Linux Audio

Check our new training course

Embedded Linux Audio

Check our new training course
with Creative Commons CC-BY-SA
lecture materials

Bootlin logo

Elixir Cross Referencer

Loading...
   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
// SPDX-License-Identifier: GPL-2.0+
/*
 * 2002-10-15  Posix Clocks & timers
 *                           by George Anzinger george@mvista.com
 *			     Copyright (C) 2002 2003 by MontaVista Software.
 *
 * 2004-06-01  Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
 *			     Copyright (C) 2004 Boris Hu
 *
 * These are all the functions necessary to implement POSIX clocks & timers
 */
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/mutex.h>
#include <linux/sched/task.h>

#include <linux/uaccess.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/hash.h>
#include <linux/posix-clock.h>
#include <linux/posix-timers.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <linux/export.h>
#include <linux/hashtable.h>
#include <linux/compat.h>
#include <linux/nospec.h>
#include <linux/time_namespace.h>

#include "timekeeping.h"
#include "posix-timers.h"

static struct kmem_cache *posix_timers_cache;

/*
 * Timers are managed in a hash table for lockless lookup. The hash key is
 * constructed from current::signal and the timer ID and the timer is
 * matched against current::signal and the timer ID when walking the hash
 * bucket list.
 *
 * This allows checkpoint/restore to reconstruct the exact timer IDs for
 * a process.
 */
static DEFINE_HASHTABLE(posix_timers_hashtable, 9);
static DEFINE_SPINLOCK(hash_lock);

static const struct k_clock * const posix_clocks[];
static const struct k_clock *clockid_to_kclock(const clockid_t id);
static const struct k_clock clock_realtime, clock_monotonic;

/* SIGEV_THREAD_ID cannot share a bit with the other SIGEV values. */
#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \
			~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
#endif

static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);

#define lock_timer(tid, flags)						   \
({	struct k_itimer *__timr;					   \
	__cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags));  \
	__timr;								   \
})

static int hash(struct signal_struct *sig, unsigned int nr)
{
	return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable));
}

static struct k_itimer *__posix_timers_find(struct hlist_head *head,
					    struct signal_struct *sig,
					    timer_t id)
{
	struct k_itimer *timer;

	hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&hash_lock)) {
		/* timer->it_signal can be set concurrently */
		if ((READ_ONCE(timer->it_signal) == sig) && (timer->it_id == id))
			return timer;
	}
	return NULL;
}

static struct k_itimer *posix_timer_by_id(timer_t id)
{
	struct signal_struct *sig = current->signal;
	struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)];

	return __posix_timers_find(head, sig, id);
}

static int posix_timer_add(struct k_itimer *timer)
{
	struct signal_struct *sig = current->signal;
	struct hlist_head *head;
	unsigned int cnt, id;

	/*
	 * FIXME: Replace this by a per signal struct xarray once there is
	 * a plan to handle the resulting CRIU regression gracefully.
	 */
	for (cnt = 0; cnt <= INT_MAX; cnt++) {
		spin_lock(&hash_lock);
		id = sig->next_posix_timer_id;

		/* Write the next ID back. Clamp it to the positive space */
		sig->next_posix_timer_id = (id + 1) & INT_MAX;

		head = &posix_timers_hashtable[hash(sig, id)];
		if (!__posix_timers_find(head, sig, id)) {
			hlist_add_head_rcu(&timer->t_hash, head);
			spin_unlock(&hash_lock);
			return id;
		}
		spin_unlock(&hash_lock);
	}
	/* POSIX return code when no timer ID could be allocated */
	return -EAGAIN;
}

static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
{
	spin_unlock_irqrestore(&timr->it_lock, flags);
}

static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_real_ts64(tp);
	return 0;
}

static ktime_t posix_get_realtime_ktime(clockid_t which_clock)
{
	return ktime_get_real();
}

static int posix_clock_realtime_set(const clockid_t which_clock,
				    const struct timespec64 *tp)
{
	return do_sys_settimeofday64(tp, NULL);
}

static int posix_clock_realtime_adj(const clockid_t which_clock,
				    struct __kernel_timex *t)
{
	return do_adjtimex(t);
}

static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_ts64(tp);
	timens_add_monotonic(tp);
	return 0;
}

static ktime_t posix_get_monotonic_ktime(clockid_t which_clock)
{
	return ktime_get();
}

static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_raw_ts64(tp);
	timens_add_monotonic(tp);
	return 0;
}

static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_coarse_real_ts64(tp);
	return 0;
}

static int posix_get_monotonic_coarse(clockid_t which_clock,
						struct timespec64 *tp)
{
	ktime_get_coarse_ts64(tp);
	timens_add_monotonic(tp);
	return 0;
}

static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *tp)
{
	*tp = ktime_to_timespec64(KTIME_LOW_RES);
	return 0;
}

static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_boottime_ts64(tp);
	timens_add_boottime(tp);
	return 0;
}

static ktime_t posix_get_boottime_ktime(const clockid_t which_clock)
{
	return ktime_get_boottime();
}

static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp)
{
	ktime_get_clocktai_ts64(tp);
	return 0;
}

static ktime_t posix_get_tai_ktime(clockid_t which_clock)
{
	return ktime_get_clocktai();
}

static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
{
	tp->tv_sec = 0;
	tp->tv_nsec = hrtimer_resolution;
	return 0;
}

static __init int init_posix_timers(void)
{
	posix_timers_cache = kmem_cache_create("posix_timers_cache",
					sizeof(struct k_itimer), 0,
					SLAB_PANIC | SLAB_ACCOUNT, NULL);
	return 0;
}
__initcall(init_posix_timers);

