summaryrefslogtreecommitdiff
path: root/kernel/time/timer.c
blob: f4465d2a25d132dd7095b654918749fdf9ce31e7 (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
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
/*
 *  linux/kernel/timer.c
 *
 *  Kernel internal timers
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-01-28  Modified by Finn Arne Gangstad to make timers scale better.
 *
 *  1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *              "A Kernel Model for Precision Timekeeping" by Dave Mills
 *  1998-12-24  Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
 *              serialize accesses to xtime/lost_ticks).
 *                              Copyright (C) 1998  Andrea Arcangeli
 *  1999-03-10  Improved NTP compatibility by Ulrich Windl
 *  2002-05-31	Move sys_sysinfo here and make its locking sane, Robert Love
 *  2000-10-05  Implemented scalable SMP per-CPU timer handling.
 *                              Copyright (C) 2000, 2001, 2002  Ingo Molnar
 *              Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
 */

#include <linux/kernel_stat.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/pid_namespace.h>
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/delay.h>
#include <linux/tick.h>
#include <linux/kallsyms.h>
#include <linux/irq_work.h>
#include <linux/sched/signal.h>
#include <linux/sched/sysctl.h>
#include <linux/slab.h>
#include <linux/compat.h>

#include <linux/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>

#include "tick-internal.h"

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

__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;

EXPORT_SYMBOL(jiffies_64);

/*
 * The timer wheel has LVL_DEPTH array levels. Each level provides an array of
 * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
 * level has a different granularity.
 *
 * The level granularity is:		LVL_CLK_DIV ^ lvl
 * The level clock frequency is:	HZ / (LVL_CLK_DIV ^ level)
 *
 * The array level of a newly armed timer depends on the relative expiry
 * time. The farther the expiry time is away the higher the array level and
 * therefor the granularity becomes.
 *
 * Contrary to the original timer wheel implementation, which aims for 'exact'
 * expiry of the timers, this implementation removes the need for recascading
 * the timers into the lower array levels. The previous 'classic' timer wheel
 * implementation of the kernel already violated the 'exact' expiry by adding
 * slack to the expiry time to provide batched expiration. The granularity
 * levels provide implicit batching.
 *
 * This is an optimization of the original timer wheel implementation for the
 * majority of the timer wheel use cases: timeouts. The vast majority of
 * timeout timers (networking, disk I/O ...) are canceled before expiry. If
 * the timeout expires it indicates that normal operation is disturbed, so it
 * does not matter much whether the timeout comes with a slight delay.
 *
 * The only exception to this are networking timers with a small expiry
 * time. They rely on the granularity. Those fit into the first wheel level,
 * which has HZ granularity.
 *
 * We don't have cascading anymore. timers with a expiry time above the
 * capacity of the last wheel level are force expired at the maximum timeout
 * value of the last wheel level. From data sampling we know that the maximum
 * value observed is 5 days (network connection tracking), so this should not
 * be an issue.
 *
 * The currently chosen array constants values are a good compromise between
 * array size and granularity.
 *
 * This results in the following granularity and range levels:
 *
 * HZ 1000 steps
 * Level Offset  Granularity            Range
 *  0      0         1 ms                0 ms -         63 ms
 *  1     64         8 ms               64 ms -        511 ms
 *  2    128        64 ms              512 ms -       4095 ms (512ms - ~4s)
 *  3    192       512 ms             4096 ms -      32767 ms (~4s - ~32s)
 *  4    256      4096 ms (~4s)      32768 ms -     262143 ms (~32s - ~4m)
 *  5    320     32768 ms (~32s)    262144 ms -    2097151 ms (~4m - ~34m)
 *  6    384    262144 ms (~4m)    2097152 ms -   16777215 ms (~34m - ~4h)
 *  7    448   2097152 ms (~34m)  16777216 ms -  134217727 ms (~4h - ~1d)
 *  8    512  16777216 ms (~4h)  134217728 ms - 1073741822 ms (~1d - ~12d)
 *
 * HZ  300
 * Level Offset  Granularity            Range
 *  0	   0         3 ms                0 ms -        210 ms
 *  1	  64        26 ms              213 ms -       1703 ms (213ms - ~1s)
 *  2	 128       213 ms             1706 ms -      13650 ms (~1s - ~13s)
 *  3	 192      1706 ms (~1s)      13653 ms -     109223 ms (~13s - ~1m)
 *  4	 256     13653 ms (~13s)    109226 ms -     873810 ms (~1m - ~14m)
 *  5	 320    109226 ms (~1m)     873813 ms -    6990503 ms (~14m - ~1h)
 *  6	 384    873813 ms (~14m)   6990506 ms -   55924050 ms (~1h - ~15h)
 *  7	 448   6990506 ms (~1h)   55924053 ms -  447392423 ms (~15h - ~5d)
 *  8    512  55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d)
 *
 * HZ  250
 * Level Offset  Granularity            Range
 *  0	   0         4 ms                0 ms -        255 ms
 *  1	  64        32 ms              256 ms -       2047 ms (256ms - ~2s)
 *  2	 128       256 ms             2048 ms -      16383 ms (~2s - ~16s)
 *  3	 192      2048 ms (~2s)      16384 ms -     131071 ms (~16s - ~2m)
 *  4	 256     16384 ms (~16s)    131072 ms -    1048575 ms (~2m - ~17m)
 *  5	 320    131072 ms (~2m)    1048576 ms -    8388607 ms (~17m - ~2h)
 *  6	 384   1048576 ms (~17m)   8388608 ms -   67108863 ms (~2h - ~18h)
 *  7	 448   8388608 ms (~2h)   67108864 ms -  536870911 ms (~18h - ~6d)
 *  8    512  67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d)
 *
 * HZ  100
 * Level Offset  Granularity            Range
 *  0	   0         10 ms               0 ms -        630 ms
 *  1	  64         80 ms             640 ms -       5110 ms (640ms - ~5s)
 *  2	 128        640 ms            5120 ms -      40950 ms (~5s - ~40s)
 *  3	 192       5120 ms (~5s)     40960 ms -     327670 ms (~40s - ~5m)
 *  4	 256      40960 ms (~40s)   327680 ms -    2621430 ms (~5m - ~43m)
 *  5	 320     327680 ms (~5m)   2621440 ms -   20971510 ms (~43m - ~5h)
 *  6	 384    2621440 ms (~43m) 20971520 ms -  167772150 ms (~5h - ~1d)
 *  7	 448   20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d)
 */

