summaryrefslogtreecommitdiff
path: root/kernel/hrtimer.c
blob: a6e9d00a8323ffc22c0a1b1397cfb0e02c48907a (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
/*
 *  linux/kernel/hrtimer.c
 *
 *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
 *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
 *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
 *
 *  High-resolution kernel timers
 *
 *  In contrast to the low-resolution timeout API implemented in
 *  kernel/timer.c, hrtimers provide finer resolution and accuracy
 *  depending on system configuration and capabilities.
 *
 *  These timers are currently used for:
 *   - itimers
 *   - POSIX timers
 *   - nanosleep
 *   - precise in-kernel timing
 *
 *  Started by: Thomas Gleixner and Ingo Molnar
 *
 *  Credits:
 *	based on kernel/timer.c
 *
 *	Help, testing, suggestions, bugfixes, improvements were
 *	provided by:
 *
 *	George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
 *	et. al.
 *
 *  For licencing details see kernel-base/COPYING
 */

#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/tick.h>
#include <linux/seq_file.h>
#include <linux/err.h>
#include <linux/debugobjects.h>
#include <linux/sched.h>
#include <linux/timer.h>

#include <asm/uaccess.h>

#include <trace/events/timer.h>

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

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

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

	do {
		seq = read_seqbegin(&xtime_lock);
		xts = current_kernel_time();
		tom = wall_to_monotonic;
	} while (read_seqretry(&xtime_lock, seq));

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

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

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

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


/*
 * Get the preferred target CPU for NOHZ
 */
static int hrtimer_get_target(int this_cpu, int pinned)
{
#ifdef CONFIG_NO_HZ
	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
		int preferred_cpu = get_nohz_load_balancer();

		if (preferred_cpu >= 0)
			return preferred_cpu;
	}
#endif
	return this_cpu;
}

/*
 * With HIGHRES=y we do not migrate the timer when it is expiring
 * before the next event on the target cpu because we cannot reprogram
 * the target cpu hardware and we would cause it to fire late.
 *
 * Called with cpu_base->lock of target cpu held.
 */
static int
hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
{
#ifdef CONFIG_HIGH_RES_TIMERS
	ktime_t expires;

	if (!new_base->cpu_base->hres_active)
		return 0;

	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
	return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
#else
	return 0;
#endif
}

/*
 * Switch the timer base to the current CPU when possible.
 */
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
		    int pinned)
{
	struct hrtimer_clock_base *new_base;
	struct hrtimer_cpu_base *new_cpu_base;
	int this_cpu = smp_processor_id();
	int cpu = hrtimer_get_target(this_cpu, pinned);

again:
	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
	new_base = &new_cpu_base->clock_base[base->index];

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

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

		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
			cpu = this_cpu;
			spin_unlock(&new_base->cpu_base->lock);
			spin_lock(&base->cpu_base->lock);
			timer->base = base;
			goto again;
		}
		timer->base = new_base;
	}
	return new_base;
}

#else /* CONFIG_SMP */

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

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

	return base;
}

# define switch_hrtimer_base(t, b, p)	(b)

#endif	/* !CONFIG_SMP */

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

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

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

	return ktime_add(kt, tmp);
}

EXPORT_SYMBOL_GPL(ktime_add_ns);

/**
 * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable
 * @kt:		minuend
 * @nsec:	the scalar nsec value to subtract
 *
 * Returns the subtraction of @nsec from @kt in ktime_t format
 */
ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec)
{
	ktime_t tmp;

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

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

	return ktime_sub(kt, tmp);
}

EXPORT_SYMBOL_GPL(ktime_sub_ns);
# endif /* !CONFIG_KTIME_SCALAR */

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

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

	return dclc;
}
#endif /* BITS_PER_LONG >= 64 */

/*
 * Add two ktime values and do a safety check for overflow:
 */
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
	ktime_t res = ktime_add(lhs, rhs);

	/*
	 * We use KTIME_SEC_MAX here, the maximum timeout which we can
	 * return to user space in a timespec:
	 */
	if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
		res = ktime_set(KTIME_SEC_MAX, 0);

	return res;
}

EXPORT_SYMBOL_GPL(ktime_add_safe);

#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr hrtimer_debug_descr;