/*
 * The siginfo si_overrun field and the return value of timer_getoverrun(2)
 * are of type int. Clamp the overrun value to INT_MAX
 */
static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
{
	s64 sum = timr->it_overrun_last + (s64)baseval;

	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
}

static void common_hrtimer_rearm(struct k_itimer *timr)
{
	struct hrtimer *timer = &timr->it.real.timer;

	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
					    timr->it_interval);
	hrtimer_restart(timer);
}

/*
 * This function is called from the signal delivery code if
 * info->si_sys_private is not zero, which indicates that the timer has to
 * be rearmed. Restart the timer and update info::si_overrun.
 */
void posixtimer_rearm(struct kernel_siginfo *info)
{
	struct k_itimer *timr;
	unsigned long flags;

	timr = lock_timer(info->si_tid, &flags);
	if (!timr)
		return;

	if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) {
		timr->kclock->timer_rearm(timr);

		timr->it_active = 1;
		timr->it_overrun_last = timr->it_overrun;
		timr->it_overrun = -1LL;
		++timr->it_requeue_pending;

		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
	}

	unlock_timer(timr, flags);
}

int posix_timer_event(struct k_itimer *timr, int si_private)
{
	enum pid_type type;
	int ret;
	/*
	 * FIXME: if ->sigq is queued we can race with
	 * dequeue_signal()->posixtimer_rearm().
	 *
	 * If dequeue_signal() sees the "right" value of
	 * si_sys_private it calls posixtimer_rearm().
	 * We re-queue ->sigq and drop ->it_lock().
	 * posixtimer_rearm() locks the timer
	 * and re-schedules it while ->sigq is pending.
	 * Not really bad, but not that we want.
	 */
	timr->sigq->info.si_sys_private = si_private;

	type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID;
	ret = send_sigqueue(timr->sigq, timr->it_pid, type);
	/* If we failed to send the signal the timer stops. */
	return ret > 0;
}

/*
 * This function gets called when a POSIX.1b interval timer expires from
 * the HRTIMER interrupt (soft interrupt on RT kernels).
 *
 * Handles CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME and CLOCK_TAI
 * based timers.
 */
static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
{
	enum hrtimer_restart ret = HRTIMER_NORESTART;
	struct k_itimer *timr;
	unsigned long flags;
	int si_private = 0;

	timr = container_of(timer, struct k_itimer, it.real.timer);
	spin_lock_irqsave(&timr->it_lock, flags);

	timr->it_active = 0;
	if (timr->it_interval != 0)
		si_private = ++timr->it_requeue_pending;

	if (posix_timer_event(timr, si_private)) {
		/*
		 * The signal was not queued due to SIG_IGN. As a
		 * consequence the timer is not going to be rearmed from
		 * the signal delivery path. But as a real signal handler
		 * can be installed later the timer must be rearmed here.
		 */
		if (timr->it_interval != 0) {
			ktime_t now = hrtimer_cb_get_time(timer);

			/*
			 * FIXME: What we really want, is to stop this
			 * timer completely and restart it in case the
			 * SIG_IGN is removed. This is a non trivial
			 * change to the signal handling code.
			 *
			 * For now let timers with an interval less than a
			 * jiffie expire every jiffie and recheck for a
			 * valid signal handler.
			 *
			 * This avoids interrupt starvation in case of a
			 * very small interval, which would expire the
			 * timer immediately again.
			 *
			 * Moving now ahead of time by one jiffie tricks
			 * hrtimer_forward() to expire the timer later,
			 * while it still maintains the overrun accuracy
			 * for the price of a slight inconsistency in the
			 * timer_gettime() case. This is at least better
			 * than a timer storm.
			 *
			 * Only required when high resolution timers are
			 * enabled as the periodic tick based timers are
			 * automatically aligned to the next tick.
			 */
			if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS)) {
				ktime_t kj = TICK_NSEC;

				if (timr->it_interval < kj)
					now = ktime_add(now, kj);
			}

			timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval);
			ret = HRTIMER_RESTART;
			++timr->it_requeue_pending;
			timr->it_active = 1;
		}
	}

	unlock_timer(timr, flags);
	return ret;
}

static struct pid *good_sigevent(sigevent_t * event)
{
	struct pid *pid = task_tgid(current);
	struct task_struct *rtn;

	switch (event->sigev_notify) {
	case SIGEV_SIGNAL | SIGEV_THREAD_ID:
		pid = find_vpid(event->sigev_notify_thread_id);
		rtn = pid_task(pid, PIDTYPE_PID);
		if (!rtn || !same_thread_group(rtn, current))
			return NULL;
		fallthrough;
	case SIGEV_SIGNAL:
	case SIGEV_THREAD:
		if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
			return NULL;
		fallthrough;
	case SIGEV_NONE:
		return pid;
	default:
		return NULL;
	}
}

static struct k_itimer * alloc_posix_timer(void)
{
	struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);

	if (!tmr)
		return tmr;
	if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
		kmem_cache_free(posix_timers_cache, tmr);
		return NULL;
	}
	clear_siginfo(&tmr->sigq->info);
	return tmr;
}

static void k_itimer_rcu_free(struct rcu_head *head)
{
	struct k_itimer *tmr = container_of(head, struct k_itimer, rcu);

	kmem_cache_free(posix_timers_cache, tmr);
}

static void posix_timer_free(struct k_itimer *tmr)
{
	put_pid(tmr->it_pid);
	sigqueue_free(tmr->sigq);
	call_rcu(&tmr->rcu, k_itimer_rcu_free);
}

static void posix_timer_unhash_and_free(struct k_itimer *tmr)
{
	spin_lock(&hash_lock);
	hlist_del_rcu(&tmr->t_hash);
	spin_unlock(&hash_lock);
	posix_timer_free(tmr);
}

static int common_timer_create(struct k_itimer *new_timer)
{
	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
	return 0;
}

