linux_dsm_epyc7002/include/linux/cpufreq.h

434 lines
14 KiB
C
Raw Normal View History

/*
* linux/include/linux/cpufreq.h
*
* Copyright (C) 2001 Russell King
* (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
*
* 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 _LINUX_CPUFREQ_H
#define _LINUX_CPUFREQ_H
#include <linux/cpumask.h>
#include <linux/completion.h>
#include <linux/kobject.h>
#include <linux/notifier.h>
#include <linux/sysfs.h>
/*********************************************************************
* CPUFREQ INTERFACE *
*********************************************************************/
/*
* Frequency values here are CPU kHz
*
* Maximum transition latency is in nanoseconds - if it's unknown,
* CPUFREQ_ETERNAL shall be used.
*/
#define CPUFREQ_ETERNAL (-1)
#define CPUFREQ_NAME_LEN 16
/* Print length for names. Extra 1 space for accomodating '\n' in prints */
#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1)
struct cpufreq_governor;
struct cpufreq_freqs {
unsigned int cpu; /* cpu nr */
unsigned int old;
unsigned int new;
u8 flags; /* flags of cpufreq_driver, see below. */
};
struct cpufreq_cpuinfo {
unsigned int max_freq;
unsigned int min_freq;
/* in 10^(-9) s = nanoseconds */
unsigned int transition_latency;
};
struct cpufreq_real_policy {
unsigned int min; /* in kHz */
unsigned int max; /* in kHz */
unsigned int policy; /* see above */
struct cpufreq_governor *governor; /* see below */
};
struct cpufreq_policy {
/* CPUs sharing clock, require sw coordination */
cpumask_var_t cpus; /* Online CPUs only */
cpumask_var_t related_cpus; /* Online + Offline CPUs */
unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs
should set cpufreq */
unsigned int cpu; /* cpu nr of CPU managing this policy */
unsigned int last_cpu; /* cpu nr of previous CPU that managed
* this policy */
struct cpufreq_cpuinfo cpuinfo;/* see above */
unsigned int min; /* in kHz */
unsigned int max; /* in kHz */
unsigned int cur; /* in kHz, only needed if cpufreq
* governors are used */
unsigned int policy; /* see above */
struct cpufreq_governor *governor; /* see below */
void *governor_data;
cpufreq: Fix governor start/stop race condition Cpufreq governors' stop and start operations should be carried out in sequence. Otherwise, there will be unexpected behavior, like in the example below. Suppose there are 4 CPUs and policy->cpu=CPU0, CPU1/2/3 are linked to CPU0. The normal sequence is: 1) Current governor is userspace. An application tries to set the governor to ondemand. It will call __cpufreq_set_policy() in which it will stop the userspace governor and then start the ondemand governor. 2) Current governor is userspace. The online of CPU3 runs on CPU0. It will call cpufreq_add_policy_cpu() in which it will first stop the userspace governor, and then start it again. If the sequence of the above two cases interleaves, it becomes: 1) Application stops userspace governor 2) Hotplug stops userspace governor which is a problem, because the governor shouldn't be stopped twice in a row. What happens next is: 3) Application starts ondemand governor 4) Hotplug starts a governor In step 4, the hotplug is supposed to start the userspace governor, but now the governor has been changed by the application to ondemand, so the ondemand governor is started once again, which is incorrect. The solution is to prevent policy governors from being stopped multiple times in a row. A governor should only be stopped once for one policy. After it has been stopped, no more governor stop operations should be executed. Also add a mutex to serialize governor operations. [rjw: Changelog. And you owe me a beverage of my choice.] Signed-off-by: Xiaoguang Chen <chenxg@marvell.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-06-19 14:00:07 +07:00
bool governor_enabled; /* governor start/stop flag */
struct work_struct update; /* if update_policy() needs to be
* called, but you're in IRQ context */
struct cpufreq_real_policy user_policy;
struct list_head policy_list;
struct kobject kobj;
struct completion kobj_unregister;
};
/* Only for ACPI */
#define CPUFREQ_SHARED_TYPE_NONE (0) /* None */
#define CPUFREQ_SHARED_TYPE_HW (1) /* HW does needed coordination */
#define CPUFREQ_SHARED_TYPE_ALL (2) /* All dependent CPUs should set freq */
#define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/
struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
void cpufreq_cpu_put(struct cpufreq_policy *policy);
static inline bool policy_is_shared(struct cpufreq_policy *policy)
{
return cpumask_weight(policy->cpus) > 1;
}
/* /sys/devices/system/cpu/cpufreq: entry point for global variables */
extern struct kobject *cpufreq_global_kobject;
int cpufreq_get_global_kobject(void);
void cpufreq_put_global_kobject(void);
int cpufreq_sysfs_create_file(const struct attribute *attr);
void cpufreq_sysfs_remove_file(const struct attribute *attr);
