summaryrefslogtreecommitdiff
path: root/kernel/locking/rwsem.c
blob: 9215b4d6a9de14e77527344e4c2f31733b4ccef7 (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
// SPDX-License-Identifier: GPL-2.0
/* kernel/rwsem.c: R/W semaphores, public implementation
 *
 * Written by David Howells (dhowells@redhat.com).
 * Derived from asm-i386/semaphore.h
 *
 * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
 * and Michel Lespinasse <walken@google.com>
 *
 * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
 * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
 *
 * Rwsem count bit fields re-definition and rwsem rearchitecture by
 * Waiman Long <longman@redhat.com> and
 * Peter Zijlstra <peterz@infradead.org>.
 */

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
#include <linux/sched/debug.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/signal.h>
#include <linux/sched/clock.h>
#include <linux/export.h>
#include <linux/rwsem.h>
#include <linux/atomic.h>

#ifndef CONFIG_PREEMPT_RT
#include "lock_events.h"

/*
 * The least significant 2 bits of the owner value has the following
 * meanings when set.
 *  - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers
 *  - Bit 1: RWSEM_NONSPINNABLE - Cannot spin on a reader-owned lock
 *
 * When the rwsem is reader-owned and a spinning writer has timed out,
 * the nonspinnable bit will be set to disable optimistic spinning.

 * When a writer acquires a rwsem, it puts its task_struct pointer
 * into the owner field. It is cleared after an unlock.
 *
 * When a reader acquires a rwsem, it will also puts its task_struct
 * pointer into the owner field with the RWSEM_READER_OWNED bit set.
 * On unlock, the owner field will largely be left untouched. So
 * for a free or reader-owned rwsem, the owner value may contain
 * information about the last reader that acquires the rwsem.
 *
 * That information may be helpful in debugging cases where the system
 * seems to hang on a reader owned rwsem especially if only one reader
 * is involved. Ideally we would like to track all the readers that own
 * a rwsem, but the overhead is simply too big.
 *
 * A fast path reader optimistic lock stealing is supported when the rwsem
 * is previously owned by a writer and the following conditions are met:
 *  - OSQ is empty
 *  - rwsem is not currently writer owned
 *  - the handoff isn't set.
 */
#define RWSEM_READER_OWNED	(1UL << 0)
#define RWSEM_NONSPINNABLE	(1UL << 1)
#define RWSEM_OWNER_FLAGS_MASK	(RWSEM_READER_OWNED | RWSEM_NONSPINNABLE)

#ifdef CONFIG_DEBUG_RWSEMS
# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
	if (!debug_locks_silent &&				\
	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, magic = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
		#c, atomic_long_read(&(sem)->count),		\
		(unsigned long) sem->magic,			\
		atomic_long_read(&(sem)->owner), (long)current,	\
		list_empty(&(sem)->wait_list) ? "" : "not "))	\
			debug_locks_off();			\
	} while (0)
#else
# define DEBUG_RWSEMS_WARN_ON(c, sem)
#endif

/*
 * On 64-bit architectures, the bit definitions of the count are:
 *
 * Bit  0    - writer locked bit
 * Bit  1    - waiters present bit
 * Bit  2    - lock handoff bit
 * Bits 3-7  - reserved
 * Bits 8-62 - 55-bit reader count
 * Bit  63   - read fail bit
 *
 * On 32-bit architectures, the bit definitions of the count are:
 *
 * Bit  0    - writer locked bit
 * Bit  1    - waiters present bit
 * Bit  2    - lock handoff bit
 * Bits 3-7  - reserved
 * Bits 8-30 - 23-bit reader count
 * Bit  31   - read fail bit
 *
 * It is not likely that the most significant bit (read fail bit) will ever
 * be set. This guard bit is still checked anyway in the down_read() fastpath
 * just in case we need to use up more of the reader bits for other purpose
 * in the future.
 *
 * atomic_long_fetch_add() is used to obtain reader lock, whereas
 * atomic_long_cmpxchg() will be used to obtain writer lock.
 *
 * There are three places where the lock handoff bit may be set or cleared.
 * 1) rwsem_mark_wake() for readers.
 * 2) rwsem_try_write_lock() for writers.
 * 3) Error path of rwsem_down_write_slowpath().
 *
 * For all the above cases, wait_lock will be held. A writer must also
 * be the first one in the wait_list to be eligible for setting the handoff
 * bit. So concurrent setting/clearing of handoff bit is not possible.
 */
#define RWSEM_WRITER_LOCKED	(1UL << 0)
#define RWSEM_FLAG_WAITERS	(1UL << 1)
#define RWSEM_FLAG_HANDOFF	(1UL << 2)
#define RWSEM_FLAG_READFAIL	(1UL << (BITS_PER_LONG - 1))

#define RWSEM_READER_SHIFT	8
#define RWSEM_READER_BIAS	(1UL << RWSEM_READER_SHIFT)
#define RWSEM_READER_MASK	(~(RWSEM_READER_BIAS - 1))
#define RWSEM_WRITER_MASK	RWSEM_WRITER_LOCKED
#define RWSEM_LOCK_MASK		(RWSEM_WRITER_MASK|RWSEM_READER_MASK)
#define RWSEM_READ_FAILED_MASK	(RWSEM_WRITER_MASK|RWSEM_FLAG_WAITERS|\
				 RWSEM_FLAG_HANDOFF|RWSEM_FLAG_READFAIL)

/*
 * All writes to owner are protected by WRITE_ONCE() to make sure that
 * store tearing can't happen as optimistic spinners may read and use
 * the owner value concurrently without lock. Read from owner, however,
 * may not need READ_ONCE() as long as the pointer value is only used
 * for comparison and isn't being dereferenced.
 */
static inline void rwsem_set_owner(struct rw_semaphore *sem)
{
	atomic_long_set(&sem->owner, (long)current);
}

static inline void rwsem_clear_owner(struct rw_semaphore *sem)
{
	atomic_long_set(&sem->owner, 0);
}