/* Create a POSIX.1b interval timer. */
static int do_timer_create(clockid_t which_clock, struct sigevent *event,
			   timer_t __user *created_timer_id)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct k_itimer *new_timer;
	int error, new_timer_id;

	if (!kc)
		return -EINVAL;
	if (!kc->timer_create)
		return -EOPNOTSUPP;

	new_timer = alloc_posix_timer();
	if (unlikely(!new_timer))
		return -EAGAIN;

	spin_lock_init(&new_timer->it_lock);

	/*
	 * Add the timer to the hash table. The timer is not yet valid
	 * because new_timer::it_signal is still NULL. The timer id is also
	 * not yet visible to user space.
	 */
	new_timer_id = posix_timer_add(new_timer);
	if (new_timer_id < 0) {
		posix_timer_free(new_timer);
		return new_timer_id;
	}

	new_timer->it_id = (timer_t) new_timer_id;
	new_timer->it_clock = which_clock;
	new_timer->kclock = kc;
	new_timer->it_overrun = -1LL;

	if (event) {
		rcu_read_lock();
		new_timer->it_pid = get_pid(good_sigevent(event));
		rcu_read_unlock();
		if (!new_timer->it_pid) {
			error = -EINVAL;
			goto out;
		}
		new_timer->it_sigev_notify     = event->sigev_notify;
		new_timer->sigq->info.si_signo = event->sigev_signo;
		new_timer->sigq->info.si_value = event->sigev_value;
	} else {
		new_timer->it_sigev_notify     = SIGEV_SIGNAL;
		new_timer->sigq->info.si_signo = SIGALRM;
		memset(&new_timer->sigq->info.si_value, 0, sizeof(sigval_t));
		new_timer->sigq->info.si_value.sival_int = new_timer->it_id;
		new_timer->it_pid = get_pid(task_tgid(current));
	}

	new_timer->sigq->info.si_tid   = new_timer->it_id;
	new_timer->sigq->info.si_code  = SI_TIMER;

	if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) {
		error = -EFAULT;
		goto out;
	}
	/*
	 * After succesful copy out, the timer ID is visible to user space
	 * now but not yet valid because new_timer::signal is still NULL.
	 *
	 * Complete the initialization with the clock specific create
	 * callback.
	 */
	error = kc->timer_create(new_timer);
	if (error)
		goto out;

	spin_lock_irq(&current->sighand->siglock);
	/* This makes the timer valid in the hash table */
	WRITE_ONCE(new_timer->it_signal, current->signal);
	list_add(&new_timer->list, &current->signal->posix_timers);
	spin_unlock_irq(&current->sighand->siglock);
	/*
	 * After unlocking sighand::siglock @new_timer is subject to
	 * concurrent removal and cannot be touched anymore
	 */
	return 0;
out:
	posix_timer_unhash_and_free(new_timer);
	return error;
}

SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
		struct sigevent __user *, timer_event_spec,
		timer_t __user *, created_timer_id)
{
	if (timer_event_spec) {
		sigevent_t event;

		if (copy_from_user(&event, timer_event_spec, sizeof (event)))
			return -EFAULT;
		return do_timer_create(which_clock, &event, created_timer_id);
	}
	return do_timer_create(which_clock, NULL, created_timer_id);
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock,
		       struct compat_sigevent __user *, timer_event_spec,
		       timer_t __user *, created_timer_id)
{
	if (timer_event_spec) {
		sigevent_t event;

		if (get_compat_sigevent(&event, timer_event_spec))
			return -EFAULT;
		return do_timer_create(which_clock, &event, created_timer_id);
	}
	return do_timer_create(which_clock, NULL, created_timer_id);
}
#endif

static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
{
	struct k_itimer *timr;

	/*
	 * timer_t could be any type >= int and we want to make sure any
	 * @timer_id outside positive int range fails lookup.
	 */
	if ((unsigned long long)timer_id > INT_MAX)
		return NULL;

	/*
	 * The hash lookup and the timers are RCU protected.
	 *
	 * Timers are added to the hash in invalid state where
	 * timr::it_signal == NULL. timer::it_signal is only set after the
	 * rest of the initialization succeeded.
	 *
	 * Timer destruction happens in steps:
	 *  1) Set timr::it_signal to NULL with timr::it_lock held
	 *  2) Release timr::it_lock
	 *  3) Remove from the hash under hash_lock
	 *  4) Call RCU for removal after the grace period
	 *
	 * Holding rcu_read_lock() accross the lookup ensures that
	 * the timer cannot be freed.
	 *
	 * The lookup validates locklessly that timr::it_signal ==
	 * current::it_signal and timr::it_id == @timer_id. timr::it_id
	 * can't change, but timr::it_signal becomes NULL during
	 * destruction.
	 */
	rcu_read_lock();
	timr = posix_timer_by_id(timer_id);
	if (timr) {
		spin_lock_irqsave(&timr->it_lock, *flags);
		/*
		 * Validate under timr::it_lock that timr::it_signal is
		 * still valid. Pairs with #1 above.
		 */
		if (timr->it_signal == current->signal) {
			rcu_read_unlock();
			return timr;
		}
		spin_unlock_irqrestore(&timr->it_lock, *flags);
	}
	rcu_read_unlock();

