OpenCloudOS-Kernel/include/linux/energy_model.h

216 lines
6.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#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>
#include <linux/sched/cpufreq.h>
#include <linux/sched/topology.h>
#include <linux/types.h>
/**
* 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_perf_state {
unsigned long frequency;
unsigned long power;
unsigned long cost;
};
/**
* 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. It's here
* for performance reasons to avoid potential cache
* misses during energy calculations in the scheduler
* and simplifies allocating/freeing that memory region.
*
* 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;
int nr_perf_states;
unsigned long cpus[];
};
#define em_span_cpus(em) (to_cpumask((em)->cpus))
#ifdef CONFIG_ENERGY_MODEL
#define EM_MAX_POWER 0xFFFF
struct em_data_callback {
/**
* 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 performance state of 'dev' above
* 'freq' and update 'power' and 'freq' to the matching active power
* and frequency.
*
* 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,
struct device *dev);
};
#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_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_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_cpu_energy(struct em_perf_domain *pd,
unsigned long max_util, unsigned long sum_util)
{
unsigned long freq, scale_cpu;
struct em_perf_state *ps;
int i, cpu;
/*
* 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);
ps = &pd->table[pd->nr_perf_states - 1];
freq = map_util_freq(max_util, ps->frequency, scale_cpu);
/*
* Find the lowest performance state of the Energy Model above the
* requested frequency.
*/
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 the performance state (ps)
* can be computed as:
*
* 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 performance state
* is estimated as:
*
* ps->power * cpu_util
* cpu_nrg = -------------------- (2)
* ps->cap
*
* 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
* over a scheduling period, since it is assumed to be
* constant during that interval.
*
* By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product
* of two terms:
*
* ps->power * cpu_max_freq cpu_util
* cpu_nrg = ------------------------ * --------- (3)
* ps->freq scale_cpu
*
* 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 '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:
*
* ps->cost * \Sum cpu_util
* pd_nrg = ------------------------ (4)
* scale_cpu
*/
return ps->cost * sum_util / scale_cpu;
}
/**
* 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 performance states in the performance domain table
*/
static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
{
return pd->nr_perf_states;
}
#else
struct em_data_callback {};
#define EM_DATA_CB(_active_power_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 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_perf_states(struct em_perf_domain *pd)
{
return 0;
}
#endif
#endif