/*
 * Test the flags in the owner field.
 */
static inline bool rwsem_test_oflags(struct rw_semaphore *sem, long flags)
{
	return atomic_long_read(&sem->owner) & flags;
}

/*
 * The task_struct pointer of the last owning reader will be left in
 * the owner field.
 *
 * Note that the owner value just indicates the task has owned the rwsem
 * previously, it may not be the real owner or one of the real owners
 * anymore when that field is examined, so take it with a grain of salt.
 *
 * The reader non-spinnable bit is preserved.
 */
static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
					    struct task_struct *owner)
{
	unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED |
		(atomic_long_read(&sem->owner) & RWSEM_NONSPINNABLE);

	atomic_long_set(&sem->owner, val);
}

static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
{
	__rwsem_set_reader_owned(sem, current);
}

/*
 * Return true if the rwsem is owned by a reader.
 */
static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
{
#ifdef CONFIG_DEBUG_RWSEMS
	/*
	 * Check the count to see if it is write-locked.
	 */
	long count = atomic_long_read(&sem->count);

	if (count & RWSEM_WRITER_MASK)
		return false;
#endif
	return rwsem_test_oflags(sem, RWSEM_READER_OWNED);
}

#ifdef CONFIG_DEBUG_RWSEMS
/*
 * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
 * is a task pointer in owner of a reader-owned rwsem, it will be the
 * real owner or one of the real owners. The only exception is when the
 * unlock is done by up_read_non_owner().
 */
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
{
	unsigned long val = atomic_long_read(&sem->owner);

	while ((val & ~RWSEM_OWNER_FLAGS_MASK) == (unsigned long)current) {
		if (atomic_long_try_cmpxchg(&sem->owner, &val,
					    val & RWSEM_OWNER_FLAGS_MASK))
			return;
	}
}
#else
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
{
}
#endif

/*
 * Set the RWSEM_NONSPINNABLE bits if the RWSEM_READER_OWNED flag
 * remains set. Otherwise, the operation will be aborted.
 */
static inline void rwsem_set_nonspinnable(struct rw_semaphore *sem)
{
	unsigned long owner = atomic_long_read(&sem->owner);

	do {
		if (!(owner & RWSEM_READER_OWNED))
			break;
		if (owner & RWSEM_NONSPINNABLE)
			break;
	} while (!atomic_long_try_cmpxchg(&sem->owner, &owner,
					  owner | RWSEM_NONSPINNABLE));
}

static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp)
{
	*cntp = atomic_long_add_return_acquire(RWSEM_READER_BIAS, &sem->count);

	if (WARN_ON_ONCE(*cntp < 0))
		rwsem_set_nonspinnable(sem);

	if (!(*cntp & RWSEM_READ_FAILED_MASK)) {
		rwsem_set_reader_owned(sem);
		return true;
	}

	return false;
}

static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
{
	long tmp = RWSEM_UNLOCKED_VALUE;

	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
		rwsem_set_owner(sem);
		return true;
	}

	return false;
}

/*
 * Return just the real task structure pointer of the owner
 */
static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
{
	return (struct task_struct *)
		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
}

/*
 * Return the real task structure pointer of the owner and the embedded
 * flags in the owner. pflags must be non-NULL.
 */
static inline struct task_struct *
rwsem_owner_flags(struct rw_semaphore *sem, unsigned long *pflags)
{
	unsigned long owner = atomic_long_read(&sem->owner);

	*pflags = owner & RWSEM_OWNER_FLAGS_MASK;
	return (struct task_struct *)(owner & ~RWSEM_OWNER_FLAGS_MASK);
}

/*
 * Guide to the rw_semaphore's count field.
 *
 * When the RWSEM_WRITER_LOCKED bit in count is set, the lock is owned
 * by a writer.
 *
 * The lock is owned by readers when
 * (1) the RWSEM_WRITER_LOCKED isn't set in count,
 * (2) some of the reader bits are set in count, and
 * (3) the owner field has RWSEM_READ_OWNED bit set.
 *
 * Having some reader bits set is not enough to guarantee a readers owned
 * lock as the readers may be in the process of backing out from the count
 * and a writer has just released the lock. So another writer may steal
 * the lock immediately after that.
 */

/*
 * Initialize an rwsem:
 */
void __init_rwsem(struct rw_semaphore *sem, const char *name,
		  struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	/*
	 * Make sure we are not reinitializing a held semaphore:
	 */
	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
	lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP);
#endif
#ifdef CONFIG_DEBUG_RWSEMS
	sem->magic = sem;
#endif
	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
	raw_spin_lock_init(&sem->wait_lock);
	INIT_LIST_HEAD(&sem->wait_list);
	atomic_long_set(&sem->owner, 0L);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
	osq_lock_init(&sem->osq);
#endif
}
EXPORT_SYMBOL(__init_rwsem);

enum rwsem_waiter_type {
	RWSEM_WAITING_FOR_WRITE,
	RWSEM_WAITING_FOR_READ
};

struct rwsem_waiter {
	struct list_head list;
	struct task_struct *task;
	enum rwsem_waiter_type type;
	unsigned long timeout;
};
#define rwsem_first_waiter(sem) \
	list_first_entry(&sem->wait_list, struct rwsem_waiter, list)

enum rwsem_wake_type {
	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
	RWSEM_WAKE_READERS,	/* Wake readers only */
	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
};

enum writer_wait_state {
	WRITER_NOT_FIRST,	/* Writer is not first in wait list */
	WRITER_FIRST,		/* Writer is first in wait list     */
	WRITER_HANDOFF		/* Writer is first & handoff needed */
};

/*
 * The typical HZ value is either 250 or 1000. So set the minimum waiting
 * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
 * queue before initiating the handoff protocol.
 */
#define RWSEM_WAIT_TIMEOUT	DIV_ROUND_UP(HZ, 250)