#ifdef CONFIG_CPU_FREQ
unsigned int cpufreq_get(unsigned int cpu);
unsigned int cpufreq_quick_get(unsigned int cpu);
unsigned int cpufreq_quick_get_max(unsigned int cpu);
void disable_cpufreq(void);
u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
int cpufreq_update_policy(unsigned int cpu);
bool have_governor_per_policy(void);
struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
#else
static inline unsigned int cpufreq_get(unsigned int cpu)
{
return 0;
}
static inline unsigned int cpufreq_quick_get(unsigned int cpu)
{
return 0;
}
static inline unsigned int cpufreq_quick_get_max(unsigned int cpu)
{
return 0;
}
static inline void disable_cpufreq(void) { }
#endif
/*********************************************************************
* CPUFREQ DRIVER INTERFACE *
*********************************************************************/
#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */
#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */
struct freq_attr {
struct attribute attr;
ssize_t (*show)(struct cpufreq_policy *, char *);
ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count);
};
#define cpufreq_freq_attr_ro(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0444, show_##_name, NULL)
#define cpufreq_freq_attr_ro_perm(_name, _perm) \
static struct freq_attr _name = \
__ATTR(_name, _perm, show_##_name, NULL)
#define cpufreq_freq_attr_rw(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)
struct global_attr {
struct attribute attr;
ssize_t (*show)(struct kobject *kobj,
struct attribute *attr, char *buf);
ssize_t (*store)(struct kobject *a, struct attribute *b,
const char *c, size_t count);
};
#define define_one_global_ro(_name) \
static struct global_attr _name = \
__ATTR(_name, 0444, show_##_name, NULL)
#define define_one_global_rw(_name) \
static struct global_attr _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)
struct cpufreq_driver {
char name[CPUFREQ_NAME_LEN];
u8 flags;
/* needed by all drivers */
int (*init) (struct cpufreq_policy *policy);
int (*verify) (struct cpufreq_policy *policy);
/* define one out of two */
int (*setpolicy) (struct cpufreq_policy *policy);
int (*target) (struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation);
/* should be defined, if possible */
unsigned int (*get) (unsigned int cpu);
/* optional */
[ACPI/CPUFREQ] Introduce bios_limit per cpu cpufreq sysfs interface This interface is mainly intended (and implemented) for ACPI _PPC BIOS frequency limitations, but other cpufreq drivers can also use it for similar use-cases. Why is this needed: Currently it's not obvious why cpufreq got limited. People see cpufreq/scaling_max_freq reduced, but this could have happened by: - any userspace prog writing to scaling_max_freq - thermal limitations - hardware (_PPC in ACPI case) limitiations Therefore export bios_limit (in kHz) to: - Point the user that it's the BIOS (broken or intended) which limits frequency - Export it as a sysfs interface for userspace progs. While this was a rarely used feature on laptops, there will appear more and more server implemenations providing "Green IT" features like allowing the service processor to limit the frequency. People want to know about HW/BIOS frequency limitations. All ACPI P-state driven cpufreq drivers are covered with this patch: - powernow-k8 - powernow-k7 - acpi-cpufreq Tested with a patched DSDT which limits the first two cores (_PPC returns 1) via _PPC, exposed by bios_limit: # echo 2200000 >cpu2/cpufreq/scaling_max_freq # cat cpu*/cpufreq/scaling_max_freq 2600000 2600000 2200000 2200000 # #scaling_max_freq shows general user/thermal/BIOS limitations # cat cpu*/cpufreq/bios_limit 2600000 2600000 2800000 2800000 # #bios_limit only shows the HW/BIOS limitation CC: Pallipadi Venkatesh <venkatesh.pallipadi@intel.com> CC: Len Brown <lenb@kernel.org> CC: davej@codemonkey.org.uk CC: linux@dominikbrodowski.net Signed-off-by: Thomas Renninger <trenn@suse.de> Signed-off-by: Dave Jones <davej@redhat.com>
2009-11-19 18:31:01 +07:00
int (*bios_limit) (int cpu, unsigned int *limit);
int (*exit) (struct cpufreq_policy *policy);
int (*suspend) (struct cpufreq_policy *policy);
int (*resume) (struct cpufreq_policy *policy);
struct freq_attr **attr;
};
/* flags */
#define CPUFREQ_STICKY (1 << 0) /* driver isn't removed even if
all ->init() calls failed */
#define CPUFREQ_CONST_LOOPS (1 << 1) /* loops_per_jiffy or other
kernel "constants" aren't
affected by frequency
transitions */
#define CPUFREQ_PM_NO_WARN (1 << 2) /* don't warn on suspend/resume
speed mismatches */
/*
* This should be set by platforms having multiple clock-domains, i.e.
* supporting multiple policies. With this sysfs directories of governor would
* be created in cpu/cpu<num>/cpufreq/ directory and so they can use the same
* governor with different tunables for different clusters.