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

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		hrtimer_cancel(timer);
		debug_object_init(timer, &hrtimer_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
{
	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		WARN_ON_ONCE(1);
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

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

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		hrtimer_cancel(timer);
		debug_object_free(timer, &hrtimer_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr hrtimer_debug_descr = {
	.name		= "hrtimer",
	.fixup_init	= hrtimer_fixup_init,
	.fixup_activate	= hrtimer_fixup_activate,
	.fixup_free	= hrtimer_fixup_free,
};

static inline void debug_hrtimer_init(struct hrtimer *timer)
{
	debug_object_init(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_activate(struct hrtimer *timer)
{
	debug_object_activate(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
{
	debug_object_deactivate(timer, &hrtimer_debug_descr);
}

static inline void debug_hrtimer_free(struct hrtimer *timer)
{
	debug_object_free(timer, &hrtimer_debug_descr);
}

static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
			   enum hrtimer_mode mode);

void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
			   enum hrtimer_mode mode)
{
	debug_object_init_on_stack(timer, &hrtimer_debug_descr);
	__hrtimer_init(timer, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);

void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
	debug_object_free(timer, &hrtimer_debug_descr);
}

#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif

static inline void
debug_init(struct hrtimer *timer, clockid_t clockid,
	   enum hrtimer_mode mode)
{
	debug_hrtimer_init(timer);
	trace_hrtimer_init(timer, clockid, mode);
}

static inline void debug_activate(struct hrtimer *timer)
{
	debug_hrtimer_activate(timer);
	trace_hrtimer_start(timer);
}

static inline void debug_deactivate(struct hrtimer *timer)
{
	debug_hrtimer_deactivate(timer);
	trace_hrtimer_cancel(timer);
}

/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS

/*
 * High resolution timer enabled ?
 */
static int hrtimer_hres_enabled __read_mostly  = 1;

/*
 * Enable / Disable high resolution mode
 */
static int __init setup_hrtimer_hres(char *str)
{
	if (!strcmp(str, "off"))
		hrtimer_hres_enabled = 0;
	else if (!strcmp(str, "on"))
		hrtimer_hres_enabled = 1;
	else
		return 0;
	return 1;
}

__setup("highres=", setup_hrtimer_hres);

/*
 * hrtimer_high_res_enabled - query, if the highres mode is enabled
 */
static inline int hrtimer_is_hres_enabled(void)
{
	return hrtimer_hres_enabled;
}

/*
 * Is the high resolution mode active ?
 */
static inline int hrtimer_hres_active(void)
{
	return __get_cpu_var(hrtimer_bases).hres_active;
}

/*
 * Reprogram the event source with checking both queues for the
 * next event
 * Called with interrupts disabled and base->lock held
 */
static void
hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
	int i;
	struct hrtimer_clock_base *base = cpu_base->clock_base;
	ktime_t expires, expires_next;

	expires_next.tv64 = KTIME_MAX;

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

		if (!base->first)
			continue;
		timer = rb_entry(base->first, struct hrtimer, node);
		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
		/*
		 * clock_was_set() has changed base->offset so the
		 * result might be negative. Fix it up to prevent a
		 * false positive in clockevents_program_event()
		 */
		if (expires.tv64 < 0)
			expires.tv64 = 0;
		if (expires.tv64 < expires_next.tv64)
			expires_next = expires;
	}

	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
		return;

	cpu_base->expires_next.tv64 = expires_next.tv64;

	if (cpu_base->expires_next.tv64 != KTIME_MAX)
		tick_program_event(cpu_base->expires_next, 1);
}

/*
 * Shared reprogramming for clock_realtime and clock_monotonic
 *
 * When a timer is enqueued and expires earlier than the already enqueued
 * timers, we have to check, whether it expires earlier than the timer for
 * which the clock event device was armed.
 *
 * Called with interrupts disabled and base->cpu_base.lock held
 */
static int hrtimer_reprogram(struct hrtimer *timer,
			     struct hrtimer_clock_base *base)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
	int res;

	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);

	/*
	 * When the callback is running, we do not reprogram the clock event
	 * device. The timer callback is either running on a different CPU or
	 * the callback is executed in the hrtimer_interrupt context. The
	 * reprogramming is handled either by the softirq, which called the
	 * callback or at the end of the hrtimer_interrupt.
	 */
	if (hrtimer_callback_running(timer))
		return 0;