/* Clock divisor for the next level */
#define LVL_CLK_SHIFT	3
#define LVL_CLK_DIV	(1UL << LVL_CLK_SHIFT)
#define LVL_CLK_MASK	(LVL_CLK_DIV - 1)
#define LVL_SHIFT(n)	((n) * LVL_CLK_SHIFT)
#define LVL_GRAN(n)	(1UL << LVL_SHIFT(n))

/*
 * The time start value for each level to select the bucket at enqueue
 * time.
 */
#define LVL_START(n)	((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT))

/* Size of each clock level */
#define LVL_BITS	6
#define LVL_SIZE	(1UL << LVL_BITS)
#define LVL_MASK	(LVL_SIZE - 1)
#define LVL_OFFS(n)	((n) * LVL_SIZE)

/* Level depth */
#if HZ > 100
# define LVL_DEPTH	9
# else
# define LVL_DEPTH	8
#endif

/* The cutoff (max. capacity of the wheel) */
#define WHEEL_TIMEOUT_CUTOFF	(LVL_START(LVL_DEPTH))
#define WHEEL_TIMEOUT_MAX	(WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1))

/*
 * The resulting wheel size. If NOHZ is configured we allocate two
 * wheels so we have a separate storage for the deferrable timers.
 */
#define WHEEL_SIZE	(LVL_SIZE * LVL_DEPTH)

#ifdef CONFIG_NO_HZ_COMMON
# define NR_BASES	2
# define BASE_STD	0
# define BASE_DEF	1
#else
# define NR_BASES	1
# define BASE_STD	0
# define BASE_DEF	0
#endif

struct timer_base {
	spinlock_t		lock;
	struct timer_list	*running_timer;
	unsigned long		clk;
	unsigned long		next_expiry;
	unsigned int		cpu;
	bool			migration_enabled;
	bool			nohz_active;
	bool			is_idle;
	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
	struct hlist_head	vectors[WHEEL_SIZE];
} ____cacheline_aligned;

static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
unsigned int sysctl_timer_migration = 1;

void timers_update_migration(bool update_nohz)
{
	bool on = sysctl_timer_migration && tick_nohz_active;
	unsigned int cpu;

	/* Avoid the loop, if nothing to update */
	if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
		return;

	for_each_possible_cpu(cpu) {
		per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
		per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
		per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
		if (!update_nohz)
			continue;
		per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
		per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
		per_cpu(hrtimer_bases.nohz_active, cpu) = true;
	}
}

int timer_migration_handler(struct ctl_table *table, int write,
			    void __user *buffer, size_t *lenp,
			    loff_t *ppos)
{
	static DEFINE_MUTEX(mutex);
	int ret;

	mutex_lock(&mutex);
	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	if (!ret && write)
		timers_update_migration(false);
	mutex_unlock(&mutex);
	return ret;
}
#endif

static unsigned long round_jiffies_common(unsigned long j, int cpu,
		bool force_up)
{
	int rem;
	unsigned long original = j;

	/*
	 * We don't want all cpus firing their timers at once hitting the
	 * same lock or cachelines, so we skew each extra cpu with an extra
	 * 3 jiffies. This 3 jiffies came originally from the mm/ code which
	 * already did this.
	 * The skew is done by adding 3*cpunr, then round, then subtract this
	 * extra offset again.
	 */
	j += cpu * 3;

	rem = j % HZ;

	/*
	 * If the target jiffie is just after a whole second (which can happen
	 * due to delays of the timer irq, long irq off times etc etc) then
	 * we should round down to the whole second, not up. Use 1/4th second
	 * as cutoff for this rounding as an extreme upper bound for this.
	 * But never round down if @force_up is set.
	 */
	if (rem < HZ/4 && !force_up) /* round down */
		j = j - rem;
	else /* round up */
		j = j - rem + HZ;

	/* now that we have rounded, subtract the extra skew again */
	j -= cpu * 3;

	/*
	 * Make sure j is still in the future. Otherwise return the
	 * unmodified value.
	 */
	return time_is_after_jiffies(j) ? j : original;
}

/**
 * __round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * __round_jiffies() rounds an absolute time in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long __round_jiffies(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, false);
}
EXPORT_SYMBOL_GPL(__round_jiffies);

/**
 * __round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * __round_jiffies_relative() rounds a time delta  in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long __round_jiffies_relative(unsigned long j, int cpu)
{
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, false) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_relative);

/**
 * round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
 * round_jiffies() rounds an absolute time in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long round_jiffies(unsigned long j)
{
	return round_jiffies_common(j, raw_smp_processor_id(), false);
}
EXPORT_SYMBOL_GPL(round_jiffies);

/**
 * round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
 * round_jiffies_relative() rounds a time delta  in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long round_jiffies_relative(unsigned long j)
{
	return __round_jiffies_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_relative);

/**
 * __round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, true);
}
EXPORT_SYMBOL_GPL(__round_jiffies_up);

/**
 * __round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
{
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, true) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);

/**
 * round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
 * This is the same as round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up(unsigned long j)
{
	return round_jiffies_common(j, raw_smp_processor_id(), true);
}
EXPORT_SYMBOL_GPL(round_jiffies_up);

/**
 * round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
 * This is the same as round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up_relative(unsigned long j)
{
	return __round_jiffies_up_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_up_relative);


static inline unsigned int timer_get_idx(struct timer_list *timer)
{
	return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT;
}

static inline void timer_set_idx(struct timer_list *timer, unsigned int idx)
{
	timer->flags = (timer->flags & ~TIMER_ARRAYMASK) |
			idx << TIMER_ARRAYSHIFT;
}

