OpenCloudOS-Kernel/include/linux/hrtimer.h

468 lines
14 KiB
C
Raw Normal View History

/*
* include/linux/hrtimer.h
*
* hrtimers - High-resolution kernel timers
*
* Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005, Red Hat, Inc., Ingo Molnar
*
* data type definitions, declarations, prototypes
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* For licencing details see kernel-base/COPYING
*/
#ifndef _LINUX_HRTIMER_H
#define _LINUX_HRTIMER_H
#include <linux/rbtree.h>
#include <linux/ktime.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/percpu.h>
#include <linux/timer.h>
#include <linux/timerqueue.h>
struct hrtimer_clock_base;
struct hrtimer_cpu_base;
/*
* Mode arguments of xxx_hrtimer functions:
*/
enum hrtimer_mode {
HRTIMER_MODE_ABS = 0x0, /* Time value is absolute */
HRTIMER_MODE_REL = 0x1, /* Time value is relative to now */
HRTIMER_MODE_PINNED = 0x02, /* Timer is bound to CPU */
HRTIMER_MODE_ABS_PINNED = 0x02,
HRTIMER_MODE_REL_PINNED = 0x03,
};
/*
* Return values for the callback function
*/
enum hrtimer_restart {
HRTIMER_NORESTART, /* Timer is not restarted */
HRTIMER_RESTART, /* Timer must be restarted */
};
/*
* Values to track state of the timer
*
* Possible states:
*
* 0x00 inactive
* 0x01 enqueued into rbtree
*
* The callback state is not part of the timer->state because clearing it would
* mean touching the timer after the callback, this makes it impossible to free
* the timer from the callback function.
*
* Therefore we track the callback state in:
*
* timer->base->cpu_base->running == timer
*
* On SMP it is possible to have a "callback function running and enqueued"
* status. It happens for example when a posix timer expired and the callback
* queued a signal. Between dropping the lock which protects the posix timer
* and reacquiring the base lock of the hrtimer, another CPU can deliver the
* signal and rearm the timer.
*
* All state transitions are protected by cpu_base->lock.
*/
#define HRTIMER_STATE_INACTIVE 0x00
#define HRTIMER_STATE_ENQUEUED 0x01
/**
* struct hrtimer - the basic hrtimer structure
* @node: timerqueue node, which also manages node.expires,
* the absolute expiry time in the hrtimers internal
* representation. The time is related to the clock on
* which the timer is based. Is setup by adding
* slack to the _softexpires value. For non range timers
* identical to _softexpires.
* @_softexpires: the absolute earliest expiry time of the hrtimer.
* The time which was given as expiry time when the timer
* was armed.
* @function: timer expiry callback function
* @base: pointer to the timer base (per cpu and per clock)
* @state: state information (See bit values above)
* @start_pid: timer statistics field to store the pid of the task which
* started the timer
* @start_site: timer statistics field to store the site where the timer
* was started
* @start_comm: timer statistics field to store the name of the process which
* started the timer
*
* The hrtimer structure must be initialized by hrtimer_init()
*/
struct hrtimer {
struct timerqueue_node node;
ktime_t _softexpires;
enum hrtimer_restart (*function)(struct hrtimer *);
struct hrtimer_clock_base *base;
unsigned long state;
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 17:28:13 +08:00
#ifdef CONFIG_TIMER_STATS
int start_pid;
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 17:28:13 +08:00
void *start_site;
char start_comm[16];
#endif
};
/**
* struct hrtimer_sleeper - simple sleeper structure
* @timer: embedded timer structure
* @task: task to wake up
*
* task is set to NULL, when the timer expires.
*/
struct hrtimer_sleeper {
struct hrtimer timer;
struct task_struct *task;
};
#ifdef CONFIG_64BIT
# define HRTIMER_CLOCK_BASE_ALIGN 64
#else
# define HRTIMER_CLOCK_BASE_ALIGN 32
#endif
/**
* struct hrtimer_clock_base - the timer base for a specific clock
* @cpu_base: per cpu clock base
* @index: clock type index for per_cpu support when moving a
* timer to a base on another cpu.
