summaryrefslogtreecommitdiffstats
path: root/fs/ntfs/inode.c
blob: f5c058b3192cee4910f8e955af276d460befbc0e (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
// SPDX-License-Identifier: GPL-2.0-or-later
/**
 * inode.c - NTFS kernel inode handling.
 *
 * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
 */

#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/log2.h>

#include "aops.h"
#include "attrib.h"
#include "bitmap.h"
#include "dir.h"
#include "debug.h"
#include "inode.h"
#include "lcnalloc.h"
#include "malloc.h"
#include "mft.h"
#include "time.h"
#include "ntfs.h"

/**
 * ntfs_test_inode - compare two (possibly fake) inodes for equality
 * @vi:		vfs inode which to test
 * @data:	data which is being tested with
 *
 * Compare the ntfs attribute embedded in the ntfs specific part of the vfs
 * inode @vi for equality with the ntfs attribute @data.
 *
 * If searching for the normal file/directory inode, set @na->type to AT_UNUSED.
 * @na->name and @na->name_len are then ignored.
 *
 * Return 1 if the attributes match and 0 if not.
 *
 * NOTE: This function runs with the inode_hash_lock spin lock held so it is not
 * allowed to sleep.
 */
int ntfs_test_inode(struct inode *vi, void *data)
{
	ntfs_attr *na = (ntfs_attr *)data;
	ntfs_inode *ni;

	if (vi->i_ino != na->mft_no)
		return 0;
	ni = NTFS_I(vi);
	/* If !NInoAttr(ni), @vi is a normal file or directory inode. */
	if (likely(!NInoAttr(ni))) {
		/* If not looking for a normal inode this is a mismatch. */
		if (unlikely(na->type != AT_UNUSED))
			return 0;
	} else {
		/* A fake inode describing an attribute. */
		if (ni->type != na->type)
			return 0;
		if (ni->name_len != na->name_len)
			return 0;
		if (na->name_len && memcmp(ni->name, na->name,
				na->name_len * sizeof(ntfschar)))
			return 0;
	}
	/* Match! */
	return 1;
}

/**
 * ntfs_init_locked_inode - initialize an inode
 * @vi:		vfs inode to initialize
 * @data:	data which to initialize @vi to
 *
 * Initialize the vfs inode @vi with the values from the ntfs attribute @data in
 * order to enable ntfs_test_inode() to do its work.
 *
 * If initializing the normal file/directory inode, set @na->type to AT_UNUSED.
 * In that case, @na->name and @na->name_len should be set to NULL and 0,
 * respectively. Although that is not strictly necessary as
 * ntfs_read_locked_inode() will fill them in later.
 *
 * Return 0 on success and -errno on error.
 *
 * NOTE: This function runs with the inode->i_lock spin lock held so it is not
 * allowed to sleep. (Hence the GFP_ATOMIC allocation.)
 */
static int ntfs_init_locked_inode(struct inode *vi, void *data)
{
	ntfs_attr *na = (ntfs_attr *)data;
	ntfs_inode *ni = NTFS_I(vi);

	vi->i_ino = na->mft_no;

	ni->type = na->type;
	if (na->type == AT_INDEX_ALLOCATION)
		NInoSetMstProtected(ni);

	ni->name = na->name;
	ni->name_len = na->name_len;

	/* If initializing a normal inode, we are done. */
	if (likely(na->type == AT_UNUSED)) {
		BUG_ON(na->name);
		BUG_ON(na->name_len);
		return 0;
	}

	/* It is a fake inode. */
	NInoSetAttr(ni);

	/*
	 * We have I30 global constant as an optimization as it is the name
	 * in >99.9% of named attributes! The other <0.1% incur a GFP_ATOMIC
	 * allocation but that is ok. And most attributes are unnamed anyway,
	 * thus the fraction of named attributes with name != I30 is actually
	 * absolutely tiny.
	 */
	if (na->name_len && na->name != I30) {
		unsigned int i;

		BUG_ON(!na->name);
		i = na->name_len * sizeof(ntfschar);
		ni->name = kmalloc(i + sizeof(ntfschar), GFP_ATOMIC);
		if (!ni->name)
			return -ENOMEM;
		memcpy(ni->name, na->name, i);
		ni->name[na->name_len] = 0;
	}
	return 0;
}

static int ntfs_read_locked_inode(struct inode *vi);
static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi);
static int ntfs_read_locked_index_inode(struct inode *base_vi,
		struct inode *vi);

/**
 * ntfs_iget - obtain a struct inode corresponding to a specific normal inode
 * @sb:		super block of mounted volume
 * @mft_no:	mft record number / inode number to obtain
 *
 * Obtain the struct inode corresponding to a specific normal inode (i.e. a
 * file or directory).
 *
 * If the inode is in the cache, it is just returned with an increased
 * reference count. Otherwise, a new struct inode is allocated and initialized,
 * and finally ntfs_read_locked_inode() is called to read in the inode and
 * fill in the remainder of the inode structure.
 *
 * Return the struct inode on success. Check the return value with IS_ERR() and
 * if true, the function failed and the error code is obtained from PTR_ERR().
 */
struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no)
{
	struct inode *vi;
	int err;
	ntfs_attr na;

	na.mft_no = mft_no;
	na.type = AT_UNUSED;
	na.name = NULL;
	na.name_len = 0;

	vi = iget5_locked(sb, mft_no, ntfs_test_inode,
			ntfs_init_locked_inode, &na);
	if (unlikely(!vi))
		return ERR_PTR(-ENOMEM);

	err = 0;