	/*
	 * CLOCK_REALTIME timer might be requested with an absolute
	 * expiry time which is less than base->offset. Nothing wrong
	 * about that, just avoid to call into the tick code, which
	 * has now objections against negative expiry values.
	 */
	if (expires.tv64 < 0)
		return -ETIME;

	if (expires.tv64 >= cpu_base->expires_next.tv64)
		return 0;

	/*
	 * If a hang was detected in the last timer interrupt then we
	 * do not schedule a timer which is earlier than the expiry
	 * which we enforced in the hang detection. We want the system
	 * to make progress.
	 */
	if (cpu_base->hang_detected)
		return 0;

	/*
	 * Clockevents returns -ETIME, when the event was in the past.
	 */
	res = tick_program_event(expires, 0);
	if (!IS_ERR_VALUE(res))
		cpu_base->expires_next = expires;
	return res;
}


/*
 * Retrigger next event is called after clock was set
 *
 * Called with interrupts disabled via on_each_cpu()
 */
static void retrigger_next_event(void *arg)
{
	struct hrtimer_cpu_base *base;
	struct timespec realtime_offset;
	unsigned long seq;

	if (!hrtimer_hres_active())
		return;

	do {
		seq = read_seqbegin(&xtime_lock);
		set_normalized_timespec(&realtime_offset,
					-wall_to_monotonic.tv_sec,
					-wall_to_monotonic.tv_nsec);
	} while (read_seqretry(&xtime_lock, seq));

	base = &__get_cpu_var(hrtimer_bases);

	/* Adjust CLOCK_REALTIME offset */
	spin_lock(&base->lock);
	base->clock_base[CLOCK_REALTIME].offset =
		timespec_to_ktime(realtime_offset);

	hrtimer_force_reprogram(base, 0);
	spin_unlock(&base->lock);
}

/*
 * Clock realtime was set
 *
 * Change the offset of the realtime clock vs. the monotonic
 * clock.
 *
 * We might have to reprogram the high resolution timer interrupt. On
 * SMP we call the architecture specific code to retrigger _all_ high
 * resolution timer interrupts. On UP we just disable interrupts and
 * call the high resolution interrupt code.
 */
void clock_was_set(void)
{
	/* Retrigger the CPU local events everywhere */
	on_each_cpu(retrigger_next_event, NULL, 1);
}

/*
 * During resume we might have to reprogram the high resolution timer
 * interrupt (on the local CPU):
 */
void hres_timers_resume(void)
{
	WARN_ONCE(!irqs_disabled(),
		  KERN_INFO "hres_timers_resume() called with IRQs enabled!");

	retrigger_next_event(NULL);
}

/*
 * Initialize the high resolution related parts of cpu_base
 */
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
	base->expires_next.tv64 = KTIME_MAX;
	base->hres_active = 0;
}

/*
 * Initialize the high resolution related parts of a hrtimer
 */
static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
{
}


/*
 * When High resolution timers are active, try to reprogram. Note, that in case
 * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
 * check happens. The timer gets enqueued into the rbtree. The reprogramming
 * and expiry check is done in the hrtimer_interrupt or in the softirq.
 */
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
					    struct hrtimer_clock_base *base,
					    int wakeup)
{
	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
		if (wakeup) {
			spin_unlock(&base->cpu_base->lock);
			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
			spin_lock(&base->cpu_base->lock);
		} else
			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);

		return 1;
	}

	return 0;
}

/*
 * Switch to high resolution mode
 */
static int hrtimer_switch_to_hres(void)
{
	int cpu = smp_processor_id();
	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
	unsigned long flags;

	if (base->hres_active)
		return 1;

	local_irq_save(flags);

	if (tick_init_highres()) {
		local_irq_restore(flags);
		printk(KERN_WARNING "Could not switch to high resolution "
				    "mode on CPU %d\n", cpu);
		return 0;
	}
	base->hres_active = 1;
	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;

	tick_setup_sched_timer();

	/* "Retrigger" the interrupt to get things going */
	retrigger_next_event(NULL);
	local_irq_restore(flags);
	return 1;
}

#else

static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
static inline void
hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
					    struct hrtimer_clock_base *base,
					    int wakeup)
{
	return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }

#endif /* CONFIG_HIGH_RES_TIMERS */

#ifdef CONFIG_TIMER_STATS
void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
{
	if (timer->start_site)
		return;

	timer->start_site = addr;
	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
	timer->start_pid = current->pid;
}
#endif

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

/**
 * hrtimer_forward - forward the timer expiry
 * @timer:	hrtimer to forward
 * @now:	forward past this time
 * @interval:	the interval to forward
 *
 * Forward the timer expiry so it will expire in the future.
 * Returns the number of overruns.
 */
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
	u64 orun = 1;
	ktime_t delta;

	delta = ktime_sub(now, hrtimer_get_expires(timer));

	if (delta.tv64 < 0)
		return 0;

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

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

		orun = ktime_divns(delta, incr);
		hrtimer_add_expires_ns(timer, incr * orun);
		if (hrtimer_get_expires_tv64(timer) > now.tv64)
			return orun;
		/*
		 * This (and the ktime_add() below) is the
		 * correction for exact:
		 */
		orun++;
	}
	hrtimer_add_expires(timer, interval);

	return orun;
}
EXPORT_SYMBOL_GPL(hrtimer_forward);

/*
 * enqueue_hrtimer - internal function to (re)start a timer
 *
 * The timer is inserted in expiry order. Insertion into the
 * red black tree is O(log(n)). Must hold the base lock.
 *
 * Returns 1 when the new timer is the leftmost timer in the tree.
 */
static int enqueue_hrtimer(struct hrtimer *timer,
			   struct hrtimer_clock_base *base)
{
	struct rb_node **link = &base->active.rb_node;
	struct rb_node *parent = NULL;
	struct hrtimer *entry;
	int leftmost = 1;

	debug_activate(timer);

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct hrtimer, node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same expiry time stay together.
		 */
		if (hrtimer_get_expires_tv64(timer) <
				hrtimer_get_expires_tv64(entry)) {
			link = &(*link)->rb_left;
		} else {
			link = &(*link)->rb_right;
			leftmost = 0;
		}
	}

	/*
	 * Insert the timer to the rbtree and check whether it
	 * replaces the first pending timer
	 */
	if (leftmost)
		base->first = &timer->node;

	rb_link_node(&timer->node, parent, link);
	rb_insert_color(&timer->node, &base->active);
	/*
	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
	 * state of a possibly running callback.
	 */
	timer->state |= HRTIMER_STATE_ENQUEUED;

	return leftmost;
}

/*
 * __remove_hrtimer - internal function to remove a timer
 *
 * Caller must hold the base lock.
 *
 * High resolution timer mode reprograms the clock event device when the
 * timer is the one which expires next. The caller can disable this by setting
 * reprogram to zero. This is useful, when the context does a reprogramming
 * anyway (e.g. timer interrupt)
 */
static void __remove_hrtimer(struct hrtimer *timer,
			     struct hrtimer_clock_base *base,
			     unsigned long newstate, int reprogram)
{
	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
		goto out;

	/*
	 * Remove the timer from the rbtree and replace the first
	 * entry pointer if necessary.
	 */
	if (base->first == &timer->node) {
		base->first = rb_next(&timer->node);
#ifdef CONFIG_HIGH_RES_TIMERS
		/* Reprogram the clock event device. if enabled */
		if (reprogram && hrtimer_hres_active()) {
			ktime_t expires;

			expires = ktime_sub(hrtimer_get_expires(timer),
					    base->offset);
			if (base->cpu_base->expires_next.tv64 == expires.tv64)
				hrtimer_force_reprogram(base->cpu_base, 1);
		}
#endif
	}
	rb_erase(&timer->node, &base->active);
out:
	timer->state = newstate;
}

/*
 * remove hrtimer, called with base lock held
 */
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
	if (hrtimer_is_queued(timer)) {
		unsigned long state;
		int reprogram;

