summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_inode.c
blob: 64f5f9a440aedbcac894687130d6ef4d286043f1 (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
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include <linux/iversion.h>

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_attr.h"
#include "xfs_trans_space.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"

kmem_zone_t *xfs_inode_zone;

/*
 * Used in xfs_itruncate_extents().  This is the maximum number of extents
 * freed from a file in a single transaction.
 */
#define	XFS_ITRUNC_MAX_EXTENTS	2

STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);

/*
 * helper function to extract extent size hint from inode
 */
xfs_extlen_t
xfs_get_extsz_hint(
	struct xfs_inode	*ip)
{
	/*
	 * No point in aligning allocations if we need to COW to actually
	 * write to them.
	 */
	if (xfs_is_always_cow_inode(ip))
		return 0;
	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
		return ip->i_d.di_extsize;
	if (XFS_IS_REALTIME_INODE(ip))
		return ip->i_mount->m_sb.sb_rextsize;
	return 0;
}

/*
 * Helper function to extract CoW extent size hint from inode.
 * Between the extent size hint and the CoW extent size hint, we
 * return the greater of the two.  If the value is zero (automatic),
 * use the default size.
 */
xfs_extlen_t
xfs_get_cowextsz_hint(
	struct xfs_inode	*ip)
{
	xfs_extlen_t		a, b;

	a = 0;
	if (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
		a = ip->i_d.di_cowextsize;
	b = xfs_get_extsz_hint(ip);

	a = max(a, b);
	if (a == 0)
		return XFS_DEFAULT_COWEXTSZ_HINT;
	return a;
}

/*
 * These two are wrapper routines around the xfs_ilock() routine used to
 * centralize some grungy code.  They are used in places that wish to lock the
 * inode solely for reading the extents.  The reason these places can't just
 * call xfs_ilock(ip, XFS_ILOCK_SHARED) is that the inode lock also guards to
 * bringing in of the extents from disk for a file in b-tree format.  If the
 * inode is in b-tree format, then we need to lock the inode exclusively until
 * the extents are read in.  Locking it exclusively all the time would limit
 * our parallelism unnecessarily, though.  What we do instead is check to see
 * if the extents have been read in yet, and only lock the inode exclusively
 * if they have not.
 *
 * The functions return a value which should be given to the corresponding
 * xfs_iunlock() call.
 */
uint
xfs_ilock_data_map_shared(
	struct xfs_inode	*ip)
{
	uint			lock_mode = XFS_ILOCK_SHARED;

	if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE &&
	    (ip->i_df.if_flags & XFS_IFEXTENTS) == 0)
		lock_mode = XFS_ILOCK_EXCL;
	xfs_ilock(ip, lock_mode);
	return lock_mode;
}

uint
xfs_ilock_attr_map_shared(
	struct xfs_inode	*ip)
{
	uint			lock_mode = XFS_ILOCK_SHARED;

	if (ip->i_afp &&
	    ip->i_afp->if_format == XFS_DINODE_FMT_BTREE &&
	    (ip->i_afp->if_flags & XFS_IFEXTENTS) == 0)
		lock_mode = XFS_ILOCK_EXCL;
	xfs_ilock(ip, lock_mode);
	return lock_mode;
}

/*
 * In addition to i_rwsem in the VFS inode, the xfs inode contains 2
 * multi-reader locks: i_mmap_lock and the i_lock.  This routine allows
 * various combinations of the locks to be obtained.
 *
 * The 3 locks should always be ordered so that the IO lock is obtained first,
 * the mmap lock second and the ilock last in order to prevent deadlock.
 *
 * Basic locking order:
 *
 * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
 *
 * mmap_sem locking order:
 *
 * i_rwsem -> page lock -> mmap_sem
 * mmap_sem -> i_mmap_lock -> page_lock
 *
 * The difference in mmap_sem locking order mean that we cannot hold the
 * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
 * fault in pages during copy in/out (for buffered IO) or require the mmap_sem
 * in get_user_pages() to map the user pages into the kernel address space for
 * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
 * page faults already hold the mmap_sem.
 *
 * Hence to serialise fully against both syscall and mmap based IO, we need to
 * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
 * taken in places where we need to invalidate the page cache in a race
 * free manner (e.g. truncate, hole punch and other extent manipulation
 * functions).
 */
void
xfs_ilock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	trace_xfs_ilock(ip, lock_flags, _RET_IP_);

	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
	       (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);

	if (lock_flags & XFS_IOLOCK_EXCL) {
		down_write_nested(&VFS_I(ip)->i_rwsem,
				  XFS_IOLOCK_DEP(lock_flags));
	} else if (lock_flags & XFS_IOLOCK_SHARED) {
		down_read_nested(&VFS_I(ip)->i_rwsem,
				 XFS_IOLOCK_DEP(lock_flags));
	}

	if (lock_flags & XFS_MMAPLOCK_EXCL)
		mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
	else if (lock_flags & XFS_MMAPLOCK_SHARED)
		mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));

	if (lock_flags & XFS_ILOCK_EXCL)
		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
	else if (lock_flags & XFS_ILOCK_SHARED)
		mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
}

/*
 * This is just like xfs_ilock(), except that the caller
 * is guaranteed not to sleep.  It returns 1 if it gets
 * the requested locks and 0 otherwise.  If the IO lock is
 * obtained but the inode lock cannot be, then the IO lock
 * is dropped before returning.
 *
 * ip -- the inode being locked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be locked.  See the comment for xfs_ilock() for a list
 *	 of valid values.
 */
int
xfs_ilock_nowait(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	trace_xfs_ilock_nowait(ip, lock_flags, _RET_IP_);

	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
	       (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);

	if (lock_flags & XFS_IOLOCK_EXCL) {
		if (!down_write_trylock(&VFS_I(ip)->i_rwsem))
			goto out;
	} else if (lock_flags & XFS_IOLOCK_SHARED) {
		if (!down_read_trylock(&VFS_I(ip)->i_rwsem))
			goto out;
	}

	if (lock_flags & XFS_MMAPLOCK_EXCL) {
		if (!mrtryupdate(&ip->i_mmaplock))
			goto out_undo_iolock;
	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
		if (!mrtryaccess(&ip->i_mmaplock))
			goto out_undo_iolock;
	}

	if (lock_flags & XFS_ILOCK_EXCL) {
		if (!mrtryupdate(&ip->i_lock))
			goto out_undo_mmaplock;
	} else if (lock_flags & XFS_ILOCK_SHARED) {
		if (!mrtryaccess(&ip->i_lock))
			goto out_undo_mmaplock;
	}
	return 1;

out_undo_mmaplock:
	if (lock_flags & XFS_MMAPLOCK_EXCL)
		mrunlock_excl(&ip->i_mmaplock);
	else if (lock_flags & XFS_MMAPLOCK_SHARED)
		mrunlock_shared(&ip->i_mmaplock);
out_undo_iolock:
	if (lock_flags & XFS_IOLOCK_EXCL)
		up_write(&VFS_I(ip)->i_rwsem);
	else if (lock_flags & XFS_IOLOCK_SHARED)
		up_read(&VFS_I(ip)->i_rwsem);
out:
	return 0;
}

/*
 * xfs_iunlock() is used to drop the inode locks acquired with
 * xfs_ilock() and xfs_ilock_nowait().  The caller must pass
 * in the flags given to xfs_ilock() or xfs_ilock_nowait() so
 * that we know which locks to drop.
 *
 * ip -- the inode being unlocked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be unlocked.  See the comment for xfs_ilock() for a list
 *	 of valid values for this parameter.
 *
 */
void
xfs_iunlock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) !=
	       (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
	ASSERT(lock_flags != 0);

	if (lock_flags & XFS_IOLOCK_EXCL)
		up_write(&VFS_I(ip)->i_rwsem);
	else if (lock_flags & XFS_IOLOCK_SHARED)
		up_read(&VFS_I(ip)->i_rwsem);

	if (lock_flags & XFS_MMAPLOCK_EXCL)
		mrunlock_excl(&ip->i_mmaplock);
	else if (lock_flags & XFS_MMAPLOCK_SHARED)
		mrunlock_shared(&ip->i_mmaplock);

	if (lock_flags & XFS_ILOCK_EXCL)
		mrunlock_excl(&ip->i_lock);
	else if (lock_flags & XFS_ILOCK_SHARED)
		mrunlock_shared(&ip->i_lock);

	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
}

/*
 * give up write locks.  the i/o lock cannot be held nested
 * if it is being demoted.
 */
void
xfs_ilock_demote(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL));
	ASSERT((lock_flags &
		~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);

	if (lock_flags & XFS_ILOCK_EXCL)
		mrdemote(&ip->i_lock);
	if (lock_flags & XFS_MMAPLOCK_EXCL)
		mrdemote(&ip->i_mmaplock);
	if (lock_flags & XFS_IOLOCK_EXCL)
		downgrade_write(&VFS_I(ip)->i_rwsem);

	trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_);
}

#if defined(DEBUG) || defined(XFS_WARN)
int
xfs_isilocked(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
		if (!(lock_flags & XFS_ILOCK_SHARED))
			return !!ip->i_lock.mr_writer;
		return rwsem_is_locked(&ip->i_lock.mr_lock);
	}

	if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
		if (!(lock_flags & XFS_MMAPLOCK_SHARED))
			return !!ip->i_mmaplock.mr_writer;
		return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
	}

	if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
		if (!(lock_flags & XFS_IOLOCK_SHARED))
			return !debug_locks ||
				lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0);
		return rwsem_is_locked(&VFS_I(ip)->i_rwsem);
	}

	ASSERT(0);
	return 0;
}
#endif

/*
 * xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when
 * DEBUG or XFS_WARN is set. And MAX_LOCKDEP_SUBCLASSES is then only defined
 * when CONFIG_LOCKDEP is set. Hence the complex define below to avoid build
 * errors and warnings.
 */
#if (defined(DEBUG) || defined(XFS_WARN)) && defined(CONFIG_LOCKDEP)
static bool
xfs_lockdep_subclass_ok(
	int subclass)
{
	return subclass < MAX_LOCKDEP_SUBCLASSES;
}
#else
#define xfs_lockdep_subclass_ok(subclass)	(true)
#endif

/*
 * Bump the subclass so xfs_lock_inodes() acquires each lock with a different
 * value. This can be called for any type of inode lock combination, including
 * parent locking. Care must be taken to ensure we don't overrun the subclass
 * storage fields in the class mask we build.
 */
static inline int
xfs_lock_inumorder(int lock_mode, int subclass)
{
	int	class = 0;

	ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP |
			      XFS_ILOCK_RTSUM)));
	ASSERT(xfs_lockdep_subclass_ok(subclass));

	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) {
		ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS);
		class += subclass << XFS_IOLOCK_SHIFT;
	}

	if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) {
		ASSERT(subclass <= XFS_MMAPLOCK_MAX_SUBCLASS);
		class += subclass << XFS_MMAPLOCK_SHIFT;
	}

	if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) {
		ASSERT(subclass <= XFS_ILOCK_MAX_SUBCLASS);
		class += subclass << XFS_ILOCK_SHIFT;
	}

	return (lock_mode & ~XFS_LOCK_SUBCLASS_MASK) | class;
}

/*
 * The following routine will lock n inodes in exclusive mode.  We assume the
 * caller calls us with the inodes in i_ino order.
 *
 * We need to detect deadlock where an inode that we lock is in the AIL and we
 * start waiting for another inode that is locked by a thread in a long running
 * transaction (such as truncate). This can result in deadlock since the long
 * running trans might need to wait for the inode we just locked in order to
 * push the tail and free space in the log.
 *
 * xfs_lock_inodes() can only be used to lock one type of lock at a time -
 * the iolock, the mmaplock or the ilock, but not more than one at a time. If we
 * lock more than one at a time, lockdep will report false positives saying we
 * have violated locking orders.
 */
static void
xfs_lock_inodes(
	struct xfs_inode	**ips,
	int			inodes,
	uint			lock_mode)
{
	int			attempts = 0, i, j, try_lock;
	struct xfs_log_item	*lp;

	/*
	 * Currently supports between 2 and 5 inodes with exclusive locking.  We
	 * support an arbitrary depth of locking here, but absolute limits on
	 * inodes depend on the the type of locking and the limits placed by
	 * lockdep annotations in xfs_lock_inumorder.  These are all checked by
	 * the asserts.
	 */
	ASSERT(ips && inodes >= 2 && inodes <= 5);
	ASSERT(lock_mode & (XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL |
			    XFS_ILOCK_EXCL));
	ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED |
			      XFS_ILOCK_SHARED)));
	ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) ||
		inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1);
	ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
		inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);

	if (lock_mode & XFS_IOLOCK_EXCL) {
		ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
	} else if (lock_mode & XFS_MMAPLOCK_EXCL)
		ASSERT(!(lock_mode & XFS_ILOCK_EXCL));

	try_lock = 0;
	i = 0;
again:
	for (; i < inodes; i++) {
		ASSERT(ips[i]);

		if (i && (ips[i] == ips[i - 1]))	/* Already locked */
			continue;