	/* If this is a freshly allocated inode, need to read it now. */
	if (vi->i_state & I_NEW) {
		err = ntfs_read_locked_inode(vi);
		unlock_new_inode(vi);
	}
	/*
	 * There is no point in keeping bad inodes around if the failure was
	 * due to ENOMEM. We want to be able to retry again later.
	 */
	if (unlikely(err == -ENOMEM)) {
		iput(vi);
		vi = ERR_PTR(err);
	}
	return vi;
}

/**
 * ntfs_attr_iget - obtain a struct inode corresponding to an attribute
 * @base_vi:	vfs base inode containing the attribute
 * @type:	attribute type
 * @name:	Unicode name of the attribute (NULL if unnamed)
 * @name_len:	length of @name in Unicode characters (0 if unnamed)
 *
 * Obtain the (fake) struct inode corresponding to the attribute specified by
 * @type, @name, and @name_len, which is present in the base mft record
 * specified by the vfs inode @base_vi.
 *
 * If the attribute inode is in the cache, it is just returned with an
 * increased reference count. Otherwise, a new struct inode is allocated and
 * initialized, and finally ntfs_read_locked_attr_inode() is called to read the
 * attribute and fill in the inode structure.
 *
 * Note, for index allocation attributes, you need to use ntfs_index_iget()
 * instead of ntfs_attr_iget() as working with indices is a lot more complex.
 *
 * Return the struct inode of the attribute inode on success. Check the return
 * value with IS_ERR() and if true, the function failed and the error code is
 * obtained from PTR_ERR().
 */
struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
		ntfschar *name, u32 name_len)
{
	struct inode *vi;
	int err;
	ntfs_attr na;

	/* Make sure no one calls ntfs_attr_iget() for indices. */
	BUG_ON(type == AT_INDEX_ALLOCATION);

	na.mft_no = base_vi->i_ino;
	na.type = type;
	na.name = name;
	na.name_len = name_len;

	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
			ntfs_init_locked_inode, &na);
	if (unlikely(!vi))
		return ERR_PTR(-ENOMEM);

	err = 0;

	/* If this is a freshly allocated inode, need to read it now. */
	if (vi->i_state & I_NEW) {
		err = ntfs_read_locked_attr_inode(base_vi, vi);
		unlock_new_inode(vi);
	}
	/*
	 * There is no point in keeping bad attribute inodes around. This also
	 * simplifies things in that we never need to check for bad attribute
	 * inodes elsewhere.
	 */
	if (unlikely(err)) {
		iput(vi);
		vi = ERR_PTR(err);
	}
	return vi;
}

/**
 * ntfs_index_iget - obtain a struct inode corresponding to an index
 * @base_vi:	vfs base inode containing the index related attributes
 * @name:	Unicode name of the index
 * @name_len:	length of @name in Unicode characters
 *
 * Obtain the (fake) struct inode corresponding to the index specified by @name
 * and @name_len, which is present in the base mft record specified by the vfs
 * inode @base_vi.
 *
 * If the index inode is in the cache, it is just returned with an increased
 * reference count.  Otherwise, a new struct inode is allocated and
 * initialized, and finally ntfs_read_locked_index_inode() is called to read
 * the index related attributes and fill in the inode structure.
 *
 * Return the struct inode of the index inode on success. Check the return
 * value with IS_ERR() and if true, the function failed and the error code is
 * obtained from PTR_ERR().
 */
struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
		u32 name_len)
{
	struct inode *vi;
	int err;
	ntfs_attr na;

	na.mft_no = base_vi->i_ino;
	na.type = AT_INDEX_ALLOCATION;
	na.name = name;
	na.name_len = name_len;

	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
			ntfs_init_locked_inode, &na);
	if (unlikely(!vi))
		return ERR_PTR(-ENOMEM);

	err = 0;

	/* If this is a freshly allocated inode, need to read it now. */
	if (vi->i_state & I_NEW) {
		err = ntfs_read_locked_index_inode(base_vi, vi);
		unlock_new_inode(vi);
	}
	/*
	 * There is no point in keeping bad index inodes around.  This also
	 * simplifies things in that we never need to check for bad index
	 * inodes elsewhere.
	 */
	if (unlikely(err)) {
		iput(vi);
		vi = ERR_PTR(err);
	}
	return vi;
}

struct inode *ntfs_alloc_big_inode(struct super_block *sb)
{
	ntfs_inode *ni;

	ntfs_debug("Entering.");
	ni = kmem_cache_alloc(ntfs_big_inode_cache, GFP_NOFS);
	if (likely(ni != NULL)) {
		ni->state = 0;
		return VFS_I(ni);
	}
	ntfs_error(sb, "Allocation of NTFS big inode structure failed.");
	return NULL;
}

void ntfs_free_big_inode(struct inode *inode)
{
	kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode));
}

static inline ntfs_inode *ntfs_alloc_extent_inode(void)
{
	ntfs_inode *ni;

	ntfs_debug("Entering.");
	ni = kmem_cache_alloc(ntfs_inode_cache, GFP_NOFS);
	if (likely(ni != NULL)) {
		ni->state = 0;
		return ni;
	}
	ntfs_error(NULL, "Allocation of NTFS inode structure failed.");
	return NULL;
}

static void ntfs_destroy_extent_inode(ntfs_inode *ni)
{
	ntfs_debug("Entering.");
	BUG_ON(ni->page);
	if (!atomic_dec_and_test(&ni->count))
		BUG();
	kmem_cache_free(ntfs_inode_cache, ni);
}