		/*
		 * Remove the timer and force reprogramming when high
		 * resolution mode is active and the timer is on the current
		 * CPU. If we remove a timer on another CPU, reprogramming is
		 * skipped. The interrupt event on this CPU is fired and
		 * reprogramming happens in the interrupt handler. This is a
		 * rare case and less expensive than a smp call.
		 */
		debug_deactivate(timer);
		timer_stats_hrtimer_clear_start_info(timer);
		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
		/*
		 * We must preserve the CALLBACK state flag here,
		 * otherwise we could move the timer base in
		 * switch_hrtimer_base.
		 */
		state = timer->state & HRTIMER_STATE_CALLBACK;
		__remove_hrtimer(timer, base, state, reprogram);
		return 1;
	}
	return 0;
}

int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
		unsigned long delta_ns, const enum hrtimer_mode mode,
		int wakeup)
{
	struct hrtimer_clock_base *base, *new_base;
	unsigned long flags;
	int ret, leftmost;

	base = lock_hrtimer_base(timer, &flags);

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

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

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

	hrtimer_set_expires_range_ns(timer, tim, delta_ns);

	timer_stats_hrtimer_set_start_info(timer);

	leftmost = enqueue_hrtimer(timer, new_base);

	/*
	 * Only allow reprogramming if the new base is on this CPU.
	 * (it might still be on another CPU if the timer was pending)
	 *
	 * XXX send_remote_softirq() ?
	 */
	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
		hrtimer_enqueue_reprogram(timer, new_base, wakeup);

	unlock_hrtimer_base(timer, &flags);

	return ret;
}

/**
 * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
 * @timer:	the timer to be added
 * @tim:	expiry time
 * @delta_ns:	"slack" range for the timer
 * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
 *
 * Returns:
 *  0 on success
 *  1 when the timer was active
 */
int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
		unsigned long delta_ns, const enum hrtimer_mode mode)
{
	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);

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


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

	base = lock_hrtimer_base(timer, &flags);

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

	unlock_hrtimer_base(timer, &flags);

	return ret;

}
EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);

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

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

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

	base = lock_hrtimer_base(timer, &flags);
	rem = hrtimer_expires_remaining(timer);
	unlock_hrtimer_base(timer, &flags);

	return rem;
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);

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

	spin_lock_irqsave(&cpu_base->lock, flags);

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

			if (!base->first)
				continue;

			timer = rb_entry(base->first, struct hrtimer, node);
			delta.tv64 = hrtimer_get_expires_tv64(timer);
			delta = ktime_sub(delta, base->get_time());
			if (delta.tv64 < mindelta.tv64)
				mindelta.tv64 = delta.tv64;
		}
	}

	spin_unlock_irqrestore(&cpu_base->lock, flags);

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

static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
			   enum hrtimer_mode mode)
{
	struct hrtimer_cpu_base *cpu_base;

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

	cpu_base = &__raw_get_cpu_var(hrtimer_bases);

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

	timer->base = &cpu_base->clock_base[clock_id];
	hrtimer_init_timer_hres(timer);

#ifdef CONFIG_TIMER_STATS
	timer->start_site = NULL;
	timer->start_pid = -1;
	memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
}

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

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

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

	return 0;
}
EXPORT_SYMBOL_GPL(hrtimer_get_res);

static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
{
	struct hrtimer_clock_base *base = timer->base;
	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
	enum hrtimer_restart (*fn)(struct hrtimer *);
	int restart;

	WARN_ON(!irqs_disabled());

	debug_deactivate(timer);
	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
	timer_stats_account_hrtimer(timer);
	fn = timer->function;

	/*
	 * Because we run timers from hardirq context, there is no chance
	 * they get migrated to another cpu, therefore its safe to unlock
	 * the timer base.
	 */
	spin_unlock(&cpu_base->lock);
	trace_hrtimer_expire_entry(timer, now);
	restart = fn(timer);
	trace_hrtimer_expire_exit(timer);
	spin_lock(&cpu_base->lock);

	/*
	 * Note: We clear the CALLBACK bit after enqueue_hrtimer and
	 * we do not reprogramm the event hardware. Happens either in
	 * hrtimer_start_range_ns() or in hrtimer_interrupt()
	 */
	if (restart != HRTIMER_NORESTART) {
		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
		enqueue_hrtimer(timer, base);
	}

	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));

	timer->state &= ~HRTIMER_STATE_CALLBACK;
}

#ifdef CONFIG_HIGH_RES_TIMERS

/*
 * High resolution timer interrupt
 * Called with interrupts disabled
 */
void hrtimer_interrupt(struct clock_event_device *dev)
{
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	struct hrtimer_clock_base *base;
	ktime_t expires_next, now, entry_time, delta;
	int i, retries = 0;

