mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 23:08:42 +07:00
00bfe05889
Conservative governor changes the CPU frequency in steps. That means that if a CPU runs at max frequency, it will need several sampling periods to return to min frequency when the workload is finished. If the update function that calculates the load and target frequency is deferred, the governor might need even more time to decrease the frequency. This may have impact to power consumption and after all conservative should decrease the frequency if there is no workload at every sampling rate. To resolve the above issue calculate the number of sampling periods that the update is deferred. Considering that for each sampling period conservative should drop the frequency by a freq_step because the CPU was idle apply the proper subtraction to requested frequency. Below, the kernel trace with and without this patch. First an intensive workload is applied on a specific CPU. Then the workload is removed and the CPU goes to idle. WITHOUT <idle>-0 [007] dN.. 620.329153: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 620.350857: cpu_frequency: state=1700000 cpu_id=7 kworker/7:2-556 [007] .... 620.370856: cpu_frequency: state=1900000 cpu_id=7 kworker/7:2-556 [007] .... 620.390854: cpu_frequency: state=2100000 cpu_id=7 kworker/7:2-556 [007] .... 620.411853: cpu_frequency: state=2200000 cpu_id=7 kworker/7:2-556 [007] .... 620.432854: cpu_frequency: state=2400000 cpu_id=7 kworker/7:2-556 [007] .... 620.453854: cpu_frequency: state=2600000 cpu_id=7 kworker/7:2-556 [007] .... 620.494856: cpu_frequency: state=2900000 cpu_id=7 kworker/7:2-556 [007] .... 620.515856: cpu_frequency: state=3100000 cpu_id=7 kworker/7:2-556 [007] .... 620.536858: cpu_frequency: state=3300000 cpu_id=7 kworker/7:2-556 [007] .... 620.557857: cpu_frequency: state=3401000 cpu_id=7 <idle>-0 [007] d... 669.591363: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 669.591939: cpu_idle: state=4294967295 cpu_id=7 <idle>-0 [007] d... 669.591980: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] dN.. 669.591989: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 670.201224: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 670.221975: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 670.222016: cpu_frequency: state=3300000 cpu_id=7 <idle>-0 [007] d... 670.222026: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 670.234964: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 670.801251: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.236046: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 671.236073: cpu_frequency: state=3100000 cpu_id=7 <idle>-0 [007] d... 671.236112: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.393437: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 671.401277: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.404083: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 671.404111: cpu_frequency: state=2900000 cpu_id=7 <idle>-0 [007] d... 671.404125: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.404974: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 671.501180: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.995414: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 671.995459: cpu_frequency: state=2800000 cpu_id=7 <idle>-0 [007] d... 671.995469: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 671.996287: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 672.001305: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.078374: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 672.078410: cpu_frequency: state=2600000 cpu_id=7 <idle>-0 [007] d... 672.078419: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.158020: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 672.158040: cpu_frequency: state=2400000 cpu_id=7 <idle>-0 [007] d... 672.158044: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.160038: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 672.234557: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.237121: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 672.237174: cpu_frequency: state=2100000 cpu_id=7 <idle>-0 [007] d... 672.237186: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.237778: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 672.267902: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.269860: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 672.269906: cpu_frequency: state=1900000 cpu_id=7 <idle>-0 [007] d... 672.269914: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.271902: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 672.751342: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 672.823056: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-556 [007] .... 