/*
 * The attribute runlist lock has separate locking rules from the
 * normal runlist lock, so split the two lock-classes:
 */
static struct lock_class_key attr_list_rl_lock_class;

/**
 * __ntfs_init_inode - initialize ntfs specific part of an inode
 * @sb:		super block of mounted volume
 * @ni:		freshly allocated ntfs inode which to initialize
 *
 * Initialize an ntfs inode to defaults.
 *
 * NOTE: ni->mft_no, ni->state, ni->type, ni->name, and ni->name_len are left
 * untouched. Make sure to initialize them elsewhere.
 *
 * Return zero on success and -ENOMEM on error.
 */
void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni)
{
	ntfs_debug("Entering.");
	rwlock_init(&ni->size_lock);
	ni->initialized_size = ni->allocated_size = 0;
	ni->seq_no = 0;
	atomic_set(&ni->count, 1);
	ni->vol = NTFS_SB(sb);
	ntfs_init_runlist(&ni->runlist);
	mutex_init(&ni->mrec_lock);
	ni->page = NULL;
	ni->page_ofs = 0;
	ni->attr_list_size = 0;
	ni->attr_list = NULL;
	ntfs_init_runlist(&ni->attr_list_rl);
	lockdep_set_class(&ni->attr_list_rl.lock,
				&attr_list_rl_lock_class);
	ni->itype.index.block_size = 0;
	ni->itype.index.vcn_size = 0;
	ni->itype.index.collation_rule = 0;
	ni->itype.index.block_size_bits = 0;
	ni->itype.index.vcn_size_bits = 0;
	mutex_init(&ni->extent_lock);
	ni->nr_extents = 0;
	ni->ext.base_ntfs_ino = NULL;
}

/*
 * Extent inodes get MFT-mapped in a nested way, while the base inode
 * is still mapped. Teach this nesting to the lock validator by creating
 * a separate class for nested inode's mrec_lock's:
 */
static struct lock_class_key extent_inode_mrec_lock_key;

inline ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
		unsigned long mft_no)
{
	ntfs_inode *ni = ntfs_alloc_extent_inode();

	ntfs_debug("Entering.");
	if (likely(ni != NULL)) {
		__ntfs_init_inode(sb, ni);
		lockdep_set_class(&ni->mrec_lock, &extent_inode_mrec_lock_key);
		ni->mft_no = mft_no;
		ni->type = AT_UNUSED;
		ni->name = NULL;
		ni->name_len = 0;
	}
	return ni;
}

/**
 * ntfs_is_extended_system_file - check if a file is in the $Extend directory
 * @ctx:	initialized attribute search context
 *
 * Search all file name attributes in the inode described by the attribute
 * search context @ctx and check if any of the names are in the $Extend system
 * directory.
 *
 * Return values:
 *	   1: file is in $Extend directory
 *	   0: file is not in $Extend directory
 *    -errno: failed to determine if the file is in the $Extend directory
 */
static int ntfs_is_extended_system_file(ntfs_attr_search_ctx *ctx)
{
	int nr_links, err;

	/* Restart search. */
	ntfs_attr_reinit_search_ctx(ctx);

	/* Get number of hard links. */
	nr_links = le16_to_cpu(ctx->mrec->link_count);

	/* Loop through all hard links. */
	while (!(err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0, NULL, 0,
			ctx))) {
		FILE_NAME_ATTR *file_name_attr;
		ATTR_RECORD *attr = ctx->attr;
		u8 *p, *p2;

