summaryrefslogtreecommitdiff
path: root/kernel/time/clocksource.c
blob: 03918a19cf2da854bcefa9f8188daa53a7db82f4 (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
/*
 * linux/kernel/time/clocksource.c
 *
 * This file contains the functions which manage clocksource drivers.
 *
 * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * TODO WishList:
 *   o Allow clocksource drivers to be unregistered
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/device.h>
#include <linux/clocksource.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
#include <linux/tick.h>
#include <linux/kthread.h>

#include "tick-internal.h"
#include "timekeeping_internal.h"

/**
 * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
 * @mult:	pointer to mult variable
 * @shift:	pointer to shift variable
 * @from:	frequency to convert from
 * @to:		frequency to convert to
 * @maxsec:	guaranteed runtime conversion range in seconds
 *
 * The function evaluates the shift/mult pair for the scaled math
 * operations of clocksources and clockevents.
 *
 * @to and @from are frequency values in HZ. For clock sources @to is
 * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
 * event @to is the counter frequency and @from is NSEC_PER_SEC.
 *
 * The @maxsec conversion range argument controls the time frame in
 * seconds which must be covered by the runtime conversion with the
 * calculated mult and shift factors. This guarantees that no 64bit
 * overflow happens when the input value of the conversion is
 * multiplied with the calculated mult factor. Larger ranges may
 * reduce the conversion accuracy by chosing smaller mult and shift
 * factors.
 */
void
clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
{
	u64 tmp;
	u32 sft, sftacc= 32;

	/*
	 * Calculate the shift factor which is limiting the conversion
	 * range:
	 */
	tmp = ((u64)maxsec * from) >> 32;
	while (tmp) {
		tmp >>=1;
		sftacc--;
	}

	/*
	 * Find the conversion shift/mult pair which has the best
	 * accuracy and fits the maxsec conversion range:
	 */
	for (sft = 32; sft > 0; sft--) {
		tmp = (u64) to << sft;
		tmp += from / 2;
		do_div(tmp, from);
		if ((tmp >> sftacc) == 0)
			break;
	}
	*mult = tmp;
	*shift = sft;
}
EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);

/*[Clocksource internal variables]---------
 * curr_clocksource:
 *	currently selected clocksource.
 * clocksource_list:
 *	linked list with the registered clocksources
 * clocksource_mutex:
 *	protects manipulations to curr_clocksource and the clocksource_list
 * override_name:
 *	Name of the user-specified clocksource.
 */
static struct clocksource *curr_clocksource;
static LIST_HEAD(clocksource_list);
static DEFINE_MUTEX(clocksource_mutex);
static char override_name[CS_NAME_LEN];
static int finished_booting;

#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
static void clocksource_watchdog_work(struct work_struct *work);
static void clocksource_select(void);

static LIST_HEAD(watchdog_list);
static struct clocksource *watchdog;
static struct timer_list watchdog_timer;
static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
static DEFINE_SPINLOCK(watchdog_lock);
static int watchdog_running;
static atomic_t watchdog_reset_pending;

static int clocksource_watchdog_kthread(void *data);
static void __clocksource_change_rating(struct clocksource *cs, int rating);

/*
 * Interval: 0.5sec Threshold: 0.0625s
 */
#define WATCHDOG_INTERVAL (HZ >> 1)
#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)

static void clocksource_watchdog_work(struct work_struct *work)
{
	/*
	 * If kthread_run fails the next watchdog scan over the
	 * watchdog_list will find the unstable clock again.
	 */
	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
}

static void __clocksource_unstable(struct clocksource *cs)
{
	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
	cs->flags |= CLOCK_SOURCE_UNSTABLE;

	if (cs->mark_unstable)
		cs->mark_unstable(cs);

	if (finished_booting)
		schedule_work(&watchdog_work);
}

/**
 * clocksource_mark_unstable - mark clocksource unstable via watchdog
 * @cs:		clocksource to be marked unstable
 *
 * This function is called instead of clocksource_change_rating from
 * cpu hotplug code to avoid a deadlock between the clocksource mutex
 * and the cpu hotplug mutex. It defers the update of the clocksource
 * to the watchdog thread.
 */
void clocksource_mark_unstable(struct clocksource *cs)
{
	unsigned long flags;

