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
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
|
/*-------------------------------------------------------------------------
*
* lock.c
* POSTGRES primary lock mechanism
*
* Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/storage/lmgr/lock.c
*
* NOTES
* A lock table is a shared memory hash table. When
* a process tries to acquire a lock of a type that conflicts
* with existing locks, it is put to sleep using the routines
* in storage/lmgr/proc.c.
*
* For the most part, this code should be invoked via lmgr.c
* or another lock-management module, not directly.
*
* Interface:
*
* InitLocks(), GetLocksMethodTable(), GetLockTagsMethodTable(),
* LockAcquire(), LockRelease(), LockReleaseAll(),
* LockCheckConflicts(), GrantLock()
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <signal.h>
#include <unistd.h>
#include "access/transam.h"
#include "access/twophase.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/sinvaladt.h"
#include "storage/spin.h"
#include "storage/standby.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/resowner_private.h"
/* This configuration variable is used to set the lock table size */
int max_locks_per_xact; /* set by guc.c */
#define NLOCKENTS() \
mul_size(max_locks_per_xact, add_size(MaxBackends, max_prepared_xacts))
/*
* Data structures defining the semantics of the standard lock methods.
*
* The conflict table defines the semantics of the various lock modes.
*/
static const LOCKMASK LockConflicts[] = {
0,
/* AccessShareLock */
LOCKBIT_ON(AccessExclusiveLock),
/* RowShareLock */
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* RowExclusiveLock */
LOCKBIT_ON(ShareLock) | LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* ShareUpdateExclusiveLock */
LOCKBIT_ON(ShareUpdateExclusiveLock) |
LOCKBIT_ON(ShareLock) | LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* ShareLock */
LOCKBIT_ON(RowExclusiveLock) | LOCKBIT_ON(ShareUpdateExclusiveLock) |
LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* ShareRowExclusiveLock */
LOCKBIT_ON(RowExclusiveLock) | LOCKBIT_ON(ShareUpdateExclusiveLock) |
LOCKBIT_ON(ShareLock) | LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* ExclusiveLock */
LOCKBIT_ON(RowShareLock) |
LOCKBIT_ON(RowExclusiveLock) | LOCKBIT_ON(ShareUpdateExclusiveLock) |
LOCKBIT_ON(ShareLock) | LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock),
/* AccessExclusiveLock */
LOCKBIT_ON(AccessShareLock) | LOCKBIT_ON(RowShareLock) |
LOCKBIT_ON(RowExclusiveLock) | LOCKBIT_ON(ShareUpdateExclusiveLock) |
LOCKBIT_ON(ShareLock) | LOCKBIT_ON(ShareRowExclusiveLock) |
LOCKBIT_ON(ExclusiveLock) | LOCKBIT_ON(AccessExclusiveLock)
};
/* Names of lock modes, for debug printouts */
static const char *const lock_mode_names[] =
{
"INVALID",
"AccessShareLock",
"RowShareLock",
"RowExclusiveLock",
"ShareUpdateExclusiveLock",
"ShareLock",
"ShareRowExclusiveLock",
"ExclusiveLock",
"AccessExclusiveLock"
};
#ifndef LOCK_DEBUG
static bool Dummy_trace = false;
#endif
static const LockMethodData default_lockmethod = {
AccessExclusiveLock, /* highest valid lock mode number */
LockConflicts,
lock_mode_names,
#ifdef LOCK_DEBUG
&Trace_locks
#else
&Dummy_trace
#endif
};
static const LockMethodData user_lockmethod = {
AccessExclusiveLock, /* highest valid lock mode number */
LockConflicts,
lock_mode_names,
#ifdef LOCK_DEBUG
&Trace_userlocks
#else
&Dummy_trace
#endif
};
/*
* map from lock method id to the lock table data structures
*/
static const LockMethod LockMethods[] = {
NULL,
&default_lockmethod,
&user_lockmethod
};
/* Record that's written to 2PC state file when a lock is persisted */
typedef struct TwoPhaseLockRecord
{
LOCKTAG locktag;
LOCKMODE lockmode;
} TwoPhaseLockRecord;
/*
* Count of the number of fast path lock slots we believe to be used. This
* might be higher than the real number if another backend has transferred
* our locks to the primary lock table, but it can never be lower than the
* real value, since only we can acquire locks on our own behalf.
*/
static int FastPathLocalUseCount = 0;
/* Macros for manipulating proc->fpLockBits */
#define FAST_PATH_BITS_PER_SLOT 3
#define FAST_PATH_LOCKNUMBER_OFFSET 1
#define FAST_PATH_MASK ((1 << FAST_PATH_BITS_PER_SLOT) - 1)
#define FAST_PATH_GET_BITS(proc, n) \
(((proc)->fpLockBits >> (FAST_PATH_BITS_PER_SLOT * n)) & FAST_PATH_MASK)
#define FAST_PATH_BIT_POSITION(n, l) \
(AssertMacro((l) >= FAST_PATH_LOCKNUMBER_OFFSET), \
AssertMacro((l) < FAST_PATH_BITS_PER_SLOT+FAST_PATH_LOCKNUMBER_OFFSET), \
AssertMacro((n) < FP_LOCK_SLOTS_PER_BACKEND), \
((l) - FAST_PATH_LOCKNUMBER_OFFSET + FAST_PATH_BITS_PER_SLOT * (n)))
#define FAST_PATH_SET_LOCKMODE(proc, n, l) \
(proc)->fpLockBits |= UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)
#define FAST_PATH_CLEAR_LOCKMODE(proc, n, l) \
(proc)->fpLockBits &= ~(UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l))
#define FAST_PATH_CHECK_LOCKMODE(proc, n, l) \
((proc)->fpLockBits & (UINT64CONST(1) << FAST_PATH_BIT_POSITION(n, l)))
/*
* The fast-path lock mechanism is concerned only with relation locks on
* unshared relations by backends bound to a database. The fast-path
* mechanism exists mostly to accelerate acquisition and release of locks
* that rarely conflict. Because ShareUpdateExclusiveLock is
* self-conflicting, it can't use the fast-path mechanism; but it also does
* not conflict with any of the locks that do, so we can ignore it completely.
*/
#define EligibleForRelationFastPath(locktag, mode) \
((locktag)->locktag_lockmethodid == DEFAULT_LOCKMETHOD && \
(locktag)->locktag_type == LOCKTAG_RELATION && \
(locktag)->locktag_field1 == MyDatabaseId && \
MyDatabaseId != InvalidOid && \
(mode) < ShareUpdateExclusiveLock)
#define ConflictsWithRelationFastPath(locktag, mode) \
((locktag)->locktag_lockmethodid == DEFAULT_LOCKMETHOD && \
(locktag)->locktag_type == LOCKTAG_RELATION && \
(locktag)->locktag_field1 != InvalidOid && \
(mode) > ShareUpdateExclusiveLock)
static bool FastPathGrantRelationLock(Oid relid, LOCKMODE lockmode);
static bool FastPathUnGrantRelationLock(Oid relid, LOCKMODE lockmode);
static bool FastPathTransferRelationLocks(LockMethod lockMethodTable,
const LOCKTAG *locktag, uint32 hashcode);
static PROCLOCK *FastPathGetRelationLockEntry(LOCALLOCK *locallock);
/*
* To make the fast-path lock mechanism work, we must have some way of
* preventing the use of the fast-path when a conflicting lock might be
* present. We partition* the locktag space into FAST_PATH_HASH_BUCKETS
* partitions, and maintain an integer count of the number of "strong" lockers
* in each partition. When any "strong" lockers are present (which is
* hopefully not very often), the fast-path mechanism can't be used, and we
* must fall back to the slower method of pushing matching locks directly
* into the main lock tables.
*
* The deadlock detector does not know anything about the fast path mechanism,
* so any locks that might be involved in a deadlock must be transferred from
* the fast-path queues to the main lock table.
*/
#define FAST_PATH_STRONG_LOCK_HASH_BITS 10
#define FAST_PATH_STRONG_LOCK_HASH_PARTITIONS \
(1 << FAST_PATH_STRONG_LOCK_HASH_BITS)
#define FastPathStrongLockHashPartition(hashcode) \
((hashcode) % FAST_PATH_STRONG_LOCK_HASH_PARTITIONS)
typedef struct
{
slock_t mutex;
uint32 count[FAST_PATH_STRONG_LOCK_HASH_PARTITIONS];
} FastPathStrongRelationLockData;
static volatile FastPathStrongRelationLockData *FastPathStrongRelationLocks;
/*
* Pointers to hash tables containing lock state
*
* The LockMethodLockHash and LockMethodProcLockHash hash tables are in
* shared memory; LockMethodLocalHash is local to each backend.
*/
static HTAB *LockMethodLockHash;
static HTAB *LockMethodProcLockHash;
static HTAB *LockMethodLocalHash;
/* private state for error cleanup */
static LOCALLOCK *StrongLockInProgress;
static LOCALLOCK *awaitedLock;
static ResourceOwner awaitedOwner;
#ifdef LOCK_DEBUG
/*------
* The following configuration options are available for lock debugging:
*
* TRACE_LOCKS -- give a bunch of output what's going on in this file
* TRACE_USERLOCKS -- same but for user locks
* TRACE_LOCK_OIDMIN-- do not trace locks for tables below this oid
* (use to avoid output on system tables)
* TRACE_LOCK_TABLE -- trace locks on this table (oid) unconditionally
* DEBUG_DEADLOCKS -- currently dumps locks at untimely occasions ;)
*
* Furthermore, but in storage/lmgr/lwlock.c:
* TRACE_LWLOCKS -- trace lightweight locks (pretty useless)
*
* Define LOCK_DEBUG at compile time to get all these enabled.
* --------
*/
int Trace_lock_oidmin = FirstNormalObjectId;
bool Trace_locks = false;
bool Trace_userlocks = false;
int Trace_lock_table = 0;
bool Debug_deadlocks = false;
inline static bool
LOCK_DEBUG_ENABLED(const LOCKTAG *tag)
{
return
(*(LockMethods[tag->locktag_lockmethodid]->trace_flag) &&
((Oid) tag->locktag_field2 >= (Oid) Trace_lock_oidmin))
|| (Trace_lock_table &&
(tag->locktag_field2 == Trace_lock_table));
}
inline static void
LOCK_PRINT(const char *where, const LOCK *lock, LOCKMODE type)
{
if (LOCK_DEBUG_ENABLED(&lock->tag))
elog(LOG,
"%s: lock(%p) id(%u,%u,%u,%u,%u,%u) grantMask(%x) "
"req(%d,%d,%d,%d,%d,%d,%d)=%d "
"grant(%d,%d,%d,%d,%d,%d,%d)=%d wait(%d) type(%s)",
where, lock,
lock->tag.locktag_field1, lock->tag.locktag_field2,
lock->tag.locktag_field3, lock->tag.locktag_field4,
lock->tag.locktag_type, lock->tag.locktag_lockmethodid,
lock->grantMask,
lock->requested[1], lock->requested[2], lock->requested[3],
lock->requested[4], lock->requested[5], lock->requested[6],
lock->requested[7], lock->nRequested,
lock->granted[1], lock->granted[2], lock->granted[3],
lock->granted[4], lock->granted[5], lock->granted[6],
lock->granted[7], lock->nGranted,
lock->waitProcs.size,
LockMethods[LOCK_LOCKMETHOD(*lock)]->lockModeNames[type]);
}
inline static void
PROCLOCK_PRINT(const char *where, const PROCLOCK *proclockP)
{
if (LOCK_DEBUG_ENABLED(&proclockP->tag.myLock->tag))
elog(LOG,
"%s: proclock(%p) lock(%p) method(%u) proc(%p) hold(%x)",
where, proclockP, proclockP->tag.myLock,
PROCLOCK_LOCKMETHOD(*(proclockP)),
proclockP->tag.myProc, (int) proclockP->holdMask);
}
#else /* not LOCK_DEBUG */
#define LOCK_PRINT(where, lock, type) ((void) 0)
#define PROCLOCK_PRINT(where, proclockP) ((void) 0)
#endif /* not LOCK_DEBUG */
static uint32 proclock_hash(const void *key, Size keysize);
static void RemoveLocalLock(LOCALLOCK *locallock);
static PROCLOCK *SetupLockInTable(LockMethod lockMethodTable, PGPROC *proc,
const LOCKTAG *locktag, uint32 hashcode, LOCKMODE lockmode);
static void GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner);
static void BeginStrongLockAcquire(LOCALLOCK *locallock, uint32 fasthashcode);
static void FinishStrongLockAcquire(void);
static void WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner);
static void ReleaseLockIfHeld(LOCALLOCK *locallock, bool sessionLock);
static void LockReassignOwner(LOCALLOCK *locallock, ResourceOwner parent);
static bool UnGrantLock(LOCK *lock, LOCKMODE lockmode,
PROCLOCK *proclock, LockMethod lockMethodTable);
static void CleanUpLock(LOCK *lock, PROCLOCK *proclock,
LockMethod lockMethodTable, uint32 hashcode,
bool wakeupNeeded);
static void LockRefindAndRelease(LockMethod lockMethodTable, PGPROC *proc,
LOCKTAG *locktag, LOCKMODE lockmode,
bool decrement_strong_lock_count);
static void GetSingleProcBlockerStatusData(PGPROC *blocked_proc,
BlockedProcsData *data);
/*
* InitLocks -- Initialize the lock manager's data structures.
*
* This is called from CreateSharedMemoryAndSemaphores(), which see for
* more comments. In the normal postmaster case, the shared hash tables
* are created here, as well as a locallock hash table that will remain
* unused and empty in the postmaster itself. Backends inherit the pointers
* to the shared tables via fork(), and also inherit an image of the locallock
* hash table, which they proceed to use. In the EXEC_BACKEND case, each
* backend re-executes this code to obtain pointers to the already existing
* shared hash tables and to create its locallock hash table.
*/
void
InitLocks(void)
{
HASHCTL info;
long init_table_size,
max_table_size;
bool found;
/*
* Compute init/max size to request for lock hashtables. Note these
* calculations must agree with LockShmemSize!
*/
max_table_size = NLOCKENTS();
init_table_size = max_table_size / 2;
/*
* Allocate hash table for LOCK structs. This stores per-locked-object
* information.
*/
MemSet(&info, 0, sizeof(info));
info.keysize = sizeof(LOCKTAG);
info.entrysize = sizeof(LOCK);
info.num_partitions = NUM_LOCK_PARTITIONS;
LockMethodLockHash = ShmemInitHash("LOCK hash",
init_table_size,
max_table_size,
&info,
HASH_ELEM | HASH_BLOBS | HASH_PARTITION);
/* Assume an average of 2 holders per lock */
max_table_size *= 2;
init_table_size *= 2;
/*
* Allocate hash table for PROCLOCK structs. This stores
* per-lock-per-holder information.
*/
info.keysize = sizeof(PROCLOCKTAG);
info.entrysize = sizeof(PROCLOCK);
info.hash = proclock_hash;
info.num_partitions = NUM_LOCK_PARTITIONS;
LockMethodProcLockHash = ShmemInitHash("PROCLOCK hash",
init_table_size,
max_table_size,
&info,
HASH_ELEM | HASH_FUNCTION | HASH_PARTITION);
/*
* Allocate fast-path structures.
*/
FastPathStrongRelationLocks =
ShmemInitStruct("Fast Path Strong Relation Lock Data",
sizeof(FastPathStrongRelationLockData), &found);
if (!found)
SpinLockInit(&FastPathStrongRelationLocks->mutex);
/*
* Allocate non-shared hash table for LOCALLOCK structs. This stores lock
* counts and resource owner information.
*
* The non-shared table could already exist in this process (this occurs
* when the postmaster is recreating shared memory after a backend crash).
* If so, delete and recreate it. (We could simply leave it, since it
* ought to be empty in the postmaster, but for safety let's zap it.)
*/
if (LockMethodLocalHash)
hash_destroy(LockMethodLocalHash);
info.keysize = sizeof(LOCALLOCKTAG);
info.entrysize = sizeof(LOCALLOCK);
LockMethodLocalHash = hash_create("LOCALLOCK hash",
16,
&info,
HASH_ELEM | HASH_BLOBS);
}
/*
* Fetch the lock method table associated with a given lock
*/
LockMethod
GetLocksMethodTable(const LOCK *lock)
{
LOCKMETHODID lockmethodid = LOCK_LOCKMETHOD(*lock);
Assert(0 < lockmethodid && lockmethodid < lengthof(LockMethods));
return LockMethods[lockmethodid];
}
/*
* Fetch the lock method table associated with a given locktag
*/
LockMethod
GetLockTagsMethodTable(const LOCKTAG *locktag)
{
LOCKMETHODID lockmethodid = (LOCKMETHODID) locktag->locktag_lockmethodid;
Assert(0 < lockmethodid && lockmethodid < lengthof(LockMethods));
return LockMethods[lockmethodid];
}
/*
* Compute the hash code associated with a LOCKTAG.
*
* To avoid unnecessary recomputations of the hash code, we try to do this
* just once per function, and then pass it around as needed. Aside from
* passing the hashcode to hash_search_with_hash_value(), we can extract
* the lock partition number from the hashcode.
*/
uint32
LockTagHashCode(const LOCKTAG *locktag)
{
return get_hash_value(LockMethodLockHash, (const void *) locktag);
}
/*
* Compute the hash code associated with a PROCLOCKTAG.
*
* Because we want to use just one set of partition locks for both the
* LOCK and PROCLOCK hash tables, we have to make sure that PROCLOCKs
* fall into the same partition number as their associated LOCKs.
* dynahash.c expects the partition number to be the low-order bits of
* the hash code, and therefore a PROCLOCKTAG's hash code must have the
* same low-order bits as the associated LOCKTAG's hash code. We achieve
* this with this specialized hash function.
*/
static uint32
proclock_hash(const void *key, Size keysize)
{
const PROCLOCKTAG *proclocktag = (const PROCLOCKTAG *) key;
uint32 lockhash;
Datum procptr;
Assert(keysize == sizeof(PROCLOCKTAG));
/* Look into the associated LOCK object, and compute its hash code */
lockhash = LockTagHashCode(&proclocktag->myLock->tag);
/*
* To make the hash code also depend on the PGPROC, we xor the proc
* struct's address into the hash code, left-shifted so that the
* partition-number bits don't change. Since this is only a hash, we
* don't care if we lose high-order bits of the address; use an
* intermediate variable to suppress cast-pointer-to-int warnings.
*/
procptr = PointerGetDatum(proclocktag->myProc);
lockhash ^= ((uint32) procptr) << LOG2_NUM_LOCK_PARTITIONS;
return lockhash;
}
/*
* Compute the hash code associated with a PROCLOCKTAG, given the hashcode
* for its underlying LOCK.
*
* We use this just to avoid redundant calls of LockTagHashCode().
*/
static inline uint32
ProcLockHashCode(const PROCLOCKTAG *proclocktag, uint32 hashcode)
{
uint32 lockhash = hashcode;
Datum procptr;
/*
* This must match proclock_hash()!
*/
procptr = PointerGetDatum(proclocktag->myProc);
lockhash ^= ((uint32) procptr) << LOG2_NUM_LOCK_PARTITIONS;
return lockhash;
}
/*
* Given two lock modes, return whether they would conflict.
*/
bool
DoLockModesConflict(LOCKMODE mode1, LOCKMODE mode2)
{
LockMethod lockMethodTable = LockMethods[DEFAULT_LOCKMETHOD];
if (lockMethodTable->conflictTab[mode1] & LOCKBIT_ON(mode2))
return true;
return false;
}
/*
* LockHasWaiters -- look up 'locktag' and check if releasing this
* lock would wake up other processes waiting for it.
*/
bool
LockHasWaiters(const LOCKTAG *locktag, LOCKMODE lockmode, bool sessionLock)
{
LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid;
LockMethod lockMethodTable;
LOCALLOCKTAG localtag;
LOCALLOCK *locallock;
LOCK *lock;
PROCLOCK *proclock;
LWLock *partitionLock;
bool hasWaiters = false;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
if (lockmode <= 0 || lockmode > lockMethodTable->numLockModes)
elog(ERROR, "unrecognized lock mode: %d", lockmode);
#ifdef LOCK_DEBUG
if (LOCK_DEBUG_ENABLED(locktag))
elog(LOG, "LockHasWaiters: lock [%u,%u] %s",
locktag->locktag_field1, locktag->locktag_field2,
lockMethodTable->lockModeNames[lockmode]);
#endif
/*
* Find the LOCALLOCK entry for this lock and lockmode
*/
MemSet(&localtag, 0, sizeof(localtag)); /* must clear padding */
localtag.lock = *locktag;
localtag.mode = lockmode;
locallock = (LOCALLOCK *) hash_search(LockMethodLocalHash,
(void *) &localtag,
HASH_FIND, NULL);
/*
* let the caller print its own error message, too. Do not ereport(ERROR).
*/
if (!locallock || locallock->nLocks <= 0)
{
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
return false;
}
/*
* Check the shared lock table.
*/
partitionLock = LockHashPartitionLock(locallock->hashcode);
LWLockAcquire(partitionLock, LW_SHARED);
/*
* We don't need to re-find the lock or proclock, since we kept their
* addresses in the locallock table, and they couldn't have been removed
* while we were holding a lock on them.
*/
lock = locallock->lock;
LOCK_PRINT("LockHasWaiters: found", lock, lockmode);
proclock = locallock->proclock;
PROCLOCK_PRINT("LockHasWaiters: found", proclock);
/*
* Double-check that we are actually holding a lock of the type we want to
* release.
*/
if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
{
PROCLOCK_PRINT("LockHasWaiters: WRONGTYPE", proclock);
LWLockRelease(partitionLock);
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
RemoveLocalLock(locallock);
return false;
}
/*
* Do the checking.
*/
if ((lockMethodTable->conflictTab[lockmode] & lock->waitMask) != 0)
hasWaiters = true;
LWLockRelease(partitionLock);
return hasWaiters;
}
/*
* LockAcquire -- Check for lock conflicts, sleep if conflict found,
* set lock if/when no conflicts.
*
* Inputs:
* locktag: unique identifier for the lockable object
* lockmode: lock mode to acquire
* sessionLock: if true, acquire lock for session not current transaction
* dontWait: if true, don't wait to acquire lock
*
* Returns one of:
* LOCKACQUIRE_NOT_AVAIL lock not available, and dontWait=true
* LOCKACQUIRE_OK lock successfully acquired
* LOCKACQUIRE_ALREADY_HELD incremented count for lock already held
*
* In the normal case where dontWait=false and the caller doesn't need to
* distinguish a freshly acquired lock from one already taken earlier in
* this same transaction, there is no need to examine the return value.
*
* Side Effects: The lock is acquired and recorded in lock tables.
*
* NOTE: if we wait for the lock, there is no way to abort the wait
* short of aborting the transaction.
*/
LockAcquireResult
LockAcquire(const LOCKTAG *locktag,
LOCKMODE lockmode,
bool sessionLock,
bool dontWait)
{
return LockAcquireExtended(locktag, lockmode, sessionLock, dontWait, true);
}
/*
* LockAcquireExtended - allows us to specify additional options
*
* reportMemoryError specifies whether a lock request that fills the
* lock table should generate an ERROR or not. This allows a priority
* caller to note that the lock table is full and then begin taking
* extreme action to reduce the number of other lock holders before
* retrying the action.
*/
LockAcquireResult
LockAcquireExtended(const LOCKTAG *locktag,
LOCKMODE lockmode,
bool sessionLock,
bool dontWait,
bool reportMemoryError)
{
LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid;
LockMethod lockMethodTable;
LOCALLOCKTAG localtag;
LOCALLOCK *locallock;
LOCK *lock;
PROCLOCK *proclock;
bool found;
ResourceOwner owner;
uint32 hashcode;
LWLock *partitionLock;
int status;
bool log_lock = false;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
if (lockmode <= 0 || lockmode > lockMethodTable->numLockModes)
elog(ERROR, "unrecognized lock mode: %d", lockmode);
if (RecoveryInProgress() && !InRecovery &&
(locktag->locktag_type == LOCKTAG_OBJECT ||
locktag->locktag_type == LOCKTAG_RELATION) &&
lockmode > RowExclusiveLock)
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("cannot acquire lock mode %s on database objects while recovery is in progress",
lockMethodTable->lockModeNames[lockmode]),
errhint("Only RowExclusiveLock or less can be acquired on database objects during recovery.")));
#ifdef LOCK_DEBUG
if (LOCK_DEBUG_ENABLED(locktag))
elog(LOG, "LockAcquire: lock [%u,%u] %s",
locktag->locktag_field1, locktag->locktag_field2,
lockMethodTable->lockModeNames[lockmode]);
#endif
/* Identify owner for lock */
if (sessionLock)
owner = NULL;
else
owner = CurrentResourceOwner;
/*
* Find or create a LOCALLOCK entry for this lock and lockmode
*/
MemSet(&localtag, 0, sizeof(localtag)); /* must clear padding */
localtag.lock = *locktag;
localtag.mode = lockmode;
locallock = (LOCALLOCK *) hash_search(LockMethodLocalHash,
(void *) &localtag,
HASH_ENTER, &found);
/*
* if it's a new locallock object, initialize it
*/
if (!found)
{
locallock->lock = NULL;
locallock->proclock = NULL;
locallock->hashcode = LockTagHashCode(&(localtag.lock));
locallock->nLocks = 0;
locallock->numLockOwners = 0;
locallock->maxLockOwners = 8;
locallock->holdsStrongLockCount = false;
locallock->lockOwners = NULL; /* in case next line fails */
locallock->lockOwners = (LOCALLOCKOWNER *)
MemoryContextAlloc(TopMemoryContext,
locallock->maxLockOwners * sizeof(LOCALLOCKOWNER));
}
else
{
/* Make sure there will be room to remember the lock */
if (locallock->numLockOwners >= locallock->maxLockOwners)
{
int newsize = locallock->maxLockOwners * 2;
locallock->lockOwners = (LOCALLOCKOWNER *)
repalloc(locallock->lockOwners,
newsize * sizeof(LOCALLOCKOWNER));
locallock->maxLockOwners = newsize;
}
}
hashcode = locallock->hashcode;
/*
* If we already hold the lock, we can just increase the count locally.
*/
if (locallock->nLocks > 0)
{
GrantLockLocal(locallock, owner);
return LOCKACQUIRE_ALREADY_HELD;
}
/*
* Prepare to emit a WAL record if acquisition of this lock needs to be
* replayed in a standby server.
*
* Here we prepare to log; after lock is acquired we'll issue log record.
* This arrangement simplifies error recovery in case the preparation step
* fails.
*
* Only AccessExclusiveLocks can conflict with lock types that read-only
* transactions can acquire in a standby server. Make sure this definition
* matches the one in GetRunningTransactionLocks().
*/
if (lockmode >= AccessExclusiveLock &&
locktag->locktag_type == LOCKTAG_RELATION &&
!RecoveryInProgress() &&
XLogStandbyInfoActive())
{
LogAccessExclusiveLockPrepare();
log_lock = true;
}
/*
* Attempt to take lock via fast path, if eligible. But if we remember
* having filled up the fast path array, we don't attempt to make any
* further use of it until we release some locks. It's possible that some
* other backend has transferred some of those locks to the shared hash
* table, leaving space free, but it's not worth acquiring the LWLock just
* to check. It's also possible that we're acquiring a second or third
* lock type on a relation we have already locked using the fast-path, but
* for now we don't worry about that case either.
*/
if (EligibleForRelationFastPath(locktag, lockmode) &&
FastPathLocalUseCount < FP_LOCK_SLOTS_PER_BACKEND)
{
uint32 fasthashcode = FastPathStrongLockHashPartition(hashcode);
bool acquired;
/*
* LWLockAcquire acts as a memory sequencing point, so it's safe to
* assume that any strong locker whose increment to
* FastPathStrongRelationLocks->counts becomes visible after we test
* it has yet to begin to transfer fast-path locks.
*/
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
if (FastPathStrongRelationLocks->count[fasthashcode] != 0)
acquired = false;
else
acquired = FastPathGrantRelationLock(locktag->locktag_field2,
lockmode);
LWLockRelease(&MyProc->backendLock);
if (acquired)
{
/*
* The locallock might contain stale pointers to some old shared
* objects; we MUST reset these to null before considering the
* lock to be acquired via fast-path.
*/
locallock->lock = NULL;
locallock->proclock = NULL;
GrantLockLocal(locallock, owner);
return LOCKACQUIRE_OK;
}
}
/*
* If this lock could potentially have been taken via the fast-path by
* some other backend, we must (temporarily) disable further use of the
* fast-path for this lock tag, and migrate any locks already taken via
* this method to the main lock table.
*/
if (ConflictsWithRelationFastPath(locktag, lockmode))
{
uint32 fasthashcode = FastPathStrongLockHashPartition(hashcode);
BeginStrongLockAcquire(locallock, fasthashcode);
if (!FastPathTransferRelationLocks(lockMethodTable, locktag,
hashcode))
{
AbortStrongLockAcquire();
if (reportMemoryError)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
else
return LOCKACQUIRE_NOT_AVAIL;
}
}
/*
* We didn't find the lock in our LOCALLOCK table, and we didn't manage to
* take it via the fast-path, either, so we've got to mess with the shared
* lock table.
*/
partitionLock = LockHashPartitionLock(hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
/*
* Find or create lock and proclock entries with this tag
*
* Note: if the locallock object already existed, it might have a pointer
* to the lock already ... but we should not assume that that pointer is
* valid, since a lock object with zero hold and request counts can go
* away anytime. So we have to use SetupLockInTable() to recompute the
* lock and proclock pointers, even if they're already set.
*/
proclock = SetupLockInTable(lockMethodTable, MyProc, locktag,
hashcode, lockmode);
if (!proclock)
{
AbortStrongLockAcquire();
LWLockRelease(partitionLock);
if (reportMemoryError)
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
else
return LOCKACQUIRE_NOT_AVAIL;
}
locallock->proclock = proclock;
lock = proclock->tag.myLock;
locallock->lock = lock;
/*
* If lock requested conflicts with locks requested by waiters, must join
* wait queue. Otherwise, check for conflict with already-held locks.
* (That's last because most complex check.)
*/
if (lockMethodTable->conflictTab[lockmode] & lock->waitMask)
status = STATUS_FOUND;
else
status = LockCheckConflicts(lockMethodTable, lockmode,
lock, proclock);
if (status == STATUS_OK)
{
/* No conflict with held or previously requested locks */
GrantLock(lock, proclock, lockmode);
GrantLockLocal(locallock, owner);
}
else
{
Assert(status == STATUS_FOUND);
/*
* We can't acquire the lock immediately. If caller specified no
* blocking, remove useless table entries and return NOT_AVAIL without
* waiting.
*/
if (dontWait)
{
AbortStrongLockAcquire();
if (proclock->holdMask == 0)
{
uint32 proclock_hashcode;
proclock_hashcode = ProcLockHashCode(&proclock->tag, hashcode);
SHMQueueDelete(&proclock->lockLink);
SHMQueueDelete(&proclock->procLink);
if (!hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &(proclock->tag),
proclock_hashcode,
HASH_REMOVE,
NULL))
elog(PANIC, "proclock table corrupted");
}
else
PROCLOCK_PRINT("LockAcquire: NOWAIT", proclock);
lock->nRequested--;
lock->requested[lockmode]--;
LOCK_PRINT("LockAcquire: conditional lock failed", lock, lockmode);
Assert((lock->nRequested > 0) && (lock->requested[lockmode] >= 0));
Assert(lock->nGranted <= lock->nRequested);
LWLockRelease(partitionLock);
if (locallock->nLocks == 0)
RemoveLocalLock(locallock);
return LOCKACQUIRE_NOT_AVAIL;
}
/*
* Set bitmask of locks this process already holds on this object.
*/
MyProc->heldLocks = proclock->holdMask;
/*
* Sleep till someone wakes me up.
*/
TRACE_POSTGRESQL_LOCK_WAIT_START(locktag->locktag_field1,
locktag->locktag_field2,
locktag->locktag_field3,
locktag->locktag_field4,
locktag->locktag_type,
lockmode);
WaitOnLock(locallock, owner);
TRACE_POSTGRESQL_LOCK_WAIT_DONE(locktag->locktag_field1,
locktag->locktag_field2,
locktag->locktag_field3,
locktag->locktag_field4,
locktag->locktag_type,
lockmode);
/*
* NOTE: do not do any material change of state between here and
* return. All required changes in locktable state must have been
* done when the lock was granted to us --- see notes in WaitOnLock.
*/
/*
* Check the proclock entry status, in case something in the ipc
* communication doesn't work correctly.
*/
if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
{
AbortStrongLockAcquire();
PROCLOCK_PRINT("LockAcquire: INCONSISTENT", proclock);
LOCK_PRINT("LockAcquire: INCONSISTENT", lock, lockmode);
/* Should we retry ? */
LWLockRelease(partitionLock);
elog(ERROR, "LockAcquire failed");
}
PROCLOCK_PRINT("LockAcquire: granted", proclock);
LOCK_PRINT("LockAcquire: granted", lock, lockmode);
}
/*
* Lock state is fully up-to-date now; if we error out after this, no
* special error cleanup is required.
*/
FinishStrongLockAcquire();
LWLockRelease(partitionLock);
/*
* Emit a WAL record if acquisition of this lock needs to be replayed in a
* standby server.
*/
if (log_lock)
{
/*
* Decode the locktag back to the original values, to avoid sending
* lots of empty bytes with every message. See lock.h to check how a
* locktag is defined for LOCKTAG_RELATION
*/
LogAccessExclusiveLock(locktag->locktag_field1,
locktag->locktag_field2);
}
return LOCKACQUIRE_OK;
}
/*
* Find or create LOCK and PROCLOCK objects as needed for a new lock
* request.
*
* Returns the PROCLOCK object, or NULL if we failed to create the objects
* for lack of shared memory.
*
* The appropriate partition lock must be held at entry, and will be
* held at exit.
*/
static PROCLOCK *
SetupLockInTable(LockMethod lockMethodTable, PGPROC *proc,
const LOCKTAG *locktag, uint32 hashcode, LOCKMODE lockmode)
{
LOCK *lock;
PROCLOCK *proclock;
PROCLOCKTAG proclocktag;
uint32 proclock_hashcode;
bool found;
/*
* Find or create a lock with this tag.
*/
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(const void *) locktag,
hashcode,
HASH_ENTER_NULL,
&found);
if (!lock)
return NULL;
/*
* if it's a new lock object, initialize it
*/
if (!found)
{
lock->grantMask = 0;
lock->waitMask = 0;
SHMQueueInit(&(lock->procLocks));
ProcQueueInit(&(lock->waitProcs));
lock->nRequested = 0;
lock->nGranted = 0;
MemSet(lock->requested, 0, sizeof(int) * MAX_LOCKMODES);
MemSet(lock->granted, 0, sizeof(int) * MAX_LOCKMODES);
LOCK_PRINT("LockAcquire: new", lock, lockmode);
}
else
{
LOCK_PRINT("LockAcquire: found", lock, lockmode);
Assert((lock->nRequested >= 0) && (lock->requested[lockmode] >= 0));
Assert((lock->nGranted >= 0) && (lock->granted[lockmode] >= 0));
Assert(lock->nGranted <= lock->nRequested);
}
/*
* Create the hash key for the proclock table.
*/
proclocktag.myLock = lock;
proclocktag.myProc = proc;
proclock_hashcode = ProcLockHashCode(&proclocktag, hashcode);
/*
* Find or create a proclock entry with this tag
*/
proclock = (PROCLOCK *) hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &proclocktag,
proclock_hashcode,
HASH_ENTER_NULL,
&found);
if (!proclock)
{
/* Oops, not enough shmem for the proclock */
if (lock->nRequested == 0)
{
/*
* There are no other requestors of this lock, so garbage-collect
* the lock object. We *must* do this to avoid a permanent leak
* of shared memory, because there won't be anything to cause
* anyone to release the lock object later.
*/
Assert(SHMQueueEmpty(&(lock->procLocks)));
if (!hash_search_with_hash_value(LockMethodLockHash,
(void *) &(lock->tag),
hashcode,
HASH_REMOVE,
NULL))
elog(PANIC, "lock table corrupted");
}
return NULL;
}
/*
* If new, initialize the new entry
*/
if (!found)
{
uint32 partition = LockHashPartition(hashcode);
/*
* It might seem unsafe to access proclock->groupLeader without a
* lock, but it's not really. Either we are initializing a proclock
* on our own behalf, in which case our group leader isn't changing
* because the group leader for a process can only ever be changed by
* the process itself; or else we are transferring a fast-path lock to
* the main lock table, in which case that process can't change it's
* lock group leader without first releasing all of its locks (and in
* particular the one we are currently transferring).
*/
proclock->groupLeader = proc->lockGroupLeader != NULL ?
proc->lockGroupLeader : proc;
proclock->holdMask = 0;
proclock->releaseMask = 0;
/* Add proclock to appropriate lists */
SHMQueueInsertBefore(&lock->procLocks, &proclock->lockLink);
SHMQueueInsertBefore(&(proc->myProcLocks[partition]),
&proclock->procLink);
PROCLOCK_PRINT("LockAcquire: new", proclock);
}
else
{
PROCLOCK_PRINT("LockAcquire: found", proclock);
Assert((proclock->holdMask & ~lock->grantMask) == 0);
#ifdef CHECK_DEADLOCK_RISK
/*
* Issue warning if we already hold a lower-level lock on this object
* and do not hold a lock of the requested level or higher. This
* indicates a deadlock-prone coding practice (eg, we'd have a
* deadlock if another backend were following the same code path at
* about the same time).
*
* This is not enabled by default, because it may generate log entries
* about user-level coding practices that are in fact safe in context.
* It can be enabled to help find system-level problems.
*
* XXX Doing numeric comparison on the lockmodes is a hack; it'd be
* better to use a table. For now, though, this works.
*/
{
int i;
for (i = lockMethodTable->numLockModes; i > 0; i--)
{
if (proclock->holdMask & LOCKBIT_ON(i))
{
if (i >= (int) lockmode)
break; /* safe: we have a lock >= req level */
elog(LOG, "deadlock risk: raising lock level"
" from %s to %s on object %u/%u/%u",
lockMethodTable->lockModeNames[i],
lockMethodTable->lockModeNames[lockmode],
lock->tag.locktag_field1, lock->tag.locktag_field2,
lock->tag.locktag_field3);
break;
}
}
}
#endif /* CHECK_DEADLOCK_RISK */
}
/*
* lock->nRequested and lock->requested[] count the total number of
* requests, whether granted or waiting, so increment those immediately.
* The other counts don't increment till we get the lock.
*/
lock->nRequested++;
lock->requested[lockmode]++;
Assert((lock->nRequested > 0) && (lock->requested[lockmode] > 0));
/*
* We shouldn't already hold the desired lock; else locallock table is
* broken.
*/
if (proclock->holdMask & LOCKBIT_ON(lockmode))
elog(ERROR, "lock %s on object %u/%u/%u is already held",
lockMethodTable->lockModeNames[lockmode],
lock->tag.locktag_field1, lock->tag.locktag_field2,
lock->tag.locktag_field3);
return proclock;
}
/*
* Subroutine to free a locallock entry
*/
static void
RemoveLocalLock(LOCALLOCK *locallock)
{
int i;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (locallock->lockOwners[i].owner != NULL)
ResourceOwnerForgetLock(locallock->lockOwners[i].owner, locallock);
}
locallock->numLockOwners = 0;
if (locallock->lockOwners != NULL)
pfree(locallock->lockOwners);
locallock->lockOwners = NULL;
if (locallock->holdsStrongLockCount)
{
uint32 fasthashcode;
fasthashcode = FastPathStrongLockHashPartition(locallock->hashcode);
SpinLockAcquire(&FastPathStrongRelationLocks->mutex);
Assert(FastPathStrongRelationLocks->count[fasthashcode] > 0);
FastPathStrongRelationLocks->count[fasthashcode]--;
locallock->holdsStrongLockCount = false;
SpinLockRelease(&FastPathStrongRelationLocks->mutex);
}
if (!hash_search(LockMethodLocalHash,
(void *) &(locallock->tag),
HASH_REMOVE, NULL))
elog(WARNING, "locallock table corrupted");
}
/*
* LockCheckConflicts -- test whether requested lock conflicts
* with those already granted
*
* Returns STATUS_FOUND if conflict, STATUS_OK if no conflict.
*
* NOTES:
* Here's what makes this complicated: one process's locks don't
* conflict with one another, no matter what purpose they are held for
* (eg, session and transaction locks do not conflict). Nor do the locks
* of one process in a lock group conflict with those of another process in
* the same group. So, we must subtract off these locks when determining
* whether the requested new lock conflicts with those already held.
*/
int
LockCheckConflicts(LockMethod lockMethodTable,
LOCKMODE lockmode,
LOCK *lock,
PROCLOCK *proclock)
{
int numLockModes = lockMethodTable->numLockModes;
LOCKMASK myLocks;
int conflictMask = lockMethodTable->conflictTab[lockmode];
int conflictsRemaining[MAX_LOCKMODES];
int totalConflictsRemaining = 0;
int i;
SHM_QUEUE *procLocks;
PROCLOCK *otherproclock;
/*
* first check for global conflicts: If no locks conflict with my request,
* then I get the lock.
*
* Checking for conflict: lock->grantMask represents the types of
* currently held locks. conflictTable[lockmode] has a bit set for each
* type of lock that conflicts with request. Bitwise compare tells if
* there is a conflict.
*/
if (!(conflictMask & lock->grantMask))
{
PROCLOCK_PRINT("LockCheckConflicts: no conflict", proclock);
return STATUS_OK;
}
/*
* Rats. Something conflicts. But it could still be my own lock, or a
* lock held by another member of my locking group. First, figure out how
* many conflicts remain after subtracting out any locks I hold myself.
*/
myLocks = proclock->holdMask;
for (i = 1; i <= numLockModes; i++)
{
if ((conflictMask & LOCKBIT_ON(i)) == 0)
{
conflictsRemaining[i] = 0;
continue;
}
conflictsRemaining[i] = lock->granted[i];
if (myLocks & LOCKBIT_ON(i))
--conflictsRemaining[i];
totalConflictsRemaining += conflictsRemaining[i];
}
/* If no conflicts remain, we get the lock. */
if (totalConflictsRemaining == 0)
{
PROCLOCK_PRINT("LockCheckConflicts: resolved (simple)", proclock);
return STATUS_OK;
}
/* If no group locking, it's definitely a conflict. */
if (proclock->groupLeader == MyProc && MyProc->lockGroupLeader == NULL)
{
Assert(proclock->tag.myProc == MyProc);
PROCLOCK_PRINT("LockCheckConflicts: conflicting (simple)",
proclock);
return STATUS_FOUND;
}
/*
* Locks held in conflicting modes by members of our own lock group are
* not real conflicts; we can subtract those out and see if we still have
* a conflict. This is O(N) in the number of processes holding or
* awaiting locks on this object. We could improve that by making the
* shared memory state more complex (and larger) but it doesn't seem worth
* it.
*/
procLocks = &(lock->procLocks);
otherproclock = (PROCLOCK *)
SHMQueueNext(procLocks, procLocks, offsetof(PROCLOCK, lockLink));
while (otherproclock != NULL)
{
if (proclock != otherproclock &&
proclock->groupLeader == otherproclock->groupLeader &&
(otherproclock->holdMask & conflictMask) != 0)
{
int intersectMask = otherproclock->holdMask & conflictMask;
for (i = 1; i <= numLockModes; i++)
{
if ((intersectMask & LOCKBIT_ON(i)) != 0)
{
if (conflictsRemaining[i] <= 0)
elog(PANIC, "proclocks held do not match lock");
conflictsRemaining[i]--;
totalConflictsRemaining--;
}
}
if (totalConflictsRemaining == 0)
{
PROCLOCK_PRINT("LockCheckConflicts: resolved (group)",
proclock);
return STATUS_OK;
}
}
otherproclock = (PROCLOCK *)
SHMQueueNext(procLocks, &otherproclock->lockLink,
offsetof(PROCLOCK, lockLink));
}
/* Nope, it's a real conflict. */
PROCLOCK_PRINT("LockCheckConflicts: conflicting (group)", proclock);
return STATUS_FOUND;
}
/*
* GrantLock -- update the lock and proclock data structures to show
* the lock request has been granted.
*
* NOTE: if proc was blocked, it also needs to be removed from the wait list
* and have its waitLock/waitProcLock fields cleared. That's not done here.
*
* NOTE: the lock grant also has to be recorded in the associated LOCALLOCK
* table entry; but since we may be awaking some other process, we can't do
* that here; it's done by GrantLockLocal, instead.
*/
void
GrantLock(LOCK *lock, PROCLOCK *proclock, LOCKMODE lockmode)
{
lock->nGranted++;
lock->granted[lockmode]++;
lock->grantMask |= LOCKBIT_ON(lockmode);
if (lock->granted[lockmode] == lock->requested[lockmode])
lock->waitMask &= LOCKBIT_OFF(lockmode);
proclock->holdMask |= LOCKBIT_ON(lockmode);
LOCK_PRINT("GrantLock", lock, lockmode);
Assert((lock->nGranted > 0) && (lock->granted[lockmode] > 0));
Assert(lock->nGranted <= lock->nRequested);
}
/*
* UnGrantLock -- opposite of GrantLock.
*
* Updates the lock and proclock data structures to show that the lock
* is no longer held nor requested by the current holder.
*
* Returns true if there were any waiters waiting on the lock that
* should now be woken up with ProcLockWakeup.
*/
static bool
UnGrantLock(LOCK *lock, LOCKMODE lockmode,
PROCLOCK *proclock, LockMethod lockMethodTable)
{
bool wakeupNeeded = false;
Assert((lock->nRequested > 0) && (lock->requested[lockmode] > 0));
Assert((lock->nGranted > 0) && (lock->granted[lockmode] > 0));
Assert(lock->nGranted <= lock->nRequested);
/*
* fix the general lock stats
*/
lock->nRequested--;
lock->requested[lockmode]--;
lock->nGranted--;
lock->granted[lockmode]--;
if (lock->granted[lockmode] == 0)
{
/* change the conflict mask. No more of this lock type. */
lock->grantMask &= LOCKBIT_OFF(lockmode);
}
LOCK_PRINT("UnGrantLock: updated", lock, lockmode);
/*
* We need only run ProcLockWakeup if the released lock conflicts with at
* least one of the lock types requested by waiter(s). Otherwise whatever
* conflict made them wait must still exist. NOTE: before MVCC, we could
* skip wakeup if lock->granted[lockmode] was still positive. But that's
* not true anymore, because the remaining granted locks might belong to
* some waiter, who could now be awakened because he doesn't conflict with
* his own locks.
*/
if (lockMethodTable->conflictTab[lockmode] & lock->waitMask)
wakeupNeeded = true;
/*
* Now fix the per-proclock state.
*/
proclock->holdMask &= LOCKBIT_OFF(lockmode);
PROCLOCK_PRINT("UnGrantLock: updated", proclock);
return wakeupNeeded;
}
/*
* CleanUpLock -- clean up after releasing a lock. We garbage-collect the
* proclock and lock objects if possible, and call ProcLockWakeup if there
* are remaining requests and the caller says it's OK. (Normally, this
* should be called after UnGrantLock, and wakeupNeeded is the result from
* UnGrantLock.)
*
* The appropriate partition lock must be held at entry, and will be
* held at exit.
*/
static void
CleanUpLock(LOCK *lock, PROCLOCK *proclock,
LockMethod lockMethodTable, uint32 hashcode,
bool wakeupNeeded)
{
/*
* If this was my last hold on this lock, delete my entry in the proclock
* table.
*/
if (proclock->holdMask == 0)
{
uint32 proclock_hashcode;
PROCLOCK_PRINT("CleanUpLock: deleting", proclock);
SHMQueueDelete(&proclock->lockLink);
SHMQueueDelete(&proclock->procLink);
proclock_hashcode = ProcLockHashCode(&proclock->tag, hashcode);
if (!hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &(proclock->tag),
proclock_hashcode,
HASH_REMOVE,
NULL))
elog(PANIC, "proclock table corrupted");
}
if (lock->nRequested == 0)
{
/*
* The caller just released the last lock, so garbage-collect the lock
* object.
*/
LOCK_PRINT("CleanUpLock: deleting", lock, 0);
Assert(SHMQueueEmpty(&(lock->procLocks)));
if (!hash_search_with_hash_value(LockMethodLockHash,
(void *) &(lock->tag),
hashcode,
HASH_REMOVE,
NULL))
elog(PANIC, "lock table corrupted");
}
else if (wakeupNeeded)
{
/* There are waiters on this lock, so wake them up. */
ProcLockWakeup(lockMethodTable, lock);
}
}
/*
* GrantLockLocal -- update the locallock data structures to show
* the lock request has been granted.
*
* We expect that LockAcquire made sure there is room to add a new
* ResourceOwner entry.
*/
static void
GrantLockLocal(LOCALLOCK *locallock, ResourceOwner owner)
{
LOCALLOCKOWNER *lockOwners = locallock->lockOwners;
int i;
Assert(locallock->numLockOwners < locallock->maxLockOwners);
/* Count the total */
locallock->nLocks++;
/* Count the per-owner lock */
for (i = 0; i < locallock->numLockOwners; i++)
{
if (lockOwners[i].owner == owner)
{
lockOwners[i].nLocks++;
return;
}
}
lockOwners[i].owner = owner;
lockOwners[i].nLocks = 1;
locallock->numLockOwners++;
if (owner != NULL)
ResourceOwnerRememberLock(owner, locallock);
}
/*
* BeginStrongLockAcquire - inhibit use of fastpath for a given LOCALLOCK,
* and arrange for error cleanup if it fails
*/
static void
BeginStrongLockAcquire(LOCALLOCK *locallock, uint32 fasthashcode)
{
Assert(StrongLockInProgress == NULL);
Assert(locallock->holdsStrongLockCount == false);
/*
* Adding to a memory location is not atomic, so we take a spinlock to
* ensure we don't collide with someone else trying to bump the count at
* the same time.
*
* XXX: It might be worth considering using an atomic fetch-and-add
* instruction here, on architectures where that is supported.
*/
SpinLockAcquire(&FastPathStrongRelationLocks->mutex);
FastPathStrongRelationLocks->count[fasthashcode]++;
locallock->holdsStrongLockCount = true;
StrongLockInProgress = locallock;
SpinLockRelease(&FastPathStrongRelationLocks->mutex);
}
/*
* FinishStrongLockAcquire - cancel pending cleanup for a strong lock
* acquisition once it's no longer needed
*/
static void
FinishStrongLockAcquire(void)
{
StrongLockInProgress = NULL;
}
/*
* AbortStrongLockAcquire - undo strong lock state changes performed by
* BeginStrongLockAcquire.
*/
void
AbortStrongLockAcquire(void)
{
uint32 fasthashcode;
LOCALLOCK *locallock = StrongLockInProgress;
if (locallock == NULL)
return;
fasthashcode = FastPathStrongLockHashPartition(locallock->hashcode);
Assert(locallock->holdsStrongLockCount == true);
SpinLockAcquire(&FastPathStrongRelationLocks->mutex);
Assert(FastPathStrongRelationLocks->count[fasthashcode] > 0);
FastPathStrongRelationLocks->count[fasthashcode]--;
locallock->holdsStrongLockCount = false;
StrongLockInProgress = NULL;
SpinLockRelease(&FastPathStrongRelationLocks->mutex);
}
/*
* GrantAwaitedLock -- call GrantLockLocal for the lock we are doing
* WaitOnLock on.
*
* proc.c needs this for the case where we are booted off the lock by
* timeout, but discover that someone granted us the lock anyway.
*
* We could just export GrantLockLocal, but that would require including
* resowner.h in lock.h, which creates circularity.
*/
void
GrantAwaitedLock(void)
{
GrantLockLocal(awaitedLock, awaitedOwner);
}
/*
* WaitOnLock -- wait to acquire a lock
*
* Caller must have set MyProc->heldLocks to reflect locks already held
* on the lockable object by this process.
*
* The appropriate partition lock must be held at entry.
*/
static void
WaitOnLock(LOCALLOCK *locallock, ResourceOwner owner)
{
LOCKMETHODID lockmethodid = LOCALLOCK_LOCKMETHOD(*locallock);
LockMethod lockMethodTable = LockMethods[lockmethodid];
char *volatile new_status = NULL;
LOCK_PRINT("WaitOnLock: sleeping on lock",
locallock->lock, locallock->tag.mode);
/* Report change to waiting status */
if (update_process_title)
{
const char *old_status;
int len;
old_status = get_ps_display(&len);
new_status = (char *) palloc(len + 8 + 1);
memcpy(new_status, old_status, len);
strcpy(new_status + len, " waiting");
set_ps_display(new_status, false);
new_status[len] = '\0'; /* truncate off " waiting" */
}
awaitedLock = locallock;
awaitedOwner = owner;
/*
* NOTE: Think not to put any shared-state cleanup after the call to
* ProcSleep, in either the normal or failure path. The lock state must
* be fully set by the lock grantor, or by CheckDeadLock if we give up
* waiting for the lock. This is necessary because of the possibility
* that a cancel/die interrupt will interrupt ProcSleep after someone else
* grants us the lock, but before we've noticed it. Hence, after granting,
* the locktable state must fully reflect the fact that we own the lock;
* we can't do additional work on return.
*
* We can and do use a PG_TRY block to try to clean up after failure, but
* this still has a major limitation: elog(FATAL) can occur while waiting
* (eg, a "die" interrupt), and then control won't come back here. So all
* cleanup of essential state should happen in LockErrorCleanup, not here.
* We can use PG_TRY to clear the "waiting" status flags, since doing that
* is unimportant if the process exits.
*/
PG_TRY();
{
if (ProcSleep(locallock, lockMethodTable) != STATUS_OK)
{
/*
* We failed as a result of a deadlock, see CheckDeadLock(). Quit
* now.
*/
awaitedLock = NULL;
LOCK_PRINT("WaitOnLock: aborting on lock",
locallock->lock, locallock->tag.mode);
LWLockRelease(LockHashPartitionLock(locallock->hashcode));
/*
* Now that we aren't holding the partition lock, we can give an
* error report including details about the detected deadlock.
*/
DeadLockReport();
/* not reached */
}
}
PG_CATCH();
{
/* In this path, awaitedLock remains set until LockErrorCleanup */
/* Report change to non-waiting status */
if (update_process_title)
{
set_ps_display(new_status, false);
pfree(new_status);
}
/* and propagate the error */
PG_RE_THROW();
}
PG_END_TRY();
awaitedLock = NULL;
/* Report change to non-waiting status */
if (update_process_title)
{
set_ps_display(new_status, false);
pfree(new_status);
}
LOCK_PRINT("WaitOnLock: wakeup on lock",
locallock->lock, locallock->tag.mode);
}
/*
* Remove a proc from the wait-queue it is on (caller must know it is on one).
* This is only used when the proc has failed to get the lock, so we set its
* waitStatus to STATUS_ERROR.
*
* Appropriate partition lock must be held by caller. Also, caller is
* responsible for signaling the proc if needed.
*
* NB: this does not clean up any locallock object that may exist for the lock.
*/
void
RemoveFromWaitQueue(PGPROC *proc, uint32 hashcode)
{
LOCK *waitLock = proc->waitLock;
PROCLOCK *proclock = proc->waitProcLock;
LOCKMODE lockmode = proc->waitLockMode;
LOCKMETHODID lockmethodid = LOCK_LOCKMETHOD(*waitLock);
/* Make sure proc is waiting */
Assert(proc->waitStatus == STATUS_WAITING);
Assert(proc->links.next != NULL);
Assert(waitLock);
Assert(waitLock->waitProcs.size > 0);
Assert(0 < lockmethodid && lockmethodid < lengthof(LockMethods));
/* Remove proc from lock's wait queue */
SHMQueueDelete(&(proc->links));
waitLock->waitProcs.size--;
/* Undo increments of request counts by waiting process */
Assert(waitLock->nRequested > 0);
Assert(waitLock->nRequested > proc->waitLock->nGranted);
waitLock->nRequested--;
Assert(waitLock->requested[lockmode] > 0);
waitLock->requested[lockmode]--;
/* don't forget to clear waitMask bit if appropriate */
if (waitLock->granted[lockmode] == waitLock->requested[lockmode])
waitLock->waitMask &= LOCKBIT_OFF(lockmode);
/* Clean up the proc's own state, and pass it the ok/fail signal */
proc->waitLock = NULL;
proc->waitProcLock = NULL;
proc->waitStatus = STATUS_ERROR;
/*
* Delete the proclock immediately if it represents no already-held locks.
* (This must happen now because if the owner of the lock decides to
* release it, and the requested/granted counts then go to zero,
* LockRelease expects there to be no remaining proclocks.) Then see if
* any other waiters for the lock can be woken up now.
*/
CleanUpLock(waitLock, proclock,
LockMethods[lockmethodid], hashcode,
true);
}
/*
* LockRelease -- look up 'locktag' and release one 'lockmode' lock on it.
* Release a session lock if 'sessionLock' is true, else release a
* regular transaction lock.
*
* Side Effects: find any waiting processes that are now wakable,
* grant them their requested locks and awaken them.
* (We have to grant the lock here to avoid a race between
* the waking process and any new process to
* come along and request the lock.)
*/
bool
LockRelease(const LOCKTAG *locktag, LOCKMODE lockmode, bool sessionLock)
{
LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid;
LockMethod lockMethodTable;
LOCALLOCKTAG localtag;
LOCALLOCK *locallock;
LOCK *lock;
PROCLOCK *proclock;
LWLock *partitionLock;
bool wakeupNeeded;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
if (lockmode <= 0 || lockmode > lockMethodTable->numLockModes)
elog(ERROR, "unrecognized lock mode: %d", lockmode);
#ifdef LOCK_DEBUG
if (LOCK_DEBUG_ENABLED(locktag))
elog(LOG, "LockRelease: lock [%u,%u] %s",
locktag->locktag_field1, locktag->locktag_field2,
lockMethodTable->lockModeNames[lockmode]);
#endif
/*
* Find the LOCALLOCK entry for this lock and lockmode
*/
MemSet(&localtag, 0, sizeof(localtag)); /* must clear padding */
localtag.lock = *locktag;
localtag.mode = lockmode;
locallock = (LOCALLOCK *) hash_search(LockMethodLocalHash,
(void *) &localtag,
HASH_FIND, NULL);
/*
* let the caller print its own error message, too. Do not ereport(ERROR).
*/
if (!locallock || locallock->nLocks <= 0)
{
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
return false;
}
/*
* Decrease the count for the resource owner.
*/
{
LOCALLOCKOWNER *lockOwners = locallock->lockOwners;
ResourceOwner owner;
int i;
/* Identify owner for lock */
if (sessionLock)
owner = NULL;
else
owner = CurrentResourceOwner;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (lockOwners[i].owner == owner)
{
Assert(lockOwners[i].nLocks > 0);
if (--lockOwners[i].nLocks == 0)
{
if (owner != NULL)
ResourceOwnerForgetLock(owner, locallock);
/* compact out unused slot */
locallock->numLockOwners--;
if (i < locallock->numLockOwners)
lockOwners[i] = lockOwners[locallock->numLockOwners];
}
break;
}
}
if (i < 0)
{
/* don't release a lock belonging to another owner */
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
return false;
}
}
/*
* Decrease the total local count. If we're still holding the lock, we're
* done.
*/
locallock->nLocks--;
if (locallock->nLocks > 0)
return true;
/* Attempt fast release of any lock eligible for the fast path. */
if (EligibleForRelationFastPath(locktag, lockmode) &&
FastPathLocalUseCount > 0)
{
bool released;
/*
* We might not find the lock here, even if we originally entered it
* here. Another backend may have moved it to the main table.
*/
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
released = FastPathUnGrantRelationLock(locktag->locktag_field2,
lockmode);
LWLockRelease(&MyProc->backendLock);
if (released)
{
RemoveLocalLock(locallock);
return true;
}
}
/*
* Otherwise we've got to mess with the shared lock table.
*/
partitionLock = LockHashPartitionLock(locallock->hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
/*
* Normally, we don't need to re-find the lock or proclock, since we kept
* their addresses in the locallock table, and they couldn't have been
* removed while we were holding a lock on them. But it's possible that
* the lock was taken fast-path and has since been moved to the main hash
* table by another backend, in which case we will need to look up the
* objects here. We assume the lock field is NULL if so.
*/
lock = locallock->lock;
if (!lock)
{
PROCLOCKTAG proclocktag;
Assert(EligibleForRelationFastPath(locktag, lockmode));
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(const void *) locktag,
locallock->hashcode,
HASH_FIND,
NULL);
if (!lock)
elog(ERROR, "failed to re-find shared lock object");
locallock->lock = lock;
proclocktag.myLock = lock;
proclocktag.myProc = MyProc;
locallock->proclock = (PROCLOCK *) hash_search(LockMethodProcLockHash,
(void *) &proclocktag,
HASH_FIND,
NULL);
if (!locallock->proclock)
elog(ERROR, "failed to re-find shared proclock object");
}
LOCK_PRINT("LockRelease: found", lock, lockmode);
proclock = locallock->proclock;
PROCLOCK_PRINT("LockRelease: found", proclock);
/*
* Double-check that we are actually holding a lock of the type we want to
* release.
*/
if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
{
PROCLOCK_PRINT("LockRelease: WRONGTYPE", proclock);
LWLockRelease(partitionLock);
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
RemoveLocalLock(locallock);
return false;
}
/*
* Do the releasing. CleanUpLock will waken any now-wakable waiters.
*/
wakeupNeeded = UnGrantLock(lock, lockmode, proclock, lockMethodTable);
CleanUpLock(lock, proclock,
lockMethodTable, locallock->hashcode,
wakeupNeeded);
LWLockRelease(partitionLock);
RemoveLocalLock(locallock);
return true;
}
/*
* LockReleaseAll -- Release all locks of the specified lock method that
* are held by the current process.
*
* Well, not necessarily *all* locks. The available behaviors are:
* allLocks == true: release all locks including session locks.
* allLocks == false: release all non-session locks.
*/
void
LockReleaseAll(LOCKMETHODID lockmethodid, bool allLocks)
{
HASH_SEQ_STATUS status;
LockMethod lockMethodTable;
int i,
numLockModes;
LOCALLOCK *locallock;
LOCK *lock;
PROCLOCK *proclock;
int partition;
bool have_fast_path_lwlock = false;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
#ifdef LOCK_DEBUG
if (*(lockMethodTable->trace_flag))
elog(LOG, "LockReleaseAll: lockmethod=%d", lockmethodid);
#endif
/*
* Get rid of our fast-path VXID lock, if appropriate. Note that this is
* the only way that the lock we hold on our own VXID can ever get
* released: it is always and only released when a toplevel transaction
* ends.
*/
if (lockmethodid == DEFAULT_LOCKMETHOD)
VirtualXactLockTableCleanup();
numLockModes = lockMethodTable->numLockModes;
/*
* First we run through the locallock table and get rid of unwanted
* entries, then we scan the process's proclocks and get rid of those. We
* do this separately because we may have multiple locallock entries
* pointing to the same proclock, and we daren't end up with any dangling
* pointers. Fast-path locks are cleaned up during the locallock table
* scan, though.
*/
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
{
/*
* If the LOCALLOCK entry is unused, we must've run out of shared
* memory while trying to set up this lock. Just forget the local
* entry.
*/
if (locallock->nLocks == 0)
{
RemoveLocalLock(locallock);
continue;
}
/* Ignore items that are not of the lockmethod to be removed */
if (LOCALLOCK_LOCKMETHOD(*locallock) != lockmethodid)
continue;
/*
* If we are asked to release all locks, we can just zap the entry.
* Otherwise, must scan to see if there are session locks. We assume
* there is at most one lockOwners entry for session locks.
*/
if (!allLocks)
{
LOCALLOCKOWNER *lockOwners = locallock->lockOwners;
/* If session lock is above array position 0, move it down to 0 */
for (i = 0; i < locallock->numLockOwners; i++)
{
if (lockOwners[i].owner == NULL)
lockOwners[0] = lockOwners[i];
else
ResourceOwnerForgetLock(lockOwners[i].owner, locallock);
}
if (locallock->numLockOwners > 0 &&
lockOwners[0].owner == NULL &&
lockOwners[0].nLocks > 0)
{
/* Fix the locallock to show just the session locks */
locallock->nLocks = lockOwners[0].nLocks;
locallock->numLockOwners = 1;
/* We aren't deleting this locallock, so done */
continue;
}
else
locallock->numLockOwners = 0;
}
/*
* If the lock or proclock pointers are NULL, this lock was taken via
* the relation fast-path (and is not known to have been transferred).
*/
if (locallock->proclock == NULL || locallock->lock == NULL)
{
LOCKMODE lockmode = locallock->tag.mode;
Oid relid;
/* Verify that a fast-path lock is what we've got. */
if (!EligibleForRelationFastPath(&locallock->tag.lock, lockmode))
elog(PANIC, "locallock table corrupted");
/*
* If we don't currently hold the LWLock that protects our
* fast-path data structures, we must acquire it before attempting
* to release the lock via the fast-path. We will continue to
* hold the LWLock until we're done scanning the locallock table,
* unless we hit a transferred fast-path lock. (XXX is this
* really such a good idea? There could be a lot of entries ...)
*/
if (!have_fast_path_lwlock)
{
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
have_fast_path_lwlock = true;
}
/* Attempt fast-path release. */
relid = locallock->tag.lock.locktag_field2;
if (FastPathUnGrantRelationLock(relid, lockmode))
{
RemoveLocalLock(locallock);
continue;
}
/*
* Our lock, originally taken via the fast path, has been
* transferred to the main lock table. That's going to require
* some extra work, so release our fast-path lock before starting.
*/
LWLockRelease(&MyProc->backendLock);
have_fast_path_lwlock = false;
/*
* Now dump the lock. We haven't got a pointer to the LOCK or
* PROCLOCK in this case, so we have to handle this a bit
* differently than a normal lock release. Unfortunately, this
* requires an extra LWLock acquire-and-release cycle on the
* partitionLock, but hopefully it shouldn't happen often.
*/
LockRefindAndRelease(lockMethodTable, MyProc,
&locallock->tag.lock, lockmode, false);
RemoveLocalLock(locallock);
continue;
}
/* Mark the proclock to show we need to release this lockmode */
if (locallock->nLocks > 0)
locallock->proclock->releaseMask |= LOCKBIT_ON(locallock->tag.mode);
/* And remove the locallock hashtable entry */
RemoveLocalLock(locallock);
}
/* Done with the fast-path data structures */
if (have_fast_path_lwlock)
LWLockRelease(&MyProc->backendLock);
/*
* Now, scan each lock partition separately.
*/
for (partition = 0; partition < NUM_LOCK_PARTITIONS; partition++)
{
LWLock *partitionLock;
SHM_QUEUE *procLocks = &(MyProc->myProcLocks[partition]);
PROCLOCK *nextplock;
partitionLock = LockHashPartitionLockByIndex(partition);
/*
* If the proclock list for this partition is empty, we can skip
* acquiring the partition lock. This optimization is trickier than
* it looks, because another backend could be in process of adding
* something to our proclock list due to promoting one of our
* fast-path locks. However, any such lock must be one that we
* decided not to delete above, so it's okay to skip it again now;
* we'd just decide not to delete it again. We must, however, be
* careful to re-fetch the list header once we've acquired the
* partition lock, to be sure we have a valid, up-to-date pointer.
* (There is probably no significant risk if pointer fetch/store is
* atomic, but we don't wish to assume that.)
*
* XXX This argument assumes that the locallock table correctly
* represents all of our fast-path locks. While allLocks mode
* guarantees to clean up all of our normal locks regardless of the
* locallock situation, we lose that guarantee for fast-path locks.
* This is not ideal.
*/
if (SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, procLink)) == NULL)
continue; /* needn't examine this partition */
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
for (proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, procLink));
proclock;
proclock = nextplock)
{
bool wakeupNeeded = false;
/* Get link first, since we may unlink/delete this proclock */
nextplock = (PROCLOCK *)
SHMQueueNext(procLocks, &proclock->procLink,
offsetof(PROCLOCK, procLink));
Assert(proclock->tag.myProc == MyProc);
lock = proclock->tag.myLock;
/* Ignore items that are not of the lockmethod to be removed */
if (LOCK_LOCKMETHOD(*lock) != lockmethodid)
continue;
/*
* In allLocks mode, force release of all locks even if locallock
* table had problems
*/
if (allLocks)
proclock->releaseMask = proclock->holdMask;
else
Assert((proclock->releaseMask & ~proclock->holdMask) == 0);
/*
* Ignore items that have nothing to be released, unless they have
* holdMask == 0 and are therefore recyclable
*/
if (proclock->releaseMask == 0 && proclock->holdMask != 0)
continue;
PROCLOCK_PRINT("LockReleaseAll", proclock);
LOCK_PRINT("LockReleaseAll", lock, 0);
Assert(lock->nRequested >= 0);
Assert(lock->nGranted >= 0);
Assert(lock->nGranted <= lock->nRequested);
Assert((proclock->holdMask & ~lock->grantMask) == 0);
/*
* Release the previously-marked lock modes
*/
for (i = 1; i <= numLockModes; i++)
{
if (proclock->releaseMask & LOCKBIT_ON(i))
wakeupNeeded |= UnGrantLock(lock, i, proclock,
lockMethodTable);
}
Assert((lock->nRequested >= 0) && (lock->nGranted >= 0));
Assert(lock->nGranted <= lock->nRequested);
LOCK_PRINT("LockReleaseAll: updated", lock, 0);
proclock->releaseMask = 0;
/* CleanUpLock will wake up waiters if needed. */
CleanUpLock(lock, proclock,
lockMethodTable,
LockTagHashCode(&lock->tag),
wakeupNeeded);
} /* loop over PROCLOCKs within this partition */
LWLockRelease(partitionLock);
} /* loop over partitions */
#ifdef LOCK_DEBUG
if (*(lockMethodTable->trace_flag))
elog(LOG, "LockReleaseAll done");
#endif
}
/*
* LockReleaseSession -- Release all session locks of the specified lock method
* that are held by the current process.
*/
void
LockReleaseSession(LOCKMETHODID lockmethodid)
{
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
{
/* Ignore items that are not of the specified lock method */
if (LOCALLOCK_LOCKMETHOD(*locallock) != lockmethodid)
continue;
ReleaseLockIfHeld(locallock, true);
}
}
/*
* LockReleaseCurrentOwner
* Release all locks belonging to CurrentResourceOwner
*
* If the caller knows what those locks are, it can pass them as an array.
* That speeds up the call significantly, when a lot of locks are held.
* Otherwise, pass NULL for locallocks, and we'll traverse through our hash
* table to find them.
*/
void
LockReleaseCurrentOwner(LOCALLOCK **locallocks, int nlocks)
{
if (locallocks == NULL)
{
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
ReleaseLockIfHeld(locallock, false);
}
else
{
int i;
for (i = nlocks - 1; i >= 0; i--)
ReleaseLockIfHeld(locallocks[i], false);
}
}
/*
* ReleaseLockIfHeld
* Release any session-level locks on this lockable object if sessionLock
* is true; else, release any locks held by CurrentResourceOwner.
*
* It is tempting to pass this a ResourceOwner pointer (or NULL for session
* locks), but without refactoring LockRelease() we cannot support releasing
* locks belonging to resource owners other than CurrentResourceOwner.
* If we were to refactor, it'd be a good idea to fix it so we don't have to
* do a hashtable lookup of the locallock, too. However, currently this
* function isn't used heavily enough to justify refactoring for its
* convenience.
*/
static void
ReleaseLockIfHeld(LOCALLOCK *locallock, bool sessionLock)
{
ResourceOwner owner;
LOCALLOCKOWNER *lockOwners;
int i;
/* Identify owner for lock (must match LockRelease!) */
if (sessionLock)
owner = NULL;
else
owner = CurrentResourceOwner;
/* Scan to see if there are any locks belonging to the target owner */
lockOwners = locallock->lockOwners;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (lockOwners[i].owner == owner)
{
Assert(lockOwners[i].nLocks > 0);
if (lockOwners[i].nLocks < locallock->nLocks)
{
/*
* We will still hold this lock after forgetting this
* ResourceOwner.
*/
locallock->nLocks -= lockOwners[i].nLocks;
/* compact out unused slot */
locallock->numLockOwners--;
if (owner != NULL)
ResourceOwnerForgetLock(owner, locallock);
if (i < locallock->numLockOwners)
lockOwners[i] = lockOwners[locallock->numLockOwners];
}
else
{
Assert(lockOwners[i].nLocks == locallock->nLocks);
/* We want to call LockRelease just once */
lockOwners[i].nLocks = 1;
locallock->nLocks = 1;
if (!LockRelease(&locallock->tag.lock,
locallock->tag.mode,
sessionLock))
elog(WARNING, "ReleaseLockIfHeld: failed??");
}
break;
}
}
}
/*
* LockReassignCurrentOwner
* Reassign all locks belonging to CurrentResourceOwner to belong
* to its parent resource owner.
*
* If the caller knows what those locks are, it can pass them as an array.
* That speeds up the call significantly, when a lot of locks are held
* (e.g pg_dump with a large schema). Otherwise, pass NULL for locallocks,
* and we'll traverse through our hash table to find them.
*/
void
LockReassignCurrentOwner(LOCALLOCK **locallocks, int nlocks)
{
ResourceOwner parent = ResourceOwnerGetParent(CurrentResourceOwner);
Assert(parent != NULL);
if (locallocks == NULL)
{
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
LockReassignOwner(locallock, parent);
}
else
{
int i;
for (i = nlocks - 1; i >= 0; i--)
LockReassignOwner(locallocks[i], parent);
}
}
/*
* Subroutine of LockReassignCurrentOwner. Reassigns a given lock belonging to
* CurrentResourceOwner to its parent.
*/
static void
LockReassignOwner(LOCALLOCK *locallock, ResourceOwner parent)
{
LOCALLOCKOWNER *lockOwners;
int i;
int ic = -1;
int ip = -1;
/*
* Scan to see if there are any locks belonging to current owner or its
* parent
*/
lockOwners = locallock->lockOwners;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (lockOwners[i].owner == CurrentResourceOwner)
ic = i;
else if (lockOwners[i].owner == parent)
ip = i;
}
if (ic < 0)
return; /* no current locks */
if (ip < 0)
{
/* Parent has no slot, so just give it the child's slot */
lockOwners[ic].owner = parent;
ResourceOwnerRememberLock(parent, locallock);
}
else
{
/* Merge child's count with parent's */
lockOwners[ip].nLocks += lockOwners[ic].nLocks;
/* compact out unused slot */
locallock->numLockOwners--;
if (ic < locallock->numLockOwners)
lockOwners[ic] = lockOwners[locallock->numLockOwners];
}
ResourceOwnerForgetLock(CurrentResourceOwner, locallock);
}
/*
* FastPathGrantRelationLock
* Grant lock using per-backend fast-path array, if there is space.
*/
static bool
FastPathGrantRelationLock(Oid relid, LOCKMODE lockmode)
{
uint32 f;
uint32 unused_slot = FP_LOCK_SLOTS_PER_BACKEND;
/* Scan for existing entry for this relid, remembering empty slot. */
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
{
if (FAST_PATH_GET_BITS(MyProc, f) == 0)
unused_slot = f;
else if (MyProc->fpRelId[f] == relid)
{
Assert(!FAST_PATH_CHECK_LOCKMODE(MyProc, f, lockmode));
FAST_PATH_SET_LOCKMODE(MyProc, f, lockmode);
return true;
}
}
/* If no existing entry, use any empty slot. */
if (unused_slot < FP_LOCK_SLOTS_PER_BACKEND)
{
MyProc->fpRelId[unused_slot] = relid;
FAST_PATH_SET_LOCKMODE(MyProc, unused_slot, lockmode);
++FastPathLocalUseCount;
return true;
}
/* No existing entry, and no empty slot. */
return false;
}
/*
* FastPathUnGrantRelationLock
* Release fast-path lock, if present. Update backend-private local
* use count, while we're at it.
*/
static bool
FastPathUnGrantRelationLock(Oid relid, LOCKMODE lockmode)
{
uint32 f;
bool result = false;
FastPathLocalUseCount = 0;
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
{
if (MyProc->fpRelId[f] == relid
&& FAST_PATH_CHECK_LOCKMODE(MyProc, f, lockmode))
{
Assert(!result);
FAST_PATH_CLEAR_LOCKMODE(MyProc, f, lockmode);
result = true;
/* we continue iterating so as to update FastPathLocalUseCount */
}
if (FAST_PATH_GET_BITS(MyProc, f) != 0)
++FastPathLocalUseCount;
}
return result;
}
/*
* FastPathTransferRelationLocks
* Transfer locks matching the given lock tag from per-backend fast-path
* arrays to the shared hash table.
*
* Returns true if successful, false if ran out of shared memory.
*/
static bool
FastPathTransferRelationLocks(LockMethod lockMethodTable, const LOCKTAG *locktag,
uint32 hashcode)
{
LWLock *partitionLock = LockHashPartitionLock(hashcode);
Oid relid = locktag->locktag_field2;
uint32 i;
/*
* Every PGPROC that can potentially hold a fast-path lock is present in
* ProcGlobal->allProcs. Prepared transactions are not, but any
* outstanding fast-path locks held by prepared transactions are
* transferred to the main lock table.
*/
for (i = 0; i < ProcGlobal->allProcCount; i++)
{
PGPROC *proc = &ProcGlobal->allProcs[i];
uint32 f;
LWLockAcquire(&proc->backendLock, LW_EXCLUSIVE);
/*
* If the target backend isn't referencing the same database as the
* lock, then we needn't examine the individual relation IDs at all;
* none of them can be relevant.
*
* proc->databaseId is set at backend startup time and never changes
* thereafter, so it might be safe to perform this test before
* acquiring &proc->backendLock. In particular, it's certainly safe
* to assume that if the target backend holds any fast-path locks, it
* must have performed a memory-fencing operation (in particular, an
* LWLock acquisition) since setting proc->databaseId. However, it's
* less clear that our backend is certain to have performed a memory
* fencing operation since the other backend set proc->databaseId. So
* for now, we test it after acquiring the LWLock just to be safe.
*/
if (proc->databaseId != locktag->locktag_field1)
{
LWLockRelease(&proc->backendLock);
continue;
}
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
{
uint32 lockmode;
/* Look for an allocated slot matching the given relid. */
if (relid != proc->fpRelId[f] || FAST_PATH_GET_BITS(proc, f) == 0)
continue;
/* Find or create lock object. */
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
for (lockmode = FAST_PATH_LOCKNUMBER_OFFSET;
lockmode < FAST_PATH_LOCKNUMBER_OFFSET + FAST_PATH_BITS_PER_SLOT;
++lockmode)
{
PROCLOCK *proclock;
if (!FAST_PATH_CHECK_LOCKMODE(proc, f, lockmode))
continue;
proclock = SetupLockInTable(lockMethodTable, proc, locktag,
hashcode, lockmode);
if (!proclock)
{
LWLockRelease(partitionLock);
LWLockRelease(&proc->backendLock);
return false;
}
GrantLock(proclock->tag.myLock, proclock, lockmode);
FAST_PATH_CLEAR_LOCKMODE(proc, f, lockmode);
}
LWLockRelease(partitionLock);
/* No need to examine remaining slots. */
break;
}
LWLockRelease(&proc->backendLock);
}
return true;
}
/*
* FastPathGetLockEntry
* Return the PROCLOCK for a lock originally taken via the fast-path,
* transferring it to the primary lock table if necessary.
*
* Note: caller takes care of updating the locallock object.
*/
static PROCLOCK *
FastPathGetRelationLockEntry(LOCALLOCK *locallock)
{
LockMethod lockMethodTable = LockMethods[DEFAULT_LOCKMETHOD];
LOCKTAG *locktag = &locallock->tag.lock;
PROCLOCK *proclock = NULL;
LWLock *partitionLock = LockHashPartitionLock(locallock->hashcode);
Oid relid = locktag->locktag_field2;
uint32 f;
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
{
uint32 lockmode;
/* Look for an allocated slot matching the given relid. */
if (relid != MyProc->fpRelId[f] || FAST_PATH_GET_BITS(MyProc, f) == 0)
continue;
/* If we don't have a lock of the given mode, forget it! */
lockmode = locallock->tag.mode;
if (!FAST_PATH_CHECK_LOCKMODE(MyProc, f, lockmode))
break;
/* Find or create lock object. */
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
proclock = SetupLockInTable(lockMethodTable, MyProc, locktag,
locallock->hashcode, lockmode);
if (!proclock)
{
LWLockRelease(partitionLock);
LWLockRelease(&MyProc->backendLock);
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
}
GrantLock(proclock->tag.myLock, proclock, lockmode);
FAST_PATH_CLEAR_LOCKMODE(MyProc, f, lockmode);
LWLockRelease(partitionLock);
/* No need to examine remaining slots. */
break;
}
LWLockRelease(&MyProc->backendLock);
/* Lock may have already been transferred by some other backend. */
if (proclock == NULL)
{
LOCK *lock;
PROCLOCKTAG proclocktag;
uint32 proclock_hashcode;
LWLockAcquire(partitionLock, LW_SHARED);
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(void *) locktag,
locallock->hashcode,
HASH_FIND,
NULL);
if (!lock)
elog(ERROR, "failed to re-find shared lock object");
proclocktag.myLock = lock;
proclocktag.myProc = MyProc;
proclock_hashcode = ProcLockHashCode(&proclocktag, locallock->hashcode);
proclock = (PROCLOCK *)
hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &proclocktag,
proclock_hashcode,
HASH_FIND,
NULL);
if (!proclock)
elog(ERROR, "failed to re-find shared proclock object");
LWLockRelease(partitionLock);
}
return proclock;
}
/*
* GetLockConflicts
* Get an array of VirtualTransactionIds of xacts currently holding locks
* that would conflict with the specified lock/lockmode.