/*
 * Helper function to calculate the array index for a given expiry
 * time.
 */
static inline unsigned calc_index(unsigned expires, unsigned lvl)
{
	expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl);
	return LVL_OFFS(lvl) + (expires & LVL_MASK);
}

static int calc_wheel_index(unsigned long expires, unsigned long clk)
{
	unsigned long delta = expires - clk;
	unsigned int idx;

	if (delta < LVL_START(1)) {
		idx = calc_index(expires, 0);
	} else if (delta < LVL_START(2)) {
		idx = calc_index(expires, 1);
	} else if (delta < LVL_START(3)) {
		idx = calc_index(expires, 2);
	} else if (delta < LVL_START(4)) {
		idx = calc_index(expires, 3);
	} else if (delta < LVL_START(5)) {
		idx = calc_index(expires, 4);
	} else if (delta < LVL_START(6)) {
		idx = calc_index(expires, 5);
	} else if (delta < LVL_START(7)) {
		idx = calc_index(expires, 6);
	} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
		idx = calc_index(expires, 7);
	} else if ((long) delta < 0) {
		idx = clk & LVL_MASK;
	} else {
		/*
		 * Force expire obscene large timeouts to expire at the
		 * capacity limit of the wheel.
		 */
		if (expires >= WHEEL_TIMEOUT_CUTOFF)
			expires = WHEEL_TIMEOUT_MAX;

		idx = calc_index(expires, LVL_DEPTH - 1);
	}
	return idx;
}

/*
 * Enqueue the timer into the hash bucket, mark it pending in
 * the bitmap and store the index in the timer flags.
 */
static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
			  unsigned int idx)
{
	hlist_add_head(&timer->entry, base->vectors + idx);
	__set_bit(idx, base->pending_map);
	timer_set_idx(timer, idx);
}

static void
__internal_add_timer(struct timer_base *base, struct timer_list *timer)
{
	unsigned int idx;

	idx = calc_wheel_index(timer->expires, base->clk);
	enqueue_timer(base, timer, idx);
}

static void
trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
{
	if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
		return;

	/*
	 * TODO: This wants some optimizing similar to the code below, but we
	 * will do that when we switch from push to pull for deferrable timers.
	 */
	if (timer->flags & TIMER_DEFERRABLE) {
		if (tick_nohz_full_cpu(base->cpu))
			wake_up_nohz_cpu(base->cpu);
		return;
	}

	/*
	 * We might have to IPI the remote CPU if the base is idle and the
	 * timer is not deferrable. If the other CPU is on the way to idle
	 * then it can't set base->is_idle as we hold the base lock:
	 */
	if (!base->is_idle)
		return;

	/* Check whether this is the new first expiring timer: */
	if (time_after_eq(timer->expires, base->next_expiry))
		return;

	/*
	 * Set the next expiry time and kick the CPU so it can reevaluate the
	 * wheel:
	 */
	base->next_expiry = timer->expires;
		wake_up_nohz_cpu(base->cpu);
}

static void
internal_add_timer(struct timer_base *base, struct timer_list *timer)
{
	__internal_add_timer(base, timer);
	trigger_dyntick_cpu(base, timer);
}

#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr timer_debug_descr;

static void *timer_debug_hint(void *addr)
{
	return ((struct timer_list *) addr)->function;
}

static bool timer_is_static_object(void *addr)
{
	struct timer_list *timer = addr;

	return (timer->entry.pprev == NULL &&
		timer->entry.next == TIMER_ENTRY_STATIC);
}

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static bool timer_fixup_init(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_init(timer, &timer_debug_descr);
		return true;
	default:
		return false;
	}
}

/* Stub timer callback for improperly used timers. */
static void stub_timer(unsigned long data)
{
	WARN_ON(1);
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown non-static object is activated
 */
static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_NOTAVAILABLE:
		setup_timer(timer, stub_timer, 0);
		return true;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return false;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static bool timer_fixup_free(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_free(timer, &timer_debug_descr);
		return true;
	default:
		return false;
	}
}

/*
 * fixup_assert_init is called when:
 * - an untracked/uninit-ed object is found
 */
static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_NOTAVAILABLE:
		setup_timer(timer, stub_timer, 0);
		return true;
	default:
		return false;
	}
}

static struct debug_obj_descr timer_debug_descr = {
	.name			= "timer_list",
	.debug_hint		= timer_debug_hint,
	.is_static_object	= timer_is_static_object,
	.fixup_init		= timer_fixup_init,
	.fixup_activate		= timer_fixup_activate,
	.fixup_free		= timer_fixup_free,
	.fixup_assert_init	= timer_fixup_assert_init,
};

static inline void debug_timer_init(struct timer_list *timer)
{
	debug_object_init(timer, &timer_debug_descr);
}

static inline void debug_timer_activate(struct timer_list *timer)
{
	debug_object_activate(timer, &timer_debug_descr);
}

static inline void debug_timer_deactivate(struct timer_list *timer)
{
	debug_object_deactivate(timer, &timer_debug_descr);
}

static inline void debug_timer_free(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}

static inline void debug_timer_assert_init(struct timer_list *timer)
{
	debug_object_assert_init(timer, &timer_debug_descr);
}

static void do_init_timer(struct timer_list *timer, unsigned int flags,
			  const char *name, struct lock_class_key *key);

void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags,
			     const char *name, struct lock_class_key *key)
{
	debug_object_init_on_stack(timer, &timer_debug_descr);
	do_init_timer(timer, flags, name, key);
}
EXPORT_SYMBOL_GPL(init_timer_on_stack_key);

void destroy_timer_on_stack(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_timer_on_stack);