	spin_lock_irqsave(&watchdog_lock, flags);
	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
		if (list_empty(&cs->wd_list))
			list_add(&cs->wd_list, &watchdog_list);
		__clocksource_unstable(cs);
	}
	spin_unlock_irqrestore(&watchdog_lock, flags);
}

static void clocksource_watchdog(unsigned long data)
{
	struct clocksource *cs;
	u64 csnow, wdnow, cslast, wdlast, delta;
	int64_t wd_nsec, cs_nsec;
	int next_cpu, reset_pending;

	spin_lock(&watchdog_lock);
	if (!watchdog_running)
		goto out;

	reset_pending = atomic_read(&watchdog_reset_pending);

	list_for_each_entry(cs, &watchdog_list, wd_list) {

		/* Clocksource already marked unstable? */
		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
			if (finished_booting)
				schedule_work(&watchdog_work);
			continue;
		}

		local_irq_disable();
		csnow = cs->read(cs);
		wdnow = watchdog->read(watchdog);
		local_irq_enable();

		/* Clocksource initialized ? */
		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
		    atomic_read(&watchdog_reset_pending)) {
			cs->flags |= CLOCK_SOURCE_WATCHDOG;
			cs->wd_last = wdnow;
			cs->cs_last = csnow;
			continue;
		}

		delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask);
		wd_nsec = clocksource_cyc2ns(delta, watchdog->mult,
					     watchdog->shift);

		delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
		wdlast = cs->wd_last; /* save these in case we print them */
		cslast = cs->cs_last;
		cs->cs_last = csnow;
		cs->wd_last = wdnow;

		if (atomic_read(&watchdog_reset_pending))
			continue;

		/* Check the deviation from the watchdog clocksource. */
		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
			pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
				smp_processor_id(), cs->name);
			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
				watchdog->name, wdnow, wdlast, watchdog->mask);
			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
				cs->name, csnow, cslast, cs->mask);
			__clocksource_unstable(cs);
			continue;
		}

		if (cs == curr_clocksource && cs->tick_stable)
			cs->tick_stable(cs);

		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
			/* Mark it valid for high-res. */
			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;

			/*
			 * clocksource_done_booting() will sort it if
			 * finished_booting is not set yet.
			 */
			if (!finished_booting)
				continue;

			/*
			 * If this is not the current clocksource let
			 * the watchdog thread reselect it. Due to the
			 * change to high res this clocksource might
			 * be preferred now. If it is the current
			 * clocksource let the tick code know about
			 * that change.
			 */
			if (cs != curr_clocksource) {
				cs->flags |= CLOCK_SOURCE_RESELECT;
				schedule_work(&watchdog_work);
			} else {
				tick_clock_notify();
			}
		}
	}

	/*
	 * We only clear the watchdog_reset_pending, when we did a
	 * full cycle through all clocksources.
	 */
	if (reset_pending)
		atomic_dec(&watchdog_reset_pending);

	/*
	 * Cycle through CPUs to check if the CPUs stay synchronized
	 * to each other.
	 */
	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
	if (next_cpu >= nr_cpu_ids)
		next_cpu = cpumask_first(cpu_online_mask);
	watchdog_timer.expires += WATCHDOG_INTERVAL;
	add_timer_on(&watchdog_timer, next_cpu);
out:
	spin_unlock(&watchdog_lock);
}

static inline void clocksource_start_watchdog(void)
{
	if (watchdog_running || !watchdog || list_empty(&watchdog_list))
		return;
	init_timer(&watchdog_timer);
	watchdog_timer.function = clocksource_watchdog;
	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
	watchdog_running = 1;
}

static inline void clocksource_stop_watchdog(void)
{
	if (!watchdog_running || (watchdog && !list_empty(&watchdog_list)))
		return;
	del_timer(&watchdog_timer);
	watchdog_running = 0;
}