		/*
		 * If try_lock is not set yet, make sure all locked inodes are
		 * not in the AIL.  If any are, set try_lock to be used later.
		 */
		if (!try_lock) {
			for (j = (i - 1); j >= 0 && !try_lock; j--) {
				lp = &ips[j]->i_itemp->ili_item;
				if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags))
					try_lock++;
			}
		}

		/*
		 * If any of the previous locks we have locked is in the AIL,
		 * we must TRY to get the second and subsequent locks. If
		 * we can't get any, we must release all we have
		 * and try again.
		 */
		if (!try_lock) {
			xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
			continue;
		}

		/* try_lock means we have an inode locked that is in the AIL. */
		ASSERT(i != 0);
		if (xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i)))
			continue;

		/*
		 * Unlock all previous guys and try again.  xfs_iunlock will try
		 * to push the tail if the inode is in the AIL.
		 */
		attempts++;
		for (j = i - 1; j >= 0; j--) {
			/*
			 * Check to see if we've already unlocked this one.  Not
			 * the first one going back, and the inode ptr is the
			 * same.
			 */
			if (j != (i - 1) && ips[j] == ips[j + 1])
				continue;

			xfs_iunlock(ips[j], lock_mode);
		}

		if ((attempts % 5) == 0) {
			delay(1); /* Don't just spin the CPU */
		}
		i = 0;
		try_lock = 0;
		goto again;
	}
}

/*
 * xfs_lock_two_inodes() can only be used to lock one type of lock at a time -
 * the mmaplock or the ilock, but not more than one type at a time. If we lock
 * more than one at a time, lockdep will report false positives saying we have
 * violated locking orders.  The iolock must be double-locked separately since
 * we use i_rwsem for that.  We now support taking one lock EXCL and the other
 * SHARED.
 */
void
xfs_lock_two_inodes(
	struct xfs_inode	*ip0,
	uint			ip0_mode,
	struct xfs_inode	*ip1,
	uint			ip1_mode)
{
	struct xfs_inode	*temp;
	uint			mode_temp;
	int			attempts = 0;
	struct xfs_log_item	*lp;

	ASSERT(hweight32(ip0_mode) == 1);
	ASSERT(hweight32(ip1_mode) == 1);
	ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
	ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));

	ASSERT(ip0->i_ino != ip1->i_ino);

	if (ip0->i_ino > ip1->i_ino) {
		temp = ip0;
		ip0 = ip1;
		ip1 = temp;
		mode_temp = ip0_mode;
		ip0_mode = ip1_mode;
		ip1_mode = mode_temp;
	}

 again:
	xfs_ilock(ip0, xfs_lock_inumorder(ip0_mode, 0));

	/*
	 * If the first lock we have locked is in the AIL, we must TRY to get
	 * the second lock. If we can't get it, we must release the first one
	 * and try again.
	 */
	lp = &ip0->i_itemp->ili_item;
	if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
		if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
			xfs_iunlock(ip0, ip0_mode);
			if ((++attempts % 5) == 0)
				delay(1); /* Don't just spin the CPU */
			goto again;
		}
	} else {
		xfs_ilock(ip1, xfs_lock_inumorder(ip1_mode, 1));
	}
}

void
__xfs_iflock(
	struct xfs_inode	*ip)
{
	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);

	do {
		prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
		if (xfs_isiflocked(ip))
			io_schedule();
	} while (!xfs_iflock_nowait(ip));

	finish_wait(wq, &wait.wq_entry);
}

STATIC uint
_xfs_dic2xflags(
	uint16_t		di_flags,
	uint64_t		di_flags2,
	bool			has_attr)
{
	uint			flags = 0;

	if (di_flags & XFS_DIFLAG_ANY) {
		if (di_flags & XFS_DIFLAG_REALTIME)
			flags |= FS_XFLAG_REALTIME;
		if (di_flags & XFS_DIFLAG_PREALLOC)
			flags |= FS_XFLAG_PREALLOC;
		if (di_flags & XFS_DIFLAG_IMMUTABLE)
			flags |= FS_XFLAG_IMMUTABLE;
		if (di_flags & XFS_DIFLAG_APPEND)
			flags |= FS_XFLAG_APPEND;
		if (di_flags & XFS_DIFLAG_SYNC)
			flags |= FS_XFLAG_SYNC;
		if (di_flags & XFS_DIFLAG_NOATIME)
			flags |= FS_XFLAG_NOATIME;
		if (di_flags & XFS_DIFLAG_NODUMP)
			flags |= FS_XFLAG_NODUMP;
		if (di_flags & XFS_DIFLAG_RTINHERIT)
			flags |= FS_XFLAG_RTINHERIT;
		if (di_flags & XFS_DIFLAG_PROJINHERIT)
			flags |= FS_XFLAG_PROJINHERIT;
		if (di_flags & XFS_DIFLAG_NOSYMLINKS)
			flags |= FS_XFLAG_NOSYMLINKS;
		if (di_flags & XFS_DIFLAG_EXTSIZE)
			flags |= FS_XFLAG_EXTSIZE;
		if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
			flags |= FS_XFLAG_EXTSZINHERIT;
		if (di_flags & XFS_DIFLAG_NODEFRAG)
			flags |= FS_XFLAG_NODEFRAG;
		if (di_flags & XFS_DIFLAG_FILESTREAM)
			flags |= FS_XFLAG_FILESTREAM;
	}

	if (di_flags2 & XFS_DIFLAG2_ANY) {
		if (di_flags2 & XFS_DIFLAG2_DAX)
			flags |= FS_XFLAG_DAX;
		if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
			flags |= FS_XFLAG_COWEXTSIZE;
	}

	if (has_attr)
		flags |= FS_XFLAG_HASATTR;

	return flags;
}

uint
xfs_ip2xflags(
	struct xfs_inode	*ip)
{
	struct xfs_icdinode	*dic = &ip->i_d;

	return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
}

/*
 * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
 * is allowed, otherwise it has to be an exact match. If a CI match is found,
 * ci_name->name will point to a the actual name (caller must free) or
 * will be set to NULL if an exact match is found.
 */
int
xfs_lookup(
	xfs_inode_t		*dp,
	struct xfs_name		*name,
	xfs_inode_t		**ipp,
	struct xfs_name		*ci_name)
{
	xfs_ino_t		inum;
	int			error;

	trace_xfs_lookup(dp, name);

	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
		return -EIO;

	error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
	if (error)
		goto out_unlock;

	error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
	if (error)
		goto out_free_name;

	return 0;

out_free_name:
	if (ci_name)
		kmem_free(ci_name->name);
out_unlock:
	*ipp = NULL;
	return error;
}

/*
 * Allocate an inode on disk and return a copy of its in-core version.
 * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
 * appropriately within the inode.  The uid and gid for the inode are
 * set according to the contents of the given cred structure.
 *
 * Use xfs_dialloc() to allocate the on-disk inode. If xfs_dialloc()
 * has a free inode available, call xfs_iget() to obtain the in-core
 * version of the allocated inode.  Finally, fill in the inode and
 * log its initial contents.  In this case, ialloc_context would be
 * set to NULL.
 *
 * If xfs_dialloc() does not have an available inode, it will replenish
 * its supply by doing an allocation. Since we can only do one
 * allocation within a transaction without deadlocks, we must commit
 * the current transaction before returning the inode itself.
 * In this case, therefore, we will set ialloc_context and return.
 * The caller should then commit the current transaction, start a new
 * transaction, and call xfs_ialloc() again to actually get the inode.
 *
 * To ensure that some other process does not grab the inode that
 * was allocated during the first call to xfs_ialloc(), this routine
 * also returns the [locked] bp pointing to the head of the freelist
 * as ialloc_context.  The caller should hold this buffer across
 * the commit and pass it back into this routine on the second call.
 *
 * If we are allocating quota inodes, we do not have a parent inode
 * to attach to or associate with (i.e. pip == NULL) because they
 * are not linked into the directory structure - they are attached
 * directly to the superblock - and so have no parent.
 */
static int
xfs_ialloc(
	xfs_trans_t	*tp,
	xfs_inode_t	*pip,
	umode_t		mode,
	xfs_nlink_t	nlink,
	dev_t		rdev,
	prid_t		prid,
	xfs_buf_t	**ialloc_context,
	xfs_inode_t	**ipp)
{
	struct xfs_mount *mp = tp->t_mountp;
	xfs_ino_t	ino;
	xfs_inode_t	*ip;
	uint		flags;
	int		error;
	struct timespec64 tv;
	struct inode	*inode;

	/*
	 * Call the space management code to pick
	 * the on-disk inode to be allocated.
	 */
	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode,
			    ialloc_context, &ino);
	if (error)
		return error;
	if (*ialloc_context || ino == NULLFSINO) {
		*ipp = NULL;
		return 0;
	}
	ASSERT(*ialloc_context == NULL);

	/*
	 * Protect against obviously corrupt allocation btree records. Later
	 * xfs_iget checks will catch re-allocation of other active in-memory
	 * and on-disk inodes. If we don't catch reallocating the parent inode
	 * here we will deadlock in xfs_iget() so we have to do these checks
	 * first.
	 */
	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
		return -EFSCORRUPTED;
	}

	/*
	 * Get the in-core inode with the lock held exclusively.
	 * This is because we're setting fields here we need
	 * to prevent others from looking at until we're done.
	 */
	error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE,
			 XFS_ILOCK_EXCL, &ip);
	if (error)
		return error;
	ASSERT(ip != NULL);
	inode = VFS_I(ip);
	inode->i_mode = mode;
	set_nlink(inode, nlink);
	inode->i_uid = current_fsuid();
	inode->i_rdev = rdev;
	ip->i_d.di_projid = prid;

	if (pip && XFS_INHERIT_GID(pip)) {
		inode->i_gid = VFS_I(pip)->i_gid;
		if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
			inode->i_mode |= S_ISGID;
	} else {
		inode->i_gid = current_fsgid();
	}

	/*
	 * If the group ID of the new file does not match the effective group
	 * ID or one of the supplementary group IDs, the S_ISGID bit is cleared
	 * (and only if the irix_sgid_inherit compatibility variable is set).
	 */
	if (irix_sgid_inherit &&
	    (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
		inode->i_mode &= ~S_ISGID;

	ip->i_d.di_size = 0;
	ip->i_df.if_nextents = 0;
	ASSERT(ip->i_d.di_nblocks == 0);

	tv = current_time(inode);
	inode->i_mtime = tv;
	inode->i_atime = tv;
	inode->i_ctime = tv;

	ip->i_d.di_extsize = 0;
	ip->i_d.di_dmevmask = 0;
	ip->i_d.di_dmstate = 0;
	ip->i_d.di_flags = 0;

	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
		inode_set_iversion(inode, 1);
		ip->i_d.di_flags2 = 0;
		ip->i_d.di_cowextsize = 0;
		ip->i_d.di_crtime = tv;
	}

	flags = XFS_ILOG_CORE;
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		ip->i_df.if_format = XFS_DINODE_FMT_DEV;
		ip->i_df.if_flags = 0;
		flags |= XFS_ILOG_DEV;
		break;
	case S_IFREG:
	case S_IFDIR:
		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
			uint		di_flags = 0;

			if (S_ISDIR(mode)) {
				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
					di_flags |= XFS_DIFLAG_RTINHERIT;
				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
					di_flags |= XFS_DIFLAG_EXTSZINHERIT;
					ip->i_d.di_extsize = pip->i_d.di_extsize;
				}
				if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
					di_flags |= XFS_DIFLAG_PROJINHERIT;
			} else if (S_ISREG(mode)) {
				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
					di_flags |= XFS_DIFLAG_REALTIME;
				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
					di_flags |= XFS_DIFLAG_EXTSIZE;
					ip->i_d.di_extsize = pip->i_d.di_extsize;
				}
			}
			if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
			    xfs_inherit_noatime)
				di_flags |= XFS_DIFLAG_NOATIME;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
			    xfs_inherit_nodump)
				di_flags |= XFS_DIFLAG_NODUMP;
			if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
			    xfs_inherit_sync)
				di_flags |= XFS_DIFLAG_SYNC;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
			    xfs_inherit_nosymlinks)
				di_flags |= XFS_DIFLAG_NOSYMLINKS;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
			    xfs_inherit_nodefrag)
				di_flags |= XFS_DIFLAG_NODEFRAG;
			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
				di_flags |= XFS_DIFLAG_FILESTREAM;

			ip->i_d.di_flags |= di_flags;
		}
		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) {
			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
			}
			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
				ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
		}
		/* FALLTHROUGH */
	case S_IFLNK:
		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
		ip->i_df.if_flags = XFS_IFEXTENTS;
		ip->i_df.if_bytes = 0;
		ip->i_df.if_u1.if_root = NULL;
		break;
	default:
		ASSERT(0);
	}

	/*
	 * Log the new values stuffed into the inode.
	 */
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_log_inode(tp, ip, flags);

	/* now that we have an i_mode we can setup the inode structure */
	xfs_setup_inode(ip);

