summaryrefslogtreecommitdiffstats
path: root/kernel/time/timekeeping.c
blob: f36b02838a4772a7ddaf4064e95a27ab22a6de3f (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
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
/*
 *  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/timekeeper_internal.h>
#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/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/tick.h>
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
#include <linux/compiler.h>

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

#define TK_CLEAR_NTP		(1 << 0)
#define TK_MIRROR		(1 << 1)
#define TK_CLOCK_WAS_SET	(1 << 2)

/*
 * The most important data for readout fits into a single 64 byte
 * cache line.
 */
static struct {
	seqcount_t		seq;
	struct timekeeper	timekeeper;
} tk_core ____cacheline_aligned;

static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;

/**
 * struct tk_fast - NMI safe timekeeper
 * @seq:	Sequence counter for protecting updates. The lowest bit
 *		is the index for the tk_read_base array
 * @base:	tk_read_base array. Access is indexed by the lowest bit of
 *		@seq.
 *
 * See @update_fast_timekeeper() below.
 */
struct tk_fast {
	seqcount_t		seq;
	struct tk_read_base	base[2];
};

static struct tk_fast tk_fast_mono ____cacheline_aligned;

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

/* Flag for if there is a persistent clock on this platform */
bool __read_mostly persistent_clock_exist = false;

static inline void tk_normalize_xtime(struct timekeeper *tk)
{
	while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) {
		tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift;
		tk->xtime_sec++;
	}
}

static inline struct timespec64 tk_xtime(struct timekeeper *tk)
{
	struct timespec64 ts;

	ts.tv_sec = tk->xtime_sec;
	ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
	return ts;
}

static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
	tk->xtime_sec = ts->tv_sec;
	tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift;
}

static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
{
	tk->xtime_sec += ts->tv_sec;
	tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift;
	tk_normalize_xtime(tk);
}

static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
{
	struct timespec64 tmp;

	/*
	 * Verify consistency of: offset_real = -wall_to_monotonic
	 * before modifying anything
	 */
	set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec,
					-tk->wall_to_monotonic.tv_nsec);
	WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64);
	tk->wall_to_monotonic = wtm;
	set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
	tk->offs_real = timespec64_to_ktime(tmp);
	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}

static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
	tk->offs_boot = ktime_add(tk->offs_boot, delta);
}

/**
 * tk_setup_internals - Set up internals to use clocksource clock.
 *
 * @tk:		The target timekeeper to setup.
 * @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 tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
{
	cycle_t interval;
	u64 tmp, ntpinterval;
	struct clocksource *old_clock;

	old_clock = tk->tkr.clock;
	tk->tkr.clock = clock;
	tk->tkr.read = clock->read;
	tk->tkr.mask = clock->mask;
	tk->tkr.cycle_last = tk->tkr.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;
	tk->cycle_interval = interval;

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

	 /* if changing clocks, convert xtime_nsec shift units */
	if (old_clock) {
		int shift_change = clock->shift - old_clock->shift;
		if (shift_change < 0)
			tk->tkr.xtime_nsec >>= -shift_change;
		else
			tk->tkr.xtime_nsec <<= shift_change;
	}
	tk->tkr.shift = clock->shift;

	tk->ntp_error = 0;
	tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
	tk->ntp_tick = ntpinterval << tk->ntp_error_shift;

	/*
	 * The timekeeper keeps its own mult values for the currently
	 * active clocksource. These value will be adjusted via NTP
	 * to counteract clock drifting.
	 */
	tk->tkr.mult = clock->mult;
	tk->ntp_err_mult = 0;
}

/* Timekeeper helper functions. */

#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
static u32 default_arch_gettimeoffset(void) { return 0; }
u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
#else
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif

static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
{
	cycle_t cycle_now, delta;
	s64 nsec;

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

	/* calculate the delta since the last update_wall_time: */
	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);

	nsec = delta * tkr->mult + tkr->xtime_nsec;
	nsec >>= tkr->shift;

	/* If arch requires, add in get_arch_timeoffset() */
	return nsec + arch_gettimeoffset();
}

static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
{
	struct clocksource *clock = tk->tkr.clock;
	cycle_t cycle_now, delta;
	s64 nsec;

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

	/* calculate the delta since the last update_wall_time: */
	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);

	/* convert delta to nanoseconds. */
	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);

	/* If arch requires, add in get_arch_timeoffset() */
	return nsec + arch_gettimeoffset();
}