672.823095: cpu_frequency: state=1600000 cpu_id=7 WITH <idle>-0 [007] dN.. 4380.928009: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-399 [007] .... 4380.949767: cpu_frequency: state=2000000 cpu_id=7 kworker/7:2-399 [007] .... 4380.969765: cpu_frequency: state=2200000 cpu_id=7 kworker/7:2-399 [007] .... 4381.009766: cpu_frequency: state=2500000 cpu_id=7 kworker/7:2-399 [007] .... 4381.029767: cpu_frequency: state=2600000 cpu_id=7 kworker/7:2-399 [007] .... 4381.049769: cpu_frequency: state=2800000 cpu_id=7 kworker/7:2-399 [007] .... 4381.069769: cpu_frequency: state=3000000 cpu_id=7 kworker/7:2-399 [007] .... 4381.089771: cpu_frequency: state=3100000 cpu_id=7 kworker/7:2-399 [007] .... 4381.109772: cpu_frequency: state=3400000 cpu_id=7 kworker/7:2-399 [007] .... 4381.129773: cpu_frequency: state=3401000 cpu_id=7 <idle>-0 [007] d... 4428.226159: cpu_idle: state=1 cpu_id=7 <idle>-0 [007] d... 4428.226176: cpu_idle: state=4294967295 cpu_id=7 <idle>-0 [007] d... 4428.226181: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4428.227177: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 4428.551640: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4428.649239: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-399 [007] .... 4428.649268: cpu_frequency: state=2800000 cpu_id=7 <idle>-0 [007] d... 4428.649278: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4428.689856: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 4428.799542: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4428.801683: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-399 [007] .... 4428.801748: cpu_frequency: state=1700000 cpu_id=7 <idle>-0 [007] d... 4428.801761: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4428.806545: cpu_idle: state=4294967295 cpu_id=7 ... <idle>-0 [007] d... 4429.051880: cpu_idle: state=4 cpu_id=7 <idle>-0 [007] d... 4429.086240: cpu_idle: state=4294967295 cpu_id=7 kworker/7:2-399 [007] .... 4429.086293: cpu_frequency: state=1600000 cpu_id=7 Without the patch the CPU dropped to min frequency after 3.2s With the patch applied the CPU dropped to min frequency after 0.86s Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
186 lines
5.6 KiB
C
186 lines
5.6 KiB
C
/*
|
|
* drivers/cpufreq/cpufreq_governor.h
|
|
*
|
|
* Header file for CPUFreq governors common code
|
|
*
|
|
* Copyright (C) 2001 Russell King
|
|
* (C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
|
|
* (C) 2003 Jun Nakajima <jun.nakajima@intel.com>
|
|
* (C) 2009 Alexander Clouter <alex@digriz.org.uk>
|
|
* (c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#ifndef _CPUFREQ_GOVERNOR_H
|
|
#define _CPUFREQ_GOVERNOR_H
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/irq_work.h>
|
|
#include <linux/cpufreq.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/module.h>
|
|
#include <linux/mutex.h>
|
|
|
|
/* Ondemand Sampling types */
|
|
enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
|
|
|
|
/*
|
|
* Abbreviations:
|
|
* dbs: used as a shortform for demand based switching It helps to keep variable
|
|
* names smaller, simpler
|
|
* cdbs: common dbs
|
|
* od_*: On-demand governor
|
|
* cs_*: Conservative governor
|
|
*/
|
|
|
|
/* Governor demand based switching data (per-policy or global). */
|
|
struct dbs_data {
|
|
struct gov_attr_set attr_set;
|
|
void *tuners;
|
|
unsigned int min_sampling_rate;
|
|
unsigned int ignore_nice_load;
|
|
unsigned int sampling_rate;
|
|
unsigned int sampling_down_factor;
|
|
unsigned int up_threshold;
|
|
unsigned int io_is_busy;
|
|
};
|
|
|
|
static inline struct dbs_data *to_dbs_data(struct gov_attr_set *attr_set)
|
|
{
|
|
return container_of(attr_set, struct dbs_data, attr_set);
|
|
}
|
|
|
|
#define gov_show_one(_gov, file_name) \
|
|
static ssize_t show_##file_name \
|
|
(struct gov_attr_set *attr_set, char *buf) \
|
|
{ \
|
|
struct dbs_data *dbs_data = to_dbs_data(attr_set); \
|
|
struct _gov##_dbs_tuners *tuners = dbs_data->tuners; \
|
|
return sprintf(buf, "%u\n", tuners->file_name); \
|
|
}
|
|
|
|
#define gov_show_one_common(file_name) \
|
|
static ssize_t show_##file_name \
|
|
(struct gov_attr_set *attr_set, char *buf) \
|
|
{ \
|
|
struct dbs_data *dbs_data = to_dbs_data(attr_set); \
|
|
return sprintf(buf, "%u\n", dbs_data->file_name); \
|
|
}
|
|
|
|
#define gov_attr_ro(_name) \
|
|
static struct governor_attr _name = \
|
|
__ATTR(_name, 0444, show_##_name, NULL)
|
|
|
|
#define gov_attr_rw(_name) \
|
|
static struct governor_attr _name = \
|
|
__ATTR(_name, 0644, show_##_name, store_##_name)
|
|
|
|
/* Common to all CPUs of a policy */
|
|
struct policy_dbs_info {
|
|
struct cpufreq_policy *policy;
|
|
/*
|
|
* Per policy mutex that serializes load evaluation from limit-change
|
|
* and work-handler.
