aboutsummaryrefslogtreecommitdiff
path: root/kernel/time/timekeeping.c
blob: 3bd7e3d5c6325a82563f03b8124b847ae6432623 (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
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
/*
 *  linux/kernel/time/timekeeping.c
 *
 *  Kernel timekeeping code and accessor functions
 *
 *  This code was moved from linux/kernel/timer.c.
 *  Please see that file for copyright and history logs.
 *
 */

#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sysdev.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/tick.h>
#include <linux/stop_machine.h>

/* Structure holding internal timekeeping values. */
struct timekeeper {
	/* Current clocksource used for timekeeping. */
	struct clocksource *clock;
	/* The shift value of the current clocksource. */
	int	shift;

	/* Number of clock cycles in one NTP interval. */
	cycle_t cycle_interval;
	/* Number of clock shifted nano seconds in one NTP interval. */
	u64	xtime_interval;
	/* shifted nano seconds left over when rounding cycle_interval */
	s64	xtime_remainder;
	/* Raw nano seconds accumulated per NTP interval. */
	u32	raw_interval;

	/* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */
	u64	xtime_nsec;
	/* Difference between accumulated time and NTP time in ntp
	 * shifted nano seconds. */
	s64	ntp_error;
	/* Shift conversion between clock shifted nano seconds and
	 * ntp shifted nano seconds. */
	int	ntp_error_shift;
	/* NTP adjusted clock multiplier */
	u32	mult;
};

static struct timekeeper timekeeper;

/**
 * timekeeper_setup_internals - Set up internals to use clocksource clock.
 *
 * @clock:		Pointer to clocksource.
 *
 * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
 * pair and interval request.
 *
 * Unless you're the timekeeping code, you should not be using this!
 */
static void timekeeper_setup_internals(struct clocksource *clock)
{
	cycle_t interval;
	u64 tmp, ntpinterval;

	timekeeper.clock = clock;
	clock->cycle_last = clock->read(clock);

	/* Do the ns -> cycle conversion first, using original mult */
	tmp = NTP_INTERVAL_LENGTH;
	tmp <<= clock->shift;
	ntpinterval = tmp;
	tmp += clock->mult/2;
	do_div(tmp, clock->mult);
	if (tmp == 0)
		tmp = 1;

	interval = (cycle_t) tmp;
	timekeeper.cycle_interval = interval;

	/* Go back from cycles -> shifted ns */
	timekeeper.xtime_interval = (u64) interval * clock->mult;
	timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval;
	timekeeper.raw_interval =
		((u64) interval * clock->mult) >> clock->shift;

	timekeeper.xtime_nsec = 0;
	timekeeper.shift = clock->shift;

	timekeeper.ntp_error = 0;
	timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;

	/*
	 * The timekeeper keeps its own mult values for the currently
	 * active clocksource. These value will be adjusted via NTP
	 * to counteract clock drifting.
	 */
	timekeeper.mult = clock->mult;
}

/* Timekeeper helper functions. */
static inline s64 timekeeping_get_ns(void)
{
	cycle_t cycle_now, cycle_delta;
	struct clocksource *clock;

	/* read clocksource: */
	clock = timekeeper.clock;
	cycle_now = clock->read(clock);

	/* calculate the delta since the last update_wall_time: */
	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;

	/* return delta convert to nanoseconds using ntp adjusted mult. */
	return clocksource_cyc2ns(cycle_delta, timekeeper.mult,
				  timekeeper.shift);
}

static inline s64 timekeeping_get_ns_raw(void)
{
	cycle_t cycle_now, cycle_delta;
	struct clocksource *clock;

	/* read clocksource: */
	clock = timekeeper.clock;
	cycle_now = clock->read(clock);

	/* calculate the delta since the last update_wall_time: */
	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;

	/* return delta convert to nanoseconds using ntp adjusted mult. */
	return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
}

/*
 * This read-write spinlock protects us from races in SMP while
 * playing with xtime.
 */
__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);


/*
 * The current time
 * wall_to_monotonic is what we need to add to xtime (or xtime corrected
 * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
 * at zero at system boot time, so wall_to_monotonic will be negative,
 * however, we will ALWAYS keep the tv_nsec part positive so we can use
 * the usual normalization.
 *
 * wall_to_monotonic is moved after resume from suspend for the monotonic
 * time not to jump. We need to add total_sleep_time to wall_to_monotonic
 * to get the real boot based time offset.
 *
 * - wall_to_monotonic is no longer the boot time, getboottime must be
 * used instead.
 */
static struct timespec xtime __attribute__ ((aligned (16)));
static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
static struct timespec total_sleep_time;

