/jump_label.h> #include <linux/kobject.h> #include <linux/rcupdate.h> @@ -10,13 +11,15 @@ #include <linux/types.h> /** - * em_cap_state - Capacity 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 + * em_perf_state - Performance state of a performance domain + * @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 */ -struct em_cap_state { +struct em_perf_state { unsigned long frequency; unsigned long power; unsigned long cost; @@ -24,102 +27,119 @@ struct em_cap_state { /** * em_perf_domain - Performance domain - * @table: List of capacity states, in ascending order - * @nr_cap_states: Number of capacity states - * @cpus: Cpumask covering the CPUs of the domain + * @table: List of performance states, in ascending order + * @nr_perf_states: Number of performance states + * @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_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 +#define EM_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) - * @cpu : CPU for which we do this operation + * active_power() - Provide power at the next performance state of + * a device + * @power : Active power at the performance state in mW + * (modified) + * @freq : Frequency at the performance state in kHz + * (modified) + * @dev : Device for which we do this operation (can be a CPU) * - * active_power() must find the lowest capacity 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_CPU_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 } 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); +struct em_perf_domain *em_pd_get(struct device *dev); +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 + * 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; - 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 @@ -129,55 +149,64 @@ 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 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) +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 void em_dev_unregister_perf_domain(struct device *dev) +{ +} static inline struct em_perf_domain *em_cpu_get(int cpu) { return NULL; } -static inline unsigned long em_pd_energy(struct em_perf_domain *pd, +static inline struct em_perf_domain *em_pd_get(struct device *dev) +{ + return NULL; +} +static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { 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/include/linux/freezer.h b/include/linux/freezer.h index 21f5aa0b217f..27828145ca09 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -207,6 +207,17 @@ static inline long freezable_schedule_timeout_interruptible(long timeout) return __retval; } +/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ +static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) +{ + long __retval; + + freezer_do_not_count(); + __retval = schedule_timeout_interruptible(timeout); + freezer_count_unsafe(); + return __retval; +} + /* Like schedule_timeout_killable(), but should not block the freezer. */ static inline long freezable_schedule_timeout_killable(long timeout) { @@ -285,6 +296,9 @@ static inline void set_freezable(void) {} #define freezable_schedule_timeout_interruptible(timeout) \ schedule_timeout_interruptible(timeout) +#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ + schedule_timeout_interruptible(timeout) + #define freezable_schedule_timeout_killable(timeout) \ schedule_timeout_killable(timeout) diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index efb3ce892c20..3582176a1eca 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -29,6 +29,7 @@ enum rapl_domain_reg_id { RAPL_DOMAIN_REG_PERF, RAPL_DOMAIN_REG_POLICY, RAPL_DOMAIN_REG_INFO, + RAPL_DOMAIN_REG_PL4, RAPL_DOMAIN_REG_MAX, }; @@ -38,12 +39,14 @@ enum rapl_primitives { ENERGY_COUNTER, POWER_LIMIT1, POWER_LIMIT2, + POWER_LIMIT4, FW_LOCK, PL1_ENABLE, /* power limit 1, aka long term */ PL1_CLAMP, /* allow frequency to go below OS request */ PL2_ENABLE, /* power limit 2, aka short term, instantaneous */ PL2_CLAMP, + PL4_ENABLE, /* power limit 4, aka max peak power */ TIME_WINDOW1, /* long term */ TIME_WINDOW2, /* short term */ @@ -65,7 +68,7 @@ struct rapl_domain_data { unsigned long timestamp; }; -#define NR_POWER_LIMITS (2) +#define NR_POWER_LIMITS (3) struct rapl_power_limit { struct powercap_zone_constraint *constraint; int prim_id; /* primitive ID used to enable */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 121c104a4090..a30a4b54df52 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -351,7 +351,7 @@ struct dev_pm_ops { * to RAM and hibernation. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops name = { \ +const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } @@ -369,11 +369,17 @@ const struct dev_pm_ops name = { \ * .runtime_resume(), respectively (and analogously for hibernation). */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ -const struct dev_pm_ops name = { \ +const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } +#ifdef CONFIG_PM +#define pm_ptr(_ptr) (_ptr) +#else +#define pm_ptr(_ptr) NULL +#endif + /* * PM_EVENT_ messages * diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 9ec78ee53652..ee11502a575b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -95,8 +95,8 @@ struct generic_pm_domain { struct device dev; struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ - struct list_head master_links; /* Links with PM domain as a master */ - struct list_head slave_links; /* Links with PM domain as a slave */ + struct list_head parent_links; /* Links with PM domain as a parent */ + struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; struct work_struct power_off_work; @@ -151,10 +151,10 @@ static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) } struct gpd_link { - struct generic_pm_domain *master; - struct list_head master_node; - struct generic_pm_domain *slave; - struct list_head slave_node; + struct generic_pm_domain *parent; + struct list_head parent_node; + struct generic_pm_domain *child; + struct list_head child_node; /* Sub-domain's per-master domain performance state */ unsigned int performance_state; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index d5c4a329321d..ee34c553f6bf 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> @@ -373,7 +374,11 @@ 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); int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); -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) { @@ -413,7 +418,13 @@ 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) { } |