#else
static inline void debug_timer_init(struct timer_list *timer) { }
static inline void debug_timer_activate(struct timer_list *timer) { }
static inline void debug_timer_deactivate(struct timer_list *timer) { }
static inline void debug_timer_assert_init(struct timer_list *timer) { }
#endif

static inline void debug_init(struct timer_list *timer)
{
	debug_timer_init(timer);
	trace_timer_init(timer);
}

static inline void
debug_activate(struct timer_list *timer, unsigned long expires)
{
	debug_timer_activate(timer);
	trace_timer_start(timer, expires, timer->flags);
}

static inline void debug_deactivate(struct timer_list *timer)
{
	debug_timer_deactivate(timer);
	trace_timer_cancel(timer);
}

static inline void debug_assert_init(struct timer_list *timer)
{
	debug_timer_assert_init(timer);
}

static void do_init_timer(struct timer_list *timer, unsigned int flags,
			  const char *name, struct lock_class_key *key)
{
	timer->entry.pprev = NULL;
	timer->flags = flags | raw_smp_processor_id();
	lockdep_init_map(&timer->lockdep_map, name, key, 0);
}

/**
 * init_timer_key - initialize a timer
 * @timer: the timer to be initialized
 * @flags: timer flags
 * @name: name of the timer
 * @key: lockdep class key of the fake lock used for tracking timer
 *       sync lock dependencies
 *
 * init_timer_key() must be done to a timer prior calling *any* of the
 * other timer functions.
 */
void init_timer_key(struct timer_list *timer, unsigned int flags,
		    const char *name, struct lock_class_key *key)
{
	debug_init(timer);
	do_init_timer(timer, flags, name, key);
}
EXPORT_SYMBOL(init_timer_key);

static inline void detach_timer(struct timer_list *timer, bool clear_pending)
{
	struct hlist_node *entry = &timer->entry;

	debug_deactivate(timer);

	__hlist_del(entry);
	if (clear_pending)
		entry->pprev = NULL;
	entry->next = LIST_POISON2;
}

static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
			     bool clear_pending)
{
	unsigned idx = timer_get_idx(timer);

	if (!timer_pending(timer))
		return 0;

	if (hlist_is_singular_node(&timer->entry, base->vectors + idx))
		__clear_bit(idx, base->pending_map);

	detach_timer(timer, clear_pending);
	return 1;
}

static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
{
	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);

	/*
	 * If the timer is deferrable and nohz is active then we need to use
	 * the deferrable base.
	 */
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
	    (tflags & TIMER_DEFERRABLE))
		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
	return base;
}

static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	/*
	 * If the timer is deferrable and nohz is active then we need to use
	 * the deferrable base.
	 */
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
	    (tflags & TIMER_DEFERRABLE))
		base = this_cpu_ptr(&timer_bases[BASE_DEF]);
	return base;
}

static inline struct timer_base *get_timer_base(u32 tflags)
{
	return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
}

#ifdef CONFIG_NO_HZ_COMMON
static inline struct timer_base *
get_target_base(struct timer_base *base, unsigned tflags)
{
#ifdef CONFIG_SMP
	if ((tflags & TIMER_PINNED) || !base->migration_enabled)
		return get_timer_this_cpu_base(tflags);
	return get_timer_cpu_base(tflags, get_nohz_timer_target());
#else
	return get_timer_this_cpu_base(tflags);
#endif
}

static inline void forward_timer_base(struct timer_base *base)
{
	unsigned long jnow = READ_ONCE(jiffies);

	/*
	 * We only forward the base when it's idle and we have a delta between
	 * base clock and jiffies.
	 */
	if (!base->is_idle || (long) (jnow - base->clk) < 2)
		return;

	/*
	 * If the next expiry value is > jiffies, then we fast forward to
	 * jiffies otherwise we forward to the next expiry value.
	 */
	if (time_after(base->next_expiry, jnow))
		base->clk = jnow;
	else
		base->clk = base->next_expiry;
}
#else
static inline struct timer_base *
get_target_base(struct timer_base *base, unsigned tflags)
{
	return get_timer_this_cpu_base(tflags);
}

static inline void forward_timer_base(struct timer_base *base) { }
#endif


/*
 * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
 * that all timers which are tied to this base are locked, and the base itself
 * is locked too.
 *
 * So __run_timers/migrate_timers can safely modify all timers which could
 * be found in the base->vectors array.
 *
 * When a timer is migrating then the TIMER_MIGRATING flag is set and we need
 * to wait until the migration is done.
 */
static struct timer_base *lock_timer_base(struct timer_list *timer,
					  unsigned long *flags)
	__acquires(timer->base->lock)
{
	for (;;) {
		struct timer_base *base;
		u32 tf;

		/*
		 * We need to use READ_ONCE() here, otherwise the compiler
		 * might re-read @tf between the check for TIMER_MIGRATING
		 * and spin_lock().
		 */
		tf = READ_ONCE(timer->flags);

		if (!(tf & TIMER_MIGRATING)) {
			base = get_timer_base(tf);
			spin_lock_irqsave(&base->lock, *flags);
			if (timer->flags == tf)
				return base;
			spin_unlock_irqrestore(&base->lock, *flags);
		}
		cpu_relax();
	}
}

static inline int
__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
{
	struct timer_base *base, *new_base;
	unsigned int idx = UINT_MAX;
	unsigned long clk = 0, flags;
	int ret = 0;

	BUG_ON(!timer->function);

	/*
	 * This is a common optimization triggered by the networking code - if
	 * the timer is re-modified to have the same timeout or ends up in the
	 * same array bucket then just return:
	 */
	if (timer_pending(timer)) {
		if (timer->expires == expires)
			return 1;

		/*
		 * We lock timer base and calculate the bucket index right
		 * here. If the timer ends up in the same bucket, then we
		 * just update the expiry time and avoid the whole
		 * dequeue/enqueue dance.
		 */
		base = lock_timer_base(timer, &flags);

		clk = base->clk;
		idx = calc_wheel_index(expires, clk);