/*
 * Magic number to batch-wakeup waiting readers, even when writers are
 * also present in the queue. This both limits the amount of work the
 * waking thread must do and also prevents any potential counter overflow,
 * however unlikely.
 */
#define MAX_READERS_WAKEUP	0x100

/*
 * handle the lock release when processes blocked on it that can now run
 * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
 *   have been set.
 * - there must be someone on the queue
 * - the wait_lock must be held by the caller
 * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
 *   to actually wakeup the blocked task(s) and drop the reference count,
 *   preferably when the wait_lock is released
 * - woken process blocks are discarded from the list after having task zeroed
 * - writers are only marked woken if downgrading is false
 */
static void rwsem_mark_wake(struct rw_semaphore *sem,
			    enum rwsem_wake_type wake_type,
			    struct wake_q_head *wake_q)
{
	struct rwsem_waiter *waiter, *tmp;
	long oldcount, woken = 0, adjustment = 0;
	struct list_head wlist;

	lockdep_assert_held(&sem->wait_lock);

	/*
	 * Take a peek at the queue head waiter such that we can determine
	 * the wakeup(s) to perform.
	 */
	waiter = rwsem_first_waiter(sem);

	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
		if (wake_type == RWSEM_WAKE_ANY) {
			/*
			 * Mark writer at the front of the queue for wakeup.
			 * Until the task is actually later awoken later by
			 * the caller, other writers are able to steal it.
			 * Readers, on the other hand, will block as they
			 * will notice the queued writer.
			 */
			wake_q_add(wake_q, waiter->task);
			lockevent_inc(rwsem_wake_writer);
		}

		return;
	}

	/*
	 * No reader wakeup if there are too many of them already.
	 */
	if (unlikely(atomic_long_read(&sem->count) < 0))
		return;

	/*
	 * Writers might steal the lock before we grant it to the next reader.
	 * We prefer to do the first reader grant before counting readers
	 * so we can bail out early if a writer stole the lock.
	 */
	if (wake_type != RWSEM_WAKE_READ_OWNED) {
		struct task_struct *owner;

		adjustment = RWSEM_READER_BIAS;
		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
		if (unlikely(oldcount & RWSEM_WRITER_MASK)) {
			/*
			 * When we've been waiting "too" long (for writers
			 * to give up the lock), request a HANDOFF to
			 * force the issue.
			 */
			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
			    time_after(jiffies, waiter->timeout)) {
				adjustment -= RWSEM_FLAG_HANDOFF;
				lockevent_inc(rwsem_rlock_handoff);
			}

			atomic_long_add(-adjustment, &sem->count);
			return;
		}
		/*
		 * Set it to reader-owned to give spinners an early
		 * indication that readers now have the lock.
		 * The reader nonspinnable bit seen at slowpath entry of
		 * the reader is copied over.
		 */
		owner = waiter->task;
		__rwsem_set_reader_owned(sem, owner);
	}

	/*
	 * Grant up to MAX_READERS_WAKEUP read locks to all the readers in the
	 * queue. We know that the woken will be at least 1 as we accounted
	 * for above. Note we increment the 'active part' of the count by the
	 * number of readers before waking any processes up.
	 *
	 * This is an adaptation of the phase-fair R/W locks where at the
	 * reader phase (first waiter is a reader), all readers are eligible
	 * to acquire the lock at the same time irrespective of their order
	 * in the queue. The writers acquire the lock according to their
	 * order in the queue.
	 *
	 * We have to do wakeup in 2 passes to prevent the possibility that
	 * the reader count may be decremented before it is incremented. It
	 * is because the to-be-woken waiter may not have slept yet. So it
	 * may see waiter->task got cleared, finish its critical section and
	 * do an unlock before the reader count increment.
	 *
	 * 1) Collect the read-waiters in a separate list, count them and
	 *    fully increment the reader count in rwsem.
	 * 2) For each waiters in the new list, clear waiter->task and
	 *    put them into wake_q to be woken up later.
	 */
	INIT_LIST_HEAD(&wlist);
	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
			continue;

		woken++;
		list_move_tail(&waiter->list, &wlist);

		/*
		 * Limit # of readers that can be woken up per wakeup call.
		 */
		if (woken >= MAX_READERS_WAKEUP)
			break;
	}

	adjustment = woken * RWSEM_READER_BIAS - adjustment;
	lockevent_cond_inc(rwsem_wake_reader, woken);
	if (list_empty(&sem->wait_list)) {
		/* hit end of list above */
		adjustment -= RWSEM_FLAG_WAITERS;
	}

	/*
	 * When we've woken a reader, we no longer need to force writers
	 * to give up the lock and we can clear HANDOFF.
	 */
	if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
		adjustment -= RWSEM_FLAG_HANDOFF;

	if (adjustment)
		atomic_long_add(adjustment, &sem->count);

	/* 2nd pass */
	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
		struct task_struct *tsk;

		tsk = waiter->task;
		get_task_struct(tsk);

		/*
		 * Ensure calling get_task_struct() before setting the reader
		 * waiter to nil such that rwsem_down_read_slowpath() cannot
		 * race with do_exit() by always holding a reference count
		 * to the task to wakeup.
		 */
		smp_store_release(&waiter->task, NULL);
		/*
		 * Ensure issuing the wakeup (either by us or someone else)
		 * after setting the reader waiter to nil.
		 */
		wake_q_add_safe(wake_q, tsk);
	}
}

