summaryrefslogtreecommitdiffstats
path: root/kernel/hrtimer.c
blob: a2310d1bebe14bc10ba6d261bccca9168b28151e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
/*
 *  linux/kernel/hrtimer.c
 *
 *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
 *  Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
 *  Copyright(C) 2006	    Timesys Corp., Thomas Gleixner <tglx@timesys.com>
 *
 *  High-resolution kernel timers
 *
 *  In contrast to the low-resolution timeout API implemented in
 *  kernel/timer.c, hrtimers provide finer resolution and accuracy
 *  depending on system configuration and capabilities.
 *
 *  These timers are currently used for:
 *   - itimers
 *   - POSIX timers
 *   - nanosleep
 *   - precise in-kernel timing
 *
 *  Started by: Thomas Gleixner and Ingo Molnar
 *
 *  Credits:
 *	based on kernel/timer.c
 *
 *	Help, testing, suggestions, bugfixes, improvements were
 *	provided by:
 *
 *	George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
 *	et. al.
 *
 *  For licencing details see kernel-base/COPYING
 */

#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/interrupt.h>

#include <asm/uaccess.h>

/**
 * ktime_get - get the monotonic time in ktime_t format
 *
 * returns the time in ktime_t format
 */
ktime_t ktime_get(void)
{
	struct timespec now;

	ktime_get_ts(&now);

	return timespec_to_ktime(now);
}

/**
 * ktime_get_real - get the real (wall-) time in ktime_t format
 *
 * returns the time in ktime_t format
 */
ktime_t ktime_get_real(void)
{
	struct timespec now;

	getnstimeofday(&now);

	return timespec_to_ktime(now);
}

EXPORT_SYMBOL_GPL(ktime_get_real);

/*
 * The timer bases:
 *
 * Note: If we want to add new timer bases, we have to skip the two
 * clock ids captured by the cpu-timers. We do this by holding empty
 * entries rather than doing math adjustment of the clock ids.
 * This ensures that we capture erroneous accesses to these clock ids
 * rather than moving them into the range of valid clock id's.
 */
static DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{

	.clock_base =
	{
		{
			.index = CLOCK_REALTIME,
			.get_time = &ktime_get_real,
			.resolution = KTIME_REALTIME_RES,
		},
		{
			.index = CLOCK_MONOTONIC,
			.get_time = &ktime_get,
			.resolution = KTIME_MONOTONIC_RES,
		},
	}
};

/**
 * ktime_get_ts - get the monotonic clock in timespec format
 * @ts:		pointer to timespec variable
 *
 * The function calculates the monotonic clock from the realtime
 * clock and the wall_to_monotonic offset and stores the result
 * in normalized timespec format in the variable pointed to by @ts.
 */
void ktime_get_ts(struct timespec *ts)
{
	struct timespec tomono;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);
		getnstimeofday(ts);
		tomono = wall_to_monotonic;

	} while (read_seqretry(&xtime_lock, seq));

	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
				ts->tv_nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts);

/*
 * Get the coarse grained time at the softirq based on xtime and
 * wall_to_monotonic.
 */
static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
{
	ktime_t xtim, tomono;
	struct timespec xts;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);
#ifdef CONFIG_NO_HZ
		getnstimeofday(&xts);
#else
		xts = xtime;
#endif
	} while (read_seqretry(&xtime_lock, seq));

	xtim = timespec_to_ktime(xts);
	tomono = timespec_to_ktime(wall_to_monotonic);
	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
	base->clock_base[CLOCK_MONOTONIC].softirq_time =
		ktime_add(xtim, tomono);
}

/*
 * 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->state & HRTIMER_STATE_CALLBACK;
}

/*
 * Functions and macros which are different for UP/SMP systems are kept in a
 * single place
 */
#ifdef CONFIG_SMP

/*
 * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
 * means that all timers which are tied to this base via timer->base are
 * locked, and the base itself is locked too.
 *
 * So __run_timers/migrate_timers can safely modify all timers which could
 * be found on the lists/queues.
 *
 * When the timer's base is locked, and the timer removed from list, it is
 * possible to set timer->base = NULL and drop the lock: the timer remains
 * locked.
 */
static
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
					     unsigned long *flags)
{
	struct hrtimer_clock_base *base;

	for (;;) {
		base = timer->base;
		if (likely(base != NULL)) {
			spin_lock_irqsave(&base->cpu_base->lock, *flags);
			if (likely(base == timer->base))
				return base;
			/* The timer has migrated to another CPU: */
			spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
		}
		cpu_relax();
	}
}