* xacts merely awaiting such a lock are NOT reported.
*
* The result array is palloc'd and is terminated with an invalid VXID.
*
* Of course, the result could be out of date by the time it's returned,
* so use of this function has to be thought about carefully.
*
* Note we never include the current xact's vxid in the result array,
* since an xact never blocks itself. Also, prepared transactions are
* ignored, which is a bit more debatable but is appropriate for current
* uses of the result.
*/
VirtualTransactionId *
GetLockConflicts(const LOCKTAG *locktag, LOCKMODE lockmode)
{
static VirtualTransactionId *vxids;
LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid;
LockMethod lockMethodTable;
LOCK *lock;
LOCKMASK conflictMask;
SHM_QUEUE *procLocks;
PROCLOCK *proclock;
uint32 hashcode;
LWLock *partitionLock;
int count = 0;
int fast_count = 0;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
if (lockmode <= 0 || lockmode > lockMethodTable->numLockModes)
elog(ERROR, "unrecognized lock mode: %d", lockmode);
/*
* Allocate memory to store results, and fill with InvalidVXID. We only
* need enough space for MaxBackends + a terminator, since prepared xacts
* don't count. InHotStandby allocate once in TopMemoryContext.
*/
if (InHotStandby)
{
if (vxids == NULL)
vxids = (VirtualTransactionId *)
MemoryContextAlloc(TopMemoryContext,
sizeof(VirtualTransactionId) * (MaxBackends + 1));
}
else
vxids = (VirtualTransactionId *)
palloc0(sizeof(VirtualTransactionId) * (MaxBackends + 1));
/* Compute hash code and partition lock, and look up conflicting modes. */
hashcode = LockTagHashCode(locktag);
partitionLock = LockHashPartitionLock(hashcode);
conflictMask = lockMethodTable->conflictTab[lockmode];
/*
* Fast path locks might not have been entered in the primary lock table.
* If the lock we're dealing with could conflict with such a lock, we must
* examine each backend's fast-path array for conflicts.
*/
if (ConflictsWithRelationFastPath(locktag, lockmode))
{
int i;
Oid relid = locktag->locktag_field2;
VirtualTransactionId vxid;
/*
* Iterate over relevant PGPROCs. Anything held by a prepared
* transaction will have been transferred to the primary lock table,
* so we need not worry about those. This is all a bit fuzzy, because
* new locks could be taken after we've visited a particular
* partition, but the callers had better be prepared to deal with that
* anyway, since the locks could equally well be taken between the
* time we return the value and the time the caller does something
* with it.
*/
for (i = 0; i < ProcGlobal->allProcCount; i++)
{
PGPROC *proc = &ProcGlobal->allProcs[i];
uint32 f;
/* A backend never blocks itself */
if (proc == MyProc)
continue;
LWLockAcquire(&proc->backendLock, LW_SHARED);
/*
* If the target backend isn't referencing the same database as
* the lock, then we needn't examine the individual relation IDs
* at all; none of them can be relevant.
*
* See FastPathTransferLocks() for discussion of why we do this
* test after acquiring the lock.
*/
if (proc->databaseId != locktag->locktag_field1)
{
LWLockRelease(&proc->backendLock);
continue;
}
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; f++)
{
uint32 lockmask;
/* Look for an allocated slot matching the given relid. */
if (relid != proc->fpRelId[f])
continue;
lockmask = FAST_PATH_GET_BITS(proc, f);
if (!lockmask)
continue;
lockmask <<= FAST_PATH_LOCKNUMBER_OFFSET;
/*
* There can only be one entry per relation, so if we found it
* and it doesn't conflict, we can skip the rest of the slots.
*/
if ((lockmask & conflictMask) == 0)
break;
/* Conflict! */
GET_VXID_FROM_PGPROC(vxid, *proc);
/*
* If we see an invalid VXID, then either the xact has already
* committed (or aborted), or it's a prepared xact. In either
* case we may ignore it.
*/
if (VirtualTransactionIdIsValid(vxid))
vxids[count++] = vxid;
/* No need to examine remaining slots. */
break;
}
LWLockRelease(&proc->backendLock);
}
}
/* Remember how many fast-path conflicts we found. */
fast_count = count;
/*
* Look up the lock object matching the tag.
*/
LWLockAcquire(partitionLock, LW_SHARED);
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(const void *) locktag,
hashcode,
HASH_FIND,
NULL);
if (!lock)
{
/*
* If the lock object doesn't exist, there is nothing holding a lock
* on this lockable object.
*/
LWLockRelease(partitionLock);
vxids[count].backendId = InvalidBackendId;
vxids[count].localTransactionId = InvalidLocalTransactionId;
return vxids;
}
/*
* Examine each existing holder (or awaiter) of the lock.
*/
procLocks = &(lock->procLocks);
proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, lockLink));
while (proclock)
{
if (conflictMask & proclock->holdMask)
{
PGPROC *proc = proclock->tag.myProc;
/* A backend never blocks itself */
if (proc != MyProc)
{
VirtualTransactionId vxid;
GET_VXID_FROM_PGPROC(vxid, *proc);
/*
* If we see an invalid VXID, then either the xact has already
* committed (or aborted), or it's a prepared xact. In either
* case we may ignore it.
*/
if (VirtualTransactionIdIsValid(vxid))
{
int i;
/* Avoid duplicate entries. */
for (i = 0; i < fast_count; ++i)
if (VirtualTransactionIdEquals(vxids[i], vxid))
break;
if (i >= fast_count)
vxids[count++] = vxid;
}
}
}
proclock = (PROCLOCK *) SHMQueueNext(procLocks, &proclock->lockLink,
offsetof(PROCLOCK, lockLink));
}
LWLockRelease(partitionLock);
if (count > MaxBackends) /* should never happen */
elog(PANIC, "too many conflicting locks found");
vxids[count].backendId = InvalidBackendId;
vxids[count].localTransactionId = InvalidLocalTransactionId;
return vxids;
}
/*
* Find a lock in the shared lock table and release it. It is the caller's
* responsibility to verify that this is a sane thing to do. (For example, it
* would be bad to release a lock here if there might still be a LOCALLOCK
* object with pointers to it.)
*
* We currently use this in two situations: first, to release locks held by
* prepared transactions on commit (see lock_twophase_postcommit); and second,
* to release locks taken via the fast-path, transferred to the main hash
* table, and then released (see LockReleaseAll).
*/
static void
LockRefindAndRelease(LockMethod lockMethodTable, PGPROC *proc,
LOCKTAG *locktag, LOCKMODE lockmode,
bool decrement_strong_lock_count)
{
LOCK *lock;
PROCLOCK *proclock;
PROCLOCKTAG proclocktag;
uint32 hashcode;
uint32 proclock_hashcode;
LWLock *partitionLock;
bool wakeupNeeded;
hashcode = LockTagHashCode(locktag);
partitionLock = LockHashPartitionLock(hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
/*
* Re-find the lock object (it had better be there).
*/
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(void *) locktag,
hashcode,
HASH_FIND,
NULL);
if (!lock)
elog(PANIC, "failed to re-find shared lock object");
/*
* Re-find the proclock object (ditto).
*/
proclocktag.myLock = lock;
proclocktag.myProc = proc;
proclock_hashcode = ProcLockHashCode(&proclocktag, hashcode);
proclock = (PROCLOCK *) hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &proclocktag,
proclock_hashcode,
HASH_FIND,
NULL);
if (!proclock)
elog(PANIC, "failed to re-find shared proclock object");
/*
* Double-check that we are actually holding a lock of the type we want to
* release.
*/
if (!(proclock->holdMask & LOCKBIT_ON(lockmode)))
{
PROCLOCK_PRINT("lock_twophase_postcommit: WRONGTYPE", proclock);
LWLockRelease(partitionLock);
elog(WARNING, "you don't own a lock of type %s",
lockMethodTable->lockModeNames[lockmode]);
return;
}
/*
* Do the releasing. CleanUpLock will waken any now-wakable waiters.
*/
wakeupNeeded = UnGrantLock(lock, lockmode, proclock, lockMethodTable);
CleanUpLock(lock, proclock,
lockMethodTable, hashcode,
wakeupNeeded);
LWLockRelease(partitionLock);
/*
* Decrement strong lock count. This logic is needed only for 2PC.
*/
if (decrement_strong_lock_count
&& ConflictsWithRelationFastPath(locktag, lockmode))
{
uint32 fasthashcode = FastPathStrongLockHashPartition(hashcode);
SpinLockAcquire(&FastPathStrongRelationLocks->mutex);
Assert(FastPathStrongRelationLocks->count[fasthashcode] > 0);
FastPathStrongRelationLocks->count[fasthashcode]--;
SpinLockRelease(&FastPathStrongRelationLocks->mutex);
}
}
/*
* AtPrepare_Locks
* Do the preparatory work for a PREPARE: make 2PC state file records
* for all locks currently held.
*
* Session-level locks are ignored, as are VXID locks.
*
* There are some special cases that we error out on: we can't be holding any
* locks at both session and transaction level (since we must either keep or
* give away the PROCLOCK object), and we can't be holding any locks on
* temporary objects (since that would mess up the current backend if it tries
* to exit before the prepared xact is committed).
*/
void
AtPrepare_Locks(void)
{
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
/*
* For the most part, we don't need to touch shared memory for this ---
* all the necessary state information is in the locallock table.
* Fast-path locks are an exception, however: we move any such locks to
* the main table before allowing PREPARE TRANSACTION to succeed.
*/
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
{
TwoPhaseLockRecord record;
LOCALLOCKOWNER *lockOwners = locallock->lockOwners;
bool haveSessionLock;
bool haveXactLock;
int i;
/*
* Ignore VXID locks. We don't want those to be held by prepared
* transactions, since they aren't meaningful after a restart.
*/
if (locallock->tag.lock.locktag_type == LOCKTAG_VIRTUALTRANSACTION)
continue;
/* Ignore it if we don't actually hold the lock */
if (locallock->nLocks <= 0)
continue;
/* Scan to see whether we hold it at session or transaction level */
haveSessionLock = haveXactLock = false;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (lockOwners[i].owner == NULL)
haveSessionLock = true;
else
haveXactLock = true;
}
/* Ignore it if we have only session lock */
if (!haveXactLock)
continue;
/*
* If we have both session- and transaction-level locks, fail. This
* should never happen with regular locks, since we only take those at
* session level in some special operations like VACUUM. It's
* possible to hit this with advisory locks, though.
*
* It would be nice if we could keep the session hold and give away
* the transactional hold to the prepared xact. However, that would
* require two PROCLOCK objects, and we cannot be sure that another
* PROCLOCK will be available when it comes time for PostPrepare_Locks
* to do the deed. So for now, we error out while we can still do so
* safely.
*/
if (haveSessionLock)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot PREPARE while holding both session-level and transaction-level locks on the same object")));
/*
* If the local lock was taken via the fast-path, we need to move it
* to the primary lock table, or just get a pointer to the existing
* primary lock table entry if by chance it's already been
* transferred.
*/
if (locallock->proclock == NULL)
{
locallock->proclock = FastPathGetRelationLockEntry(locallock);
locallock->lock = locallock->proclock->tag.myLock;
}
/*
* Arrange to not release any strong lock count held by this lock
* entry. We must retain the count until the prepared transaction is
* committed or rolled back.
*/
locallock->holdsStrongLockCount = false;
/*
* Create a 2PC record.
*/
memcpy(&(record.locktag), &(locallock->tag.lock), sizeof(LOCKTAG));
record.lockmode = locallock->tag.mode;
RegisterTwoPhaseRecord(TWOPHASE_RM_LOCK_ID, 0,
&record, sizeof(TwoPhaseLockRecord));
}
}
/*
* PostPrepare_Locks
* Clean up after successful PREPARE
*
* Here, we want to transfer ownership of our locks to a dummy PGPROC
* that's now associated with the prepared transaction, and we want to
* clean out the corresponding entries in the LOCALLOCK table.
*
* Note: by removing the LOCALLOCK entries, we are leaving dangling
* pointers in the transaction's resource owner. This is OK at the
* moment since resowner.c doesn't try to free locks retail at a toplevel
* transaction commit or abort. We could alternatively zero out nLocks
* and leave the LOCALLOCK entries to be garbage-collected by LockReleaseAll,
* but that probably costs more cycles.
*/
void
PostPrepare_Locks(TransactionId xid)
{
PGPROC *newproc = TwoPhaseGetDummyProc(xid);
HASH_SEQ_STATUS status;
LOCALLOCK *locallock;
LOCK *lock;
PROCLOCK *proclock;
PROCLOCKTAG proclocktag;
int partition;
/* Can't prepare a lock group follower. */
Assert(MyProc->lockGroupLeader == NULL ||
MyProc->lockGroupLeader == MyProc);
/* This is a critical section: any error means big trouble */
START_CRIT_SECTION();
/*
* First we run through the locallock table and get rid of unwanted
* entries, then we scan the process's proclocks and transfer them to the
* target proc.
*
* We do this separately because we may have multiple locallock entries
* pointing to the same proclock, and we daren't end up with any dangling
* pointers.
*/
hash_seq_init(&status, LockMethodLocalHash);
while ((locallock = (LOCALLOCK *) hash_seq_search(&status)) != NULL)
{
LOCALLOCKOWNER *lockOwners = locallock->lockOwners;
bool haveSessionLock;
bool haveXactLock;
int i;
if (locallock->proclock == NULL || locallock->lock == NULL)
{
/*
* We must've run out of shared memory while trying to set up this
* lock. Just forget the local entry.
*/
Assert(locallock->nLocks == 0);
RemoveLocalLock(locallock);
continue;
}
/* Ignore VXID locks */
if (locallock->tag.lock.locktag_type == LOCKTAG_VIRTUALTRANSACTION)
continue;
/* Scan to see whether we hold it at session or transaction level */
haveSessionLock = haveXactLock = false;
for (i = locallock->numLockOwners - 1; i >= 0; i--)
{
if (lockOwners[i].owner == NULL)
haveSessionLock = true;
else
haveXactLock = true;
}
/* Ignore it if we have only session lock */
if (!haveXactLock)
continue;
/* This can't happen, because we already checked it */
if (haveSessionLock)
ereport(PANIC,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot PREPARE while holding both session-level and transaction-level locks on the same object")));
/* Mark the proclock to show we need to release this lockmode */
if (locallock->nLocks > 0)
locallock->proclock->releaseMask |= LOCKBIT_ON(locallock->tag.mode);
/* And remove the locallock hashtable entry */
RemoveLocalLock(locallock);
}
/*
* Now, scan each lock partition separately.
*/
for (partition = 0; partition < NUM_LOCK_PARTITIONS; partition++)
{
LWLock *partitionLock;
SHM_QUEUE *procLocks = &(MyProc->myProcLocks[partition]);
PROCLOCK *nextplock;
partitionLock = LockHashPartitionLockByIndex(partition);
/*
* If the proclock list for this partition is empty, we can skip
* acquiring the partition lock. This optimization is safer than the
* situation in LockReleaseAll, because we got rid of any fast-path
* locks during AtPrepare_Locks, so there cannot be any case where
* another backend is adding something to our lists now. For safety,
* though, we code this the same way as in LockReleaseAll.
*/
if (SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, procLink)) == NULL)
continue; /* needn't examine this partition */
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
for (proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, procLink));
proclock;
proclock = nextplock)
{
/* Get link first, since we may unlink/relink this proclock */
nextplock = (PROCLOCK *)
SHMQueueNext(procLocks, &proclock->procLink,
offsetof(PROCLOCK, procLink));
Assert(proclock->tag.myProc == MyProc);
lock = proclock->tag.myLock;
/* Ignore VXID locks */
if (lock->tag.locktag_type == LOCKTAG_VIRTUALTRANSACTION)
continue;
PROCLOCK_PRINT("PostPrepare_Locks", proclock);
LOCK_PRINT("PostPrepare_Locks", lock, 0);
Assert(lock->nRequested >= 0);
Assert(lock->nGranted >= 0);
Assert(lock->nGranted <= lock->nRequested);
Assert((proclock->holdMask & ~lock->grantMask) == 0);
/* Ignore it if nothing to release (must be a session lock) */
if (proclock->releaseMask == 0)
continue;
/* Else we should be releasing all locks */
if (proclock->releaseMask != proclock->holdMask)
elog(PANIC, "we seem to have dropped a bit somewhere");
/*
* We cannot simply modify proclock->tag.myProc to reassign
* ownership of the lock, because that's part of the hash key and
* the proclock would then be in the wrong hash chain. Instead
* use hash_update_hash_key. (We used to create a new hash entry,
* but that risks out-of-memory failure if other processes are
* busy making proclocks too.) We must unlink the proclock from
* our procLink chain and put it into the new proc's chain, too.