/**
 * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
 * @tk:		The timekeeper from which we take the update
 * @tkf:	The fast timekeeper to update
 * @tbase:	The time base for the fast timekeeper (mono/raw)
 *
 * We want to use this from any context including NMI and tracing /
 * instrumenting the timekeeping code itself.
 *
 * So we handle this differently than the other timekeeping accessor
 * functions which retry when the sequence count has changed. The
 * update side does:
 *
 * smp_wmb();	<- Ensure that the last base[1] update is visible
 * tkf->seq++;
 * smp_wmb();	<- Ensure that the seqcount update is visible
 * update(tkf->base[0], tk);
 * smp_wmb();	<- Ensure that the base[0] update is visible
 * tkf->seq++;
 * smp_wmb();	<- Ensure that the seqcount update is visible
 * update(tkf->base[1], tk);
 *
 * The reader side does:
 *
 * do {
 *	seq = tkf->seq;
 *	smp_rmb();
 *	idx = seq & 0x01;
 *	now = now(tkf->base[idx]);
 *	smp_rmb();
 * } while (seq != tkf->seq)
 *
 * As long as we update base[0] readers are forced off to
 * base[1]. Once base[0] is updated readers are redirected to base[0]
 * and the base[1] update takes place.
 *
 * So if a NMI hits the update of base[0] then it will use base[1]
 * which is still consistent. In the worst case this can result is a
 * slightly wrong timestamp (a few nanoseconds). See
 * @ktime_get_mono_fast_ns.
 */
static void update_fast_timekeeper(struct timekeeper *tk)
{
	struct tk_read_base *base = tk_fast_mono.base;

	/* Force readers off to base[1] */
	raw_write_seqcount_latch(&tk_fast_mono.seq);

	/* Update base[0] */
	memcpy(base, &tk->tkr, sizeof(*base));

	/* Force readers back to base[0] */
	raw_write_seqcount_latch(&tk_fast_mono.seq);

	/* Update base[1] */
	memcpy(base + 1, base, sizeof(*base));
}

/**
 * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic
 *
 * This timestamp is not guaranteed to be monotonic across an update.
 * The timestamp is calculated by:
 *
 *	now = base_mono + clock_delta * slope
 *
 * So if the update lowers the slope, readers who are forced to the
 * not yet updated second array are still using the old steeper slope.
 *
 * tmono
 * ^
 * |    o  n
 * |   o n
 * |  u
 * | o
 * |o
 * |12345678---> reader order
 *
 * o = old slope
 * u = update
 * n = new slope
 *
 * So reader 6 will observe time going backwards versus reader 5.
 *
 * While other CPUs are likely to be able observe that, the only way
 * for a CPU local observation is when an NMI hits in the middle of
 * the update. Timestamps taken from that NMI context might be ahead
 * of the following timestamps. Callers need to be aware of that and
 * deal with it.
 */
u64 notrace ktime_get_mono_fast_ns(void)
{
	struct tk_read_base *tkr;
	unsigned int seq;
	u64 now;

	do {
		seq = raw_read_seqcount(&tk_fast_mono.seq);
		tkr = tk_fast_mono.base + (seq & 0x01);
		now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr);

	} while (read_seqcount_retry(&tk_fast_mono.seq, seq));
	return now;
}
EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);

#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD

static inline void update_vsyscall(struct timekeeper *tk)
{
	struct timespec xt;

	xt = timespec64_to_timespec(tk_xtime(tk));
	update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->tkr.clock, tk->tkr.mult,
			    tk->tkr.cycle_last);
}

static inline void old_vsyscall_fixup(struct timekeeper *tk)
{
	s64 remainder;

	/*
	* Store only full nanoseconds into xtime_nsec after rounding
	* it up and add the remainder to the error difference.
	* XXX - This is necessary to avoid small 1ns inconsistnecies caused
	* by truncating the remainder in vsyscalls. However, it causes
	* additional work to be done in timekeeping_adjust(). Once
	* the vsyscall implementations are converted to use xtime_nsec
	* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
	* users are removed, this can be killed.
	*/
	remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1);
	tk->tkr.xtime_nsec -= remainder;
	tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift;
	tk->ntp_error += remainder << tk->ntp_error_shift;
	tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift;
}
#else
#define old_vsyscall_fixup(tk)
#endif

static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);

static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
{
	raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
}

/**
 * pvclock_gtod_register_notifier - register a pvclock timedata update listener
 */
int pvclock_gtod_register_notifier(struct notifier_block *nb)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
	update_pvclock_gtod(tk, true);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);

/**
 * pvclock_gtod_unregister_notifier - unregister a pvclock
 * timedata update listener
 */
int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
{
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);

/*
 * Update the ktime_t based scalar nsec members of the timekeeper
 */
static inline void tk_update_ktime_data(struct timekeeper *tk)
{
	s64 nsec;

	/*
	 * The xtime based monotonic readout is:
	 *	nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now();
	 * The ktime based monotonic readout is:
	 *	nsec = base_mono + now();
	 * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec
	 */
	nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
	nsec *= NSEC_PER_SEC;
	nsec += tk->wall_to_monotonic.tv_nsec;
	tk->tkr.base_mono = ns_to_ktime(nsec);