/*
 * Switch the timer base to the current CPU when possible.
 */
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
	struct hrtimer_clock_base *new_base;
	struct hrtimer_cpu_base *new_cpu_base;

	new_cpu_base = &__get_cpu_var(hrtimer_bases);
	new_base = &new_cpu_base->clock_base[base->index];

	if (base != new_base) {
		/*
		 * We are trying to schedule the timer on the local CPU.
		 * However we can't change timer's base while it is running,
		 * so we keep it on the same CPU. No hassle vs. reprogramming
		 * the event source in the high resolution case. The softirq
		 * code will take care of this when the timer function has
		 * completed. There is no conflict as we hold the lock until
		 * the timer is enqueued.
		 */
		if (unlikely(timer->state & HRTIMER_STATE_CALLBACK))
			return base;

		/* See the comment in lock_timer_base() */
		timer->base = NULL;
		spin_unlock(&base->cpu_base->lock);
		spin_lock(&new_base->cpu_base->lock);
		timer->base = new_base;
	}
	return new_base;
}

#else /* CONFIG_SMP */

static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
	struct hrtimer_clock_base *base = timer->base;

	spin_lock_irqsave(&base->cpu_base->lock, *flags);

	return base;
}

#define switch_hrtimer_base(t, b)	(b)

#endif	/* !CONFIG_SMP */

/*
 * Functions for the union type storage format of ktime_t which are
 * too large for inlining:
 */
#if BITS_PER_LONG < 64
# ifndef CONFIG_KTIME_SCALAR
/**
 * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable
 * @kt:		addend
 * @nsec:	the scalar nsec value to add
 *
 * Returns the sum of kt and nsec in ktime_t format
 */
ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
{
	ktime_t tmp;

	if (likely(nsec < NSEC_PER_SEC)) {
		tmp.tv64 = nsec;
	} else {
		unsigned long rem = do_div(nsec, NSEC_PER_SEC);

		tmp = ktime_set((long)nsec, rem);
	}

	return ktime_add(kt, tmp);
}

#else /* CONFIG_KTIME_SCALAR */

# endif /* !CONFIG_KTIME_SCALAR */

/*
 * Divide a ktime value by a nanosecond value
 */
static unsigned long ktime_divns(const ktime_t kt, s64 div)
{
	u64 dclc, inc, dns;
	int sft = 0;

	dclc = dns = ktime_to_ns(kt);
	inc = div;
	/* Make sure the divisor is less than 2^32: */
	while (div >> 32) {
		sft++;
		div >>= 1;
	}
	dclc >>= sft;
	do_div(dclc, (unsigned long) div);

	return (unsigned long) dclc;
}

#else /* BITS_PER_LONG < 64 */
# define ktime_divns(kt, div)		(unsigned long)((kt).tv64 / (div))
#endif /* BITS_PER_LONG >= 64 */

/*
 * Counterpart to lock_timer_base above:
 */
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
	spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}

/**
 * hrtimer_forward - forward the timer expiry
 * @timer:	hrtimer to forward
 * @now:	forward past this time
 * @interval:	the interval to forward
 *
 * Forward the timer expiry so it will expire in the future.
 * Returns the number of overruns.
 */
unsigned long
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
	unsigned long orun = 1;
	ktime_t delta;

	delta = ktime_sub(now, timer->expires);

	if (delta.tv64 < 0)
		return 0;

	if (interval.tv64 < timer->base->resolution.tv64)
		interval.tv64 = timer->base->resolution.tv64;

	if (unlikely(delta.tv64 >= interval.tv64)) {
		s64 incr = ktime_to_ns(interval);

		orun = ktime_divns(delta, incr);
		timer->expires = ktime_add_ns(timer->expires, incr * orun);
		if (timer->expires.tv64 > now.tv64)
			return orun;
		/*
		 * This (and the ktime_add() below) is the
		 * correction for exact:
		 */
		orun++;
	}
	timer->expires = ktime_add(timer->expires, interval);

	return orun;
}

/*
 * enqueue_hrtimer - internal function to (re)start a timer
 *
 * The timer is inserted in expiry order. Insertion into the
 * red black tree is O(log(n)). Must hold the base lock.
 */
static void enqueue_hrtimer(struct hrtimer *timer,
			    struct hrtimer_clock_base *base)
{
	struct rb_node **link = &base->active.rb_node;
	struct rb_node *parent = NULL;
	struct hrtimer *entry;