/*
 * This function must be called with the sem->wait_lock held to prevent
 * race conditions between checking the rwsem wait list and setting the
 * sem->count accordingly.
 *
 * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
 * bit is set or the lock is acquired with handoff bit cleared.
 */
static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
					enum writer_wait_state wstate)
{
	long count, new;

	lockdep_assert_held(&sem->wait_lock);

	count = atomic_long_read(&sem->count);
	do {
		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);

		if (has_handoff && wstate == WRITER_NOT_FIRST)
			return false;

		new = count;

		if (count & RWSEM_LOCK_MASK) {
			if (has_handoff || (wstate != WRITER_HANDOFF))
				return false;

			new |= RWSEM_FLAG_HANDOFF;
		} else {
			new |= RWSEM_WRITER_LOCKED;
			new &= ~RWSEM_FLAG_HANDOFF;

			if (list_is_singular(&sem->wait_list))
				new &= ~RWSEM_FLAG_WAITERS;
		}
	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));

	/*
	 * We have either acquired the lock with handoff bit cleared or
	 * set the handoff bit.
	 */
	if (new & RWSEM_FLAG_HANDOFF)
		return false;

	rwsem_set_owner(sem);
	return true;
}

#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
/*
 * Try to acquire write lock before the writer has been put on wait queue.
 */
static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
{
	long count = atomic_long_read(&sem->count);

	while (!(count & (RWSEM_LOCK_MASK|RWSEM_FLAG_HANDOFF))) {
		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
					count | RWSEM_WRITER_LOCKED)) {
			rwsem_set_owner(sem);
			lockevent_inc(rwsem_opt_lock);
			return true;
		}
	}
	return false;
}

static inline bool owner_on_cpu(struct task_struct *owner)
{
	/*
	 * As lock holder preemption issue, we both skip spinning if
	 * task is not on cpu or its cpu is preempted
	 */
	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
}

static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
{
	struct task_struct *owner;
	unsigned long flags;
	bool ret = true;

	if (need_resched()) {
		lockevent_inc(rwsem_opt_fail);
		return false;
	}

	preempt_disable();
	rcu_read_lock();
	owner = rwsem_owner_flags(sem, &flags);
	/*
	 * Don't check the read-owner as the entry may be stale.
	 */
	if ((flags & RWSEM_NONSPINNABLE) ||
	    (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner)))
		ret = false;
	rcu_read_unlock();
	preempt_enable();

	lockevent_cond_inc(rwsem_opt_fail, !ret);
	return ret;
}

/*
 * The rwsem_spin_on_owner() function returns the following 4 values
 * depending on the lock owner state.
 *   OWNER_NULL  : owner is currently NULL
 *   OWNER_WRITER: when owner changes and is a writer
 *   OWNER_READER: when owner changes and the new owner may be a reader.
 *   OWNER_NONSPINNABLE:
 *		   when optimistic spinning has to stop because either the
 *		   owner stops running, is unknown, or its timeslice has
 *		   been used up.
 */
enum owner_state {
	OWNER_NULL		= 1 << 0,
	OWNER_WRITER		= 1 << 1,
	OWNER_READER		= 1 << 2,
	OWNER_NONSPINNABLE	= 1 << 3,
};
#define OWNER_SPINNABLE		(OWNER_NULL | OWNER_WRITER | OWNER_READER)

static inline enum owner_state
rwsem_owner_state(struct task_struct *owner, unsigned long flags)
{
	if (flags & RWSEM_NONSPINNABLE)
		return OWNER_NONSPINNABLE;

	if (flags & RWSEM_READER_OWNED)
		return OWNER_READER;

	return owner ? OWNER_WRITER : OWNER_NULL;
}

static noinline enum owner_state
rwsem_spin_on_owner(struct rw_semaphore *sem)
{
	struct task_struct *new, *owner;
	unsigned long flags, new_flags;
	enum owner_state state;

	owner = rwsem_owner_flags(sem, &flags);
	state = rwsem_owner_state(owner, flags);
	if (state != OWNER_WRITER)
		return state;

	rcu_read_lock();
	for (;;) {
		/*
		 * When a waiting writer set the handoff flag, it may spin
		 * on the owner as well. Once that writer acquires the lock,
		 * we can spin on it. So we don't need to quit even when the
		 * handoff bit is set.
		 */
		new = rwsem_owner_flags(sem, &new_flags);
		if ((new != owner) || (new_flags != flags)) {
			state = rwsem_owner_state(new, new_flags);
			break;
		}

		/*
		 * Ensure we emit the owner->on_cpu, dereference _after_
		 * checking sem->owner still matches owner, if that fails,
		 * owner might point to free()d memory, if it still matches,
		 * the rcu_read_lock() ensures the memory stays valid.
		 */
		barrier();

		if (need_resched() || !owner_on_cpu(owner)) {
			state = OWNER_NONSPINNABLE;
			break;
		}

		cpu_relax();
	}
	rcu_read_unlock();

	return state;
}

/*
 * Calculate reader-owned rwsem spinning threshold for writer
 *
 * The more readers own the rwsem, the longer it will take for them to
 * wind down and free the rwsem. So the empirical formula used to
 * determine the actual spinning time limit here is:
 *
 *   Spinning threshold = (10 + nr_readers/2)us
 *
 * The limit is capped to a maximum of 25us (30 readers). This is just
 * a heuristic and is subjected to change in the future.
 */
static inline u64 rwsem_rspin_threshold(struct rw_semaphore *sem)
{
	long count = atomic_long_read(&sem->count);
	int readers = count >> RWSEM_READER_SHIFT;
	u64 delta;

	if (readers > 30)
		readers = 30;
	delta = (20 + readers) * NSEC_PER_USEC / 2;

	return sched_clock() + delta;
}

static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
	bool taken = false;
	int prev_owner_state = OWNER_NULL;
	int loop = 0;
	u64 rspin_threshold = 0;

	preempt_disable();

	/* sem->wait_lock should not be held when doing optimistic spinning */
	if (!osq_lock(&sem->osq))
		goto done;

	/*
	 * Optimistically spin on the owner field and attempt to acquire the
	 * lock whenever the owner changes. Spinning will be stopped when:
	 *  1) the owning writer isn't running; or
	 *  2) readers own the lock and spinning time has exceeded limit.
	 */
	for (;;) {
		enum owner_state owner_state;

		owner_state = rwsem_spin_on_owner(sem);
		if (!(owner_state & OWNER_SPINNABLE))
			break;