	*ipp = ip;
	return 0;
}

/*
 * Allocates a new inode from disk and return a pointer to the
 * incore copy. This routine will internally commit the current
 * transaction and allocate a new one if the Space Manager needed
 * to do an allocation to replenish the inode free-list.
 *
 * This routine is designed to be called from xfs_create and
 * xfs_create_dir.
 *
 */
int
xfs_dir_ialloc(
	xfs_trans_t	**tpp,		/* input: current transaction;
					   output: may be a new transaction. */
	xfs_inode_t	*dp,		/* directory within whose allocate
					   the inode. */
	umode_t		mode,
	xfs_nlink_t	nlink,
	dev_t		rdev,
	prid_t		prid,		/* project id */
	xfs_inode_t	**ipp)		/* pointer to inode; it will be
					   locked. */
{
	xfs_trans_t	*tp;
	xfs_inode_t	*ip;
	xfs_buf_t	*ialloc_context = NULL;
	int		code;
	void		*dqinfo;
	uint		tflags;

	tp = *tpp;
	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);

	/*
	 * xfs_ialloc will return a pointer to an incore inode if
	 * the Space Manager has an available inode on the free
	 * list. Otherwise, it will do an allocation and replenish
	 * the freelist.  Since we can only do one allocation per
	 * transaction without deadlocks, we will need to commit the
	 * current transaction and start a new one.  We will then
	 * need to call xfs_ialloc again to get the inode.
	 *
	 * If xfs_ialloc did an allocation to replenish the freelist,
	 * it returns the bp containing the head of the freelist as
	 * ialloc_context. We will hold a lock on it across the
	 * transaction commit so that no other process can steal
	 * the inode(s) that we've just allocated.
	 */
	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context,
			&ip);

	/*
	 * Return an error if we were unable to allocate a new inode.
	 * This should only happen if we run out of space on disk or
	 * encounter a disk error.
	 */
	if (code) {
		*ipp = NULL;
		return code;
	}
	if (!ialloc_context && !ip) {
		*ipp = NULL;
		return -ENOSPC;
	}

	/*
	 * If the AGI buffer is non-NULL, then we were unable to get an
	 * inode in one operation.  We need to commit the current
	 * transaction and call xfs_ialloc() again.  It is guaranteed
	 * to succeed the second time.
	 */
	if (ialloc_context) {
		/*
		 * Normally, xfs_trans_commit releases all the locks.
		 * We call bhold to hang on to the ialloc_context across
		 * the commit.  Holding this buffer prevents any other
		 * processes from doing any allocations in this
		 * allocation group.
		 */
		xfs_trans_bhold(tp, ialloc_context);

		/*
		 * We want the quota changes to be associated with the next
		 * transaction, NOT this one. So, detach the dqinfo from this
		 * and attach it to the next transaction.
		 */
		dqinfo = NULL;
		tflags = 0;
		if (tp->t_dqinfo) {
			dqinfo = (void *)tp->t_dqinfo;
			tp->t_dqinfo = NULL;
			tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY;
			tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
		}

		code = xfs_trans_roll(&tp);

		/*
		 * Re-attach the quota info that we detached from prev trx.
		 */
		if (dqinfo) {
			tp->t_dqinfo = dqinfo;
			tp->t_flags |= tflags;
		}

		if (code) {
			xfs_buf_relse(ialloc_context);
			*tpp = tp;
			*ipp = NULL;
			return code;
		}
		xfs_trans_bjoin(tp, ialloc_context);

		/*
		 * Call ialloc again. Since we've locked out all
		 * other allocations in this allocation group,
		 * this call should always succeed.
		 */
		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
				  &ialloc_context, &ip);

		/*
		 * If we get an error at this point, return to the caller
		 * so that the current transaction can be aborted.
		 */
		if (code) {
			*tpp = tp;
			*ipp = NULL;
			return code;
		}
		ASSERT(!ialloc_context && ip);

	}

	*ipp = ip;
	*tpp = tp;

	return 0;
}

/*
 * Decrement the link count on an inode & log the change.  If this causes the
 * link count to go to zero, move the inode to AGI unlinked list so that it can
 * be freed when the last active reference goes away via xfs_inactive().
 */
static int			/* error */
xfs_droplink(
	xfs_trans_t *tp,
	xfs_inode_t *ip)
{
	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);

	drop_nlink(VFS_I(ip));
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	if (VFS_I(ip)->i_nlink)
		return 0;

	return xfs_iunlink(tp, ip);
}

/*
 * Increment the link count on an inode & log the change.
 */
static void
xfs_bumplink(
	xfs_trans_t *tp,
	xfs_inode_t *ip)
{
	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);

	inc_nlink(VFS_I(ip));
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}

int
xfs_create(
	xfs_inode_t		*dp,
	struct xfs_name		*name,
	umode_t			mode,
	dev_t			rdev,
	xfs_inode_t		**ipp)
{
	int			is_dir = S_ISDIR(mode);
	struct xfs_mount	*mp = dp->i_mount;
	struct xfs_inode	*ip = NULL;
	struct xfs_trans	*tp = NULL;
	int			error;
	bool                    unlock_dp_on_error = false;
	prid_t			prid;
	struct xfs_dquot	*udqp = NULL;
	struct xfs_dquot	*gdqp = NULL;
	struct xfs_dquot	*pdqp = NULL;
	struct xfs_trans_res	*tres;
	uint			resblks;

	trace_xfs_create(dp, name);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	prid = xfs_get_initial_prid(dp);

	/*
	 * Make sure that we have allocated dquot(s) on disk.
	 */
	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
					&udqp, &gdqp, &pdqp);
	if (error)
		return error;

	if (is_dir) {
		resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
		tres = &M_RES(mp)->tr_mkdir;
	} else {
		resblks = XFS_CREATE_SPACE_RES(mp, name->len);
		tres = &M_RES(mp)->tr_create;
	}

	/*
	 * Initially assume that the file does not exist and
	 * reserve the resources for that case.  If that is not
	 * the case we'll drop the one we have and get a more
	 * appropriate transaction later.
	 */
	error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
	if (error == -ENOSPC) {
		/* flush outstanding delalloc blocks and retry */
		xfs_flush_inodes(mp);
		error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
	}
	if (error)
		goto out_release_inode;

	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
	unlock_dp_on_error = true;

	/*
	 * Reserve disk quota and the inode.
	 */
	error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
						pdqp, resblks, 1, 0);
	if (error)
		goto out_trans_cancel;

	/*
	 * A newly created regular or special file just has one directory
	 * entry pointing to them, but a directory also the "." entry
	 * pointing to itself.
	 */
	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip);
	if (error)
		goto out_trans_cancel;

	/*
	 * Now we join the directory inode to the transaction.  We do not do it
	 * earlier because xfs_dir_ialloc might commit the previous transaction
	 * (and release all the locks).  An error from here on will result in
	 * the transaction cancel unlocking dp so don't do it explicitly in the
	 * error path.
	 */
	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
	unlock_dp_on_error = false;

	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
					resblks - XFS_IALLOC_SPACE_RES(mp));
	if (error) {
		ASSERT(error != -ENOSPC);
		goto out_trans_cancel;
	}
	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);

	if (is_dir) {
		error = xfs_dir_init(tp, ip, dp);
		if (error)
			goto out_trans_cancel;

		xfs_bumplink(tp, dp);
	}

	/*
	 * If this is a synchronous mount, make sure that the
	 * create transaction goes to disk before returning to
	 * the user.
	 */
	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
		xfs_trans_set_sync(tp);

	/*
	 * Attach the dquot(s) to the inodes and modify them incore.
	 * These ids of the inode couldn't have changed since the new
	 * inode has been locked ever since it was created.
	 */
	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);

	error = xfs_trans_commit(tp);
	if (error)
		goto out_release_inode;

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	*ipp = ip;
	return 0;

 out_trans_cancel:
	xfs_trans_cancel(tp);
 out_release_inode:
	/*
	 * Wait until after the current transaction is aborted to finish the
	 * setup of the inode and release the inode.  This prevents recursive
	 * transactions and deadlocks from xfs_inactive.
	 */
	if (ip) {
		xfs_finish_inode_setup(ip);
		xfs_irele(ip);
	}

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	if (unlock_dp_on_error)
		xfs_iunlock(dp, XFS_ILOCK_EXCL);
	return error;
}

int
xfs_create_tmpfile(
	struct xfs_inode	*dp,
	umode_t			mode,
	struct xfs_inode	**ipp)
{
	struct xfs_mount	*mp = dp->i_mount;
	struct xfs_inode	*ip = NULL;
	struct xfs_trans	*tp = NULL;
	int			error;
	prid_t                  prid;
	struct xfs_dquot	*udqp = NULL;
	struct xfs_dquot	*gdqp = NULL;
	struct xfs_dquot	*pdqp = NULL;
	struct xfs_trans_res	*tres;
	uint			resblks;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	prid = xfs_get_initial_prid(dp);

	/*
	 * Make sure that we have allocated dquot(s) on disk.
	 */
	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
				XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
				&udqp, &gdqp, &pdqp);
	if (error)
		return error;

	resblks = XFS_IALLOC_SPACE_RES(mp);
	tres = &M_RES(mp)->tr_create_tmpfile;

	error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
	if (error)
		goto out_release_inode;

	error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
						pdqp, resblks, 1, 0);
	if (error)
		goto out_trans_cancel;

	error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip);
	if (error)
		goto out_trans_cancel;

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	/*
	 * Attach the dquot(s) to the inodes and modify them incore.
	 * These ids of the inode couldn't have changed since the new
	 * inode has been locked ever since it was created.
	 */
	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);

	error = xfs_iunlink(tp, ip);
	if (error)
		goto out_trans_cancel;

	error = xfs_trans_commit(tp);
	if (error)
		goto out_release_inode;

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	*ipp = ip;
	return 0;

 out_trans_cancel:
	xfs_trans_cancel(tp);
 out_release_inode:
	/*
	 * Wait until after the current transaction is aborted to finish the
	 * setup of the inode and release the inode.  This prevents recursive
	 * transactions and deadlocks from xfs_inactive.
	 */
	if (ip) {
		xfs_finish_inode_setup(ip);
		xfs_irele(ip);
	}

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	return error;
}

int
xfs_link(
	xfs_inode_t		*tdp,
	xfs_inode_t		*sip,
	struct xfs_name		*target_name)
{
	xfs_mount_t		*mp = tdp->i_mount;
	xfs_trans_t		*tp;
	int			error;
	int			resblks;

	trace_xfs_link(tdp, target_name);

	ASSERT(!S_ISDIR(VFS_I(sip)->i_mode));

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	error = xfs_qm_dqattach(sip);
	if (error)
		goto std_return;

	error = xfs_qm_dqattach(tdp);
	if (error)
		goto std_return;

	resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, resblks, 0, 0, &tp);
	if (error == -ENOSPC) {
		resblks = 0;
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &tp);
	}
	if (error)
		goto std_return;

	xfs_lock_two_inodes(sip, XFS_ILOCK_EXCL, tdp, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);

	/*
	 * If we are using project inheritance, we only allow hard link
	 * creation in our tree when the project IDs are the same; else
	 * the tree quota mechanism could be circumvented.
	 */
	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
		     tdp->i_d.di_projid != sip->i_d.di_projid)) {
		error = -EXDEV;
		goto error_return;
	}

	if (!resblks) {
		error = xfs_dir_canenter(tp, tdp, target_name);
		if (error)
			goto error_return;
	}

	/*
	 * Handle initial link state of O_TMPFILE inode
	 */
	if (VFS_I(sip)->i_nlink == 0) {
		error = xfs_iunlink_remove(tp, sip);
		if (error)
			goto error_return;
	}

	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
				   resblks);
	if (error)
		goto error_return;
	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);

	xfs_bumplink(tp, sip);

	/*
	 * If this is a synchronous mount, make sure that the
	 * link transaction goes to disk before returning to
	 * the user.
	 */
	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
		xfs_trans_set_sync(tp);

	return xfs_trans_commit(tp);

 error_return:
	xfs_trans_cancel(tp);
 std_return:
	return error;
}

/* Clear the reflink flag and the cowblocks tag if possible. */
static void
xfs_itruncate_clear_reflink_flags(
	struct xfs_inode	*ip)
{
	struct xfs_ifork	*dfork;
	struct xfs_ifork	*cfork;

	if (!xfs_is_reflink_inode(ip))
		return;
	dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
	cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK);
	if (dfork->if_bytes == 0 && cfork->if_bytes == 0)
		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
	if (cfork->if_bytes == 0)
		xfs_inode_clear_cowblocks_tag(ip);
}

/*
 * Free up the underlying blocks past new_size.  The new size must be smaller
 * than the current size.  This routine can be used both for the attribute and
 * data fork, and does not modify the inode size, which is left to the caller.
 *
 * The transaction passed to this routine must have made a permanent log
 * reservation of at least XFS_ITRUNCATE_LOG_RES.  This routine may commit the
 * given transaction and start new ones, so make sure everything involved in
 * the transaction is tidy before calling here.  Some transaction will be
 * returned to the caller to be committed.  The incoming transaction must
 * already include the inode, and both inode locks must be held exclusively.
 * The inode must also be "held" within the transaction.  On return the inode
 * will be "held" within the returned transaction.  This routine does NOT
 * require any disk space to be reserved for it within the transaction.
 *
 * If we get an error, we must return with the inode locked and linked into the
 * current transaction. This keeps things simple for the higher level code,
 * because it always knows that the inode is locked and held in the transaction
 * that returns to it whether errors occur or not.  We don't mark the inode
 * dirty on error so that transactions can be easily aborted if possible.
 */
int
xfs_itruncate_extents_flags(
	struct xfs_trans	**tpp,
	struct xfs_inode	*ip,
	int			whichfork,
	xfs_fsize_t		new_size,
	int			flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp = *tpp;
	xfs_fileoff_t		first_unmap_block;
	xfs_filblks_t		unmap_len;
	int			error = 0;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
	       xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(new_size <= XFS_ISIZE(ip));
	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
	ASSERT(ip->i_itemp != NULL);
	ASSERT(ip->i_itemp->ili_lock_flags == 0);
	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));

	trace_xfs_itruncate_extents_start(ip, new_size);

	flags |= xfs_bmapi_aflag(whichfork);