	return NULL;
}

static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now)
{
	struct hrtimer *timer = &timr->it.real.timer;

	return __hrtimer_expires_remaining_adjusted(timer, now);
}

static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
{
	struct hrtimer *timer = &timr->it.real.timer;

	return hrtimer_forward(timer, now, timr->it_interval);
}

/*
 * Get the time remaining on a POSIX.1b interval timer.
 *
 * Two issues to handle here:
 *
 *  1) The timer has a requeue pending. The return value must appear as
 *     if the timer has been requeued right now.
 *
 *  2) The timer is a SIGEV_NONE timer. These timers are never enqueued
 *     into the hrtimer queue and therefore never expired. Emulate expiry
 *     here taking #1 into account.
 */
void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
{
	const struct k_clock *kc = timr->kclock;
	ktime_t now, remaining, iv;
	bool sig_none;

	sig_none = timr->it_sigev_notify == SIGEV_NONE;
	iv = timr->it_interval;

	/* interval timer ? */
	if (iv) {
		cur_setting->it_interval = ktime_to_timespec64(iv);
	} else if (!timr->it_active) {
		/*
		 * SIGEV_NONE oneshot timers are never queued and therefore
		 * timr->it_active is always false. The check below
		 * vs. remaining time will handle this case.
		 *
		 * For all other timers there is nothing to update here, so
		 * return.
		 */
		if (!sig_none)
			return;
	}

	now = kc->clock_get_ktime(timr->it_clock);

	/*
	 * If this is an interval timer and either has requeue pending or
	 * is a SIGEV_NONE timer move the expiry time forward by intervals,
	 * so expiry is > now.
	 */
	if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none))
		timr->it_overrun += kc->timer_forward(timr, now);

	remaining = kc->timer_remaining(timr, now);
	/*
	 * As @now is retrieved before a possible timer_forward() and
	 * cannot be reevaluated by the compiler @remaining is based on the
	 * same @now value. Therefore @remaining is consistent vs. @now.
	 *
	 * Consequently all interval timers, i.e. @iv > 0, cannot have a
	 * remaining time <= 0 because timer_forward() guarantees to move
	 * them forward so that the next timer expiry is > @now.
	 */
	if (remaining <= 0) {
		/*
		 * A single shot SIGEV_NONE timer must return 0, when it is
		 * expired! Timers which have a real signal delivery mode
		 * must return a remaining time greater than 0 because the
		 * signal has not yet been delivered.
		 */
		if (!sig_none)
			cur_setting->it_value.tv_nsec = 1;
	} else {
		cur_setting->it_value = ktime_to_timespec64(remaining);
	}
}

static int do_timer_gettime(timer_t timer_id,  struct itimerspec64 *setting)
{
	const struct k_clock *kc;
	struct k_itimer *timr;
	unsigned long flags;
	int ret = 0;

	timr = lock_timer(timer_id, &flags);
	if (!timr)
		return -EINVAL;

	memset(setting, 0, sizeof(*setting));
	kc = timr->kclock;
	if (WARN_ON_ONCE(!kc || !kc->timer_get))
		ret = -EINVAL;
	else
		kc->timer_get(timr, setting);

	unlock_timer(timr, flags);
	return ret;
}

/* Get the time remaining on a POSIX.1b interval timer. */
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
		struct __kernel_itimerspec __user *, setting)
{
	struct itimerspec64 cur_setting;

	int ret = do_timer_gettime(timer_id, &cur_setting);
	if (!ret) {
		if (put_itimerspec64(&cur_setting, setting))
			ret = -EFAULT;
	}
	return ret;
}

#ifdef CONFIG_COMPAT_32BIT_TIME

SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id,
		struct old_itimerspec32 __user *, setting)
{
	struct itimerspec64 cur_setting;

	int ret = do_timer_gettime(timer_id, &cur_setting);
	if (!ret) {
		if (put_old_itimerspec32(&cur_setting, setting))
			ret = -EFAULT;
	}
	return ret;
}

#endif

/**
 * sys_timer_getoverrun - Get the number of overruns of a POSIX.1b interval timer
 * @timer_id:	The timer ID which identifies the timer
 *
 * The "overrun count" of a timer is one plus the number of expiration
 * intervals which have elapsed between the first expiry, which queues the
 * signal and the actual signal delivery. On signal delivery the "overrun
 * count" is calculated and cached, so it can be returned directly here.
 *
 * As this is relative to the last queued signal the returned overrun count
 * is meaningless outside of the signal delivery path and even there it
 * does not accurately reflect the current state when user space evaluates
 * it.
 *
 * Returns:
 *	-EINVAL		@timer_id is invalid
 *	1..INT_MAX	The number of overruns related to the last delivered signal
 */
SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
{
	struct k_itimer *timr;
	unsigned long flags;
	int overrun;

	timr = lock_timer(timer_id, &flags);
	if (!timr)
		return -EINVAL;

	overrun = timer_overrun_to_int(timr, 0);
	unlock_timer(timr, flags);

	return overrun;
}

static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
			       bool absolute, bool sigev_none)
{
	struct hrtimer *timer = &timr->it.real.timer;
	enum hrtimer_mode mode;

	mode = absolute ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL;
	/*
	 * Posix magic: Relative CLOCK_REALTIME timers are not affected by
	 * clock modifications, so they become CLOCK_MONOTONIC based under the
	 * hood. See hrtimer_init(). Update timr->kclock, so the generic
	 * functions which use timr->kclock->clock_get_*() work.
	 *
	 * Note: it_clock stays unmodified, because the next timer_set() might
	 * use ABSTIME, so it needs to switch back.
	 */
	if (timr->it_clock == CLOCK_REALTIME)
		timr->kclock = absolute ? &clock_realtime : &clock_monotonic;

	hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
	timr->it.real.timer.function = posix_timer_fn;

	if (!absolute)
		expires = ktime_add_safe(expires, timer->base->get_time());
	hrtimer_set_expires(timer, expires);

	if (!sigev_none)
		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}

static int common_hrtimer_try_to_cancel(struct k_itimer *timr)
{
	return hrtimer_try_to_cancel(&timr->it.real.timer);
}

static void common_timer_wait_running(struct k_itimer *timer)
{
	hrtimer_cancel_wait_running(&timer->it.real.timer);
}

/*
 * On PREEMPT_RT this prevents priority inversion and a potential livelock
 * against the ksoftirqd thread in case that ksoftirqd gets preempted while
 * executing a hrtimer callback.
 *
 * See the comments in hrtimer_cancel_wait_running(). For PREEMPT_RT=n this
 * just results in a cpu_relax().
 *
 * For POSIX CPU timers with CONFIG_POSIX_CPU_TIMERS_TASK_WORK=n this is
 * just a cpu_relax(). With CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y this
 * prevents spinning on an eventually scheduled out task and a livelock
 * when the task which tries to delete or disarm the timer has preempted
 * the task which runs the expiry in task work context.
 */
static struct k_itimer *timer_wait_running(struct k_itimer *timer,
					   unsigned long *flags)
{
	const struct k_clock *kc = READ_ONCE(timer->kclock);
	timer_t timer_id = READ_ONCE(timer->it_id);

	/* Prevent kfree(timer) after dropping the lock */
	rcu_read_lock();
	unlock_timer(timer, *flags);

	/*
	 * kc->timer_wait_running() might drop RCU lock. So @timer
	 * cannot be touched anymore after the function returns!
	 */
	if (!WARN_ON_ONCE(!kc->timer_wait_running))
		kc->timer_wait_running(timer);

	rcu_read_unlock();
	/* Relock the timer. It might be not longer hashed. */
	return lock_timer(timer_id, flags);
}

/* Set a POSIX.1b interval timer. */
int common_timer_set(struct k_itimer *timr, int flags,
		     struct itimerspec64 *new_setting,
		     struct itimerspec64 *old_setting)
{
	const struct k_clock *kc = timr->kclock;
	bool sigev_none;
	ktime_t expires;

	if (old_setting)
		common_timer_get(timr, old_setting);

	/* Prevent rearming by clearing the interval */
	timr->it_interval = 0;
	/*
	 * Careful here. On SMP systems the timer expiry function could be
	 * active and spinning on timr->it_lock.
	 */
	if (kc->timer_try_to_cancel(timr) < 0)
		return TIMER_RETRY;

	timr->it_active = 0;
	timr->it_requeue_pending = (timr->it_requeue_pending + 2) &
		~REQUEUE_PENDING;
	timr->it_overrun_last = 0;

	/* Switch off the timer when it_value is zero */
	if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
		return 0;

	timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
	expires = timespec64_to_ktime(new_setting->it_value);
	if (flags & TIMER_ABSTIME)
		expires = timens_ktime_to_host(timr->it_clock, expires);
	sigev_none = timr->it_sigev_notify == SIGEV_NONE;

	kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
	timr->it_active = !sigev_none;
	return 0;
}

static int do_timer_settime(timer_t timer_id, int tmr_flags,
			    struct itimerspec64 *new_spec64,
			    struct itimerspec64 *old_spec64)
{
	const struct k_clock *kc;
	struct k_itimer *timr;
	unsigned long flags;
	int error = 0;

	if (!timespec64_valid(&new_spec64->it_interval) ||
	    !timespec64_valid(&new_spec64->it_value))
		return -EINVAL;

	if (old_spec64)
		memset(old_spec64, 0, sizeof(*old_spec64));

	timr = lock_timer(timer_id, &flags);
retry:
	if (!timr)
		return -EINVAL;

	kc = timr->kclock;
	if (WARN_ON_ONCE(!kc || !kc->timer_set))
		error = -EINVAL;
	else
		error = kc->timer_set(timr, tmr_flags, new_spec64, old_spec64);

	if (error == TIMER_RETRY) {
		// We already got the old time...
		old_spec64 = NULL;
		/* Unlocks and relocks the timer if it still exists */
		timr = timer_wait_running(timr, &flags);
		goto retry;
	}
	unlock_timer(timr, flags);

	return error;
}

/* Set a POSIX.1b interval timer */
SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
		const struct __kernel_itimerspec __user *, new_setting,
		struct __kernel_itimerspec __user *, old_setting)
{
	struct itimerspec64 new_spec, old_spec, *rtn;
	int error = 0;

	if (!new_setting)
		return -EINVAL;

	if (get_itimerspec64(&new_spec, new_setting))
		return -EFAULT;

	rtn = old_setting ? &old_spec : NULL;
	error = do_timer_settime(timer_id, flags, &new_spec, rtn);
	if (!error && old_setting) {
		if (put_itimerspec64(&old_spec, old_setting))
			error = -EFAULT;
	}
	return error;
}

#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags,
		struct old_itimerspec32 __user *, new,
		struct old_itimerspec32 __user *, old)
{
	struct itimerspec64 new_spec, old_spec;
	struct itimerspec64 *rtn = old ? &old_spec : NULL;
	int error = 0;

	if (!new)
		return -EINVAL;
	if (get_old_itimerspec32(&new_spec, new))
		return -EFAULT;

	error = do_timer_settime(timer_id, flags, &new_spec, rtn);
	if (!error && old) {
		if (put_old_itimerspec32(&old_spec, old))
			error = -EFAULT;
	}
	return error;
}
#endif

int common_timer_del(struct k_itimer *timer)
{
	const struct k_clock *kc = timer->kclock;

	timer->it_interval = 0;
	if (kc->timer_try_to_cancel(timer) < 0)
		return TIMER_RETRY;
	timer->it_active = 0;
	return 0;
}

static inline int timer_delete_hook(struct k_itimer *timer)
{
	const struct k_clock *kc = timer->kclock;

	if (WARN_ON_ONCE(!kc || !kc->timer_del))
		return -EINVAL;
	return kc->timer_del(timer);
}

/* Delete a POSIX.1b interval timer. */
SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
{
	struct k_itimer *timer;
	unsigned long flags;

	timer = lock_timer(timer_id, &flags);

retry_delete:
	if (!timer)
		return -EINVAL;

	if (unlikely(timer_delete_hook(timer) == TIMER_RETRY)) {
		/* Unlocks and relocks the timer if it still exists */
		timer = timer_wait_running(timer, &flags);
		goto retry_delete;
	}

	spin_lock(&current->sighand->siglock);
	list_del(&timer->list);
	spin_unlock(&current->sighand->siglock);
	/*
	 * A concurrent lookup could check timer::it_signal lockless. It
	 * will reevaluate with timer::it_lock held and observe the NULL.
	 */
	WRITE_ONCE(timer->it_signal, NULL);

	unlock_timer(timer, flags);
	posix_timer_unhash_and_free(timer);
	return 0;
}

/*
 * Delete a timer if it is armed, remove it from the hash and schedule it
 * for RCU freeing.
 */
static void itimer_delete(struct k_itimer *timer)
{
	unsigned long flags;

	/*
	 * irqsave is required to make timer_wait_running() work.
	 */
	spin_lock_irqsave(&timer->it_lock, flags);

retry_delete:
	/*
	 * Even if the timer is not longer accessible from other tasks
	 * it still might be armed and queued in the underlying timer
	 * mechanism. Worse, that timer mechanism might run the expiry
	 * function concurrently.
	 */
	if (timer_delete_hook(timer) == TIMER_RETRY) {
		/*
		 * Timer is expired concurrently, prevent livelocks
		 * and pointless spinning on RT.
		 *
		 * timer_wait_running() drops timer::it_lock, which opens
		 * the possibility for another task to delete the timer.
		 *
		 * That's not possible here because this is invoked from
		 * do_exit() only for the last thread of the thread group.
		 * So no other task can access and delete that timer.
		 */
		if (WARN_ON_ONCE(timer_wait_running(timer, &flags) != timer))
			return;

		goto retry_delete;
	}
	list_del(&timer->list);

	/*
	 * Setting timer::it_signal to NULL is technically not required
	 * here as nothing can access the timer anymore legitimately via
	 * the hash table. Set it to NULL nevertheless so that all deletion
	 * paths are consistent.
	 */
	WRITE_ONCE(timer->it_signal, NULL);

	spin_unlock_irqrestore(&timer->it_lock, flags);
	posix_timer_unhash_and_free(timer);
}

/*
 * Invoked from do_exit() when the last thread of a thread group exits.
 * At that point no other task can access the timers of the dying
 * task anymore.
 */
void exit_itimers(struct task_struct *tsk)
{
	struct list_head timers;
	struct k_itimer *tmr;

	if (list_empty(&tsk->signal->posix_timers))
		return;

	/* Protect against concurrent read via /proc/$PID/timers */
	spin_lock_irq(&tsk->sighand->siglock);
	list_replace_init(&tsk->signal->posix_timers, &timers);
	spin_unlock_irq(&tsk->sighand->siglock);

	/* The timers are not longer accessible via tsk::signal */
	while (!list_empty(&timers)) {
		tmr = list_first_entry(&timers, struct k_itimer, list);
		itimer_delete(tmr);
	}
}

SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
		const struct __kernel_timespec __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 new_tp;

	if (!kc || !kc->clock_set)
		return -EINVAL;

	if (get_timespec64(&new_tp, tp))
		return -EFAULT;

	/*
	 * Permission checks have to be done inside the clock specific
	 * setter callback.
	 */
	return kc->clock_set(which_clock, &new_tp);
}

SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
		struct __kernel_timespec __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 kernel_tp;
	int error;

	if (!kc)
		return -EINVAL;

	error = kc->clock_get_timespec(which_clock, &kernel_tp);

	if (!error && put_timespec64(&kernel_tp, tp))
		error = -EFAULT;

	return error;
}

int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);

	if (!kc)
		return -EINVAL;
	if (!kc->clock_adj)
		return -EOPNOTSUPP;

	return kc->clock_adj(which_clock, ktx);
}

SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
		struct __kernel_timex __user *, utx)
{
	struct __kernel_timex ktx;
	int err;

	if (copy_from_user(&ktx, utx, sizeof(ktx)))
		return -EFAULT;

	err = do_clock_adjtime(which_clock, &ktx);

	if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
		return -EFAULT;