		/*
		 * Try to acquire the lock
		 */
		taken = rwsem_try_write_lock_unqueued(sem);

		if (taken)
			break;

		/*
		 * Time-based reader-owned rwsem optimistic spinning
		 */
		if (owner_state == OWNER_READER) {
			/*
			 * Re-initialize rspin_threshold every time when
			 * the owner state changes from non-reader to reader.
			 * This allows a writer to steal the lock in between
			 * 2 reader phases and have the threshold reset at
			 * the beginning of the 2nd reader phase.
			 */
			if (prev_owner_state != OWNER_READER) {
				if (rwsem_test_oflags(sem, RWSEM_NONSPINNABLE))
					break;
				rspin_threshold = rwsem_rspin_threshold(sem);
				loop = 0;
			}

			/*
			 * Check time threshold once every 16 iterations to
			 * avoid calling sched_clock() too frequently so
			 * as to reduce the average latency between the times
			 * when the lock becomes free and when the spinner
			 * is ready to do a trylock.
			 */
			else if (!(++loop & 0xf) && (sched_clock() > rspin_threshold)) {
				rwsem_set_nonspinnable(sem);
				lockevent_inc(rwsem_opt_nospin);
				break;
			}
		}

		/*
		 * An RT task cannot do optimistic spinning if it cannot
		 * be sure the lock holder is running or live-lock may
		 * happen if the current task and the lock holder happen
		 * to run in the same CPU. However, aborting optimistic
		 * spinning while a NULL owner is detected may miss some
		 * opportunity where spinning can continue without causing
		 * problem.
		 *
		 * There are 2 possible cases where an RT task may be able
		 * to continue spinning.
		 *
		 * 1) The lock owner is in the process of releasing the
		 *    lock, sem->owner is cleared but the lock has not
		 *    been released yet.
		 * 2) The lock was free and owner cleared, but another
		 *    task just comes in and acquire the lock before
		 *    we try to get it. The new owner may be a spinnable
		 *    writer.
		 *
		 * To take advantage of two scenarios listed above, the RT
		 * task is made to retry one more time to see if it can
		 * acquire the lock or continue spinning on the new owning
		 * writer. Of course, if the time lag is long enough or the
		 * new owner is not a writer or spinnable, the RT task will
		 * quit spinning.
		 *
		 * If the owner is a writer, the need_resched() check is
		 * done inside rwsem_spin_on_owner(). If the owner is not
		 * a writer, need_resched() check needs to be done here.
		 */
		if (owner_state != OWNER_WRITER) {
			if (need_resched())
				break;
			if (rt_task(current) &&
			   (prev_owner_state != OWNER_WRITER))
				break;
		}
		prev_owner_state = owner_state;

		/*
		 * The cpu_relax() call is a compiler barrier which forces
		 * everything in this loop to be re-loaded. We don't need
		 * memory barriers as we'll eventually observe the right
		 * values at the cost of a few extra spins.
		 */
		cpu_relax();
	}
	osq_unlock(&sem->osq);
done:
	preempt_enable();
	lockevent_cond_inc(rwsem_opt_fail, !taken);
	return taken;
}

/*
 * Clear the owner's RWSEM_NONSPINNABLE bit if it is set. This should
 * only be called when the reader count reaches 0.
 */
static inline void clear_nonspinnable(struct rw_semaphore *sem)
{
	if (rwsem_test_oflags(sem, RWSEM_NONSPINNABLE))
		atomic_long_andnot(RWSEM_NONSPINNABLE, &sem->owner);
}

#else
static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
{
	return false;
}

static inline bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
	return false;
}

static inline void clear_nonspinnable(struct rw_semaphore *sem) { }

static inline int
rwsem_spin_on_owner(struct rw_semaphore *sem)
{
	return 0;
}
#define OWNER_NULL	1
#endif

/*
 * Wait for the read lock to be granted
 */
static struct rw_semaphore __sched *
rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int state)
{
	long adjustment = -RWSEM_READER_BIAS;
	long rcnt = (count >> RWSEM_READER_SHIFT);
	struct rwsem_waiter waiter;
	DEFINE_WAKE_Q(wake_q);
	bool wake = false;

	/*
	 * To prevent a constant stream of readers from starving a sleeping
	 * waiter, don't attempt optimistic lock stealing if the lock is
	 * currently owned by readers.
	 */
	if ((atomic_long_read(&sem->owner) & RWSEM_READER_OWNED) &&
	    (rcnt > 1) && !(count & RWSEM_WRITER_LOCKED))
		goto queue;

	/*
	 * Reader optimistic lock stealing.
	 */
	if (!(count & (RWSEM_WRITER_LOCKED | RWSEM_FLAG_HANDOFF))) {
		rwsem_set_reader_owned(sem);
		lockevent_inc(rwsem_rlock_steal);

		/*
		 * Wake up other readers in the wait queue if it is
		 * the first reader.
		 */
		if ((rcnt == 1) && (count & RWSEM_FLAG_WAITERS)) {
			raw_spin_lock_irq(&sem->wait_lock);
			if (!list_empty(&sem->wait_list))
				rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED,
						&wake_q);
			raw_spin_unlock_irq(&sem->wait_lock);
			wake_up_q(&wake_q);
		}
		return sem;
	}

queue:
	waiter.task = current;
	waiter.type = RWSEM_WAITING_FOR_READ;
	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;

	raw_spin_lock_irq(&sem->wait_lock);
	if (list_empty(&sem->wait_list)) {
		/*
		 * In case the wait queue is empty and the lock isn't owned
		 * by a writer or has the handoff bit set, this reader can
		 * exit the slowpath and return immediately as its
		 * RWSEM_READER_BIAS has already been set in the count.
		 */
		if (!(atomic_long_read(&sem->count) &
		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
			/* Provide lock ACQUIRE */
			smp_acquire__after_ctrl_dep();
			raw_spin_unlock_irq(&sem->wait_lock);
			rwsem_set_reader_owned(sem);
			lockevent_inc(rwsem_rlock_fast);
			return sem;
		}
		adjustment += RWSEM_FLAG_WAITERS;
	}
	list_add_tail(&waiter.list, &sem->wait_list);