static inline void clocksource_reset_watchdog(void)
{
	struct clocksource *cs;

	list_for_each_entry(cs, &watchdog_list, wd_list)
		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
}

static void clocksource_resume_watchdog(void)
{
	atomic_inc(&watchdog_reset_pending);
}

static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
	unsigned long flags;

	spin_lock_irqsave(&watchdog_lock, flags);
	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
		/* cs is a clocksource to be watched. */
		list_add(&cs->wd_list, &watchdog_list);
		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
	} else {
		/* cs is a watchdog. */
		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
	}
	spin_unlock_irqrestore(&watchdog_lock, flags);
}

static void clocksource_select_watchdog(bool fallback)
{
	struct clocksource *cs, *old_wd;
	unsigned long flags;

	spin_lock_irqsave(&watchdog_lock, flags);
	/* save current watchdog */
	old_wd = watchdog;
	if (fallback)
		watchdog = NULL;

	list_for_each_entry(cs, &clocksource_list, list) {
		/* cs is a clocksource to be watched. */
		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
			continue;

		/* Skip current if we were requested for a fallback. */
		if (fallback && cs == old_wd)
			continue;

		/* Pick the best watchdog. */
		if (!watchdog || cs->rating > watchdog->rating)
			watchdog = cs;
	}
	/* If we failed to find a fallback restore the old one. */
	if (!watchdog)
		watchdog = old_wd;

	/* If we changed the watchdog we need to reset cycles. */
	if (watchdog != old_wd)
		clocksource_reset_watchdog();

	/* Check if the watchdog timer needs to be started. */
	clocksource_start_watchdog();
	spin_unlock_irqrestore(&watchdog_lock, flags);
}

static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
	unsigned long flags;

	spin_lock_irqsave(&watchdog_lock, flags);
	if (cs != watchdog) {
		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
			/* cs is a watched clocksource. */
			list_del_init(&cs->wd_list);
			/* Check if the watchdog timer needs to be stopped. */
			clocksource_stop_watchdog();
		}
	}
	spin_unlock_irqrestore(&watchdog_lock, flags);
}

static int __clocksource_watchdog_kthread(void)
{
	struct clocksource *cs, *tmp;
	unsigned long flags;
	LIST_HEAD(unstable);
	int select = 0;

	spin_lock_irqsave(&watchdog_lock, flags);
	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
			list_del_init(&cs->wd_list);
			list_add(&cs->wd_list, &unstable);
			select = 1;
		}
		if (cs->flags & CLOCK_SOURCE_RESELECT) {
			cs->flags &= ~CLOCK_SOURCE_RESELECT;
			select = 1;
		}
	}
	/* Check if the watchdog timer needs to be stopped. */
	clocksource_stop_watchdog();
	spin_unlock_irqrestore(&watchdog_lock, flags);

	/* Needs to be done outside of watchdog lock */
	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
		list_del_init(&cs->wd_list);
		__clocksource_change_rating(cs, 0);
	}
	return select;
}

static int clocksource_watchdog_kthread(void *data)
{
	mutex_lock(&clocksource_mutex);
	if (__clocksource_watchdog_kthread())
		clocksource_select();
	mutex_unlock(&clocksource_mutex);
	return 0;
}

static bool clocksource_is_watchdog(struct clocksource *cs)
{
	return cs == watchdog;
}

#else /* CONFIG_CLOCKSOURCE_WATCHDOG */

static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
	if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}

static void clocksource_select_watchdog(bool fallback) { }
static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
static inline int __clocksource_watchdog_kthread(void) { return 0; }
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
void clocksource_mark_unstable(struct clocksource *cs) { }

#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */

/**
 * clocksource_suspend - suspend the clocksource(s)
 */
void clocksource_suspend(void)
{
	struct clocksource *cs;

	list_for_each_entry_reverse(cs, &clocksource_list, list)
		if (cs->suspend)
			cs->suspend(cs);
}