	/*
	 * Since it is possible for space to become allocated beyond
	 * the end of the file (in a crash where the space is allocated
	 * but the inode size is not yet updated), simply remove any
	 * blocks which show up between the new EOF and the maximum
	 * possible file size.
	 *
	 * We have to free all the blocks to the bmbt maximum offset, even if
	 * the page cache can't scale that far.
	 */
	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
	if (first_unmap_block >= XFS_MAX_FILEOFF) {
		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
		return 0;
	}

	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
	while (unmap_len > 0) {
		ASSERT(tp->t_firstblock == NULLFSBLOCK);
		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
				flags, XFS_ITRUNC_MAX_EXTENTS);
		if (error)
			goto out;

		/*
		 * Duplicate the transaction that has the permanent
		 * reservation and commit the old transaction.
		 */
		error = xfs_defer_finish(&tp);
		if (error)
			goto out;

		error = xfs_trans_roll_inode(&tp, ip);
		if (error)
			goto out;
	}

	if (whichfork == XFS_DATA_FORK) {
		/* Remove all pending CoW reservations. */
		error = xfs_reflink_cancel_cow_blocks(ip, &tp,
				first_unmap_block, XFS_MAX_FILEOFF, true);
		if (error)
			goto out;

		xfs_itruncate_clear_reflink_flags(ip);
	}

	/*
	 * Always re-log the inode so that our permanent transaction can keep
	 * on rolling it forward in the log.
	 */
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	trace_xfs_itruncate_extents_end(ip, new_size);

out:
	*tpp = tp;
	return error;
}

int
xfs_release(
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp = ip->i_mount;
	int		error;

	if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
		return 0;

	/* If this is a read-only mount, don't do this (would generate I/O) */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return 0;

	if (!XFS_FORCED_SHUTDOWN(mp)) {
		int truncated;

		/*
		 * If we previously truncated this file and removed old data
		 * in the process, we want to initiate "early" writeout on
		 * the last close.  This is an attempt to combat the notorious
		 * NULL files problem which is particularly noticeable from a
		 * truncate down, buffered (re-)write (delalloc), followed by
		 * a crash.  What we are effectively doing here is
		 * significantly reducing the time window where we'd otherwise
		 * be exposed to that problem.
		 */
		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
		if (truncated) {
			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
			if (ip->i_delayed_blks > 0) {
				error = filemap_flush(VFS_I(ip)->i_mapping);
				if (error)
					return error;
			}
		}
	}

	if (VFS_I(ip)->i_nlink == 0)
		return 0;

	if (xfs_can_free_eofblocks(ip, false)) {

		/*
		 * Check if the inode is being opened, written and closed
		 * frequently and we have delayed allocation blocks outstanding
		 * (e.g. streaming writes from the NFS server), truncating the
		 * blocks past EOF will cause fragmentation to occur.
		 *
		 * In this case don't do the truncation, but we have to be
		 * careful how we detect this case. Blocks beyond EOF show up as
		 * i_delayed_blks even when the inode is clean, so we need to
		 * truncate them away first before checking for a dirty release.
		 * Hence on the first dirty close we will still remove the
		 * speculative allocation, but after that we will leave it in
		 * place.
		 */
		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
			return 0;
		/*
		 * If we can't get the iolock just skip truncating the blocks
		 * past EOF because we could deadlock with the mmap_sem
		 * otherwise. We'll get another chance to drop them once the
		 * last reference to the inode is dropped, so we'll never leak
		 * blocks permanently.
		 */
		if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
			error = xfs_free_eofblocks(ip);
			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
			if (error)
				return error;
		}

		/* delalloc blocks after truncation means it really is dirty */
		if (ip->i_delayed_blks)
			xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
	}
	return 0;
}

/*
 * xfs_inactive_truncate
 *
 * Called to perform a truncate when an inode becomes unlinked.
 */
STATIC int
xfs_inactive_truncate(
	struct xfs_inode *ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
	if (error) {
		ASSERT(XFS_FORCED_SHUTDOWN(mp));
		return error;
	}
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, 0);

	/*
	 * Log the inode size first to prevent stale data exposure in the event
	 * of a system crash before the truncate completes. See the related
	 * comment in xfs_vn_setattr_size() for details.
	 */
	ip->i_d.di_size = 0;
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
	if (error)
		goto error_trans_cancel;

	ASSERT(ip->i_df.if_nextents == 0);

	error = xfs_trans_commit(tp);
	if (error)
		goto error_unlock;

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return 0;

error_trans_cancel:
	xfs_trans_cancel(tp);
error_unlock:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

/*
 * xfs_inactive_ifree()
 *
 * Perform the inode free when an inode is unlinked.
 */
STATIC int
xfs_inactive_ifree(
	struct xfs_inode *ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error;

	/*
	 * We try to use a per-AG reservation for any block needed by the finobt
	 * tree, but as the finobt feature predates the per-AG reservation
	 * support a degraded file system might not have enough space for the
	 * reservation at mount time.  In that case try to dip into the reserved
	 * pool and pray.
	 *
	 * Send a warning if the reservation does happen to fail, as the inode
	 * now remains allocated and sits on the unlinked list until the fs is
	 * repaired.
	 */
	if (unlikely(mp->m_finobt_nores)) {
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
				XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
				&tp);
	} else {
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp);
	}
	if (error) {
		if (error == -ENOSPC) {
			xfs_warn_ratelimited(mp,
			"Failed to remove inode(s) from unlinked list. "
			"Please free space, unmount and run xfs_repair.");
		} else {
			ASSERT(XFS_FORCED_SHUTDOWN(mp));
		}
		return error;
	}

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, 0);

	error = xfs_ifree(tp, ip);
	if (error) {
		/*
		 * If we fail to free the inode, shut down.  The cancel
		 * might do that, we need to make sure.  Otherwise the
		 * inode might be lost for a long time or forever.
		 */
		if (!XFS_FORCED_SHUTDOWN(mp)) {
			xfs_notice(mp, "%s: xfs_ifree returned error %d",
				__func__, error);
			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
		}
		xfs_trans_cancel(tp);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		return error;
	}

	/*
	 * Credit the quota account(s). The inode is gone.
	 */
	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);

	/*
	 * Just ignore errors at this point.  There is nothing we can do except
	 * to try to keep going. Make sure it's not a silent error.
	 */
	error = xfs_trans_commit(tp);
	if (error)
		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
			__func__, error);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return 0;
}

/*
 * xfs_inactive
 *
 * This is called when the vnode reference count for the vnode
 * goes to zero.  If the file has been unlinked, then it must
 * now be truncated.  Also, we clear all of the read-ahead state
 * kept for the inode here since the file is now closed.
 */
void
xfs_inactive(
	xfs_inode_t	*ip)
{
	struct xfs_mount	*mp;
	int			error;
	int			truncate = 0;

	/*
	 * If the inode is already free, then there can be nothing
	 * to clean up here.
	 */
	if (VFS_I(ip)->i_mode == 0) {
		ASSERT(ip->i_df.if_broot_bytes == 0);
		return;
	}

	mp = ip->i_mount;
	ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));

	/* If this is a read-only mount, don't do this (would generate I/O) */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return;

	/* Try to clean out the cow blocks if there are any. */
	if (xfs_inode_has_cow_data(ip))
		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);

	if (VFS_I(ip)->i_nlink != 0) {
		/*
		 * force is true because we are evicting an inode from the
		 * cache. Post-eof blocks must be freed, lest we end up with
		 * broken free space accounting.
		 *
		 * Note: don't bother with iolock here since lockdep complains
		 * about acquiring it in reclaim context. We have the only
		 * reference to the inode at this point anyways.
		 */
		if (xfs_can_free_eofblocks(ip, true))
			xfs_free_eofblocks(ip);

		return;
	}

	if (S_ISREG(VFS_I(ip)->i_mode) &&
	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
	     ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
		truncate = 1;

	error = xfs_qm_dqattach(ip);
	if (error)
		return;

	if (S_ISLNK(VFS_I(ip)->i_mode))
		error = xfs_inactive_symlink(ip);
	else if (truncate)
		error = xfs_inactive_truncate(ip);
	if (error)
		return;

	/*
	 * If there are attributes associated with the file then blow them away
	 * now.  The code calls a routine that recursively deconstructs the
	 * attribute fork. If also blows away the in-core attribute fork.
	 */
	if (XFS_IFORK_Q(ip)) {
		error = xfs_attr_inactive(ip);
		if (error)
			return;
	}

	ASSERT(!ip->i_afp);
	ASSERT(ip->i_d.di_forkoff == 0);

	/*
	 * Free the inode.
	 */
	error = xfs_inactive_ifree(ip);
	if (error)
		return;

	/*
	 * Release the dquots held by inode, if any.
	 */
	xfs_qm_dqdetach(ip);
}

/*
 * In-Core Unlinked List Lookups
 * =============================
 *
 * Every inode is supposed to be reachable from some other piece of metadata
 * with the exception of the root directory.  Inodes with a connection to a
 * file descriptor but not linked from anywhere in the on-disk directory tree
 * are collectively known as unlinked inodes, though the filesystem itself
 * maintains links to these inodes so that on-disk metadata are consistent.
 *
 * XFS implements a per-AG on-disk hash table of unlinked inodes.  The AGI
 * header contains a number of buckets that point to an inode, and each inode
 * record has a pointer to the next inode in the hash chain.  This
 * singly-linked list causes scaling problems in the iunlink remove function
 * because we must walk that list to find the inode that points to the inode
 * being removed from the unlinked hash bucket list.
 *
 * What if we modelled the unlinked list as a collection of records capturing
 * "X.next_unlinked = Y" relations?  If we indexed those records on Y, we'd
 * have a fast way to look up unlinked list predecessors, which avoids the
 * slow list walk.  That's exactly what we do here (in-core) with a per-AG
 * rhashtable.
 *
 * Because this is a backref cache, we ignore operational failures since the
 * iunlink code can fall back to the slow bucket walk.  The only errors that
 * should bubble out are for obviously incorrect situations.
 *
 * All users of the backref cache MUST hold the AGI buffer lock to serialize
 * access or have otherwise provided for concurrency control.
 */

/* Capture a "X.next_unlinked = Y" relationship. */
struct xfs_iunlink {
	struct rhash_head	iu_rhash_head;
	xfs_agino_t		iu_agino;		/* X */
	xfs_agino_t		iu_next_unlinked;	/* Y */
};

/* Unlinked list predecessor lookup hashtable construction */
static int
xfs_iunlink_obj_cmpfn(
	struct rhashtable_compare_arg	*arg,
	const void			*obj)
{
	const xfs_agino_t		*key = arg->key;
	const struct xfs_iunlink	*iu = obj;

	if (iu->iu_next_unlinked != *key)
		return 1;
	return 0;
}

static const struct rhashtable_params xfs_iunlink_hash_params = {
	.min_size		= XFS_AGI_UNLINKED_BUCKETS,
	.key_len		= sizeof(xfs_agino_t),
	.key_offset		= offsetof(struct xfs_iunlink,
					   iu_next_unlinked),
	.head_offset		= offsetof(struct xfs_iunlink, iu_rhash_head),
	.automatic_shrinking	= true,
	.obj_cmpfn		= xfs_iunlink_obj_cmpfn,
};

/*
 * Return X, where X.next_unlinked == @agino.  Returns NULLAGINO if no such
 * relation is found.
 */
static xfs_agino_t
xfs_iunlink_lookup_backref(
	struct xfs_perag	*pag,
	xfs_agino_t		agino)
{
	struct xfs_iunlink	*iu;

	iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
			xfs_iunlink_hash_params);
	return iu ? iu->iu_agino : NULLAGINO;
}

/*
 * Take ownership of an iunlink cache entry and insert it into the hash table.
 * If successful, the entry will be owned by the cache; if not, it is freed.
 * Either way, the caller does not own @iu after this call.
 */
static int
xfs_iunlink_insert_backref(
	struct xfs_perag	*pag,
	struct xfs_iunlink	*iu)
{
	int			error;

	error = rhashtable_insert_fast(&pag->pagi_unlinked_hash,
			&iu->iu_rhash_head, xfs_iunlink_hash_params);
	/*
	 * Fail loudly if there already was an entry because that's a sign of
	 * corruption of in-memory data.  Also fail loudly if we see an error
	 * code we didn't anticipate from the rhashtable code.  Currently we
	 * only anticipate ENOMEM.
	 */
	if (error) {
		WARN(error != -ENOMEM, "iunlink cache insert error %d", error);
		kmem_free(iu);
	}
	/*
	 * Absorb any runtime errors that aren't a result of corruption because
	 * this is a cache and we can always fall back to bucket list scanning.
	 */
	if (error != 0 && error != -EEXIST)
		error = 0;
	return error;
}