	return err;
}

/**
 * sys_clock_getres - Get the resolution of a clock
 * @which_clock:	The clock to get the resolution for
 * @tp:			Pointer to a a user space timespec64 for storage
 *
 * POSIX defines:
 *
 * "The clock_getres() function shall return the resolution of any
 * clock. Clock resolutions are implementation-defined and cannot be set by
 * a process. If the argument res is not NULL, the resolution of the
 * specified clock shall be stored in the location pointed to by res. If
 * res is NULL, the clock resolution is not returned. If the time argument
 * of clock_settime() is not a multiple of res, then the value is truncated
 * to a multiple of res."
 *
 * Due to the various hardware constraints the real resolution can vary
 * wildly and even change during runtime when the underlying devices are
 * replaced. The kernel also can use hardware devices with different
 * resolutions for reading the time and for arming timers.
 *
 * The kernel therefore deviates from the POSIX spec in various aspects:
 *
 * 1) The resolution returned to user space
 *
 *    For CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, CLOCK_TAI,
 *    CLOCK_REALTIME_ALARM, CLOCK_BOOTTIME_ALAREM and CLOCK_MONOTONIC_RAW
 *    the kernel differentiates only two cases:
 *
 *    I)  Low resolution mode:
 *
 *	  When high resolution timers are disabled at compile or runtime
 *	  the resolution returned is nanoseconds per tick, which represents
 *	  the precision at which timers expire.
 *
 *    II) High resolution mode:
 *
 *	  When high resolution timers are enabled the resolution returned
 *	  is always one nanosecond independent of the actual resolution of
 *	  the underlying hardware devices.
 *
 *	  For CLOCK_*_ALARM the actual resolution depends on system
 *	  state. When system is running the resolution is the same as the
 *	  resolution of the other clocks. During suspend the actual
 *	  resolution is the resolution of the underlying RTC device which
 *	  might be way less precise than the clockevent device used during
 *	  running state.
 *
 *   For CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE the resolution
 *   returned is always nanoseconds per tick.
 *
 *   For CLOCK_PROCESS_CPUTIME and CLOCK_THREAD_CPUTIME the resolution
 *   returned is always one nanosecond under the assumption that the
 *   underlying scheduler clock has a better resolution than nanoseconds
 *   per tick.
 *
 *   For dynamic POSIX clocks (PTP devices) the resolution returned is
 *   always one nanosecond.
 *
 * 2) Affect on sys_clock_settime()
 *
 *    The kernel does not truncate the time which is handed in to
 *    sys_clock_settime(). The kernel internal timekeeping is always using
 *    nanoseconds precision independent of the clocksource device which is
 *    used to read the time from. The resolution of that device only
 *    affects the presicion of the time returned by sys_clock_gettime().
 *
 * Returns:
 *	0		Success. @tp contains the resolution
 *	-EINVAL		@which_clock is not a valid clock ID
 *	-EFAULT		Copying the resolution to @tp faulted
 *	-ENODEV		Dynamic POSIX clock is not backed by a device
 *	-EOPNOTSUPP	Dynamic POSIX clock does not support getres()
 */
SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
		struct __kernel_timespec __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 rtn_tp;
	int error;

	if (!kc)
		return -EINVAL;

	error = kc->clock_getres(which_clock, &rtn_tp);

	if (!error && tp && put_timespec64(&rtn_tp, tp))
		error = -EFAULT;

	return error;
}

#ifdef CONFIG_COMPAT_32BIT_TIME

SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock,
		struct old_timespec32 __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 ts;

	if (!kc || !kc->clock_set)
		return -EINVAL;

	if (get_old_timespec32(&ts, tp))
		return -EFAULT;

	return kc->clock_set(which_clock, &ts);
}

SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
		struct old_timespec32 __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 ts;
	int err;

	if (!kc)
		return -EINVAL;

	err = kc->clock_get_timespec(which_clock, &ts);

	if (!err && put_old_timespec32(&ts, tp))
		err = -EFAULT;

	return err;
}

SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock,
		struct old_timex32 __user *, utp)
{
	struct __kernel_timex ktx;
	int err;

	err = get_old_timex32(&ktx, utp);
	if (err)
		return err;

	err = do_clock_adjtime(which_clock, &ktx);

	if (err >= 0 && put_old_timex32(utp, &ktx))
		return -EFAULT;

	return err;
}

SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
		struct old_timespec32 __user *, tp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 ts;
	int err;

	if (!kc)
		return -EINVAL;

	err = kc->clock_getres(which_clock, &ts);
	if (!err && tp && put_old_timespec32(&ts, tp))
		return -EFAULT;

	return err;
}

#endif

/*
 * sys_clock_nanosleep() for CLOCK_REALTIME and CLOCK_TAI
 */
static int common_nsleep(const clockid_t which_clock, int flags,
			 const struct timespec64 *rqtp)
{
	ktime_t texp = timespec64_to_ktime(*rqtp);

	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
				 which_clock);
}

/*
 * sys_clock_nanosleep() for CLOCK_MONOTONIC and CLOCK_BOOTTIME
 *
 * Absolute nanosleeps for these clocks are time-namespace adjusted.
 */
static int common_nsleep_timens(const clockid_t which_clock, int flags,
				const struct timespec64 *rqtp)
{
	ktime_t texp = timespec64_to_ktime(*rqtp);

	if (flags & TIMER_ABSTIME)
		texp = timens_ktime_to_host(which_clock, texp);