/*
 * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
 */
static struct timespec raw_time;

/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;

/* must hold xtime_lock */
void timekeeping_leap_insert(int leapsecond)
{
	xtime.tv_sec += leapsecond;
	wall_to_monotonic.tv_sec -= leapsecond;
	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
			timekeeper.mult);
}

/**
 * timekeeping_forward_now - update clock to the current time
 *
 * Forward the current clock to update its state since the last call to
 * update_wall_time(). This is useful before significant clock changes,
 * as it avoids having to deal with this time offset explicitly.
 */
static void timekeeping_forward_now(void)
{
	cycle_t cycle_now, cycle_delta;
	struct clocksource *clock;
	s64 nsec;

	clock = timekeeper.clock;
	cycle_now = clock->read(clock);
	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
	clock->cycle_last = cycle_now;

	nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult,
				  timekeeper.shift);

	/* If arch requires, add in gettimeoffset() */
	nsec += arch_gettimeoffset();

	timespec_add_ns(&xtime, nsec);

	nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
	timespec_add_ns(&raw_time, nsec);
}

/**
 * getnstimeofday - Returns the time of day in a timespec
 * @ts:		pointer to the timespec to be set
 *
 * Returns the time of day in a timespec.
 */
void getnstimeofday(struct timespec *ts)
{
	unsigned long seq;
	s64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqbegin(&xtime_lock);

		*ts = xtime;
		nsecs = timekeeping_get_ns();

		/* If arch requires, add in gettimeoffset() */
		nsecs += arch_gettimeoffset();

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

	timespec_add_ns(ts, nsecs);
}

EXPORT_SYMBOL(getnstimeofday);

ktime_t ktime_get(void)
{
	unsigned int seq;
	s64 secs, nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqbegin(&xtime_lock);
		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
		nsecs += timekeeping_get_ns();

	} while (read_seqretry(&xtime_lock, seq));
	/*
	 * Use ktime_set/ktime_add_ns to create a proper ktime on
	 * 32-bit architectures without CONFIG_KTIME_SCALAR.
	 */
	return ktime_add_ns(ktime_set(secs, 0), nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get);

/**
 * 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 int seq;
	s64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqbegin(&xtime_lock);
		*ts = xtime;
		tomono = wall_to_monotonic;
		nsecs = timekeeping_get_ns();

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

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

#ifdef CONFIG_NTP_PPS

/**
 * getnstime_raw_and_real - get day and raw monotonic time in timespec format
 * @ts_raw:	pointer to the timespec to be set to raw monotonic time
 * @ts_real:	pointer to the timespec to be set to the time of day
 *
 * This function reads both the time of day and raw monotonic time at the
 * same time atomically and stores the resulting timestamps in timespec
 * format.
 */
void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
{
	unsigned long seq;
	s64 nsecs_raw, nsecs_real;

	WARN_ON_ONCE(timekeeping_suspended);

	do {
		u32 arch_offset;

		seq = read_seqbegin(&xtime_lock);

		*ts_raw = raw_time;
		*ts_real = xtime;

		nsecs_raw = timekeeping_get_ns_raw();
		nsecs_real = timekeeping_get_ns();

		/* If arch requires, add in gettimeoffset() */
		arch_offset = arch_gettimeoffset();
		nsecs_raw += arch_offset;
		nsecs_real += arch_offset;

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

	timespec_add_ns(ts_raw, nsecs_raw);
	timespec_add_ns(ts_real, nsecs_real);
}
EXPORT_SYMBOL(getnstime_raw_and_real);

#endif /* CONFIG_NTP_PPS */

/**
 * do_gettimeofday - Returns the time of day in a timeval
 * @tv:		pointer to the timeval to be set
 *
 * NOTE: Users should be converted to using getnstimeofday()
 */
void do_gettimeofday(struct timeval *tv)
{
	struct timespec now;

	getnstimeofday(&now);
	tv->tv_sec = now.tv_sec;
	tv->tv_usec = now.tv_nsec/1000;
}

EXPORT_SYMBOL(do_gettimeofday);
/**
 * do_settimeofday - Sets the time of day
 * @tv:		pointer to the timespec variable containing the new time
 *
 * Sets the time of day to the new time and update NTP and notify hrtimers
 */
int do_settimeofday(const struct timespec *tv)
{
	struct timespec ts_delta;
	unsigned long flags;

