linux/drivers/cpufreq/cpufreq_governor.h
Viresh Kumar c443563036 cpufreq: governor: New sysfs show/store callbacks for governor tunables
The ondemand and conservative governors use the global-attr or freq-attr
structures to represent sysfs attributes corresponding to their tunables
(which of them is actually used depends on whether or not different
policy objects can use the same governor with different tunables at the
same time and, consequently, on where those attributes are located in
sysfs).

Unfortunately, in the freq-attr case, the standard cpufreq show/store
sysfs attribute callbacks are applied to the governor tunable attributes
and they always acquire the policy->rwsem lock before carrying out the
operation.  That may lead to an ABBA deadlock if governor tunable
attributes are removed under policy->rwsem while one of them is being
accessed concurrently (if sysfs attributes removal wins the race, it
will wait for the access to complete with policy->rwsem held while the
attribute callback will block on policy->rwsem indefinitely).

We attempted to address this issue by dropping policy->rwsem around
governor tunable attributes removal (that is, around invocations of the
->governor callback with the event arg equal to CPUFREQ_GOV_POLICY_EXIT)
in cpufreq_set_policy(), but that opened up race conditions that had not
been possible with policy->rwsem held all the time.  Therefore
policy->rwsem cannot be dropped in cpufreq_set_policy() at any point,
but the deadlock situation described above must be avoided too.

To that end, use the observation that in principle governor tunables may
be represented by the same data type regardless of whether the governor
is system-wide or per-policy and introduce a new structure, struct
governor_attr, for representing them and new corresponding macros for
creating show/store sysfs callbacks for them.  Also make their parent
kobject use a new kobject type whose default show/store callbacks are
not related to the standard core cpufreq ones in any way (and they don't
acquire policy->rwsem in particular).

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[ rjw: Subject & changelog + rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-03-09 14:40:58 +01:00