	/* Update the monotonic raw base */
	tk->base_raw = timespec64_to_ktime(tk->raw_time);
}

/* must hold timekeeper_lock */
static void timekeeping_update(struct timekeeper *tk, unsigned int action)
{
	if (action & TK_CLEAR_NTP) {
		tk->ntp_error = 0;
		ntp_clear();
	}
	update_vsyscall(tk);
	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);

	tk_update_ktime_data(tk);

	if (action & TK_MIRROR)
		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
		       sizeof(tk_core.timekeeper));

	update_fast_timekeeper(tk);
}

/**
 * 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(struct timekeeper *tk)
{
	struct clocksource *clock = tk->tkr.clock;
	cycle_t cycle_now, delta;
	s64 nsec;

	cycle_now = tk->tkr.read(clock);
	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);
	tk->tkr.cycle_last = cycle_now;

	tk->tkr.xtime_nsec += delta * tk->tkr.mult;

	/* If arch requires, add in get_arch_timeoffset() */
	tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift;

	tk_normalize_xtime(tk);

	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);
	timespec64_add_ns(&tk->raw_time, nsec);
}

/**
 * __getnstimeofday64 - Returns the time of day in a timespec64.
 * @ts:		pointer to the timespec to be set
 *
 * Updates the time of day in the timespec.
 * Returns 0 on success, or -ve when suspended (timespec will be undefined).
 */
int __getnstimeofday64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	s64 nsecs = 0;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ts->tv_sec = tk->xtime_sec;
		nsecs = timekeeping_get_ns(&tk->tkr);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	ts->tv_nsec = 0;
	timespec64_add_ns(ts, nsecs);

	/*
	 * Do not bail out early, in case there were callers still using
	 * the value, even in the face of the WARN_ON.
	 */
	if (unlikely(timekeeping_suspended))
		return -EAGAIN;
	return 0;
}
EXPORT_SYMBOL(__getnstimeofday64);

/**
 * getnstimeofday64 - Returns the time of day in a timespec64.
 * @ts:		pointer to the timespec to be set
 *
 * Returns the time of day in a timespec (WARN if suspended).
 */
void getnstimeofday64(struct timespec64 *ts)
{
	WARN_ON(__getnstimeofday64(ts));
}
EXPORT_SYMBOL(getnstimeofday64);

ktime_t ktime_get(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	s64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = tk->tkr.base_mono;
		nsecs = timekeeping_get_ns(&tk->tkr);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get);

static ktime_t *offsets[TK_OFFS_MAX] = {
	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
	[TK_OFFS_TAI]	= &tk_core.timekeeper.offs_tai,
};

ktime_t ktime_get_with_offset(enum tk_offsets offs)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base, *offset = offsets[offs];
	s64 nsecs;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = ktime_add(tk->tkr.base_mono, *offset);
		nsecs = timekeeping_get_ns(&tk->tkr);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);

}
EXPORT_SYMBOL_GPL(ktime_get_with_offset);

/**
 * ktime_mono_to_any() - convert mononotic time to any other time
 * @tmono:	time to convert.
 * @offs:	which offset to use
 */
ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
{
	ktime_t *offset = offsets[offs];
	unsigned long seq;
	ktime_t tconv;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		tconv = ktime_add(tmono, *offset);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return tconv;
}
EXPORT_SYMBOL_GPL(ktime_mono_to_any);

/**
 * ktime_get_raw - Returns the raw monotonic time in ktime_t format
 */
ktime_t ktime_get_raw(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	s64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		base = tk->base_raw;
		nsecs = timekeeping_get_ns_raw(tk);

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get_raw);

/**
 * ktime_get_ts64 - get the monotonic clock in timespec64 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_ts64(struct timespec64 *ts)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 tomono;
	s64 nsec;
	unsigned int seq;

	WARN_ON(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		ts->tv_sec = tk->xtime_sec;
		nsec = timekeeping_get_ns(&tk->tkr);
		tomono = tk->wall_to_monotonic;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	ts->tv_sec += tomono.tv_sec;
	ts->tv_nsec = 0;
	timespec64_add_ns(ts, nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);

#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)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	s64 nsecs_raw, nsecs_real;

	WARN_ON_ONCE(timekeeping_suspended);

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		*ts_raw = timespec64_to_timespec(tk->raw_time);
		ts_real->tv_sec = tk->xtime_sec;
		ts_real->tv_nsec = 0;

		nsecs_raw = timekeeping_get_ns_raw(tk);
		nsecs_real = timekeeping_get_ns(&tk->tkr);