* @clockid: clock id for per_cpu support
* @active: red black tree root node for the active timers
* @get_time: function to retrieve the current time of the clock
* @offset: offset of this clock to the monotonic base
*/
struct hrtimer_clock_base {
struct hrtimer_cpu_base *cpu_base;
int index;
clockid_t clockid;
struct timerqueue_head active;
ktime_t (*get_time)(void);
ktime_t offset;
} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
HRTIMER_BASE_REALTIME,
HRTIMER_BASE_BOOTTIME,
HRTIMER_BASE_TAI,
HRTIMER_MAX_CLOCK_BASES,
};
/*
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
* @seq: seqcount around __run_hrtimer
* @running: pointer to the currently running hrtimer
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
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>
2015-05-27 06:50:33 +08:00
* @migration_enabled: The migration of hrtimers to other cpus is enabled
timer: Minimize nohz off overhead If nohz is disabled on the kernel command line the [hr]timer code still calls wake_up_nohz_cpu() and tick_nohz_full_cpu(), a pretty pointless exercise. Cache nohz_active in [hr]timer per cpu bases and avoid the overhead. Before: 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 After: 48.73% hog [.] main 15.36% [kernel] [k] _raw_spin_lock_irqsave 9.77% [kernel] [k] _raw_spin_unlock_irqrestore 6.61% [kernel] [k] lock_timer_base.isra.38 6.42% [kernel] [k] mod_timer 3.90% [kernel] [k] detach_if_pending 3.76% [kernel] [k] del_timer 2.41% [kernel] [k] internal_add_timer 1.39% [kernel] [k] __internal_add_timer 0.76% [kernel] [k] timerfn We probably should have a cached value for nohz full in the per cpu bases as well to avoid the cpumask check. The base cache line is hot already, the cpumask not necessarily. 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: Eric Dumazet <edumazet@google.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/20150526224512.207378134@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 06:50:35 +08:00
* @nohz_active: The nohz functionality is enabled
* @expires_next: absolute time of the next event which was scheduled
* via clock_set_next_event()
* @next_timer: Pointer to the first expiring timer
hrtimer: Prevent stale expiry time in hrtimer_interrupt() hrtimer_interrupt() has the following subtle issue: hrtimer_interrupt() lock(cpu_base); expires_next = KTIME_MAX; expire_timers(CLOCK_MONOTONIC); expires = get_next_timer(CLOCK_MONOTONIC); if (expires < expires_next) expires_next = expires; expire_timers(CLOCK_REALTIME); unlock(cpu_base); wakeup() hrtimer_start(CLOCK_MONOTONIC, newtimer); lock(cpu_base(); expires = get_next_timer(CLOCK_REALTIME); if (expires < expires_next) expires_next = expires; So because we already evaluated the next expiring timer of CLOCK_MONOTONIC we ignore that the expiry time of newtimer might be earlier than the overall next expiry time in hrtimer_interrupt(). To solve this, remove the caching of the next expiry value from hrtimer_interrupt() and reevaluate all active clock bases for the next expiry value. To avoid another code duplication, create a shared evaluation function and use it for hrtimer_get_next_event(), hrtimer_force_reprogram() and hrtimer_interrupt(). There is another subtlety in this mechanism: While hrtimer_interrupt() is running, we want to avoid to touch the hardware device because we will reprogram it anyway at the end of hrtimer_interrupt(). This works nicely for hrtimers which get rearmed via the HRTIMER_RESTART mechanism, because we drop out when the callback on that CPU is running. But that fails, if a new timer gets enqueued like in the example above. This has another implication: While hrtimer_interrupt() is running we refuse remote enqueueing of timers - see hrtimer_interrupt() and hrtimer_check_target(). hrtimer_interrupt() tries to prevent this by setting cpu_base->expires to KTIME_MAX, but that fails if a new timer gets queued. Prevent both the hardware access and the remote enqueue explicitely. We can loosen the restriction on the remote enqueue now due to reevaluation of the next expiry value, but that needs a seperate patch. Folded in a fix from Vignesh Radhakrishnan. Reported-and-tested-by: Stanislav Fomichev <stfomichev@yandex-team.ru> Based-on-patch-by: Stanislav Fomichev <stfomichev@yandex-team.ru> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: vigneshr@codeaurora.org Cc: john.stultz@linaro.org Cc: viresh.kumar@linaro.org Cc: fweisbec@gmail.com Cc: cl@linux.com Cc: stuart.w.hayes@gmail.com Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1501202049190.5526@nanos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-01-21 04:24:10 +08:00
* @in_hrtirq: hrtimer_interrupt() is currently executing
* @hres_active: State of high resolution mode
* @hang_detected: The last hrtimer interrupt detected a hang
* @nr_events: Total number of hrtimer interrupt events
* @nr_retries: Total number of hrtimer interrupt retries
* @nr_hangs: Total number of hrtimer interrupt hangs
* @max_hang_time: Maximum time spent in hrtimer_interrupt
* @clock_base: array of clock bases for this cpu
*
* Note: next_timer is just an optimization for __remove_hrtimer().