327 lines
9.6 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>
/*
* The polling frequency depends on the capability of the processor. Default
* polling frequency is 1000 times the transition latency of the processor. The
* governor will work on any processor with transition latency <= 10ms, using
* appropriate sampling rate.
*
* For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL)
* this governor will not work. All times here are in us (micro seconds).
*/
#define MIN_SAMPLING_RATE_RATIO (2)
#define LATENCY_MULTIPLIER (1000)
#define MIN_LATENCY_MULTIPLIER (20)
#define TRANSITION_LATENCY_LIMIT (10 * 1000 * 1000)
/* Ondemand Sampling types */
enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
/*
* Macro for creating governors sysfs routines
*
* - gov_sys: One governor instance per whole system
* - gov_pol: One governor instance per policy
*/
/* Create attributes */
#define gov_sys_attr_ro(_name) \
static struct global_attr _name##_gov_sys = \
__ATTR(_name, 0444, show_##_name##_gov_sys, NULL)
#define gov_sys_attr_rw(_name) \
static struct global_attr _name##_gov_sys = \
__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
#define gov_pol_attr_ro(_name) \
static struct freq_attr _name##_gov_pol = \
__ATTR(_name, 0444, show_##_name##_gov_pol, NULL)
#define gov_pol_attr_rw(_name) \
static struct freq_attr _name##_gov_pol = \
__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
#define gov_sys_pol_attr_rw(_name) \
gov_sys_attr_rw(_name); \
gov_pol_attr_rw(_name)
#define gov_sys_pol_attr_ro(_name) \
gov_sys_attr_ro(_name); \
gov_pol_attr_ro(_name)
/* Create show/store routines */
#define show_one(_gov, file_name) \
static ssize_t show_##file_name##_gov_sys \
(struct kobject *kobj, struct attribute *attr, char *buf) \
{ \
struct _gov##_dbs_tuners *tuners = _gov##_dbs_gov.gdbs_data->tuners; \
return sprintf(buf, "%u\n", tuners->file_name); \
} \
\
static ssize_t show_##file_name##_gov_pol \
(struct cpufreq_policy *policy, char *buf) \
{ \
struct policy_dbs_info *policy_dbs = policy->governor_data; \
struct dbs_data *dbs_data = policy_dbs->dbs_data; \
struct _gov##_dbs_tuners *tuners = dbs_data->tuners; \
return sprintf(buf, "%u\n", tuners->file_name); \
}
#define store_one(_gov, file_name) \
static ssize_t store_##file_name##_gov_sys \
(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) \
{ \
struct dbs_data *dbs_data = _gov##_dbs_gov.gdbs_data; \
return store_##file_name(dbs_data, buf, count); \
} \
\
static ssize_t store_##file_name##_gov_pol \
(struct cpufreq_policy *policy, const char *buf, size_t count) \
{ \
struct policy_dbs_info *policy_dbs = policy->governor_data; \
return store_##file_name(policy_dbs->dbs_data, buf, count); \
}
#define show_store_one(_gov, file_name) \
show_one(_gov, file_name); \
store_one(_gov, file_name)
#define show_one_common(_gov, file_name) \
static ssize_t show_##file_name##_gov_sys \
(struct kobject *kobj, struct attribute *attr, char *buf) \
{ \
struct dbs_data *dbs_data = _gov##_dbs_gov.gdbs_data; \
return sprintf(buf, "%u\n", dbs_data->file_name); \
} \
\
static ssize_t show_##file_name##_gov_pol \
(struct cpufreq_policy *policy, char *buf) \
{ \
struct policy_dbs_info *policy_dbs = policy->governor_data; \
struct dbs_data *dbs_data = policy_dbs->dbs_data; \
return sprintf(buf, "%u\n", dbs_data->file_name); \
}
#define show_store_one_common(_gov, file_name) \
show_one_common(_gov, file_name); \
store_one(_gov, file_name)
/* create helper routines */
#define define_get_cpu_dbs_routines(_dbs_info) \
static struct cpu_dbs_info *get_cpu_cdbs(int cpu) \
{ \
return &per_cpu(_dbs_info, cpu).cdbs; \
} \
\
static void *get_cpu_dbs_info_s(int cpu) \
{ \
return &per_cpu(_dbs_info, cpu); \
}
/*
* 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 {
int usage_count;
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;
struct kobject kobj;
/* Protect concurrent updates to governor tunables from sysfs */
struct mutex mutex;
};
/* Governor's specific attributes */
struct dbs_data;
struct governor_attr {
struct attribute attr;
ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
size_t count);
};
#define gov_show_one(_gov, file_name) \
static ssize_t show_##file_name \
(struct dbs_data *dbs_data, char *buf) \
{ \
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 dbs_data *dbs_data, char *buf) \
{ \
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 timer_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;
};
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_cpu_wall;
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;
};
struct od_cpu_dbs_info_s {
struct cpu_dbs_info cdbs;
struct cpufreq_frequency_table *freq_table;
unsigned int freq_lo;
unsigned int freq_lo_jiffies;
unsigned int freq_hi_jiffies;
unsigned int rate_mult;
unsigned int sample_type:1;
};
struct cs_cpu_dbs_info_s {
struct cpu_dbs_info cdbs;
unsigned int down_skip;
unsigned int requested_freq;
};
/* Per policy Governors sysfs tunables */
struct od_dbs_tuners {
unsigned int powersave_bias;
unsigned int io_is_busy;
};
struct cs_dbs_tuners {
unsigned int down_threshold;
unsigned int freq_step;
};
/* Common Governor data across policies */
struct dbs_governor {
struct cpufreq_governor gov;
#define GOV_ONDEMAND 0
#define GOV_CONSERVATIVE 1
int governor;
struct kobj_type kobj_type;
/*
* Common data for platforms that don't set
* CPUFREQ_HAVE_GOVERNOR_PER_POLICY
*/
struct dbs_data *gdbs_data;
struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
void *(*get_cpu_dbs_info_s)(int cpu);
unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
void (*gov_check_cpu)(int cpu, unsigned int load);
int (*init)(struct dbs_data *dbs_data, bool notify);
void (*exit)(struct dbs_data *dbs_data, bool notify);
/* Governor specific ops, see below */
void *gov_ops;
};
static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
{
return container_of(policy->governor, struct dbs_governor, gov);
}
/* Governor specific ops, will be passed to dbs_data->gov_ops */
struct od_ops {
void (*powersave_bias_init_cpu)(int cpu);
unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
unsigned int freq_next, unsigned int relation);
void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
};
static inline int delay_for_sampling_rate(unsigned int sampling_rate)
{
int delay = usecs_to_jiffies(sampling_rate);
/* We want all CPUs to do sampling nearly on same jiffy */
if (num_online_cpus() > 1)
delay -= jiffies % delay;
return delay;
}
extern struct mutex dbs_data_mutex;
extern struct mutex cpufreq_governor_lock;
void dbs_check_cpu(struct cpufreq_policy *policy);
int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
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);
#endif /* _CPUFREQ_GOVERNOR_H */