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct hrtimer, node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same expiry time stay together.
		 */
		if (timer->expires.tv64 < entry->expires.tv64)
			link = &(*link)->rb_left;
		else
			link = &(*link)->rb_right;
	}

	/*
	 * Insert the timer to the rbtree and check whether it
	 * replaces the first pending timer
	 */
	rb_link_node(&timer->node, parent, link);
	rb_insert_color(&timer->node, &base->active);
	/*
	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
	 * state of a possibly running callback.
	 */
	timer->state |= HRTIMER_STATE_ENQUEUED;

	if (!base->first || timer->expires.tv64 <
	    rb_entry(base->first, struct hrtimer, node)->expires.tv64)
		base->first = &timer->node;
}

/*
 * __remove_hrtimer - internal function to remove a timer
 *
 * Caller must hold the base lock.
 */
static void __remove_hrtimer(struct hrtimer *timer,
			     struct hrtimer_clock_base *base,
			     unsigned long newstate)
{
	/*
	 * Remove the timer from the rbtree and replace the
	 * first entry pointer if necessary.
	 */
	if (base->first == &timer->node)
		base->first = rb_next(&timer->node);
	rb_erase(&timer->node, &base->active);
	timer->state = newstate;
}

/*
 * remove hrtimer, called with base lock held
 */
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
	if (hrtimer_is_queued(timer)) {
		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE);
		return 1;
	}
	return 0;
}

/**
 * hrtimer_start - (re)start an relative timer on the current CPU
 * @timer:	the timer to be added
 * @tim:	expiry time
 * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
 *
 * Returns:
 *  0 on success
 *  1 when the timer was active
 */
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
	struct hrtimer_clock_base *base, *new_base;
	unsigned long flags;
	int ret;

	base = lock_hrtimer_base(timer, &flags);

	/* Remove an active timer from the queue: */
	ret = remove_hrtimer(timer, base);

	/* Switch the timer base, if necessary: */
	new_base = switch_hrtimer_base(timer, base);

	if (mode == HRTIMER_MODE_REL) {
		tim = ktime_add(tim, new_base->get_time());
		/*
		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
		 * to signal that they simply return xtime in
		 * do_gettimeoffset(). In this case we want to round up by
		 * resolution when starting a relative timer, to avoid short
		 * timeouts. This will go away with the GTOD framework.
		 */
#ifdef CONFIG_TIME_LOW_RES
		tim = ktime_add(tim, base->resolution);
#endif
	}
	timer->expires = tim;

	enqueue_hrtimer(timer, new_base);

	unlock_hrtimer_base(timer, &flags);

	return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_start);

/**
 * hrtimer_try_to_cancel - try to deactivate a timer
 * @timer:	hrtimer to stop
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 * -1 when the timer is currently excuting the callback function and
 *    cannot be stopped
 */
int hrtimer_try_to_cancel(struct hrtimer *timer)
{
	struct hrtimer_clock_base *base;
	unsigned long flags;
	int ret = -1;

	base = lock_hrtimer_base(timer, &flags);

	if (!hrtimer_callback_running(timer))
		ret = remove_hrtimer(timer, base);

	unlock_hrtimer_base(timer, &flags);

	return ret;

}
EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);

/**
 * hrtimer_cancel - cancel a timer and wait for the handler to finish.
 * @timer:	the timer to be cancelled
 *
 * Returns:
 *  0 when the timer was not active
 *  1 when the timer was active
 */
int hrtimer_cancel(struct hrtimer *timer)
{
	for (;;) {
		int ret = hrtimer_try_to_cancel(timer);

		if (ret >= 0)
			return ret;
		cpu_relax();
	}
}
EXPORT_SYMBOL_GPL(hrtimer_cancel);

/**
 * hrtimer_get_remaining - get remaining time for the timer
 * @timer:	the timer to read
 */
ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
{
	struct hrtimer_clock_base *base;
	unsigned long flags;
	ktime_t rem;

	base = lock_hrtimer_base(timer, &flags);
	rem = ktime_sub(timer->expires, base->get_time());
	unlock_hrtimer_base(timer, &flags);

	return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);