	BUG_ON(!cpu_base->hres_active);
	cpu_base->nr_events++;
	dev->next_event.tv64 = KTIME_MAX;

	entry_time = now = ktime_get();
retry:
	expires_next.tv64 = KTIME_MAX;

	spin_lock(&cpu_base->lock);
	/*
	 * We set expires_next to KTIME_MAX here with cpu_base->lock
	 * held to prevent that a timer is enqueued in our queue via
	 * the migration code. This does not affect enqueueing of
	 * timers which run their callback and need to be requeued on
	 * this CPU.
	 */
	cpu_base->expires_next.tv64 = KTIME_MAX;

	base = cpu_base->clock_base;

	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		ktime_t basenow;
		struct rb_node *node;

		basenow = ktime_add(now, base->offset);

		while ((node = base->first)) {
			struct hrtimer *timer;

			timer = rb_entry(node, struct hrtimer, node);

			/*
			 * The immediate goal for using the softexpires is
			 * minimizing wakeups, not running timers at the
			 * earliest interrupt after their soft expiration.
			 * This allows us to avoid using a Priority Search
			 * Tree, which can answer a stabbing querry for
			 * overlapping intervals and instead use the simple
			 * BST we already have.
			 * We don't add extra wakeups by delaying timers that
			 * are right-of a not yet expired timer, because that
			 * timer will have to trigger a wakeup anyway.
			 */

			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
				ktime_t expires;

				expires = ktime_sub(hrtimer_get_expires(timer),
						    base->offset);
				if (expires.tv64 < expires_next.tv64)
					expires_next = expires;
				break;
			}

			__run_hrtimer(timer, &basenow);
		}
		base++;
	}

	/*
	 * Store the new expiry value so the migration code can verify
	 * against it.
	 */
	cpu_base->expires_next = expires_next;
	spin_unlock(&cpu_base->lock);

	/* Reprogramming necessary ? */
	if (expires_next.tv64 == KTIME_MAX ||
	    !tick_program_event(expires_next, 0)) {
		cpu_base->hang_detected = 0;
		return;
	}

	/*
	 * The next timer was already expired due to:
	 * - tracing
	 * - long lasting callbacks
	 * - being scheduled away when running in a VM
	 *
	 * We need to prevent that we loop forever in the hrtimer
	 * interrupt routine. We give it 3 attempts to avoid
	 * overreacting on some spurious event.
	 */
	now = ktime_get();
	cpu_base->nr_retries++;
	if (++retries < 3)
		goto retry;
	/*
	 * Give the system a chance to do something else than looping
	 * here. We stored the entry time, so we know exactly how long
	 * we spent here. We schedule the next event this amount of
	 * time away.
	 */
	cpu_base->nr_hangs++;
	cpu_base->hang_detected = 1;
	delta = ktime_sub(now, entry_time);
	if (delta.tv64 > cpu_base->max_hang_time.tv64)
		cpu_base->max_hang_time = delta;
	/*
	 * Limit it to a sensible value as we enforce a longer
	 * delay. Give the CPU at least 100ms to catch up.
	 */
	if (delta.tv64 > 100 * NSEC_PER_MSEC)
		expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
	else
		expires_next = ktime_add(now, delta);
	tick_program_event(expires_next, 1);
	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
		    ktime_to_ns(delta));
}

/*
 * local version of hrtimer_peek_ahead_timers() called with interrupts
 * disabled.
 */
static void __hrtimer_peek_ahead_timers(void)
{
	struct tick_device *td;

	if (!hrtimer_hres_active())
		return;

	td = &__get_cpu_var(tick_cpu_device);
	if (td && td->evtdev)
		hrtimer_interrupt(td->evtdev);
}

/**
 * hrtimer_peek_ahead_timers -- run soft-expired timers now
 *
 * hrtimer_peek_ahead_timers will peek at the timer queue of
 * the current cpu and check if there are any timers for which
 * the soft expires time has passed. If any such timers exist,
 * they are run immediately and then removed from the timer queue.
 *
 */
void hrtimer_peek_ahead_timers(void)
{
	unsigned long flags;

	local_irq_save(flags);
	__hrtimer_peek_ahead_timers();
	local_irq_restore(flags);
}

static void run_hrtimer_softirq(struct softirq_action *h)
{
	hrtimer_peek_ahead_timers();
}