		nr_links--;
		/*
		 * Maximum sanity checking as we are called on an inode that
		 * we suspect might be corrupt.
		 */
		p = (u8*)attr + le32_to_cpu(attr->length);
		if (p < (u8*)ctx->mrec || (u8*)p > (u8*)ctx->mrec +
				le32_to_cpu(ctx->mrec->bytes_in_use)) {
err_corrupt_attr:
			ntfs_error(ctx->ntfs_ino->vol->sb, "Corrupt file name "
					"attribute. You should run chkdsk.");
			return -EIO;
		}
		if (attr->non_resident) {
			ntfs_error(ctx->ntfs_ino->vol->sb, "Non-resident file "
					"name. You should run chkdsk.");
			return -EIO;
		}
		if (attr->flags) {
			ntfs_error(ctx->ntfs_ino->vol->sb, "File name with "
					"invalid flags. You should run "
					"chkdsk.");
			return -EIO;
		}
		if (!(attr->data.resident.flags & RESIDENT_ATTR_IS_INDEXED)) {
			ntfs_error(ctx->ntfs_ino->vol->sb, "Unindexed file "
					"name. You should run chkdsk.");
			return -EIO;
		}
		file_name_attr = (FILE_NAME_ATTR*)((u8*)attr +
				le16_to_cpu(attr->data.resident.value_offset));
		p2 = (u8*)attr + le32_to_cpu(attr->data.resident.value_length);
		if (p2 < (u8*)attr || p2 > p)
			goto err_corrupt_attr;
		/* This attribute is ok, but is it in the $Extend directory? */
		if (MREF_LE(file_name_attr->parent_directory) == FILE_Extend)
			return 1;	/* YES, it's an extended system file. */
	}
	if (unlikely(err != -ENOENT))
		return err;
	if (unlikely(nr_links)) {
		ntfs_error(ctx->ntfs_ino->vol->sb, "Inode hard link count "
				"doesn't match number of name attributes. You "
				"should run chkdsk.");
		return -EIO;
	}
	return 0;	/* NO, it is not an extended system file. */
}

/**
 * ntfs_read_locked_inode - read an inode from its device
 * @vi:		inode to read
 *
 * ntfs_read_locked_inode() is called from ntfs_iget() to read the inode
 * described by @vi into memory from the device.
 *
 * The only fields in @vi that we need to/can look at when the function is
 * called are i_sb, pointing to the mounted device's super block, and i_ino,
 * the number of the inode to load.
 *
 * ntfs_read_locked_inode() maps, pins and locks the mft record number i_ino
 * for reading and sets up the necessary @vi fields as well as initializing
 * the ntfs inode.
 *
 * Q: What locks are held when the function is called?
 * A: i_state has I_NEW set, hence the inode is locked, also
 *    i_count is set to 1, so it is not going to go away
 *    i_flags is set to 0 and we have no business touching it.  Only an ioctl()
 *    is allowed to write to them. We should of course be honouring them but
 *    we need to do that using the IS_* macros defined in include/linux/fs.h.
 *    In any case ntfs_read_locked_inode() has nothing to do with i_flags.
 *
 * Return 0 on success and -errno on error.  In the error case, the inode will
 * have had make_bad_inode() executed on it.
 */
static int ntfs_read_locked_inode(struct inode *vi)
{
	ntfs_volume *vol = NTFS_SB(vi->i_sb);
	ntfs_inode *ni;
	struct inode *bvi;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	STANDARD_INFORMATION *si;
	ntfs_attr_search_ctx *ctx;
	int err = 0;

	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);

	/* Setup the generic vfs inode parts now. */
	vi->i_uid = vol->uid;
	vi->i_gid = vol->gid;
	vi->i_mode = 0;

	/*
	 * Initialize the ntfs specific part of @vi special casing
	 * FILE_MFT which we need to do at mount time.
	 */
	if (vi->i_ino != FILE_MFT)
		ntfs_init_big_inode(vi);
	ni = NTFS_I(vi);

	m = map_mft_record(ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(ni, m);
	if (!ctx) {
		err = -ENOMEM;
		goto unm_err_out;
	}

	if (!(m->flags & MFT_RECORD_IN_USE)) {
		ntfs_error(vi->i_sb, "Inode is not in use!");
		goto unm_err_out;
	}
	if (m->base_mft_record) {
		ntfs_error(vi->i_sb, "Inode is an extent inode!");
		goto unm_err_out;
	}

	/* Transfer information from mft record into vfs and ntfs inodes. */
	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);

	/*
	 * FIXME: Keep in mind that link_count is two for files which have both
	 * a long file name and a short file name as separate entries, so if
	 * we are hiding short file names this will be too high. Either we need
	 * to account for the short file names by subtracting them or we need
	 * to make sure we delete files even though i_nlink is not zero which
	 * might be tricky due to vfs interactions. Need to think about this
	 * some more when implementing the unlink command.
	 */
	set_nlink(vi, le16_to_cpu(m->link_count));
	/*
	 * FIXME: Reparse points can have the directory bit set even though
	 * they would be S_IFLNK. Need to deal with this further below when we
	 * implement reparse points / symbolic links but it will do for now.
	 * Also if not a directory, it could be something else, rather than
	 * a regular file. But again, will do for now.
	 */
	/* Everyone gets all permissions. */
	vi->i_mode |= S_IRWXUGO;
	/* If read-only, no one gets write permissions. */
	if (IS_RDONLY(vi))
		vi->i_mode &= ~S_IWUGO;
	if (m->flags & MFT_RECORD_IS_DIRECTORY) {
		vi->i_mode |= S_IFDIR;
		/*
		 * Apply the directory permissions mask set in the mount
		 * options.
		 */
		vi->i_mode &= ~vol->dmask;
		/* Things break without this kludge! */
		if (vi->i_nlink > 1)
			set_nlink(vi, 1);
	} else {
		vi->i_mode |= S_IFREG;
		/* Apply the file permissions mask set in the mount options. */
		vi->i_mode &= ~vol->fmask;
	}
	/*
	 * Find the standard information attribute in the mft record. At this
	 * stage we haven't setup the attribute list stuff yet, so this could
	 * in fact fail if the standard information is in an extent record, but
	 * I don't think this actually ever happens.
	 */
	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0, 0, 0, NULL, 0,
			ctx);
	if (unlikely(err)) {
		if (err == -ENOENT) {
			/*
			 * TODO: We should be performing a hot fix here (if the
			 * recover mount option is set) by creating a new
			 * attribute.
			 */
			ntfs_error(vi->i_sb, "$STANDARD_INFORMATION attribute "
					"is missing.");
		}
		goto unm_err_out;
	}
	a = ctx->attr;
	/* Get the standard information attribute value. */
	if ((u8 *)a + le16_to_cpu(a->data.resident.value_offset)
			+ le32_to_cpu(a->data.resident.value_length) >
			(u8 *)ctx->mrec + vol->mft_record_size) {
		ntfs_error(vi->i_sb, "Corrupt standard information attribute in inode.");
		goto unm_err_out;
	}
	si = (STANDARD_INFORMATION*)((u8*)a +
			le16_to_cpu(a->data.resident.value_offset));