/* Remember that @prev_agino.next_unlinked = @this_agino. */
static int
xfs_iunlink_add_backref(
	struct xfs_perag	*pag,
	xfs_agino_t		prev_agino,
	xfs_agino_t		this_agino)
{
	struct xfs_iunlink	*iu;

	if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK))
		return 0;

	iu = kmem_zalloc(sizeof(*iu), KM_NOFS);
	iu->iu_agino = prev_agino;
	iu->iu_next_unlinked = this_agino;

	return xfs_iunlink_insert_backref(pag, iu);
}

/*
 * Replace X.next_unlinked = @agino with X.next_unlinked = @next_unlinked.
 * If @next_unlinked is NULLAGINO, we drop the backref and exit.  If there
 * wasn't any such entry then we don't bother.
 */
static int
xfs_iunlink_change_backref(
	struct xfs_perag	*pag,
	xfs_agino_t		agino,
	xfs_agino_t		next_unlinked)
{
	struct xfs_iunlink	*iu;
	int			error;

	/* Look up the old entry; if there wasn't one then exit. */
	iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
			xfs_iunlink_hash_params);
	if (!iu)
		return 0;

	/*
	 * Remove the entry.  This shouldn't ever return an error, but if we
	 * couldn't remove the old entry we don't want to add it again to the
	 * hash table, and if the entry disappeared on us then someone's
	 * violated the locking rules and we need to fail loudly.  Either way
	 * we cannot remove the inode because internal state is or would have
	 * been corrupt.
	 */
	error = rhashtable_remove_fast(&pag->pagi_unlinked_hash,
			&iu->iu_rhash_head, xfs_iunlink_hash_params);
	if (error)
		return error;

	/* If there is no new next entry just free our item and return. */
	if (next_unlinked == NULLAGINO) {
		kmem_free(iu);
		return 0;
	}

	/* Update the entry and re-add it to the hash table. */
	iu->iu_next_unlinked = next_unlinked;
	return xfs_iunlink_insert_backref(pag, iu);
}

/* Set up the in-core predecessor structures. */
int
xfs_iunlink_init(
	struct xfs_perag	*pag)
{
	return rhashtable_init(&pag->pagi_unlinked_hash,
			&xfs_iunlink_hash_params);
}

/* Free the in-core predecessor structures. */
static void
xfs_iunlink_free_item(
	void			*ptr,
	void			*arg)
{
	struct xfs_iunlink	*iu = ptr;
	bool			*freed_anything = arg;

	*freed_anything = true;
	kmem_free(iu);
}

void
xfs_iunlink_destroy(
	struct xfs_perag	*pag)
{
	bool			freed_anything = false;

	rhashtable_free_and_destroy(&pag->pagi_unlinked_hash,
			xfs_iunlink_free_item, &freed_anything);

	ASSERT(freed_anything == false || XFS_FORCED_SHUTDOWN(pag->pag_mount));
}

/*
 * Point the AGI unlinked bucket at an inode and log the results.  The caller
 * is responsible for validating the old value.
 */
STATIC int
xfs_iunlink_update_bucket(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	struct xfs_buf		*agibp,
	unsigned int		bucket_index,
	xfs_agino_t		new_agino)
{
	struct xfs_agi		*agi = agibp->b_addr;
	xfs_agino_t		old_value;
	int			offset;

	ASSERT(xfs_verify_agino_or_null(tp->t_mountp, agno, new_agino));

	old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
	trace_xfs_iunlink_update_bucket(tp->t_mountp, agno, bucket_index,
			old_value, new_agino);

	/*
	 * We should never find the head of the list already set to the value
	 * passed in because either we're adding or removing ourselves from the
	 * head of the list.
	 */
	if (old_value == new_agino) {
		xfs_buf_mark_corrupt(agibp);
		return -EFSCORRUPTED;
	}

	agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
	offset = offsetof(struct xfs_agi, agi_unlinked) +
			(sizeof(xfs_agino_t) * bucket_index);
	xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1);
	return 0;
}

/* Set an on-disk inode's next_unlinked pointer. */
STATIC void
xfs_iunlink_update_dinode(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agino_t		agino,
	struct xfs_buf		*ibp,
	struct xfs_dinode	*dip,
	struct xfs_imap		*imap,
	xfs_agino_t		next_agino)
{
	struct xfs_mount	*mp = tp->t_mountp;
	int			offset;

	ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));

	trace_xfs_iunlink_update_dinode(mp, agno, agino,
			be32_to_cpu(dip->di_next_unlinked), next_agino);

	dip->di_next_unlinked = cpu_to_be32(next_agino);
	offset = imap->im_boffset +
			offsetof(struct xfs_dinode, di_next_unlinked);

	/* need to recalc the inode CRC if appropriate */
	xfs_dinode_calc_crc(mp, dip);
	xfs_trans_inode_buf(tp, ibp);
	xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
	xfs_inobp_check(mp, ibp);
}

/* Set an in-core inode's unlinked pointer and return the old value. */
STATIC int
xfs_iunlink_update_inode(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	xfs_agnumber_t		agno,
	xfs_agino_t		next_agino,
	xfs_agino_t		*old_next_agino)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_dinode	*dip;
	struct xfs_buf		*ibp;
	xfs_agino_t		old_value;
	int			error;

	ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));

	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, 0);
	if (error)
		return error;

	/* Make sure the old pointer isn't garbage. */
	old_value = be32_to_cpu(dip->di_next_unlinked);
	if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
				sizeof(*dip), __this_address);
		error = -EFSCORRUPTED;
		goto out;
	}

	/*
	 * Since we're updating a linked list, we should never find that the
	 * current pointer is the same as the new value, unless we're
	 * terminating the list.
	 */
	*old_next_agino = old_value;
	if (old_value == next_agino) {
		if (next_agino != NULLAGINO) {
			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
					dip, sizeof(*dip), __this_address);
			error = -EFSCORRUPTED;
		}
		goto out;
	}

	/* Ok, update the new pointer. */
	xfs_iunlink_update_dinode(tp, agno, XFS_INO_TO_AGINO(mp, ip->i_ino),
			ibp, dip, &ip->i_imap, next_agino);
	return 0;
out:
	xfs_trans_brelse(tp, ibp);
	return error;
}

/*
 * This is called when the inode's link count has gone to 0 or we are creating
 * a tmpfile via O_TMPFILE.  The inode @ip must have nlink == 0.
 *
 * We place the on-disk inode on a list in the AGI.  It will be pulled from this
 * list when the inode is freed.
 */
STATIC int
xfs_iunlink(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_agi		*agi;
	struct xfs_buf		*agibp;
	xfs_agino_t		next_agino;
	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
	short			bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
	int			error;

	ASSERT(VFS_I(ip)->i_nlink == 0);
	ASSERT(VFS_I(ip)->i_mode != 0);
	trace_xfs_iunlink(ip);

	/* Get the agi buffer first.  It ensures lock ordering on the list. */
	error = xfs_read_agi(mp, tp, agno, &agibp);
	if (error)
		return error;
	agi = agibp->b_addr;

	/*
	 * Get the index into the agi hash table for the list this inode will
	 * go on.  Make sure the pointer isn't garbage and that this inode
	 * isn't already on the list.
	 */
	next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
	if (next_agino == agino ||
	    !xfs_verify_agino_or_null(mp, agno, next_agino)) {
		xfs_buf_mark_corrupt(agibp);
		return -EFSCORRUPTED;
	}

	if (next_agino != NULLAGINO) {
		struct xfs_perag	*pag;
		xfs_agino_t		old_agino;

		/*
		 * There is already another inode in the bucket, so point this
		 * inode to the current head of the list.
		 */
		error = xfs_iunlink_update_inode(tp, ip, agno, next_agino,
				&old_agino);
		if (error)
			return error;
		ASSERT(old_agino == NULLAGINO);

		/*
		 * agino has been unlinked, add a backref from the next inode
		 * back to agino.
		 */
		pag = xfs_perag_get(mp, agno);
		error = xfs_iunlink_add_backref(pag, agino, next_agino);
		xfs_perag_put(pag);
		if (error)
			return error;
	}

	/* Point the head of the list to point to this inode. */
	return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index, agino);
}

/* Return the imap, dinode pointer, and buffer for an inode. */
STATIC int
xfs_iunlink_map_ino(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agino_t		agino,
	struct xfs_imap		*imap,
	struct xfs_dinode	**dipp,
	struct xfs_buf		**bpp)
{
	struct xfs_mount	*mp = tp->t_mountp;
	int			error;

	imap->im_blkno = 0;
	error = xfs_imap(mp, tp, XFS_AGINO_TO_INO(mp, agno, agino), imap, 0);
	if (error) {
		xfs_warn(mp, "%s: xfs_imap returned error %d.",
				__func__, error);
		return error;
	}

	error = xfs_imap_to_bp(mp, tp, imap, dipp, bpp, 0);
	if (error) {
		xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
				__func__, error);
		return error;
	}

	return 0;
}

/*
 * Walk the unlinked chain from @head_agino until we find the inode that
 * points to @target_agino.  Return the inode number, map, dinode pointer,
 * and inode cluster buffer of that inode as @agino, @imap, @dipp, and @bpp.
 *
 * @tp, @pag, @head_agino, and @target_agino are input parameters.
 * @agino, @imap, @dipp, and @bpp are all output parameters.
 *
 * Do not call this function if @target_agino is the head of the list.
 */
STATIC int
xfs_iunlink_map_prev(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agino_t		head_agino,
	xfs_agino_t		target_agino,
	xfs_agino_t		*agino,
	struct xfs_imap		*imap,
	struct xfs_dinode	**dipp,
	struct xfs_buf		**bpp,
	struct xfs_perag	*pag)
{
	struct xfs_mount	*mp = tp->t_mountp;
	xfs_agino_t		next_agino;
	int			error;

	ASSERT(head_agino != target_agino);
	*bpp = NULL;

	/* See if our backref cache can find it faster. */
	*agino = xfs_iunlink_lookup_backref(pag, target_agino);
	if (*agino != NULLAGINO) {
		error = xfs_iunlink_map_ino(tp, agno, *agino, imap, dipp, bpp);
		if (error)
			return error;

		if (be32_to_cpu((*dipp)->di_next_unlinked) == target_agino)
			return 0;

		/*
		 * If we get here the cache contents were corrupt, so drop the
		 * buffer and fall back to walking the bucket list.
		 */
		xfs_trans_brelse(tp, *bpp);
		*bpp = NULL;
		WARN_ON_ONCE(1);
	}

	trace_xfs_iunlink_map_prev_fallback(mp, agno);

	/* Otherwise, walk the entire bucket until we find it. */
	next_agino = head_agino;
	while (next_agino != target_agino) {
		xfs_agino_t	unlinked_agino;

		if (*bpp)
			xfs_trans_brelse(tp, *bpp);

		*agino = next_agino;
		error = xfs_iunlink_map_ino(tp, agno, next_agino, imap, dipp,
				bpp);
		if (error)
			return error;

		unlinked_agino = be32_to_cpu((*dipp)->di_next_unlinked);
		/*
		 * Make sure this pointer is valid and isn't an obvious
		 * infinite loop.
		 */
		if (!xfs_verify_agino(mp, agno, unlinked_agino) ||
		    next_agino == unlinked_agino) {
			XFS_CORRUPTION_ERROR(__func__,
					XFS_ERRLEVEL_LOW, mp,
					*dipp, sizeof(**dipp));
			error = -EFSCORRUPTED;
			return error;
		}
		next_agino = unlinked_agino;
	}

	return 0;
}

/*
 * Pull the on-disk inode from the AGI unlinked list.
 */
STATIC int
xfs_iunlink_remove(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_agi		*agi;
	struct xfs_buf		*agibp;
	struct xfs_buf		*last_ibp;
	struct xfs_dinode	*last_dip = NULL;
	struct xfs_perag	*pag = NULL;
	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
	xfs_agino_t		next_agino;
	xfs_agino_t		head_agino;
	short			bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
	int			error;

	trace_xfs_iunlink_remove(ip);

	/* Get the agi buffer first.  It ensures lock ordering on the list. */
	error = xfs_read_agi(mp, tp, agno, &agibp);
	if (error)
		return error;
	agi = agibp->b_addr;

	/*
	 * Get the index into the agi hash table for the list this inode will
	 * go on.  Make sure the head pointer isn't garbage.
	 */
	head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
	if (!xfs_verify_agino(mp, agno, head_agino)) {
		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
				agi, sizeof(*agi));
		return -EFSCORRUPTED;
	}

	/*
	 * Set our inode's next_unlinked pointer to NULL and then return
	 * the old pointer value so that we can update whatever was previous
	 * to us in the list to point to whatever was next in the list.
	 */
	error = xfs_iunlink_update_inode(tp, ip, agno, NULLAGINO, &next_agino);
	if (error)
		return error;