#else /* CONFIG_HIGH_RES_TIMERS */

static inline void __hrtimer_peek_ahead_timers(void) { }

#endif	/* !CONFIG_HIGH_RES_TIMERS */

/*
 * Called from timer softirq every jiffy, expire hrtimers:
 *
 * For HRT its the fall back code to run the softirq in the timer
 * softirq context in case the hrtimer initialization failed or has
 * not been done yet.
 */
void hrtimer_run_pending(void)
{
	if (hrtimer_hres_active())
		return;

	/*
	 * This _is_ ugly: We have to check in the softirq context,
	 * whether we can switch to highres and / or nohz mode. The
	 * clocksource switch happens in the timer interrupt with
	 * xtime_lock held. Notification from there only sets the
	 * check bit in the tick_oneshot code, otherwise we might
	 * deadlock vs. xtime_lock.
	 */
	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
		hrtimer_switch_to_hres();
}

/*
 * Called from hardirq context every jiffy
 */
void hrtimer_run_queues(void)
{
	struct rb_node *node;
	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
	struct hrtimer_clock_base *base;
	int index, gettime = 1;

	if (hrtimer_hres_active())
		return;

	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
		base = &cpu_base->clock_base[index];

		if (!base->first)
			continue;

		if (gettime) {
			hrtimer_get_softirq_time(cpu_base);
			gettime = 0;
		}

		spin_lock(&cpu_base->lock);

		while ((node = base->first)) {
			struct hrtimer *timer;

			timer = rb_entry(node, struct hrtimer, node);
			if (base->softirq_time.tv64 <=
					hrtimer_get_expires_tv64(timer))
				break;

			__run_hrtimer(timer, &base->softirq_time);
		}
		spin_unlock(&cpu_base->lock);
	}
}

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

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

	return HRTIMER_NORESTART;
}

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

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

	do {
		set_current_state(TASK_INTERRUPTIBLE);
		hrtimer_start_expires(&t->timer, mode);
		if (!hrtimer_active(&t->timer))
			t->task = NULL;

		if (likely(t->task))
			schedule();

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

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

	__set_current_state(TASK_RUNNING);

	return t->task == NULL;
}

static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
{
	struct timespec rmt;
	ktime_t rem;

	rem = hrtimer_expires_remaining(timer);
	if (rem.tv64 <= 0)
		return 0;
	rmt = ktime_to_timespec(rem);

	if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
		return -EFAULT;

	return 1;
}

long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
{
	struct hrtimer_sleeper t;
	struct timespec __user  *rmtp;
	int ret = 0;

	hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
				HRTIMER_MODE_ABS);
	hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);

	if (do_nanosleep(&t, HRTIMER_MODE_ABS))
		goto out;

	rmtp = restart->nanosleep.rmtp;
	if (rmtp) {
		ret = update_rmtp(&t.timer, rmtp);
		if (ret <= 0)
			goto out;
	}

	/* The other values in restart are already filled in */
	ret = -ERESTART_RESTARTBLOCK;
out:
	destroy_hrtimer_on_stack(&t.timer);
	return ret;
}

long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
		       const enum hrtimer_mode mode, const clockid_t clockid)
{
	struct restart_block *restart;
	struct hrtimer_sleeper t;
	int ret = 0;
	unsigned long slack;

	slack = current->timer_slack_ns;
	if (rt_task(current))
		slack = 0;

	hrtimer_init_on_stack(&t.timer, clockid, mode);
	hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
	if (do_nanosleep(&t, mode))
		goto out;

	/* Absolute timers do not update the rmtp value and restart: */
	if (mode == HRTIMER_MODE_ABS) {
		ret = -ERESTARTNOHAND;
		goto out;
	}

	if (rmtp) {
		ret = update_rmtp(&t.timer, rmtp);
		if (ret <= 0)
			goto out;
	}

	restart = &current_thread_info()->restart_block;
	restart->fn = hrtimer_nanosleep_restart;
	restart->nanosleep.index = t.timer.base->index;
	restart->nanosleep.rmtp = rmtp;
	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);

	ret = -ERESTART_RESTARTBLOCK;
out:
	destroy_hrtimer_on_stack(&t.timer);
	return ret;
}

SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
		struct timespec __user *, rmtp)
{
	struct timespec tu;

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

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

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

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

	spin_lock_init(&cpu_base->lock);

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

	hrtimer_init_hres(cpu_base);
}

#ifdef CONFIG_HOTPLUG_CPU

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

	while ((node = rb_first(&old_base->active))) {
		timer = rb_entry(node, struct hrtimer, node);
		BUG_ON(hrtimer_callback_running(timer));
		debug_deactivate(timer);

		/*
		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
		 * timer could be seen as !active and just vanish away
		 * under us on another CPU
		 */
		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
		timer->base = new_base;
		/*
		 * Enqueue the timers on the new cpu. This does not
		 * reprogram the event device in case the timer
		 * expires before the earliest on this CPU, but we run
		 * hrtimer_interrupt after we migrated everything to
		 * sort out already expired timers and reprogram the
		 * event device.
		 */
		enqueue_hrtimer(timer, new_base);

		/* Clear the migration state bit */
		timer->state &= ~HRTIMER_STATE_MIGRATE;
	}
}

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

	BUG_ON(cpu_online(scpu));
	tick_cancel_sched_timer(scpu);

	local_irq_disable();
	old_base = &per_cpu(hrtimer_bases, scpu);
	new_base = &__get_cpu_var(hrtimer_bases);
	/*
	 * The caller is globally serialized and nobody else
	 * takes two locks at once, deadlock is not possible.
	 */
	spin_lock(&new_base->lock);
	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);

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

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

	/* Check, if we got expired work to do */
	__hrtimer_peek_ahead_timers();
	local_irq_enable();
}

#endif /* CONFIG_HOTPLUG_CPU */

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

	switch (action) {

	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		init_hrtimers_cpu(scpu);
		break;

#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DYING:
	case CPU_DYING_FROZEN:
		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
	{
		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
		migrate_hrtimers(scpu);
		break;
	}
#endif

	default:
		break;
	}

	return NOTIFY_OK;
}

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

void __init hrtimers_init(void)
{
	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
			  (void *)(long)smp_processor_id());
	register_cpu_notifier(&hrtimers_nb);
#ifdef CONFIG_HIGH_RES_TIMERS
	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
}

/**
 * schedule_hrtimeout_range - sleep until timeout
 * @expires:	timeout value (ktime_t)
 * @delta:	slack in expires timeout (ktime_t)
 * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
 *
 * Make the current task sleep until the given expiry time has
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * The @delta argument gives the kernel the freedom to schedule the
 * actual wakeup to a time that is both power and performance friendly.
 * The kernel give the normal best effort behavior for "@expires+@delta",
 * but may decide to fire the timer earlier, but no earlier than @expires.
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
 * pass before the routine returns.
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task.
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Returns 0 when the timer has expired otherwise -EINTR
 */
int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
			       const enum hrtimer_mode mode)
{
	struct hrtimer_sleeper t;

	/*
	 * Optimize when a zero timeout value is given. It does not
	 * matter whether this is an absolute or a relative time.
	 */
	if (expires && !expires->tv64) {
		__set_current_state(TASK_RUNNING);
		return 0;
	}

	/*
	 * A NULL parameter means "inifinte"
	 */
	if (!expires) {
		schedule();
		__set_current_state(TASK_RUNNING);
		return -EINTR;
	}

	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);

	hrtimer_init_sleeper(&t, current);

	hrtimer_start_expires(&t.timer, mode);
	if (!hrtimer_active(&t.timer))
		t.task = NULL;

	if (likely(t.task))
		schedule();

	hrtimer_cancel(&t.timer);
	destroy_hrtimer_on_stack(&t.timer);

	__set_current_state(TASK_RUNNING);

	return !t.task ? 0 : -EINTR;
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);

/**
 * schedule_hrtimeout - sleep until timeout
 * @expires:	timeout value (ktime_t)
 * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
 *
 * Make the current task sleep until the given expiry time has
 * 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 time is guaranteed to
 * pass before the routine returns.
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task.
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Returns 0 when the timer has expired otherwise -EINTR
 */
int __sched schedule_hrtimeout(ktime_t *expires,
			       const enum hrtimer_mode mode)
{
	return schedule_hrtimeout_range(expires, 0, mode);
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout);