alistair23-linux/include/linux/timer.h
Thomas Gleixner bc7a34b8b9 timer: Reduce timer migration overhead if disabled
Eric reported that the timer_migration sysctl is not really nice
performance wise as it needs to check at every timer insertion whether
the feature is enabled or not. Further the check does not live in the
timer code, so we have an extra function call which checks an extra
cache line to figure out that it is disabled.

We can do better and store that information in the per cpu (hr)timer
bases. I pondered to use a static key, but that's a nightmare to
update from the nohz code and the timer base cache line is hot anyway
when we select a timer base.

The old logic enabled the timer migration unconditionally if
CONFIG_NO_HZ was set even if nohz was disabled on the kernel command
line.

With this modification, we start off with migration disabled. The user
visible sysctl is still set to enabled. If the kernel switches to NOHZ
migration is enabled, if the user did not disable it via the sysctl
prior to the switch. If nohz=off is on the kernel command line,
migration stays disabled no matter what.

Before:
  47.76%  hog       [.] main
  14.84%  [kernel]  [k] _raw_spin_lock_irqsave
   9.55%  [kernel]  [k] _raw_spin_unlock_irqrestore
   6.71%  [kernel]  [k] mod_timer
   6.24%  [kernel]  [k] lock_timer_base.isra.38
   3.76%  [kernel]  [k] detach_if_pending
   3.71%  [kernel]  [k] del_timer
   2.50%  [kernel]  [k] internal_add_timer
   1.51%  [kernel]  [k] get_nohz_timer_target
   1.28%  [kernel]  [k] __internal_add_timer
   0.78%  [kernel]  [k] timerfn
   0.48%  [kernel]  [k] wake_up_nohz_cpu

After:
  48.10%  hog       [.] main
  15.25%  [kernel]  [k] _raw_spin_lock_irqsave
   9.76%  [kernel]  [k] _raw_spin_unlock_irqrestore
   6.50%  [kernel]  [k] mod_timer
   6.44%  [kernel]  [k] lock_timer_base.isra.38
   3.87%  [kernel]  [k] detach_if_pending
   3.80%  [kernel]  [k] del_timer
   2.67%  [kernel]  [k] internal_add_timer
   1.33%  [kernel]  [k] __internal_add_timer
   0.73%  [kernel]  [k] timerfn
   0.54%  [kernel]  [k] wake_up_nohz_cpu


Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Joonwoo Park <joonwoop@codeaurora.org>
Cc: Wenbo Wang <wenbo.wang@memblaze.com>
Link: http://lkml.kernel.org/r/20150526224512.127050787@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-06-19 15:18:28 +02:00

261 lines
7.7 KiB
C

#ifndef _LINUX_TIMER_H
#define _LINUX_TIMER_H
#include <linux/list.h>
#include <linux/ktime.h>
#include <linux/stddef.h>
#include <linux/debugobjects.h>
#include <linux/stringify.h>
struct tvec_base;
struct timer_list {
/*
* All fields that change during normal runtime grouped to the
* same cacheline
*/
struct hlist_node entry;
unsigned long expires;
void (*function)(unsigned long);
unsigned long data;
u32 flags;
int slack;
#ifdef CONFIG_TIMER_STATS
int start_pid;
void *start_site;
char start_comm[16];
#endif
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
};
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting the lockdep_map key
* (second argument) here is required, otherwise it could be initialised to
* the copy of the lockdep_map later! We use the pointer to and the string
* "<file>:<line>" as the key resp. the name of the lockdep_map.
*/
#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) \
.lockdep_map = STATIC_LOCKDEP_MAP_INIT(_kn, &_kn),
#else
#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)
#endif
/*
* A deferrable timer will work normally when the system is busy, but
* will not cause a CPU to come out of idle just to service it; instead,
* the timer will be serviced when the CPU eventually wakes up with a
* subsequent non-deferrable timer.
*
* An irqsafe timer is executed with IRQ disabled and it's safe to wait for
* the completion of the running instance from IRQ handlers, for example,
* by calling del_timer_sync().
*
* Note: The irq disabled callback execution is a special case for
* workqueue locking issues. It's not meant for executing random crap
* with interrupts disabled. Abuse is monitored!
*/
#define TIMER_CPUMASK 0x0007FFFF
#define TIMER_MIGRATING 0x00080000
#define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING)
#define TIMER_DEFERRABLE 0x00100000
#define TIMER_IRQSAFE 0x00200000
#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
.entry = { .next = TIMER_ENTRY_STATIC }, \
.function = (_function), \
.expires = (_expires), \
.data = (_data), \
.flags = (_flags), \
.slack = -1, \
__TIMER_LOCKDEP_MAP_INITIALIZER( \
__FILE__ ":" __stringify(__LINE__)) \
}
#define TIMER_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), 0)
#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE)
#define DEFINE_TIMER(_name, _function, _expires, _data) \
struct timer_list _name = \
TIMER_INITIALIZER(_function, _expires, _data)
void init_timer_key(struct timer_list *timer, unsigned int flags,
const char *name, struct lock_class_key *key);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
extern void init_timer_on_stack_key(struct timer_list *timer,
unsigned int flags, const char *name,
struct lock_class_key *key);
extern void destroy_timer_on_stack(struct timer_list *timer);
#else
static inline void destroy_timer_on_stack(struct timer_list *timer) { }
static inline void init_timer_on_stack_key(struct timer_list *timer,
unsigned int flags, const char *name,
struct lock_class_key *key)
{
init_timer_key(timer, flags, name, key);
}
#endif
#ifdef CONFIG_LOCKDEP
#define __init_timer(_timer, _flags) \
do { \
static struct lock_class_key __key; \
init_timer_key((_timer), (_flags), #_timer, &__key); \
} while (0)
#define __init_timer_on_stack(_timer, _flags) \
do { \
static struct lock_class_key __key; \
init_timer_on_stack_key((_timer), (_flags), #_timer, &__key); \
} while (0)
#else
#define __init_timer(_timer, _flags) \
init_timer_key((_timer), (_flags), NULL, NULL)
#define __init_timer_on_stack(_timer, _flags) \
init_timer_on_stack_key((_timer), (_flags), NULL, NULL)
#endif
#define init_timer(timer) \
__init_timer((timer), 0)
#define init_timer_deferrable(timer) \
__init_timer((timer), TIMER_DEFERRABLE)
#define init_timer_on_stack(timer) \
__init_timer_on_stack((timer), 0)
#define __setup_timer(_timer, _fn, _data, _flags) \
do { \
__init_timer((_timer), (_flags)); \
(_timer)->function = (_fn); \
(_timer)->data = (_data); \
} while (0)
#define __setup_timer_on_stack(_timer, _fn, _data, _flags) \
do { \
__init_timer_on_stack((_timer), (_flags)); \
(_timer)->function = (_fn); \
(_timer)->data = (_data); \
} while (0)
#define setup_timer(timer, fn, data) \
__setup_timer((timer), (fn), (data), 0)
#define setup_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), 0)
#define setup_deferrable_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE)
/**
* timer_pending - is a timer pending?
* @timer: the timer in question
*
* timer_pending will tell whether a given timer is currently pending,
* or not. Callers must ensure serialization wrt. other operations done
* to this timer, eg. interrupt contexts, or other CPUs on SMP.
*
* return value: 1 if the timer is pending, 0 if not.
*/
static inline int timer_pending(const struct timer_list * timer)
{
return timer->entry.pprev != NULL;
}
extern void add_timer_on(struct timer_list *timer, int cpu);
extern int del_timer(struct timer_list * timer);
extern int mod_timer(struct timer_list *timer, unsigned long expires);
extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires);
extern void set_timer_slack(struct timer_list *time, int slack_hz);
#define TIMER_NOT_PINNED 0
#define TIMER_PINNED 1
/*
* The jiffies value which is added to now, when there is no timer
* in the timer wheel:
*/
#define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1)
/*
* Timer-statistics info:
*/
#ifdef CONFIG_TIMER_STATS
extern int timer_stats_active;
extern void init_timer_stats(void);
extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
void *timerf, char *comm, u32 flags);
extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
void *addr);
static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
{
if (likely(!timer_stats_active))
return;
__timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
}
static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
{
timer->start_site = NULL;
}
#else
static inline void init_timer_stats(void)
{
}
static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
{
}
static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
{
}
#endif
extern void add_timer(struct timer_list *timer);
extern int try_to_del_timer_sync(struct timer_list *timer);
#ifdef CONFIG_SMP
extern int del_timer_sync(struct timer_list *timer);
#else
# define del_timer_sync(t) del_timer(t)
#endif
#define del_singleshot_timer_sync(t) del_timer_sync(t)
extern void init_timers(void);
extern void run_local_timers(void);
struct hrtimer;
extern enum hrtimer_restart it_real_fn(struct hrtimer *);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
#include <linux/sysctl.h>
extern unsigned int sysctl_timer_migration;
int timer_migration_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
#endif
unsigned long __round_jiffies(unsigned long j, int cpu);
unsigned long __round_jiffies_relative(unsigned long j, int cpu);
unsigned long round_jiffies(unsigned long j);
unsigned long round_jiffies_relative(unsigned long j);
unsigned long __round_jiffies_up(unsigned long j, int cpu);
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu);
unsigned long round_jiffies_up(unsigned long j);
unsigned long round_jiffies_up_relative(unsigned long j);
#endif