	/*
	 * If there was a backref pointing from the next inode back to this
	 * one, remove it because we've removed this inode from the list.
	 *
	 * Later, if this inode was in the middle of the list we'll update
	 * this inode's backref to point from the next inode.
	 */
	if (next_agino != NULLAGINO) {
		pag = xfs_perag_get(mp, agno);
		error = xfs_iunlink_change_backref(pag, next_agino,
				NULLAGINO);
		if (error)
			goto out;
	}

	if (head_agino == agino) {
		/* Point the head of the list to the next unlinked inode. */
		error = xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
				next_agino);
		if (error)
			goto out;
	} else {
		struct xfs_imap	imap;
		xfs_agino_t	prev_agino;

		if (!pag)
			pag = xfs_perag_get(mp, agno);

		/* We need to search the list for the inode being freed. */
		error = xfs_iunlink_map_prev(tp, agno, head_agino, agino,
				&prev_agino, &imap, &last_dip, &last_ibp,
				pag);
		if (error)
			goto out;

		/* Point the previous inode on the list to the next inode. */
		xfs_iunlink_update_dinode(tp, agno, prev_agino, last_ibp,
				last_dip, &imap, next_agino);

		/*
		 * Now we deal with the backref for this inode.  If this inode
		 * pointed at a real inode, change the backref that pointed to
		 * us to point to our old next.  If this inode was the end of
		 * the list, delete the backref that pointed to us.  Note that
		 * change_backref takes care of deleting the backref if
		 * next_agino is NULLAGINO.
		 */
		error = xfs_iunlink_change_backref(pag, agino, next_agino);
		if (error)
			goto out;
	}

out:
	if (pag)
		xfs_perag_put(pag);
	return error;
}

/*
 * Look up the inode number specified and mark it stale if it is found. If it is
 * dirty, return the inode so it can be attached to the cluster buffer so it can
 * be processed appropriately when the cluster free transaction completes.
 */
static struct xfs_inode *
xfs_ifree_get_one_inode(
	struct xfs_perag	*pag,
	struct xfs_inode	*free_ip,
	xfs_ino_t		inum)
{
	struct xfs_mount	*mp = pag->pag_mount;
	struct xfs_inode	*ip;

retry:
	rcu_read_lock();
	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));

	/* Inode not in memory, nothing to do */
	if (!ip)
		goto out_rcu_unlock;

	/*
	 * because this is an RCU protected lookup, we could find a recently
	 * freed or even reallocated inode during the lookup. We need to check
	 * under the i_flags_lock for a valid inode here. Skip it if it is not
	 * valid, the wrong inode or stale.
	 */
	spin_lock(&ip->i_flags_lock);
	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
		spin_unlock(&ip->i_flags_lock);
		goto out_rcu_unlock;
	}
	spin_unlock(&ip->i_flags_lock);

	/*
	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
	 * other inodes that we did not find in the list attached to the buffer
	 * and are not already marked stale. If we can't lock it, back off and
	 * retry.
	 */
	if (ip != free_ip) {
		if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
			rcu_read_unlock();
			delay(1);
			goto retry;
		}

		/*
		 * Check the inode number again in case we're racing with
		 * freeing in xfs_reclaim_inode().  See the comments in that
		 * function for more information as to why the initial check is
		 * not sufficient.
		 */
		if (ip->i_ino != inum) {
			xfs_iunlock(ip, XFS_ILOCK_EXCL);
			goto out_rcu_unlock;
		}
	}
	rcu_read_unlock();

	xfs_iflock(ip);
	xfs_iflags_set(ip, XFS_ISTALE);

	/*
	 * We don't need to attach clean inodes or those only with unlogged
	 * changes (which we throw away, anyway).
	 */
	if (!ip->i_itemp || xfs_inode_clean(ip)) {
		ASSERT(ip != free_ip);
		xfs_ifunlock(ip);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		goto out_no_inode;
	}
	return ip;

out_rcu_unlock:
	rcu_read_unlock();
out_no_inode:
	return NULL;
}

/*
 * A big issue when freeing the inode cluster is that we _cannot_ skip any
 * inodes that are in memory - they all must be marked stale and attached to
 * the cluster buffer.
 */
STATIC int
xfs_ifree_cluster(
	xfs_inode_t		*free_ip,
	xfs_trans_t		*tp,
	struct xfs_icluster	*xic)
{
	xfs_mount_t		*mp = free_ip->i_mount;
	int			nbufs;
	int			i, j;
	int			ioffset;
	xfs_daddr_t		blkno;
	xfs_buf_t		*bp;
	xfs_inode_t		*ip;
	struct xfs_inode_log_item *iip;
	struct xfs_log_item	*lip;
	struct xfs_perag	*pag;
	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
	xfs_ino_t		inum;
	int			error;

	inum = xic->first_ino;
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
	nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster;

	for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) {
		/*
		 * The allocation bitmap tells us which inodes of the chunk were
		 * physically allocated. Skip the cluster if an inode falls into
		 * a sparse region.
		 */
		ioffset = inum - xic->first_ino;
		if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) {
			ASSERT(ioffset % igeo->inodes_per_cluster == 0);
			continue;
		}

		blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum),
					 XFS_INO_TO_AGBNO(mp, inum));

		/*
		 * We obtain and lock the backing buffer first in the process
		 * here, as we have to ensure that any dirty inode that we
		 * can't get the flush lock on is attached to the buffer.
		 * If we scan the in-memory inodes first, then buffer IO can
		 * complete before we get a lock on it, and hence we may fail
		 * to mark all the active inodes on the buffer stale.
		 */
		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
				mp->m_bsize * igeo->blocks_per_cluster,
				XBF_UNMAPPED, &bp);
		if (error)
			return error;

		/*
		 * This buffer may not have been correctly initialised as we
		 * didn't read it from disk. That's not important because we are
		 * only using to mark the buffer as stale in the log, and to
		 * attach stale cached inodes on it. That means it will never be
		 * dispatched for IO. If it is, we want to know about it, and we
		 * want it to fail. We can acheive this by adding a write
		 * verifier to the buffer.
		 */
		bp->b_ops = &xfs_inode_buf_ops;

		/*
		 * Walk the inodes already attached to the buffer and mark them
		 * stale. These will all have the flush locks held, so an
		 * in-memory inode walk can't lock them. By marking them all
		 * stale first, we will not attempt to lock them in the loop
		 * below as the XFS_ISTALE flag will be set.
		 */
		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
			if (lip->li_type == XFS_LI_INODE) {
				iip = (struct xfs_inode_log_item *)lip;
				ASSERT(iip->ili_logged == 1);
				lip->li_cb = xfs_istale_done;
				xfs_trans_ail_copy_lsn(mp->m_ail,
							&iip->ili_flush_lsn,
							&iip->ili_item.li_lsn);
				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
			}
		}


		/*
		 * For each inode in memory attempt to add it to the inode
		 * buffer and set it up for being staled on buffer IO
		 * completion.  This is safe as we've locked out tail pushing
		 * and flushing by locking the buffer.
		 *
		 * We have already marked every inode that was part of a
		 * transaction stale above, which means there is no point in
		 * even trying to lock them.
		 */
		for (i = 0; i < igeo->inodes_per_cluster; i++) {
			ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i);
			if (!ip)
				continue;

			iip = ip->i_itemp;
			iip->ili_last_fields = iip->ili_fields;
			iip->ili_fields = 0;
			iip->ili_fsync_fields = 0;
			iip->ili_logged = 1;
			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
						&iip->ili_item.li_lsn);

			xfs_buf_attach_iodone(bp, xfs_istale_done,
						  &iip->ili_item);

			if (ip != free_ip)
				xfs_iunlock(ip, XFS_ILOCK_EXCL);
		}

		xfs_trans_stale_inode_buf(tp, bp);
		xfs_trans_binval(tp, bp);
	}

	xfs_perag_put(pag);
	return 0;
}

/*
 * This is called to return an inode to the inode free list.
 * The inode should already be truncated to 0 length and have
 * no pages associated with it.  This routine also assumes that
 * the inode is already a part of the transaction.
 *
 * The on-disk copy of the inode will have been added to the list
 * of unlinked inodes in the AGI. We need to remove the inode from
 * that list atomically with respect to freeing it here.
 */
int
xfs_ifree(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip)
{
	int			error;
	struct xfs_icluster	xic = { 0 };

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
	ASSERT(VFS_I(ip)->i_nlink == 0);
	ASSERT(ip->i_df.if_nextents == 0);
	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
	ASSERT(ip->i_d.di_nblocks == 0);

	/*
	 * Pull the on-disk inode from the AGI unlinked list.
	 */
	error = xfs_iunlink_remove(tp, ip);
	if (error)
		return error;

	error = xfs_difree(tp, ip->i_ino, &xic);
	if (error)
		return error;

	/*
	 * Free any local-format data sitting around before we reset the
	 * data fork to extents format.  Note that the attr fork data has
	 * already been freed by xfs_attr_inactive.
	 */
	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
		kmem_free(ip->i_df.if_u1.if_data);
		ip->i_df.if_u1.if_data = NULL;
		ip->i_df.if_bytes = 0;
	}

	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
	ip->i_d.di_flags = 0;
	ip->i_d.di_flags2 = 0;
	ip->i_d.di_dmevmask = 0;
	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;

	/* Don't attempt to replay owner changes for a deleted inode */
	ip->i_itemp->ili_fields &= ~(XFS_ILOG_AOWNER|XFS_ILOG_DOWNER);

	/*
	 * Bump the generation count so no one will be confused
	 * by reincarnations of this inode.
	 */
	VFS_I(ip)->i_generation++;
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	if (xic.deleted)
		error = xfs_ifree_cluster(ip, tp, &xic);

	return error;
}

/*
 * This is called to unpin an inode.  The caller must have the inode locked
 * in at least shared mode so that the buffer cannot be subsequently pinned
 * once someone is waiting for it to be unpinned.
 */
static void
xfs_iunpin(
	struct xfs_inode	*ip)
{
	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));

	trace_xfs_inode_unpin_nowait(ip, _RET_IP_);

	/* Give the log a push to start the unpinning I/O */
	xfs_log_force_lsn(ip->i_mount, ip->i_itemp->ili_last_lsn, 0, NULL);

}

static void
__xfs_iunpin_wait(
	struct xfs_inode	*ip)
{
	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IPINNED_BIT);
	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IPINNED_BIT);

	xfs_iunpin(ip);

	do {
		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
		if (xfs_ipincount(ip))
			io_schedule();
	} while (xfs_ipincount(ip));
	finish_wait(wq, &wait.wq_entry);
}

void
xfs_iunpin_wait(
	struct xfs_inode	*ip)
{
	if (xfs_ipincount(ip))
		__xfs_iunpin_wait(ip);
}

/*
 * Removing an inode from the namespace involves removing the directory entry
 * and dropping the link count on the inode. Removing the directory entry can
 * result in locking an AGF (directory blocks were freed) and removing a link
 * count can result in placing the inode on an unlinked list which results in
 * locking an AGI.
 *
 * The big problem here is that we have an ordering constraint on AGF and AGI
 * locking - inode allocation locks the AGI, then can allocate a new extent for
 * new inodes, locking the AGF after the AGI. Similarly, freeing the inode
 * removes the inode from the unlinked list, requiring that we lock the AGI
 * first, and then freeing the inode can result in an inode chunk being freed
 * and hence freeing disk space requiring that we lock an AGF.
 *
 * Hence the ordering that is imposed by other parts of the code is AGI before
 * AGF. This means we cannot remove the directory entry before we drop the inode
 * reference count and put it on the unlinked list as this results in a lock
 * order of AGF then AGI, and this can deadlock against inode allocation and
 * freeing. Therefore we must drop the link counts before we remove the
 * directory entry.
 *
 * This is still safe from a transactional point of view - it is not until we
 * get to xfs_defer_finish() that we have the possibility of multiple
 * transactions in this operation. Hence as long as we remove the directory
 * entry and drop the link count in the first transaction of the remove
 * operation, there are no transactional constraints on the ordering here.
 */
int
xfs_remove(
	xfs_inode_t             *dp,
	struct xfs_name		*name,
	xfs_inode_t		*ip)
{
	xfs_mount_t		*mp = dp->i_mount;
	xfs_trans_t             *tp = NULL;
	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
	int                     error = 0;
	uint			resblks;

	trace_xfs_remove(dp, name);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	error = xfs_qm_dqattach(dp);
	if (error)
		goto std_return;

	error = xfs_qm_dqattach(ip);
	if (error)
		goto std_return;

	/*
	 * We try to get the real space reservation first,
	 * allowing for directory btree deletion(s) implying
	 * possible bmap insert(s).  If we can't get the space
	 * reservation then we use 0 instead, and avoid the bmap
	 * btree insert(s) in the directory code by, if the bmap
	 * insert tries to happen, instead trimming the LAST
	 * block from the directory.
	 */
	resblks = XFS_REMOVE_SPACE_RES(mp);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, resblks, 0, 0, &tp);
	if (error == -ENOSPC) {
		resblks = 0;
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, 0, 0, 0,
				&tp);
	}
	if (error) {
		ASSERT(error != -ENOSPC);
		goto std_return;
	}

	xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);

	/*
	 * If we're removing a directory perform some additional validation.
	 */
	if (is_dir) {
		ASSERT(VFS_I(ip)->i_nlink >= 2);
		if (VFS_I(ip)->i_nlink != 2) {
			error = -ENOTEMPTY;
			goto out_trans_cancel;
		}
		if (!xfs_dir_isempty(ip)) {
			error = -ENOTEMPTY;
			goto out_trans_cancel;
		}

		/* Drop the link from ip's "..".  */
		error = xfs_droplink(tp, dp);
		if (error)
			goto out_trans_cancel;

		/* Drop the "." link from ip to self.  */
		error = xfs_droplink(tp, ip);
		if (error)
			goto out_trans_cancel;
	} else {
		/*
		 * When removing a non-directory we need to log the parent
		 * inode here.  For a directory this is done implicitly
		 * by the xfs_droplink call for the ".." entry.
		 */
		xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
	}
	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);

	/* Drop the link from dp to ip. */
	error = xfs_droplink(tp, ip);
	if (error)
		goto out_trans_cancel;

	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
	if (error) {
		ASSERT(error != -ENOENT);
		goto out_trans_cancel;
	}

	/*
	 * If this is a synchronous mount, make sure that the
	 * remove transaction goes to disk before returning to
	 * the user.
	 */
	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp);
	if (error)
		goto std_return;

	if (is_dir && xfs_inode_is_filestream(ip))
		xfs_filestream_deassociate(ip);

	return 0;

 out_trans_cancel:
	xfs_trans_cancel(tp);
 std_return:
	return error;
}

/*
 * Enter all inodes for a rename transaction into a sorted array.
 */
#define __XFS_SORT_INODES	5
STATIC void
xfs_sort_for_rename(
	struct xfs_inode	*dp1,	/* in: old (source) directory inode */
	struct xfs_inode	*dp2,	/* in: new (target) directory inode */
	struct xfs_inode	*ip1,	/* in: inode of old entry */
	struct xfs_inode	*ip2,	/* in: inode of new entry */
	struct xfs_inode	*wip,	/* in: whiteout inode */
	struct xfs_inode	**i_tab,/* out: sorted array of inodes */
	int			*num_inodes)  /* in/out: inodes in array */
{
	int			i, j;

	ASSERT(*num_inodes == __XFS_SORT_INODES);
	memset(i_tab, 0, *num_inodes * sizeof(struct xfs_inode *));

	/*
	 * i_tab contains a list of pointers to inodes.  We initialize
	 * the table here & we'll sort it.  We will then use it to
	 * order the acquisition of the inode locks.
	 *
	 * Note that the table may contain duplicates.  e.g., dp1 == dp2.
	 */
	i = 0;
	i_tab[i++] = dp1;
	i_tab[i++] = dp2;
	i_tab[i++] = ip1;
	if (ip2)
		i_tab[i++] = ip2;
	if (wip)
		i_tab[i++] = wip;
	*num_inodes = i;

	/*
	 * Sort the elements via bubble sort.  (Remember, there are at
	 * most 5 elements to sort, so this is adequate.)
	 */
	for (i = 0; i < *num_inodes; i++) {
		for (j = 1; j < *num_inodes; j++) {
			if (i_tab[j]->i_ino < i_tab[j-1]->i_ino) {
				struct xfs_inode *temp = i_tab[j];
				i_tab[j] = i_tab[j-1];
				i_tab[j-1] = temp;
			}
		}
	}
}

static int
xfs_finish_rename(
	struct xfs_trans	*tp)
{
	/*
	 * If this is a synchronous mount, make sure that the rename transaction
	 * goes to disk before returning to the user.
	 */
	if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
		xfs_trans_set_sync(tp);

	return xfs_trans_commit(tp);
}

/*
 * xfs_cross_rename()
 *
 * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall
 */
STATIC int
xfs_cross_rename(
	struct xfs_trans	*tp,
	struct xfs_inode	*dp1,
	struct xfs_name		*name1,
	struct xfs_inode	*ip1,
	struct xfs_inode	*dp2,
	struct xfs_name		*name2,
	struct xfs_inode	*ip2,
	int			spaceres)
{
	int		error = 0;
	int		ip1_flags = 0;
	int		ip2_flags = 0;
	int		dp2_flags = 0;

	/* Swap inode number for dirent in first parent */
	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
	if (error)
		goto out_trans_abort;

	/* Swap inode number for dirent in second parent */
	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
	if (error)
		goto out_trans_abort;

	/*
	 * If we're renaming one or more directories across different parents,
	 * update the respective ".." entries (and link counts) to match the new
	 * parents.
	 */
	if (dp1 != dp2) {
		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;

		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
						dp1->i_ino, spaceres);
			if (error)
				goto out_trans_abort;

			/* transfer ip2 ".." reference to dp1 */
			if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
				error = xfs_droplink(tp, dp2);
				if (error)
					goto out_trans_abort;
				xfs_bumplink(tp, dp1);
			}

			/*
			 * Although ip1 isn't changed here, userspace needs
			 * to be warned about the change, so that applications
			 * relying on it (like backup ones), will properly
			 * notify the change
			 */
			ip1_flags |= XFS_ICHGTIME_CHG;
			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
		}

		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
						dp2->i_ino, spaceres);
			if (error)
				goto out_trans_abort;

			/* transfer ip1 ".." reference to dp2 */
			if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
				error = xfs_droplink(tp, dp1);
				if (error)
					goto out_trans_abort;
				xfs_bumplink(tp, dp2);
			}

			/*
			 * Although ip2 isn't changed here, userspace needs
			 * to be warned about the change, so that applications
			 * relying on it (like backup ones), will properly
			 * notify the change
			 */
			ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
			ip2_flags |= XFS_ICHGTIME_CHG;
		}
	}

	if (ip1_flags) {
		xfs_trans_ichgtime(tp, ip1, ip1_flags);
		xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
	}
	if (ip2_flags) {
		xfs_trans_ichgtime(tp, ip2, ip2_flags);
		xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
	}
	if (dp2_flags) {
		xfs_trans_ichgtime(tp, dp2, dp2_flags);
		xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
	}
	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
	return xfs_finish_rename(tp);

out_trans_abort:
	xfs_trans_cancel(tp);
	return error;
}

/*
 * xfs_rename_alloc_whiteout()
 *
 * Return a referenced, unlinked, unlocked inode that that can be used as a
 * whiteout in a rename transaction. We use a tmpfile inode here so that if we
 * crash between allocating the inode and linking it into the rename transaction
 * recovery will free the inode and we won't leak it.
 */
static int
xfs_rename_alloc_whiteout(
	struct xfs_inode	*dp,
	struct xfs_inode	**wip)
{
	struct xfs_inode	*tmpfile;
	int			error;

	error = xfs_create_tmpfile(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile);
	if (error)
		return error;

	/*
	 * Prepare the tmpfile inode as if it were created through the VFS.
	 * Complete the inode setup and flag it as linkable.  nlink is already
	 * zero, so we can skip the drop_nlink.
	 */
	xfs_setup_iops(tmpfile);
	xfs_finish_inode_setup(tmpfile);
	VFS_I(tmpfile)->i_state |= I_LINKABLE;

	*wip = tmpfile;
	return 0;
}

/*
 * xfs_rename
 */
int
xfs_rename(
	struct xfs_inode	*src_dp,
	struct xfs_name		*src_name,
	struct xfs_inode	*src_ip,
	struct xfs_inode	*target_dp,
	struct xfs_name		*target_name,
	struct xfs_inode	*target_ip,
	unsigned int		flags)
{
	struct xfs_mount	*mp = src_dp->i_mount;
	struct xfs_trans	*tp;
	struct xfs_inode	*wip = NULL;		/* whiteout inode */
	struct xfs_inode	*inodes[__XFS_SORT_INODES];
	struct xfs_buf		*agibp;
	int			num_inodes = __XFS_SORT_INODES;
	bool			new_parent = (src_dp != target_dp);
	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
	int			spaceres;
	int			error;

	trace_xfs_rename(src_dp, target_dp, src_name, target_name);

	if ((flags & RENAME_EXCHANGE) && !target_ip)
		return -EINVAL;

	/*
	 * If we are doing a whiteout operation, allocate the whiteout inode
	 * we will be placing at the target and ensure the type is set
	 * appropriately.
	 */
	if (flags & RENAME_WHITEOUT) {
		ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
		error = xfs_rename_alloc_whiteout(target_dp, &wip);
		if (error)
			return error;

		/* setup target dirent info as whiteout */
		src_name->type = XFS_DIR3_FT_CHRDEV;
	}

	xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip,
				inodes, &num_inodes);

	spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp);
	if (error == -ENOSPC) {
		spaceres = 0;
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0,
				&tp);
	}
	if (error)
		goto out_release_wip;

	/*
	 * Attach the dquots to the inodes
	 */
	error = xfs_qm_vop_rename_dqattach(inodes);
	if (error)
		goto out_trans_cancel;

	/*
	 * Lock all the participating inodes. Depending upon whether
	 * the target_name exists in the target directory, and
	 * whether the target directory is the same as the source
	 * directory, we can lock from 2 to 4 inodes.
	 */
	xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL);

	/*
	 * Join all the inodes to the transaction. From this point on,
	 * we can rely on either trans_commit or trans_cancel to unlock
	 * them.
	 */
	xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL);
	if (new_parent)
		xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL);
	if (target_ip)
		xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL);
	if (wip)
		xfs_trans_ijoin(tp, wip, XFS_ILOCK_EXCL);

	/*
	 * If we are using project inheritance, we only allow renames
	 * into our tree when the project IDs are the same; else the
	 * tree quota mechanism would be circumvented.
	 */
	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
		     target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
		error = -EXDEV;
		goto out_trans_cancel;
	}

	/* RENAME_EXCHANGE is unique from here on. */
	if (flags & RENAME_EXCHANGE)
		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
					target_dp, target_name, target_ip,
					spaceres);

	/*
	 * Check for expected errors before we dirty the transaction
	 * so we can return an error without a transaction abort.
	 */
	if (target_ip == NULL) {
		/*
		 * If there's no space reservation, check the entry will
		 * fit before actually inserting it.
		 */
		if (!spaceres) {
			error = xfs_dir_canenter(tp, target_dp, target_name);
			if (error)
				goto out_trans_cancel;
		}
	} else {
		/*
		 * If target exists and it's a directory, check that whether
		 * it can be destroyed.
		 */
		if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
		    (!xfs_dir_isempty(target_ip) ||
		     (VFS_I(target_ip)->i_nlink > 2))) {
			error = -EEXIST;
			goto out_trans_cancel;
		}
	}

	/*
	 * Directory entry creation below may acquire the AGF. Remove
	 * the whiteout from the unlinked list first to preserve correct
	 * AGI/AGF locking order. This dirties the transaction so failures
	 * after this point will abort and log recovery will clean up the
	 * mess.
	 *
	 * For whiteouts, we need to bump the link count on the whiteout
	 * inode. After this point, we have a real link, clear the tmpfile
	 * state flag from the inode so it doesn't accidentally get misused
	 * in future.
	 */
	if (wip) {
		ASSERT(VFS_I(wip)->i_nlink == 0);
		error = xfs_iunlink_remove(tp, wip);
		if (error)
			goto out_trans_cancel;

		xfs_bumplink(tp, wip);
		VFS_I(wip)->i_state &= ~I_LINKABLE;
	}

	/*
	 * Set up the target.
	 */
	if (target_ip == NULL) {
		/*
		 * If target does not exist and the rename crosses
		 * directories, adjust the target directory link count
		 * to account for the ".." reference from the new entry.
		 */
		error = xfs_dir_createname(tp, target_dp, target_name,
					   src_ip->i_ino, spaceres);
		if (error)
			goto out_trans_cancel;

		xfs_trans_ichgtime(tp, target_dp,
					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);

		if (new_parent && src_is_directory) {
			xfs_bumplink(tp, target_dp);
		}
	} else { /* target_ip != NULL */
		/*
		 * Link the source inode under the target name.
		 * If the source inode is a directory and we are moving
		 * it across directories, its ".." entry will be
		 * inconsistent until we replace that down below.
		 *
		 * In case there is already an entry with the same
		 * name at the destination directory, remove it first.
		 */

		/*
		 * Check whether the replace operation will need to allocate
		 * blocks.  This happens when the shortform directory lacks
		 * space and we have to convert it to a block format directory.
		 * When more blocks are necessary, we must lock the AGI first
		 * to preserve locking order (AGI -> AGF).
		 */
		if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) {
			error = xfs_read_agi(mp, tp,
					XFS_INO_TO_AGNO(mp, target_ip->i_ino),
					&agibp);
			if (error)
				goto out_trans_cancel;
		}

		error = xfs_dir_replace(tp, target_dp, target_name,
					src_ip->i_ino, spaceres);
		if (error)
			goto out_trans_cancel;

		xfs_trans_ichgtime(tp, target_dp,
					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);

		/*
		 * Decrement the link count on the target since the target
		 * dir no longer points to it.
		 */
		error = xfs_droplink(tp, target_ip);
		if (error)
			goto out_trans_cancel;

		if (src_is_directory) {
			/*
			 * Drop the link from the old "." entry.
			 */
			error = xfs_droplink(tp, target_ip);
			if (error)
				goto out_trans_cancel;
		}
	} /* target_ip != NULL */

