summaryrefslogtreecommitdiffstats
path: root/src/backend/storage/lmgr/proc.c
blob: c50a419a5469a6f5eca1d05b0ccb0d3623ad1f61 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
/*-------------------------------------------------------------------------
 *
 * proc.c
 *	  routines to manage per-process shared memory data structure
 *
 * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/storage/lmgr/proc.c
 *
 *-------------------------------------------------------------------------
 */
/*
 * Interface (a):
 *		ProcSleep(), ProcWakeup(),
 *		ProcQueueAlloc() -- create a shm queue for sleeping processes
 *		ProcQueueInit() -- create a queue without allocing memory
 *
 * Waiting for a lock causes the backend to be put to sleep.  Whoever releases
 * the lock wakes the process up again (and gives it an error code so it knows
 * whether it was awoken on an error condition).
 *
 * Interface (b):
 *
 * ProcReleaseLocks -- frees the locks associated with current transaction
 *
 * ProcKill -- destroys the shared memory state (and locks)
 * associated with the process.
 */
#include "postgres.h"

#include <signal.h>
#include <unistd.h>
#include <sys/time.h>

#include "access/transam.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "replication/slot.h"
#include "replication/syncrep.h"
#include "replication/walsender.h"
#include "storage/condition_variable.h"
#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/pmsignal.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/procsignal.h"
#include "storage/spin.h"
#include "storage/standby.h"
#include "utils/timeout.h"
#include "utils/timestamp.h"

/* GUC variables */
int			DeadlockTimeout = 1000;
int			StatementTimeout = 0;
int			LockTimeout = 0;
int			IdleInTransactionSessionTimeout = 0;
int			IdleSessionTimeout = 0;
bool		log_lock_waits = false;

/* Pointer to this process's PGPROC struct, if any */
PGPROC	   *MyProc = NULL;

/*
 * This spinlock protects the freelist of recycled PGPROC structures.
 * We cannot use an LWLock because the LWLock manager depends on already
 * having a PGPROC and a wait semaphore!  But these structures are touched
 * relatively infrequently (only at backend startup or shutdown) and not for
 * very long, so a spinlock is okay.
 */
NON_EXEC_STATIC slock_t *ProcStructLock = NULL;

/* Pointers to shared-memory structures */
PROC_HDR   *ProcGlobal = NULL;
NON_EXEC_STATIC PGPROC *AuxiliaryProcs = NULL;
PGPROC	   *PreparedXactProcs = NULL;

/* If we are waiting for a lock, this points to the associated LOCALLOCK */
static LOCALLOCK *lockAwaited = NULL;

static DeadLockState deadlock_state = DS_NOT_YET_CHECKED;

/* Is a deadlock check pending? */
static volatile sig_atomic_t got_deadlock_timeout;

static void RemoveProcFromArray(int code, Datum arg);
static void ProcKill(int code, Datum arg);
static void AuxiliaryProcKill(int code, Datum arg);
static void CheckDeadLock(void);


/*
 * Report shared-memory space needed by InitProcGlobal.
 */
Size
ProcGlobalShmemSize(void)
{
	Size		size = 0;
	Size		TotalProcs =
	add_size(MaxBackends, add_size(NUM_AUXILIARY_PROCS, max_prepared_xacts));

	/* ProcGlobal */
	size = add_size(size, sizeof(PROC_HDR));
	size = add_size(size, mul_size(TotalProcs, sizeof(PGPROC)));
	size = add_size(size, sizeof(slock_t));

	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->xids)));
	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->subxidStates)));
	size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->statusFlags)));

	return size;
}

/*
 * Report number of semaphores needed by InitProcGlobal.
 */
int
ProcGlobalSemas(void)
{
	/*
	 * We need a sema per backend (including autovacuum), plus one for each
	 * auxiliary process.
	 */
	return MaxBackends + NUM_AUXILIARY_PROCS;
}

/*
 * InitProcGlobal -
 *	  Initialize the global process table during postmaster or standalone
 *	  backend startup.
 *
 *	  We also create all the per-process semaphores we will need to support
 *	  the requested number of backends.  We used to allocate semaphores
 *	  only when backends were actually started up, but that is bad because
 *	  it lets Postgres fail under load --- a lot of Unix systems are
 *	  (mis)configured with small limits on the number of semaphores, and
 *	  running out when trying to start another backend is a common failure.
 *	  So, now we grab enough semaphores to support the desired max number
 *	  of backends immediately at initialization --- if the sysadmin has set
 *	  MaxConnections, max_worker_processes, max_wal_senders, or
 *	  autovacuum_max_workers higher than his kernel will support, he'll
 *	  find out sooner rather than later.
 *
 *	  Another reason for creating semaphores here is that the semaphore
 *	  implementation typically requires us to create semaphores in the
 *	  postmaster, not in backends.
 *
 * Note: this is NOT called by individual backends under a postmaster,
 * not even in the EXEC_BACKEND case.  The ProcGlobal and AuxiliaryProcs
 * pointers must be propagated specially for EXEC_BACKEND operation.
 */
void
InitProcGlobal(void)
{
	PGPROC	   *procs;
	int			i,
				j;
	bool		found;
	uint32		TotalProcs = MaxBackends + NUM_AUXILIARY_PROCS + max_prepared_xacts;

	/* Create the ProcGlobal shared structure */
	ProcGlobal = (PROC_HDR *)
		ShmemInitStruct("Proc Header", sizeof(PROC_HDR), &found);
	Assert(!found);

	/*
	 * Initialize the data structures.
	 */
	ProcGlobal->spins_per_delay = DEFAULT_SPINS_PER_DELAY;
	ProcGlobal->freeProcs = NULL;
	ProcGlobal->autovacFreeProcs = NULL;
	ProcGlobal->bgworkerFreeProcs = NULL;
	ProcGlobal->walsenderFreeProcs = NULL;
	ProcGlobal->startupProc = NULL;
	ProcGlobal->startupProcPid = 0;
	ProcGlobal->startupBufferPinWaitBufId = -1;
	ProcGlobal->walwriterLatch = NULL;
	ProcGlobal->checkpointerLatch = NULL;
	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);

	/*
	 * Create and initialize all the PGPROC structures we'll need.  There are
	 * five separate consumers: (1) normal backends, (2) autovacuum workers
	 * and the autovacuum launcher, (3) background workers, (4) auxiliary
	 * processes, and (5) prepared transactions.  Each PGPROC structure is
	 * dedicated to exactly one of these purposes, and they do not move
	 * between groups.
	 */
	procs = (PGPROC *) ShmemAlloc(TotalProcs * sizeof(PGPROC));
	MemSet(procs, 0, TotalProcs * sizeof(PGPROC));
	ProcGlobal->allProcs = procs;
	/* XXX allProcCount isn't really all of them; it excludes prepared xacts */
	ProcGlobal->allProcCount = MaxBackends + NUM_AUXILIARY_PROCS;

	/*
	 * Allocate arrays mirroring PGPROC fields in a dense manner. See
	 * PROC_HDR.
	 *
	 * XXX: It might make sense to increase padding for these arrays, given
	 * how hotly they are accessed.
	 */
	ProcGlobal->xids =
		(TransactionId *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->xids));
	MemSet(ProcGlobal->xids, 0, TotalProcs * sizeof(*ProcGlobal->xids));
	ProcGlobal->subxidStates = (XidCacheStatus *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->subxidStates));
	MemSet(ProcGlobal->subxidStates, 0, TotalProcs * sizeof(*ProcGlobal->subxidStates));
	ProcGlobal->statusFlags = (uint8 *) ShmemAlloc(TotalProcs * sizeof(*ProcGlobal->statusFlags));
	MemSet(ProcGlobal->statusFlags, 0, TotalProcs * sizeof(*ProcGlobal->statusFlags));

	for (i = 0; i < TotalProcs; i++)
	{
		/* Common initialization for all PGPROCs, regardless of type. */

		/*
		 * Set up per-PGPROC semaphore, latch, and fpInfoLock.  Prepared xact
		 * dummy PGPROCs don't need these though - they're never associated
		 * with a real process
		 */
		if (i < MaxBackends + NUM_AUXILIARY_PROCS)
		{
			procs[i].sem = PGSemaphoreCreate();
			InitSharedLatch(&(procs[i].procLatch));
			LWLockInitialize(&(procs[i].fpInfoLock), LWTRANCHE_LOCK_FASTPATH);
		}
		procs[i].pgprocno = i;

		/*
		 * Newly created PGPROCs for normal backends, autovacuum and bgworkers
		 * must be queued up on the appropriate free list.  Because there can
		 * only ever be a small, fixed number of auxiliary processes, no free
		 * list is used in that case; InitAuxiliaryProcess() instead uses a
		 * linear search.   PGPROCs for prepared transactions are added to a
		 * free list by TwoPhaseShmemInit().
		 */
		if (i < MaxConnections)
		{
			/* PGPROC for normal backend, add to freeProcs list */
			procs[i].links.next = (SHM_QUEUE *) ProcGlobal->freeProcs;
			ProcGlobal->freeProcs = &procs[i];
			procs[i].procgloballist = &ProcGlobal->freeProcs;
		}
		else if (i < MaxConnections + autovacuum_max_workers + 1)
		{
			/* PGPROC for AV launcher/worker, add to autovacFreeProcs list */
			procs[i].links.next = (SHM_QUEUE *) ProcGlobal->autovacFreeProcs;
			ProcGlobal->autovacFreeProcs = &procs[i];
			procs[i].procgloballist = &ProcGlobal->autovacFreeProcs;
		}
		else if (i < MaxConnections + autovacuum_max_workers + 1 + max_worker_processes)
		{
			/* PGPROC for bgworker, add to bgworkerFreeProcs list */
			procs[i].links.next = (SHM_QUEUE *) ProcGlobal->bgworkerFreeProcs;
			ProcGlobal->bgworkerFreeProcs = &procs[i];
			procs[i].procgloballist = &ProcGlobal->bgworkerFreeProcs;
		}
		else if (i < MaxBackends)
		{
			/* PGPROC for walsender, add to walsenderFreeProcs list */
			procs[i].links.next = (SHM_QUEUE *) ProcGlobal->walsenderFreeProcs;
			ProcGlobal->walsenderFreeProcs = &procs[i];
			procs[i].procgloballist = &ProcGlobal->walsenderFreeProcs;
		}

		/* Initialize myProcLocks[] shared memory queues. */
		for (j = 0; j < NUM_LOCK_PARTITIONS; j++)
			SHMQueueInit(&(procs[i].myProcLocks[j]));

		/* Initialize lockGroupMembers list. */
		dlist_init(&procs[i].lockGroupMembers);

		/*
		 * Initialize the atomic variables, otherwise, it won't be safe to
		 * access them for backends that aren't currently in use.
		 */
		pg_atomic_init_u32(&(procs[i].procArrayGroupNext), INVALID_PGPROCNO);
		pg_atomic_init_u32(&(procs[i].clogGroupNext), INVALID_PGPROCNO);
		pg_atomic_init_u64(&(procs[i].waitStart), 0);
	}

	/*
	 * Save pointers to the blocks of PGPROC structures reserved for auxiliary
	 * processes and prepared transactions.
	 */
	AuxiliaryProcs = &procs[MaxBackends];
	PreparedXactProcs = &procs[MaxBackends + NUM_AUXILIARY_PROCS];

	/* Create ProcStructLock spinlock, too */
	ProcStructLock = (slock_t *) ShmemAlloc(sizeof(slock_t));
	SpinLockInit(ProcStructLock);
}

/*
 * InitProcess -- initialize a per-process data structure for this backend
 */
void
InitProcess(void)
{
	PGPROC	   *volatile *procgloballist;

	/*
	 * ProcGlobal should be set up already (if we are a backend, we inherit
	 * this by fork() or EXEC_BACKEND mechanism from the postmaster).
	 */
	if (ProcGlobal == NULL)
		elog(PANIC, "proc header uninitialized");

	if (MyProc != NULL)
		elog(ERROR, "you already exist");

	/* Decide which list should supply our PGPROC. */
	if (IsAnyAutoVacuumProcess())
		procgloballist = &ProcGlobal->autovacFreeProcs;
	else if (IsBackgroundWorker)
		procgloballist = &ProcGlobal->bgworkerFreeProcs;
	else if (am_walsender)
		procgloballist = &ProcGlobal->walsenderFreeProcs;
	else
		procgloballist = &ProcGlobal->freeProcs;

	/*
	 * Try to get a proc struct from the appropriate free list.  If this
	 * fails, we must be out of PGPROC structures (not to mention semaphores).
	 *
	 * While we are holding the ProcStructLock, also copy the current shared
	 * estimate of spins_per_delay to local storage.
	 */
	SpinLockAcquire(ProcStructLock);

	set_spins_per_delay(ProcGlobal->spins_per_delay);

	MyProc = *procgloballist;

	if (MyProc != NULL)
	{
		*procgloballist = (PGPROC *) MyProc->links.next;
		SpinLockRelease(ProcStructLock);
	}
	else
	{
		/*
		 * If we reach here, all the PGPROCs are in use.  This is one of the
		 * possible places to detect "too many backends", so give the standard
		 * error message.  XXX do we need to give a different failure message
		 * in the autovacuum case?
		 */
		SpinLockRelease(ProcStructLock);
		if (am_walsender)
			ereport(FATAL,
					(errcode(ERRCODE_TOO_MANY_CONNECTIONS),
					 errmsg("number of requested standby connections exceeds max_wal_senders (currently %d)",
							max_wal_senders)));
		ereport(FATAL,
				(errcode(ERRCODE_TOO_MANY_CONNECTIONS),
				 errmsg("sorry, too many clients already")));
	}

	/*
	 * Cross-check that the PGPROC is of the type we expect; if this were not
	 * the case, it would get returned to the wrong list.
	 */
	Assert(MyProc->procgloballist == procgloballist);

	/*
	 * Now that we have a PGPROC, mark ourselves as an active postmaster
	 * child; this is so that the postmaster can detect it if we exit without
	 * cleaning up.  (XXX autovac launcher currently doesn't participate in
	 * this; it probably should.)
	 */
	if (IsUnderPostmaster && !IsAutoVacuumLauncherProcess())
		MarkPostmasterChildActive();

	/*
	 * Initialize all fields of MyProc, except for those previously
	 * initialized by InitProcGlobal.
	 */
	SHMQueueElemInit(&(MyProc->links));
	MyProc->waitStatus = PROC_WAIT_STATUS_OK;
	MyProc->lxid = InvalidLocalTransactionId;
	MyProc->fpVXIDLock = false;
	MyProc->fpLocalTransactionId = InvalidLocalTransactionId;
	MyProc->xid = InvalidTransactionId;
	MyProc->xmin = InvalidTransactionId;
	MyProc->pid = MyProcPid;
	/* backendId, databaseId and roleId will be filled in later */
	MyProc->backendId = InvalidBackendId;
	MyProc->databaseId = InvalidOid;
	MyProc->roleId = InvalidOid;
	MyProc->tempNamespaceId = InvalidOid;
	MyProc->isBackgroundWorker = IsBackgroundWorker;
	MyProc->delayChkpt = 0;
	MyProc->statusFlags = 0;
	/* NB -- autovac launcher intentionally does not set IS_AUTOVACUUM */
	if (IsAutoVacuumWorkerProcess())
		MyProc->statusFlags |= PROC_IS_AUTOVACUUM;
	MyProc->lwWaiting = false;
	MyProc->lwWaitMode = 0;
	MyProc->waitLock = NULL;
	MyProc->waitProcLock = NULL;
	pg_atomic_write_u64(&MyProc->waitStart, 0);
#ifdef USE_ASSERT_CHECKING
	{
		int			i;

		/* Last process should have released all locks. */
		for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
			Assert(SHMQueueEmpty(&(MyProc->myProcLocks[i])));
	}
#endif
	MyProc->recoveryConflictPending = false;

	/* Initialize fields for sync rep */
	MyProc->waitLSN = 0;
	MyProc->syncRepState = SYNC_REP_NOT_WAITING;
	SHMQueueElemInit(&(MyProc->syncRepLinks));

	/* Initialize fields for group XID clearing. */
	MyProc->procArrayGroupMember = false;
	MyProc->procArrayGroupMemberXid = InvalidTransactionId;
	Assert(pg_atomic_read_u32(&MyProc->procArrayGroupNext) == INVALID_PGPROCNO);

	/* Check that group locking fields are in a proper initial state. */
	Assert(MyProc->lockGroupLeader == NULL);
	Assert(dlist_is_empty(&MyProc->lockGroupMembers));

	/* Initialize wait event information. */
	MyProc->wait_event_info = 0;

	/* Initialize fields for group transaction status update. */
	MyProc->clogGroupMember = false;
	MyProc->clogGroupMemberXid = InvalidTransactionId;
	MyProc->clogGroupMemberXidStatus = TRANSACTION_STATUS_IN_PROGRESS;
	MyProc->clogGroupMemberPage = -1;
	MyProc->clogGroupMemberLsn = InvalidXLogRecPtr;
	Assert(pg_atomic_read_u32(&MyProc->clogGroupNext) == INVALID_PGPROCNO);

	/*
	 * Acquire ownership of the PGPROC's latch, so that we can use WaitLatch
	 * on it.  That allows us to repoint the process latch, which so far
	 * points to process local one, to the shared one.
	 */
	OwnLatch(&MyProc->procLatch);
	SwitchToSharedLatch();

	/* now that we have a proc, report wait events to shared memory */
	pgstat_set_wait_event_storage(&MyProc->wait_event_info);

	/*
	 * We might be reusing a semaphore that belonged to a failed process. So
	 * be careful and reinitialize its value here.  (This is not strictly
	 * necessary anymore, but seems like a good idea for cleanliness.)
	 */
	PGSemaphoreReset(MyProc->sem);

	/*
	 * Arrange to clean up at backend exit.
	 */
	on_shmem_exit(ProcKill, 0);

	/*
	 * Now that we have a PGPROC, we could try to acquire locks, so initialize
	 * local state needed for LWLocks, and the deadlock checker.
	 */
	InitLWLockAccess();
	InitDeadLockChecking();
}

/*
 * InitProcessPhase2 -- make MyProc visible in the shared ProcArray.
 *
 * This is separate from InitProcess because we can't acquire LWLocks until
 * we've created a PGPROC, but in the EXEC_BACKEND case ProcArrayAdd won't
 * work until after we've done CreateSharedMemoryAndSemaphores.
 */
void
InitProcessPhase2(void)
{
	Assert(MyProc != NULL);

	/*
	 * Add our PGPROC to the PGPROC array in shared memory.
	 */
	ProcArrayAdd(MyProc);

	/*
	 * Arrange to clean that up at backend exit.
	 */
	on_shmem_exit(RemoveProcFromArray, 0);
}

/*
 * InitAuxiliaryProcess -- create a per-auxiliary-process data structure
 *
 * This is called by bgwriter and similar processes so that they will have a
 * MyProc value that's real enough to let them wait for LWLocks.  The PGPROC
 * and sema that are assigned are one of the extra ones created during
 * InitProcGlobal.
 *
 * Auxiliary processes are presently not expected to wait for real (lockmgr)
 * locks, so we need not set up the deadlock checker.  They are never added
 * to the ProcArray or the sinval messaging mechanism, either.  They also
 * don't get a VXID assigned, since this is only useful when we actually
 * hold lockmgr locks.
 *
 * Startup process however uses locks but never waits for them in the
 * normal backend sense. Startup process also takes part in sinval messaging
 * as a sendOnly process, so never reads messages from sinval queue. So
 * Startup process does have a VXID and does show up in pg_locks.
 */
void
InitAuxiliaryProcess(void)
{
	PGPROC	   *auxproc;
	int			proctype;

	/*
	 * ProcGlobal should be set up already (if we are a backend, we inherit
	 * this by fork() or EXEC_BACKEND mechanism from the postmaster).
	 */
	if (ProcGlobal == NULL || AuxiliaryProcs == NULL)
		elog(PANIC, "proc header uninitialized");

	if (MyProc != NULL)
		elog(ERROR, "you already exist");

	/*
	 * We use the ProcStructLock to protect assignment and releasing of
	 * AuxiliaryProcs entries.
	 *
	 * While we are holding the ProcStructLock, also copy the current shared
	 * estimate of spins_per_delay to local storage.
	 */
	SpinLockAcquire(ProcStructLock);

	set_spins_per_delay(ProcGlobal->spins_per_delay);

	/*
	 * Find a free auxproc ... *big* trouble if there isn't one ...
	 */
	for (proctype = 0; proctype < NUM_AUXILIARY_PROCS; proctype++)
	{
		auxproc = &AuxiliaryProcs[proctype];
		if (auxproc->pid == 0)
			break;
	}
	if (proctype >= NUM_AUXILIARY_PROCS)
	{
		SpinLockRelease(ProcStructLock);
		elog(FATAL, "all AuxiliaryProcs are in use");
	}

	/* Mark auxiliary proc as in use by me */
	/* use volatile pointer to prevent code rearrangement */
	((volatile PGPROC *) auxproc)->pid = MyProcPid;

	MyProc = auxproc;

	SpinLockRelease(ProcStructLock);

	/*
	 * Initialize all fields of MyProc, except for those previously
	 * initialized by InitProcGlobal.
	 */
	SHMQueueElemInit(&(MyProc->links));
	MyProc->waitStatus = PROC_WAIT_STATUS_OK;
	MyProc->lxid = InvalidLocalTransactionId;
	MyProc->fpVXIDLock = false;
	MyProc->fpLocalTransactionId = InvalidLocalTransactionId;
	MyProc->xid = InvalidTransactionId;
	MyProc->xmin = InvalidTransactionId;
	MyProc->backendId = InvalidBackendId;
	MyProc->databaseId = InvalidOid;
	MyProc->roleId = InvalidOid;
	MyProc->tempNamespaceId = InvalidOid;
	MyProc->isBackgroundWorker = IsBackgroundWorker;
	MyProc->delayChkpt = 0;
	MyProc->statusFlags = 0;
	MyProc->lwWaiting = false;
	MyProc->lwWaitMode = 0;
	MyProc->waitLock = NULL;
	MyProc->waitProcLock = NULL;
	pg_atomic_write_u64(&MyProc->waitStart, 0);
#ifdef USE_ASSERT_CHECKING
	{
		int			i;

		/* Last process should have released all locks. */
		for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
			Assert(SHMQueueEmpty(&(MyProc->myProcLocks[i])));
	}
#endif

	/*
	 * Acquire ownership of the PGPROC's latch, so that we can use WaitLatch
	 * on it.  That allows us to repoint the process latch, which so far
	 * points to process local one, to the shared one.
	 */
	OwnLatch(&MyProc->procLatch);
	SwitchToSharedLatch();

	/* now that we have a proc, report wait events to shared memory */
	pgstat_set_wait_event_storage(&MyProc->wait_event_info);

	/* Check that group locking fields are in a proper initial state. */
	Assert(MyProc->lockGroupLeader == NULL);
	Assert(dlist_is_empty(&MyProc->lockGroupMembers));

	/*
	 * We might be reusing a semaphore that belonged to a failed process. So
	 * be careful and reinitialize its value here.  (This is not strictly
	 * necessary anymore, but seems like a good idea for cleanliness.)
	 */
	PGSemaphoreReset(MyProc->sem);

	/*
	 * Arrange to clean up at process exit.
	 */
	on_shmem_exit(AuxiliaryProcKill, Int32GetDatum(proctype));
}

/*
 * Record the PID and PGPROC structures for the Startup process, for use in
 * ProcSendSignal().  See comments there for further explanation.
 */
void
PublishStartupProcessInformation(void)
{
	SpinLockAcquire(ProcStructLock);

	ProcGlobal->startupProc = MyProc;
	ProcGlobal->startupProcPid = MyProcPid;

	SpinLockRelease(ProcStructLock);
}

/*
 * Used from bufmgr to share the value of the buffer that Startup waits on,
 * or to reset the value to "not waiting" (-1). This allows processing
 * of recovery conflicts for buffer pins. Set is made before backends look
 * at this value, so locking not required, especially since the set is
 * an atomic integer set operation.
 */
void
SetStartupBufferPinWaitBufId(int bufid)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile PROC_HDR *procglobal = ProcGlobal;

	procglobal->startupBufferPinWaitBufId = bufid;
}

/*
 * Used by backends when they receive a request to check for buffer pin waits.
 */
int
GetStartupBufferPinWaitBufId(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile PROC_HDR *procglobal = ProcGlobal;

	return procglobal->startupBufferPinWaitBufId;
}

/*
 * Check whether there are at least N free PGPROC objects.
 *
 * Note: this is designed on the assumption that N will generally be small.
 */
bool
HaveNFreeProcs(int n)
{
	PGPROC	   *proc;

	SpinLockAcquire(ProcStructLock);

	proc = ProcGlobal->freeProcs;

	while (n > 0 && proc != NULL)
	{
		proc = (PGPROC *) proc->links.next;
		n--;
	}

	SpinLockRelease(ProcStructLock);

	return (n <= 0);
}

/*
 * Check if the current process is awaiting a lock.
 */
bool
IsWaitingForLock(void)
{
	if (lockAwaited == NULL)
		return false;

	return true;
}

/*
 * Cancel any pending wait for lock, when aborting a transaction, and revert
 * any strong lock count acquisition for a lock being acquired.
 *
 * (Normally, this would only happen if we accept a cancel/die
 * interrupt while waiting; but an ereport(ERROR) before or during the lock
 * wait is within the realm of possibility, too.)
 */
void
LockErrorCleanup(void)
{
	LWLock	   *partitionLock;
	DisableTimeoutParams timeouts[2];

	HOLD_INTERRUPTS();

	AbortStrongLockAcquire();

	/* Nothing to do if we weren't waiting for a lock */
	if (lockAwaited == NULL)
	{
		RESUME_INTERRUPTS();
		return;
	}

	/*
	 * Turn off the deadlock and lock timeout timers, if they are still
	 * running (see ProcSleep).  Note we must preserve the LOCK_TIMEOUT
	 * indicator flag, since this function is executed before
	 * ProcessInterrupts when responding to SIGINT; else we'd lose the
	 * knowledge that the SIGINT came from a lock timeout and not an external
	 * source.
	 */
	timeouts[0].id = DEADLOCK_TIMEOUT;
	timeouts[0].keep_indicator = false;
	timeouts[1].id = LOCK_TIMEOUT;
	timeouts[1].keep_indicator = true;
	disable_timeouts(timeouts, 2);

	/* Unlink myself from the wait queue, if on it (might not be anymore!) */
	partitionLock = LockHashPartitionLock(lockAwaited->hashcode);
	LWLockAcquire(partitionLock, LW_EXCLUSIVE);

	if (MyProc->links.next != NULL)
	{
		/* We could not have been granted the lock yet */
		RemoveFromWaitQueue(MyProc, lockAwaited->hashcode);
	}
	else
	{
		/*
		 * Somebody kicked us off the lock queue already.  Perhaps they
		 * granted us the lock, or perhaps they detected a deadlock. If they
		 * did grant us the lock, we'd better remember it in our local lock
		 * table.
		 */
		if (MyProc->waitStatus == PROC_WAIT_STATUS_OK)
			GrantAwaitedLock();
	}

	lockAwaited = NULL;

	LWLockRelease(partitionLock);

	RESUME_INTERRUPTS();
}


/*
 * ProcReleaseLocks() -- release locks associated with current transaction
 *			at main transaction commit or abort
 *
 * At main transaction commit, we release standard locks except session locks.
 * At main transaction abort, we release all locks including session locks.
 *
 * Advisory locks are released only if they are transaction-level;
 * session-level holds remain, whether this is a commit or not.
 *
 * At subtransaction commit, we don't release any locks (so this func is not
 * needed at all); we will defer the releasing to the parent transaction.
 * At subtransaction abort, we release all locks held by the subtransaction;
 * this is implemented by retail releasing of the locks under control of
 * the ResourceOwner mechanism.
 */
void
ProcReleaseLocks(bool isCommit)
{
	if (!MyProc)
		return;
	/* If waiting, get off wait queue (should only be needed after error) */
	LockErrorCleanup();
	/* Release standard locks, including session-level if aborting */
	LockReleaseAll(DEFAULT_LOCKMETHOD, !isCommit);
	/* Release transaction-level advisory locks */
	LockReleaseAll(USER_LOCKMETHOD, false);
}


/*
 * RemoveProcFromArray() -- Remove this process from the shared ProcArray.
 */
static void
RemoveProcFromArray(int code, Datum arg)
{
	Assert(MyProc != NULL);
	ProcArrayRemove(MyProc, InvalidTransactionId);
}

/*
 * ProcKill() -- Destroy the per-proc data structure for
 *		this process. Release any of its held LW locks.
 */
static void
ProcKill(int code, Datum arg)
{
	PGPROC	   *proc;
	PGPROC	   *volatile *procgloballist;

	Assert(MyProc != NULL);

	/* Make sure we're out of the sync rep lists */
	SyncRepCleanupAtProcExit();

#ifdef USE_ASSERT_CHECKING
	{
		int			i;

		/* Last process should have released all locks. */
		for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
			Assert(SHMQueueEmpty(&(MyProc->myProcLocks[i])));
	}
#endif

	/*
	 * Release any LW locks I am holding.  There really shouldn't be any, but
	 * it's cheap to check again before we cut the knees off the LWLock
	 * facility by releasing our PGPROC ...
	 */
	LWLockReleaseAll();

	/* Cancel any pending condition variable sleep, too */
	ConditionVariableCancelSleep();

	/* Make sure active replication slots are released */
	if (MyReplicationSlot != NULL)
		ReplicationSlotRelease();

	/* Also cleanup all the temporary slots. */
	ReplicationSlotCleanup();

	/*
	 * Detach from any lock group of which we are a member.  If the leader
	 * exist before all other group members, its PGPROC will remain allocated
	 * until the last group process exits; that process must return the
	 * leader's PGPROC to the appropriate list.
	 */
	if (MyProc->lockGroupLeader != NULL)
	{
		PGPROC	   *leader = MyProc->lockGroupLeader;
		LWLock	   *leader_lwlock = LockHashPartitionLockByProc(leader);

		LWLockAcquire(leader_lwlock, LW_EXCLUSIVE);
		Assert(!dlist_is_empty(&leader->lockGroupMembers));
		dlist_delete(&MyProc->lockGroupLink);
		if (dlist_is_empty(&leader->lockGroupMembers))
		{
			leader->lockGroupLeader = NULL;
			if (leader != MyProc)
			{
				procgloballist = leader->procgloballist;

				/* Leader exited first; return its PGPROC. */
				SpinLockAcquire(ProcStructLock);
				leader->links.next = (SHM_QUEUE *) *procgloballist;
				*procgloballist = leader;
				SpinLockRelease(ProcStructLock);
			}
		}
		else if (leader != MyProc)
			MyProc->lockGroupLeader = NULL;
		LWLockRelease(leader_lwlock);
	}

	/*
	 * Reset MyLatch to the process local one.  This is so that signal
	 * handlers et al can continue using the latch after the shared latch
	 * isn't ours anymore.
	 *
	 * Similarly, stop reporting wait events to MyProc->wait_event_info.
	 *
	 * After that clear MyProc and disown the shared latch.
	 */
	SwitchBackToLocalLatch();
	pgstat_reset_wait_event_storage();

	proc = MyProc;
	MyProc = NULL;
	DisownLatch(&proc->procLatch);

	procgloballist = proc->procgloballist;
	SpinLockAcquire(ProcStructLock);

	/*
	 * If we're still a member of a locking group, that means we're a leader
	 * which has somehow exited before its children.  The last remaining child
	 * will release our PGPROC.  Otherwise, release it now.
	 */
	if (proc->lockGroupLeader == NULL)
	{
		/* Since lockGroupLeader is NULL, lockGroupMembers should be empty. */
		Assert(dlist_is_empty(&proc->lockGroupMembers));

		/* Return PGPROC structure (and semaphore) to appropriate freelist */
		proc->links.next = (SHM_QUEUE *) *procgloballist;
		*procgloballist = proc;
	}

	/* Update shared estimate of spins_per_delay */
	ProcGlobal->spins_per_delay = update_spins_per_delay(ProcGlobal->spins_per_delay);

	SpinLockRelease(ProcStructLock);

	/*
	 * This process is no longer present in shared memory in any meaningful
	 * way, so tell the postmaster we've cleaned up acceptably well. (XXX
	 * autovac launcher should be included here someday)
	 */
	if (IsUnderPostmaster && !IsAutoVacuumLauncherProcess())
		MarkPostmasterChildInactive();

	/* wake autovac launcher if needed -- see comments in FreeWorkerInfo */
	if (AutovacuumLauncherPid != 0)
		kill(AutovacuumLauncherPid, SIGUSR2);
}

/*
 * AuxiliaryProcKill() -- Cut-down version of ProcKill for auxiliary
 *		processes (bgwriter, etc).  The PGPROC and sema are not released, only
 *		marked as not-in-use.
 */
static void
AuxiliaryProcKill(int code, Datum arg)
{
	int			proctype = DatumGetInt32(arg);
	PGPROC	   *auxproc PG_USED_FOR_ASSERTS_ONLY;
	PGPROC	   *proc;

	Assert(proctype >= 0 && proctype < NUM_AUXILIARY_PROCS);

	auxproc = &AuxiliaryProcs[proctype];

	Assert(MyProc == auxproc);

	/* Release any LW locks I am holding (see notes above) */
	LWLockReleaseAll();

	/* Cancel any pending condition variable sleep, too */
	ConditionVariableCancelSleep();

	/* look at the equivalent ProcKill() code for comments */
	SwitchBackToLocalLatch();
	pgstat_reset_wait_event_storage();

	proc = MyProc;
	MyProc = NULL;
	DisownLatch(&proc->procLatch);

	SpinLockAcquire(ProcStructLock);

	/* Mark auxiliary proc no longer in use */
	proc->pid = 0;

	/* Update shared estimate of spins_per_delay */
	ProcGlobal->spins_per_delay = update_spins_per_delay(ProcGlobal->spins_per_delay);

	SpinLockRelease(ProcStructLock);
}

/*
 * AuxiliaryPidGetProc -- get PGPROC for an auxiliary process
 * given its PID
 *
 * Returns NULL if not found.
 */
PGPROC *
AuxiliaryPidGetProc(int pid)
{
	PGPROC	   *result = NULL;
	int			index;

	if (pid == 0)				/* never match dummy PGPROCs */
		return NULL;

	for (index = 0; index < NUM_AUXILIARY_PROCS; index++)
	{
		PGPROC	   *proc = &AuxiliaryProcs[index];

		if (proc->pid == pid)
		{
			result = proc;
			break;
		}
	}
	return result;
}

/*
 * ProcQueue package: routines for putting processes to sleep
 *		and  waking them up
 */

/*
 * ProcQueueAlloc -- alloc/attach to a shared memory process queue
 *
 * Returns: a pointer to the queue
 * Side Effects: Initializes the queue if it wasn't there before
 */
#ifdef NOT_USED
PROC_QUEUE *
ProcQueueAlloc(const char *name)
{
	PROC_QUEUE *queue;
	bool		found;

	queue = (PROC_QUEUE *)
		ShmemInitStruct(name, sizeof(PROC_QUEUE), &found);

	if (!found)
		ProcQueueInit(queue);

	return queue;
}
#endif

/*
 * ProcQueueInit -- initialize a shared memory process queue
 */
void
ProcQueueInit(PROC_QUEUE *queue)
{
	SHMQueueInit(&(queue->links));
	queue->size = 0;
}


/*
 * ProcSleep -- put a process to sleep on the specified lock
 *
 * Caller must have set MyProc->heldLocks to reflect locks already held
 * on the lockable object by this process (under all XIDs).
 *
 * The lock table's partition lock must be held at entry, and will be held
 * at exit.
 *
 * Result: PROC_WAIT_STATUS_OK if we acquired the lock, PROC_WAIT_STATUS_ERROR if not (deadlock).
 *
 * ASSUME: that no one will fiddle with the queue until after
 *		we release the partition lock.
 *
 * NOTES: The process queue is now a priority queue for locking.
 */
ProcWaitStatus
ProcSleep(LOCALLOCK *locallock, LockMethod lockMethodTable)
{
	LOCKMODE	lockmode = locallock->tag.mode;
	LOCK	   *lock = locallock->lock;
	PROCLOCK   *proclock = locallock->proclock;
	uint32		hashcode = locallock->hashcode;
	LWLock	   *partitionLock = LockHashPartitionLock(hashcode);
	PROC_QUEUE *waitQueue = &(lock->waitProcs);
	LOCKMASK	myHeldLocks = MyProc->heldLocks;
	TimestampTz standbyWaitStart = 0;
	bool		early_deadlock = false;
	bool		allow_autovacuum_cancel = true;
	bool		logged_recovery_conflict = false;
	ProcWaitStatus myWaitStatus;
	PGPROC	   *proc;
	PGPROC	   *leader = MyProc->lockGroupLeader;
	int			i;

	/*
	 * If group locking is in use, locks held by members of my locking group
	 * need to be included in myHeldLocks.  This is not required for relation
	 * extension or page locks which conflict among group members. However,
	 * including them in myHeldLocks will give group members the priority to
	 * get those locks as compared to other backends which are also trying to
	 * acquire those locks.  OTOH, we can avoid giving priority to group
	 * members for that kind of locks, but there doesn't appear to be a clear
	 * advantage of the same.
	 */
	if (leader != NULL)
	{
		SHM_QUEUE  *procLocks = &(lock->procLocks);
		PROCLOCK   *otherproclock;

		otherproclock = (PROCLOCK *)
			SHMQueueNext(procLocks, procLocks, offsetof(PROCLOCK, lockLink));
		while (otherproclock != NULL)
		{
			if (otherproclock->groupLeader == leader)
				myHeldLocks |= otherproclock->holdMask;
			otherproclock = (PROCLOCK *)
				SHMQueueNext(procLocks, &otherproclock->lockLink,
							 offsetof(PROCLOCK, lockLink));
		}
	}

	/*
	 * Determine where to add myself in the wait queue.
	 *
	 * Normally I should go at the end of the queue.  However, if I already
	 * hold locks that conflict with the request of any previous waiter, put
	 * myself in the queue just in front of the first such waiter. This is not
	 * a necessary step, since deadlock detection would move me to before that
	 * waiter anyway; but it's relatively cheap to detect such a conflict
	 * immediately, and avoid delaying till deadlock timeout.
	 *
	 * Special case: if I find I should go in front of some waiter, check to
	 * see if I conflict with already-held locks or the requests before that
	 * waiter.  If not, then just grant myself the requested lock immediately.
	 * This is the same as the test for immediate grant in LockAcquire, except
	 * we are only considering the part of the wait queue before my insertion
	 * point.
	 */
	if (myHeldLocks != 0)
	{
		LOCKMASK	aheadRequests = 0;

		proc = (PGPROC *) waitQueue->links.next;
		for (i = 0; i < waitQueue->size; i++)
		{
			/*
			 * If we're part of the same locking group as this waiter, its
			 * locks neither conflict with ours nor contribute to
			 * aheadRequests.
			 */
			if (leader != NULL && leader == proc->lockGroupLeader)
			{
				proc = (PGPROC *) proc->links.next;
				continue;
			}
			/* Must he wait for me? */
			if (lockMethodTable->conflictTab[proc->waitLockMode] & myHeldLocks)
			{
				/* Must I wait for him ? */
				if (lockMethodTable->conflictTab[lockmode] & proc->heldLocks)
				{
					/*
					 * Yes, so we have a deadlock.  Easiest way to clean up
					 * correctly is to call RemoveFromWaitQueue(), but we
					 * can't do that until we are *on* the wait queue. So, set
					 * a flag to check below, and break out of loop.  Also,
					 * record deadlock info for later message.
					 */
					RememberSimpleDeadLock(MyProc, lockmode, lock, proc);
					early_deadlock = true;
					break;
				}
				/* I must go before this waiter.  Check special case. */
				if ((lockMethodTable->conflictTab[lockmode] & aheadRequests) == 0 &&
					!LockCheckConflicts(lockMethodTable, lockmode, lock,
										proclock))
				{
					/* Skip the wait and just grant myself the lock. */
					GrantLock(lock, proclock, lockmode);
					GrantAwaitedLock();
					return PROC_WAIT_STATUS_OK;
				}
				/* Break out of loop to put myself before him */
				break;
			}
			/* Nope, so advance to next waiter */
			aheadRequests |= LOCKBIT_ON(proc->waitLockMode);
			proc = (PGPROC *) proc->links.next;
		}

		/*
		 * If we fall out of loop normally, proc points to waitQueue head, so
		 * we will insert at tail of queue as desired.
		 */
	}
	else
	{
		/* I hold no locks, so I can't push in front of anyone. */
		proc = (PGPROC *) &(waitQueue->links);
	}

	/*
	 * Insert self into queue, ahead of the given proc (or at tail of queue).
	 */
	SHMQueueInsertBefore(&(proc->links), &(MyProc->links));
	waitQueue->size++;

	lock->waitMask |= LOCKBIT_ON(lockmode);

	/* Set up wait information in PGPROC object, too */
	MyProc->waitLock = lock;
	MyProc->waitProcLock = proclock;
	MyProc->waitLockMode = lockmode;

	MyProc->waitStatus = PROC_WAIT_STATUS_WAITING;

	/*
	 * If we detected deadlock, give up without waiting.  This must agree with
	 * CheckDeadLock's recovery code.
	 */
	if (early_deadlock)
	{
		RemoveFromWaitQueue(MyProc, hashcode);
		return PROC_WAIT_STATUS_ERROR;
	}

	/* mark that we are waiting for a lock */
	lockAwaited = locallock;

	/*
	 * Release the lock table's partition lock.
	 *
	 * NOTE: this may also cause us to exit critical-section state, possibly
	 * allowing a cancel/die interrupt to be accepted. This is OK because we
	 * have recorded the fact that we are waiting for a lock, and so
	 * LockErrorCleanup will clean up if cancel/die happens.
	 */
	LWLockRelease(partitionLock);

	/*
	 * Also, now that we will successfully clean up after an ereport, it's
	 * safe to check to see if there's a buffer pin deadlock against the
	 * Startup process.  Of course, that's only necessary if we're doing Hot
	 * Standby and are not the Startup process ourselves.
	 */
	if (RecoveryInProgress() && !InRecovery)
		CheckRecoveryConflictDeadlock();

	/* Reset deadlock_state before enabling the timeout handler */
	deadlock_state = DS_NOT_YET_CHECKED;
	got_deadlock_timeout = false;

	/*
	 * Set timer so we can wake up after awhile and check for a deadlock. If a
	 * deadlock is detected, the handler sets MyProc->waitStatus =
	 * PROC_WAIT_STATUS_ERROR, allowing us to know that we must report failure
	 * rather than success.
	 *
	 * By delaying the check until we've waited for a bit, we can avoid
	 * running the rather expensive deadlock-check code in most cases.
	 *
	 * If LockTimeout is set, also enable the timeout for that.  We can save a
	 * few cycles by enabling both timeout sources in one call.
	 *
	 * If InHotStandby we set lock waits slightly later for clarity with other
	 * code.
	 */
	if (!InHotStandby)
	{
		if (LockTimeout > 0)
		{
			EnableTimeoutParams timeouts[2];

			timeouts[0].id = DEADLOCK_TIMEOUT;
			timeouts[0].type = TMPARAM_AFTER;
			timeouts[0].delay_ms = DeadlockTimeout;
			timeouts[1].id = LOCK_TIMEOUT;
			timeouts[1].type = TMPARAM_AFTER;
			timeouts[1].delay_ms = LockTimeout;
			enable_timeouts(timeouts, 2);
		}
		else
			enable_timeout_after(DEADLOCK_TIMEOUT, DeadlockTimeout);

		/*
		 * Use the current time obtained for the deadlock timeout timer as
		 * waitStart (i.e., the time when this process started waiting for the
		 * lock). Since getting the current time newly can cause overhead, we
		 * reuse the already-obtained time to avoid that overhead.
		 *
		 * Note that waitStart is updated without holding the lock table's
		 * partition lock, to avoid the overhead by additional lock
		 * acquisition. This can cause "waitstart" in pg_locks to become NULL
		 * for a very short period of time after the wait started even though
		 * "granted" is false. This is OK in practice because we can assume
		 * that users are likely to look at "waitstart" when waiting for the
		 * lock for a long time.
		 */
		pg_atomic_write_u64(&MyProc->waitStart,
							get_timeout_start_time(DEADLOCK_TIMEOUT));
	}
	else if (log_recovery_conflict_waits)
	{
		/*
		 * Set the wait start timestamp if logging is enabled and in hot
		 * standby.
		 */
		standbyWaitStart = GetCurrentTimestamp();
	}

	/*
	 * If somebody wakes us between LWLockRelease and WaitLatch, the latch
	 * will not wait. But a set latch does not necessarily mean that the lock
	 * is free now, as there are many other sources for latch sets than
	 * somebody releasing the lock.
	 *
	 * We process interrupts whenever the latch has been set, so cancel/die
	 * interrupts are processed quickly. This means we must not mind losing
	 * control to a cancel/die interrupt here.  We don't, because we have no
	 * shared-state-change work to do after being granted the lock (the
	 * grantor did it all).  We do have to worry about canceling the deadlock
	 * timeout and updating the locallock table, but if we lose control to an
	 * error, LockErrorCleanup will fix that up.
	 */
	do
	{
		if (InHotStandby)
		{
			bool		maybe_log_conflict =
			(standbyWaitStart != 0 && !logged_recovery_conflict);

			/* Set a timer and wait for that or for the lock to be granted */
			ResolveRecoveryConflictWithLock(locallock->tag.lock,
											maybe_log_conflict);

			/*
			 * Emit the log message if the startup process is waiting longer
			 * than deadlock_timeout for recovery conflict on lock.
			 */
			if (maybe_log_conflict)
			{
				TimestampTz now = GetCurrentTimestamp();

				if (TimestampDifferenceExceeds(standbyWaitStart, now,
											   DeadlockTimeout))
				{
					VirtualTransactionId *vxids;
					int			cnt;

					vxids = GetLockConflicts(&locallock->tag.lock,
											 AccessExclusiveLock, &cnt);

					/*
					 * Log the recovery conflict and the list of PIDs of
					 * backends holding the conflicting lock. Note that we do
					 * logging even if there are no such backends right now
					 * because the startup process here has already waited
					 * longer than deadlock_timeout.
					 */
					LogRecoveryConflict(PROCSIG_RECOVERY_CONFLICT_LOCK,
										standbyWaitStart, now,
										cnt > 0 ? vxids : NULL, true);
					logged_recovery_conflict = true;
				}
			}
		}
		else
		{
			(void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, 0,
							 PG_WAIT_LOCK | locallock->tag.lock.locktag_type);
			ResetLatch(MyLatch);
			/* check for deadlocks first, as that's probably log-worthy */
			if (got_deadlock_timeout)
			{
				CheckDeadLock();
				got_deadlock_timeout = false;
			}
			CHECK_FOR_INTERRUPTS();
		}

		/*
		 * waitStatus could change from PROC_WAIT_STATUS_WAITING to something
		 * else asynchronously.  Read it just once per loop to prevent
		 * surprising behavior (such as missing log messages).
		 */
		myWaitStatus = *((volatile ProcWaitStatus *) &MyProc->waitStatus);

		/*
		 * If we are not deadlocked, but are waiting on an autovacuum-induced
		 * task, send a signal to interrupt it.
		 */
		if (deadlock_state == DS_BLOCKED_BY_AUTOVACUUM && allow_autovacuum_cancel)
		{
			PGPROC	   *autovac = GetBlockingAutoVacuumPgproc();
			uint8		statusFlags;
			uint8		lockmethod_copy;
			LOCKTAG		locktag_copy;

			/*
			 * Grab info we need, then release lock immediately.  Note this
			 * coding means that there is a tiny chance that the process
			 * terminates its current transaction and starts a different one
			 * before we have a change to send the signal; the worst possible
			 * consequence is that a for-wraparound vacuum is cancelled.  But
			 * that could happen in any case unless we were to do kill() with
			 * the lock held, which is much more undesirable.
			 */
			LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
			statusFlags = ProcGlobal->statusFlags[autovac->pgxactoff];
			lockmethod_copy = lock->tag.locktag_lockmethodid;
			locktag_copy = lock->tag;
			LWLockRelease(ProcArrayLock);

			/*
			 * Only do it if the worker is not working to protect against Xid
			 * wraparound.
			 */
			if ((statusFlags & PROC_IS_AUTOVACUUM) &&
				!(statusFlags & PROC_VACUUM_FOR_WRAPAROUND))
			{
				int			pid = autovac->pid;

				/* report the case, if configured to do so */
				if (message_level_is_interesting(DEBUG1))
				{
					StringInfoData locktagbuf;
					StringInfoData logbuf;	/* errdetail for server log */

					initStringInfo(&locktagbuf);
					initStringInfo(&logbuf);
					DescribeLockTag(&locktagbuf, &locktag_copy);
					appendStringInfo(&logbuf,
									 "Process %d waits for %s on %s.",
									 MyProcPid,
									 GetLockmodeName(lockmethod_copy, lockmode),
									 locktagbuf.data);

					ereport(DEBUG1,
							(errmsg_internal("sending cancel to blocking autovacuum PID %d",
											 pid),
							 errdetail_log("%s", logbuf.data)));

					pfree(locktagbuf.data);
					pfree(logbuf.data);
				}

				/* send the autovacuum worker Back to Old Kent Road */
				if (kill(pid, SIGINT) < 0)
				{
					/*
					 * There's a race condition here: once we release the
					 * ProcArrayLock, it's possible for the autovac worker to
					 * close up shop and exit before we can do the kill().
					 * Therefore, we do not whinge about no-such-process.
					 * Other errors such as EPERM could conceivably happen if
					 * the kernel recycles the PID fast enough, but such cases
					 * seem improbable enough that it's probably best to issue
					 * a warning if we see some other errno.
					 */
					if (errno != ESRCH)
						ereport(WARNING,
								(errmsg("could not send signal to process %d: %m",
										pid)));
				}
			}

			/* prevent signal from being sent again more than once */
			allow_autovacuum_cancel = false;
		}

		/*
		 * If awoken after the deadlock check interrupt has run, and
		 * log_lock_waits is on, then report about the wait.
		 */
		if (log_lock_waits && deadlock_state != DS_NOT_YET_CHECKED)
		{
			StringInfoData buf,
						lock_waiters_sbuf,
						lock_holders_sbuf;
			const char *modename;
			long		secs;
			int			usecs;
			long		msecs;
			SHM_QUEUE  *procLocks;
			PROCLOCK   *proclock;
			bool		first_holder = true,
						first_waiter = true;
			int			lockHoldersNum = 0;

			initStringInfo(&buf);
			initStringInfo(&lock_waiters_sbuf);
			initStringInfo(&lock_holders_sbuf);

			DescribeLockTag(&buf, &locallock->tag.lock);
			modename = GetLockmodeName(locallock->tag.lock.locktag_lockmethodid,
									   lockmode);
			TimestampDifference(get_timeout_start_time(DEADLOCK_TIMEOUT),
								GetCurrentTimestamp(),
								&secs, &usecs);
			msecs = secs * 1000 + usecs / 1000;
			usecs = usecs % 1000;

			/*
			 * we loop over the lock's procLocks to gather a list of all
			 * holders and waiters. Thus we will be able to provide more
			 * detailed information for lock debugging purposes.
			 *
			 * lock->procLocks contains all processes which hold or wait for
			 * this lock.
			 */

			LWLockAcquire(partitionLock, LW_SHARED);

			procLocks = &(lock->procLocks);
			proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
												 offsetof(PROCLOCK, lockLink));

			while (proclock)
			{
				/*
				 * we are a waiter if myProc->waitProcLock == proclock; we are
				 * a holder if it is NULL or something different
				 */
				if (proclock->tag.myProc->waitProcLock == proclock)
				{
					if (first_waiter)
					{
						appendStringInfo(&lock_waiters_sbuf, "%d",
										 proclock->tag.myProc->pid);
						first_waiter = false;
					}
					else
						appendStringInfo(&lock_waiters_sbuf, ", %d",
										 proclock->tag.myProc->pid);
				}
				else
				{
					if (first_holder)
					{
						appendStringInfo(&lock_holders_sbuf, "%d",
										 proclock->tag.myProc->pid);
						first_holder = false;
					}
					else
						appendStringInfo(&lock_holders_sbuf, ", %d",
										 proclock->tag.myProc->pid);

					lockHoldersNum++;
				}

				proclock = (PROCLOCK *) SHMQueueNext(procLocks, &proclock->lockLink,
													 offsetof(PROCLOCK, lockLink));
			}

			LWLockRelease(partitionLock);

			if (deadlock_state == DS_SOFT_DEADLOCK)
				ereport(LOG,
						(errmsg("process %d avoided deadlock for %s on %s by rearranging queue order after %ld.%03d ms",
								MyProcPid, modename, buf.data, msecs, usecs),
						 (errdetail_log_plural("Process holding the lock: %s. Wait queue: %s.",
											   "Processes holding the lock: %s. Wait queue: %s.",
											   lockHoldersNum, lock_holders_sbuf.data, lock_waiters_sbuf.data))));
			else if (deadlock_state == DS_HARD_DEADLOCK)
			{
				/*
				 * This message is a bit redundant with the error that will be
				 * reported subsequently, but in some cases the error report
				 * might not make it to the log (eg, if it's caught by an
				 * exception handler), and we want to ensure all long-wait
				 * events get logged.
				 */
				ereport(LOG,
						(errmsg("process %d detected deadlock while waiting for %s on %s after %ld.%03d ms",
								MyProcPid, modename, buf.data, msecs, usecs),
						 (errdetail_log_plural("Process holding the lock: %s. Wait queue: %s.",
											   "Processes holding the lock: %s. Wait queue: %s.",
											   lockHoldersNum, lock_holders_sbuf.data, lock_waiters_sbuf.data))));
			}

			if (myWaitStatus == PROC_WAIT_STATUS_WAITING)
				ereport(LOG,
						(errmsg("process %d still waiting for %s on %s after %ld.%03d ms",
								MyProcPid, modename, buf.data, msecs, usecs),
						 (errdetail_log_plural("Process holding the lock: %s. Wait queue: %s.",
											   "Processes holding the lock: %s. Wait queue: %s.",
											   lockHoldersNum, lock_holders_sbuf.data, lock_waiters_sbuf.data))));
			else if (myWaitStatus == PROC_WAIT_STATUS_OK)
				ereport(LOG,
						(errmsg("process %d acquired %s on %s after %ld.%03d ms",
								MyProcPid, modename, buf.data, msecs, usecs)));
			else
			{
				Assert(myWaitStatus == PROC_WAIT_STATUS_ERROR);

				/*
				 * Currently, the deadlock checker always kicks its own
				 * process, which means that we'll only see
				 * PROC_WAIT_STATUS_ERROR when deadlock_state ==
				 * DS_HARD_DEADLOCK, and there's no need to print redundant
				 * messages.  But for completeness and future-proofing, print
				 * a message if it looks like someone else kicked us off the
				 * lock.
				 */
				if (deadlock_state != DS_HARD_DEADLOCK)
					ereport(LOG,
							(errmsg("process %d failed to acquire %s on %s after %ld.%03d ms",
									MyProcPid, modename, buf.data, msecs, usecs),
							 (errdetail_log_plural("Process holding the lock: %s. Wait queue: %s.",
												   "Processes holding the lock: %s. Wait queue: %s.",
												   lockHoldersNum, lock_holders_sbuf.data, lock_waiters_sbuf.data))));
			}

			/*
			 * At this point we might still need to wait for the lock. Reset
			 * state so we don't print the above messages again.
			 */
			deadlock_state = DS_NO_DEADLOCK;

			pfree(buf.data);
			pfree(lock_holders_sbuf.data);
			pfree(lock_waiters_sbuf.data);
		}
	} while (myWaitStatus == PROC_WAIT_STATUS_WAITING);

	/*
	 * Disable the timers, if they are still running.  As in LockErrorCleanup,
	 * we must preserve the LOCK_TIMEOUT indicator flag: if a lock timeout has
	 * already caused QueryCancelPending to become set, we want the cancel to
	 * be reported as a lock timeout, not a user cancel.
	 */
	if (!InHotStandby)
	{
		if (LockTimeout > 0)
		{
			DisableTimeoutParams timeouts[2];

			timeouts[0].id = DEADLOCK_TIMEOUT;
			timeouts[0].keep_indicator = false;
			timeouts[1].id = LOCK_TIMEOUT;
			timeouts[1].keep_indicator = true;
			disable_timeouts(timeouts, 2);
		}
		else
			disable_timeout(DEADLOCK_TIMEOUT, false);
	}

	/*
	 * Emit the log message if recovery conflict on lock was resolved but the
	 * startup process waited longer than deadlock_timeout for it.
	 */
	if (InHotStandby && logged_recovery_conflict)
		LogRecoveryConflict(PROCSIG_RECOVERY_CONFLICT_LOCK,
							standbyWaitStart, GetCurrentTimestamp(),
							NULL, false);

	/*
	 * Re-acquire the lock table's partition lock.  We have to do this to hold
	 * off cancel/die interrupts before we can mess with lockAwaited (else we
	 * might have a missed or duplicated locallock update).
	 */
	LWLockAcquire(partitionLock, LW_EXCLUSIVE);

	/*
	 * We no longer want LockErrorCleanup to do anything.
	 */
	lockAwaited = NULL;

	/*
	 * If we got the lock, be sure to remember it in the locallock table.
	 */
	if (MyProc->waitStatus == PROC_WAIT_STATUS_OK)
		GrantAwaitedLock();

	/*
	 * We don't have to do anything else, because the awaker did all the
	 * necessary update of the lock table and MyProc.
	 */
	return MyProc->waitStatus;
}


/*
 * ProcWakeup -- wake up a process by setting its latch.
 *
 *	 Also remove the process from the wait queue and set its links invalid.
 *	 RETURN: the next process in the wait queue.
 *
 * The appropriate lock partition lock must be held by caller.
 *
 * XXX: presently, this code is only used for the "success" case, and only
 * works correctly for that case.  To clean up in failure case, would need
 * to twiddle the lock's request counts too --- see RemoveFromWaitQueue.
 * Hence, in practice the waitStatus parameter must be PROC_WAIT_STATUS_OK.
 */
PGPROC *
ProcWakeup(PGPROC *proc, ProcWaitStatus waitStatus)
{
	PGPROC	   *retProc;

	/* Proc should be sleeping ... */
	if (proc->links.prev == NULL ||
		proc->links.next == NULL)
		return NULL;
	Assert(proc->waitStatus == PROC_WAIT_STATUS_WAITING);

	/* Save next process before we zap the list link */
	retProc = (PGPROC *) proc->links.next;

	/* Remove process from wait queue */
	SHMQueueDelete(&(proc->links));
	(proc->waitLock->waitProcs.size)--;

	/* Clean up process' state and pass it the ok/fail signal */
	proc->waitLock = NULL;
	proc->waitProcLock = NULL;
	proc->waitStatus = waitStatus;
	pg_atomic_write_u64(&MyProc->waitStart, 0);

	/* And awaken it */
	SetLatch(&proc->procLatch);

	return retProc;
}

/*
 * ProcLockWakeup -- routine for waking up processes when a lock is
 *		released (or a prior waiter is aborted).  Scan all waiters
 *		for lock, waken any that are no longer blocked.
 *
 * The appropriate lock partition lock must be held by caller.
 */
void
ProcLockWakeup(LockMethod lockMethodTable, LOCK *lock)
{
	PROC_QUEUE *waitQueue = &(lock->waitProcs);
	int			queue_size = waitQueue->size;
	PGPROC	   *proc;
	LOCKMASK	aheadRequests = 0;

	Assert(queue_size >= 0);

	if (queue_size == 0)
		return;

	proc = (PGPROC *) waitQueue->links.next;

	while (queue_size-- > 0)
	{
		LOCKMODE	lockmode = proc->waitLockMode;