* Do not dereference the pointer because it is not reliable on
* cross cpu removals.
*/
struct hrtimer_cpu_base {
raw_spinlock_t lock;
seqcount_t seq;
struct hrtimer *running;
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
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>
2015-05-27 06:50:33 +08:00
bool migration_enabled;
timer: Minimize nohz off overhead If nohz is disabled on the kernel command line the [hr]timer code still calls wake_up_nohz_cpu() and tick_nohz_full_cpu(), a pretty pointless exercise. Cache nohz_active in [hr]timer per cpu bases and avoid the overhead. Before: 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 After: 48.73% hog [.] main 15.36% [kernel] [k] _raw_spin_lock_irqsave 9.77% [kernel] [k] _raw_spin_unlock_irqrestore 6.61% [kernel] [k] lock_timer_base.isra.38 6.42% [kernel] [k] mod_timer 3.90% [kernel] [k] detach_if_pending 3.76% [kernel] [k] del_timer 2.41% [kernel] [k] internal_add_timer 1.39% [kernel] [k] __internal_add_timer 0.76% [kernel] [k] timerfn We probably should have a cached value for nohz full in the per cpu bases as well to avoid the cpumask check. The base cache line is hot already, the cpumask not necessarily. 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: Eric Dumazet <edumazet@google.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/20150526224512.207378134@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 06:50:35 +08:00
bool nohz_active;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int in_hrtirq : 1,
hres_active : 1,
hang_detected : 1;
ktime_t expires_next;
struct hrtimer *next_timer;
unsigned int nr_events;
unsigned int nr_retries;
unsigned int nr_hangs;
unsigned int max_hang_time;
#endif
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
} ____cacheline_aligned;
static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
{
BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
timer->node.expires = time;
timer->_softexpires = time;
}
static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta)
{
timer->_softexpires = time;
timer->node.expires = ktime_add_safe(time, delta);
}
static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
{
timer->_softexpires = time;
timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta));
}
static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
{
timer->node.expires.tv64 = tv64;
timer->_softexpires.tv64 = tv64;
}
static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
{
timer->node.expires = ktime_add_safe(timer->node.expires, time);
timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
}
static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns)
{
timer->node.expires = ktime_add_ns(timer->node.expires, ns);
timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
}
static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
{
return timer->node.expires;
}
static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
{
return timer->_softexpires;
}
static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
{
return timer->node.expires.tv64;
}
static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
{
return timer->_softexpires.tv64;
}
static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
{
return ktime_to_ns(timer->node.expires);
}
static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
{
return ktime_sub(timer->node.expires, timer->base->get_time());
}
static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
{
return timer->base->get_time();
}
#ifdef CONFIG_HIGH_RES_TIMERS
struct clock_event_device;
extern void hrtimer_interrupt(struct clock_event_device *dev);
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
return timer->base->cpu_base->hres_active;
}
extern void hrtimer_peek_ahead_timers(void);
/*
* The resolution of the clocks. The resolution value is returned in
* the clock_getres() system call to give application programmers an
* idea of the (in)accuracy of timers. Timer values are rounded up to
* this resolution values.