*
* Note: the updated proclock hash key will still belong to the
* same hash partition, cf proclock_hash(). So the partition lock
* we already hold is sufficient for this.
*/
SHMQueueDelete(&proclock->procLink);
/*
* Create the new hash key for the proclock.
*/
proclocktag.myLock = lock;
proclocktag.myProc = newproc;
/*
* Update groupLeader pointer to point to the new proc. (We'd
* better not be a member of somebody else's lock group!)
*/
Assert(proclock->groupLeader == proclock->tag.myProc);
proclock->groupLeader = newproc;
/*
* Update the proclock. We should not find any existing entry for
* the same hash key, since there can be only one entry for any
* given lock with my own proc.
*/
if (!hash_update_hash_key(LockMethodProcLockHash,
(void *) proclock,
(void *) &proclocktag))
elog(PANIC, "duplicate entry found while reassigning a prepared transaction's locks");
/* Re-link into the new proc's proclock list */
SHMQueueInsertBefore(&(newproc->myProcLocks[partition]),
&proclock->procLink);
PROCLOCK_PRINT("PostPrepare_Locks: updated", proclock);
} /* loop over PROCLOCKs within this partition */
LWLockRelease(partitionLock);
} /* loop over partitions */
END_CRIT_SECTION();
}
/*
* Estimate shared-memory space used for lock tables
*/
Size
LockShmemSize(void)
{
Size size = 0;
long max_table_size;
/* lock hash table */
max_table_size = NLOCKENTS();
size = add_size(size, hash_estimate_size(max_table_size, sizeof(LOCK)));
/* proclock hash table */
max_table_size *= 2;
size = add_size(size, hash_estimate_size(max_table_size, sizeof(PROCLOCK)));
/*
* Since NLOCKENTS is only an estimate, add 10% safety margin.
*/
size = add_size(size, size / 10);
return size;
}
/*
* GetLockStatusData - Return a summary of the lock manager's internal
* status, for use in a user-level reporting function.
*
* The return data consists of an array of LockInstanceData objects,
* which are a lightly abstracted version of the PROCLOCK data structures,
* i.e. there is one entry for each unique lock and interested PGPROC.
* It is the caller's responsibility to match up related items (such as
* references to the same lockable object or PGPROC) if wanted.
*
* The design goal is to hold the LWLocks for as short a time as possible;
* thus, this function simply makes a copy of the necessary data and releases
* the locks, allowing the caller to contemplate and format the data for as
* long as it pleases.
*/
LockData *
GetLockStatusData(void)
{
LockData *data;
PROCLOCK *proclock;
HASH_SEQ_STATUS seqstat;
int els;
int el;
int i;
data = (LockData *) palloc(sizeof(LockData));
/* Guess how much space we'll need. */
els = MaxBackends;
el = 0;
data->locks = (LockInstanceData *) palloc(sizeof(LockInstanceData) * els);
/*
* First, we iterate through the per-backend fast-path arrays, locking
* them one at a time. This might produce an inconsistent picture of the
* system state, but taking all of those LWLocks at the same time seems
* impractical (in particular, note MAX_SIMUL_LWLOCKS). It shouldn't
* matter too much, because none of these locks can be involved in lock
* conflicts anyway - anything that might must be present in the main lock
* table. (For the same reason, we don't sweat about making leaderPid
* completely valid. We cannot safely dereference another backend's
* lockGroupLeader field without holding all lock partition locks, and
* it's not worth that.)
*/
for (i = 0; i < ProcGlobal->allProcCount; ++i)
{
PGPROC *proc = &ProcGlobal->allProcs[i];
uint32 f;
LWLockAcquire(&proc->backendLock, LW_SHARED);
for (f = 0; f < FP_LOCK_SLOTS_PER_BACKEND; ++f)
{
LockInstanceData *instance;
uint32 lockbits = FAST_PATH_GET_BITS(proc, f);
/* Skip unallocated slots. */
if (!lockbits)
continue;
if (el >= els)
{
els += MaxBackends;
data->locks = (LockInstanceData *)
repalloc(data->locks, sizeof(LockInstanceData) * els);
}
instance = &data->locks[el];
SET_LOCKTAG_RELATION(instance->locktag, proc->databaseId,
proc->fpRelId[f]);
instance->holdMask = lockbits << FAST_PATH_LOCKNUMBER_OFFSET;
instance->waitLockMode = NoLock;
instance->backend = proc->backendId;
instance->lxid = proc->lxid;
instance->pid = proc->pid;
instance->leaderPid = proc->pid;
instance->fastpath = true;
el++;
}
if (proc->fpVXIDLock)
{
VirtualTransactionId vxid;
LockInstanceData *instance;
if (el >= els)
{
els += MaxBackends;
data->locks = (LockInstanceData *)
repalloc(data->locks, sizeof(LockInstanceData) * els);
}
vxid.backendId = proc->backendId;
vxid.localTransactionId = proc->fpLocalTransactionId;
instance = &data->locks[el];
SET_LOCKTAG_VIRTUALTRANSACTION(instance->locktag, vxid);
instance->holdMask = LOCKBIT_ON(ExclusiveLock);
instance->waitLockMode = NoLock;
instance->backend = proc->backendId;
instance->lxid = proc->lxid;
instance->pid = proc->pid;
instance->leaderPid = proc->pid;
instance->fastpath = true;
el++;
}
LWLockRelease(&proc->backendLock);
}
/*
* Next, acquire lock on the entire shared lock data structure. We do
* this so that, at least for locks in the primary lock table, the state
* will be self-consistent.
*
* Since this is a read-only operation, we take shared instead of
* exclusive lock. There's not a whole lot of point to this, because all
* the normal operations require exclusive lock, but it doesn't hurt
* anything either. It will at least allow two backends to do
* GetLockStatusData in parallel.
*
* Must grab LWLocks in partition-number order to avoid LWLock deadlock.
*/
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
LWLockAcquire(LockHashPartitionLockByIndex(i), LW_SHARED);
/* Now we can safely count the number of proclocks */
data->nelements = el + hash_get_num_entries(LockMethodProcLockHash);
if (data->nelements > els)
{
els = data->nelements;
data->locks = (LockInstanceData *)
repalloc(data->locks, sizeof(LockInstanceData) * els);
}
/* Now scan the tables to copy the data */
hash_seq_init(&seqstat, LockMethodProcLockHash);
while ((proclock = (PROCLOCK *) hash_seq_search(&seqstat)))
{
PGPROC *proc = proclock->tag.myProc;
LOCK *lock = proclock->tag.myLock;
LockInstanceData *instance = &data->locks[el];
memcpy(&instance->locktag, &lock->tag, sizeof(LOCKTAG));
instance->holdMask = proclock->holdMask;
if (proc->waitLock == proclock->tag.myLock)
instance->waitLockMode = proc->waitLockMode;
else
instance->waitLockMode = NoLock;
instance->backend = proc->backendId;
instance->lxid = proc->lxid;
instance->pid = proc->pid;
instance->leaderPid = proclock->groupLeader->pid;
instance->fastpath = false;
el++;
}
/*
* 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.
*/
for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
LWLockRelease(LockHashPartitionLockByIndex(i));
Assert(el == data->nelements);
return data;
}
/*
* GetBlockerStatusData - Return a summary of the lock manager's state
* concerning locks that are blocking the specified PID or any member of
* the PID's lock group, for use in a user-level reporting function.
*
* For each PID within the lock group that is awaiting some heavyweight lock,
* the return data includes an array of LockInstanceData objects, which are
* the same data structure used by GetLockStatusData; but unlike that function,
* this one reports only the PROCLOCKs associated with the lock that that PID
* is blocked on. (Hence, all the locktags should be the same for any one
* blocked PID.) In addition, we return an array of the PIDs of those backends
* that are ahead of the blocked PID in the lock's wait queue. These can be
* compared with the PIDs in the LockInstanceData objects to determine which
* waiters are ahead of or behind the blocked PID in the queue.
*
* If blocked_pid isn't a valid backend PID or nothing in its lock group is
* waiting on any heavyweight lock, return empty arrays.
*
* The design goal is to hold the LWLocks for as short a time as possible;
* thus, this function simply makes a copy of the necessary data and releases
* the locks, allowing the caller to contemplate and format the data for as
* long as it pleases.
*/
BlockedProcsData *
GetBlockerStatusData(int blocked_pid)
{
BlockedProcsData *data;
PGPROC *proc;
int i;
data = (BlockedProcsData *) palloc(sizeof(BlockedProcsData));
/*
* Guess how much space we'll need, and preallocate. Most of the time
* this will avoid needing to do repalloc while holding the LWLocks. (We
* assume, but check with an Assert, that MaxBackends is enough entries
* for the procs[] array; the other two could need enlargement, though.)
*/
data->nprocs = data->nlocks = data->npids = 0;
data->maxprocs = data->maxlocks = data->maxpids = MaxBackends;
data->procs = (BlockedProcData *) palloc(sizeof(BlockedProcData) * data->maxprocs);
data->locks = (LockInstanceData *) palloc(sizeof(LockInstanceData) * data->maxlocks);
data->waiter_pids = (int *) palloc(sizeof(int) * data->maxpids);
/*
* In order to search the ProcArray for blocked_pid and assume that that
* entry won't immediately disappear under us, we must hold ProcArrayLock.
* In addition, to examine the lock grouping fields of any other backend,
* we must hold all the hash partition locks. (Only one of those locks is
* actually relevant for any one lock group, but we can't know which one
* ahead of time.) It's fairly annoying to hold all those locks
* throughout this, but it's no worse than GetLockStatusData(), and it
* does have the advantage that we're guaranteed to return a
* self-consistent instantaneous state.
*/
LWLockAcquire(ProcArrayLock, LW_SHARED);
proc = BackendPidGetProcWithLock(blocked_pid);
/* Nothing to do if it's gone */
if (proc != NULL)
{
/*
* Acquire lock on the entire shared lock data structure. See notes
* in GetLockStatusData().
*/
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
LWLockAcquire(LockHashPartitionLockByIndex(i), LW_SHARED);
if (proc->lockGroupLeader == NULL)
{
/* Easy case, proc is not a lock group member */
GetSingleProcBlockerStatusData(proc, data);
}
else
{
/* Examine all procs in proc's lock group */
dlist_iter iter;
dlist_foreach(iter, &proc->lockGroupLeader->lockGroupMembers)
{
PGPROC *memberProc;
memberProc = dlist_container(PGPROC, lockGroupLink, iter.cur);
GetSingleProcBlockerStatusData(memberProc, data);
}
}
/*
* And release locks. See notes in GetLockStatusData().
*/
for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
LWLockRelease(LockHashPartitionLockByIndex(i));
Assert(data->nprocs <= data->maxprocs);
}
LWLockRelease(ProcArrayLock);
return data;
}
/* Accumulate data about one possibly-blocked proc for GetBlockerStatusData */
static void
GetSingleProcBlockerStatusData(PGPROC *blocked_proc, BlockedProcsData *data)
{
LOCK *theLock = blocked_proc->waitLock;
BlockedProcData *bproc;
SHM_QUEUE *procLocks;
PROCLOCK *proclock;
PROC_QUEUE *waitQueue;
PGPROC *proc;
int queue_size;
int i;
/* Nothing to do if this proc is not blocked */
if (theLock == NULL)
return;
/* Set up a procs[] element */
bproc = &data->procs[data->nprocs++];
bproc->pid = blocked_proc->pid;
bproc->first_lock = data->nlocks;
bproc->first_waiter = data->npids;
/*
* We may ignore the proc's fast-path arrays, since nothing in those could
* be related to a contended lock.
*/
/* Collect all PROCLOCKs associated with theLock */
procLocks = &(theLock->procLocks);
proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, lockLink));
while (proclock)
{
PGPROC *proc = proclock->tag.myProc;
LOCK *lock = proclock->tag.myLock;
LockInstanceData *instance;
if (data->nlocks >= data->maxlocks)
{
data->maxlocks += MaxBackends;
data->locks = (LockInstanceData *)
repalloc(data->locks, sizeof(LockInstanceData) * data->maxlocks);
}
instance = &data->locks[data->nlocks];
memcpy(&instance->locktag, &lock->tag, sizeof(LOCKTAG));
instance->holdMask = proclock->holdMask;
if (proc->waitLock == lock)
instance->waitLockMode = proc->waitLockMode;
else
instance->waitLockMode = NoLock;
instance->backend = proc->backendId;
instance->lxid = proc->lxid;
instance->pid = proc->pid;
instance->leaderPid = proclock->groupLeader->pid;
instance->fastpath = false;
data->nlocks++;
proclock = (PROCLOCK *) SHMQueueNext(procLocks, &proclock->lockLink,
offsetof(PROCLOCK, lockLink));
}
/* Enlarge waiter_pids[] if it's too small to hold all wait queue PIDs */
waitQueue = &(theLock->waitProcs);
queue_size = waitQueue->size;
if (queue_size > data->maxpids - data->npids)
{
data->maxpids = Max(data->maxpids + MaxBackends,
data->npids + queue_size);
data->waiter_pids = (int *) repalloc(data->waiter_pids,
sizeof(int) * data->maxpids);
}
/* Collect PIDs from the lock's wait queue, stopping at blocked_proc */
proc = (PGPROC *) waitQueue->links.next;
for (i = 0; i < queue_size; i++)
{
if (proc == blocked_proc)
break;
data->waiter_pids[data->npids++] = proc->pid;
proc = (PGPROC *) proc->links.next;
}
bproc->num_locks = data->nlocks - bproc->first_lock;
bproc->num_waiters = data->npids - bproc->first_waiter;
}
/*
* Returns a list of currently held AccessExclusiveLocks, for use by
* LogStandbySnapshot(). The result is a palloc'd array,
* with the number of elements returned into *nlocks.
*
* XXX This currently takes a lock on all partitions of the lock table,
* but it's possible to do better. By reference counting locks and storing
* the value in the ProcArray entry for each backend we could tell if any
* locks need recording without having to acquire the partition locks and
* scan the lock table. Whether that's worth the additional overhead
* is pretty dubious though.
*/
xl_standby_lock *
GetRunningTransactionLocks(int *nlocks)
{
xl_standby_lock *accessExclusiveLocks;
PROCLOCK *proclock;
HASH_SEQ_STATUS seqstat;
int i;
int index;
int els;
/*
* Acquire lock on the entire shared lock data structure.
*
* Must grab LWLocks in partition-number order to avoid LWLock deadlock.
*/
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
LWLockAcquire(LockHashPartitionLockByIndex(i), LW_SHARED);
/* Now we can safely count the number of proclocks */
els = hash_get_num_entries(LockMethodProcLockHash);
/*
* Allocating enough space for all locks in the lock table is overkill,
* but it's more convenient and faster than having to enlarge the array.
*/
accessExclusiveLocks = palloc(els * sizeof(xl_standby_lock));
/* Now scan the tables to copy the data */
hash_seq_init(&seqstat, LockMethodProcLockHash);
/*
* If lock is a currently granted AccessExclusiveLock then it will have
* just one proclock holder, so locks are never accessed twice in this
* particular case. Don't copy this code for use elsewhere because in the
* general case this will give you duplicate locks when looking at
* non-exclusive lock types.
*/
index = 0;
while ((proclock = (PROCLOCK *) hash_seq_search(&seqstat)))
{
/* make sure this definition matches the one used in LockAcquire */
if ((proclock->holdMask & LOCKBIT_ON(AccessExclusiveLock)) &&
proclock->tag.myLock->tag.locktag_type == LOCKTAG_RELATION)
{
PGPROC *proc = proclock->tag.myProc;
PGXACT *pgxact = &ProcGlobal->allPgXact[proc->pgprocno];
LOCK *lock = proclock->tag.myLock;
TransactionId xid = pgxact->xid;
/*
* Don't record locks for transactions if we know they have
* already issued their WAL record for commit but not yet released
* lock. It is still possible that we see locks held by already
* complete transactions, if they haven't yet zeroed their xids.
*/
if (!TransactionIdIsValid(xid))
continue;
accessExclusiveLocks[index].xid = xid;
accessExclusiveLocks[index].dbOid = lock->tag.locktag_field1;
accessExclusiveLocks[index].relOid = lock->tag.locktag_field2;
index++;
}
}
Assert(index <= els);
/*
* 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.