/**
 * clocksource_resume - resume the clocksource(s)
 */
void clocksource_resume(void)
{
	struct clocksource *cs;

	list_for_each_entry(cs, &clocksource_list, list)
		if (cs->resume)
			cs->resume(cs);

	clocksource_resume_watchdog();
}

/**
 * clocksource_touch_watchdog - Update watchdog
 *
 * Update the watchdog after exception contexts such as kgdb so as not
 * to incorrectly trip the watchdog. This might fail when the kernel
 * was stopped in code which holds watchdog_lock.
 */
void clocksource_touch_watchdog(void)
{
	clocksource_resume_watchdog();
}

/**
 * clocksource_max_adjustment- Returns max adjustment amount
 * @cs:         Pointer to clocksource
 *
 */
static u32 clocksource_max_adjustment(struct clocksource *cs)
{
	u64 ret;
	/*
	 * We won't try to correct for more than 11% adjustments (110,000 ppm),
	 */
	ret = (u64)cs->mult * 11;
	do_div(ret,100);
	return (u32)ret;
}

/**
 * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
 * @mult:	cycle to nanosecond multiplier
 * @shift:	cycle to nanosecond divisor (power of two)
 * @maxadj:	maximum adjustment value to mult (~11%)
 * @mask:	bitmask for two's complement subtraction of non 64 bit counters
 * @max_cyc:	maximum cycle value before potential overflow (does not include
 *		any safety margin)
 *
 * NOTE: This function includes a safety margin of 50%, in other words, we
 * return half the number of nanoseconds the hardware counter can technically
 * cover. This is done so that we can potentially detect problems caused by
 * delayed timers or bad hardware, which might result in time intervals that
 * are larger than what the math used can handle without overflows.
 */
u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
{
	u64 max_nsecs, max_cycles;

	/*
	 * Calculate the maximum number of cycles that we can pass to the
	 * cyc2ns() function without overflowing a 64-bit result.
	 */
	max_cycles = ULLONG_MAX;
	do_div(max_cycles, mult+maxadj);

	/*
	 * The actual maximum number of cycles we can defer the clocksource is
	 * determined by the minimum of max_cycles and mask.
	 * Note: Here we subtract the maxadj to make sure we don't sleep for
	 * too long if there's a large negative adjustment.
	 */
	max_cycles = min(max_cycles, mask);
	max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);

	/* return the max_cycles value as well if requested */
	if (max_cyc)
		*max_cyc = max_cycles;

	/* Return 50% of the actual maximum, so we can detect bad values */
	max_nsecs >>= 1;

	return max_nsecs;
}

/**
 * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles
 * @cs:         Pointer to clocksource to be updated
 *
 */
static inline void clocksource_update_max_deferment(struct clocksource *cs)
{
	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
						cs->maxadj, cs->mask,
						&cs->max_cycles);
}

#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET

static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
{
	struct clocksource *cs;

	if (!finished_booting || list_empty(&clocksource_list))
		return NULL;

	/*
	 * We pick the clocksource with the highest rating. If oneshot
	 * mode is active, we pick the highres valid clocksource with
	 * the best rating.
	 */
	list_for_each_entry(cs, &clocksource_list, list) {
		if (skipcur && cs == curr_clocksource)
			continue;
		if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
			continue;
		return cs;
	}
	return NULL;
}

static void __clocksource_select(bool skipcur)
{
	bool oneshot = tick_oneshot_mode_active();
	struct clocksource *best, *cs;

	/* Find the best suitable clocksource */
	best = clocksource_find_best(oneshot, skipcur);
	if (!best)
		return;

	/* Check for the override clocksource. */
	list_for_each_entry(cs, &clocksource_list, list) {
		if (skipcur && cs == curr_clocksource)
			continue;
		if (strcmp(cs->name, override_name) != 0)
			continue;
		/*
		 * Check to make sure we don't switch to a non-highres
		 * capable clocksource if the tick code is in oneshot
		 * mode (highres or nohz)
		 */
		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
			/* Override clocksource cannot be used. */
			if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
				pr_warn("Override clocksource %s is unstable and not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
					cs->name);
				override_name[0] = 0;
			} else {
				/*
				 * The override cannot be currently verified.
				 * Deferring to let the watchdog check.
				 */
				pr_info("Override clocksource %s is not currently HRT compatible - deferring\n",
					cs->name);
			}
		} else
			/* Override clocksource can be used. */
			best = cs;
		break;
	}

	if (curr_clocksource != best && !timekeeping_notify(best)) {
		pr_info("Switched to clocksource %s\n", best->name);
		curr_clocksource = best;
	}
}

