/**
* struct tick_sched - sched tick emulation and no idle tick control/stats
* @sched_timer: hrtimer to schedule the periodic tick in high
* resolution mode
* @idle_tick: Store the last idle tick expiry time when the tick
* timer is modified for idle sleeps. This is necessary
* to resume the tick timer operation in the timeline
* when the CPU returns from idle
* @tick_stopped: Indicator that the idle tick has been stopped
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
* @idle_calls: Total number of idle calls
* @idle_sleeps: Number of idle calls, where the sched tick was stopped
* @idle_entrytime: Time when the idle call was entered
* @idle_waketime: Time when the idle was interrupted
* @idle_exittime: Time when the idle state was left
* @idle_sleeptime: Sum of the time slept in idle with sched tick stopped
* @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding
* @sleep_length: Duration of the current idle sleep
* @do_timer_lst: CPU was the last one doing do_timer before going idle
*/
struct tick_sched {
struct hrtimer sched_timer; //实现时钟的定时器
unsigned long check_clocks;
enum tick_nohz_mode nohz_mode; //当前运作模式
ktime_t idle_tick; //在禁用周期时钟之前,上一个时钟信号的到期时间。
int inidle;
int tick_stopped; //如果周期时钟已经停用,则为1.
unsigned long idle_jiffies; //周期时钟听用的jiffies值
unsigned long idle_calls; //内核试图停用时钟周期的次数
unsigned long idle_sleeps; //成功停用时钟周期的次数。(如果下一个时钟即将在一个jiffy之后到期,内核是不会停用时钟的)。
int idle_active; //
ktime_t idle_entrytime;
ktime_t idle_waketime;
ktime_t idle_exittime;
ktime_t idle_sleeptime;//周期时钟上一次禁用的准确时间
ktime_t iowait_sleeptime;
ktime_t sleep_length; //周期时钟将禁用的时间长度。
unsigned long last_jiffies;
unsigned long next_jiffies; //下一个定时器到期时间的jiffy值。
ktime_t idle_expires; //下一个将到期的经典定时器的的到期时间。
int do_timer_last;
};
tick_cpu_sched是一个全局各CPU变量,提供一个struct tick_sched实例。这是必须的,因为对时钟的禁用是按照CPU指定的,而不是对整个系统指定的。
1、低精度系统下的动态时钟
(1)切换到动态时钟
/**
* tick_nohz_switch_to_nohz - switch to nohz mode
*/
static void tick_nohz_switch_to_nohz(void)
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t next;
if (!tick_nohz_enabled)
return;
local_irq_disable();
if (tick_switch_to_oneshot(tick_nohz_handler)) {
local_irq_enable();
return;
}
ts->nohz_mode = NOHZ_MODE_LOWRES;
/*
* Recycle the hrtimer in ts, so we can share the
* hrtimer_forward with the highres code.
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
/* Get the next period */
next = tick_init_jiffy_update();
for (;;) {
hrtimer_set_expires(&ts->sched_timer, next);
if (!tick_program_event(next, 0))
break;
next = ktime_add(next, tick_period);
}
local_irq_enable();
printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id());
}
(2)动态时钟处理程序
/*
* The nohz low res interrupt handler
*/
static void tick_nohz_handler(struct clock_event_device *dev)
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
struct pt_regs *regs = get_irq_regs();
int cpu = smp_processor_id();
ktime_t now = ktime_get();
dev->next_event.tv64 = KTIME_MAX;
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the cpu in charge went
* into a long sleep. If two cpus happen to assign themself to
* this duty, then the jiffies update is still serialized by
* xtime_lock.
*/
/*
*全局时钟设备的角色由一个特定的CPU承担,但是如果该CPU也要休眠你,则不能继续承担全局时钟的角色。
*那么接下来如果哪个CPU的时钟定时器处理程序被调用,该CPU必须承担责任。
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
tick_do_timer_cpu = cpu;
/* Check, if the jiffies need an update */
/*
*如果CPU负责提供全局时钟,那么更新jiffies
*/
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
* time. This happens on complete idle SMP systems while
* waiting on the login prompt. We also increment the "start
* of idle" jiffy stamp so the idle accounting adjustment we
* do when we go busy again does not account too much ticks.