	/* we're now waiting on the lock, but no longer actively locking */
	count = atomic_long_add_return(adjustment, &sem->count);

	/*
	 * If there are no active locks, wake the front queued process(es).
	 *
	 * If there are no writers and we are first in the queue,
	 * wake our own waiter to join the existing active readers !
	 */
	if (!(count & RWSEM_LOCK_MASK)) {
		clear_nonspinnable(sem);
		wake = true;
	}
	if (wake || (!(count & RWSEM_WRITER_MASK) &&
		    (adjustment & RWSEM_FLAG_WAITERS)))
		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);

	raw_spin_unlock_irq(&sem->wait_lock);
	wake_up_q(&wake_q);

	/* wait to be given the lock */
	for (;;) {
		set_current_state(state);
		if (!smp_load_acquire(&waiter.task)) {
			/* Matches rwsem_mark_wake()'s smp_store_release(). */
			break;
		}
		if (signal_pending_state(state, current)) {
			raw_spin_lock_irq(&sem->wait_lock);
			if (waiter.task)
				goto out_nolock;
			raw_spin_unlock_irq(&sem->wait_lock);
			/* Ordered by sem->wait_lock against rwsem_mark_wake(). */
			break;
		}
		schedule();
		lockevent_inc(rwsem_sleep_reader);
	}

	__set_current_state(TASK_RUNNING);
	lockevent_inc(rwsem_rlock);
	return sem;

out_nolock:
	list_del(&waiter.list);
	if (list_empty(&sem->wait_list)) {
		atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
				   &sem->count);
	}
	raw_spin_unlock_irq(&sem->wait_lock);
	__set_current_state(TASK_RUNNING);
	lockevent_inc(rwsem_rlock_fail);
	return ERR_PTR(-EINTR);
}

/*
 * Wait until we successfully acquire the write lock
 */
static struct rw_semaphore *
rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
{
	long count;
	enum writer_wait_state wstate;
	struct rwsem_waiter waiter;
	struct rw_semaphore *ret = sem;
	DEFINE_WAKE_Q(wake_q);

	/* do optimistic spinning and steal lock if possible */
	if (rwsem_can_spin_on_owner(sem) && rwsem_optimistic_spin(sem)) {
		/* rwsem_optimistic_spin() implies ACQUIRE on success */
		return sem;
	}

	/*
	 * Optimistic spinning failed, proceed to the slowpath
	 * and block until we can acquire the sem.
	 */
	waiter.task = current;
	waiter.type = RWSEM_WAITING_FOR_WRITE;
	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;

	raw_spin_lock_irq(&sem->wait_lock);

	/* account for this before adding a new element to the list */
	wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;

	list_add_tail(&waiter.list, &sem->wait_list);

	/* we're now waiting on the lock */
	if (wstate == WRITER_NOT_FIRST) {
		count = atomic_long_read(&sem->count);

		/*
		 * If there were already threads queued before us and:
		 *  1) there are no active locks, wake the front
		 *     queued process(es) as the handoff bit might be set.
		 *  2) there are no active writers and some readers, the lock
		 *     must be read owned; so we try to wake any read lock
		 *     waiters that were queued ahead of us.
		 */
		if (count & RWSEM_WRITER_MASK)
			goto wait;

		rwsem_mark_wake(sem, (count & RWSEM_READER_MASK)
					? RWSEM_WAKE_READERS
					: RWSEM_WAKE_ANY, &wake_q);

		if (!wake_q_empty(&wake_q)) {
			/*
			 * We want to minimize wait_lock hold time especially
			 * when a large number of readers are to be woken up.
			 */
			raw_spin_unlock_irq(&sem->wait_lock);
			wake_up_q(&wake_q);
			wake_q_init(&wake_q);	/* Used again, reinit */
			raw_spin_lock_irq(&sem->wait_lock);
		}
	} else {
		atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count);
	}

wait:
	/* wait until we successfully acquire the lock */
	set_current_state(state);
	for (;;) {
		if (rwsem_try_write_lock(sem, wstate)) {
			/* rwsem_try_write_lock() implies ACQUIRE on success */
			break;
		}

		raw_spin_unlock_irq(&sem->wait_lock);

		/*
		 * After setting the handoff bit and failing to acquire
		 * the lock, attempt to spin on owner to accelerate lock
		 * transfer. If the previous owner is a on-cpu writer and it
		 * has just released the lock, OWNER_NULL will be returned.
		 * In this case, we attempt to acquire the lock again
		 * without sleeping.
		 */
		if (wstate == WRITER_HANDOFF &&
		    rwsem_spin_on_owner(sem) == OWNER_NULL)
			goto trylock_again;

		/* Block until there are no active lockers. */
		for (;;) {
			if (signal_pending_state(state, current))
				goto out_nolock;

			schedule();
			lockevent_inc(rwsem_sleep_writer);
			set_current_state(state);
			/*
			 * If HANDOFF bit is set, unconditionally do
			 * a trylock.
			 */
			if (wstate == WRITER_HANDOFF)
				break;

			if ((wstate == WRITER_NOT_FIRST) &&
			    (rwsem_first_waiter(sem) == &waiter))
				wstate = WRITER_FIRST;

			count = atomic_long_read(&sem->count);
			if (!(count & RWSEM_LOCK_MASK))
				break;

			/*
			 * The setting of the handoff bit is deferred
			 * until rwsem_try_write_lock() is called.
			 */
			if ((wstate == WRITER_FIRST) && (rt_task(current) ||
			    time_after(jiffies, waiter.timeout))) {
				wstate = WRITER_HANDOFF;
				lockevent_inc(rwsem_wlock_handoff);
				break;
			}
		}
trylock_again:
		raw_spin_lock_irq(&sem->wait_lock);
	}
	__set_current_state(TASK_RUNNING);
	list_del(&waiter.list);
	raw_spin_unlock_irq(&sem->wait_lock);
	lockevent_inc(rwsem_wlock);

	return ret;

out_nolock:
	__set_current_state(TASK_RUNNING);
	raw_spin_lock_irq(&sem->wait_lock);
	list_del(&waiter.list);

	if (unlikely(wstate == WRITER_HANDOFF))
		atomic_long_add(-RWSEM_FLAG_HANDOFF,  &sem->count);

	if (list_empty(&sem->wait_list))
		atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
	else
		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
	raw_spin_unlock_irq(&sem->wait_lock);
	wake_up_q(&wake_q);
	lockevent_inc(rwsem_wlock_fail);

	return ERR_PTR(-EINTR);
}

/*
 * handle waking up a waiter on the semaphore
 * - up_read/up_write has decremented the active part of count if we come here
 */
static struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
	unsigned long flags;
	DEFINE_WAKE_Q(wake_q);

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (!list_empty(&sem->wait_list))
		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
	wake_up_q(&wake_q);

	return sem;
}

/*
 * downgrade a write lock into a read lock
 * - caller incremented waiting part of count and discovered it still negative
 * - just wake up any readers at the front of the queue
 */
static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
	unsigned long flags;
	DEFINE_WAKE_Q(wake_q);

	raw_spin_lock_irqsave(&sem->wait_lock, flags);

	if (!list_empty(&sem->wait_list))
		rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);

	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
	wake_up_q(&wake_q);

	return sem;
}

/*
 * lock for reading
 */
static inline int __down_read_common(struct rw_semaphore *sem, int state)
{
	long count;

	if (!rwsem_read_trylock(sem, &count)) {
		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state)))
			return -EINTR;
		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
	}
	return 0;
}

static inline void __down_read(struct rw_semaphore *sem)
{
	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
}

static inline int __down_read_interruptible(struct rw_semaphore *sem)
{
	return __down_read_common(sem, TASK_INTERRUPTIBLE);
}

static inline int __down_read_killable(struct rw_semaphore *sem)
{
	return __down_read_common(sem, TASK_KILLABLE);
}

static inline int __down_read_trylock(struct rw_semaphore *sem)
{
	long tmp;

	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);

	/*
	 * Optimize for the case when the rwsem is not locked at all.
	 */
	tmp = RWSEM_UNLOCKED_VALUE;
	do {
		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
					tmp + RWSEM_READER_BIAS)) {
			rwsem_set_reader_owned(sem);
			return 1;
		}
	} while (!(tmp & RWSEM_READ_FAILED_MASK));
	return 0;
}

/*
 * lock for writing
 */
static inline int __down_write_common(struct rw_semaphore *sem, int state)
{
	if (unlikely(!rwsem_write_trylock(sem))) {
		if (IS_ERR(rwsem_down_write_slowpath(sem, state)))
			return -EINTR;
	}

	return 0;
}

static inline void __down_write(struct rw_semaphore *sem)
{
	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
}

static inline int __down_write_killable(struct rw_semaphore *sem)
{
	return __down_write_common(sem, TASK_KILLABLE);
}

static inline int __down_write_trylock(struct rw_semaphore *sem)
{
	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
	return rwsem_write_trylock(sem);
}

/*
 * unlock after reading
 */
static inline void __up_read(struct rw_semaphore *sem)
{
	long tmp;

	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);

	rwsem_clear_reader_owned(sem);
	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
	if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
		      RWSEM_FLAG_WAITERS)) {
		clear_nonspinnable(sem);
		rwsem_wake(sem);
	}
}

/*
 * unlock after writing
 */
static inline void __up_write(struct rw_semaphore *sem)
{
	long tmp;

	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
	/*
	 * sem->owner may differ from current if the ownership is transferred
	 * to an anonymous writer by setting the RWSEM_NONSPINNABLE bits.
	 */
	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);

	rwsem_clear_owner(sem);
	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
		rwsem_wake(sem);
}

/*
 * downgrade write lock to read lock
 */
static inline void __downgrade_write(struct rw_semaphore *sem)
{
	long tmp;

	/*
	 * When downgrading from exclusive to shared ownership,
	 * anything inside the write-locked region cannot leak
	 * into the read side. In contrast, anything in the
	 * read-locked region is ok to be re-ordered into the
	 * write side. As such, rely on RELEASE semantics.
	 */
	DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem);
	tmp = atomic_long_fetch_add_release(
		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
	rwsem_set_reader_owned(sem);
	if (tmp & RWSEM_FLAG_WAITERS)
		rwsem_downgrade_wake(sem);
}

#else /* !CONFIG_PREEMPT_RT */

#define RT_MUTEX_BUILD_MUTEX
#include "rtmutex.c"

#define rwbase_set_and_save_current_state(state)	\
	set_current_state(state)

#define rwbase_restore_current_state()			\
	__set_current_state(TASK_RUNNING)

#define rwbase_rtmutex_lock_state(rtm, state)		\
	__rt_mutex_lock(rtm, state)

#define rwbase_rtmutex_slowlock_locked(rtm, state)	\
	__rt_mutex_slowlock_locked(rtm, NULL, state)

#define rwbase_rtmutex_unlock(rtm)			\
	__rt_mutex_unlock(rtm)

#define rwbase_rtmutex_trylock(rtm)			\
	__rt_mutex_trylock(rtm)

#define rwbase_signal_pending_state(state, current)	\
	signal_pending_state(state, current)

#define rwbase_schedule()				\
	schedule()

#include "rwbase_rt.c"