*/
# define HIGH_RES_NSEC 1
# define KTIME_HIGH_RES (ktime_t) { .tv64 = HIGH_RES_NSEC }
# define MONOTONIC_RES_NSEC HIGH_RES_NSEC
# define KTIME_MONOTONIC_RES KTIME_HIGH_RES
extern void clock_was_set_delayed(void);
extern unsigned int hrtimer_resolution;
#else
# define MONOTONIC_RES_NSEC LOW_RES_NSEC
# define KTIME_MONOTONIC_RES KTIME_LOW_RES
#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
static inline void hrtimer_peek_ahead_timers(void) { }
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
return 0;
}
static inline void clock_was_set_delayed(void) { }
#endif
extern void clock_was_set(void);
#ifdef CONFIG_TIMERFD
extern void timerfd_clock_was_set(void);
#else
static inline void timerfd_clock_was_set(void) { }
#endif
extern void hrtimers_resume(void);
DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
/* Exported timer functions: */
/* Initialize timers: */
extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
enum hrtimer_mode mode);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
enum hrtimer_mode mode);
extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
#else
static inline void hrtimer_init_on_stack(struct hrtimer *timer,
clockid_t which_clock,
enum hrtimer_mode mode)
{
hrtimer_init(timer, which_clock, mode);
}
static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
#endif
/* Basic timer operations: */
extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
unsigned long range_ns, const enum hrtimer_mode mode);
/**
* hrtimer_start - (re)start an hrtimer on the current CPU
* @timer: the timer to be added
* @tim: expiry time
* @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
* relative (HRTIMER_MODE_REL)
*/
static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode)
{
hrtimer_start_range_ns(timer, tim, 0, mode);
}
extern int hrtimer_cancel(struct hrtimer *timer);
extern int hrtimer_try_to_cancel(struct hrtimer *timer);
static inline void hrtimer_start_expires(struct hrtimer *timer,
enum hrtimer_mode mode)
{
unsigned long delta;
ktime_t soft, hard;
soft = hrtimer_get_softexpires(timer);
hard = hrtimer_get_expires(timer);
delta = ktime_to_ns(ktime_sub(hard, soft));
hrtimer_start_range_ns(timer, soft, delta, mode);
}
static inline void hrtimer_restart(struct hrtimer *timer)
{
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
/* Query timers: */
extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
extern u64 hrtimer_get_next_event(void);
extern bool hrtimer_active(const struct hrtimer *timer);
/*
* Helper function to check, whether the timer is on one of the queues
*/
static inline int hrtimer_is_queued(struct hrtimer *timer)
{
return timer->state & HRTIMER_STATE_ENQUEUED;
}
/*
* Helper function to check, whether the timer is running the callback
* function
*/
static inline int hrtimer_callback_running(struct hrtimer *timer)
{
return timer->base->cpu_base->running == timer;
}
/* Forward a hrtimer so it expires after now: */
timerfd: new timerfd API This is the new timerfd API as it is implemented by the following patch: int timerfd_create(int clockid, int flags); int timerfd_settime(int ufd, int flags, const struct itimerspec *utmr, struct itimerspec *otmr); int timerfd_gettime(int ufd, struct itimerspec *otmr); The timerfd_create() API creates an un-programmed timerfd fd. The "clockid" parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME. The timerfd_settime() API give new settings by the timerfd fd, by optionally retrieving the previous expiration time (in case the "otmr" parameter is not NULL). The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit is set in the "flags" parameter. Otherwise it's a relative time. The timerfd_gettime() API returns the next expiration time of the timer, or {0, 0} if the timerfd has not been set yet. Like the previous timerfd API implementation, read(2) and poll(2) are supported (with the same interface). Here's a simple test program I used to exercise the new timerfd APIs: http://www.xmailserver.org/timerfd-test2.c [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: fix ia64 build] [akpm@linux-foundation.org: fix m68k build] [akpm@linux-foundation.org: fix mips build] [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds] [heiko.carstens@de.ibm.com: fix s390] [akpm@linux-foundation.org: fix powerpc build] [akpm@linux-foundation.org: fix sparc64 more] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:26 +08:00
extern u64
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
/**
* hrtimer_forward_now - forward the timer expiry so it expires after now
* @timer: hrtimer to forward
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire after the current time
* of the hrtimer clock base. Returns the number of overruns.