	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
		return -EINVAL;

	write_seqlock_irqsave(&xtime_lock, flags);

	timekeeping_forward_now();

	ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
	ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
	wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);

	xtime = *tv;

	timekeeper.ntp_error = 0;
	ntp_clear();

	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
				timekeeper.mult);

	write_sequnlock_irqrestore(&xtime_lock, flags);

	/* signal hrtimers about time change */
	clock_was_set();

	return 0;
}

EXPORT_SYMBOL(do_settimeofday);


/**
 * timekeeping_inject_offset - Adds or subtracts from the current time.
 * @tv:		pointer to the timespec variable containing the offset
 *
 * Adds or subtracts an offset value from the current time.
 */
int timekeeping_inject_offset(struct timespec *ts)
{
	unsigned long flags;

	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
		return -EINVAL;

	write_seqlock_irqsave(&xtime_lock, flags);

	timekeeping_forward_now();

	xtime = timespec_add(xtime, *ts);
	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);

	timekeeper.ntp_error = 0;
	ntp_clear();

	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
				timekeeper.mult);

	write_sequnlock_irqrestore(&xtime_lock, flags);

	/* signal hrtimers about time change */
	clock_was_set();

	return 0;
}
EXPORT_SYMBOL(timekeeping_inject_offset);

/**
 * change_clocksource - Swaps clocksources if a new one is available
 *
 * Accumulates current time interval and initializes new clocksource
 */
static int change_clocksource(void *data)
{
	struct clocksource *new, *old;

	new = (struct clocksource *) data;

	timekeeping_forward_now();
	if (!new->enable || new->enable(new) == 0) {
		old = timekeeper.clock;
		timekeeper_setup_internals(new);
		if (old->disable)
			old->disable(old);
	}
	return 0;
}

/**
 * timekeeping_notify - Install a new clock source
 * @clock:		pointer to the clock source
 *
 * This function is called from clocksource.c after a new, better clock
 * source has been registered. The caller holds the clocksource_mutex.
 */
void timekeeping_notify(struct clocksource *clock)
{
	if (timekeeper.clock == clock)
		return;
	stop_machine(change_clocksource, clock, NULL);
	tick_clock_notify();
}

/**
 * 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);

/**
 * getrawmonotonic - Returns the raw monotonic time in a timespec
 * @ts:		pointer to the timespec to be set
 *
 * Returns the raw monotonic time (completely un-modified by ntp)
 */
void getrawmonotonic(struct timespec *ts)
{
	unsigned long seq;
	s64 nsecs;

	do {
		seq = read_seqbegin(&xtime_lock);
		nsecs = timekeeping_get_ns_raw();
		*ts = raw_time;

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

	timespec_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(getrawmonotonic);


/**
 * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
 */
int timekeeping_valid_for_hres(void)
{
	unsigned long seq;
	int ret;

	do {
		seq = read_seqbegin(&xtime_lock);

		ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;

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

	return ret;
}

/**
 * timekeeping_max_deferment - Returns max time the clocksource can be deferred
 *
 * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
 * ensure that the clocksource does not change!
 */
u64 timekeeping_max_deferment(void)
{
	return timekeeper.clock->max_idle_ns;
}

/**
 * read_persistent_clock -  Return time from the persistent clock.
 *
 * Weak dummy function for arches that do not yet support it.
 * Reads the time from the battery backed persistent clock.
 * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
 *
 *  XXX - Do be sure to remove it once all arches implement it.
 */
void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
{
	ts->tv_sec = 0;
	ts->tv_nsec = 0;
}

/**
 * read_boot_clock -  Return time of the system start.
 *
 * Weak dummy function for arches that do not yet support it.
 * Function to read the exact time the system has been started.
 * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
 *
 *  XXX - Do be sure to remove it once all arches implement it.
 */
void __attribute__((weak)) read_boot_clock(struct timespec *ts)
{
	ts->tv_sec = 0;
	ts->tv_nsec = 0;
}

/*
 * timekeeping_init - Initializes the clocksource and common timekeeping values
 */
void __init timekeeping_init(void)
{
	struct clocksource *clock;
	unsigned long flags;
	struct timespec now, boot;

	read_persistent_clock(&now);
	read_boot_clock(&boot);

	write_seqlock_irqsave(&xtime_lock, flags);

	ntp_init();

	clock = clocksource_default_clock();
	if (clock->enable)
		clock->enable(clock);
	timekeeper_setup_internals(clock);

	xtime.tv_sec = now.tv_sec;
	xtime.tv_nsec = now.tv_nsec;
	raw_time.tv_sec = 0;
	raw_time.tv_nsec = 0;
	if (boot.tv_sec == 0 && boot.tv_nsec == 0) {
		boot.tv_sec = xtime.tv_sec;
		boot.tv_nsec = xtime.tv_nsec;
	}
	set_normalized_timespec(&wall_to_monotonic,
				-boot.tv_sec, -boot.tv_nsec);
	total_sleep_time.tv_sec = 0;
	total_sleep_time.tv_nsec = 0;
	write_sequnlock_irqrestore(&xtime_lock, flags);
}

/* time in seconds when suspend began */
static struct timespec timekeeping_suspend_time;

/**
 * timekeeping_resume - Resumes the generic timekeeping subsystem.
 * @dev:	unused
 *
 * This is for the generic clocksource timekeeping.
 * xtime/wall_to_monotonic/jiffies/etc are
 * still managed by arch specific suspend/resume code.
 */
static int timekeeping_resume(struct sys_device *dev)
{
	unsigned long flags;
	struct timespec ts;

	read_persistent_clock(&ts);

	clocksource_resume();

	write_seqlock_irqsave(&xtime_lock, flags);

	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
		ts = timespec_sub(ts, timekeeping_suspend_time);
		xtime = timespec_add(xtime, ts);
		wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
		total_sleep_time = timespec_add(total_sleep_time, ts);
	}
	/* re-base the last cycle value */
	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
	timekeeper.ntp_error = 0;
	timekeeping_suspended = 0;
	write_sequnlock_irqrestore(&xtime_lock, flags);

	touch_softlockup_watchdog();

	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);

	/* Resume hrtimers */
	hres_timers_resume();

	return 0;
}

static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
{
	unsigned long flags;

	read_persistent_clock(&timekeeping_suspend_time);

	write_seqlock_irqsave(&xtime_lock, flags);
	timekeeping_forward_now();
	timekeeping_suspended = 1;
	write_sequnlock_irqrestore(&xtime_lock, flags);

	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
	clocksource_suspend();

	return 0;
}

/* sysfs resume/suspend bits for timekeeping */
static struct sysdev_class timekeeping_sysclass = {
	.name		= "timekeeping",
	.resume		= timekeeping_resume,
	.suspend	= timekeeping_suspend,
};

static struct sys_device device_timer = {
	.id		= 0,
	.cls		= &timekeeping_sysclass,
};

static int __init timekeeping_init_device(void)
{
	int error = sysdev_class_register(&timekeeping_sysclass);
	if (!error)
		error = sysdev_register(&device_timer);
	return error;
}

device_initcall(timekeeping_init_device);

/*
 * If the error is already larger, we look ahead even further
 * to compensate for late or lost adjustments.
 */
static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
						 s64 *offset)
{
	s64 tick_error, i;
	u32 look_ahead, adj;
	s32 error2, mult;

	/*
	 * Use the current error value to determine how much to look ahead.
	 * The larger the error the slower we adjust for it to avoid problems
	 * with losing too many ticks, otherwise we would overadjust and
	 * produce an even larger error.  The smaller the adjustment the
	 * faster we try to adjust for it, as lost ticks can do less harm
	 * here.  This is tuned so that an error of about 1 msec is adjusted
	 * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
	 */
	error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
	error2 = abs(error2);
	for (look_ahead = 0; error2 > 0; look_ahead++)
		error2 >>= 2;

	/*
	 * Now calculate the error in (1 << look_ahead) ticks, but first
	 * remove the single look ahead already included in the error.
	 */
	tick_error = tick_length >> (timekeeper.ntp_error_shift + 1);
	tick_error -= timekeeper.xtime_interval >> 1;
	error = ((error - tick_error) >> look_ahead) + tick_error;

	/* Finally calculate the adjustment shift value.  */
	i = *interval;
	mult = 1;
	if (error < 0) {
		error = -error;
		*interval = -*interval;
		*offset = -*offset;
		mult = -1;
	}
	for (adj = 0; error > i; adj++)
		error >>= 1;