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __rwsem_init(struct rw_semaphore *sem, const char *name,
		  struct lock_class_key *key)
{
	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
	lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP);
}
EXPORT_SYMBOL(__rwsem_init);
#endif

static inline void __down_read(struct rw_semaphore *sem)
{
	rwbase_read_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE);
}

static inline int __down_read_interruptible(struct rw_semaphore *sem)
{
	return rwbase_read_lock(&sem->rwbase, TASK_INTERRUPTIBLE);
}

static inline int __down_read_killable(struct rw_semaphore *sem)
{
	return rwbase_read_lock(&sem->rwbase, TASK_KILLABLE);
}

static inline int __down_read_trylock(struct rw_semaphore *sem)
{
	return rwbase_read_trylock(&sem->rwbase);
}

static inline void __up_read(struct rw_semaphore *sem)
{
	rwbase_read_unlock(&sem->rwbase, TASK_NORMAL);
}

static inline void __sched __down_write(struct rw_semaphore *sem)
{
	rwbase_write_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE);
}

static inline int __sched __down_write_killable(struct rw_semaphore *sem)
{
	return rwbase_write_lock(&sem->rwbase, TASK_KILLABLE);
}

static inline int __down_write_trylock(struct rw_semaphore *sem)
{
	return rwbase_write_trylock(&sem->rwbase);
}

static inline void __up_write(struct rw_semaphore *sem)
{
	rwbase_write_unlock(&sem->rwbase);
}

static inline void __downgrade_write(struct rw_semaphore *sem)
{
	rwbase_write_downgrade(&sem->rwbase);
}

/* Debug stubs for the common API */
#define DEBUG_RWSEMS_WARN_ON(c, sem)

static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
					    struct task_struct *owner)
{
}

static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
{
	int count = atomic_read(&sem->rwbase.readers);

	return count < 0 && count != READER_BIAS;
}

#endif /* CONFIG_PREEMPT_RT */

/*
 * lock for reading
 */
void __sched down_read(struct rw_semaphore *sem)
{
	might_sleep();
	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);

	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
}
EXPORT_SYMBOL(down_read);

int __sched down_read_interruptible(struct rw_semaphore *sem)
{
	might_sleep();
	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);

	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_interruptible)) {
		rwsem_release(&sem->dep_map, _RET_IP_);
		return -EINTR;
	}

	return 0;
}
EXPORT_SYMBOL(down_read_interruptible);

int __sched down_read_killable(struct rw_semaphore *sem)
{
	might_sleep();
	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);

	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
		rwsem_release(&sem->dep_map, _RET_IP_);
		return -EINTR;
	}

	return 0;
}
EXPORT_SYMBOL(down_read_killable);

/*
 * trylock for reading -- returns 1 if successful, 0 if contention
 */
int down_read_trylock(struct rw_semaphore *sem)
{
	int ret = __down_read_trylock(sem);

	if (ret == 1)
		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
	return ret;
}
EXPORT_SYMBOL(down_read_trylock);

/*
 * lock for writing
 */
void __sched down_write(struct rw_semaphore *sem)
{
	might_sleep();
	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
}
EXPORT_SYMBOL(down_write);

/*
 * lock for writing
 */
int __sched down_write_killable(struct rw_semaphore *sem)
{
	might_sleep();
	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);

	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
				  __down_write_killable)) {
		rwsem_release(&sem->dep_map, _RET_IP_);
		return -EINTR;
	}

	return 0;
}
EXPORT_SYMBOL(down_write_killable);

/*
 * trylock for writing -- returns 1 if successful, 0 if contention
 */
int down_write_trylock(struct rw_semaphore *sem)
{
	int ret = __down_write_trylock(sem);

	if (ret == 1)
		rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);

	return ret;
}
EXPORT_SYMBOL(down_write_trylock);

/*
 * release a read lock
 */
void up_read(struct rw_semaphore *sem)
{
	rwsem_release(&sem->dep_map, _RET_IP_);
	__up_read(sem);
}
EXPORT_SYMBOL(up_read);

/*
 * release a write lock
 */
void up_write(struct rw_semaphore *sem)
{
	rwsem_release(&sem->dep_map, _RET_IP_);
	__up_write(sem);
}
EXPORT_SYMBOL(up_write);

/*
 * downgrade write lock to read lock
 */
void downgrade_write(struct rw_semaphore *sem)
{
	lock_downgrade(&sem->dep_map, _RET_IP_);
	__downgrade_write(sem);
}
EXPORT_SYMBOL(downgrade_write);

#ifdef CONFIG_DEBUG_LOCK_ALLOC

void down_read_nested(struct rw_semaphore *sem, int subclass)
{
	might_sleep();
	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
}
EXPORT_SYMBOL(down_read_nested);

int down_read_killable_nested(struct rw_semaphore *sem, int subclass)
{
	might_sleep();
	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);

	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
		rwsem_release(&sem->dep_map, _RET_IP_);
		return -EINTR;
	}

	return 0;
}
EXPORT_SYMBOL(down_read_killable_nested);

void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
{
	might_sleep();
	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
}
EXPORT_SYMBOL(_down_write_nest_lock);

void down_read_non_owner(struct rw_semaphore *sem)
{
	might_sleep();
	__down_read(sem);
	__rwsem_set_reader_owned(sem, NULL);
}
EXPORT_SYMBOL(down_read_non_owner);

void down_write_nested(struct rw_semaphore *sem, int subclass)
{
	might_sleep();
	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
}
EXPORT_SYMBOL(down_write_nested);

int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
{
	might_sleep();
	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);

	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
				  __down_write_killable)) {
		rwsem_release(&sem->dep_map, _RET_IP_);
		return -EINTR;
	}

	return 0;
}
EXPORT_SYMBOL(down_write_killable_nested);

void up_read_non_owner(struct rw_semaphore *sem)
{
	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
	__up_read(sem);
}
EXPORT_SYMBOL(up_read_non_owner);

#endif