summaryrefslogtreecommitdiff
path: root/src/backend/storage/lmgr/lmgr.c
blob: ee9b89a67262195fbac38a6c38427e5046fa9f4d (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
/*-------------------------------------------------------------------------
 *
 * lmgr.c
 *	  POSTGRES lock manager code
 *
 * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/storage/lmgr/lmgr.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include "access/subtrans.h"
#include "access/transam.h"
#include "access/xact.h"
#include "catalog/catalog.h"
#include "commands/progress.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/lmgr.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/sinvaladt.h"
#include "utils/inval.h"


/*
 * Per-backend counter for generating speculative insertion tokens.
 *
 * This may wrap around, but that's OK as it's only used for the short
 * duration between inserting a tuple and checking that there are no (unique)
 * constraint violations.  It's theoretically possible that a backend sees a
 * tuple that was speculatively inserted by another backend, but before it has
 * started waiting on the token, the other backend completes its insertion,
 * and then performs 2^32 unrelated insertions.  And after all that, the
 * first backend finally calls SpeculativeInsertionLockAcquire(), with the
 * intention of waiting for the first insertion to complete, but ends up
 * waiting for the latest unrelated insertion instead.  Even then, nothing
 * particularly bad happens: in the worst case they deadlock, causing one of
 * the transactions to abort.
 */
static uint32 speculativeInsertionToken = 0;


/*
 * Struct to hold context info for transaction lock waits.
 *
 * 'oper' is the operation that needs to wait for the other transaction; 'rel'
 * and 'ctid' specify the address of the tuple being waited for.
 */
typedef struct XactLockTableWaitInfo
{
	XLTW_Oper	oper;
	Relation	rel;
	ItemPointer ctid;
} XactLockTableWaitInfo;

static void XactLockTableWaitErrorCb(void *arg);

/*
 * RelationInitLockInfo
 *		Initializes the lock information in a relation descriptor.
 *
 *		relcache.c must call this during creation of any reldesc.
 */
void
RelationInitLockInfo(Relation relation)
{
	Assert(RelationIsValid(relation));
	Assert(OidIsValid(RelationGetRelid(relation)));

	relation->rd_lockInfo.lockRelId.relId = RelationGetRelid(relation);

	if (relation->rd_rel->relisshared)
		relation->rd_lockInfo.lockRelId.dbId = InvalidOid;
	else
		relation->rd_lockInfo.lockRelId.dbId = MyDatabaseId;
}

/*
 * SetLocktagRelationOid
 *		Set up a locktag for a relation, given only relation OID
 */
static inline void
SetLocktagRelationOid(LOCKTAG *tag, Oid relid)
{
	Oid			dbid;

	if (IsSharedRelation(relid))
		dbid = InvalidOid;
	else
		dbid = MyDatabaseId;

	SET_LOCKTAG_RELATION(*tag, dbid, relid);
}

/*
 *		LockRelationOid
 *
 * Lock a relation given only its OID.  This should generally be used
 * before attempting to open the relation's relcache entry.
 */
void
LockRelationOid(Oid relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;
	LOCALLOCK  *locallock;
	LockAcquireResult res;

	SetLocktagRelationOid(&tag, relid);

	res = LockAcquireExtended(&tag, lockmode, false, false, true, &locallock);

	/*
	 * Now that we have the lock, check for invalidation messages, so that we
	 * will update or flush any stale relcache entry before we try to use it.
	 * RangeVarGetRelid() specifically relies on us for this.  We can skip
	 * this in the not-uncommon case that we already had the same type of lock
	 * being requested, since then no one else could have modified the
	 * relcache entry in an undesirable way.  (In the case where our own xact
	 * modifies the rel, the relcache update happens via
	 * CommandCounterIncrement, not here.)
	 *
	 * However, in corner cases where code acts on tables (usually catalogs)
	 * recursively, we might get here while still processing invalidation
	 * messages in some outer execution of this function or a sibling.  The
	 * "cleared" status of the lock tells us whether we really are done
	 * absorbing relevant inval messages.
	 */
	if (res != LOCKACQUIRE_ALREADY_CLEAR)
	{
		AcceptInvalidationMessages();
		MarkLockClear(locallock);
	}
}

/*
 *		ConditionalLockRelationOid
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns true iff the lock was acquired.
 *
 * NOTE: we do not currently need conditional versions of all the
 * LockXXX routines in this file, but they could easily be added if needed.
 */
bool
ConditionalLockRelationOid(Oid relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;
	LOCALLOCK  *locallock;
	LockAcquireResult res;

	SetLocktagRelationOid(&tag, relid);

	res = LockAcquireExtended(&tag, lockmode, false, true, true, &locallock);

	if (res == LOCKACQUIRE_NOT_AVAIL)
		return false;

	/*
	 * Now that we have the lock, check for invalidation messages; see notes
	 * in LockRelationOid.
	 */
	if (res != LOCKACQUIRE_ALREADY_CLEAR)
	{
		AcceptInvalidationMessages();
		MarkLockClear(locallock);
	}

	return true;
}

/*
 *		LockRelationId
 *
 * Lock, given a LockRelId.  Same as LockRelationOid but take LockRelId as an
 * input.
 */
void
LockRelationId(LockRelId *relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;
	LOCALLOCK  *locallock;
	LockAcquireResult res;

	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);

	res = LockAcquireExtended(&tag, lockmode, false, false, true, &locallock);

	/*
	 * Now that we have the lock, check for invalidation messages; see notes
	 * in LockRelationOid.
	 */
	if (res != LOCKACQUIRE_ALREADY_CLEAR)
	{
		AcceptInvalidationMessages();
		MarkLockClear(locallock);
	}
}

/*
 *		UnlockRelationId
 *
 * Unlock, given a LockRelId.  This is preferred over UnlockRelationOid
 * for speed reasons.
 */
void
UnlockRelationId(LockRelId *relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);

	LockRelease(&tag, lockmode, false);
}

/*
 *		UnlockRelationOid
 *
 * Unlock, given only a relation Oid.  Use UnlockRelationId if you can.
 */
void
UnlockRelationOid(Oid relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SetLocktagRelationOid(&tag, relid);

	LockRelease(&tag, lockmode, false);
}

/*
 *		LockRelation
 *
 * This is a convenience routine for acquiring an additional lock on an
 * already-open relation.  Never try to do "relation_open(foo, NoLock)"
 * and then lock with this.
 */
void
LockRelation(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;
	LOCALLOCK  *locallock;
	LockAcquireResult res;

	SET_LOCKTAG_RELATION(tag,
						 relation->rd_lockInfo.lockRelId.dbId,
						 relation->rd_lockInfo.lockRelId.relId);

	res = LockAcquireExtended(&tag, lockmode, false, false, true, &locallock);

	/*
	 * Now that we have the lock, check for invalidation messages; see notes
	 * in LockRelationOid.
	 */
	if (res != LOCKACQUIRE_ALREADY_CLEAR)
	{
		AcceptInvalidationMessages();
		MarkLockClear(locallock);
	}
}

/*
 *		ConditionalLockRelation
 *
 * This is a convenience routine for acquiring an additional lock on an
 * already-open relation.  Never try to do "relation_open(foo, NoLock)"
 * and then lock with this.
 */
bool
ConditionalLockRelation(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;
	LOCALLOCK  *locallock;
	LockAcquireResult res;

	SET_LOCKTAG_RELATION(tag,
						 relation->rd_lockInfo.lockRelId.dbId,
						 relation->rd_lockInfo.lockRelId.relId);

	res = LockAcquireExtended(&tag, lockmode, false, true, true, &locallock);

	if (res == LOCKACQUIRE_NOT_AVAIL)
		return false;

	/*
	 * Now that we have the lock, check for invalidation messages; see notes
	 * in LockRelationOid.
	 */
	if (res != LOCKACQUIRE_ALREADY_CLEAR)
	{
		AcceptInvalidationMessages();
		MarkLockClear(locallock);
	}

	return true;
}

/*
 *		UnlockRelation
 *
 * This is a convenience routine for unlocking a relation without also
 * closing it.
 */
void
UnlockRelation(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag,
						 relation->rd_lockInfo.lockRelId.dbId,
						 relation->rd_lockInfo.lockRelId.relId);

	LockRelease(&tag, lockmode, false);
}

/*
 *		CheckRelationLockedByMe
 *
 * Returns true if current transaction holds a lock on 'relation' of mode
 * 'lockmode'.  If 'orstronger' is true, a stronger lockmode is also OK.
 * ("Stronger" is defined as "numerically higher", which is a bit
 * semantically dubious but is OK for the purposes we use this for.)
 */
bool
CheckRelationLockedByMe(Relation relation, LOCKMODE lockmode, bool orstronger)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag,
						 relation->rd_lockInfo.lockRelId.dbId,
						 relation->rd_lockInfo.lockRelId.relId);

	if (LockHeldByMe(&tag, lockmode))
		return true;

	if (orstronger)
	{
		LOCKMODE	slockmode;

		for (slockmode = lockmode + 1;
			 slockmode <= MaxLockMode;
			 slockmode++)
		{
			if (LockHeldByMe(&tag, slockmode))
			{
#ifdef NOT_USED
				/* Sometimes this might be useful for debugging purposes */
				elog(WARNING, "lock mode %s substituted for %s on relation %s",
					 GetLockmodeName(tag.locktag_lockmethodid, slockmode),
					 GetLockmodeName(tag.locktag_lockmethodid, lockmode),
					 RelationGetRelationName(relation));
#endif
				return true;
			}
		}
	}

	return false;
}

/*
 *		LockHasWaitersRelation
 *
 * This is a function to check whether someone else is waiting for a
 * lock which we are currently holding.
 */
bool
LockHasWaitersRelation(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag,
						 relation->rd_lockInfo.lockRelId.dbId,
						 relation->rd_lockInfo.lockRelId.relId);

	return LockHasWaiters(&tag, lockmode, false);
}

/*
 *		LockRelationIdForSession
 *
 * This routine grabs a session-level lock on the target relation.  The
 * session lock persists across transaction boundaries.  It will be removed
 * when UnlockRelationIdForSession() is called, or if an ereport(ERROR) occurs,
 * or if the backend exits.
 *
 * Note that one should also grab a transaction-level lock on the rel
 * in any transaction that actually uses the rel, to ensure that the
 * relcache entry is up to date.
 */
void
LockRelationIdForSession(LockRelId *relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);

	(void) LockAcquire(&tag, lockmode, true, false);
}

/*
 *		UnlockRelationIdForSession
 */
void
UnlockRelationIdForSession(LockRelId *relid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION(tag, relid->dbId, relid->relId);

	LockRelease(&tag, lockmode, true);
}

/*
 *		LockRelationForExtension
 *
 * This lock tag is used to interlock addition of pages to relations.
 * We need such locking because bufmgr/smgr definition of P_NEW is not
 * race-condition-proof.
 *
 * We assume the caller is already holding some type of regular lock on
 * the relation, so no AcceptInvalidationMessages call is needed here.
 */
void
LockRelationForExtension(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION_EXTEND(tag,
								relation->rd_lockInfo.lockRelId.dbId,
								relation->rd_lockInfo.lockRelId.relId);

	(void) LockAcquire(&tag, lockmode, false, false);
}

/*
 *		ConditionalLockRelationForExtension
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns true iff the lock was acquired.
 */
bool
ConditionalLockRelationForExtension(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION_EXTEND(tag,
								relation->rd_lockInfo.lockRelId.dbId,
								relation->rd_lockInfo.lockRelId.relId);

	return (LockAcquire(&tag, lockmode, false, true) != LOCKACQUIRE_NOT_AVAIL);
}

/*
 *		RelationExtensionLockWaiterCount
 *
 * Count the number of processes waiting for the given relation extension lock.
 */
int
RelationExtensionLockWaiterCount(Relation relation)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION_EXTEND(tag,
								relation->rd_lockInfo.lockRelId.dbId,
								relation->rd_lockInfo.lockRelId.relId);

	return LockWaiterCount(&tag);
}

/*
 *		UnlockRelationForExtension
 */
void
UnlockRelationForExtension(Relation relation, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_RELATION_EXTEND(tag,
								relation->rd_lockInfo.lockRelId.dbId,
								relation->rd_lockInfo.lockRelId.relId);

	LockRelease(&tag, lockmode, false);
}

/*
 *		LockDatabaseFrozenIds
 *
 * This allows one backend per database to execute vac_update_datfrozenxid().
 */
void
LockDatabaseFrozenIds(LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_DATABASE_FROZEN_IDS(tag, MyDatabaseId);

	(void) LockAcquire(&tag, lockmode, false, false);
}

/*
 *		LockPage
 *
 * Obtain a page-level lock.  This is currently used by some index access
 * methods to lock individual index pages.
 */
void
LockPage(Relation relation, BlockNumber blkno, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_PAGE(tag,
					 relation->rd_lockInfo.lockRelId.dbId,
					 relation->rd_lockInfo.lockRelId.relId,
					 blkno);

	(void) LockAcquire(&tag, lockmode, false, false);
}

/*
 *		ConditionalLockPage
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns true iff the lock was acquired.
 */
bool
ConditionalLockPage(Relation relation, BlockNumber blkno, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_PAGE(tag,
					 relation->rd_lockInfo.lockRelId.dbId,
					 relation->rd_lockInfo.lockRelId.relId,
					 blkno);

	return (LockAcquire(&tag, lockmode, false, true) != LOCKACQUIRE_NOT_AVAIL);
}

/*
 *		UnlockPage
 */
void
UnlockPage(Relation relation, BlockNumber blkno, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_PAGE(tag,
					 relation->rd_lockInfo.lockRelId.dbId,
					 relation->rd_lockInfo.lockRelId.relId,
					 blkno);

	LockRelease(&tag, lockmode, false);
}

/*
 *		LockTuple
 *
 * Obtain a tuple-level lock.  This is used in a less-than-intuitive fashion
 * because we can't afford to keep a separate lock in shared memory for every
 * tuple.  See heap_lock_tuple before using this!
 */
void
LockTuple(Relation relation, ItemPointer tid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_TUPLE(tag,
					  relation->rd_lockInfo.lockRelId.dbId,
					  relation->rd_lockInfo.lockRelId.relId,
					  ItemPointerGetBlockNumber(tid),
					  ItemPointerGetOffsetNumber(tid));

	(void) LockAcquire(&tag, lockmode, false, false);
}

/*
 *		ConditionalLockTuple
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns true iff the lock was acquired.
 */
bool
ConditionalLockTuple(Relation relation, ItemPointer tid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_TUPLE(tag,
					  relation->rd_lockInfo.lockRelId.dbId,
					  relation->rd_lockInfo.lockRelId.relId,
					  ItemPointerGetBlockNumber(tid),
					  ItemPointerGetOffsetNumber(tid));

	return (LockAcquire(&tag, lockmode, false, true) != LOCKACQUIRE_NOT_AVAIL);
}

/*
 *		UnlockTuple
 */
void
UnlockTuple(Relation relation, ItemPointer tid, LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_TUPLE(tag,
					  relation->rd_lockInfo.lockRelId.dbId,
					  relation->rd_lockInfo.lockRelId.relId,
					  ItemPointerGetBlockNumber(tid),
					  ItemPointerGetOffsetNumber(tid));

	LockRelease(&tag, lockmode, false);
}

/*
 *		XactLockTableInsert
 *
 * Insert a lock showing that the given transaction ID is running ---
 * this is done when an XID is acquired by a transaction or subtransaction.
 * The lock can then be used to wait for the transaction to finish.
 */
void
XactLockTableInsert(TransactionId xid)
{
	LOCKTAG		tag;

	SET_LOCKTAG_TRANSACTION(tag, xid);

	(void) LockAcquire(&tag, ExclusiveLock, false, false);
}

/*
 *		XactLockTableDelete
 *
 * Delete the lock showing that the given transaction ID is running.
 * (This is never used for main transaction IDs; those locks are only
 * released implicitly at transaction end.  But we do use it for subtrans IDs.)
 */
void
XactLockTableDelete(TransactionId xid)
{
	LOCKTAG		tag;

	SET_LOCKTAG_TRANSACTION(tag, xid);

	LockRelease(&tag, ExclusiveLock, false);
}

/*
 *		XactLockTableWait
 *
 * Wait for the specified transaction to commit or abort.  If an operation
 * is specified, an error context callback is set up.  If 'oper' is passed as
 * None, no error context callback is set up.
 *
 * Note that this does the right thing for subtransactions: if we wait on a
 * subtransaction, we will exit as soon as it aborts or its top parent commits.
 * It takes some extra work to ensure this, because to save on shared memory
 * the XID lock of a subtransaction is released when it ends, whether
 * successfully or unsuccessfully.  So we have to check if it's "still running"
 * and if so wait for its parent.
 */
void
XactLockTableWait(TransactionId xid, Relation rel, ItemPointer ctid,
				  XLTW_Oper oper)
{
	LOCKTAG		tag;
	XactLockTableWaitInfo info;
	ErrorContextCallback callback;
	bool		first = true;

	/*
	 * If an operation is specified, set up our verbose error context
	 * callback.
	 */
	if (oper != XLTW_None)
	{
		Assert(RelationIsValid(rel));
		Assert(ItemPointerIsValid(ctid));

		info.rel = rel;
		info.ctid = ctid;
		info.oper = oper;

		callback.callback = XactLockTableWaitErrorCb;
		callback.arg = &info;
		callback.previous = error_context_stack;
		error_context_stack = &callback;
	}

	for (;;)
	{
		Assert(TransactionIdIsValid(xid));
		Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));

		SET_LOCKTAG_TRANSACTION(tag, xid);

		(void) LockAcquire(&tag, ShareLock, false, false);

		LockRelease(&tag, ShareLock, false);

		if (!TransactionIdIsInProgress(xid))
			break;

		/*
		 * If the Xid belonged to a subtransaction, then the lock would have
		 * gone away as soon as it was finished; for correct tuple visibility,
		 * the right action is to wait on its parent transaction to go away.
		 * But instead of going levels up one by one, we can just wait for the
		 * topmost transaction to finish with the same end result, which also
		 * incurs less locktable traffic.
		 *
		 * Some uses of this function don't involve tuple visibility -- such
		 * as when building snapshots for logical decoding.  It is possible to
		 * see a transaction in ProcArray before it registers itself in the
		 * locktable.  The topmost transaction in that case is the same xid,
		 * so we try again after a short sleep.  (Don't sleep the first time
		 * through, to avoid slowing down the normal case.)
		 */
		if (!first)
			pg_usleep(1000L);
		first = false;
		xid = SubTransGetTopmostTransaction(xid);
	}

	if (oper != XLTW_None)
		error_context_stack = callback.previous;
}

/*
 *		ConditionalXactLockTableWait
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns true if the lock was acquired.
 */
bool
ConditionalXactLockTableWait(TransactionId xid)
{
	LOCKTAG		tag;
	bool		first = true;

	for (;;)
	{
		Assert(TransactionIdIsValid(xid));
		Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));

		SET_LOCKTAG_TRANSACTION(tag, xid);

		if (LockAcquire(&tag, ShareLock, false, true) == LOCKACQUIRE_NOT_AVAIL)
			return false;

		LockRelease(&tag, ShareLock, false);

		if (!TransactionIdIsInProgress(xid))
			break;

		/* See XactLockTableWait about this case */
		if (!first)
			pg_usleep(1000L);
		first = false;
		xid = SubTransGetTopmostTransaction(xid);
	}

	return true;
}

/*
 *		SpeculativeInsertionLockAcquire
 *
 * Insert a lock showing that the given transaction ID is inserting a tuple,
 * but hasn't yet decided whether it's going to keep it.  The lock can then be
 * used to wait for the decision to go ahead with the insertion, or aborting
 * it.
 *
 * The token is used to distinguish multiple insertions by the same
 * transaction.  It is returned to caller.
 */
uint32
SpeculativeInsertionLockAcquire(TransactionId xid)
{
	LOCKTAG		tag;

	speculativeInsertionToken++;

	/*
	 * Check for wrap-around. Zero means no token is held, so don't use that.
	 */
	if (speculativeInsertionToken == 0)
		speculativeInsertionToken = 1;

	SET_LOCKTAG_SPECULATIVE_INSERTION(tag, xid, speculativeInsertionToken);

	(void) LockAcquire(&tag, ExclusiveLock, false, false);

	return speculativeInsertionToken;
}

/*
 *		SpeculativeInsertionLockRelease
 *
 * Delete the lock showing that the given transaction is speculatively
 * inserting a tuple.
 */
void
SpeculativeInsertionLockRelease(TransactionId xid)
{
	LOCKTAG		tag;

	SET_LOCKTAG_SPECULATIVE_INSERTION(tag, xid, speculativeInsertionToken);

	LockRelease(&tag, ExclusiveLock, false);
}

/*
 *		SpeculativeInsertionWait
 *
 * Wait for the specified transaction to finish or abort the insertion of a
 * tuple.
 */
void
SpeculativeInsertionWait(TransactionId xid, uint32 token)
{
	LOCKTAG		tag;

	SET_LOCKTAG_SPECULATIVE_INSERTION(tag, xid, token);

	Assert(TransactionIdIsValid(xid));
	Assert(token != 0);

	(void) LockAcquire(&tag, ShareLock, false, false);
	LockRelease(&tag, ShareLock, false);
}

/*
 * XactLockTableWaitErrorCb
 *		Error context callback for transaction lock waits.
 */
static void
XactLockTableWaitErrorCb(void *arg)
{
	XactLockTableWaitInfo *info = (XactLockTableWaitInfo *) arg;

	/*
	 * We would like to print schema name too, but that would require a
	 * syscache lookup.
	 */
	if (info->oper != XLTW_None &&
		ItemPointerIsValid(info->ctid) && RelationIsValid(info->rel))
	{
		const char *cxt;

		switch (info->oper)
		{
			case XLTW_Update:
				cxt = gettext_noop("while updating tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_Delete:
				cxt = gettext_noop("while deleting tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_Lock:
				cxt = gettext_noop("while locking tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_LockUpdated:
				cxt = gettext_noop("while locking updated version (%u,%u) of tuple in relation \"%s\"");
				break;
			case XLTW_InsertIndex:
				cxt = gettext_noop("while inserting index tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_InsertIndexUnique:
				cxt = gettext_noop("while checking uniqueness of tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_FetchUpdated:
				cxt = gettext_noop("while rechecking updated tuple (%u,%u) in relation \"%s\"");
				break;
			case XLTW_RecheckExclusionConstr:
				cxt = gettext_noop("while checking exclusion constraint on tuple (%u,%u) in relation \"%s\"");
				break;

			default:
				return;
		}

		errcontext(cxt,
				   ItemPointerGetBlockNumber(info->ctid),
				   ItemPointerGetOffsetNumber(info->ctid),
				   RelationGetRelationName(info->rel));
	}
}

/*
 * WaitForLockersMultiple
 *		Wait until no transaction holds locks that conflict with the given
 *		locktags at the given lockmode.
 *
 * To do this, obtain the current list of lockers, and wait on their VXIDs
 * until they are finished.
 *
 * Note we don't try to acquire the locks on the given locktags, only the
 * VXIDs and XIDs of their lock holders; if somebody grabs a conflicting lock
 * on the objects after we obtained our initial list of lockers, we will not
 * wait for them.
 */
void
WaitForLockersMultiple(List *locktags, LOCKMODE lockmode, bool progress)
{
	List	   *holders = NIL;
	ListCell   *lc;
	int			total = 0;
	int			done = 0;

	/* Done if no locks to wait for */
	if (locktags == NIL)
		return;

	/* Collect the transactions we need to wait on */
	foreach(lc, locktags)
	{
		LOCKTAG    *locktag = lfirst(lc);
		int			count;

		holders = lappend(holders,
						  GetLockConflicts(locktag, lockmode,
										   progress ? &count : NULL));
		if (progress)
			total += count;
	}

	if (progress)
		pgstat_progress_update_param(PROGRESS_WAITFOR_TOTAL, total);

	/*
	 * Note: GetLockConflicts() never reports our own xid, hence we need not
	 * check for that.  Also, prepared xacts are reported and awaited.
	 */

	/* Finally wait for each such transaction to complete */
	foreach(lc, holders)
	{
		VirtualTransactionId *lockholders = lfirst(lc);

		while (VirtualTransactionIdIsValid(*lockholders))
		{
			/* If requested, publish who we're going to wait for. */
			if (progress)
			{
				PGPROC	   *holder = BackendIdGetProc(lockholders->backendId);

				if (holder)
					pgstat_progress_update_param(PROGRESS_WAITFOR_CURRENT_PID,
												 holder->pid);
			}
			VirtualXactLock(*lockholders, true);
			lockholders++;

			if (progress)
				pgstat_progress_update_param(PROGRESS_WAITFOR_DONE, ++done);
		}
	}
	if (progress)
	{
		const int	index[] = {
			PROGRESS_WAITFOR_TOTAL,
			PROGRESS_WAITFOR_DONE,
			PROGRESS_WAITFOR_CURRENT_PID
		};
		const int64 values[] = {
			0, 0, 0
		};

		pgstat_progress_update_multi_param(3, index, values);
	}

	list_free_deep(holders);
}

/*
 * WaitForLockers
 *
 * Same as WaitForLockersMultiple, for a single lock tag.
 */
void
WaitForLockers(LOCKTAG heaplocktag, LOCKMODE lockmode, bool progress)
{
	List	   *l;

	l = list_make1(&heaplocktag);
	WaitForLockersMultiple(l, lockmode, progress);
	list_free(l);
}


/*
 *		LockDatabaseObject
 *
 * Obtain a lock on a general object of the current database.  Don't use
 * this for shared objects (such as tablespaces).  It's unwise to apply it
 * to relations, also, since a lock taken this way will NOT conflict with
 * locks taken via LockRelation and friends.
 */
void
LockDatabaseObject(Oid classid, Oid objid, uint16 objsubid,
				   LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   MyDatabaseId,
					   classid,
					   objid,
					   objsubid);

	(void) LockAcquire(&tag, lockmode, false, false);

	/* Make sure syscaches are up-to-date with any changes we waited for */
	AcceptInvalidationMessages();
}

/*
 *		UnlockDatabaseObject
 */
void
UnlockDatabaseObject(Oid classid, Oid objid, uint16 objsubid,
					 LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   MyDatabaseId,
					   classid,
					   objid,
					   objsubid);

	LockRelease(&tag, lockmode, false);
}

/*
 *		LockSharedObject
 *
 * Obtain a lock on a shared-across-databases object.
 */
void
LockSharedObject(Oid classid, Oid objid, uint16 objsubid,
				 LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   InvalidOid,
					   classid,
					   objid,
					   objsubid);

	(void) LockAcquire(&tag, lockmode, false, false);

	/* Make sure syscaches are up-to-date with any changes we waited for */
	AcceptInvalidationMessages();
}

/*
 *		UnlockSharedObject
 */
void
UnlockSharedObject(Oid classid, Oid objid, uint16 objsubid,
				   LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   InvalidOid,
					   classid,
					   objid,
					   objsubid);

	LockRelease(&tag, lockmode, false);
}

/*
 *		LockSharedObjectForSession
 *
 * Obtain a session-level lock on a shared-across-databases object.
 * See LockRelationIdForSession for notes about session-level locks.
 */
void
LockSharedObjectForSession(Oid classid, Oid objid, uint16 objsubid,
						   LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   InvalidOid,
					   classid,
					   objid,
					   objsubid);

	(void) LockAcquire(&tag, lockmode, true, false);
}

/*
 *		UnlockSharedObjectForSession
 */
void
UnlockSharedObjectForSession(Oid classid, Oid objid, uint16 objsubid,
							 LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_OBJECT(tag,
					   InvalidOid,
					   classid,
					   objid,
					   objsubid);

