示例#1
0
__BEGIN_PROGRAM

/*
 *  kernel/sched/core.c
 *
 *  Kernel scheduler and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *
 *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
 *		make semaphores SMP safe
 *  1998-11-19	Implemented schedule_timeout() and related stuff
 *		by Andrea Arcangeli
 *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
 *		hybrid priority-list and round-robin design with
 *		an array-switch method of distributing timeslices
 *		and per-CPU runqueues.  Cleanups and useful suggestions
 *		by Davide Libenzi, preemptible kernel bits by Robert Love.
 *  2003-09-03	Interactivity tuning by Con Kolivas.
 *  2004-04-02	Scheduler domains code by Nick Piggin
 *  2007-04-15  Work begun on replacing all interactivity tuning with a
 *              fair scheduling design by Con Kolivas.
 *  2007-05-05  Load balancing (smp-nice) and other improvements
 *              by Peter Williams
 *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
 *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
 *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
 *              Thomas Gleixner, Mike Kravetz
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/debug_locks.h>
#include <linux/perf_event.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/freezer.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/pid_namespace.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
#include <linux/init_task.h>
#include <linux/binfmts.h>

#include <asm/switch_to.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
#include <asm/mutex.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif

#include "sched.h"
#include "../workqueue_sched.h"
#include "../smpboot.h"

#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>

void start_bandwidth_timer(struct hrtimer period_timer , int period)
{
	unsigned long delta;
	int soft, hard, now;

	for (;;) {
		if (hrtimer_active(period_timer))
			break;

		now = hrtimer_cb_get_time(period_timer);
		hrtimer_forward(period_timer, now, period);

		soft = hrtimer_get_softexpires(period_timer);
		hard = hrtimer_get_expires(period_timer);
		delta = into_ns(ktime_sub(hard, soft));
		hrtimer_start_range_ns(period_timer, soft, delta,
					 HRTIMER_MODE_ABS_PINNED, 0);
	}
}
示例#2
0
/**
 * 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 less)
	 * 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);
}
static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
{
	hrtimer_forward(&ts->sched_timer, now, tick_period);
	return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
}
/*
 * High resolution timer interrupt
 * Called with interrupts disabled
 */
void hrtimer_interrupt(struct clock_event_device *dev)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	ktime_t expires_next, now, entry_time, delta;
	int i, retries = 0;

	BUG_ON(!cpu_base->hres_active);
	cpu_base->nr_events++;
	dev->next_event.tv64 = KTIME_MAX;

	raw_spin_lock(&cpu_base->lock);
	entry_time = now = hrtimer_update_base(cpu_base);
retry:
	expires_next.tv64 = KTIME_MAX;
	/*
	 * We set expires_next to KTIME_MAX here with cpu_base->lock
	 * held to prevent that a timer is enqueued in our queue via
	 * the migration code. This does not affect enqueueing of
	 * timers which run their callback and need to be requeued on
	 * this CPU.
	 */
	cpu_base->expires_next.tv64 = KTIME_MAX;

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		struct hrtimer_clock_base *base;
		struct timerqueue_node *node;
		ktime_t basenow;

		if (!(cpu_base->active_bases & (1 << i)))
			continue;

		base = cpu_base->clock_base + i;
		basenow = ktime_add(now, base->offset);

		while ((node = timerqueue_getnext(&base->active))) {
			struct hrtimer *timer;

			timer = container_of(node, struct hrtimer, node);

			/*
			 * The immediate goal for using the softexpires is
			 * minimizing wakeups, not running timers at the
			 * earliest interrupt after their soft expiration.
			 * This allows us to avoid using a Priority Search
			 * Tree, which can answer a stabbing querry for
			 * overlapping intervals and instead use the simple
			 * BST we already have.
			 * We don't add extra wakeups by delaying timers that
			 * are right-of a not yet expired timer, because that
			 * timer will have to trigger a wakeup anyway.
			 */

			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
				ktime_t expires;

				expires = ktime_sub(hrtimer_get_expires(timer),
						    base->offset);
				if (expires.tv64 < expires_next.tv64)
					expires_next = expires;
				break;
			}