	} while (read_seqcount_retry(&tk_core.seq, 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 timespec64 now;

	getnstimeofday64(&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 timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 ts_delta, xt, tmp;
	unsigned long flags;

	if (!timespec_valid_strict(tv))
		return -EINVAL;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	xt = tk_xtime(tk);
	ts_delta.tv_sec = tv->tv_sec - xt.tv_sec;
	ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec;

	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta));

	tmp = timespec_to_timespec64(*tv);
	tk_set_xtime(tk, &tmp);

	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_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)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64 ts64, tmp;
	int ret = 0;

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

	ts64 = timespec_to_timespec64(*ts);

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	/* Make sure the proposed value is valid */
	tmp = timespec64_add(tk_xtime(tk),  ts64);
	if (!timespec64_valid_strict(&tmp)) {
		ret = -EINVAL;
		goto error;
	}

	tk_xtime_add(tk, &ts64);
	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64));

error: /* even if we error out, we forwarded the time, so call update */
	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

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

	return ret;
}
EXPORT_SYMBOL(timekeeping_inject_offset);


/**
 * timekeeping_get_tai_offset - Returns current TAI offset from UTC
 *
 */
s32 timekeeping_get_tai_offset(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	s32 ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		ret = tk->tai_offset;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ret;
}

/**
 * __timekeeping_set_tai_offset - Lock free worker function
 *
 */
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
	tk->tai_offset = tai_offset;
	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}

/**
 * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
 *
 */
void timekeeping_set_tai_offset(s32 tai_offset)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);
	__timekeeping_set_tai_offset(tk, tai_offset);
	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
	clock_was_set();
}

/**
 * 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 timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *new, *old;
	unsigned long flags;

	new = (struct clocksource *) data;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);
	/*
	 * If the cs is in module, get a module reference. Succeeds
	 * for built-in code (owner == NULL) as well.
	 */
	if (try_module_get(new->owner)) {
		if (!new->enable || new->enable(new) == 0) {
			old = tk->tkr.clock;
			tk_setup_internals(tk, new);
			if (old->disable)
				old->disable(old);
			module_put(old->owner);
		} else {
			module_put(new->owner);
		}
	}
	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	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.
 */
int timekeeping_notify(struct clocksource *clock)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	if (tk->tkr.clock == clock)
		return 0;
	stop_machine(change_clocksource, clock, NULL);
	tick_clock_notify();
	return tk->tkr.clock == clock ? 0 : -1;
}

/**
 * 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)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 ts64;
	unsigned long seq;
	s64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);
		nsecs = timekeeping_get_ns_raw(tk);
		ts64 = tk->raw_time;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	timespec64_add_ns(&ts64, nsecs);
	*ts = timespec64_to_timespec(ts64);
}
EXPORT_SYMBOL(getrawmonotonic);

/**
 * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
 */
int timekeeping_valid_for_hres(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	int ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ret;
}

/**
 * timekeeping_max_deferment - Returns max time the clocksource can be deferred
 */
u64 timekeeping_max_deferment(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long seq;
	u64 ret;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		ret = tk->tkr.clock->max_idle_ns;

	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ret;
}

/**
 * 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 __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 __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 timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *clock;
	unsigned long flags;
	struct timespec64 now, boot, tmp;
	struct timespec ts;

	read_persistent_clock(&ts);
	now = timespec_to_timespec64(ts);
	if (!timespec64_valid_strict(&now)) {
		pr_warn("WARNING: Persistent clock returned invalid value!\n"
			"         Check your CMOS/BIOS settings.\n");
		now.tv_sec = 0;
		now.tv_nsec = 0;
	} else if (now.tv_sec || now.tv_nsec)
		persistent_clock_exist = true;

	read_boot_clock(&ts);
	boot = timespec_to_timespec64(ts);
	if (!timespec64_valid_strict(&boot)) {
		pr_warn("WARNING: Boot clock returned invalid value!\n"
			"         Check your CMOS/BIOS settings.\n");
		boot.tv_sec = 0;
		boot.tv_nsec = 0;
	}

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);
	ntp_init();

	clock = clocksource_default_clock();
	if (clock->enable)
		clock->enable(clock);
	tk_setup_internals(tk, clock);

	tk_set_xtime(tk, &now);
	tk->raw_time.tv_sec = 0;
	tk->raw_time.tv_nsec = 0;
	tk->base_raw.tv64 = 0;
	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
		boot = tk_xtime(tk);

	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
	tk_set_wall_to_mono(tk, tmp);

	timekeeping_update(tk, TK_MIRROR);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}

/* time in seconds when suspend began */
static struct timespec64 timekeeping_suspend_time;