|
|
*/
|
|
struct mutex update_mutex;
|
|
|
|
u64 last_sample_time;
|
|
s64 sample_delay_ns;
|
|
atomic_t work_count;
|
|
struct irq_work irq_work;
|
|
struct work_struct work;
|
|
/* dbs_data may be shared between multiple policy objects */
|
|
struct dbs_data *dbs_data;
|
|
struct list_head list;
|
|
/* Multiplier for increasing sample delay temporarily. */
|
|
unsigned int rate_mult;
|
|
unsigned int idle_periods; /* For conservative */
|
|
/* Status indicators */
|
|
bool is_shared; /* This object is used by multiple CPUs */
|
|
bool work_in_progress; /* Work is being queued up or in progress */
|
|
};
|
|
|
|
static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs,
|
|
unsigned int delay_us)
|
|
{
|
|
policy_dbs->sample_delay_ns = delay_us * NSEC_PER_USEC;
|
|
}
|
|
|
|
/* Per cpu structures */
|
|
struct cpu_dbs_info {
|
|
u64 prev_cpu_idle;
|
|
u64 prev_update_time;
|
|
u64 prev_cpu_nice;
|
|
/*
|
|
* Used to keep track of load in the previous interval. However, when
|
|
* explicitly set to zero, it is used as a flag to ensure that we copy
|
|
* the previous load to the current interval only once, upon the first
|
|
* wake-up from idle.
|
|
*/
|
|
unsigned int prev_load;
|
|
struct update_util_data update_util;
|
|
struct policy_dbs_info *policy_dbs;
|
|
};
|
|
|
|
/* Common Governor data across policies */
|
|
struct dbs_governor {
|
|
struct cpufreq_governor gov;
|
|
struct kobj_type kobj_type;
|
|
|
|
/*
|
|
* Common data for platforms that don't set
|
|
* CPUFREQ_HAVE_GOVERNOR_PER_POLICY
|
|
*/
|
|
struct dbs_data *gdbs_data;
|
|
|
|
unsigned int (*gov_dbs_update)(struct cpufreq_policy *policy);
|
|
struct policy_dbs_info *(*alloc)(void);
|
|
void (*free)(struct policy_dbs_info *policy_dbs);
|
|
int (*init)(struct dbs_data *dbs_data);
|
|
void (*exit)(struct dbs_data *dbs_data);
|
|
void (*start)(struct cpufreq_policy *policy);
|
|
};
|
|
|
|
static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
|
|
{
|
|
return container_of(policy->governor, struct dbs_governor, gov);
|
|
}
|
|
|
|
/* Governor callback routines */
|
|
int cpufreq_dbs_governor_init(struct cpufreq_policy *policy);
|
|
void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy);
|
|
int cpufreq_dbs_governor_start(struct cpufreq_policy *policy);
|
|
void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy);
|
|
void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy);
|
|
|
|
#define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \
|
|
{ \
|
|
.name = _name_, \
|
|
.max_transition_latency = TRANSITION_LATENCY_LIMIT, \
|
|
.owner = THIS_MODULE, \
|
|
.init = cpufreq_dbs_governor_init, \
|
|
.exit = cpufreq_dbs_governor_exit, \
|
|
.start = cpufreq_dbs_governor_start, \
|
|
.stop = cpufreq_dbs_governor_stop, \
|
|
.limits = cpufreq_dbs_governor_limits, \
|
|
}
|
|
|
|
/* Governor specific operations */
|
|
struct od_ops {
|
|
unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
|
|
unsigned int freq_next, unsigned int relation);
|
|
};
|
|
|
|
unsigned int dbs_update(struct cpufreq_policy *policy);
|
|
void od_register_powersave_bias_handler(unsigned int (*f)
|
|
(struct cpufreq_policy *, unsigned int, unsigned int),
|
|
unsigned int powersave_bias);
|
|
void od_unregister_powersave_bias_handler(void);
|
|
ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
|
|
size_t count);
|
|
void gov_update_cpu_data(struct dbs_data *dbs_data);
|
|
#endif /* _CPUFREQ_GOVERNOR_H */
|