			__run_hrtimer(timer, &basenow);
		}
	}

	/*
	 * Store the new expiry value so the migration code can verify
	 * against it.
	 */
	cpu_base->expires_next = expires_next;
	raw_spin_unlock(&cpu_base->lock);

	/* Reprogramming necessary ? */
	if (expires_next.tv64 == KTIME_MAX ||
	    !tick_program_event(expires_next, 0)) {
		cpu_base->hang_detected = 0;
		return;
	}

	/*
	 * The next timer was already expired due to:
	 * - tracing
	 * - long lasting callbacks
	 * - being scheduled away when running in a VM
	 *
	 * We need to prevent that we loop forever in the hrtimer
	 * interrupt routine. We give it 3 attempts to avoid
	 * overreacting on some spurious event.
	 *
	 * Acquire base lock for updating the offsets and retrieving
	 * the current time.
	 */
	raw_spin_lock(&cpu_base->lock);
	now = hrtimer_update_base(cpu_base);
	cpu_base->nr_retries++;
	if (++retries < 3)
		goto retry;
	/*
	 * Give the system a chance to do something else than looping
	 * here. We stored the entry time, so we know exactly how long
	 * we spent here. We schedule the next event this amount of
	 * time away.
	 */
	cpu_base->nr_hangs++;
	cpu_base->hang_detected = 1;
	raw_spin_unlock(&cpu_base->lock);
	delta = ktime_sub(now, entry_time);
	if (delta.tv64 > cpu_base->max_hang_time.tv64)
		cpu_base->max_hang_time = delta;
	/*
	 * Limit it to a sensible value as we enforce a longer
	 * delay. Give the CPU at least 100ms to catch up.
	 */
	if (delta.tv64 > 100 * NSEC_PER_MSEC)
		expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
	else
		expires_next = ktime_add(now, delta);
	tick_program_event(expires_next, 1);
	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
		    ktime_to_ns(delta));
}
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
					 ktime_t now, int cpu)
{
	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
	unsigned long rcu_delta_jiffies;
	ktime_t last_update, expires, ret = { .tv64 = 0 };
	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
	u64 time_delta;


	/* Read jiffies and the time when jiffies were updated last */
	do {
		seq = read_seqbegin(&jiffies_lock);
		last_update = last_jiffies_update;
		last_jiffies = jiffies;
		time_delta = timekeeping_max_deferment();
	} while (read_seqretry(&jiffies_lock, seq));

	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || arch_needs_cpu(cpu) ||
	    irq_work_needs_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;
		if (rcu_delta_jiffies < delta_jiffies) {
			next_jiffies = last_jiffies + rcu_delta_jiffies;
			delta_jiffies = rcu_delta_jiffies;
		}
	}

	/*
	 * Do not stop the tick, if we are only one off (or less)
	 * 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;

		/* Skip reprogram of event if its not changed */
		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
			goto out;

		ret = expires;

		/*
		 * 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) {
			nohz_balance_enter_idle(cpu);
			calc_load_enter_idle();

			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
			ts->tick_stopped = 1;
		}

		/*
		 * 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());
	}
	raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
	ts->next_jiffies = next_jiffies;
	ts->last_jiffies = last_jiffies;

	return ret;
}

static bool can_stop_idle_tick(int cpu, struct tick_sched *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;
		return false;
	}

	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
		return false;

	if (need_resched())
		return false;

	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
		static int ratelimit;

		if (ratelimit < 10 &&
		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
			pr_warn("NOHZ: local_softirq_pending %02x\n",
				(unsigned int) local_softirq_pending());
			ratelimit++;
		}
		return false;
	}

	if (have_nohz_full_mask) {
		/*
		 * Keep the tick alive to guarantee timekeeping progression
		 * if there are full dynticks CPUs around
		 */
		if (tick_do_timer_cpu == cpu)
			return false;
		/*
		 * Boot safety: make sure the timekeeping duty has been
		 * assigned before entering dyntick-idle mode,
		 */
		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
			return false;
	}

	return true;
}

static void __tick_nohz_idle_enter(struct tick_sched *ts)
{
	ktime_t now, expires;
	int cpu = smp_processor_id();

	now = tick_nohz_start_idle(cpu, ts);

	if (can_stop_idle_tick(cpu, ts)) {
		int was_stopped = ts->tick_stopped;

		ts->idle_calls++;