*/
if (ts->tick_stopped) {
touch_softlockup_watchdog();
ts->idle_jiffies++;
}
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
while (tick_nohz_reprogram(ts, now)) {
now = ktime_get();
tick_do_update_jiffies64(now);
}
}
主要完成两个工作:
1>执行时钟机制所需的所有操作
2>对时钟设备重新编程,使得下一个时钟信号在适当的时候到期。
我们重点来看作为全局时钟的CPU更新jiffies的操作tick_do_update_jiffies64:
/*
* Must be called with interrupts disabled !
*/
static void tick_do_update_jiffies64(ktime_t now)
{
unsigned long ticks = 0;
ktime_t delta;
/*
* Do a quick check without holding xtime_lock:
*/
delta = ktime_sub(now, last_jiffies_update); //距离上次更新jiffy的时间
if (delta.tv64 < tick_period.tv64) //如果delta.tv64小于一个tick周期,则不需要更新
return;
/* Reevalute with xtime_lock held */
write_seqlock(&xtime_lock);
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 >= tick_period.tv64) {
delta = ktime_sub(delta, tick_period);
last_jiffies_update = ktime_add(last_jiffies_update,
tick_period);
/* Slow path for long timeouts */
if (unlikely(delta.tv64 >= tick_period.tv64)) { //如果距离上次更新jiffies已经过去了多余一个时钟周期
s64 incr = ktime_to_ns(tick_period); //将tick_period换算成ns
ticks = ktime_divns(delta, incr); //将delta换算成ticks
last_jiffies_update = ktime_add_ns(last_jiffies_update, //更新last_jiffies_update
incr * ticks);
}
do_timer(++ticks); //更新全局jiffies值
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
}
write_sequnlock(&xtime_lock);
}
我们看到关于jiffies是存储在内存中的,因此只需要一个时钟来更新存储在内存中的jiffies就可,而其它的CPU如有需要可以去内存读取。
(2)高精度系统下的动态时钟
(4)停止周期时钟
在调度idle进程时,表示CPU确实没什么可做,因此停用周期时钟:
/*
* The idle thread. There's no useful work to be
* done, so just try to conserve power and have a
* low exit latency (ie sit in a loop waiting for
* somebody to say that they'd like to reschedule)
*/
void cpu_idle(void)
{
int cpu = smp_processor_id();
/*
* If we're the non-boot CPU, nothing set the stack canary up
* for us. CPU0 already has it initialized but no harm in
* doing it again. This is a good place for updating it, as
* we wont ever return from this function (so the invalid
* canaries already on the stack wont ever trigger).
*/
boot_init_stack_canary();
current_thread_info()->status |= TS_POLLING;
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick(1); //关闭周期时钟,并进入无时钟状态
while (!need_resched()) { //进入一个死循环,直到可以有其它的任务可供调度。
check_pgt_cache();
rmb();
if (cpu_is_offline(cpu))
play_dead();
local_irq_disable();
/* Don't trace irqs off for idle */
stop_critical_timings();
pm_idle();
start_critical_timings();
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
来看关键的操作tick_nohz_stop_sched_tick(1),这个函数涉及到许多边边角角的东西,因此之需要大致的了解其功能就OK了:
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
* Called either from the idle loop or from irq_exit() when an idle period was
* just interrupted by an interrupt which did not cause a reschedule.
*/
void tick_nohz_stop_sched_tick(int inidle)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
/*
* Call to tick_nohz_start_idle stops the last_update_time from being
* updated. Thus, it must not be called in the event we are called from
* irq_exit() with the prior state different than idle.
*/
if (!inidle && !ts->inidle)
goto end;
/*
* Set ts->inidle unconditionally. Even if the system did not
* switch to NOHZ mode the cpu frequency governers rely on the
* update of the idle time accounting in tick_nohz_start_idle().