	*interval <<= adj;
	*offset <<= adj;
	return mult << adj;
}

/*
 * Adjust the multiplier to reduce the error value,
 * this is optimized for the most common adjustments of -1,0,1,
 * for other values we can do a bit more work.
 */
static void timekeeping_adjust(s64 offset)
{
	s64 error, interval = timekeeper.cycle_interval;
	int adj;

	error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
	if (error > interval) {
		error >>= 2;
		if (likely(error <= interval))
			adj = 1;
		else
			adj = timekeeping_bigadjust(error, &interval, &offset);
	} else if (error < -interval) {
		error >>= 2;
		if (likely(error >= -interval)) {
			adj = -1;
			interval = -interval;
			offset = -offset;
		} else
			adj = timekeeping_bigadjust(error, &interval, &offset);
	} else
		return;

	timekeeper.mult += adj;
	timekeeper.xtime_interval += interval;
	timekeeper.xtime_nsec -= offset;
	timekeeper.ntp_error -= (interval - offset) <<
				timekeeper.ntp_error_shift;
}


/**
 * logarithmic_accumulation - shifted accumulation of cycles
 *
 * This functions accumulates a shifted interval of cycles into
 * into a shifted interval nanoseconds. Allows for O(log) accumulation
 * loop.
 *
 * Returns the unconsumed cycles.
 */
static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
{
	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
	u64 raw_nsecs;

	/* If the offset is smaller then a shifted interval, do nothing */
	if (offset < timekeeper.cycle_interval<<shift)
		return offset;

	/* Accumulate one shifted interval */
	offset -= timekeeper.cycle_interval << shift;
	timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;

	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
	while (timekeeper.xtime_nsec >= nsecps) {
		timekeeper.xtime_nsec -= nsecps;
		xtime.tv_sec++;
		second_overflow();
	}

	/* Accumulate raw time */
	raw_nsecs = timekeeper.raw_interval << shift;
	raw_nsecs += raw_time.tv_nsec;
	if (raw_nsecs >= NSEC_PER_SEC) {
		u64 raw_secs = raw_nsecs;
		raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
		raw_time.tv_sec += raw_secs;
	}
	raw_time.tv_nsec = raw_nsecs;

	/* Accumulate error between NTP and clock interval */
	timekeeper.ntp_error += tick_length << shift;
	timekeeper.ntp_error -=
	    (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
				(timekeeper.ntp_error_shift + shift);

	return offset;
}


/**
 * update_wall_time - Uses the current clocksource to increment the wall time
 *
 * Called from the timer interrupt, must hold a write on xtime_lock.
 */
static void update_wall_time(void)
{
	struct clocksource *clock;
	cycle_t offset;
	int shift = 0, maxshift;

	/* Make sure we're fully resumed: */
	if (unlikely(timekeeping_suspended))
		return;

	clock = timekeeper.clock;

#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
	offset = timekeeper.cycle_interval;
#else
	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
#endif
	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;

	/*
	 * With NO_HZ we may have to accumulate many cycle_intervals
	 * (think "ticks") worth of time at once. To do this efficiently,
	 * we calculate the largest doubling multiple of cycle_intervals
	 * that is smaller then the offset. We then accumulate that
	 * chunk in one go, and then try to consume the next smaller
	 * doubled multiple.
	 */
	shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
	shift = max(0, shift);
	/* Bound shift to one less then what overflows tick_length */
	maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
	shift = min(shift, maxshift);
	while (offset >= timekeeper.cycle_interval) {
		offset = logarithmic_accumulation(offset, shift);
		if(offset < timekeeper.cycle_interval<<shift)
			shift--;
	}

	/* correct the clock when NTP error is too big */
	timekeeping_adjust(offset);

	/*
	 * Since in the loop above, we accumulate any amount of time
	 * in xtime_nsec over a second into xtime.tv_sec, its possible for
	 * xtime_nsec to be fairly small after the loop. Further, if we're
	 * slightly speeding the clocksource up in timekeeping_adjust(),
	 * its possible the required corrective factor to xtime_nsec could
	 * cause it to underflow.
	 *
	 * Now, we cannot simply roll the accumulated second back, since
	 * the NTP subsystem has been notified via second_overflow. So
	 * instead we push xtime_nsec forward by the amount we underflowed,
	 * and add that amount into the error.
	 *
	 * We'll correct this error next time through this function, when
	 * xtime_nsec is not as small.
	 */
	if (unlikely((s64)timekeeper.xtime_nsec < 0)) {
		s64 neg = -(s64)timekeeper.xtime_nsec;
		timekeeper.xtime_nsec = 0;
		timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
	}