		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
		if (expires.tv64 > 0LL) {
			ts->idle_sleeps++;
			ts->idle_expires = expires;
		}

		if (!was_stopped && ts->tick_stopped)
			ts->idle_jiffies = ts->last_jiffies;
	}
}
void hrtimer_interrupt(struct clock_event_device *dev)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	ktime_t expires_next, now, entry_time, delta;
	int i, retries = 0;

	BUG_ON(!cpu_base->hres_active);
	cpu_base->nr_events++;
	dev->next_event.tv64 = KTIME_MAX;

	raw_spin_lock(&cpu_base->lock);
	entry_time = now = hrtimer_update_base(cpu_base);
retry:
	expires_next.tv64 = KTIME_MAX;
	cpu_base->expires_next.tv64 = KTIME_MAX;

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		struct hrtimer_clock_base *base;
		struct timerqueue_node *node;
		ktime_t basenow;

		if (!(cpu_base->active_bases & (1 << i)))
			continue;

		base = cpu_base->clock_base + i;
		basenow = ktime_add(now, base->offset);

		while ((node = timerqueue_getnext(&base->active))) {
			struct hrtimer *timer;

			timer = container_of(node, struct hrtimer, node);


			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
				ktime_t expires;

				expires = ktime_sub(hrtimer_get_expires(timer),
						    base->offset);
				if (expires.tv64 < expires_next.tv64)
					expires_next = expires;
				break;
			}

			__run_hrtimer(timer, &basenow);
		}
	}

	cpu_base->expires_next = expires_next;
	raw_spin_unlock(&cpu_base->lock);

	
	if (expires_next.tv64 == KTIME_MAX ||
	    !tick_program_event(expires_next, 0)) {
		cpu_base->hang_detected = 0;
		return;
	}

	raw_spin_lock(&cpu_base->lock);
	now = hrtimer_update_base(cpu_base);
	cpu_base->nr_retries++;
	if (++retries < 3)
		goto retry;
	cpu_base->nr_hangs++;
	cpu_base->hang_detected = 1;
	raw_spin_unlock(&cpu_base->lock);
	delta = ktime_sub(now, entry_time);
	if (delta.tv64 > cpu_base->max_hang_time.tv64)
		cpu_base->max_hang_time = delta;
	if (delta.tv64 > 100 * NSEC_PER_MSEC)
		expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
	else
		expires_next = ktime_add(now, delta);
	tick_program_event(expires_next, 1);
	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
		    ktime_to_ns(delta));
}
示例#7
0
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
	ktime_t last_update, expires, now;
	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
	u64 time_delta;
	int cpu;

	cpu = smp_processor_id();
	ts = &per_cpu(tick_cpu_sched, cpu);

	now = tick_nohz_start_idle(cpu, ts);

	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))
		return;

	if (need_resched())
		return;

	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++;
		}
		return;
	}

	ts->idle_calls++;
	
	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 {
		
		next_jiffies = get_next_timer_interrupt(last_jiffies);
		delta_jiffies = next_jiffies - last_jiffies;
	}
	if (!ts->tick_stopped && delta_jiffies <= 1)
		goto out;

	
	if ((long)delta_jiffies >= 1) {

		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;
		}

		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
			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 (ts->tick_stopped && ktime_equal(expires, dev->next_event))
			goto out;

		if (!ts->tick_stopped) {
			select_nohz_load_balancer(1);
			calc_load_enter_idle();

			ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
			ts->tick_stopped = 1;
			ts->idle_jiffies = last_jiffies;
		}

		ts->idle_sleeps++;

		
		ts->idle_expires = expires;

		 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);
			
			if (hrtimer_active(&ts->sched_timer))
				goto out;
		} else if (!tick_program_event(expires, 0))
				goto out;
		tick_do_update_jiffies64(ktime_get());
	}
	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);
}