#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
/**
 * hrtimer_get_next_event - get the time until next expiry event
 *
 * Returns the delta to the next expiry event or KTIME_MAX if no timer
 * is pending.
 */
ktime_t hrtimer_get_next_event(void)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	struct hrtimer_clock_base *base = cpu_base->clock_base;
	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
	unsigned long flags;
	int i;

	spin_lock_irqsave(&cpu_base->lock, flags);

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
		struct hrtimer *timer;

		if (!base->first)
			continue;

		timer = rb_entry(base->first, struct hrtimer, node);
		delta.tv64 = timer->expires.tv64;
		delta = ktime_sub(delta, base->get_time());
		if (delta.tv64 < mindelta.tv64)
			mindelta.tv64 = delta.tv64;
	}

	spin_unlock_irqrestore(&cpu_base->lock, flags);

	if (mindelta.tv64 < 0)
		mindelta.tv64 = 0;
	return mindelta;
}
#endif

/**
 * hrtimer_init - initialize a timer to the given clock
 * @timer:	the timer to be initialized
 * @clock_id:	the clock to be used
 * @mode:	timer mode abs/rel
 */
void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
		  enum hrtimer_mode mode)
{
	struct hrtimer_cpu_base *cpu_base;

	memset(timer, 0, sizeof(struct hrtimer));

	cpu_base = &__raw_get_cpu_var(hrtimer_bases);

	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
		clock_id = CLOCK_MONOTONIC;

	timer->base = &cpu_base->clock_base[clock_id];
}
EXPORT_SYMBOL_GPL(hrtimer_init);

/**
 * hrtimer_get_res - get the timer resolution for a clock
 * @which_clock: which clock to query
 * @tp:		 pointer to timespec variable to store the resolution
 *
 * Store the resolution of the clock selected by @which_clock in the
 * variable pointed to by @tp.
 */
int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
{
	struct hrtimer_cpu_base *cpu_base;

	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);

	return 0;
}
EXPORT_SYMBOL_GPL(hrtimer_get_res);

/*
 * Expire the per base hrtimer-queue:
 */
static inline void run_hrtimer_queue(struct hrtimer_cpu_base *cpu_base,
				     int index)
{
	struct rb_node *node;
	struct hrtimer_clock_base *base = &cpu_base->clock_base[index];

	if (!base->first)
		return;

	if (base->get_softirq_time)
		base->softirq_time = base->get_softirq_time();

	spin_lock_irq(&cpu_base->lock);

	while ((node = base->first)) {
		struct hrtimer *timer;
		enum hrtimer_restart (*fn)(struct hrtimer *);
		int restart;

		timer = rb_entry(node, struct hrtimer, node);
		if (base->softirq_time.tv64 <= timer->expires.tv64)
			break;

		fn = timer->function;
		__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK);
		spin_unlock_irq(&cpu_base->lock);

		restart = fn(timer);

		spin_lock_irq(&cpu_base->lock);

		timer->state &= ~HRTIMER_STATE_CALLBACK;
		if (restart != HRTIMER_NORESTART) {
			BUG_ON(hrtimer_active(timer));
			enqueue_hrtimer(timer, base);
		}
	}
	spin_unlock_irq(&cpu_base->lock);
}

/*
 * Called from timer softirq every jiffy, expire hrtimers:
 */
void hrtimer_run_queues(void)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	int i;

	hrtimer_get_softirq_time(cpu_base);

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
		run_hrtimer_queue(cpu_base, i);
}

/*
 * Sleep related functions:
 */
static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
{
	struct hrtimer_sleeper *t =
		container_of(timer, struct hrtimer_sleeper, timer);
	struct task_struct *task = t->task;

	t->task = NULL;
	if (task)
		wake_up_process(task);

	return HRTIMER_NORESTART;
}

void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
{
	sl->timer.function = hrtimer_wakeup;
	sl->task = task;
}

static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
{
	hrtimer_init_sleeper(t, current);

	do {
		set_current_state(TASK_INTERRUPTIBLE);
		hrtimer_start(&t->timer, t->timer.expires, mode);

		schedule();

		hrtimer_cancel(&t->timer);
		mode = HRTIMER_MODE_ABS;