/**
 * clocksource_select - Select the best clocksource available
 *
 * Private function. Must hold clocksource_mutex when called.
 *
 * Select the clocksource with the best rating, or the clocksource,
 * which is selected by userspace override.
 */
static void clocksource_select(void)
{
	__clocksource_select(false);
}

static void clocksource_select_fallback(void)
{
	__clocksource_select(true);
}

#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
static inline void clocksource_select(void) { }
static inline void clocksource_select_fallback(void) { }

#endif

/*
 * clocksource_done_booting - Called near the end of core bootup
 *
 * Hack to avoid lots of clocksource churn at boot time.
 * We use fs_initcall because we want this to start before
 * device_initcall but after subsys_initcall.
 */
static int __init clocksource_done_booting(void)
{
	mutex_lock(&clocksource_mutex);
	curr_clocksource = clocksource_default_clock();
	finished_booting = 1;
	/*
	 * Run the watchdog first to eliminate unstable clock sources
	 */
	__clocksource_watchdog_kthread();
	clocksource_select();
	mutex_unlock(&clocksource_mutex);
	return 0;
}
fs_initcall(clocksource_done_booting);

/*
 * Enqueue the clocksource sorted by rating
 */
static void clocksource_enqueue(struct clocksource *cs)
{
	struct list_head *entry = &clocksource_list;
	struct clocksource *tmp;

	list_for_each_entry(tmp, &clocksource_list, list) {
		/* Keep track of the place, where to insert */
		if (tmp->rating < cs->rating)
			break;
		entry = &tmp->list;
	}
	list_add(&cs->list, entry);
}

/**
 * __clocksource_update_freq_scale - Used update clocksource with new freq
 * @cs:		clocksource to be registered
 * @scale:	Scale factor multiplied against freq to get clocksource hz
 * @freq:	clocksource frequency (cycles per second) divided by scale
 *
 * This should only be called from the clocksource->enable() method.
 *
 * This *SHOULD NOT* be called directly! Please use the
 * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
 * functions.
 */
void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
	u64 sec;

	/*
	 * Default clocksources are *special* and self-define their mult/shift.
	 * But, you're not special, so you should specify a freq value.
	 */
	if (freq) {
		/*
		 * Calc the maximum number of seconds which we can run before
		 * wrapping around. For clocksources which have a mask > 32-bit
		 * we need to limit the max sleep time to have a good
		 * conversion precision. 10 minutes is still a reasonable
		 * amount. That results in a shift value of 24 for a
		 * clocksource with mask >= 40-bit and f >= 4GHz. That maps to
		 * ~ 0.06ppm granularity for NTP.
		 */
		sec = cs->mask;
		do_div(sec, freq);
		do_div(sec, scale);
		if (!sec)
			sec = 1;
		else if (sec > 600 && cs->mask > UINT_MAX)
			sec = 600;

		clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
				       NSEC_PER_SEC / scale, sec * scale);
	}
	/*
	 * Ensure clocksources that have large 'mult' values don't overflow
	 * when adjusted.
	 */
	cs->maxadj = clocksource_max_adjustment(cs);
	while (freq && ((cs->mult + cs->maxadj < cs->mult)
		|| (cs->mult - cs->maxadj > cs->mult))) {
		cs->mult >>= 1;
		cs->shift--;
		cs->maxadj = clocksource_max_adjustment(cs);
	}

	/*
	 * Only warn for *special* clocksources that self-define
	 * their mult/shift values and don't specify a freq.
	 */
	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
		"timekeeping: Clocksource %s might overflow on 11%% adjustment\n",
		cs->name);

	clocksource_update_max_deferment(cs);

	pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
		cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
}
EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);