*/
#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY (1 << 3)
int cpufreq_register_driver(struct cpufreq_driver *driver_data);
int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
const char *cpufreq_get_current_driver(void);
static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
unsigned int min, unsigned int max)
{
if (policy->min < min)
policy->min = min;
if (policy->max < min)
policy->max = min;
if (policy->min > max)
policy->min = max;
if (policy->max > max)
policy->max = max;
if (policy->min > policy->max)
policy->min = policy->max;
return;
}
static inline void
cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
{
cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
policy->cpuinfo.max_freq);
}
/*********************************************************************
* CPUFREQ NOTIFIER INTERFACE *
*********************************************************************/
#define CPUFREQ_TRANSITION_NOTIFIER (0)
#define CPUFREQ_POLICY_NOTIFIER (1)
/* Transition notifiers */
#define CPUFREQ_PRECHANGE (0)
#define CPUFREQ_POSTCHANGE (1)
#define CPUFREQ_RESUMECHANGE (8)
#define CPUFREQ_SUSPENDCHANGE (9)
/* Policy Notifiers */
#define CPUFREQ_ADJUST (0)
#define CPUFREQ_INCOMPATIBLE (1)
#define CPUFREQ_NOTIFY (2)
#define CPUFREQ_START (3)
#define CPUFREQ_UPDATE_POLICY_CPU (4)
#ifdef CONFIG_CPU_FREQ
int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
void cpufreq_notify_transition(struct cpufreq_policy *policy,
struct cpufreq_freqs *freqs, unsigned int state);
#else /* CONFIG_CPU_FREQ */
static inline int cpufreq_register_notifier(struct notifier_block *nb,
unsigned int list)
{
return 0;
}
static inline int cpufreq_unregister_notifier(struct notifier_block *nb,
unsigned int list)
{
return 0;
}
#endif /* !CONFIG_CPU_FREQ */
/**
* cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch
* safe)
* @old: old value
* @div: divisor
* @mult: multiplier
*
*
* new = old * mult / div
*/
static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
u_int mult)
{
#if BITS_PER_LONG == 32
u64 result = ((u64) old) * ((u64) mult);
do_div(result, div);
return (unsigned long) result;
#elif BITS_PER_LONG == 64
unsigned long result = old * ((u64) mult);
result /= div;
return result;
#endif
}
/*********************************************************************
* CPUFREQ GOVERNORS *
*********************************************************************/
/*
* If (cpufreq_driver->target) exists, the ->governor decides what frequency
* within the limits is used. If (cpufreq_driver->setpolicy> exists, these
* two generic policies are available:
*/
#define CPUFREQ_POLICY_POWERSAVE (1)
#define CPUFREQ_POLICY_PERFORMANCE (2)
/* Governor Events */
#define CPUFREQ_GOV_START 1
#define CPUFREQ_GOV_STOP 2
#define CPUFREQ_GOV_LIMITS 3
#define CPUFREQ_GOV_POLICY_INIT 4
#define CPUFREQ_GOV_POLICY_EXIT 5
struct cpufreq_governor {
char name[CPUFREQ_NAME_LEN];
int initialized;
int (*governor) (struct cpufreq_policy *policy,
unsigned int event);
ssize_t (*show_setspeed) (struct cpufreq_policy *policy,
char *buf);
int (*store_setspeed) (struct cpufreq_policy *policy,
unsigned int freq);
unsigned int max_transition_latency; /* HW must be able to switch to
next freq faster than this value in nano secs or we
will fallback to performance governor */
struct list_head governor_list;
struct module *owner;
};
/* Pass a target to the cpufreq driver */
int cpufreq_driver_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation);
int __cpufreq_driver_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation);
int cpufreq_register_governor(struct cpufreq_governor *governor);
void cpufreq_unregister_governor(struct cpufreq_governor *governor);
/* CPUFREQ DEFAULT GOVERNOR */
/*
* Performance governor is fallback governor if any other gov failed to auto
* load due latency restrictions
*/
#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
extern struct cpufreq_governor cpufreq_gov_performance;
#endif
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_performance)
#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
extern struct cpufreq_governor cpufreq_gov_powersave;
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_powersave)
#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
extern struct cpufreq_governor cpufreq_gov_userspace;
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_userspace)
#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND)
extern struct cpufreq_governor cpufreq_gov_ondemand;
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_ondemand)
#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
extern struct cpufreq_governor cpufreq_gov_conservative;
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative)
#endif
/*********************************************************************
* FREQUENCY TABLE HELPERS *
*********************************************************************/
#define CPUFREQ_ENTRY_INVALID ~0
#define CPUFREQ_TABLE_END ~1
struct cpufreq_frequency_table {
unsigned int driver_data; /* driver specific data, not used by core */
unsigned int frequency; /* kHz - doesn't need to be in ascending
* order */
};
int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table);
int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table);
int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy);
int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table,
unsigned int target_freq,
unsigned int relation,
unsigned int *index);
void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy);
ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
/* the following funtion is for cpufreq core use only */
struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
/* the following are really really optional */
extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
extern struct freq_attr *cpufreq_generic_attr[];
void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
unsigned int cpu);
void cpufreq_frequency_table_put_attr(unsigned int cpu);
int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table);
static inline int cpufreq_generic_exit(struct cpufreq_policy *policy)
{
cpufreq_frequency_table_put_attr(policy->cpu);
return 0;
}
#endif /* _LINUX_CPUFREQ_H */