summaryrefslogtreecommitdiff
path: root/fs/locks.c
blob: 76ad05f8070ad980ed732df223093789f808c4b0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/fs/locks.c
 *
 * We implement four types of file locks: BSD locks, posix locks, open
 * file description locks, and leases.  For details about BSD locks,
 * see the flock(2) man page; for details about the other three, see
 * fcntl(2).
 *
 *
 * Locking conflicts and dependencies:
 * If multiple threads attempt to lock the same byte (or flock the same file)
 * only one can be granted the lock, and other must wait their turn.
 * The first lock has been "applied" or "granted", the others are "waiting"
 * and are "blocked" by the "applied" lock..
 *
 * Waiting and applied locks are all kept in trees whose properties are:
 *
 *	- the root of a tree may be an applied or waiting lock.
 *	- every other node in the tree is a waiting lock that
 *	  conflicts with every ancestor of that node.
 *
 * Every such tree begins life as a waiting singleton which obviously
 * satisfies the above properties.
 *
 * The only ways we modify trees preserve these properties:
 *
 *	1. We may add a new leaf node, but only after first verifying that it
 *	   conflicts with all of its ancestors.
 *	2. We may remove the root of a tree, creating a new singleton
 *	   tree from the root and N new trees rooted in the immediate
 *	   children.
 *	3. If the root of a tree is not currently an applied lock, we may
 *	   apply it (if possible).
 *	4. We may upgrade the root of the tree (either extend its range,
 *	   or upgrade its entire range from read to write).
 *
 * When an applied lock is modified in a way that reduces or downgrades any
 * part of its range, we remove all its children (2 above).  This particularly
 * happens when a lock is unlocked.
 *
 * For each of those child trees we "wake up" the thread which is
 * waiting for the lock so it can continue handling as follows: if the
 * root of the tree applies, we do so (3).  If it doesn't, it must
 * conflict with some applied lock.  We remove (wake up) all of its children
 * (2), and add it is a new leaf to the tree rooted in the applied
 * lock (1).  We then repeat the process recursively with those
 * children.
 *
 */

#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/filelock.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/time.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/hashtable.h>
#include <linux/percpu.h>
#include <linux/sysctl.h>

#define CREATE_TRACE_POINTS
#include <trace/events/filelock.h>

#include <linux/uaccess.h>

#define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
#define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
#define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
#define IS_REMOTELCK(fl)	(fl->fl_pid <= 0)

static bool lease_breaking(struct file_lock *fl)
{
	return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
}

static int target_leasetype(struct file_lock *fl)
{
	if (fl->fl_flags & FL_UNLOCK_PENDING)
		return F_UNLCK;
	if (fl->fl_flags & FL_DOWNGRADE_PENDING)
		return F_RDLCK;
	return fl->fl_type;
}

static int leases_enable = 1;
static int lease_break_time = 45;

#ifdef CONFIG_SYSCTL
static struct ctl_table locks_sysctls[] = {
	{
		.procname	= "leases-enable",
		.data		= &leases_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_MMU
	{
		.procname	= "lease-break-time",
		.data		= &lease_break_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif /* CONFIG_MMU */
	{}
};

static int __init init_fs_locks_sysctls(void)
{
	register_sysctl_init("fs", locks_sysctls);
	return 0;
}
early_initcall(init_fs_locks_sysctls);
#endif /* CONFIG_SYSCTL */

/*
 * The global file_lock_list is only used for displaying /proc/locks, so we
 * keep a list on each CPU, with each list protected by its own spinlock.
 * Global serialization is done using file_rwsem.
 *
 * Note that alterations to the list also require that the relevant flc_lock is
 * held.
 */
struct file_lock_list_struct {
	spinlock_t		lock;
	struct hlist_head	hlist;
};
static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list);
DEFINE_STATIC_PERCPU_RWSEM(file_rwsem);


/*
 * The blocked_hash is used to find POSIX lock loops for deadlock detection.
 * It is protected by blocked_lock_lock.
 *
 * We hash locks by lockowner in order to optimize searching for the lock a
 * particular lockowner is waiting on.
 *
 * FIXME: make this value scale via some heuristic? We generally will want more
 * buckets when we have more lockowners holding locks, but that's a little
 * difficult to determine without knowing what the workload will look like.
 */
#define BLOCKED_HASH_BITS	7
static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);

/*
 * This lock protects the blocked_hash. Generally, if you're accessing it, you
 * want to be holding this lock.
 *
 * In addition, it also protects the fl->fl_blocked_requests list, and the
 * fl->fl_blocker pointer for file_lock structures that are acting as lock
 * requests (in contrast to those that are acting as records of acquired locks).
 *
 * Note that when we acquire this lock in order to change the above fields,
 * we often hold the flc_lock as well. In certain cases, when reading the fields
 * protected by this lock, we can skip acquiring it iff we already hold the
 * flc_lock.
 */
static DEFINE_SPINLOCK(blocked_lock_lock);

static struct kmem_cache *flctx_cache __read_mostly;
static struct kmem_cache *filelock_cache __read_mostly;

static struct file_lock_context *
locks_get_lock_context(struct inode *inode, int type)
{
	struct file_lock_context *ctx;

	/* paired with cmpxchg() below */
	ctx = locks_inode_context(inode);
	if (likely(ctx) || type == F_UNLCK)
		goto out;

	ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL);
	if (!ctx)
		goto out;

	spin_lock_init(&ctx->flc_lock);
	INIT_LIST_HEAD(&ctx->flc_flock);
	INIT_LIST_HEAD(&ctx->flc_posix);
	INIT_LIST_HEAD(&ctx->flc_lease);

	/*
	 * Assign the pointer if it's not already assigned. If it is, then
	 * free the context we just allocated.
	 */
	if (cmpxchg(&inode->i_flctx, NULL, ctx)) {
		kmem_cache_free(flctx_cache, ctx);
		ctx = locks_inode_context(inode);
	}
out:
	trace_locks_get_lock_context(inode, type, ctx);
	return ctx;
}

static void
locks_dump_ctx_list(struct list_head *list, char *list_type)
{
	struct file_lock *fl;

	list_for_each_entry(fl, list, fl_list) {
		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
	}
}

static void
locks_check_ctx_lists(struct inode *inode)
{
	struct file_lock_context *ctx = inode->i_flctx;

	if (unlikely(!list_empty(&ctx->flc_flock) ||
		     !list_empty(&ctx->flc_posix) ||
		     !list_empty(&ctx->flc_lease))) {
		pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n",
			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
			inode->i_ino);
		locks_dump_ctx_list(&ctx->flc_flock, "FLOCK");
		locks_dump_ctx_list(&ctx->flc_posix, "POSIX");
		locks_dump_ctx_list(&ctx->flc_lease, "LEASE");
	}
}

static void
locks_check_ctx_file_list(struct file *filp, struct list_head *list,
				char *list_type)
{
	struct file_lock *fl;
	struct inode *inode = file_inode(filp);

	list_for_each_entry(fl, list, fl_list)
		if (fl->fl_file == filp)
			pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx "
				" fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
				list_type, MAJOR(inode->i_sb->s_dev),
				MINOR(inode->i_sb->s_dev), inode->i_ino,
				fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
}

void
locks_free_lock_context(struct inode *inode)
{
	struct file_lock_context *ctx = locks_inode_context(inode);

	if (unlikely(ctx)) {
		locks_check_ctx_lists(inode);
		kmem_cache_free(flctx_cache, ctx);
	}
}

static void locks_init_lock_heads(struct file_lock *fl)
{
	INIT_HLIST_NODE(&fl->fl_link);
	INIT_LIST_HEAD(&fl->fl_list);
	INIT_LIST_HEAD(&fl->fl_blocked_requests);
	INIT_LIST_HEAD(&fl->fl_blocked_member);
	init_waitqueue_head(&fl->fl_wait);
}

/* Allocate an empty lock structure. */
struct file_lock *locks_alloc_lock(void)
{
	struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL);

	if (fl)
		locks_init_lock_heads(fl);

	return fl;
}
EXPORT_SYMBOL_GPL(locks_alloc_lock);

void locks_release_private(struct file_lock *fl)
{
	BUG_ON(waitqueue_active(&fl->fl_wait));
	BUG_ON(!list_empty(&fl->fl_list));
	BUG_ON(!list_empty(&fl->fl_blocked_requests));
	BUG_ON(!list_empty(&fl->fl_blocked_member));
	BUG_ON(!hlist_unhashed(&fl->fl_link));

	if (fl->fl_ops) {
		if (fl->fl_ops->fl_release_private)
			fl->fl_ops->fl_release_private(fl);
		fl->fl_ops = NULL;
	}

	if (fl->fl_lmops) {
		if (fl->fl_lmops->lm_put_owner) {
			fl->fl_lmops->lm_put_owner(fl->fl_owner);
			fl->fl_owner = NULL;
		}
		fl->fl_lmops = NULL;
	}
}
EXPORT_SYMBOL_GPL(locks_release_private);

/**
 * locks_owner_has_blockers - Check for blocking lock requests
 * @flctx: file lock context
 * @owner: lock owner
 *
 * Return values:
 *   %true: @owner has at least one blocker
 *   %false: @owner has no blockers
 */
bool locks_owner_has_blockers(struct file_lock_context *flctx,
		fl_owner_t owner)
{
	struct file_lock *fl;

	spin_lock(&flctx->flc_lock);
	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
		if (fl->fl_owner != owner)
			continue;
		if (!list_empty(&fl->fl_blocked_requests)) {
			spin_unlock(&flctx->flc_lock);
			return true;
		}
	}
	spin_unlock(&flctx->flc_lock);
	return false;
}
EXPORT_SYMBOL_GPL(locks_owner_has_blockers);

/* Free a lock which is not in use. */
void locks_free_lock(struct file_lock *fl)
{
	locks_release_private(fl);
	kmem_cache_free(filelock_cache, fl);
}
EXPORT_SYMBOL(locks_free_lock);

static void
locks_dispose_list(struct list_head *dispose)
{
	struct file_lock *fl;

	while (!list_empty(dispose)) {
		fl = list_first_entry(dispose, struct file_lock, fl_list);
		list_del_init(&fl->fl_list);
		locks_free_lock(fl);
	}
}

void locks_init_lock(struct file_lock *fl)
{
	memset(fl, 0, sizeof(struct file_lock));
	locks_init_lock_heads(fl);
}
EXPORT_SYMBOL(locks_init_lock);