	/*
	 * Store full nanoseconds into xtime after rounding it up and
	 * add the remainder to the error difference.
	 */
	xtime.tv_nsec =	((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
	timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift;
	timekeeper.ntp_error +=	timekeeper.xtime_nsec <<
				timekeeper.ntp_error_shift;

	/*
	 * Finally, make sure that after the rounding
	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
	 */
	if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
		xtime.tv_nsec -= NSEC_PER_SEC;
		xtime.tv_sec++;
		second_overflow();
	}

	/* check to see if there is a new clocksource to use */
	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
				timekeeper.mult);
}

/**
 * getboottime - Return the real time of system boot.
 * @ts:		pointer to the timespec to be set
 *
 * Returns the wall-time of boot in a timespec.
 *
 * This is based on the wall_to_monotonic offset and the total suspend
 * time. Calls to settimeofday will affect the value returned (which
 * basically means that however wrong your real time clock is at boot time,
 * you get the right time here).
 */
void getboottime(struct timespec *ts)
{
	struct timespec boottime = {
		.tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec,
		.tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec
	};

	set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
}
EXPORT_SYMBOL_GPL(getboottime);


/**
 * get_monotonic_boottime - Returns monotonic time since boot
 * @ts:		pointer to the timespec to be set
 *
 * Returns the monotonic time since boot in a timespec.
 *
 * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
 * includes the time spent in suspend.
 */
void get_monotonic_boottime(struct timespec *ts)
{
	struct timespec tomono, sleep;
	unsigned int seq;
	s64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqbegin(&xtime_lock);
		*ts = xtime;
		tomono = wall_to_monotonic;
		sleep = total_sleep_time;
		nsecs = timekeeping_get_ns();

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

	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
}
EXPORT_SYMBOL_GPL(get_monotonic_boottime);

/**
 * ktime_get_boottime - Returns monotonic time since boot in a ktime
 *
 * Returns the monotonic time since boot in a ktime
 *
 * This is similar to CLOCK_MONTONIC/ktime_get, but also
 * includes the time spent in suspend.
 */
ktime_t ktime_get_boottime(void)
{
	struct timespec ts;

	get_monotonic_boottime(&ts);
	return timespec_to_ktime(ts);
}
EXPORT_SYMBOL_GPL(ktime_get_boottime);

/**
 * monotonic_to_bootbased - Convert the monotonic time to boot based.
 * @ts:		pointer to the timespec to be converted
 */
void monotonic_to_bootbased(struct timespec *ts)
{
	*ts = timespec_add(*ts, total_sleep_time);
}
EXPORT_SYMBOL_GPL(monotonic_to_bootbased);

unsigned long get_seconds(void)
{
	return xtime.tv_sec;
}
EXPORT_SYMBOL(get_seconds);

struct timespec __current_kernel_time(void)
{
	return xtime;
}

struct timespec current_kernel_time(void)
{
	struct timespec now;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);

		now = xtime;
	} while (read_seqretry(&xtime_lock, seq));

	return now;
}
EXPORT_SYMBOL(current_kernel_time);

struct timespec get_monotonic_coarse(void)
{
	struct timespec now, mono;
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);

		now = xtime;
		mono = wall_to_monotonic;
	} while (read_seqretry(&xtime_lock, seq));

	set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
				now.tv_nsec + mono.tv_nsec);
	return now;
}

/*
 * The 64-bit jiffies value is not atomic - you MUST NOT read it
 * without sampling the sequence number in xtime_lock.
 * jiffies is defined in the linker script...
 */
void do_timer(unsigned long ticks)
{
	jiffies_64 += ticks;
	update_wall_time();
	calc_global_load(ticks);
}

/**
 * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
 *    and sleep offsets.
 * @xtim:	pointer to timespec to be set with xtime
 * @wtom:	pointer to timespec to be set with wall_to_monotonic
 * @sleep:	pointer to timespec to be set with time in suspend
 */
void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
				struct timespec *wtom, struct timespec *sleep)
{
	unsigned long seq;

	do {
		seq = read_seqbegin(&xtime_lock);
		*xtim = xtime;
		*wtom = wall_to_monotonic;
		*sleep = total_sleep_time;
	} while (read_seqretry(&xtime_lock, seq));
}

/**
 * xtime_update() - advances the timekeeping infrastructure
 * @ticks:	number of ticks, that have elapsed since the last call.
 *
 * Must be called with interrupts disabled.
 */
void xtime_update(unsigned long ticks)
{
	write_seqlock(&xtime_lock);
	do_timer(ticks);
	write_sequnlock(&xtime_lock);
}