		/*
		 * Retrieve and compare the array index of the pending
		 * timer. If it matches set the expiry to the new value so a
		 * subsequent call will exit in the expires check above.
		 */
		if (idx == timer_get_idx(timer)) {
			timer->expires = expires;
			ret = 1;
			goto out_unlock;
		}
	} else {
		base = lock_timer_base(timer, &flags);
	}

	ret = detach_if_pending(timer, base, false);
	if (!ret && pending_only)
		goto out_unlock;

	debug_activate(timer, expires);

	new_base = get_target_base(base, timer->flags);

	if (base != new_base) {
		/*
		 * We are trying to schedule the timer on the new base.
		 * However we can't change timer's base while it is running,
		 * otherwise del_timer_sync() can't detect that the timer's
		 * handler yet has not finished. This also guarantees that the
		 * timer is serialized wrt itself.
		 */
		if (likely(base->running_timer != timer)) {
			/* See the comment in lock_timer_base() */
			timer->flags |= TIMER_MIGRATING;

			spin_unlock(&base->lock);
			base = new_base;
			spin_lock(&base->lock);
			WRITE_ONCE(timer->flags,
				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
		}
	}

	/* Try to forward a stale timer base clock */
	forward_timer_base(base);

	timer->expires = expires;
	/*
	 * If 'idx' was calculated above and the base time did not advance
	 * between calculating 'idx' and possibly switching the base, only
	 * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise
	 * we need to (re)calculate the wheel index via
	 * internal_add_timer().
	 */
	if (idx != UINT_MAX && clk == base->clk) {
		enqueue_timer(base, timer, idx);
		trigger_dyntick_cpu(base, timer);
	} else {
		internal_add_timer(base, timer);
	}

out_unlock:
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}

/**
 * mod_timer_pending - modify a pending timer's timeout
 * @timer: the pending timer to be modified
 * @expires: new timeout in jiffies
 *
 * mod_timer_pending() is the same for pending timers as mod_timer(),
 * but will not re-activate and modify already deleted timers.
 *
 * It is useful for unserialized use of timers.
 */
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
{
	return __mod_timer(timer, expires, true);
}
EXPORT_SYMBOL(mod_timer_pending);

/**
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
 * @expires: new timeout in jiffies
 *
 * mod_timer() is a more efficient way to update the expire field of an
 * active timer (if the timer is inactive it will be activated)
 *
 * mod_timer(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 *
 * Note that if there are multiple unserialized concurrent users of the
 * same timer, then mod_timer() is the only safe way to modify the timeout,
 * since add_timer() cannot modify an already running timer.
 *
 * The function returns whether it has modified a pending timer or not.
 * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
 * active timer returns 1.)
 */
int mod_timer(struct timer_list *timer, unsigned long expires)
{
	return __mod_timer(timer, expires, false);
}
EXPORT_SYMBOL(mod_timer);

/**
 * add_timer - start a timer
 * @timer: the timer to be added
 *
 * The kernel will do a ->function(->data) callback from the
 * timer interrupt at the ->expires point in the future. The
 * current time is 'jiffies'.
 *
 * The timer's ->expires, ->function (and if the handler uses it, ->data)
 * fields must be set prior calling this function.
 *
 * Timers with an ->expires field in the past will be executed in the next
 * timer tick.
 */
void add_timer(struct timer_list *timer)
{
	BUG_ON(timer_pending(timer));
	mod_timer(timer, timer->expires);
}
EXPORT_SYMBOL(add_timer);

/**
 * add_timer_on - start a timer on a particular CPU
 * @timer: the timer to be added
 * @cpu: the CPU to start it on
 *
 * This is not very scalable on SMP. Double adds are not possible.
 */
void add_timer_on(struct timer_list *timer, int cpu)
{
	struct timer_base *new_base, *base;
	unsigned long flags;

	BUG_ON(timer_pending(timer) || !timer->function);

	new_base = get_timer_cpu_base(timer->flags, cpu);

	/*
	 * If @timer was on a different CPU, it should be migrated with the
	 * old base locked to prevent other operations proceeding with the
	 * wrong base locked.  See lock_timer_base().
	 */
	base = lock_timer_base(timer, &flags);
	if (base != new_base) {
		timer->flags |= TIMER_MIGRATING;

		spin_unlock(&base->lock);
		base = new_base;
		spin_lock(&base->lock);
		WRITE_ONCE(timer->flags,
			   (timer->flags & ~TIMER_BASEMASK) | cpu);
	}

	debug_activate(timer, timer->expires);
	internal_add_timer(base, timer);
	spin_unlock_irqrestore(&base->lock, flags);
}
EXPORT_SYMBOL_GPL(add_timer_on);

/**
 * del_timer - deactive a timer.
 * @timer: the timer to be deactivated
 *
 * del_timer() deactivates a timer - this works on both active and inactive
 * timers.
 *
 * The function returns whether it has deactivated a pending timer or not.
 * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
 * active timer returns 1.)
 */
int del_timer(struct timer_list *timer)
{
	struct timer_base *base;
	unsigned long flags;
	int ret = 0;

	debug_assert_init(timer);

	if (timer_pending(timer)) {
		base = lock_timer_base(timer, &flags);
		ret = detach_if_pending(timer, base, true);
		spin_unlock_irqrestore(&base->lock, flags);
	}

	return ret;
}
EXPORT_SYMBOL(del_timer);

/**
 * try_to_del_timer_sync - Try to deactivate a timer
 * @timer: timer do del
 *
 * This function tries to deactivate a timer. Upon successful (ret >= 0)
 * exit the timer is not queued and the handler is not running on any CPU.
 */
int try_to_del_timer_sync(struct timer_list *timer)
{
	struct timer_base *base;
	unsigned long flags;
	int ret = -1;

	debug_assert_init(timer);

	base = lock_timer_base(timer, &flags);

	if (base->running_timer != timer)
		ret = detach_if_pending(timer, base, true);