	/* Transfer information from the standard information into vi. */
	/*
	 * Note: The i_?times do not quite map perfectly onto the NTFS times,
	 * but they are close enough, and in the end it doesn't really matter
	 * that much...
	 */
	/*
	 * mtime is the last change of the data within the file. Not changed
	 * when only metadata is changed, e.g. a rename doesn't affect mtime.
	 */
	vi->i_mtime = ntfs2utc(si->last_data_change_time);
	/*
	 * ctime is the last change of the metadata of the file. This obviously
	 * always changes, when mtime is changed. ctime can be changed on its
	 * own, mtime is then not changed, e.g. when a file is renamed.
	 */
	vi->i_ctime = ntfs2utc(si->last_mft_change_time);
	/*
	 * Last access to the data within the file. Not changed during a rename
	 * for example but changed whenever the file is written to.
	 */
	vi->i_atime = ntfs2utc(si->last_access_time);

	/* Find the attribute list attribute if present. */
	ntfs_attr_reinit_search_ctx(ctx);
	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
	if (err) {
		if (unlikely(err != -ENOENT)) {
			ntfs_error(vi->i_sb, "Failed to lookup attribute list "
					"attribute.");
			goto unm_err_out;
		}
	} else /* if (!err) */ {
		if (vi->i_ino == FILE_MFT)
			goto skip_attr_list_load;
		ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
		NInoSetAttrList(ni);
		a = ctx->attr;
		if (a->flags & ATTR_COMPRESSION_MASK) {
			ntfs_error(vi->i_sb, "Attribute list attribute is "
					"compressed.");
			goto unm_err_out;
		}
		if (a->flags & ATTR_IS_ENCRYPTED ||
				a->flags & ATTR_IS_SPARSE) {
			if (a->non_resident) {
				ntfs_error(vi->i_sb, "Non-resident attribute "
						"list attribute is encrypted/"
						"sparse.");
				goto unm_err_out;
			}
			ntfs_warning(vi->i_sb, "Resident attribute list "
					"attribute in inode 0x%lx is marked "
					"encrypted/sparse which is not true.  "
					"However, Windows allows this and "
					"chkdsk does not detect or correct it "
					"so we will just ignore the invalid "
					"flags and pretend they are not set.",
					vi->i_ino);
		}
		/* Now allocate memory for the attribute list. */
		ni->attr_list_size = (u32)ntfs_attr_size(a);
		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
		if (!ni->attr_list) {
			ntfs_error(vi->i_sb, "Not enough memory to allocate "
					"buffer for attribute list.");
			err = -ENOMEM;
			goto unm_err_out;
		}
		if (a->non_resident) {
			NInoSetAttrListNonResident(ni);
			if (a->data.non_resident.lowest_vcn) {
				ntfs_error(vi->i_sb, "Attribute list has non "
						"zero lowest_vcn.");
				goto unm_err_out;
			}
			/*
			 * Setup the runlist. No need for locking as we have
			 * exclusive access to the inode at this time.
			 */
			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
					a, NULL);
			if (IS_ERR(ni->attr_list_rl.rl)) {
				err = PTR_ERR(ni->attr_list_rl.rl);
				ni->attr_list_rl.rl = NULL;
				ntfs_error(vi->i_sb, "Mapping pairs "
						"decompression failed.");
				goto unm_err_out;
			}
			/* Now load the attribute list. */
			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
					ni->attr_list, ni->attr_list_size,
					sle64_to_cpu(a->data.non_resident.
					initialized_size)))) {
				ntfs_error(vi->i_sb, "Failed to load "
						"attribute list attribute.");
				goto unm_err_out;
			}
		} else /* if (!a->non_resident) */ {
			if ((u8*)a + le16_to_cpu(a->data.resident.value_offset)
					+ le32_to_cpu(
					a->data.resident.value_length) >
					(u8*)ctx->mrec + vol->mft_record_size) {
				ntfs_error(vi->i_sb, "Corrupt attribute list "
						"in inode.");
				goto unm_err_out;
			}
			/* Now copy the attribute list. */
			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
					a->data.resident.value_offset),
					le32_to_cpu(
					a->data.resident.value_length));
		}
	}
skip_attr_list_load:
	/*
	 * If an attribute list is present we now have the attribute list value
	 * in ntfs_ino->attr_list and it is ntfs_ino->attr_list_size bytes.
	 */
	if (S_ISDIR(vi->i_mode)) {
		loff_t bvi_size;
		ntfs_inode *bni;
		INDEX_ROOT *ir;
		u8 *ir_end, *index_end;

		/* It is a directory, find index root attribute. */
		ntfs_attr_reinit_search_ctx(ctx);
		err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE,
				0, NULL, 0, ctx);
		if (unlikely(err)) {
			if (err == -ENOENT) {
				// FIXME: File is corrupt! Hot-fix with empty
				// index root attribute if recovery option is
				// set.
				ntfs_error(vi->i_sb, "$INDEX_ROOT attribute "
						"is missing.");
			}
			goto unm_err_out;
		}
		a = ctx->attr;
		/* Set up the state. */
		if (unlikely(a->non_resident)) {
			ntfs_error(vol->sb, "$INDEX_ROOT attribute is not "
					"resident.");
			goto unm_err_out;
		}
		/* Ensure the attribute name is placed before the value. */
		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
				le16_to_cpu(a->data.resident.value_offset)))) {
			ntfs_error(vol->sb, "$INDEX_ROOT attribute name is "
					"placed after the attribute value.");
			goto unm_err_out;
		}
		/*
		 * Compressed/encrypted index root just means that the newly
		 * created files in that directory should be created compressed/
		 * encrypted. However index root cannot be both compressed and
		 * encrypted.
		 */
		if (a->flags & ATTR_COMPRESSION_MASK)
			NInoSetCompressed(ni);
		if (a->flags & ATTR_IS_ENCRYPTED) {
			if (a->flags & ATTR_COMPRESSION_MASK) {
				ntfs_error(vi->i_sb, "Found encrypted and "
						"compressed attribute.");
				goto unm_err_out;
			}
			NInoSetEncrypted(ni);
		}
		if (a->flags & ATTR_IS_SPARSE)
			NInoSetSparse(ni);
		ir = (INDEX_ROOT*)((u8*)a +
				le16_to_cpu(a->data.resident.value_offset));
		ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
		if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
					"corrupt.");
			goto unm_err_out;
		}
		index_end = (u8*)&ir->index +
				le32_to_cpu(ir->index.index_length);
		if (index_end > ir_end) {
			ntfs_error(vi->i_sb, "Directory index is corrupt.");
			goto unm_err_out;
		}
		if (ir->type != AT_FILE_NAME) {
			ntfs_error(vi->i_sb, "Indexed attribute is not "
					"$FILE_NAME.");
			goto unm_err_out;
		}
		if (ir->collation_rule != COLLATION_FILE_NAME) {
			ntfs_error(vi->i_sb, "Index collation rule is not "
					"COLLATION_FILE_NAME.");
			goto unm_err_out;
		}
		ni->itype.index.collation_rule = ir->collation_rule;
		ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
		if (ni->itype.index.block_size &
				(ni->itype.index.block_size - 1)) {
			ntfs_error(vi->i_sb, "Index block size (%u) is not a "
					"power of two.",
					ni->itype.index.block_size);
			goto unm_err_out;
		}
		if (ni->itype.index.block_size > PAGE_SIZE) {
			ntfs_error(vi->i_sb, "Index block size (%u) > "
					"PAGE_SIZE (%ld) is not "
					"supported.  Sorry.",
					ni->itype.index.block_size,
					PAGE_SIZE);
			err = -EOPNOTSUPP;
			goto unm_err_out;
		}
		if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
			ntfs_error(vi->i_sb, "Index block size (%u) < "
					"NTFS_BLOCK_SIZE (%i) is not "
					"supported.  Sorry.",
					ni->itype.index.block_size,
					NTFS_BLOCK_SIZE);
			err = -EOPNOTSUPP;
			goto unm_err_out;
		}
		ni->itype.index.block_size_bits =
				ffs(ni->itype.index.block_size) - 1;
		/* Determine the size of a vcn in the directory index. */
		if (vol->cluster_size <= ni->itype.index.block_size) {
			ni->itype.index.vcn_size = vol->cluster_size;
			ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
		} else {
			ni->itype.index.vcn_size = vol->sector_size;
			ni->itype.index.vcn_size_bits = vol->sector_size_bits;
		}

		/* Setup the index allocation attribute, even if not present. */
		NInoSetMstProtected(ni);
		ni->type = AT_INDEX_ALLOCATION;
		ni->name = I30;
		ni->name_len = 4;

		if (!(ir->index.flags & LARGE_INDEX)) {
			/* No index allocation. */
			vi->i_size = ni->initialized_size =
					ni->allocated_size = 0;
			/* We are done with the mft record, so we release it. */
			ntfs_attr_put_search_ctx(ctx);
			unmap_mft_record(ni);
			m = NULL;
			ctx = NULL;
			goto skip_large_dir_stuff;
		} /* LARGE_INDEX: Index allocation present. Setup state. */
		NInoSetIndexAllocPresent(ni);
		/* Find index allocation attribute. */
		ntfs_attr_reinit_search_ctx(ctx);
		err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, I30, 4,
				CASE_SENSITIVE, 0, NULL, 0, ctx);
		if (unlikely(err)) {
			if (err == -ENOENT)
				ntfs_error(vi->i_sb, "$INDEX_ALLOCATION "
						"attribute is not present but "
						"$INDEX_ROOT indicated it is.");
			else
				ntfs_error(vi->i_sb, "Failed to lookup "
						"$INDEX_ALLOCATION "
						"attribute.");
			goto unm_err_out;
		}
		a = ctx->attr;
		if (!a->non_resident) {
			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
					"is resident.");
			goto unm_err_out;
		}
		/*
		 * Ensure the attribute name is placed before the mapping pairs
		 * array.
		 */
		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
				le16_to_cpu(
				a->data.non_resident.mapping_pairs_offset)))) {
			ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name "
					"is placed after the mapping pairs "
					"array.");
			goto unm_err_out;
		}
		if (a->flags & ATTR_IS_ENCRYPTED) {
			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
					"is encrypted.");
			goto unm_err_out;
		}
		if (a->flags & ATTR_IS_SPARSE) {
			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
					"is sparse.");
			goto unm_err_out;
		}
		if (a->flags & ATTR_COMPRESSION_MASK) {
			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
					"is compressed.");
			goto unm_err_out;
		}
		if (a->data.non_resident.lowest_vcn) {
			ntfs_error(vi->i_sb, "First extent of "
					"$INDEX_ALLOCATION attribute has non "
					"zero lowest_vcn.");
			goto unm_err_out;
		}
		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
		ni->initialized_size = sle64_to_cpu(
				a->data.non_resident.initialized_size);
		ni->allocated_size = sle64_to_cpu(
				a->data.non_resident.allocated_size);
		/*
		 * We are done with the mft record, so we release it. Otherwise
		 * we would deadlock in ntfs_attr_iget().
		 */
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(ni);
		m = NULL;
		ctx = NULL;
		/* Get the index bitmap attribute inode. */
		bvi = ntfs_attr_iget(vi, AT_BITMAP, I30, 4);
		if (IS_ERR(bvi)) {
			ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
			err = PTR_ERR(bvi);
			goto unm_err_out;
		}
		bni = NTFS_I(bvi);
		if (NInoCompressed(bni) || NInoEncrypted(bni) ||
				NInoSparse(bni)) {
			ntfs_error(vi->i_sb, "$BITMAP attribute is compressed "
					"and/or encrypted and/or sparse.");
			goto iput_unm_err_out;
		}
		/* Consistency check bitmap size vs. index allocation size. */
		bvi_size = i_size_read(bvi);
		if ((bvi_size << 3) < (vi->i_size >>
				ni->itype.index.block_size_bits)) {
			ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) "
					"for index allocation (0x%llx).",
					bvi_size << 3, vi->i_size);
			goto iput_unm_err_out;
		}
		/* No longer need the bitmap attribute inode. */
		iput(bvi);
skip_large_dir_stuff:
		/* Setup the operations for this inode. */
		vi->i_op = &ntfs_dir_inode_ops;
		vi->i_fop = &ntfs_dir_ops;
		vi->i_mapping->a_ops = &ntfs_mst_aops;
	} else {
		/* It is a file. */
		ntfs_attr_reinit_search_ctx(ctx);

		/* Setup the data attribute, even if not present. */
		ni->type = AT_DATA;
		ni->name = NULL;
		ni->name_len = 0;