	/*
	 * Remove the source.
	 */
	if (new_parent && src_is_directory) {
		/*
		 * Rewrite the ".." entry to point to the new
		 * directory.
		 */
		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
					target_dp->i_ino, spaceres);
		ASSERT(error != -EEXIST);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * We always want to hit the ctime on the source inode.
	 *
	 * This isn't strictly required by the standards since the source
	 * inode isn't really being changed, but old unix file systems did
	 * it and some incremental backup programs won't work without it.
	 */
	xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);

	/*
	 * Adjust the link count on src_dp.  This is necessary when
	 * renaming a directory, either within one parent when
	 * the target existed, or across two parent directories.
	 */
	if (src_is_directory && (new_parent || target_ip != NULL)) {

		/*
		 * Decrement link count on src_directory since the
		 * entry that's moved no longer points to it.
		 */
		error = xfs_droplink(tp, src_dp);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * For whiteouts, we only need to update the source dirent with the
	 * inode number of the whiteout inode rather than removing it
	 * altogether.
	 */
	if (wip) {
		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
					spaceres);
	} else
		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
					   spaceres);
	if (error)
		goto out_trans_cancel;

	xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
	if (new_parent)
		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);

	error = xfs_finish_rename(tp);
	if (wip)
		xfs_irele(wip);
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
out_release_wip:
	if (wip)
		xfs_irele(wip);
	return error;
}

STATIC int
xfs_iflush_cluster(
	struct xfs_inode	*ip,
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_perag	*pag;
	unsigned long		first_index, mask;
	int			cilist_size;
	struct xfs_inode	**cilist;
	struct xfs_inode	*cip;
	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
	int			error = 0;
	int			nr_found;
	int			clcount = 0;
	int			i;

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));

	cilist_size = igeo->inodes_per_cluster * sizeof(struct xfs_inode *);
	cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
	if (!cilist)
		goto out_put;

	mask = ~(igeo->inodes_per_cluster - 1);
	first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
	rcu_read_lock();
	/* really need a gang lookup range call here */
	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
					first_index, igeo->inodes_per_cluster);
	if (nr_found == 0)
		goto out_free;

	for (i = 0; i < nr_found; i++) {
		cip = cilist[i];
		if (cip == ip)
			continue;

		/*
		 * because this is an RCU protected lookup, we could find a
		 * recently freed or even reallocated inode during the lookup.
		 * We need to check under the i_flags_lock for a valid inode
		 * here. Skip it if it is not valid or the wrong inode.
		 */
		spin_lock(&cip->i_flags_lock);
		if (!cip->i_ino ||
		    __xfs_iflags_test(cip, XFS_ISTALE)) {
			spin_unlock(&cip->i_flags_lock);
			continue;
		}

		/*
		 * Once we fall off the end of the cluster, no point checking
		 * any more inodes in the list because they will also all be
		 * outside the cluster.
		 */
		if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
			spin_unlock(&cip->i_flags_lock);
			break;
		}
		spin_unlock(&cip->i_flags_lock);

		/*
		 * Do an un-protected check to see if the inode is dirty and
		 * is a candidate for flushing.  These checks will be repeated
		 * later after the appropriate locks are acquired.
		 */
		if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
			continue;

		/*
		 * Try to get locks.  If any are unavailable or it is pinned,
		 * then this inode cannot be flushed and is skipped.
		 */

		if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
			continue;
		if (!xfs_iflock_nowait(cip)) {
			xfs_iunlock(cip, XFS_ILOCK_SHARED);
			continue;
		}
		if (xfs_ipincount(cip)) {
			xfs_ifunlock(cip);
			xfs_iunlock(cip, XFS_ILOCK_SHARED);
			continue;
		}


		/*
		 * Check the inode number again, just to be certain we are not
		 * racing with freeing in xfs_reclaim_inode(). See the comments
		 * in that function for more information as to why the initial
		 * check is not sufficient.
		 */
		if (!cip->i_ino) {
			xfs_ifunlock(cip);
			xfs_iunlock(cip, XFS_ILOCK_SHARED);
			continue;
		}

		/*
		 * arriving here means that this inode can be flushed.  First
		 * re-check that it's dirty before flushing.
		 */
		if (!xfs_inode_clean(cip)) {
			error = xfs_iflush_int(cip, bp);
			if (error) {
				xfs_iunlock(cip, XFS_ILOCK_SHARED);
				goto out_free;
			}
			clcount++;
		} else {
			xfs_ifunlock(cip);
		}
		xfs_iunlock(cip, XFS_ILOCK_SHARED);
	}

	if (clcount) {
		XFS_STATS_INC(mp, xs_icluster_flushcnt);
		XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
	}

out_free:
	rcu_read_unlock();
	kmem_free(cilist);
out_put:
	xfs_perag_put(pag);
	return error;
}

/*
 * Flush dirty inode metadata into the backing buffer.
 *
 * The caller must have the inode lock and the inode flush lock held.  The
 * inode lock will still be held upon return to the caller, and the inode
 * flush lock will be released after the inode has reached the disk.
 *
 * The caller must write out the buffer returned in *bpp and release it.
 */
int
xfs_iflush(
	struct xfs_inode	*ip,
	struct xfs_buf		**bpp)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_buf		*bp = NULL;
	struct xfs_dinode	*dip;
	int			error;

	XFS_STATS_INC(mp, xs_iflush_count);

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
	ASSERT(xfs_isiflocked(ip));
	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));

	*bpp = NULL;

	xfs_iunpin_wait(ip);

	/*
	 * For stale inodes we cannot rely on the backing buffer remaining
	 * stale in cache for the remaining life of the stale inode and so
	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
	 * inodes below. We have to check this after ensuring the inode is
	 * unpinned so that it is safe to reclaim the stale inode after the
	 * flush call.
	 */
	if (xfs_iflags_test(ip, XFS_ISTALE)) {
		xfs_ifunlock(ip);
		return 0;
	}

	/*
	 * Get the buffer containing the on-disk inode. We are doing a try-lock
	 * operation here, so we may get an EAGAIN error. In that case, return
	 * leaving the inode dirty.
	 *
	 * If we get any other error, we effectively have a corruption situation
	 * and we cannot flush the inode. Abort the flush and shut down.
	 */
	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK);
	if (error == -EAGAIN) {
		xfs_ifunlock(ip);
		return error;
	}
	if (error)
		goto abort;

	/*
	 * If the buffer is pinned then push on the log now so we won't
	 * get stuck waiting in the write for too long.
	 */
	if (xfs_buf_ispinned(bp))
		xfs_log_force(mp, 0);

	/*
	 * Flush the provided inode then attempt to gather others from the
	 * cluster into the write.
	 *
	 * Note: Once we attempt to flush an inode, we must run buffer
	 * completion callbacks on any failure. If this fails, simulate an I/O
	 * failure on the buffer and shut down.
	 */
	error = xfs_iflush_int(ip, bp);
	if (!error)
		error = xfs_iflush_cluster(ip, bp);
	if (error) {
		bp->b_flags |= XBF_ASYNC;
		xfs_buf_ioend_fail(bp);
		goto shutdown;
	}

	*bpp = bp;
	return 0;

abort:
	xfs_iflush_abort(ip);
shutdown:
	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
	return error;
}

STATIC int
xfs_iflush_int(
	struct xfs_inode	*ip,
	struct xfs_buf		*bp)
{
	struct xfs_inode_log_item *iip = ip->i_itemp;
	struct xfs_dinode	*dip;
	struct xfs_mount	*mp = ip->i_mount;
	int			error;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
	ASSERT(xfs_isiflocked(ip));
	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
	ASSERT(iip != NULL && iip->ili_fields != 0);

	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);

	/*
	 * We don't flush the inode if any of the following checks fail, but we
	 * do still update the log item and attach to the backing buffer as if
	 * the flush happened. This is a formality to facilitate predictable
	 * error handling as the caller will shutdown and fail the buffer.
	 */
	error = -EFSCORRUPTED;
	if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
			       mp, XFS_ERRTAG_IFLUSH_1)) {
		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
			"%s: Bad inode %Lu magic number 0x%x, ptr "PTR_FMT,
			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
		goto flush_out;
	}
	if (S_ISREG(VFS_I(ip)->i_mode)) {
		if (XFS_TEST_ERROR(
		    ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
		    ip->i_df.if_format != XFS_DINODE_FMT_BTREE,
		    mp, XFS_ERRTAG_IFLUSH_3)) {
			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
				"%s: Bad regular inode %Lu, ptr "PTR_FMT,
				__func__, ip->i_ino, ip);
			goto flush_out;
		}
	} else if (S_ISDIR(VFS_I(ip)->i_mode)) {
		if (XFS_TEST_ERROR(
		    ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
		    ip->i_df.if_format != XFS_DINODE_FMT_BTREE &&
		    ip->i_df.if_format != XFS_DINODE_FMT_LOCAL,
		    mp, XFS_ERRTAG_IFLUSH_4)) {
			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
				"%s: Bad directory inode %Lu, ptr "PTR_FMT,
				__func__, ip->i_ino, ip);
			goto flush_out;
		}
	}
	if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) >
				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
			"%s: detected corrupt incore inode %Lu, "
			"total extents = %d, nblocks = %Ld, ptr "PTR_FMT,
			__func__, ip->i_ino,
			ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp),
			ip->i_d.di_nblocks, ip);
		goto flush_out;
	}
	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
				mp, XFS_ERRTAG_IFLUSH_6)) {
		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
			"%s: bad inode %Lu, forkoff 0x%x, ptr "PTR_FMT,
			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
		goto flush_out;
	}

	/*
	 * Inode item log recovery for v2 inodes are dependent on the
	 * di_flushiter count for correct sequencing. We bump the flush
	 * iteration count so we can detect flushes which postdate a log record
	 * during recovery. This is redundant as we now log every change and
	 * hence this can't happen but we need to still do it to ensure
	 * backwards compatibility with old kernels that predate logging all
	 * inode changes.
	 */
	if (!xfs_sb_version_has_v3inode(&mp->m_sb))
		ip->i_d.di_flushiter++;

	/*
	 * If there are inline format data / attr forks attached to this inode,
	 * make sure they are not corrupt.
	 */
	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL &&
	    xfs_ifork_verify_local_data(ip))
		goto flush_out;
	if (ip->i_afp && ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL &&
	    xfs_ifork_verify_local_attr(ip))
		goto flush_out;

	/*
	 * Copy the dirty parts of the inode into the on-disk inode.  We always
	 * copy out the core of the inode, because if the inode is dirty at all
	 * the core must be.
	 */
	xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);

	/* Wrap, we never let the log put out DI_MAX_FLUSH */
	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
		ip->i_d.di_flushiter = 0;

	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
	if (XFS_IFORK_Q(ip))
		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
	xfs_inobp_check(mp, bp);

	/*
	 * We've recorded everything logged in the inode, so we'd like to clear
	 * the ili_fields bits so we don't log and flush things unnecessarily.
	 * However, we can't stop logging all this information until the data
	 * we've copied into the disk buffer is written to disk.  If we did we
	 * might overwrite the copy of the inode in the log with all the data
	 * after re-logging only part of it, and in the face of a crash we
	 * wouldn't have all the data we need to recover.
	 *
	 * What we do is move the bits to the ili_last_fields field.  When
	 * logging the inode, these bits are moved back to the ili_fields field.
	 * In the xfs_iflush_done() routine we clear ili_last_fields, since we
	 * know that the information those bits represent is permanently on
	 * disk.  As long as the flush completes before the inode is logged
	 * again, then both ili_fields and ili_last_fields will be cleared.
	 *
	 * We can play with the ili_fields bits here, because the inode lock
	 * must be held exclusively in order to set bits there and the flush
	 * lock protects the ili_last_fields bits.  Set ili_logged so the flush
	 * done routine can tell whether or not to look in the AIL.  Also, store
	 * the current LSN of the inode so that we can tell whether the item has
	 * moved in the AIL from xfs_iflush_done().  In order to read the lsn we
	 * need the AIL lock, because it is a 64 bit value that cannot be read
	 * atomically.
	 */
	error = 0;
flush_out:
	iip->ili_last_fields = iip->ili_fields;
	iip->ili_fields = 0;
	iip->ili_fsync_fields = 0;
	iip->ili_logged = 1;

	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
				&iip->ili_item.li_lsn);

	/*
	 * Attach the inode item callback to the buffer whether the flush
	 * succeeded or not. If not, the caller will shut down and fail I/O
	 * completion on the buffer to remove the inode from the AIL and release
	 * the flush lock.
	 */
	xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);

	/* generate the checksum. */
	xfs_dinode_calc_crc(mp, dip);

	ASSERT(!list_empty(&bp->b_li_list));
	ASSERT(bp->b_iodone != NULL);
	return error;
}

/* Release an inode. */
void
xfs_irele(
	struct xfs_inode	*ip)
{
	trace_xfs_irele(ip, _RET_IP_);
	iput(VFS_I(ip));
}

/*
 * Ensure all commited transactions touching the inode are written to the log.
 */
int
xfs_log_force_inode(
	struct xfs_inode	*ip)
{
	xfs_lsn_t		lsn = 0;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_ipincount(ip))
		lsn = ip->i_itemp->ili_last_lsn;
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	if (!lsn)
		return 0;
	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
}