	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}
EXPORT_SYMBOL(try_to_del_timer_sync);

#ifdef CONFIG_SMP
/**
 * del_timer_sync - deactivate a timer and wait for the handler to finish.
 * @timer: the timer to be deactivated
 *
 * This function only differs from del_timer() on SMP: besides deactivating
 * the timer it also makes sure the handler has finished executing on other
 * CPUs.
 *
 * Synchronization rules: Callers must prevent restarting of the timer,
 * otherwise this function is meaningless. It must not be called from
 * interrupt contexts unless the timer is an irqsafe one. The caller must
 * not hold locks which would prevent completion of the timer's
 * handler. The timer's handler must not call add_timer_on(). Upon exit the
 * timer is not queued and the handler is not running on any CPU.
 *
 * Note: For !irqsafe timers, you must not hold locks that are held in
 *   interrupt context while calling this function. Even if the lock has
 *   nothing to do with the timer in question.  Here's why:
 *
 *    CPU0                             CPU1
 *    ----                             ----
 *                                   <SOFTIRQ>
 *                                   call_timer_fn();
 *                                     base->running_timer = mytimer;
 *  spin_lock_irq(somelock);
 *                                     <IRQ>
 *                                        spin_lock(somelock);
 *  del_timer_sync(mytimer);
 *   while (base->running_timer == mytimer);
 *
 * Now del_timer_sync() will never return and never release somelock.
 * The interrupt on the other CPU is waiting to grab somelock but
 * it has interrupted the softirq that CPU0 is waiting to finish.
 *
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
#ifdef CONFIG_LOCKDEP
	unsigned long flags;

	/*
	 * If lockdep gives a backtrace here, please reference
	 * the synchronization rules above.
	 */
	local_irq_save(flags);
	lock_map_acquire(&timer->lockdep_map);
	lock_map_release(&timer->lockdep_map);
	local_irq_restore(flags);
#endif
	/*
	 * don't use it in hardirq context, because it
	 * could lead to deadlock.
	 */
	WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
	for (;;) {
		int ret = try_to_del_timer_sync(timer);
		if (ret >= 0)
			return ret;
		cpu_relax();
	}
}
EXPORT_SYMBOL(del_timer_sync);
#endif

static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
			  unsigned long data)
{
	int count = preempt_count();

#ifdef CONFIG_LOCKDEP
	/*
	 * It is permissible to free the timer from inside the
	 * function that is called from it, this we need to take into
	 * account for lockdep too. To avoid bogus "held lock freed"
	 * warnings as well as problems when looking into
	 * timer->lockdep_map, make a copy and use that here.
	 */
	struct lockdep_map lockdep_map;

	lockdep_copy_map(&lockdep_map, &timer->lockdep_map);
#endif
	/*
	 * Couple the lock chain with the lock chain at
	 * del_timer_sync() by acquiring the lock_map around the fn()
	 * call here and in del_timer_sync().
	 */
	lock_map_acquire(&lockdep_map);

	trace_timer_expire_entry(timer);
	fn(data);
	trace_timer_expire_exit(timer);

	lock_map_release(&lockdep_map);

	if (count != preempt_count()) {
		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
			  fn, count, preempt_count());
		/*
		 * Restore the preempt count. That gives us a decent
		 * chance to survive and extract information. If the
		 * callback kept a lock held, bad luck, but not worse
		 * than the BUG() we had.
		 */
		preempt_count_set(count);
	}
}

static void expire_timers(struct timer_base *base, struct hlist_head *head)
{
	while (!hlist_empty(head)) {
		struct timer_list *timer;
		void (*fn)(unsigned long);
		unsigned long data;

		timer = hlist_entry(head->first, struct timer_list, entry);

		base->running_timer = timer;
		detach_timer(timer, true);

		fn = timer->function;
		data = timer->data;

		if (timer->flags & TIMER_IRQSAFE) {
			spin_unlock(&base->lock);
			call_timer_fn(timer, fn, data);
			spin_lock(&base->lock);
		} else {
			spin_unlock_irq(&base->lock);
			call_timer_fn(timer, fn, data);
			spin_lock_irq(&base->lock);
		}
	}
}

static int __collect_expired_timers(struct timer_base *base,
				    struct hlist_head *heads)
{
	unsigned long clk = base->clk;
	struct hlist_head *vec;
	int i, levels = 0;
	unsigned int idx;

	for (i = 0; i < LVL_DEPTH; i++) {
		idx = (clk & LVL_MASK) + i * LVL_SIZE;

		if (__test_and_clear_bit(idx, base->pending_map)) {
			vec = base->vectors + idx;
			hlist_move_list(vec, heads++);
			levels++;
		}
		/* Is it time to look at the next level? */
		if (clk & LVL_CLK_MASK)
			break;
		/* Shift clock for the next level granularity */
		clk >>= LVL_CLK_SHIFT;
	}
	return levels;
}

#ifdef CONFIG_NO_HZ_COMMON
/*
 * Find the next pending bucket of a level. Search from level start (@offset)
 * + @clk upwards and if nothing there, search from start of the level
 * (@offset) up to @offset + clk.
 */
static int next_pending_bucket(struct timer_base *base, unsigned offset,
			       unsigned clk)
{
	unsigned pos, start = offset + clk;
	unsigned end = offset + LVL_SIZE;

	pos = find_next_bit(base->pending_map, end, start);
	if (pos < end)
		return pos - start;

	pos = find_next_bit(base->pending_map, start, offset);
	return pos < start ? pos + LVL_SIZE - start : -1;
}