*
* Can be safely called from the callback function of @timer. If
* called from other contexts @timer must neither be enqueued nor
* running the callback and the caller needs to take care of
* serialization.
*
* Note: This only updates the timer expiry value and does not requeue
* the timer.
*/
timerfd: new timerfd API This is the new timerfd API as it is implemented by the following patch: int timerfd_create(int clockid, int flags); int timerfd_settime(int ufd, int flags, const struct itimerspec *utmr, struct itimerspec *otmr); int timerfd_gettime(int ufd, struct itimerspec *otmr); The timerfd_create() API creates an un-programmed timerfd fd. The "clockid" parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME. The timerfd_settime() API give new settings by the timerfd fd, by optionally retrieving the previous expiration time (in case the "otmr" parameter is not NULL). The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit is set in the "flags" parameter. Otherwise it's a relative time. The timerfd_gettime() API returns the next expiration time of the timer, or {0, 0} if the timerfd has not been set yet. Like the previous timerfd API implementation, read(2) and poll(2) are supported (with the same interface). Here's a simple test program I used to exercise the new timerfd APIs: http://www.xmailserver.org/timerfd-test2.c [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: fix ia64 build] [akpm@linux-foundation.org: fix m68k build] [akpm@linux-foundation.org: fix mips build] [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds] [heiko.carstens@de.ibm.com: fix s390] [akpm@linux-foundation.org: fix powerpc build] [akpm@linux-foundation.org: fix sparc64 more] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:26 +08:00
static inline u64 hrtimer_forward_now(struct hrtimer *timer,
ktime_t interval)
{
return hrtimer_forward(timer, timer->base->get_time(), interval);
}
/* Precise sleep: */
extern long hrtimer_nanosleep(struct timespec *rqtp,
hrtimer: fix *rmtp handling in hrtimer_nanosleep() Spotted by Pavel Emelyanov and Alexey Dobriyan. hrtimer_nanosleep() sets restart_block->arg1 = rmtp, but this rmtp points to the local variable which lives in the caller's stack frame. This means that if sys_restart_syscall() actually happens and it is interrupted as well, we don't update the user-space variable, but write into the already dead stack frame. Introduced by commit 04c227140fed77587432667a574b14736a06dd7f hrtimer: Rework hrtimer_nanosleep to make sys_compat_nanosleep easier Change the callers to pass "__user *rmtp" to hrtimer_nanosleep(), and change hrtimer_nanosleep() to use copy_to_user() to actually update *rmtp. Small problem remains. man 2 nanosleep states that *rtmp should be written if nanosleep() was interrupted (it says nothing whether it is OK to update *rmtp if nanosleep returns 0), but (with or without this patch) we can dirty *rem even if nanosleep() returns 0. NOTE: this patch doesn't change compat_sys_nanosleep(), because it has other bugs. Fixed by the next patch. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Alexey Dobriyan <adobriyan@sw.ru> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: Pavel Emelyanov <xemul@sw.ru> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Toyo Abe <toyoa@mvista.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> include/linux/hrtimer.h | 2 - kernel/hrtimer.c | 51 +++++++++++++++++++++++++----------------------- kernel/posix-timers.c | 14 +------------ 3 files changed, 30 insertions(+), 37 deletions(-)
2008-02-01 22:29:05 +08:00
struct timespec __user *rmtp,
const enum hrtimer_mode mode,
const clockid_t clockid);
extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
struct task_struct *tsk);
extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
const enum hrtimer_mode mode);
extern int schedule_hrtimeout_range_clock(ktime_t *expires,
unsigned long delta, const enum hrtimer_mode mode, int clock);
extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
/* Soft interrupt function to run the hrtimer queues: */
extern void hrtimer_run_queues(void);
/* Bootup initialization: */
extern void __init hrtimers_init(void);
/* Show pending timers: */
extern void sysrq_timer_list_show(void);
#endif