	} while (t->task && !signal_pending(current));

	return t->task == NULL;
}

long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
{
	struct hrtimer_sleeper t;
	struct timespec __user *rmtp;
	struct timespec tu;
	ktime_t time;

	restart->fn = do_no_restart_syscall;

	hrtimer_init(&t.timer, restart->arg0, HRTIMER_MODE_ABS);
	t.timer.expires.tv64 = ((u64)restart->arg3 << 32) | (u64) restart->arg2;

	if (do_nanosleep(&t, HRTIMER_MODE_ABS))
		return 0;

	rmtp = (struct timespec __user *) restart->arg1;
	if (rmtp) {
		time = ktime_sub(t.timer.expires, t.timer.base->get_time());
		if (time.tv64 <= 0)
			return 0;
		tu = ktime_to_timespec(time);
		if (copy_to_user(rmtp, &tu, sizeof(tu)))
			return -EFAULT;
	}

	restart->fn = hrtimer_nanosleep_restart;

	/* The other values in restart are already filled in */
	return -ERESTART_RESTARTBLOCK;
}

long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
		       const enum hrtimer_mode mode, const clockid_t clockid)
{
	struct restart_block *restart;
	struct hrtimer_sleeper t;
	struct timespec tu;
	ktime_t rem;

	hrtimer_init(&t.timer, clockid, mode);
	t.timer.expires = timespec_to_ktime(*rqtp);
	if (do_nanosleep(&t, mode))
		return 0;

	/* Absolute timers do not update the rmtp value and restart: */
	if (mode == HRTIMER_MODE_ABS)
		return -ERESTARTNOHAND;

	if (rmtp) {
		rem = ktime_sub(t.timer.expires, t.timer.base->get_time());
		if (rem.tv64 <= 0)
			return 0;
		tu = ktime_to_timespec(rem);
		if (copy_to_user(rmtp, &tu, sizeof(tu)))
			return -EFAULT;
	}

	restart = &current_thread_info()->restart_block;
	restart->fn = hrtimer_nanosleep_restart;
	restart->arg0 = (unsigned long) t.timer.base->index;
	restart->arg1 = (unsigned long) rmtp;
	restart->arg2 = t.timer.expires.tv64 & 0xFFFFFFFF;
	restart->arg3 = t.timer.expires.tv64 >> 32;

	return -ERESTART_RESTARTBLOCK;
}

asmlinkage long
sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
{
	struct timespec tu;

	if (copy_from_user(&tu, rqtp, sizeof(tu)))
		return -EFAULT;

	if (!timespec_valid(&tu))
		return -EINVAL;

	return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}

/*
 * Functions related to boot-time initialization:
 */
static void __devinit init_hrtimers_cpu(int cpu)
{
	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
	int i;

	spin_lock_init(&cpu_base->lock);
	lockdep_set_class(&cpu_base->lock, &cpu_base->lock_key);

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
		cpu_base->clock_base[i].cpu_base = cpu_base;

}

#ifdef CONFIG_HOTPLUG_CPU

static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
				struct hrtimer_clock_base *new_base)
{
	struct hrtimer *timer;
	struct rb_node *node;

	while ((node = rb_first(&old_base->active))) {
		timer = rb_entry(node, struct hrtimer, node);
		BUG_ON(timer->state & HRTIMER_STATE_CALLBACK);
		__remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE);
		timer->base = new_base;
		enqueue_hrtimer(timer, new_base);
	}
}

static void migrate_hrtimers(int cpu)
{
	struct hrtimer_cpu_base *old_base, *new_base;
	int i;

	BUG_ON(cpu_online(cpu));
	old_base = &per_cpu(hrtimer_bases, cpu);
	new_base = &get_cpu_var(hrtimer_bases);

	local_irq_disable();

	spin_lock(&new_base->lock);
	spin_lock(&old_base->lock);

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		migrate_hrtimer_list(&old_base->clock_base[i],
				     &new_base->clock_base[i]);
	}
	spin_unlock(&old_base->lock);
	spin_unlock(&new_base->lock);

	local_irq_enable();
	put_cpu_var(hrtimer_bases);
}
#endif /* CONFIG_HOTPLUG_CPU */

static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
					unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;

	switch (action) {

	case CPU_UP_PREPARE:
		init_hrtimers_cpu(cpu);
		break;

#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
		migrate_hrtimers(cpu);
		break;
#endif

	default:
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata hrtimers_nb = {
	.notifier_call = hrtimer_cpu_notify,
};

void __init hrtimers_init(void)
{
	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
			  (void *)(long)smp_processor_id());
	register_cpu_notifier(&hrtimers_nb);
}