/*
 * Search the first expiring timer in the various clock levels. Caller must
 * hold base->lock.
 */
static unsigned long __next_timer_interrupt(struct timer_base *base)
{
	unsigned long clk, next, adj;
	unsigned lvl, offset = 0;

	next = base->clk + NEXT_TIMER_MAX_DELTA;
	clk = base->clk;
	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
		int pos = next_pending_bucket(base, offset, clk & LVL_MASK);

		if (pos >= 0) {
			unsigned long tmp = clk + (unsigned long) pos;

			tmp <<= LVL_SHIFT(lvl);
			if (time_before(tmp, next))
				next = tmp;
		}
		/*
		 * Clock for the next level. If the current level clock lower
		 * bits are zero, we look at the next level as is. If not we
		 * need to advance it by one because that's going to be the
		 * next expiring bucket in that level. base->clk is the next
		 * expiring jiffie. So in case of:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    0    0
		 *
		 * we have to look at all levels @index 0. With
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    0    2
		 *
		 * LVL0 has the next expiring bucket @index 2. The upper
		 * levels have the next expiring bucket @index 1.
		 *
		 * In case that the propagation wraps the next level the same
		 * rules apply:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
		 *  0    0    0    0    F    2
		 *
		 * So after looking at LVL0 we get:
		 *
		 * LVL5 LVL4 LVL3 LVL2 LVL1
		 *  0    0    0    1    0
		 *
		 * So no propagation from LVL1 to LVL2 because that happened
		 * with the add already, but then we need to propagate further
		 * from LVL2 to LVL3.
		 *
		 * So the simple check whether the lower bits of the current
		 * level are 0 or not is sufficient for all cases.
		 */
		adj = clk & LVL_CLK_MASK ? 1 : 0;
		clk >>= LVL_CLK_SHIFT;
		clk += adj;
	}
	return next;
}

/*
 * Check, if the next hrtimer event is before the next timer wheel
 * event:
 */
static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
{
	u64 nextevt = hrtimer_get_next_event();

	/*
	 * If high resolution timers are enabled
	 * hrtimer_get_next_event() returns KTIME_MAX.
	 */
	if (expires <= nextevt)
		return expires;

	/*
	 * If the next timer is already expired, return the tick base
	 * time so the tick is fired immediately.
	 */
	if (nextevt <= basem)
		return basem;

	/*
	 * Round up to the next jiffie. High resolution timers are
	 * off, so the hrtimers are expired in the tick and we need to
	 * make sure that this tick really expires the timer to avoid
	 * a ping pong of the nohz stop code.
	 *
	 * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
	 */
	return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
}

/**
 * get_next_timer_interrupt - return the time (clock mono) of the next timer
 * @basej:	base time jiffies
 * @basem:	base time clock monotonic
 *
 * Returns the tick aligned clock monotonic time of the next pending
 * timer or KTIME_MAX if no timer is pending.
 */
u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
	u64 expires = KTIME_MAX;
	unsigned long nextevt;
	bool is_max_delta;

	/*
	 * Pretend that there is no timer pending if the cpu is offline.
	 * Possible pending timers will be migrated later to an active cpu.
	 */
	if (cpu_is_offline(smp_processor_id()))
		return expires;

	spin_lock(&base->lock);
	nextevt = __next_timer_interrupt(base);
	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
	base->next_expiry = nextevt;
	/*
	 * We have a fresh next event. Check whether we can forward the
	 * base. We can only do that when @basej is past base->clk
	 * otherwise we might rewind base->clk.
	 */
	if (time_after(basej, base->clk)) {
		if (time_after(nextevt, basej))
			base->clk = basej;
		else if (time_after(nextevt, base->clk))
			base->clk = nextevt;
	}

	if (time_before_eq(nextevt, basej)) {
		expires = basem;
		base->is_idle = false;
	} else {
		if (!is_max_delta)
			expires = basem + (nextevt - basej) * TICK_NSEC;
		/*
		 * If we expect to sleep more than a tick, mark the base idle:
		 */
		if ((expires - basem) > TICK_NSEC)
			base->is_idle = true;
	}
	spin_unlock(&base->lock);

	return cmp_next_hrtimer_event(basem, expires);
}

/**
 * timer_clear_idle - Clear the idle state of the timer base
 *
 * Called with interrupts disabled
 */
void timer_clear_idle(void)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	/*
	 * We do this unlocked. The worst outcome is a remote enqueue sending
	 * a pointless IPI, but taking the lock would just make the window for
	 * sending the IPI a few instructions smaller for the cost of taking
	 * the lock in the exit from idle path.
	 */
	base->is_idle = false;
}

static int collect_expired_timers(struct timer_base *base,
				  struct hlist_head *heads)
{
	/*
	 * NOHZ optimization. After a long idle sleep we need to forward the
	 * base to current jiffies. Avoid a loop by searching the bitfield for
	 * the next expiring timer.
	 */
	if ((long)(jiffies - base->clk) > 2) {
		unsigned long next = __next_timer_interrupt(base);

		/*
		 * If the next timer is ahead of time forward to current
		 * jiffies, otherwise forward to the next expiry time:
		 */
		if (time_after(next, jiffies)) {
			/* The call site will increment clock! */
			base->clk = jiffies - 1;
			return 0;
		}
		base->clk = next;
	}
	return __collect_expired_timers(base, heads);
}
#else
static inline int collect_expired_timers(struct timer_base *base,
					 struct hlist_head *heads)
{
	return __collect_expired_timers(base, heads);
}
#endif

/*
 * Called from the timer interrupt handler to charge one tick to the current
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
	struct task_struct *p = current;

	/* Note: this timer irq context must be accounted for as well. */
	account_process_tick(p, user_tick);
	run_local_timers();
	rcu_check_callbacks(user_tick);
#ifdef CONFIG_IRQ_WORK
	if (in_irq())
		irq_work_tick();
#endif
	scheduler_tick();
	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
		run_posix_cpu_timers(p);
}

/**
 * __run_timers - run all expired timers (if any) on this CPU.
 * @base: the timer vector to be processed.
 */
static inline void __run_timers(struct timer_base *base)
{
	struct hlist_head heads[LVL_DEPTH];
	int levels;

	if (!time_after_eq(jiffies, base->clk))
		return;

	spin_lock_irq(&base->lock);

	while (time_after_eq(jiffies, base->clk)) {

		levels = collect_expired_timers(base, heads);
		base->clk++;

		while (levels--)
			expire_timers(base, heads + levels);
	}
	base->running_timer = NULL;
	spin_unlock_irq(&base->lock);
}