/**
 * __timekeeping_inject_sleeptime - Internal function to add sleep interval
 * @delta: pointer to a timespec delta value
 *
 * Takes a timespec offset measuring a suspend interval and properly
 * adds the sleep offset to the timekeeping variables.
 */
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
					   struct timespec64 *delta)
{
	if (!timespec64_valid_strict(delta)) {
		printk_deferred(KERN_WARNING
				"__timekeeping_inject_sleeptime: Invalid "
				"sleep delta value!\n");
		return;
	}
	tk_xtime_add(tk, delta);
	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
	tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
	tk_debug_account_sleep_time(delta);
}

/**
 * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values
 * @delta: pointer to a timespec delta value
 *
 * This hook is for architectures that cannot support read_persistent_clock
 * because their RTC/persistent clock is only accessible when irqs are enabled.
 *
 * This function should only be called by rtc_resume(), and allows
 * a suspend offset to be injected into the timekeeping values.
 */
void timekeeping_inject_sleeptime(struct timespec *delta)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 tmp;
	unsigned long flags;

	/*
	 * Make sure we don't set the clock twice, as timekeeping_resume()
	 * already did it
	 */
	if (has_persistent_clock())
		return;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	timekeeping_forward_now(tk);

	tmp = timespec_to_timespec64(*delta);
	__timekeeping_inject_sleeptime(tk, &tmp);

	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

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

/**
 * timekeeping_resume - Resumes the generic timekeeping subsystem.
 *
 * This is for the generic clocksource timekeeping.
 * xtime/wall_to_monotonic/jiffies/etc are
 * still managed by arch specific suspend/resume code.
 */
static void timekeeping_resume(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct clocksource *clock = tk->tkr.clock;
	unsigned long flags;
	struct timespec64 ts_new, ts_delta;
	struct timespec tmp;
	cycle_t cycle_now, cycle_delta;
	bool suspendtime_found = false;

	read_persistent_clock(&tmp);
	ts_new = timespec_to_timespec64(tmp);

	clockevents_resume();
	clocksource_resume();

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	/*
	 * After system resumes, we need to calculate the suspended time and
	 * compensate it for the OS time. There are 3 sources that could be
	 * used: Nonstop clocksource during suspend, persistent clock and rtc
	 * device.
	 *
	 * One specific platform may have 1 or 2 or all of them, and the
	 * preference will be:
	 *	suspend-nonstop clocksource -> persistent clock -> rtc
	 * The less preferred source will only be tried if there is no better
	 * usable source. The rtc part is handled separately in rtc core code.
	 */
	cycle_now = tk->tkr.read(clock);
	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
		cycle_now > tk->tkr.cycle_last) {
		u64 num, max = ULLONG_MAX;
		u32 mult = clock->mult;
		u32 shift = clock->shift;
		s64 nsec = 0;

		cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last,
						tk->tkr.mask);

		/*
		 * "cycle_delta * mutl" may cause 64 bits overflow, if the
		 * suspended time is too long. In that case we need do the
		 * 64 bits math carefully
		 */
		do_div(max, mult);
		if (cycle_delta > max) {
			num = div64_u64(cycle_delta, max);
			nsec = (((u64) max * mult) >> shift) * num;
			cycle_delta -= num * max;
		}
		nsec += ((u64) cycle_delta * mult) >> shift;

		ts_delta = ns_to_timespec64(nsec);
		suspendtime_found = true;
	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
		suspendtime_found = true;
	}

	if (suspendtime_found)
		__timekeeping_inject_sleeptime(tk, &ts_delta);

	/* Re-base the last cycle value */
	tk->tkr.cycle_last = cycle_now;
	tk->ntp_error = 0;
	timekeeping_suspended = 0;
	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	touch_softlockup_watchdog();

	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);

	/* Resume hrtimers */
	hrtimers_resume();
}

static int timekeeping_suspend(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64		delta, delta_delta;
	static struct timespec64	old_delta;
	struct timespec tmp;

	read_persistent_clock(&tmp);
	timekeeping_suspend_time = timespec_to_timespec64(tmp);

	/*
	 * On some systems the persistent_clock can not be detected at
	 * timekeeping_init by its return value, so if we see a valid
	 * value returned, update the persistent_clock_exists flag.
	 */
	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
		persistent_clock_exist = true;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);
	timekeeping_forward_now(tk);
	timekeeping_suspended = 1;