/*
 * Initialize a new lock from an existing file_lock structure.
 */
void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
	new->fl_owner = fl->fl_owner;
	new->fl_pid = fl->fl_pid;
	new->fl_file = NULL;
	new->fl_flags = fl->fl_flags;
	new->fl_type = fl->fl_type;
	new->fl_start = fl->fl_start;
	new->fl_end = fl->fl_end;
	new->fl_lmops = fl->fl_lmops;
	new->fl_ops = NULL;

	if (fl->fl_lmops) {
		if (fl->fl_lmops->lm_get_owner)
			fl->fl_lmops->lm_get_owner(fl->fl_owner);
	}
}
EXPORT_SYMBOL(locks_copy_conflock);

void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	/* "new" must be a freshly-initialized lock */
	WARN_ON_ONCE(new->fl_ops);

	locks_copy_conflock(new, fl);

	new->fl_file = fl->fl_file;
	new->fl_ops = fl->fl_ops;

	if (fl->fl_ops) {
		if (fl->fl_ops->fl_copy_lock)
			fl->fl_ops->fl_copy_lock(new, fl);
	}
}
EXPORT_SYMBOL(locks_copy_lock);

static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
{
	struct file_lock *f;

	/*
	 * As ctx->flc_lock is held, new requests cannot be added to
	 * ->fl_blocked_requests, so we don't need a lock to check if it
	 * is empty.
	 */
	if (list_empty(&fl->fl_blocked_requests))
		return;
	spin_lock(&blocked_lock_lock);
	list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests);
	list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member)
		f->fl_blocker = new;
	spin_unlock(&blocked_lock_lock);
}

static inline int flock_translate_cmd(int cmd) {
	switch (cmd) {
	case LOCK_SH:
		return F_RDLCK;
	case LOCK_EX:
		return F_WRLCK;
	case LOCK_UN:
		return F_UNLCK;
	}
	return -EINVAL;
}

/* Fill in a file_lock structure with an appropriate FLOCK lock. */
static void flock_make_lock(struct file *filp, struct file_lock *fl, int type)
{
	locks_init_lock(fl);

	fl->fl_file = filp;
	fl->fl_owner = filp;
	fl->fl_pid = current->tgid;
	fl->fl_flags = FL_FLOCK;
	fl->fl_type = type;
	fl->fl_end = OFFSET_MAX;
}

static int assign_type(struct file_lock *fl, int type)
{
	switch (type) {
	case F_RDLCK:
	case F_WRLCK:
	case F_UNLCK:
		fl->fl_type = type;
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
				 struct flock64 *l)
{
	switch (l->l_whence) {
	case SEEK_SET:
		fl->fl_start = 0;
		break;
	case SEEK_CUR:
		fl->fl_start = filp->f_pos;
		break;
	case SEEK_END:
		fl->fl_start = i_size_read(file_inode(filp));
		break;
	default:
		return -EINVAL;
	}
	if (l->l_start > OFFSET_MAX - fl->fl_start)
		return -EOVERFLOW;
	fl->fl_start += l->l_start;
	if (fl->fl_start < 0)
		return -EINVAL;

	/* POSIX-1996 leaves the case l->l_len < 0 undefined;
	   POSIX-2001 defines it. */
	if (l->l_len > 0) {
		if (l->l_len - 1 > OFFSET_MAX - fl->fl_start)
			return -EOVERFLOW;
		fl->fl_end = fl->fl_start + (l->l_len - 1);

	} else if (l->l_len < 0) {
		if (fl->fl_start + l->l_len < 0)
			return -EINVAL;
		fl->fl_end = fl->fl_start - 1;
		fl->fl_start += l->l_len;
	} else
		fl->fl_end = OFFSET_MAX;

	fl->fl_owner = current->files;
	fl->fl_pid = current->tgid;
	fl->fl_file = filp;
	fl->fl_flags = FL_POSIX;
	fl->fl_ops = NULL;
	fl->fl_lmops = NULL;

	return assign_type(fl, l->l_type);
}

/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
 * style lock.
 */
static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
			       struct flock *l)
{
	struct flock64 ll = {
		.l_type = l->l_type,
		.l_whence = l->l_whence,
		.l_start = l->l_start,
		.l_len = l->l_len,
	};

	return flock64_to_posix_lock(filp, fl, &ll);
}

/* default lease lock manager operations */
static bool
lease_break_callback(struct file_lock *fl)
{
	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
	return false;
}

static void
lease_setup(struct file_lock *fl, void **priv)
{
	struct file *filp = fl->fl_file;
	struct fasync_struct *fa = *priv;

	/*
	 * fasync_insert_entry() returns the old entry if any. If there was no
	 * old entry, then it used "priv" and inserted it into the fasync list.
	 * Clear the pointer to indicate that it shouldn't be freed.
	 */
	if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa))
		*priv = NULL;

	__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
}

static const struct lock_manager_operations lease_manager_ops = {
	.lm_break = lease_break_callback,
	.lm_change = lease_modify,
	.lm_setup = lease_setup,
};

/*
 * Initialize a lease, use the default lock manager operations
 */
static int lease_init(struct file *filp, int type, struct file_lock *fl)
{
	if (assign_type(fl, type) != 0)
		return -EINVAL;

	fl->fl_owner = filp;
	fl->fl_pid = current->tgid;

	fl->fl_file = filp;
	fl->fl_flags = FL_LEASE;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;
	fl->fl_ops = NULL;
	fl->fl_lmops = &lease_manager_ops;
	return 0;
}

/* Allocate a file_lock initialised to this type of lease */
static struct file_lock *lease_alloc(struct file *filp, int type)
{
	struct file_lock *fl = locks_alloc_lock();
	int error = -ENOMEM;

	if (fl == NULL)
		return ERR_PTR(error);

	error = lease_init(filp, type, fl);
	if (error) {
		locks_free_lock(fl);
		return ERR_PTR(error);
	}
	return fl;
}

/* Check if two locks overlap each other.
 */
static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
{
	return ((fl1->fl_end >= fl2->fl_start) &&
		(fl2->fl_end >= fl1->fl_start));
}

/*
 * Check whether two locks have the same owner.
 */
static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
{
	return fl1->fl_owner == fl2->fl_owner;
}

/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock *fl)
{
	struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);

	percpu_rwsem_assert_held(&file_rwsem);

	spin_lock(&fll->lock);
	fl->fl_link_cpu = smp_processor_id();
	hlist_add_head(&fl->fl_link, &fll->hlist);
	spin_unlock(&fll->lock);
}

/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock *fl)
{
	struct file_lock_list_struct *fll;

	percpu_rwsem_assert_held(&file_rwsem);

	/*
	 * Avoid taking lock if already unhashed. This is safe since this check
	 * is done while holding the flc_lock, and new insertions into the list
	 * also require that it be held.
	 */
	if (hlist_unhashed(&fl->fl_link))
		return;

	fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu);
	spin_lock(&fll->lock);
	hlist_del_init(&fl->fl_link);
	spin_unlock(&fll->lock);
}

static unsigned long
posix_owner_key(struct file_lock *fl)
{
	return (unsigned long)fl->fl_owner;
}

static void locks_insert_global_blocked(struct file_lock *waiter)
{
	lockdep_assert_held(&blocked_lock_lock);

	hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter));
}

static void locks_delete_global_blocked(struct file_lock *waiter)
{
	lockdep_assert_held(&blocked_lock_lock);

	hash_del(&waiter->fl_link);
}

/* Remove waiter from blocker's block list.
 * When blocker ends up pointing to itself then the list is empty.
 *
 * Must be called with blocked_lock_lock held.
 */
static void __locks_delete_block(struct file_lock *waiter)
{
	locks_delete_global_blocked(waiter);
	list_del_init(&waiter->fl_blocked_member);
}

static void __locks_wake_up_blocks(struct file_lock *blocker)
{
	while (!list_empty(&blocker->fl_blocked_requests)) {
		struct file_lock *waiter;

		waiter = list_first_entry(&blocker->fl_blocked_requests,
					  struct file_lock, fl_blocked_member);
		__locks_delete_block(waiter);
		if (waiter->fl_lmops && waiter->fl_lmops->lm_notify)
			waiter->fl_lmops->lm_notify(waiter);
		else
			wake_up(&waiter->fl_wait);

		/*
		 * The setting of fl_blocker to NULL marks the "done"
		 * point in deleting a block. Paired with acquire at the top
		 * of locks_delete_block().
		 */
		smp_store_release(&waiter->fl_blocker, NULL);
	}
}

/**
 *	locks_delete_block - stop waiting for a file lock
 *	@waiter: the lock which was waiting
 *
 *	lockd/nfsd need to disconnect the lock while working on it.
 */
int locks_delete_block(struct file_lock *waiter)
{
	int status = -ENOENT;

	/*
	 * If fl_blocker is NULL, it won't be set again as this thread "owns"
	 * the lock and is the only one that might try to claim the lock.
	 *
	 * We use acquire/release to manage fl_blocker so that we can
	 * optimize away taking the blocked_lock_lock in many cases.
	 *
	 * The smp_load_acquire guarantees two things:
	 *
	 * 1/ that fl_blocked_requests can be tested locklessly. If something
	 * was recently added to that list it must have been in a locked region
	 * *before* the locked region when fl_blocker was set to NULL.
	 *
	 * 2/ that no other thread is accessing 'waiter', so it is safe to free
	 * it.  __locks_wake_up_blocks is careful not to touch waiter after
	 * fl_blocker is released.
	 *
	 * If a lockless check of fl_blocker shows it to be NULL, we know that
	 * no new locks can be inserted into its fl_blocked_requests list, and
	 * can avoid doing anything further if the list is empty.
	 */
	if (!smp_load_acquire(&waiter->fl_blocker) &&
	    list_empty(&waiter->fl_blocked_requests))
		return status;

	spin_lock(&blocked_lock_lock);
	if (waiter->fl_blocker)
		status = 0;
	__locks_wake_up_blocks(waiter);
	__locks_delete_block(waiter);

	/*
	 * The setting of fl_blocker to NULL marks the "done" point in deleting
	 * a block. Paired with acquire at the top of this function.
	 */
	smp_store_release(&waiter->fl_blocker, NULL);
	spin_unlock(&blocked_lock_lock);
	return status;
}
EXPORT_SYMBOL(locks_delete_block);

/* Insert waiter into blocker's block list.
 * We use a circular list so that processes can be easily woken up in
 * the order they blocked. The documentation doesn't require this but
 * it seems like the reasonable thing to do.
 *
 * Must be called with both the flc_lock and blocked_lock_lock held. The
 * fl_blocked_requests list itself is protected by the blocked_lock_lock,
 * but by ensuring that the flc_lock is also held on insertions we can avoid
 * taking the blocked_lock_lock in some cases when we see that the
 * fl_blocked_requests list is empty.
 *
 * Rather than just adding to the list, we check for conflicts with any existing
 * waiters, and add beneath any waiter that blocks the new waiter.
 * Thus wakeups don't happen until needed.
 */
static void __locks_insert_block(struct file_lock *blocker,
				 struct file_lock *waiter,
				 bool conflict(struct file_lock *,
					       struct file_lock *))
{
	struct file_lock *fl;
	BUG_ON(!list_empty(&waiter->fl_blocked_member));

new_blocker:
	list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member)
		if (conflict(fl, waiter)) {
			blocker =  fl;
			goto new_blocker;
		}
	waiter->fl_blocker = blocker;
	list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests);
	if (IS_POSIX(blocker) && !IS_OFDLCK(blocker))
		locks_insert_global_blocked(waiter);

	/* The requests in waiter->fl_blocked are known to conflict with
	 * waiter, but might not conflict with blocker, or the requests
	 * and lock which block it.  So they all need to be woken.
	 */
	__locks_wake_up_blocks(waiter);
}

/* Must be called with flc_lock held. */
static void locks_insert_block(struct file_lock *blocker,
			       struct file_lock *waiter,
			       bool conflict(struct file_lock *,
					     struct file_lock *))
{
	spin_lock(&blocked_lock_lock);
	__locks_insert_block(blocker, waiter, conflict);
	spin_unlock(&blocked_lock_lock);
}

/*
 * Wake up processes blocked waiting for blocker.
 *
 * Must be called with the inode->flc_lock held!
 */
static void locks_wake_up_blocks(struct file_lock *blocker)
{
	/*
	 * Avoid taking global lock if list is empty. This is safe since new
	 * blocked requests are only added to the list under the flc_lock, and
	 * the flc_lock is always held here. Note that removal from the
	 * fl_blocked_requests list does not require the flc_lock, so we must
	 * recheck list_empty() after acquiring the blocked_lock_lock.
	 */
	if (list_empty(&blocker->fl_blocked_requests))
		return;

	spin_lock(&blocked_lock_lock);
	__locks_wake_up_blocks(blocker);
	spin_unlock(&blocked_lock_lock);
}

static void
locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
{
	list_add_tail(&fl->fl_list, before);
	locks_insert_global_locks(fl);
}

static void
locks_unlink_lock_ctx(struct file_lock *fl)
{
	locks_delete_global_locks(fl);
	list_del_init(&fl->fl_list);
	locks_wake_up_blocks(fl);
}

static void
locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
{
	locks_unlink_lock_ctx(fl);
	if (dispose)
		list_add(&fl->fl_list, dispose);
	else
		locks_free_lock(fl);
}

/* Determine if lock sys_fl blocks lock caller_fl. Common functionality
 * checks for shared/exclusive status of overlapping locks.
 */
static bool locks_conflict(struct file_lock *caller_fl,
			   struct file_lock *sys_fl)
{
	if (sys_fl->fl_type == F_WRLCK)
		return true;
	if (caller_fl->fl_type == F_WRLCK)
		return true;
	return false;
}

/* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
 * checking before calling the locks_conflict().
 */
static bool posix_locks_conflict(struct file_lock *caller_fl,
				 struct file_lock *sys_fl)
{
	/* POSIX locks owned by the same process do not conflict with
	 * each other.
	 */
	if (posix_same_owner(caller_fl, sys_fl))
		return false;

	/* Check whether they overlap */
	if (!locks_overlap(caller_fl, sys_fl))
		return false;

	return locks_conflict(caller_fl, sys_fl);
}

/* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK
 * path so checks for additional GETLK-specific things like F_UNLCK.
 */
static bool posix_test_locks_conflict(struct file_lock *caller_fl,
				      struct file_lock *sys_fl)
{
	/* F_UNLCK checks any locks on the same fd. */
	if (caller_fl->fl_type == F_UNLCK) {
		if (!posix_same_owner(caller_fl, sys_fl))
			return false;
		return locks_overlap(caller_fl, sys_fl);
	}
	return posix_locks_conflict(caller_fl, sys_fl);
}

/* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
 * checking before calling the locks_conflict().
 */
static bool flock_locks_conflict(struct file_lock *caller_fl,
				 struct file_lock *sys_fl)
{
	/* FLOCK locks referring to the same filp do not conflict with
	 * each other.
	 */
	if (caller_fl->fl_file == sys_fl->fl_file)
		return false;

	return locks_conflict(caller_fl, sys_fl);
}

void
posix_test_lock(struct file *filp, struct file_lock *fl)
{
	struct file_lock *cfl;
	struct file_lock_context *ctx;
	struct inode *inode = file_inode(filp);
	void *owner;
	void (*func)(void);

	ctx = locks_inode_context(inode);
	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
		fl->fl_type = F_UNLCK;
		return;
	}

retry:
	spin_lock(&ctx->flc_lock);
	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
		if (!posix_test_locks_conflict(fl, cfl))
			continue;
		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
			&& (*cfl->fl_lmops->lm_lock_expirable)(cfl)) {
			owner = cfl->fl_lmops->lm_mod_owner;
			func = cfl->fl_lmops->lm_expire_lock;
			__module_get(owner);
			spin_unlock(&ctx->flc_lock);
			(*func)();
			module_put(owner);
			goto retry;
		}
		locks_copy_conflock(fl, cfl);
		goto out;
	}
	fl->fl_type = F_UNLCK;
out:
	spin_unlock(&ctx->flc_lock);
	return;
}
EXPORT_SYMBOL(posix_test_lock);

/*
 * Deadlock detection:
 *
 * We attempt to detect deadlocks that are due purely to posix file
 * locks.
 *
 * We assume that a task can be waiting for at most one lock at a time.
 * So for any acquired lock, the process holding that lock may be
 * waiting on at most one other lock.  That lock in turns may be held by
 * someone waiting for at most one other lock.  Given a requested lock
 * caller_fl which is about to wait for a conflicting lock block_fl, we
 * follow this chain of waiters to ensure we are not about to create a
 * cycle.
 *
 * Since we do this before we ever put a process to sleep on a lock, we
 * are ensured that there is never a cycle; that is what guarantees that
 * the while() loop in posix_locks_deadlock() eventually completes.
 *
 * Note: the above assumption may not be true when handling lock
 * requests from a broken NFS client. It may also fail in the presence
 * of tasks (such as posix threads) sharing the same open file table.
 * To handle those cases, we just bail out after a few iterations.
 *
 * For FL_OFDLCK locks, the owner is the filp, not the files_struct.
 * Because the owner is not even nominally tied to a thread of
 * execution, the deadlock detection below can't reasonably work well. Just
 * skip it for those.
 *
 * In principle, we could do a more limited deadlock detection on FL_OFDLCK
 * locks that just checks for the case where two tasks are attempting to
 * upgrade from read to write locks on the same inode.
 */

#define MAX_DEADLK_ITERATIONS 10

/* Find a lock that the owner of the given block_fl is blocking on. */
static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
{
	struct file_lock *fl;

	hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) {
		if (posix_same_owner(fl, block_fl)) {
			while (fl->fl_blocker)
				fl = fl->fl_blocker;
			return fl;
		}
	}
	return NULL;
}

/* Must be called with the blocked_lock_lock held! */
static int posix_locks_deadlock(struct file_lock *caller_fl,
				struct file_lock *block_fl)
{
	int i = 0;

	lockdep_assert_held(&blocked_lock_lock);

	/*
	 * This deadlock detector can't reasonably detect deadlocks with
	 * FL_OFDLCK locks, since they aren't owned by a process, per-se.
	 */
	if (IS_OFDLCK(caller_fl))
		return 0;

	while ((block_fl = what_owner_is_waiting_for(block_fl))) {
		if (i++ > MAX_DEADLK_ITERATIONS)
			return 0;
		if (posix_same_owner(caller_fl, block_fl))
			return 1;
	}
	return 0;
}

/* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
 * after any leases, but before any posix locks.
 *
 * Note that if called with an FL_EXISTS argument, the caller may determine
 * whether or not a lock was successfully freed by testing the return
 * value for -ENOENT.
 */
static int flock_lock_inode(struct inode *inode, struct file_lock *request)
{
	struct file_lock *new_fl = NULL;
	struct file_lock *fl;
	struct file_lock_context *ctx;
	int error = 0;
	bool found = false;
	LIST_HEAD(dispose);

	ctx = locks_get_lock_context(inode, request->fl_type);
	if (!ctx) {
		if (request->fl_type != F_UNLCK)
			return -ENOMEM;
		return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0;
	}

	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
		new_fl = locks_alloc_lock();
		if (!new_fl)
			return -ENOMEM;
	}

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	if (request->fl_flags & FL_ACCESS)
		goto find_conflict;

	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
		if (request->fl_file != fl->fl_file)
			continue;
		if (request->fl_type == fl->fl_type)
			goto out;
		found = true;
		locks_delete_lock_ctx(fl, &dispose);
		break;
	}

	if (request->fl_type == F_UNLCK) {
		if ((request->fl_flags & FL_EXISTS) && !found)
			error = -ENOENT;
		goto out;
	}

find_conflict:
	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
		if (!flock_locks_conflict(request, fl))
			continue;
		error = -EAGAIN;
		if (!(request->fl_flags & FL_SLEEP))
			goto out;
		error = FILE_LOCK_DEFERRED;
		locks_insert_block(fl, request, flock_locks_conflict);
		goto out;
	}
	if (request->fl_flags & FL_ACCESS)
		goto out;
	locks_copy_lock(new_fl, request);
	locks_move_blocks(new_fl, request);
	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
	new_fl = NULL;
	error = 0;

out:
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);
	if (new_fl)
		locks_free_lock(new_fl);
	locks_dispose_list(&dispose);
	trace_flock_lock_inode(inode, request, error);
	return error;
}

static int posix_lock_inode(struct inode *inode, struct file_lock *request,
			    struct file_lock *conflock)
{
	struct file_lock *fl, *tmp;
	struct file_lock *new_fl = NULL;
	struct file_lock *new_fl2 = NULL;
	struct file_lock *left = NULL;
	struct file_lock *right = NULL;
	struct file_lock_context *ctx;
	int error;
	bool added = false;
	LIST_HEAD(dispose);
	void *owner;
	void (*func)(void);

	ctx = locks_get_lock_context(inode, request->fl_type);
	if (!ctx)
		return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM;

	/*
	 * We may need two file_lock structures for this operation,
	 * so we get them in advance to avoid races.
	 *
	 * In some cases we can be sure, that no new locks will be needed
	 */
	if (!(request->fl_flags & FL_ACCESS) &&
	    (request->fl_type != F_UNLCK ||
	     request->fl_start != 0 || request->fl_end != OFFSET_MAX)) {
		new_fl = locks_alloc_lock();
		new_fl2 = locks_alloc_lock();
	}

retry:
	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	/*
	 * New lock request. Walk all POSIX locks and look for conflicts. If
	 * there are any, either return error or put the request on the
	 * blocker's list of waiters and the global blocked_hash.
	 */
	if (request->fl_type != F_UNLCK) {
		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
			if (!posix_locks_conflict(request, fl))
				continue;
			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
				owner = fl->fl_lmops->lm_mod_owner;
				func = fl->fl_lmops->lm_expire_lock;
				__module_get(owner);
				spin_unlock(&ctx->flc_lock);
				percpu_up_read(&file_rwsem);
				(*func)();
				module_put(owner);
				goto retry;
			}
			if (conflock)
				locks_copy_conflock(conflock, fl);
			error = -EAGAIN;
			if (!(request->fl_flags & FL_SLEEP))
				goto out;
			/*
			 * Deadlock detection and insertion into the blocked
			 * locks list must be done while holding the same lock!
			 */
			error = -EDEADLK;
			spin_lock(&blocked_lock_lock);
			/*
			 * Ensure that we don't find any locks blocked on this
			 * request during deadlock detection.
			 */
			__locks_wake_up_blocks(request);
			if (likely(!posix_locks_deadlock(request, fl))) {
				error = FILE_LOCK_DEFERRED;
				__locks_insert_block(fl, request,
						     posix_locks_conflict);
			}
			spin_unlock(&blocked_lock_lock);
			goto out;
		}
	}

	/* If we're just looking for a conflict, we're done. */
	error = 0;
	if (request->fl_flags & FL_ACCESS)
		goto out;

	/* Find the first old lock with the same owner as the new lock */
	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
		if (posix_same_owner(request, fl))
			break;
	}

	/* Process locks with this owner. */
	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
		if (!posix_same_owner(request, fl))
			break;

		/* Detect adjacent or overlapping regions (if same lock type) */
		if (request->fl_type == fl->fl_type) {
			/* In all comparisons of start vs end, use
			 * "start - 1" rather than "end + 1". If end
			 * is OFFSET_MAX, end + 1 will become negative.
			 */
			if (fl->fl_end < request->fl_start - 1)
				continue;
			/* If the next lock in the list has entirely bigger
			 * addresses than the new one, insert the lock here.
			 */
			if (fl->fl_start - 1 > request->fl_end)
				break;

			/* If we come here, the new and old lock are of the
			 * same type and adjacent or overlapping. Make one
			 * lock yielding from the lower start address of both
			 * locks to the higher end address.
			 */
			if (fl->fl_start > request->fl_start)
				fl->fl_start = request->fl_start;
			else
				request->fl_start = fl->fl_start;
			if (fl->fl_end < request->fl_end)
				fl->fl_end = request->fl_end;
			else
				request->fl_end = fl->fl_end;
			if (added) {
				locks_delete_lock_ctx(fl, &dispose);
				continue;
			}
			request = fl;
			added = true;
		} else {
			/* Processing for different lock types is a bit
			 * more complex.
			 */
			if (fl->fl_end < request->fl_start)
				continue;
			if (fl->fl_start > request->fl_end)
				break;
			if (request->fl_type == F_UNLCK)
				added = true;
			if (fl->fl_start < request->fl_start)
				left = fl;
			/* If the next lock in the list has a higher end
			 * address than the new one, insert the new one here.
			 */
			if (fl->fl_end > request->fl_end) {
				right = fl;
				break;
			}
			if (fl->fl_start >= request->fl_start) {
				/* The new lock completely replaces an old
				 * one (This may happen several times).
				 */
				if (added) {
					locks_delete_lock_ctx(fl, &dispose);
					continue;
				}
				/*
				 * Replace the old lock with new_fl, and
				 * remove the old one. It's safe to do the
				 * insert here since we know that we won't be
				 * using new_fl later, and that the lock is
				 * just replacing an existing lock.
				 */
				error = -ENOLCK;
				if (!new_fl)
					goto out;
				locks_copy_lock(new_fl, request);
				locks_move_blocks(new_fl, request);
				request = new_fl;
				new_fl = NULL;
				locks_insert_lock_ctx(request, &fl->fl_list);
				locks_delete_lock_ctx(fl, &dispose);
				added = true;
			}
		}
	}

	/*
	 * The above code only modifies existing locks in case of merging or
	 * replacing. If new lock(s) need to be inserted all modifications are
	 * done below this, so it's safe yet to bail out.
	 */
	error = -ENOLCK; /* "no luck" */
	if (right && left == right && !new_fl2)
		goto out;

	error = 0;
	if (!added) {
		if (request->fl_type == F_UNLCK) {
			if (request->fl_flags & FL_EXISTS)
				error = -ENOENT;
			goto out;
		}

		if (!new_fl) {
			error = -ENOLCK;
			goto out;
		}
		locks_copy_lock(new_fl, request);
		locks_move_blocks(new_fl, request);
		locks_insert_lock_ctx(new_fl, &fl->fl_list);
		fl = new_fl;
		new_fl = NULL;
	}
	if (right) {
		if (left == right) {
			/* The new lock breaks the old one in two pieces,
			 * so we have to use the second new lock.
			 */
			left = new_fl2;
			new_fl2 = NULL;
			locks_copy_lock(left, right);
			locks_insert_lock_ctx(left, &fl->fl_list);
		}
		right->fl_start = request->fl_end + 1;
		locks_wake_up_blocks(right);
	}
	if (left) {
		left->fl_end = request->fl_start - 1;
		locks_wake_up_blocks(left);
	}
 out:
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);
	trace_posix_lock_inode(inode, request, error);
	/*
	 * Free any unused locks.
	 */
	if (new_fl)
		locks_free_lock(new_fl);
	if (new_fl2)
		locks_free_lock(new_fl2);
	locks_dispose_list(&dispose);

	return error;
}

/**
 * posix_lock_file - Apply a POSIX-style lock to a file
 * @filp: The file to apply the lock to
 * @fl: The lock to be applied
 * @conflock: Place to return a copy of the conflicting lock, if found.
 *
 * Add a POSIX style lock to a file.
 * We merge adjacent & overlapping locks whenever possible.
 * POSIX locks are sorted by owner task, then by starting address
 *
 * Note that if called with an FL_EXISTS argument, the caller may determine
 * whether or not a lock was successfully freed by testing the return
 * value for -ENOENT.
 */
int posix_lock_file(struct file *filp, struct file_lock *fl,
			struct file_lock *conflock)
{
	return posix_lock_inode(file_inode(filp), fl, conflock);
}
EXPORT_SYMBOL(posix_lock_file);

/**
 * posix_lock_inode_wait - Apply a POSIX-style lock to a file
 * @inode: inode of file to which lock request should be applied
 * @fl: The lock to be applied
 *
 * Apply a POSIX style lock request to an inode.
 */
static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	int error;
	might_sleep ();
	for (;;) {
		error = posix_lock_inode(inode, fl, NULL);
		if (error != FILE_LOCK_DEFERRED)
			break;
		error = wait_event_interruptible(fl->fl_wait,
					list_empty(&fl->fl_blocked_member));
		if (error)
			break;
	}
	locks_delete_block(fl);
	return error;
}

static void lease_clear_pending(struct file_lock *fl, int arg)
{
	switch (arg) {
	case F_UNLCK:
		fl->fl_flags &= ~FL_UNLOCK_PENDING;
		fallthrough;
	case F_RDLCK:
		fl->fl_flags &= ~FL_DOWNGRADE_PENDING;
	}
}

/* We already had a lease on this file; just change its type */
int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
{
	int error = assign_type(fl, arg);

	if (error)
		return error;
	lease_clear_pending(fl, arg);
	locks_wake_up_blocks(fl);
	if (arg == F_UNLCK) {
		struct file *filp = fl->fl_file;

		f_delown(filp);
		filp->f_owner.signum = 0;
		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
		if (fl->fl_fasync != NULL) {
			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
			fl->fl_fasync = NULL;
		}
		locks_delete_lock_ctx(fl, dispose);
	}
	return 0;
}
EXPORT_SYMBOL(lease_modify);

static bool past_time(unsigned long then)
{
	if (!then)
		/* 0 is a special value meaning "this never expires": */
		return false;
	return time_after(jiffies, then);
}

static void time_out_leases(struct inode *inode, struct list_head *dispose)
{
	struct file_lock_context *ctx = inode->i_flctx;
	struct file_lock *fl, *tmp;

	lockdep_assert_held(&ctx->flc_lock);

	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
		trace_time_out_leases(inode, fl);
		if (past_time(fl->fl_downgrade_time))
			lease_modify(fl, F_RDLCK, dispose);
		if (past_time(fl->fl_break_time))
			lease_modify(fl, F_UNLCK, dispose);
	}
}

static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
{
	bool rc;

	if (lease->fl_lmops->lm_breaker_owns_lease
			&& lease->fl_lmops->lm_breaker_owns_lease(lease))
		return false;
	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) {
		rc = false;
		goto trace;
	}
	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) {
		rc = false;
		goto trace;
	}

	rc = locks_conflict(breaker, lease);
trace:
	trace_leases_conflict(rc, lease, breaker);
	return rc;
}

static bool
any_leases_conflict(struct inode *inode, struct file_lock *breaker)
{
	struct file_lock_context *ctx = inode->i_flctx;
	struct file_lock *fl;

	lockdep_assert_held(&ctx->flc_lock);

	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
		if (leases_conflict(fl, breaker))
			return true;
	}
	return false;
}

/**
 *	__break_lease	-	revoke all outstanding leases on file
 *	@inode: the inode of the file to return
 *	@mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
 *	    break all leases
 *	@type: FL_LEASE: break leases and delegations; FL_DELEG: break
 *	    only delegations
 *
 *	break_lease (inlined for speed) has checked there already is at least
 *	some kind of lock (maybe a lease) on this file.  Leases are broken on
 *	a call to open() or truncate().  This function can sleep unless you
 *	specified %O_NONBLOCK to your open().
 */
int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
	int error = 0;
	struct file_lock_context *ctx;
	struct file_lock *new_fl, *fl, *tmp;
	unsigned long break_time;
	int want_write = (mode & O_ACCMODE) != O_RDONLY;
	LIST_HEAD(dispose);

	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
	if (IS_ERR(new_fl))
		return PTR_ERR(new_fl);
	new_fl->fl_flags = type;

	/* typically we will check that ctx is non-NULL before calling */
	ctx = locks_inode_context(inode);
	if (!ctx) {
		WARN_ON_ONCE(1);
		goto free_lock;
	}

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);

	time_out_leases(inode, &dispose);

	if (!any_leases_conflict(inode, new_fl))
		goto out;

	break_time = 0;
	if (lease_break_time > 0) {
		break_time = jiffies + lease_break_time * HZ;
		if (break_time == 0)
			break_time++;	/* so that 0 means no break time */
	}

	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
		if (!leases_conflict(fl, new_fl))
			continue;
		if (want_write) {
			if (fl->fl_flags & FL_UNLOCK_PENDING)
				continue;
			fl->fl_flags |= FL_UNLOCK_PENDING;
			fl->fl_break_time = break_time;
		} else {
			if (lease_breaking(fl))
				continue;
			fl->fl_flags |= FL_DOWNGRADE_PENDING;
			fl->fl_downgrade_time = break_time;
		}
		if (fl->fl_lmops->lm_break(fl))
			locks_delete_lock_ctx(fl, &dispose);
	}

	if (list_empty(&ctx->flc_lease))
		goto out;

	if (mode & O_NONBLOCK) {
		trace_break_lease_noblock(inode, new_fl);
		error = -EWOULDBLOCK;
		goto out;
	}

restart:
	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
	break_time = fl->fl_break_time;
	if (break_time != 0)
		break_time -= jiffies;
	if (break_time == 0)
		break_time++;
	locks_insert_block(fl, new_fl, leases_conflict);
	trace_break_lease_block(inode, new_fl);
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);

	locks_dispose_list(&dispose);
	error = wait_event_interruptible_timeout(new_fl->fl_wait,
					list_empty(&new_fl->fl_blocked_member),
					break_time);

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	trace_break_lease_unblock(inode, new_fl);
	locks_delete_block(new_fl);
	if (error >= 0) {
		/*
		 * Wait for the next conflicting lease that has not been
		 * broken yet
		 */
		if (error == 0)
			time_out_leases(inode, &dispose);
		if (any_leases_conflict(inode, new_fl))
			goto restart;
		error = 0;
	}
out:
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);
	locks_dispose_list(&dispose);
free_lock:
	locks_free_lock(new_fl);
	return error;
}
EXPORT_SYMBOL(__break_lease);

/**
 *	lease_get_mtime - update modified time of an inode with exclusive lease
 *	@inode: the inode
 *      @time:  pointer to a timespec which contains the last modified time
 *
 * This is to force NFS clients to flush their caches for files with
 * exclusive leases.  The justification is that if someone has an
 * exclusive lease, then they could be modifying it.
 */
void lease_get_mtime(struct inode *inode, struct timespec64 *time)
{
	bool has_lease = false;
	struct file_lock_context *ctx;
	struct file_lock *fl;

	ctx = locks_inode_context(inode);
	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
		spin_lock(&ctx->flc_lock);
		fl = list_first_entry_or_null(&ctx->flc_lease,
					      struct file_lock, fl_list);
		if (fl && (fl->fl_type == F_WRLCK))
			has_lease = true;
		spin_unlock(&ctx->flc_lock);
	}

	if (has_lease)
		*time = current_time(inode);
}
EXPORT_SYMBOL(lease_get_mtime);

/**
 *	fcntl_getlease - Enquire what lease is currently active
 *	@filp: the file
 *
 *	The value returned by this function will be one of
 *	(if no lease break is pending):
 *
 *	%F_RDLCK to indicate a shared lease is held.
 *
 *	%F_WRLCK to indicate an exclusive lease is held.
 *
 *	%F_UNLCK to indicate no lease is held.
 *
 *	(if a lease break is pending):
 *
 *	%F_RDLCK to indicate an exclusive lease needs to be
 *		changed to a shared lease (or removed).
 *
 *	%F_UNLCK to indicate the lease needs to be removed.
 *
 *	XXX: sfr & willy disagree over whether F_INPROGRESS
 *	should be returned to userspace.
 */
int fcntl_getlease(struct file *filp)
{
	struct file_lock *fl;
	struct inode *inode = file_inode(filp);
	struct file_lock_context *ctx;
	int type = F_UNLCK;
	LIST_HEAD(dispose);

	ctx = locks_inode_context(inode);
	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
		percpu_down_read(&file_rwsem);
		spin_lock(&ctx->flc_lock);
		time_out_leases(inode, &dispose);
		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
			if (fl->fl_file != filp)
				continue;
			type = target_leasetype(fl);
			break;
		}
		spin_unlock(&ctx->flc_lock);
		percpu_up_read(&file_rwsem);

		locks_dispose_list(&dispose);
	}
	return type;
}

/**
 * check_conflicting_open - see if the given file points to an inode that has
 *			    an existing open that would conflict with the
 *			    desired lease.
 * @filp:	file to check
 * @arg:	type of lease that we're trying to acquire
 * @flags:	current lock flags
 *
 * Check to see if there's an existing open fd on this file that would
 * conflict with the lease we're trying to set.
 */
static int
check_conflicting_open(struct file *filp, const int arg, int flags)
{
	struct inode *inode = file_inode(filp);
	int self_wcount = 0, self_rcount = 0;

	if (flags & FL_LAYOUT)
		return 0;
	if (flags & FL_DELEG)
		/* We leave these checks to the caller */
		return 0;

	if (arg == F_RDLCK)
		return inode_is_open_for_write(inode) ? -EAGAIN : 0;
	else if (arg != F_WRLCK)
		return 0;

	/*
	 * Make sure that only read/write count is from lease requestor.
	 * Note that this will result in denying write leases when i_writecount
	 * is negative, which is what we want.  (We shouldn't grant write leases
	 * on files open for execution.)
	 */
	if (filp->f_mode & FMODE_WRITE)
		self_wcount = 1;
	else if (filp->f_mode & FMODE_READ)
		self_rcount = 1;

	if (atomic_read(&inode->i_writecount) != self_wcount ||
	    atomic_read(&inode->i_readcount) != self_rcount)
		return -EAGAIN;

	return 0;
}

static int
generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **priv)
{
	struct file_lock *fl, *my_fl = NULL, *lease;
	struct inode *inode = file_inode(filp);
	struct file_lock_context *ctx;
	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
	int error;
	LIST_HEAD(dispose);

	lease = *flp;
	trace_generic_add_lease(inode, lease);

	/* Note that arg is never F_UNLCK here */
	ctx = locks_get_lock_context(inode, arg);
	if (!ctx)
		return -ENOMEM;

	/*
	 * In the delegation case we need mutual exclusion with
	 * a number of operations that take the i_mutex.  We trylock
	 * because delegations are an optional optimization, and if
	 * there's some chance of a conflict--we'd rather not
	 * bother, maybe that's a sign this just isn't a good file to
	 * hand out a delegation on.
	 */
	if (is_deleg && !inode_trylock(inode))
		return -EAGAIN;

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	time_out_leases(inode, &dispose);
	error = check_conflicting_open(filp, arg, lease->fl_flags);
	if (error)
		goto out;

	/*
	 * At this point, we know that if there is an exclusive
	 * lease on this file, then we hold it on this filp
	 * (otherwise our open of this file would have blocked).
	 * And if we are trying to acquire an exclusive lease,
	 * then the file is not open by anyone (including us)
	 * except for this filp.
	 */
	error = -EAGAIN;
	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
		if (fl->fl_file == filp &&
		    fl->fl_owner == lease->fl_owner) {
			my_fl = fl;
			continue;
		}

		/*
		 * No exclusive leases if someone else has a lease on
		 * this file:
		 */
		if (arg == F_WRLCK)
			goto out;
		/*
		 * Modifying our existing lease is OK, but no getting a
		 * new lease if someone else is opening for write:
		 */
		if (fl->fl_flags & FL_UNLOCK_PENDING)
			goto out;
	}

	if (my_fl != NULL) {
		lease = my_fl;
		error = lease->fl_lmops->lm_change(lease, arg, &dispose);
		if (error)
			goto out;
		goto out_setup;
	}

	error = -EINVAL;
	if (!leases_enable)
		goto out;

	locks_insert_lock_ctx(lease, &ctx->flc_lease);
	/*
	 * The check in break_lease() is lockless. It's possible for another
	 * open to race in after we did the earlier check for a conflicting
	 * open but before the lease was inserted. Check again for a
	 * conflicting open and cancel the lease if there is one.
	 *
	 * We also add a barrier here to ensure that the insertion of the lock
	 * precedes these checks.
	 */
	smp_mb();
	error = check_conflicting_open(filp, arg, lease->fl_flags);
	if (error) {
		locks_unlink_lock_ctx(lease);
		goto out;
	}

out_setup:
	if (lease->fl_lmops->lm_setup)
		lease->fl_lmops->lm_setup(lease, priv);
out:
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);
	locks_dispose_list(&dispose);
	if (is_deleg)
		inode_unlock(inode);
	if (!error && !my_fl)
		*flp = NULL;
	return error;
}

static int generic_delete_lease(struct file *filp, void *owner)
{
	int error = -EAGAIN;
	struct file_lock *fl, *victim = NULL;
	struct inode *inode = file_inode(filp);
	struct file_lock_context *ctx;
	LIST_HEAD(dispose);

	ctx = locks_inode_context(inode);
	if (!ctx) {
		trace_generic_delete_lease(inode, NULL);
		return error;
	}

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
		if (fl->fl_file == filp &&
		    fl->fl_owner == owner) {
			victim = fl;
			break;
		}
	}
	trace_generic_delete_lease(inode, victim);
	if (victim)
		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);
	locks_dispose_list(&dispose);
	return error;
}

/**
 *	generic_setlease	-	sets a lease on an open file
 *	@filp:	file pointer
 *	@arg:	type of lease to obtain
 *	@flp:	input - file_lock to use, output - file_lock inserted
 *	@priv:	private data for lm_setup (may be NULL if lm_setup
 *		doesn't require it)
 *
 *	The (input) flp->fl_lmops->lm_break function is required
 *	by break_lease().
 */
int generic_setlease(struct file *filp, int arg, struct file_lock **flp,
			void **priv)
{
	struct inode *inode = file_inode(filp);
	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
	int error;

	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
		return -EACCES;
	if (!S_ISREG(inode->i_mode))
		return -EINVAL;
	error = security_file_lock(filp, arg);
	if (error)
		return error;

	switch (arg) {
	case F_UNLCK:
		return generic_delete_lease(filp, *priv);
	case F_RDLCK:
	case F_WRLCK:
		if (!(*flp)->fl_lmops->lm_break) {
			WARN_ON_ONCE(1);
			return -ENOLCK;
		}

		return generic_add_lease(filp, arg, flp, priv);
	default:
		return -EINVAL;
	}
}
EXPORT_SYMBOL(generic_setlease);

/*
 * Kernel subsystems can register to be notified on any attempt to set
 * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd
 * to close files that it may have cached when there is an attempt to set a
 * conflicting lease.
 */
static struct srcu_notifier_head lease_notifier_chain;

static inline void
lease_notifier_chain_init(void)
{
	srcu_init_notifier_head(&lease_notifier_chain);
}

static inline void
setlease_notifier(int arg, struct file_lock *lease)
{
	if (arg != F_UNLCK)
		srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
}

int lease_register_notifier(struct notifier_block *nb)
{
	return srcu_notifier_chain_register(&lease_notifier_chain, nb);
}
EXPORT_SYMBOL_GPL(lease_register_notifier);

void lease_unregister_notifier(struct notifier_block *nb)
{
	srcu_notifier_chain_unregister(&lease_notifier_chain, nb);
}
EXPORT_SYMBOL_GPL(lease_unregister_notifier);

/**
 * vfs_setlease        -       sets a lease on an open file
 * @filp:	file pointer
 * @arg:	type of lease to obtain
 * @lease:	file_lock to use when adding a lease
 * @priv:	private info for lm_setup when adding a lease (may be
 *		NULL if lm_setup doesn't require it)
 *
 * Call this to establish a lease on the file. The "lease" argument is not
 * used for F_UNLCK requests and may be NULL. For commands that set or alter
 * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be
 * set; if not, this function will return -ENOLCK (and generate a scary-looking
 * stack trace).
 *
 * The "priv" pointer is passed directly to the lm_setup function as-is. It
 * may be NULL if the lm_setup operation doesn't require it.
 */
int
vfs_setlease(struct file *filp, int arg, struct file_lock **lease, void **priv)
{
	if (lease)
		setlease_notifier(arg, *lease);
	if (filp->f_op->setlease)
		return filp->f_op->setlease(filp, arg, lease, priv);
	else
		return generic_setlease(filp, arg, lease, priv);
}
EXPORT_SYMBOL_GPL(vfs_setlease);

static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
{
	struct file_lock *fl;
	struct fasync_struct *new;
	int error;

	fl = lease_alloc(filp, arg);
	if (IS_ERR(fl))
		return PTR_ERR(fl);

	new = fasync_alloc();
	if (!new) {
		locks_free_lock(fl);
		return -ENOMEM;
	}
	new->fa_fd = fd;

	error = vfs_setlease(filp, arg, &fl, (void **)&new);
	if (fl)
		locks_free_lock(fl);
	if (new)
		fasync_free(new);
	return error;
}

/**
 *	fcntl_setlease	-	sets a lease on an open file
 *	@fd: open file descriptor
 *	@filp: file pointer
 *	@arg: type of lease to obtain
 *
 *	Call this fcntl to establish a lease on the file.
 *	Note that you also need to call %F_SETSIG to
 *	receive a signal when the lease is broken.
 */
int fcntl_setlease(unsigned int fd, struct file *filp, int arg)
{
	if (arg == F_UNLCK)
		return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp);
	return do_fcntl_add_lease(fd, filp, arg);
}

/**
 * flock_lock_inode_wait - Apply a FLOCK-style lock to a file
 * @inode: inode of the file to apply to
 * @fl: The lock to be applied
 *
 * Apply a FLOCK style lock request to an inode.
 */
static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	int error;
	might_sleep();
	for (;;) {
		error = flock_lock_inode(inode, fl);
		if (error != FILE_LOCK_DEFERRED)
			break;
		error = wait_event_interruptible(fl->fl_wait,
				list_empty(&fl->fl_blocked_member));
		if (error)
			break;
	}
	locks_delete_block(fl);
	return error;
}

/**
 * locks_lock_inode_wait - Apply a lock to an inode
 * @inode: inode of the file to apply to
 * @fl: The lock to be applied
 *
 * Apply a POSIX or FLOCK style lock request to an inode.
 */
int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	int res = 0;
	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
		case FL_POSIX:
			res = posix_lock_inode_wait(inode, fl);
			break;
		case FL_FLOCK:
			res = flock_lock_inode_wait(inode, fl);
			break;
		default:
			BUG();
	}
	return res;
}
EXPORT_SYMBOL(locks_lock_inode_wait);

/**
 *	sys_flock: - flock() system call.
 *	@fd: the file descriptor to lock.
 *	@cmd: the type of lock to apply.
 *
 *	Apply a %FL_FLOCK style lock to an open file descriptor.
 *	The @cmd can be one of:
 *
 *	- %LOCK_SH -- a shared lock.
 *	- %LOCK_EX -- an exclusive lock.
 *	- %LOCK_UN -- remove an existing lock.
 *	- %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED)
 *
 *	%LOCK_MAND support has been removed from the kernel.
 */
SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
	int can_sleep, error, type;
	struct file_lock fl;
	struct fd f;

	/*
	 * LOCK_MAND locks were broken for a long time in that they never
	 * conflicted with one another and didn't prevent any sort of open,
	 * read or write activity.
	 *
	 * Just ignore these requests now, to preserve legacy behavior, but
	 * throw a warning to let people know that they don't actually work.
	 */
	if (cmd & LOCK_MAND) {
		pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid);
		return 0;
	}

	type = flock_translate_cmd(cmd & ~LOCK_NB);
	if (type < 0)
		return type;

	error = -EBADF;
	f = fdget(fd);
	if (!f.file)
		return error;

	if (type != F_UNLCK && !(f.file->f_mode & (FMODE_READ | FMODE_WRITE)))
		goto out_putf;

	flock_make_lock(f.file, &fl, type);

	error = security_file_lock(f.file, fl.fl_type);
	if (error)
		goto out_putf;

	can_sleep = !(cmd & LOCK_NB);
	if (can_sleep)
		fl.fl_flags |= FL_SLEEP;

	if (f.file->f_op->flock)
		error = f.file->f_op->flock(f.file,
					    (can_sleep) ? F_SETLKW : F_SETLK,
					    &fl);
	else
		error = locks_lock_file_wait(f.file, &fl);

	locks_release_private(&fl);
 out_putf:
	fdput(f);

	return error;
}

/**
 * vfs_test_lock - test file byte range lock
 * @filp: The file to test lock for
 * @fl: The lock to test; also used to hold result
 *
 * Returns -ERRNO on failure.  Indicates presence of conflicting lock by
 * setting conf->fl_type to something other than F_UNLCK.
 */
int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
	WARN_ON_ONCE(filp != fl->fl_file);
	if (filp->f_op->lock)
		return filp->f_op->lock(filp, F_GETLK, fl);
	posix_test_lock(filp, fl);
	return 0;
}
EXPORT_SYMBOL_GPL(vfs_test_lock);

/**
 * locks_translate_pid - translate a file_lock's fl_pid number into a namespace
 * @fl: The file_lock who's fl_pid should be translated
 * @ns: The namespace into which the pid should be translated
 *
 * Used to translate a fl_pid into a namespace virtual pid number
 */
static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
{
	pid_t vnr;
	struct pid *pid;

	if (IS_OFDLCK(fl))
		return -1;
	if (IS_REMOTELCK(fl))
		return fl->fl_pid;
	/*
	 * If the flock owner process is dead and its pid has been already
	 * freed, the translation below won't work, but we still want to show
	 * flock owner pid number in init pidns.
	 */
	if (ns == &init_pid_ns)
		return (pid_t)fl->fl_pid;

	rcu_read_lock();
	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
	vnr = pid_nr_ns(pid, ns);
	rcu_read_unlock();
	return vnr;
}

static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
{
	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
#if BITS_PER_LONG == 32
	/*
	 * Make sure we can represent the posix lock via
	 * legacy 32bit flock.
	 */
	if (fl->fl_start > OFFT_OFFSET_MAX)
		return -EOVERFLOW;
	if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX)
		return -EOVERFLOW;
#endif
	flock->l_start = fl->fl_start;
	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
		fl->fl_end - fl->fl_start + 1;
	flock->l_whence = 0;
	flock->l_type = fl->fl_type;
	return 0;
}

#if BITS_PER_LONG == 32
static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
{
	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
	flock->l_start = fl->fl_start;
	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
		fl->fl_end - fl->fl_start + 1;
	flock->l_whence = 0;
	flock->l_type = fl->fl_type;
}
#endif

/* Report the first existing lock that would conflict with l.
 * This implements the F_GETLK command of fcntl().
 */
int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
{
	struct file_lock *fl;
	int error;

	fl = locks_alloc_lock();
	if (fl == NULL)
		return -ENOMEM;
	error = -EINVAL;
	if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK
			&& flock->l_type != F_WRLCK)
		goto out;

	error = flock_to_posix_lock(filp, fl, flock);
	if (error)
		goto out;

	if (cmd == F_OFD_GETLK) {
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		fl->fl_flags |= FL_OFDLCK;
		fl->fl_owner = filp;
	}

	error = vfs_test_lock(filp, fl);
	if (error)
		goto out;

	flock->l_type = fl->fl_type;
	if (fl->fl_type != F_UNLCK) {
		error = posix_lock_to_flock(flock, fl);
		if (error)
			goto out;
	}
out:
	locks_free_lock(fl);
	return error;
}

/**
 * vfs_lock_file - file byte range lock
 * @filp: The file to apply the lock to
 * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.)
 * @fl: The lock to be applied
 * @conf: Place to return a copy of the conflicting lock, if found.
 *
 * A caller that doesn't care about the conflicting lock may pass NULL
 * as the final argument.
 *
 * If the filesystem defines a private ->lock() method, then @conf will
 * be left unchanged; so a caller that cares should initialize it to
 * some acceptable default.
 *
 * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX
 * locks, the ->lock() interface may return asynchronously, before the lock has
 * been granted or denied by the underlying filesystem, if (and only if)
 * lm_grant is set. Callers expecting ->lock() to return asynchronously
 * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if)
 * the request is for a blocking lock. When ->lock() does return asynchronously,
 * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock
 * request completes.
 * If the request is for non-blocking lock the file system should return
 * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine
 * with the result. If the request timed out the callback routine will return a
 * nonzero return code and the file system should release the lock. The file
 * system is also responsible to keep a corresponding posix lock when it
 * grants a lock so the VFS can find out which locks are locally held and do
 * the correct lock cleanup when required.
 * The underlying filesystem must not drop the kernel lock or call
 * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED
 * return code.
 */
int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
{
	WARN_ON_ONCE(filp != fl->fl_file);
	if (filp->f_op->lock)
		return filp->f_op->lock(filp, cmd, fl);
	else
		return posix_lock_file(filp, fl, conf);
}
EXPORT_SYMBOL_GPL(vfs_lock_file);

static int do_lock_file_wait(struct file *filp, unsigned int cmd,
			     struct file_lock *fl)
{
	int error;

	error = security_file_lock(filp, fl->fl_type);
	if (error)
		return error;

	for (;;) {
		error = vfs_lock_file(filp, cmd, fl, NULL);
		if (error != FILE_LOCK_DEFERRED)
			break;
		error = wait_event_interruptible(fl->fl_wait,
					list_empty(&fl->fl_blocked_member));
		if (error)
			break;
	}
	locks_delete_block(fl);

	return error;
}

/* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */
static int
check_fmode_for_setlk(struct file_lock *fl)
{
	switch (fl->fl_type) {
	case F_RDLCK:
		if (!(fl->fl_file->f_mode & FMODE_READ))
			return -EBADF;
		break;
	case F_WRLCK:
		if (!(fl->fl_file->f_mode & FMODE_WRITE))
			return -EBADF;
	}
	return 0;
}

/* Apply the lock described by l to an open file descriptor.
 * This implements both the F_SETLK and F_SETLKW commands of fcntl().
 */
int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
		struct flock *flock)
{
	struct file_lock *file_lock = locks_alloc_lock();
	struct inode *inode = file_inode(filp);
	struct file *f;
	int error;

	if (file_lock == NULL)
		return -ENOLCK;

	error = flock_to_posix_lock(filp, file_lock, flock);
	if (error)
		goto out;

	error = check_fmode_for_setlk(file_lock);
	if (error)
		goto out;

	/*
	 * If the cmd is requesting file-private locks, then set the
	 * FL_OFDLCK flag and override the owner.
	 */
	switch (cmd) {
	case F_OFD_SETLK:
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		cmd = F_SETLK;
		file_lock->fl_flags |= FL_OFDLCK;
		file_lock->fl_owner = filp;
		break;
	case F_OFD_SETLKW:
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		cmd = F_SETLKW;
		file_lock->fl_flags |= FL_OFDLCK;
		file_lock->fl_owner = filp;
		fallthrough;
	case F_SETLKW:
		file_lock->fl_flags |= FL_SLEEP;
	}

	error = do_lock_file_wait(filp, cmd, file_lock);

	/*
	 * Attempt to detect a close/fcntl race and recover by releasing the
	 * lock that was just acquired. There is no need to do that when we're
	 * unlocking though, or for OFD locks.
	 */
	if (!error && file_lock->fl_type != F_UNLCK &&
	    !(file_lock->fl_flags & FL_OFDLCK)) {
		struct files_struct *files = current->files;
		/*
		 * We need that spin_lock here - it prevents reordering between
		 * update of i_flctx->flc_posix and check for it done in
		 * close(). rcu_read_lock() wouldn't do.
		 */
		spin_lock(&files->file_lock);
		f = files_lookup_fd_locked(files, fd);
		spin_unlock(&files->file_lock);
		if (f != filp) {
			file_lock->fl_type = F_UNLCK;
			error = do_lock_file_wait(filp, cmd, file_lock);
			WARN_ON_ONCE(error);
			error = -EBADF;
		}
	}
out:
	trace_fcntl_setlk(inode, file_lock, error);
	locks_free_lock(file_lock);
	return error;
}

#if BITS_PER_LONG == 32
/* Report the first existing lock that would conflict with l.
 * This implements the F_GETLK command of fcntl().
 */
int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
{
	struct file_lock *fl;
	int error;

	fl = locks_alloc_lock();
	if (fl == NULL)
		return -ENOMEM;

	error = -EINVAL;
	if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK
			&& flock->l_type != F_WRLCK)
		goto out;

	error = flock64_to_posix_lock(filp, fl, flock);
	if (error)
		goto out;

	if (cmd == F_OFD_GETLK) {
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		fl->fl_flags |= FL_OFDLCK;
		fl->fl_owner = filp;
	}

	error = vfs_test_lock(filp, fl);
	if (error)
		goto out;

	flock->l_type = fl->fl_type;
	if (fl->fl_type != F_UNLCK)
		posix_lock_to_flock64(flock, fl);

out:
	locks_free_lock(fl);
	return error;
}

/* Apply the lock described by l to an open file descriptor.
 * This implements both the F_SETLK and F_SETLKW commands of fcntl().
 */
int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
		struct flock64 *flock)
{
	struct file_lock *file_lock = locks_alloc_lock();
	struct file *f;
	int error;

	if (file_lock == NULL)
		return -ENOLCK;

	error = flock64_to_posix_lock(filp, file_lock, flock);
	if (error)
		goto out;

	error = check_fmode_for_setlk(file_lock);
	if (error)
		goto out;

	/*
	 * If the cmd is requesting file-private locks, then set the
	 * FL_OFDLCK flag and override the owner.
	 */
	switch (cmd) {
	case F_OFD_SETLK:
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		cmd = F_SETLK64;
		file_lock->fl_flags |= FL_OFDLCK;
		file_lock->fl_owner = filp;
		break;
	case F_OFD_SETLKW:
		error = -EINVAL;
		if (flock->l_pid != 0)
			goto out;

		cmd = F_SETLKW64;
		file_lock->fl_flags |= FL_OFDLCK;
		file_lock->fl_owner = filp;
		fallthrough;
	case F_SETLKW64:
		file_lock->fl_flags |= FL_SLEEP;
	}

	error = do_lock_file_wait(filp, cmd, file_lock);

	/*
	 * Attempt to detect a close/fcntl race and recover by releasing the
	 * lock that was just acquired. There is no need to do that when we're
	 * unlocking though, or for OFD locks.
	 */
	if (!error && file_lock->fl_type != F_UNLCK &&
	    !(file_lock->fl_flags & FL_OFDLCK)) {
		struct files_struct *files = current->files;
		/*
		 * We need that spin_lock here - it prevents reordering between
		 * update of i_flctx->flc_posix and check for it done in
		 * close(). rcu_read_lock() wouldn't do.
		 */
		spin_lock(&files->file_lock);
		f = files_lookup_fd_locked(files, fd);
		spin_unlock(&files->file_lock);
		if (f != filp) {
			file_lock->fl_type = F_UNLCK;
			error = do_lock_file_wait(filp, cmd, file_lock);
			WARN_ON_ONCE(error);
			error = -EBADF;
		}
	}
out:
	locks_free_lock(file_lock);
	return error;
}
#endif /* BITS_PER_LONG == 32 */

/*
 * This function is called when the file is being removed
 * from the task's fd array.  POSIX locks belonging to this task
 * are deleted at this time.
 */
void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
	int error;
	struct inode *inode = file_inode(filp);
	struct file_lock lock;
	struct file_lock_context *ctx;