/**
 * __clocksource_register_scale - Used to install new clocksources
 * @cs:		clocksource to be registered
 * @scale:	Scale factor multiplied against freq to get clocksource hz
 * @freq:	clocksource frequency (cycles per second) divided by scale
 *
 * Returns -EBUSY if registration fails, zero otherwise.
 *
 * This *SHOULD NOT* be called directly! Please use the
 * clocksource_register_hz() or clocksource_register_khz helper functions.
 */
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{

	/* Initialize mult/shift and max_idle_ns */
	__clocksource_update_freq_scale(cs, scale, freq);

	/* Add clocksource to the clocksource list */
	mutex_lock(&clocksource_mutex);
	clocksource_enqueue(cs);
	clocksource_enqueue_watchdog(cs);
	clocksource_select();
	clocksource_select_watchdog(false);
	mutex_unlock(&clocksource_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(__clocksource_register_scale);

static void __clocksource_change_rating(struct clocksource *cs, int rating)
{
	list_del(&cs->list);
	cs->rating = rating;
	clocksource_enqueue(cs);
}

/**
 * clocksource_change_rating - Change the rating of a registered clocksource
 * @cs:		clocksource to be changed
 * @rating:	new rating
 */
void clocksource_change_rating(struct clocksource *cs, int rating)
{
	mutex_lock(&clocksource_mutex);
	__clocksource_change_rating(cs, rating);
	clocksource_select();
	clocksource_select_watchdog(false);
	mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);

/*
 * Unbind clocksource @cs. Called with clocksource_mutex held
 */
static int clocksource_unbind(struct clocksource *cs)
{
	if (clocksource_is_watchdog(cs)) {
		/* Select and try to install a replacement watchdog. */
		clocksource_select_watchdog(true);
		if (clocksource_is_watchdog(cs))
			return -EBUSY;
	}

	if (cs == curr_clocksource) {
		/* Select and try to install a replacement clock source */
		clocksource_select_fallback();
		if (curr_clocksource == cs)
			return -EBUSY;
	}
	clocksource_dequeue_watchdog(cs);
	list_del_init(&cs->list);
	return 0;
}

/**
 * clocksource_unregister - remove a registered clocksource
 * @cs:	clocksource to be unregistered
 */
int clocksource_unregister(struct clocksource *cs)
{
	int ret = 0;

	mutex_lock(&clocksource_mutex);
	if (!list_empty(&cs->list))
		ret = clocksource_unbind(cs);
	mutex_unlock(&clocksource_mutex);
	return ret;
}
EXPORT_SYMBOL(clocksource_unregister);

#ifdef CONFIG_SYSFS
/**
 * sysfs_show_current_clocksources - sysfs interface for current clocksource
 * @dev:	unused
 * @attr:	unused
 * @buf:	char buffer to be filled with clocksource list
 *
 * Provides sysfs interface for listing current clocksource.
 */
static ssize_t
sysfs_show_current_clocksources(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	ssize_t count = 0;

	mutex_lock(&clocksource_mutex);
	count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name);
	mutex_unlock(&clocksource_mutex);

	return count;
}

ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
{
	size_t ret = cnt;

	/* strings from sysfs write are not 0 terminated! */
	if (!cnt || cnt >= CS_NAME_LEN)
		return -EINVAL;

	/* strip of \n: */
	if (buf[cnt-1] == '\n')
		cnt--;
	if (cnt > 0)
		memcpy(dst, buf, cnt);
	dst[cnt] = 0;
	return ret;
}