		/*
		 * Waken if (a) doesn't conflict with requests of earlier waiters, and
		 * (b) doesn't conflict with already-held locks.
		 */
		if ((lockMethodTable->conflictTab[lockmode] & aheadRequests) == 0 &&
			!LockCheckConflicts(lockMethodTable, lockmode, lock,
								proc->waitProcLock))
		{
			/* OK to waken */
			GrantLock(lock, proc->waitProcLock, lockmode);
			proc = ProcWakeup(proc, PROC_WAIT_STATUS_OK);

			/*
			 * ProcWakeup removes proc from the lock's waiting process queue
			 * and returns the next proc in chain; don't use proc's next-link,
			 * because it's been cleared.
			 */
		}
		else
		{
			/*
			 * Cannot wake this guy. Remember his request for later checks.
			 */
			aheadRequests |= LOCKBIT_ON(lockmode);
			proc = (PGPROC *) proc->links.next;
		}
	}

	Assert(waitQueue->size >= 0);
}

/*
 * CheckDeadLock
 *
 * We only get to this routine, if DEADLOCK_TIMEOUT fired while waiting for a
 * lock to be released by some other process.  Check if there's a deadlock; if
 * not, just return.  (But signal ProcSleep to log a message, if
 * log_lock_waits is true.)  If we have a real deadlock, remove ourselves from
 * the lock's wait queue and signal an error to ProcSleep.
 */
static void
CheckDeadLock(void)
{
	int			i;

	/*
	 * Acquire exclusive lock on the entire shared lock data structures. Must
	 * grab LWLocks in partition-number order to avoid LWLock deadlock.
	 *
	 * Note that the deadlock check interrupt had better not be enabled
	 * anywhere that this process itself holds lock partition locks, else this
	 * will wait forever.  Also note that LWLockAcquire creates a critical
	 * section, so that this routine cannot be interrupted by cancel/die
	 * interrupts.
	 */
	for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
		LWLockAcquire(LockHashPartitionLockByIndex(i), LW_EXCLUSIVE);

	/*
	 * Check to see if we've been awoken by anyone in the interim.
	 *
	 * If we have, we can return and resume our transaction -- happy day.
	 * Before we are awoken the process releasing the lock grants it to us so
	 * we know that we don't have to wait anymore.
	 *
	 * We check by looking to see if we've been unlinked from the wait queue.
	 * This is safe because we hold the lock partition lock.
	 */
	if (MyProc->links.prev == NULL ||
		MyProc->links.next == NULL)
		goto check_done;

#ifdef LOCK_DEBUG
	if (Debug_deadlocks)
		DumpAllLocks();
#endif

	/* Run the deadlock check, and set deadlock_state for use by ProcSleep */
	deadlock_state = DeadLockCheck(MyProc);

	if (deadlock_state == DS_HARD_DEADLOCK)
	{
		/*
		 * Oops.  We have a deadlock.
		 *
		 * Get this process out of wait state. (Note: we could do this more
		 * efficiently by relying on lockAwaited, but use this coding to
		 * preserve the flexibility to kill some other transaction than the
		 * one detecting the deadlock.)
		 *
		 * RemoveFromWaitQueue sets MyProc->waitStatus to
		 * PROC_WAIT_STATUS_ERROR, so ProcSleep will report an error after we
		 * return from the signal handler.
		 */
		Assert(MyProc->waitLock != NULL);
		RemoveFromWaitQueue(MyProc, LockTagHashCode(&(MyProc->waitLock->tag)));

		/*
		 * We're done here.  Transaction abort caused by the error that
		 * ProcSleep will raise will cause any other locks we hold to be
		 * released, thus allowing other processes to wake up; we don't need
		 * to do that here.  NOTE: an exception is that releasing locks we
		 * hold doesn't consider the possibility of waiters that were blocked
		 * behind us on the lock we just failed to get, and might now be
		 * wakable because we're not in front of them anymore.  However,
		 * RemoveFromWaitQueue took care of waking up any such processes.
		 */
	}

	/*
	 * And release locks.  We do this in reverse order for two reasons: (1)
	 * Anyone else who needs more than one of the locks will be trying to lock
	 * them in increasing order; we don't want to release the other process
	 * until it can get all the locks it needs. (2) This avoids O(N^2)
	 * behavior inside LWLockRelease.
	 */
check_done:
	for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
		LWLockRelease(LockHashPartitionLockByIndex(i));
}

/*
 * CheckDeadLockAlert - Handle the expiry of deadlock_timeout.
 *
 * NB: Runs inside a signal handler, be careful.
 */
void
CheckDeadLockAlert(void)
{
	int			save_errno = errno;

	got_deadlock_timeout = true;

	/*
	 * Have to set the latch again, even if handle_sig_alarm already did. Back
	 * then got_deadlock_timeout wasn't yet set... It's unlikely that this
	 * ever would be a problem, but setting a set latch again is cheap.
	 *
	 * Note that, when this function runs inside procsignal_sigusr1_handler(),
	 * the handler function sets the latch again after the latch is set here.
	 */
	SetLatch(MyLatch);
	errno = save_errno;
}

/*
 * ProcWaitForSignal - wait for a signal from another backend.
 *
 * As this uses the generic process latch the caller has to be robust against
 * unrelated wakeups: Always check that the desired state has occurred, and
 * wait again if not.
 */
void
ProcWaitForSignal(uint32 wait_event_info)
{
	(void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, 0,
					 wait_event_info);
	ResetLatch(MyLatch);
	CHECK_FOR_INTERRUPTS();
}

/*
 * ProcSendSignal - send a signal to a backend identified by PID
 */
void
ProcSendSignal(int pid)
{
	PGPROC	   *proc = NULL;

	if (RecoveryInProgress())
	{
		SpinLockAcquire(ProcStructLock);

		/*
		 * Check to see whether it is the Startup process we wish to signal.
		 * This call is made by the buffer manager when it wishes to wake up a
		 * process that has been waiting for a pin in so it can obtain a
		 * cleanup lock using LockBufferForCleanup(). Startup is not a normal
		 * backend, so BackendPidGetProc() will not return any pid at all. So
		 * we remember the information for this special case.
		 */
		if (pid == ProcGlobal->startupProcPid)
			proc = ProcGlobal->startupProc;

		SpinLockRelease(ProcStructLock);
	}

	if (proc == NULL)
		proc = BackendPidGetProc(pid);

	if (proc != NULL)
	{
		SetLatch(&proc->procLatch);
	}
}

/*
 * BecomeLockGroupLeader - designate process as lock group leader
 *
 * Once this function has returned, other processes can join the lock group
 * by calling BecomeLockGroupMember.
 */
void
BecomeLockGroupLeader(void)
{
	LWLock	   *leader_lwlock;

	/* If we already did it, we don't need to do it again. */
	if (MyProc->lockGroupLeader == MyProc)
		return;

	/* We had better not be a follower. */
	Assert(MyProc->lockGroupLeader == NULL);

	/* Create single-member group, containing only ourselves. */
	leader_lwlock = LockHashPartitionLockByProc(MyProc);
	LWLockAcquire(leader_lwlock, LW_EXCLUSIVE);
	MyProc->lockGroupLeader = MyProc;
	dlist_push_head(&MyProc->lockGroupMembers, &MyProc->lockGroupLink);
	LWLockRelease(leader_lwlock);
}

/*
 * BecomeLockGroupMember - designate process as lock group member
 *
 * This is pretty straightforward except for the possibility that the leader
 * whose group we're trying to join might exit before we manage to do so;
 * and the PGPROC might get recycled for an unrelated process.  To avoid
 * that, we require the caller to pass the PID of the intended PGPROC as
 * an interlock.  Returns true if we successfully join the intended lock
 * group, and false if not.
 */
bool
BecomeLockGroupMember(PGPROC *leader, int pid)
{
	LWLock	   *leader_lwlock;
	bool		ok = false;

	/* Group leader can't become member of group */
	Assert(MyProc != leader);

	/* Can't already be a member of a group */
	Assert(MyProc->lockGroupLeader == NULL);

	/* PID must be valid. */
	Assert(pid != 0);

	/*
	 * Get lock protecting the group fields.  Note LockHashPartitionLockByProc
	 * accesses leader->pgprocno in a PGPROC that might be free.  This is safe
	 * because all PGPROCs' pgprocno fields are set during shared memory
	 * initialization and never change thereafter; so we will acquire the
	 * correct lock even if the leader PGPROC is in process of being recycled.
	 */
	leader_lwlock = LockHashPartitionLockByProc(leader);
	LWLockAcquire(leader_lwlock, LW_EXCLUSIVE);

	/* Is this the leader we're looking for? */
	if (leader->pid == pid && leader->lockGroupLeader == leader)
	{
		/* OK, join the group */
		ok = true;
		MyProc->lockGroupLeader = leader;
		dlist_push_tail(&leader->lockGroupMembers, &MyProc->lockGroupLink);
	}
	LWLockRelease(leader_lwlock);

	return ok;
}