*/
ts->inidle = 1;
now = tick_nohz_start_idle(cpu, ts);
/*
* If this cpu is offline and it is the one which updates
* jiffies, then give up the assignment and let it be taken by
* the cpu which runs the tick timer next. If we don't drop
* this here the jiffies might be stale and do_timer() never
* invoked.
*/
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
if (need_resched())
goto end;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
(unsigned int) local_softirq_pending());
ratelimit++;
}
goto end;
}
ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
} else {
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
}
/*
* Do not stop the tick, if we are only one off
* or if the cpu is required for rcu
*/
if (!ts->tick_stopped && delta_jiffies == 1)
goto out;
/* Schedule the tick, if we are at least one jiffie off */
if ((long)delta_jiffies >= 1) {
/*
* If this cpu is the one which updates jiffies, then
* give up the assignment and let it be taken by the
* cpu which runs the tick timer next, which might be
* this cpu as well. If we don't drop this here the
* jiffies might be stale and do_timer() never
* invoked. Keep track of the fact that it was the one
* which had the do_timer() duty last. If this cpu is
* the one which had the do_timer() duty last, we
* limit the sleep time to the timekeeping
* max_deferement value which we retrieved
* above. Otherwise we can sleep as long as we want.
*/
if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
ts->do_timer_last = 1;
} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
time_delta = KTIME_MAX;
ts->do_timer_last = 0;
} else if (!ts->do_timer_last) {
time_delta = KTIME_MAX;
}
/*
* calculate the expiry time for the next timer wheel
* timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
* that there is no timer pending or at least extremely
* far into the future (12 days for HZ=1000). In this
* case we set the expiry to the end of time.
*/
if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
/*
* Calculate the time delta for the next timer event.
* If the time delta exceeds the maximum time delta
* permitted by the current clocksource then adjust
* the time delta accordingly to ensure the
* clocksource does not wrap.
*/
time_delta = min_t(u64, time_delta,
tick_period.tv64 * delta_jiffies);
}
if (time_delta < KTIME_MAX)
expires = ktime_add_ns(last_update, time_delta);
else
expires.tv64 = KTIME_MAX;
if (delta_jiffies > 1)
cpumask_set_cpu(cpu, nohz_cpu_mask);
/* Skip reprogram of event if its not changed */
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
/*
* nohz_stop_sched_tick can be called several times before
* the nohz_restart_sched_tick is called. This happens when
* interrupts arrive which do not cause a reschedule. In the
* first call we save the current tick time, so we can restart
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
select_nohz_load_balancer(1);
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
}
ts->idle_sleeps++;
/* Mark expires */
ts->idle_expires = expires;
/*
* If the expiration time == KTIME_MAX, then
* in this case we simply stop the tick timer.
*/
if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
goto out;
} else if (!tick_program_event(expires, 0))
goto out;
/*
* We are past the event already. So we crossed a
* jiffie boundary. Update jiffies and raise the
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
cpumask_clear_cpu(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
end:
local_irq_restore(flags);
}
这个函数主要完成三个任务:
(1)检查下一个定时器轮时间是否在一个时钟周期之后
(2)如果是这样,则重新编程时钟设备,忽略下一个时钟周期信号,直至有必要时才恢复。这将自动忽略所有不需要的时钟
(3)在tick_sched中更新统计信息。
(5)重启周期时钟
/**
* tick_nohz_restart_sched_tick - restart the idle tick from the idle task
*
* Restart the idle tick when the CPU is woken up from idle
*/
void tick_nohz_restart_sched_tick(void)
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
unsigned long ticks;
#endif
ktime_t now;
local_irq_disable();
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
if (ts->idle_active)
tick_nohz_stop_idle(cpu, now);
if (!ts->inidle || !ts->tick_stopped) {
ts->inidle = 0;
local_irq_enable();
return;
}
ts->inidle = 0;
rcu_exit_nohz();
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
cpumask_clear_cpu(cpu, nohz_cpu_mask);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
* accounting. Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
if (ticks && ticks < LONG_MAX)
account_idle_ticks(ticks);
#endif
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
*/
ts->tick_stopped = 0;
ts->idle_exittime = now;
tick_nohz_restart(ts, now);
local_irq_enable();
}
参考:《深入Linux内核架构》