	/*
	 * To avoid drift caused by repeated suspend/resumes,
	 * which each can add ~1 second drift error,
	 * try to compensate so the difference in system time
	 * and persistent_clock time stays close to constant.
	 */
	delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
	delta_delta = timespec64_sub(delta, old_delta);
	if (abs(delta_delta.tv_sec)  >= 2) {
		/*
		 * if delta_delta is too large, assume time correction
		 * has occured and set old_delta to the current delta.
		 */
		old_delta = delta;
	} else {
		/* Otherwise try to adjust old_system to compensate */
		timekeeping_suspend_time =
			timespec64_add(timekeeping_suspend_time, delta_delta);
	}

	timekeeping_update(tk, TK_MIRROR);
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
	clocksource_suspend();
	clockevents_suspend();

	return 0;
}

/* sysfs resume/suspend bits for timekeeping */
static struct syscore_ops timekeeping_syscore_ops = {
	.resume		= timekeeping_resume,
	.suspend	= timekeeping_suspend,
};

static int __init timekeeping_init_ops(void)
{
	register_syscore_ops(&timekeeping_syscore_ops);
	return 0;
}
device_initcall(timekeeping_init_ops);

/*
 * Apply a multiplier adjustment to the timekeeper
 */
static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
							 s64 offset,
							 bool negative,
							 int adj_scale)
{
	s64 interval = tk->cycle_interval;
	s32 mult_adj = 1;

	if (negative) {
		mult_adj = -mult_adj;
		interval = -interval;
		offset  = -offset;
	}
	mult_adj <<= adj_scale;
	interval <<= adj_scale;
	offset <<= adj_scale;

	/*
	 * So the following can be confusing.
	 *
	 * To keep things simple, lets assume mult_adj == 1 for now.
	 *
	 * When mult_adj != 1, remember that the interval and offset values
	 * have been appropriately scaled so the math is the same.
	 *
	 * The basic idea here is that we're increasing the multiplier
	 * by one, this causes the xtime_interval to be incremented by
	 * one cycle_interval. This is because:
	 *	xtime_interval = cycle_interval * mult
	 * So if mult is being incremented by one:
	 *	xtime_interval = cycle_interval * (mult + 1)
	 * Its the same as:
	 *	xtime_interval = (cycle_interval * mult) + cycle_interval
	 * Which can be shortened to:
	 *	xtime_interval += cycle_interval
	 *
	 * So offset stores the non-accumulated cycles. Thus the current
	 * time (in shifted nanoseconds) is:
	 *	now = (offset * adj) + xtime_nsec
	 * Now, even though we're adjusting the clock frequency, we have
	 * to keep time consistent. In other words, we can't jump back
	 * in time, and we also want to avoid jumping forward in time.
	 *
	 * So given the same offset value, we need the time to be the same
	 * both before and after the freq adjustment.
	 *	now = (offset * adj_1) + xtime_nsec_1
	 *	now = (offset * adj_2) + xtime_nsec_2
	 * So:
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * adj_2) + xtime_nsec_2
	 * And we know:
	 *	adj_2 = adj_1 + 1
	 * So:
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * (adj_1+1)) + xtime_nsec_2
	 *	(offset * adj_1) + xtime_nsec_1 =
	 *		(offset * adj_1) + offset + xtime_nsec_2
	 * Canceling the sides:
	 *	xtime_nsec_1 = offset + xtime_nsec_2
	 * Which gives us:
	 *	xtime_nsec_2 = xtime_nsec_1 - offset
	 * Which simplfies to:
	 *	xtime_nsec -= offset
	 *
	 * XXX - TODO: Doc ntp_error calculation.
	 */
	tk->tkr.mult += mult_adj;
	tk->xtime_interval += interval;
	tk->tkr.xtime_nsec -= offset;
	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
}

/*
 * Calculate the multiplier adjustment needed to match the frequency
 * specified by NTP
 */
static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
							s64 offset)
{
	s64 interval = tk->cycle_interval;
	s64 xinterval = tk->xtime_interval;
	s64 tick_error;
	bool negative;
	u32 adj;

	/* Remove any current error adj from freq calculation */
	if (tk->ntp_err_mult)
		xinterval -= tk->cycle_interval;

	tk->ntp_tick = ntp_tick_length();

	/* Calculate current error per tick */
	tick_error = ntp_tick_length() >> tk->ntp_error_shift;
	tick_error -= (xinterval + tk->xtime_remainder);

	/* Don't worry about correcting it if its small */
	if (likely((tick_error >= 0) && (tick_error <= interval)))
		return;

	/* preserve the direction of correction */
	negative = (tick_error < 0);

	/* Sort out the magnitude of the correction */
	tick_error = abs(tick_error);
	for (adj = 0; tick_error > interval; adj++)
		tick_error >>= 1;

	/* scale the corrections */
	timekeeping_apply_adjustment(tk, offset, negative, adj);
}

/*
 * Adjust the timekeeper's multiplier to the correct frequency
 * and also to reduce the accumulated error value.
 */
static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
{
	/* Correct for the current frequency error */
	timekeeping_freqadjust(tk, offset);