	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
				 which_clock);
}

SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
		const struct __kernel_timespec __user *, rqtp,
		struct __kernel_timespec __user *, rmtp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 t;

	if (!kc)
		return -EINVAL;
	if (!kc->nsleep)
		return -EOPNOTSUPP;

	if (get_timespec64(&t, rqtp))
		return -EFAULT;

	if (!timespec64_valid(&t))
		return -EINVAL;
	if (flags & TIMER_ABSTIME)
		rmtp = NULL;
	current->restart_block.fn = do_no_restart_syscall;
	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
	current->restart_block.nanosleep.rmtp = rmtp;

	return kc->nsleep(which_clock, flags, &t);
}

#ifdef CONFIG_COMPAT_32BIT_TIME

SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
		struct old_timespec32 __user *, rqtp,
		struct old_timespec32 __user *, rmtp)
{
	const struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec64 t;

	if (!kc)
		return -EINVAL;
	if (!kc->nsleep)
		return -EOPNOTSUPP;

	if (get_old_timespec32(&t, rqtp))
		return -EFAULT;

	if (!timespec64_valid(&t))
		return -EINVAL;
	if (flags & TIMER_ABSTIME)
		rmtp = NULL;
	current->restart_block.fn = do_no_restart_syscall;
	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
	current->restart_block.nanosleep.compat_rmtp = rmtp;

	return kc->nsleep(which_clock, flags, &t);
}

#endif

static const struct k_clock clock_realtime = {
	.clock_getres		= posix_get_hrtimer_res,
	.clock_get_timespec	= posix_get_realtime_timespec,
	.clock_get_ktime	= posix_get_realtime_ktime,
	.clock_set		= posix_clock_realtime_set,
	.clock_adj		= posix_clock_realtime_adj,
	.nsleep			= common_nsleep,
	.timer_create		= common_timer_create,
	.timer_set		= common_timer_set,
	.timer_get		= common_timer_get,
	.timer_del		= common_timer_del,
	.timer_rearm		= common_hrtimer_rearm,
	.timer_forward		= common_hrtimer_forward,
	.timer_remaining	= common_hrtimer_remaining,
	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
	.timer_wait_running	= common_timer_wait_running,
	.timer_arm		= common_hrtimer_arm,
};

static const struct k_clock clock_monotonic = {
	.clock_getres		= posix_get_hrtimer_res,
	.clock_get_timespec	= posix_get_monotonic_timespec,
	.clock_get_ktime	= posix_get_monotonic_ktime,
	.nsleep			= common_nsleep_timens,
	.timer_create		= common_timer_create,
	.timer_set		= common_timer_set,
	.timer_get		= common_timer_get,
	.timer_del		= common_timer_del,
	.timer_rearm		= common_hrtimer_rearm,
	.timer_forward		= common_hrtimer_forward,
	.timer_remaining	= common_hrtimer_remaining,
	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
	.timer_wait_running	= common_timer_wait_running,
	.timer_arm		= common_hrtimer_arm,
};

static const struct k_clock clock_monotonic_raw = {
	.clock_getres		= posix_get_hrtimer_res,
	.clock_get_timespec	= posix_get_monotonic_raw,
};

static const struct k_clock clock_realtime_coarse = {
	.clock_getres		= posix_get_coarse_res,
	.clock_get_timespec	= posix_get_realtime_coarse,
};

static const struct k_clock clock_monotonic_coarse = {
	.clock_getres		= posix_get_coarse_res,
	.clock_get_timespec	= posix_get_monotonic_coarse,
};

static const struct k_clock clock_tai = {
	.clock_getres		= posix_get_hrtimer_res,
	.clock_get_ktime	= posix_get_tai_ktime,
	.clock_get_timespec	= posix_get_tai_timespec,
	.nsleep			= common_nsleep,
	.timer_create		= common_timer_create,
	.timer_set		= common_timer_set,
	.timer_get		= common_timer_get,
	.timer_del		= common_timer_del,
	.timer_rearm		= common_hrtimer_rearm,
	.timer_forward		= common_hrtimer_forward,
	.timer_remaining	= common_hrtimer_remaining,
	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
	.timer_wait_running	= common_timer_wait_running,
	.timer_arm		= common_hrtimer_arm,
};

static const struct k_clock clock_boottime = {
	.clock_getres		= posix_get_hrtimer_res,
	.clock_get_ktime	= posix_get_boottime_ktime,
	.clock_get_timespec	= posix_get_boottime_timespec,
	.nsleep			= common_nsleep_timens,
	.timer_create		= common_timer_create,
	.timer_set		= common_timer_set,
	.timer_get		= common_timer_get,
	.timer_del		= common_timer_del,
	.timer_rearm		= common_hrtimer_rearm,
	.timer_forward		= common_hrtimer_forward,
	.timer_remaining	= common_hrtimer_remaining,
	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
	.timer_wait_running	= common_timer_wait_running,
	.timer_arm		= common_hrtimer_arm,
};

static const struct k_clock * const posix_clocks[] = {
	[CLOCK_REALTIME]		= &clock_realtime,
	[CLOCK_MONOTONIC]		= &clock_monotonic,
	[CLOCK_PROCESS_CPUTIME_ID]	= &clock_process,
	[CLOCK_THREAD_CPUTIME_ID]	= &clock_thread,
	[CLOCK_MONOTONIC_RAW]		= &clock_monotonic_raw,
	[CLOCK_REALTIME_COARSE]		= &clock_realtime_coarse,
	[CLOCK_MONOTONIC_COARSE]	= &clock_monotonic_coarse,
	[CLOCK_BOOTTIME]		= &clock_boottime,
	[CLOCK_REALTIME_ALARM]		= &alarm_clock,
	[CLOCK_BOOTTIME_ALARM]		= &alarm_clock,
	[CLOCK_TAI]			= &clock_tai,
};

static const struct k_clock *clockid_to_kclock(const clockid_t id)
{
	clockid_t idx = id;

	if (id < 0) {
		return (id & CLOCKFD_MASK) == CLOCKFD ?
			&clock_posix_dynamic : &clock_posix_cpu;
	}

	if (id >= ARRAY_SIZE(posix_clocks))
		return NULL;

	return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))];
}