	LockRelease(&tag, lockmode, true);
}

/*
 *		LockApplyTransactionForSession
 *
 * Obtain a session-level lock on a transaction being applied on a logical
 * replication subscriber. See LockRelationIdForSession for notes about
 * session-level locks.
 */
void
LockApplyTransactionForSession(Oid suboid, TransactionId xid, uint16 objid,
							   LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_APPLY_TRANSACTION(tag,
								  MyDatabaseId,
								  suboid,
								  xid,
								  objid);

	(void) LockAcquire(&tag, lockmode, true, false);
}

/*
 *		UnlockApplyTransactionForSession
 */
void
UnlockApplyTransactionForSession(Oid suboid, TransactionId xid, uint16 objid,
								 LOCKMODE lockmode)
{
	LOCKTAG		tag;

	SET_LOCKTAG_APPLY_TRANSACTION(tag,
								  MyDatabaseId,
								  suboid,
								  xid,
								  objid);

	LockRelease(&tag, lockmode, true);
}

/*
 * Append a description of a lockable object to buf.
 *
 * Ideally we would print names for the numeric values, but that requires
 * getting locks on system tables, which might cause problems since this is
 * typically used to report deadlock situations.
 */
void
DescribeLockTag(StringInfo buf, const LOCKTAG *tag)
{
	switch ((LockTagType) tag->locktag_type)
	{
		case LOCKTAG_RELATION:
			appendStringInfo(buf,
							 _("relation %u of database %u"),
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_RELATION_EXTEND:
			appendStringInfo(buf,
							 _("extension of relation %u of database %u"),
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_DATABASE_FROZEN_IDS:
			appendStringInfo(buf,
							 _("pg_database.datfrozenxid of database %u"),
							 tag->locktag_field1);
			break;
		case LOCKTAG_PAGE:
			appendStringInfo(buf,
							 _("page %u of relation %u of database %u"),
							 tag->locktag_field3,
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_TUPLE:
			appendStringInfo(buf,
							 _("tuple (%u,%u) of relation %u of database %u"),
							 tag->locktag_field3,
							 tag->locktag_field4,
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_TRANSACTION:
			appendStringInfo(buf,
							 _("transaction %u"),
							 tag->locktag_field1);
			break;
		case LOCKTAG_VIRTUALTRANSACTION:
			appendStringInfo(buf,
							 _("virtual transaction %d/%u"),
							 tag->locktag_field1,
							 tag->locktag_field2);
			break;
		case LOCKTAG_SPECULATIVE_TOKEN:
			appendStringInfo(buf,
							 _("speculative token %u of transaction %u"),
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_OBJECT:
			appendStringInfo(buf,
							 _("object %u of class %u of database %u"),
							 tag->locktag_field3,
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		case LOCKTAG_USERLOCK:
			/* reserved for old contrib code, now on pgfoundry */
			appendStringInfo(buf,
							 _("user lock [%u,%u,%u]"),
							 tag->locktag_field1,
							 tag->locktag_field2,
							 tag->locktag_field3);
			break;
		case LOCKTAG_ADVISORY:
			appendStringInfo(buf,
							 _("advisory lock [%u,%u,%u,%u]"),
							 tag->locktag_field1,
							 tag->locktag_field2,
							 tag->locktag_field3,
							 tag->locktag_field4);
			break;
		case LOCKTAG_APPLY_TRANSACTION:
			appendStringInfo(buf,
							 _("remote transaction %u of subscription %u of database %u"),
							 tag->locktag_field3,
							 tag->locktag_field2,
							 tag->locktag_field1);
			break;
		default:
			appendStringInfo(buf,
							 _("unrecognized locktag type %d"),
							 (int) tag->locktag_type);
			break;
	}
}

/*
 * GetLockNameFromTagType
 *
 *	Given locktag type, return the corresponding lock name.
 */
const char *
GetLockNameFromTagType(uint16 locktag_type)
{
	if (locktag_type > LOCKTAG_LAST_TYPE)
		return "???";
	return LockTagTypeNames[locktag_type];
}