	/* Next make a small adjustment to fix any cumulative error */
	if (!tk->ntp_err_mult && (tk->ntp_error > 0)) {
		tk->ntp_err_mult = 1;
		timekeeping_apply_adjustment(tk, offset, 0, 0);
	} else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) {
		/* Undo any existing error adjustment */
		timekeeping_apply_adjustment(tk, offset, 1, 0);
		tk->ntp_err_mult = 0;
	}

	if (unlikely(tk->tkr.clock->maxadj &&
		(tk->tkr.mult > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) {
		printk_once(KERN_WARNING
			"Adjusting %s more than 11%% (%ld vs %ld)\n",
			tk->tkr.clock->name, (long)tk->tkr.mult,
			(long)tk->tkr.clock->mult + tk->tkr.clock->maxadj);
	}

	/*
	 * It may be possible that when we entered this function, xtime_nsec
	 * was very small.  Further, if we're slightly speeding the clocksource
	 * in the code above, its possible the required corrective factor to
	 * xtime_nsec could cause it to underflow.
	 *
	 * Now, since we already accumulated the second, 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)tk->tkr.xtime_nsec < 0)) {
		s64 neg = -(s64)tk->tkr.xtime_nsec;
		tk->tkr.xtime_nsec = 0;
		tk->ntp_error += neg << tk->ntp_error_shift;
	}
}

/**
 * accumulate_nsecs_to_secs - Accumulates nsecs into secs
 *
 * Helper function that accumulates a the nsecs greater then a second
 * from the xtime_nsec field to the xtime_secs field.
 * It also calls into the NTP code to handle leapsecond processing.
 *
 */
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift;
	unsigned int clock_set = 0;

	while (tk->tkr.xtime_nsec >= nsecps) {
		int leap;

		tk->tkr.xtime_nsec -= nsecps;
		tk->xtime_sec++;

		/* Figure out if its a leap sec and apply if needed */
		leap = second_overflow(tk->xtime_sec);
		if (unlikely(leap)) {
			struct timespec64 ts;

			tk->xtime_sec += leap;

			ts.tv_sec = leap;
			ts.tv_nsec = 0;
			tk_set_wall_to_mono(tk,
				timespec64_sub(tk->wall_to_monotonic, ts));

			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);

			clock_set = TK_CLOCK_WAS_SET;
		}
	}
	return clock_set;
}

/**
 * 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(struct timekeeper *tk, cycle_t offset,
						u32 shift,
						unsigned int *clock_set)
{
	cycle_t interval = tk->cycle_interval << shift;
	u64 raw_nsecs;

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

	/* Accumulate one shifted interval */
	offset -= interval;
	tk->tkr.cycle_last += interval;

	tk->tkr.xtime_nsec += tk->xtime_interval << shift;
	*clock_set |= accumulate_nsecs_to_secs(tk);

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

	/* Accumulate error between NTP and clock interval */
	tk->ntp_error += tk->ntp_tick << shift;
	tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
						(tk->ntp_error_shift + shift);

	return offset;
}

/**
 * update_wall_time - Uses the current clocksource to increment the wall time
 *
 */
void update_wall_time(void)
{
	struct timekeeper *real_tk = &tk_core.timekeeper;
	struct timekeeper *tk = &shadow_timekeeper;
	cycle_t offset;
	int shift = 0, maxshift;
	unsigned int clock_set = 0;
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);

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

#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
	offset = real_tk->cycle_interval;
#else
	offset = clocksource_delta(tk->tkr.read(tk->tkr.clock),
				   tk->tkr.cycle_last, tk->tkr.mask);
#endif

	/* Check if there's really nothing to do */
	if (offset < real_tk->cycle_interval)
		goto out;

	/*
	 * 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 than the offset.  We then accumulate that
	 * chunk in one go, and then try to consume the next smaller
	 * doubled multiple.
	 */
	shift = ilog2(offset) - ilog2(tk->cycle_interval);
	shift = max(0, shift);
	/* Bound shift to one less than what overflows tick_length */
	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
	shift = min(shift, maxshift);
	while (offset >= tk->cycle_interval) {
		offset = logarithmic_accumulation(tk, offset, shift,
							&clock_set);
		if (offset < tk->cycle_interval<<shift)
			shift--;
	}

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

	/*
	 * XXX This can be killed once everyone converts
	 * to the new update_vsyscall.
	 */
	old_vsyscall_fixup(tk);

	/*
	 * Finally, make sure that after the rounding
	 * xtime_nsec isn't larger than NSEC_PER_SEC
	 */
	clock_set |= accumulate_nsecs_to_secs(tk);

	write_seqcount_begin(&tk_core.seq);
	/*
	 * Update the real timekeeper.
	 *
	 * We could avoid this memcpy by switching pointers, but that
	 * requires changes to all other timekeeper usage sites as
	 * well, i.e. move the timekeeper pointer getter into the
	 * spinlocked/seqcount protected sections. And we trade this
	 * memcpy under the tk_core.seq against one before we start
	 * updating.
	 */
	memcpy(real_tk, tk, sizeof(*tk));
	timekeeping_update(real_tk, clock_set);
	write_seqcount_end(&tk_core.seq);
out:
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
	if (clock_set)
		/* Have to call _delayed version, since in irq context*/
		clock_was_set_delayed();
}