	/*
	 * If there are no locks held on this file, we don't need to call
	 * posix_lock_file().  Another process could be setting a lock on this
	 * file at the same time, but we wouldn't remove that lock anyway.
	 */
	ctx = locks_inode_context(inode);
	if (!ctx || list_empty(&ctx->flc_posix))
		return;

	locks_init_lock(&lock);
	lock.fl_type = F_UNLCK;
	lock.fl_flags = FL_POSIX | FL_CLOSE;
	lock.fl_start = 0;
	lock.fl_end = OFFSET_MAX;
	lock.fl_owner = owner;
	lock.fl_pid = current->tgid;
	lock.fl_file = filp;
	lock.fl_ops = NULL;
	lock.fl_lmops = NULL;

	error = vfs_lock_file(filp, F_SETLK, &lock, NULL);

	if (lock.fl_ops && lock.fl_ops->fl_release_private)
		lock.fl_ops->fl_release_private(&lock);
	trace_locks_remove_posix(inode, &lock, error);
}
EXPORT_SYMBOL(locks_remove_posix);

/* The i_flctx must be valid when calling into here */
static void
locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
{
	struct file_lock fl;
	struct inode *inode = file_inode(filp);

	if (list_empty(&flctx->flc_flock))
		return;

	flock_make_lock(filp, &fl, F_UNLCK);
	fl.fl_flags |= FL_CLOSE;

	if (filp->f_op->flock)
		filp->f_op->flock(filp, F_SETLKW, &fl);
	else
		flock_lock_inode(inode, &fl);

	if (fl.fl_ops && fl.fl_ops->fl_release_private)
		fl.fl_ops->fl_release_private(&fl);
}

/* The i_flctx must be valid when calling into here */
static void
locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
{
	struct file_lock *fl, *tmp;
	LIST_HEAD(dispose);

	if (list_empty(&ctx->flc_lease))
		return;

	percpu_down_read(&file_rwsem);
	spin_lock(&ctx->flc_lock);
	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
		if (filp == fl->fl_file)
			lease_modify(fl, F_UNLCK, &dispose);
	spin_unlock(&ctx->flc_lock);
	percpu_up_read(&file_rwsem);

	locks_dispose_list(&dispose);
}

/*
 * This function is called on the last close of an open file.
 */
void locks_remove_file(struct file *filp)
{
	struct file_lock_context *ctx;

	ctx = locks_inode_context(file_inode(filp));
	if (!ctx)
		return;

	/* remove any OFD locks */
	locks_remove_posix(filp, filp);

	/* remove flock locks */
	locks_remove_flock(filp, ctx);

	/* remove any leases */
	locks_remove_lease(filp, ctx);

	spin_lock(&ctx->flc_lock);
	locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX");
	locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK");
	locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE");
	spin_unlock(&ctx->flc_lock);
}

/**
 * vfs_cancel_lock - file byte range unblock lock
 * @filp: The file to apply the unblock to
 * @fl: The lock to be unblocked
 *
 * Used by lock managers to cancel blocked requests
 */
int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
	WARN_ON_ONCE(filp != fl->fl_file);
	if (filp->f_op->lock)
		return filp->f_op->lock(filp, F_CANCELLK, fl);
	return 0;
}
EXPORT_SYMBOL_GPL(vfs_cancel_lock);

/**
 * vfs_inode_has_locks - are any file locks held on @inode?
 * @inode: inode to check for locks
 *
 * Return true if there are any FL_POSIX or FL_FLOCK locks currently
 * set on @inode.
 */
bool vfs_inode_has_locks(struct inode *inode)
{
	struct file_lock_context *ctx;
	bool ret;

	ctx = locks_inode_context(inode);
	if (!ctx)
		return false;

	spin_lock(&ctx->flc_lock);
	ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock);
	spin_unlock(&ctx->flc_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(vfs_inode_has_locks);

#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

struct locks_iterator {
	int	li_cpu;
	loff_t	li_pos;
};

static void lock_get_status(struct seq_file *f, struct file_lock *fl,
			    loff_t id, char *pfx, int repeat)
{
	struct inode *inode = NULL;
	unsigned int fl_pid;
	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
	int type;

	fl_pid = locks_translate_pid(fl, proc_pidns);
	/*
	 * If lock owner is dead (and pid is freed) or not visible in current
	 * pidns, zero is shown as a pid value. Check lock info from
	 * init_pid_ns to get saved lock pid value.
	 */

	if (fl->fl_file != NULL)
		inode = file_inode(fl->fl_file);

	seq_printf(f, "%lld: ", id);

	if (repeat)
		seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);

	if (IS_POSIX(fl)) {
		if (fl->fl_flags & FL_ACCESS)
			seq_puts(f, "ACCESS");
		else if (IS_OFDLCK(fl))
			seq_puts(f, "OFDLCK");
		else
			seq_puts(f, "POSIX ");

		seq_printf(f, " %s ",
			     (inode == NULL) ? "*NOINODE*" : "ADVISORY ");
	} else if (IS_FLOCK(fl)) {
		seq_puts(f, "FLOCK  ADVISORY  ");
	} else if (IS_LEASE(fl)) {
		if (fl->fl_flags & FL_DELEG)
			seq_puts(f, "DELEG  ");
		else
			seq_puts(f, "LEASE  ");

		if (lease_breaking(fl))
			seq_puts(f, "BREAKING  ");
		else if (fl->fl_file)
			seq_puts(f, "ACTIVE    ");
		else
			seq_puts(f, "BREAKER   ");
	} else {
		seq_puts(f, "UNKNOWN UNKNOWN  ");
	}
	type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;

	seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
			     (type == F_RDLCK) ? "READ" : "UNLCK");
	if (inode) {
		/* userspace relies on this representation of dev_t */
		seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
				MAJOR(inode->i_sb->s_dev),
				MINOR(inode->i_sb->s_dev), inode->i_ino);
	} else {
		seq_printf(f, "%d <none>:0 ", fl_pid);
	}
	if (IS_POSIX(fl)) {
		if (fl->fl_end == OFFSET_MAX)
			seq_printf(f, "%Ld EOF\n", fl->fl_start);
		else
			seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end);
	} else {
		seq_puts(f, "0 EOF\n");
	}
}

static struct file_lock *get_next_blocked_member(struct file_lock *node)
{
	struct file_lock *tmp;

	/* NULL node or root node */
	if (node == NULL || node->fl_blocker == NULL)
		return NULL;

	/* Next member in the linked list could be itself */
	tmp = list_next_entry(node, fl_blocked_member);
	if (list_entry_is_head(tmp, &node->fl_blocker->fl_blocked_requests, fl_blocked_member)
		|| tmp == node) {
		return NULL;
	}

	return tmp;
}

static int locks_show(struct seq_file *f, void *v)
{
	struct locks_iterator *iter = f->private;
	struct file_lock *cur, *tmp;
	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
	int level = 0;

	cur = hlist_entry(v, struct file_lock, fl_link);

	if (locks_translate_pid(cur, proc_pidns) == 0)
		return 0;

	/* View this crossed linked list as a binary tree, the first member of fl_blocked_requests
	 * is the left child of current node, the next silibing in fl_blocked_member is the
	 * right child, we can alse get the parent of current node from fl_blocker, so this
	 * question becomes traversal of a binary tree
	 */
	while (cur != NULL) {
		if (level)
			lock_get_status(f, cur, iter->li_pos, "-> ", level);
		else
			lock_get_status(f, cur, iter->li_pos, "", level);

		if (!list_empty(&cur->fl_blocked_requests)) {
			/* Turn left */
			cur = list_first_entry_or_null(&cur->fl_blocked_requests,
				struct file_lock, fl_blocked_member);
			level++;
		} else {
			/* Turn right */
			tmp = get_next_blocked_member(cur);
			/* Fall back to parent node */
			while (tmp == NULL && cur->fl_blocker != NULL) {
				cur = cur->fl_blocker;
				level--;
				tmp = get_next_blocked_member(cur);
			}
			cur = tmp;
		}
	}

	return 0;
}

static void __show_fd_locks(struct seq_file *f,
			struct list_head *head, int *id,
			struct file *filp, struct files_struct *files)
{
	struct file_lock *fl;

	list_for_each_entry(fl, head, fl_list) {

		if (filp != fl->fl_file)
			continue;
		if (fl->fl_owner != files &&
		    fl->fl_owner != filp)
			continue;

		(*id)++;
		seq_puts(f, "lock:\t");
		lock_get_status(f, fl, *id, "", 0);
	}
}

void show_fd_locks(struct seq_file *f,
		  struct file *filp, struct files_struct *files)
{
	struct inode *inode = file_inode(filp);
	struct file_lock_context *ctx;
	int id = 0;

	ctx = locks_inode_context(inode);
	if (!ctx)
		return;

	spin_lock(&ctx->flc_lock);
	__show_fd_locks(f, &ctx->flc_flock, &id, filp, files);
	__show_fd_locks(f, &ctx->flc_posix, &id, filp, files);
	__show_fd_locks(f, &ctx->flc_lease, &id, filp, files);
	spin_unlock(&ctx->flc_lock);
}

static void *locks_start(struct seq_file *f, loff_t *pos)
	__acquires(&blocked_lock_lock)
{
	struct locks_iterator *iter = f->private;

	iter->li_pos = *pos + 1;
	percpu_down_write(&file_rwsem);
	spin_lock(&blocked_lock_lock);
	return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos);
}

static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
{
	struct locks_iterator *iter = f->private;

	++iter->li_pos;
	return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos);
}

static void locks_stop(struct seq_file *f, void *v)
	__releases(&blocked_lock_lock)
{
	spin_unlock(&blocked_lock_lock);
	percpu_up_write(&file_rwsem);
}

static const struct seq_operations locks_seq_operations = {
	.start	= locks_start,
	.next	= locks_next,
	.stop	= locks_stop,
	.show	= locks_show,
};

static int __init proc_locks_init(void)
{
	proc_create_seq_private("locks", 0, NULL, &locks_seq_operations,
			sizeof(struct locks_iterator), NULL);
	return 0;
}
fs_initcall(proc_locks_init);
#endif

static int __init filelock_init(void)
{
	int i;

	flctx_cache = kmem_cache_create("file_lock_ctx",
			sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);

	filelock_cache = kmem_cache_create("file_lock_cache",
			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);

	for_each_possible_cpu(i) {
		struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);

		spin_lock_init(&fll->lock);
		INIT_HLIST_HEAD(&fll->hlist);
	}

	lease_notifier_chain_init();
	return 0;
}
core_initcall(filelock_init);