/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static __latent_entropy void run_timer_softirq(struct softirq_action *h)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	__run_timers(base);
	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
}

/*
 * Called by the local, per-CPU timer interrupt on SMP.
 */
void run_local_timers(void)
{
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

	hrtimer_run_queues();
	/* Raise the softirq only if required. */
	if (time_before(jiffies, base->clk)) {
		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
			return;
		/* CPU is awake, so check the deferrable base. */
		base++;
		if (time_before(jiffies, base->clk))
			return;
	}
	raise_softirq(TIMER_SOFTIRQ);
}

static void process_timeout(unsigned long __data)
{
	wake_up_process((struct task_struct *)__data);
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns unless the current task is explicitly
 * woken up, (e.g. by wake_up_process())".
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task or the current task is explicitly woken
 * up.
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * Returns 0 when the timer has expired otherwise the remaining time in
 * jiffies will be returned.  In all cases the return value is guaranteed
 * to be non-negative.
 */
signed long __sched schedule_timeout(signed long timeout)
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT:
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default:
		/*
		 * Another bit of PARANOID. Note that the retval will be
		 * 0 since no piece of kernel is supposed to do a check
		 * for a negative retval of schedule_timeout() (since it
		 * should never happens anyway). You just have the printk()
		 * that will tell you if something is gone wrong and where.
		 */
		if (timeout < 0) {
			printk(KERN_ERR "schedule_timeout: wrong timeout "
				"value %lx\n", timeout);
			dump_stack();
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	expire = timeout + jiffies;

	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
	__mod_timer(&timer, expire, false);
	schedule();
	del_singleshot_timer_sync(&timer);

	/* Remove the timer from the object tracker */
	destroy_timer_on_stack(&timer);

	timeout = expire - jiffies;

 out:
	return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);

/*
 * We can use __set_current_state() here because schedule_timeout() calls
 * schedule() unconditionally.
 */
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
	__set_current_state(TASK_INTERRUPTIBLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_interruptible);

signed long __sched schedule_timeout_killable(signed long timeout)
{
	__set_current_state(TASK_KILLABLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_killable);

signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
	__set_current_state(TASK_UNINTERRUPTIBLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);

/*
 * Like schedule_timeout_uninterruptible(), except this task will not contribute
 * to load average.
 */
signed long __sched schedule_timeout_idle(signed long timeout)
{
	__set_current_state(TASK_IDLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_idle);

#ifdef CONFIG_HOTPLUG_CPU
static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head)
{
	struct timer_list *timer;
	int cpu = new_base->cpu;

	while (!hlist_empty(head)) {
		timer = hlist_entry(head->first, struct timer_list, entry);
		detach_timer(timer, false);
		timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
		internal_add_timer(new_base, timer);
	}
}

int timers_dead_cpu(unsigned int cpu)
{
	struct timer_base *old_base;
	struct timer_base *new_base;
	int b, i;

	BUG_ON(cpu_online(cpu));

	for (b = 0; b < NR_BASES; b++) {
		old_base = per_cpu_ptr(&timer_bases[b], cpu);
		new_base = get_cpu_ptr(&timer_bases[b]);
		/*
		 * The caller is globally serialized and nobody else
		 * takes two locks at once, deadlock is not possible.
		 */
		spin_lock_irq(&new_base->lock);
		spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);

		BUG_ON(old_base->running_timer);

		for (i = 0; i < WHEEL_SIZE; i++)
			migrate_timer_list(new_base, old_base->vectors + i);

		spin_unlock(&old_base->lock);
		spin_unlock_irq(&new_base->lock);
		put_cpu_ptr(&timer_bases);
	}
	return 0;
}

#endif /* CONFIG_HOTPLUG_CPU */

static void __init init_timer_cpu(int cpu)
{
	struct timer_base *base;
	int i;

	for (i = 0; i < NR_BASES; i++) {
		base = per_cpu_ptr(&timer_bases[i], cpu);
		base->cpu = cpu;
		spin_lock_init(&base->lock);
		base->clk = jiffies;
	}
}

static void __init init_timer_cpus(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		init_timer_cpu(cpu);
}

void __init init_timers(void)
{
	init_timer_cpus();
	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
}

/**
 * msleep - sleep safely even with waitqueue interruptions
 * @msecs: Time in milliseconds to sleep for
 */
void msleep(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

	while (timeout)
		timeout = schedule_timeout_uninterruptible(timeout);
}

EXPORT_SYMBOL(msleep);

/**
 * msleep_interruptible - sleep waiting for signals
 * @msecs: Time in milliseconds to sleep for
 */
unsigned long msleep_interruptible(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

	while (timeout && !signal_pending(current))
		timeout = schedule_timeout_interruptible(timeout);
	return jiffies_to_msecs(timeout);
}

EXPORT_SYMBOL(msleep_interruptible);

/**
 * usleep_range - Sleep for an approximate time
 * @min: Minimum time in usecs to sleep
 * @max: Maximum time in usecs to sleep
 *
 * In non-atomic context where the exact wakeup time is flexible, use
 * usleep_range() instead of udelay().  The sleep improves responsiveness
 * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
 * power usage by allowing hrtimers to take advantage of an already-
 * scheduled interrupt instead of scheduling a new one just for this sleep.
 */
void __sched usleep_range(unsigned long min, unsigned long max)
{
	ktime_t exp = ktime_add_us(ktime_get(), min);
	u64 delta = (u64)(max - min) * NSEC_PER_USEC;

	for (;;) {
		__set_current_state(TASK_UNINTERRUPTIBLE);
		/* Do not return before the requested sleep time has elapsed */
		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
			break;
	}
}
EXPORT_SYMBOL(usleep_range);