/**
 * sysfs_override_clocksource - interface for manually overriding clocksource
 * @dev:	unused
 * @attr:	unused
 * @buf:	name of override clocksource
 * @count:	length of buffer
 *
 * Takes input from sysfs interface for manually overriding the default
 * clocksource selection.
 */
static ssize_t sysfs_override_clocksource(struct device *dev,
					  struct device_attribute *attr,
					  const char *buf, size_t count)
{
	ssize_t ret;

	mutex_lock(&clocksource_mutex);

	ret = sysfs_get_uname(buf, override_name, count);
	if (ret >= 0)
		clocksource_select();

	mutex_unlock(&clocksource_mutex);

	return ret;
}

/**
 * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource
 * @dev:	unused
 * @attr:	unused
 * @buf:	unused
 * @count:	length of buffer
 *
 * Takes input from sysfs interface for manually unbinding a clocksource.
 */
static ssize_t sysfs_unbind_clocksource(struct device *dev,
					struct device_attribute *attr,
					const char *buf, size_t count)
{
	struct clocksource *cs;
	char name[CS_NAME_LEN];
	ssize_t ret;

	ret = sysfs_get_uname(buf, name, count);
	if (ret < 0)
		return ret;

	ret = -ENODEV;
	mutex_lock(&clocksource_mutex);
	list_for_each_entry(cs, &clocksource_list, list) {
		if (strcmp(cs->name, name))
			continue;
		ret = clocksource_unbind(cs);
		break;
	}
	mutex_unlock(&clocksource_mutex);

	return ret ? ret : count;
}

/**
 * sysfs_show_available_clocksources - sysfs interface for listing clocksource
 * @dev:	unused
 * @attr:	unused
 * @buf:	char buffer to be filled with clocksource list
 *
 * Provides sysfs interface for listing registered clocksources
 */
static ssize_t
sysfs_show_available_clocksources(struct device *dev,
				  struct device_attribute *attr,
				  char *buf)
{
	struct clocksource *src;
	ssize_t count = 0;

	mutex_lock(&clocksource_mutex);
	list_for_each_entry(src, &clocksource_list, list) {
		/*
		 * Don't show non-HRES clocksource if the tick code is
		 * in one shot mode (highres=on or nohz=on)
		 */
		if (!tick_oneshot_mode_active() ||
		    (src->flags & CLOCK_SOURCE_VALID_FOR_HRES))
			count += snprintf(buf + count,
				  max((ssize_t)PAGE_SIZE - count, (ssize_t)0),
				  "%s ", src->name);
	}
	mutex_unlock(&clocksource_mutex);

	count += snprintf(buf + count,
			  max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n");

	return count;
}

/*
 * Sysfs setup bits:
 */
static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
		   sysfs_override_clocksource);

static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource);

static DEVICE_ATTR(available_clocksource, 0444,
		   sysfs_show_available_clocksources, NULL);

static struct bus_type clocksource_subsys = {
	.name = "clocksource",
	.dev_name = "clocksource",
};

static struct device device_clocksource = {
	.id	= 0,
	.bus	= &clocksource_subsys,
};

static int __init init_clocksource_sysfs(void)
{
	int error = subsys_system_register(&clocksource_subsys, NULL);

	if (!error)
		error = device_register(&device_clocksource);
	if (!error)
		error = device_create_file(
				&device_clocksource,
				&dev_attr_current_clocksource);
	if (!error)
		error = device_create_file(&device_clocksource,
					   &dev_attr_unbind_clocksource);
	if (!error)
		error = device_create_file(
				&device_clocksource,
				&dev_attr_available_clocksource);
	return error;
}

device_initcall(init_clocksource_sysfs);
#endif /* CONFIG_SYSFS */

/**
 * boot_override_clocksource - boot clock override
 * @str:	override name
 *
 * Takes a clocksource= boot argument and uses it
 * as the clocksource override name.
 */
static int __init boot_override_clocksource(char* str)
{
	mutex_lock(&clocksource_mutex);
	if (str)
		strlcpy(override_name, str, sizeof(override_name));
	mutex_unlock(&clocksource_mutex);
	return 1;
}

__setup("clocksource=", boot_override_clocksource);

/**
 * boot_override_clock - Compatibility layer for deprecated boot option
 * @str:	override name
 *
 * DEPRECATED! Takes a clock= boot argument and uses it
 * as the clocksource override name
 */
static int __init boot_override_clock(char* str)
{
	if (!strcmp(str, "pmtmr")) {
		pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
		return boot_override_clocksource("acpi_pm");
	}
	pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
	return boot_override_clocksource(str);
}

__setup("clock=", boot_override_clock);