/**
 * 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 timekeeper *tk = &tk_core.timekeeper;
	ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);

	*ts = ktime_to_timespec(t);
}
EXPORT_SYMBOL_GPL(getboottime);

unsigned long get_seconds(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return tk->xtime_sec;
}
EXPORT_SYMBOL(get_seconds);

struct timespec __current_kernel_time(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;

	return timespec64_to_timespec(tk_xtime(tk));
}

struct timespec current_kernel_time(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 now;
	unsigned long seq;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		now = tk_xtime(tk);
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return timespec64_to_timespec(now);
}
EXPORT_SYMBOL(current_kernel_time);

struct timespec get_monotonic_coarse(void)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	struct timespec64 now, mono;
	unsigned long seq;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		now = tk_xtime(tk);
		mono = tk->wall_to_monotonic;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
				now.tv_nsec + mono.tv_nsec);

	return timespec64_to_timespec(now);
}

/*
 * Must hold jiffies_lock
 */
void do_timer(unsigned long ticks)
{
	jiffies_64 += ticks;
	calc_global_load(ticks);
}

/**
 * ktime_get_update_offsets_tick - hrtimer helper
 * @offs_real:	pointer to storage for monotonic -> realtime offset
 * @offs_boot:	pointer to storage for monotonic -> boottime offset
 * @offs_tai:	pointer to storage for monotonic -> clock tai offset
 *
 * Returns monotonic time at last tick and various offsets
 */
ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
							ktime_t *offs_tai)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		base = tk->tkr.base_mono;
		nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift;

		*offs_real = tk->offs_real;
		*offs_boot = tk->offs_boot;
		*offs_tai = tk->offs_tai;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}

#ifdef CONFIG_HIGH_RES_TIMERS
/**
 * ktime_get_update_offsets_now - hrtimer helper
 * @offs_real:	pointer to storage for monotonic -> realtime offset
 * @offs_boot:	pointer to storage for monotonic -> boottime offset
 * @offs_tai:	pointer to storage for monotonic -> clock tai offset
 *
 * Returns current monotonic time and updates the offsets
 * Called from hrtimer_interrupt() or retrigger_next_event()
 */
ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
							ktime_t *offs_tai)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned int seq;
	ktime_t base;
	u64 nsecs;

	do {
		seq = read_seqcount_begin(&tk_core.seq);

		base = tk->tkr.base_mono;
		nsecs = timekeeping_get_ns(&tk->tkr);

		*offs_real = tk->offs_real;
		*offs_boot = tk->offs_boot;
		*offs_tai = tk->offs_tai;
	} while (read_seqcount_retry(&tk_core.seq, seq));

	return ktime_add_ns(base, nsecs);
}
#endif

/**
 * do_adjtimex() - Accessor function to NTP __do_adjtimex function
 */
int do_adjtimex(struct timex *txc)
{
	struct timekeeper *tk = &tk_core.timekeeper;
	unsigned long flags;
	struct timespec64 ts;
	s32 orig_tai, tai;
	int ret;

	/* Validate the data before disabling interrupts */
	ret = ntp_validate_timex(txc);
	if (ret)
		return ret;

	if (txc->modes & ADJ_SETOFFSET) {
		struct timespec delta;
		delta.tv_sec  = txc->time.tv_sec;
		delta.tv_nsec = txc->time.tv_usec;
		if (!(txc->modes & ADJ_NANO))
			delta.tv_nsec *= 1000;
		ret = timekeeping_inject_offset(&delta);
		if (ret)
			return ret;
	}

	getnstimeofday64(&ts);

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	orig_tai = tai = tk->tai_offset;
	ret = __do_adjtimex(txc, &ts, &tai);

	if (tai != orig_tai) {
		__timekeeping_set_tai_offset(tk, tai);
		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
	}
	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);

	if (tai != orig_tai)
		clock_was_set();

	ntp_notify_cmos_timer();

	return ret;
}

#ifdef CONFIG_NTP_PPS
/**
 * hardpps() - Accessor function to NTP __hardpps function
 */
void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&timekeeper_lock, flags);
	write_seqcount_begin(&tk_core.seq);

	__hardpps(phase_ts, raw_ts);

	write_seqcount_end(&tk_core.seq);
	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
EXPORT_SYMBOL(hardpps);
#endif

/**
 * 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(&jiffies_lock);
	do_timer(ticks);
	write_sequnlock(&jiffies_lock);
	update_wall_time();
}