*/
for (i = NUM_LOCK_PARTITIONS; --i >= 0;)
LWLockRelease(LockHashPartitionLockByIndex(i));
*nlocks = index;
return accessExclusiveLocks;
}
/* Provide the textual name of any lock mode */
const char *
GetLockmodeName(LOCKMETHODID lockmethodid, LOCKMODE mode)
{
Assert(lockmethodid > 0 && lockmethodid < lengthof(LockMethods));
Assert(mode > 0 && mode <= LockMethods[lockmethodid]->numLockModes);
return LockMethods[lockmethodid]->lockModeNames[mode];
}
#ifdef LOCK_DEBUG
/*
* Dump all locks in the given proc's myProcLocks lists.
*
* Caller is responsible for having acquired appropriate LWLocks.
*/
void
DumpLocks(PGPROC *proc)
{
SHM_QUEUE *procLocks;
PROCLOCK *proclock;
LOCK *lock;
int i;
if (proc == NULL)
return;
if (proc->waitLock)
LOCK_PRINT("DumpLocks: waiting on", proc->waitLock, 0);
for (i = 0; i < NUM_LOCK_PARTITIONS; i++)
{
procLocks = &(proc->myProcLocks[i]);
proclock = (PROCLOCK *) SHMQueueNext(procLocks, procLocks,
offsetof(PROCLOCK, procLink));
while (proclock)
{
Assert(proclock->tag.myProc == proc);
lock = proclock->tag.myLock;
PROCLOCK_PRINT("DumpLocks", proclock);
LOCK_PRINT("DumpLocks", lock, 0);
proclock = (PROCLOCK *)
SHMQueueNext(procLocks, &proclock->procLink,
offsetof(PROCLOCK, procLink));
}
}
}
/*
* Dump all lmgr locks.
*
* Caller is responsible for having acquired appropriate LWLocks.
*/
void
DumpAllLocks(void)
{
PGPROC *proc;
PROCLOCK *proclock;
LOCK *lock;
HASH_SEQ_STATUS status;
proc = MyProc;
if (proc && proc->waitLock)
LOCK_PRINT("DumpAllLocks: waiting on", proc->waitLock, 0);
hash_seq_init(&status, LockMethodProcLockHash);
while ((proclock = (PROCLOCK *) hash_seq_search(&status)) != NULL)
{
PROCLOCK_PRINT("DumpAllLocks", proclock);
lock = proclock->tag.myLock;
if (lock)
LOCK_PRINT("DumpAllLocks", lock, 0);
else
elog(LOG, "DumpAllLocks: proclock->tag.myLock = NULL");
}
}
#endif /* LOCK_DEBUG */
/*
* LOCK 2PC resource manager's routines
*/
/*
* Re-acquire a lock belonging to a transaction that was prepared.
*
* Because this function is run at db startup, re-acquiring the locks should
* never conflict with running transactions because there are none. We
* assume that the lock state represented by the stored 2PC files is legal.
*
* When switching from Hot Standby mode to normal operation, the locks will
* be already held by the startup process. The locks are acquired for the new
* procs without checking for conflicts, so we don't get a conflict between the
* startup process and the dummy procs, even though we will momentarily have
* a situation where two procs are holding the same AccessExclusiveLock,
* which isn't normally possible because the conflict. If we're in standby
* mode, but a recovery snapshot hasn't been established yet, it's possible
* that some but not all of the locks are already held by the startup process.
*
* This approach is simple, but also a bit dangerous, because if there isn't
* enough shared memory to acquire the locks, an error will be thrown, which
* is promoted to FATAL and recovery will abort, bringing down postmaster.
* A safer approach would be to transfer the locks like we do in
* AtPrepare_Locks, but then again, in hot standby mode it's possible for
* read-only backends to use up all the shared lock memory anyway, so that
* replaying the WAL record that needs to acquire a lock will throw an error
* and PANIC anyway.
*/
void
lock_twophase_recover(TransactionId xid, uint16 info,
void *recdata, uint32 len)
{
TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata;
PGPROC *proc = TwoPhaseGetDummyProc(xid);
LOCKTAG *locktag;
LOCKMODE lockmode;
LOCKMETHODID lockmethodid;
LOCK *lock;
PROCLOCK *proclock;
PROCLOCKTAG proclocktag;
bool found;
uint32 hashcode;
uint32 proclock_hashcode;
int partition;
LWLock *partitionLock;
LockMethod lockMethodTable;
Assert(len == sizeof(TwoPhaseLockRecord));
locktag = &rec->locktag;
lockmode = rec->lockmode;
lockmethodid = locktag->locktag_lockmethodid;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
hashcode = LockTagHashCode(locktag);
partition = LockHashPartition(hashcode);
partitionLock = LockHashPartitionLock(hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
/*
* Find or create a lock with this tag.
*/
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(void *) locktag,
hashcode,
HASH_ENTER_NULL,
&found);
if (!lock)
{
LWLockRelease(partitionLock);
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
}
/*
* if it's a new lock object, initialize it
*/
if (!found)
{
lock->grantMask = 0;
lock->waitMask = 0;
SHMQueueInit(&(lock->procLocks));
ProcQueueInit(&(lock->waitProcs));
lock->nRequested = 0;
lock->nGranted = 0;
MemSet(lock->requested, 0, sizeof(int) * MAX_LOCKMODES);
MemSet(lock->granted, 0, sizeof(int) * MAX_LOCKMODES);
LOCK_PRINT("lock_twophase_recover: new", lock, lockmode);
}
else
{
LOCK_PRINT("lock_twophase_recover: found", lock, lockmode);
Assert((lock->nRequested >= 0) && (lock->requested[lockmode] >= 0));
Assert((lock->nGranted >= 0) && (lock->granted[lockmode] >= 0));
Assert(lock->nGranted <= lock->nRequested);
}
/*
* Create the hash key for the proclock table.
*/
proclocktag.myLock = lock;
proclocktag.myProc = proc;
proclock_hashcode = ProcLockHashCode(&proclocktag, hashcode);
/*
* Find or create a proclock entry with this tag
*/
proclock = (PROCLOCK *) hash_search_with_hash_value(LockMethodProcLockHash,
(void *) &proclocktag,
proclock_hashcode,
HASH_ENTER_NULL,
&found);
if (!proclock)
{
/* Oops, not enough shmem for the proclock */
if (lock->nRequested == 0)
{
/*
* There are no other requestors of this lock, so garbage-collect
* the lock object. We *must* do this to avoid a permanent leak
* of shared memory, because there won't be anything to cause
* anyone to release the lock object later.
*/
Assert(SHMQueueEmpty(&(lock->procLocks)));
if (!hash_search_with_hash_value(LockMethodLockHash,
(void *) &(lock->tag),
hashcode,
HASH_REMOVE,
NULL))
elog(PANIC, "lock table corrupted");
}
LWLockRelease(partitionLock);
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
}
/*
* If new, initialize the new entry
*/
if (!found)
{
Assert(proc->lockGroupLeader == NULL);
proclock->groupLeader = proc;
proclock->holdMask = 0;
proclock->releaseMask = 0;
/* Add proclock to appropriate lists */
SHMQueueInsertBefore(&lock->procLocks, &proclock->lockLink);
SHMQueueInsertBefore(&(proc->myProcLocks[partition]),
&proclock->procLink);
PROCLOCK_PRINT("lock_twophase_recover: new", proclock);
}
else
{
PROCLOCK_PRINT("lock_twophase_recover: found", proclock);
Assert((proclock->holdMask & ~lock->grantMask) == 0);
}
/*
* lock->nRequested and lock->requested[] count the total number of
* requests, whether granted or waiting, so increment those immediately.
*/
lock->nRequested++;
lock->requested[lockmode]++;
Assert((lock->nRequested > 0) && (lock->requested[lockmode] > 0));
/*
* We shouldn't already hold the desired lock.
*/
if (proclock->holdMask & LOCKBIT_ON(lockmode))
elog(ERROR, "lock %s on object %u/%u/%u is already held",
lockMethodTable->lockModeNames[lockmode],
lock->tag.locktag_field1, lock->tag.locktag_field2,
lock->tag.locktag_field3);
/*
* We ignore any possible conflicts and just grant ourselves the lock. Not
* only because we don't bother, but also to avoid deadlocks when
* switching from standby to normal mode. See function comment.
*/
GrantLock(lock, proclock, lockmode);
/*
* Bump strong lock count, to make sure any fast-path lock requests won't
* be granted without consulting the primary lock table.
*/
if (ConflictsWithRelationFastPath(&lock->tag, lockmode))
{
uint32 fasthashcode = FastPathStrongLockHashPartition(hashcode);
SpinLockAcquire(&FastPathStrongRelationLocks->mutex);
FastPathStrongRelationLocks->count[fasthashcode]++;
SpinLockRelease(&FastPathStrongRelationLocks->mutex);
}
LWLockRelease(partitionLock);
}
/*
* Re-acquire a lock belonging to a transaction that was prepared, when
* starting up into hot standby mode.
*/
void
lock_twophase_standby_recover(TransactionId xid, uint16 info,
void *recdata, uint32 len)
{
TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata;
LOCKTAG *locktag;
LOCKMODE lockmode;
LOCKMETHODID lockmethodid;
Assert(len == sizeof(TwoPhaseLockRecord));
locktag = &rec->locktag;
lockmode = rec->lockmode;
lockmethodid = locktag->locktag_lockmethodid;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
if (lockmode == AccessExclusiveLock &&
locktag->locktag_type == LOCKTAG_RELATION)
{
StandbyAcquireAccessExclusiveLock(xid,
locktag->locktag_field1 /* dboid */ ,
locktag->locktag_field2 /* reloid */ );
}
}
/*
* 2PC processing routine for COMMIT PREPARED case.
*
* Find and release the lock indicated by the 2PC record.
*/
void
lock_twophase_postcommit(TransactionId xid, uint16 info,
void *recdata, uint32 len)
{
TwoPhaseLockRecord *rec = (TwoPhaseLockRecord *) recdata;
PGPROC *proc = TwoPhaseGetDummyProc(xid);
LOCKTAG *locktag;
LOCKMETHODID lockmethodid;
LockMethod lockMethodTable;
Assert(len == sizeof(TwoPhaseLockRecord));
locktag = &rec->locktag;
lockmethodid = locktag->locktag_lockmethodid;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
lockMethodTable = LockMethods[lockmethodid];
LockRefindAndRelease(lockMethodTable, proc, locktag, rec->lockmode, true);
}
/*
* 2PC processing routine for ROLLBACK PREPARED case.
*
* This is actually just the same as the COMMIT case.
*/
void
lock_twophase_postabort(TransactionId xid, uint16 info,
void *recdata, uint32 len)
{
lock_twophase_postcommit(xid, info, recdata, len);
}
/*
* VirtualXactLockTableInsert
*
* Take vxid lock via the fast-path. There can't be any pre-existing
* lockers, as we haven't advertised this vxid via the ProcArray yet.
*
* Since MyProc->fpLocalTransactionId will normally contain the same data
* as MyProc->lxid, you might wonder if we really need both. The
* difference is that MyProc->lxid is set and cleared unlocked, and
* examined by procarray.c, while fpLocalTransactionId is protected by
* backendLock and is used only by the locking subsystem. Doing it this
* way makes it easier to verify that there are no funny race conditions.
*
* We don't bother recording this lock in the local lock table, since it's
* only ever released at the end of a transaction. Instead,
* LockReleaseAll() calls VirtualXactLockTableCleanup().
*/
void
VirtualXactLockTableInsert(VirtualTransactionId vxid)
{
Assert(VirtualTransactionIdIsValid(vxid));
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
Assert(MyProc->backendId == vxid.backendId);
Assert(MyProc->fpLocalTransactionId == InvalidLocalTransactionId);
Assert(MyProc->fpVXIDLock == false);
MyProc->fpVXIDLock = true;
MyProc->fpLocalTransactionId = vxid.localTransactionId;
LWLockRelease(&MyProc->backendLock);
}
/*
* VirtualXactLockTableCleanup
*
* Check whether a VXID lock has been materialized; if so, release it,
* unblocking waiters.
*/
void
VirtualXactLockTableCleanup(void)
{
bool fastpath;
LocalTransactionId lxid;
Assert(MyProc->backendId != InvalidBackendId);
/*
* Clean up shared memory state.
*/
LWLockAcquire(&MyProc->backendLock, LW_EXCLUSIVE);
fastpath = MyProc->fpVXIDLock;
lxid = MyProc->fpLocalTransactionId;
MyProc->fpVXIDLock = false;
MyProc->fpLocalTransactionId = InvalidLocalTransactionId;
LWLockRelease(&MyProc->backendLock);
/*
* If fpVXIDLock has been cleared without touching fpLocalTransactionId,
* that means someone transferred the lock to the main lock table.
*/
if (!fastpath && LocalTransactionIdIsValid(lxid))
{
VirtualTransactionId vxid;
LOCKTAG locktag;
vxid.backendId = MyBackendId;
vxid.localTransactionId = lxid;
SET_LOCKTAG_VIRTUALTRANSACTION(locktag, vxid);
LockRefindAndRelease(LockMethods[DEFAULT_LOCKMETHOD], MyProc,
&locktag, ExclusiveLock, false);
}
}
/*
* VirtualXactLock
*
* If wait = true, wait until the given VXID has been released, and then
* return true.
*
* If wait = false, just check whether the VXID is still running, and return
* true or false.
*/
bool
VirtualXactLock(VirtualTransactionId vxid, bool wait)
{
LOCKTAG tag;
PGPROC *proc;
Assert(VirtualTransactionIdIsValid(vxid));
SET_LOCKTAG_VIRTUALTRANSACTION(tag, vxid);
/*
* If a lock table entry must be made, this is the PGPROC on whose behalf
* it must be done. Note that the transaction might end or the PGPROC
* might be reassigned to a new backend before we get around to examining
* it, but it doesn't matter. If we find upon examination that the
* relevant lxid is no longer running here, that's enough to prove that
* it's no longer running anywhere.
*/
proc = BackendIdGetProc(vxid.backendId);
if (proc == NULL)
return true;
/*
* We must acquire this lock before checking the backendId and lxid
* against the ones we're waiting for. The target backend will only set
* or clear lxid while holding this lock.
*/
LWLockAcquire(&proc->backendLock, LW_EXCLUSIVE);
/* If the transaction has ended, our work here is done. */
if (proc->backendId != vxid.backendId
|| proc->fpLocalTransactionId != vxid.localTransactionId)
{
LWLockRelease(&proc->backendLock);
return true;
}
/*
* If we aren't asked to wait, there's no need to set up a lock table
* entry. The transaction is still in progress, so just return false.
*/
if (!wait)
{
LWLockRelease(&proc->backendLock);
return false;
}
/*
* OK, we're going to need to sleep on the VXID. But first, we must set
* up the primary lock table entry, if needed (ie, convert the proc's
* fast-path lock on its VXID to a regular lock).
*/
if (proc->fpVXIDLock)
{
PROCLOCK *proclock;
uint32 hashcode;
LWLock *partitionLock;
hashcode = LockTagHashCode(&tag);
partitionLock = LockHashPartitionLock(hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
proclock = SetupLockInTable(LockMethods[DEFAULT_LOCKMETHOD], proc,
&tag, hashcode, ExclusiveLock);
if (!proclock)
{
LWLockRelease(partitionLock);
LWLockRelease(&proc->backendLock);
ereport(ERROR,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of shared memory"),
errhint("You might need to increase max_locks_per_transaction.")));
}
GrantLock(proclock->tag.myLock, proclock, ExclusiveLock);
LWLockRelease(partitionLock);
proc->fpVXIDLock = false;
}
/* Done with proc->fpLockBits */
LWLockRelease(&proc->backendLock);
/* Time to wait. */
(void) LockAcquire(&tag, ShareLock, false, false);
LockRelease(&tag, ShareLock, false);
return true;
}
/*
* LockWaiterCount
*
* Find the number of lock requester on this locktag
*/
int
LockWaiterCount(const LOCKTAG *locktag)
{
LOCKMETHODID lockmethodid = locktag->locktag_lockmethodid;
LOCK *lock;
bool found;
uint32 hashcode;
LWLock *partitionLock;
int waiters = 0;
if (lockmethodid <= 0 || lockmethodid >= lengthof(LockMethods))
elog(ERROR, "unrecognized lock method: %d", lockmethodid);
hashcode = LockTagHashCode(locktag);
partitionLock = LockHashPartitionLock(hashcode);
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
lock = (LOCK *) hash_search_with_hash_value(LockMethodLockHash,
(const void *) locktag,
hashcode,
HASH_FIND,
&found);
if (found)
{
Assert(lock != NULL);
waiters = lock->nRequested;
}
LWLockRelease(partitionLock);
return waiters;
}
|