		/* Find first extent of the unnamed data attribute. */
		err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, 0, NULL, 0, ctx);
		if (unlikely(err)) {
			vi->i_size = ni->initialized_size =
					ni->allocated_size = 0;
			if (err != -ENOENT) {
				ntfs_error(vi->i_sb, "Failed to lookup $DATA "
						"attribute.");
				goto unm_err_out;
			}
			/*
			 * FILE_Secure does not have an unnamed $DATA
			 * attribute, so we special case it here.
			 */
			if (vi->i_ino == FILE_Secure)
				goto no_data_attr_special_case;
			/*
			 * Most if not all the system files in the $Extend
			 * system directory do not have unnamed data
			 * attributes so we need to check if the parent
			 * directory of the file is FILE_Extend and if it is
			 * ignore this error. To do this we need to get the
			 * name of this inode from the mft record as the name
			 * contains the back reference to the parent directory.
			 */
			if (ntfs_is_extended_system_file(ctx) > 0)
				goto no_data_attr_special_case;
			// FIXME: File is corrupt! Hot-fix with empty data
			// attribute if recovery option is set.
			ntfs_error(vi->i_sb, "$DATA attribute is missing.");
			goto unm_err_out;
		}
		a = ctx->attr;
		/* Setup the state. */
		if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
			if (a->flags & ATTR_COMPRESSION_MASK) {
				NInoSetCompressed(ni);
				if (vol->cluster_size > 4096) {
					ntfs_error(vi->i_sb, "Found "
							"compressed data but "
							"compression is "
							"disabled due to "
							"cluster size (%i) > "
							"4kiB.",
							vol->cluster_size);
					goto unm_err_out;
				}
				if ((a->flags & ATTR_COMPRESSION_MASK)
						!= ATTR_IS_COMPRESSED) {
					ntfs_error(vi->i_sb, "Found unknown "
							"compression method "
							"or corrupt file.");
					goto unm_err_out;
				}
			}
			if (a->flags & ATTR_IS_SPARSE)
				NInoSetSparse(ni);
		}
		if (a->flags & ATTR_IS_ENCRYPTED) {
			if (NInoCompressed(ni)) {
				ntfs_error(vi->i_sb, "Found encrypted and "
						"compressed data.");
				goto unm_err_out;
			}
			NInoSetEncrypted(ni);
		}
		if (a->non_resident) {
			NInoSetNonResident(ni);
			if (NInoCompressed(ni) || NInoSparse(ni)) {
				if (NInoCompressed(ni) && a->data.non_resident.
						compression_unit != 4) {
					ntfs_error(vi->i_sb, "Found "
							"non-standard "
							"compression unit (%u "
							"instead of 4).  "
							"Cannot handle this.",
							a->data.non_resident.
							compression_unit);
					err = -EOPNOTSUPP;
					goto unm_err_out;
				}
				if (a->data.non_resident.compression_unit) {
					ni->itype.compressed.block_size = 1U <<
							(a->data.non_resident.
							compression_unit +
							vol->cluster_size_bits);
					ni->itype.compressed.block_size_bits =
							ffs(ni->itype.
							compressed.
							block_size) - 1;
					ni->itype.compressed.block_clusters =
							1U << a->data.
							non_resident.
							compression_unit;
				} else {
					ni->itype.compressed.block_size = 0;
					ni->itype.compressed.block_size_bits =
							0;
					ni->itype.compressed.block_clusters =
							0;
				}
				ni->itype.compressed.size = sle64_to_cpu(
						a->data.non_resident.
						compressed_size);
			}
			if (a->data.non_resident.lowest_vcn) {
				ntfs_error(vi->i_sb, "First extent of $DATA "
						"attribute has non zero "
						"lowest_vcn.");
				goto unm_err_out;
			}
			vi->i_size = sle64_to_cpu(
					a->data.non_resident.data_size);
			ni->initialized_size = sle64_to_cpu(
					a->data.non_resident.initialized_size);
			ni->allocated_size = sle64_to_cpu(
					a->data.non_resident.allocated_size);
		} else { /* Resident attribute. */
			vi->i_size = ni->initialized_size = le32_to_cpu(
					a->data.resident.value_length);
			ni->allocated_size = le32_to_cpu(a->length) -
					le16_to_cpu(
					a->data.resident.value_offset);
			if (vi->i_size > ni->allocated_size) {
				ntfs_error(vi->i_sb, "Resident data attribute "
						"is corrupt (size exceeds "
						"allocation).");
				goto unm_err_out;
			}
		}
no_data_attr_special_case:
		/* We are done with the mft record, so we release it. */
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(ni);
		m = NULL;
		ctx = NULL;
		/* Setup the operations for this inode. */
		vi->i_op = &ntfs_file_inode_ops;
		vi->i_fop = &ntfs_file_ops;
		vi->i_mapping->a_ops = &ntfs_normal_aops;
		if (NInoMstProtected(ni))
			vi->i_mapping->a_ops = &ntfs_mst_aops;
		else if (NInoCompressed(ni))
			vi->i_mapping->a_ops = &ntfs_compressed_aops;
	}
	/*
	 * The number of 512-byte blocks used on disk (for stat). This is in so
	 * far inaccurate as it doesn't account for any named streams or other
	 * special non-resident attributes, but that is how Windows works, too,
	 * so we are at least consistent with Windows, if not entirely
	 * consistent with the Linux Way. Doing it the Linux Way would cause a
	 * significant slowdown as it would involve iterating over all
	 * attributes in the mft record and adding the allocated/compressed
	 * sizes of all non-resident attributes present to give us the Linux
	 * correct size that should go into i_blocks (after division by 512).
	 */
	if (S_ISREG(vi->i_mode) && (NInoCompressed(ni) || NInoSparse(ni)))
		vi->i_blocks = ni->itype.compressed.size >> 9;
	else
		vi->i_blocks = ni->allocated_size >> 9;
	ntfs_debug("Done.");
	return 0;
iput_unm_err_out:
	iput(bvi);
unm_err_out:
	if (!err)
		err = -EIO;
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(ni);
err_out:
	ntfs_error(vol->sb, "Failed with error code %i.  Marking corrupt "
			"inode 0x%lx as bad.  Run chkdsk.", err, vi->i_ino);
	make_bad_inode(vi);
	if (err != -EOPNOTSUPP && err != -ENOMEM)
		NVolSetErrors(vol);
	return err;
}

/**
 * ntfs_read_locked_attr_inode - read an attribute inode from its base inode
 * @base_vi:	base inode
 * @vi:		attribute inode to read
 *
 * ntfs_read_locked_attr_inode() is called from ntfs_attr_iget() to read the
 * attribute inode described by @vi into memory from the base mft record
 * described by @base_ni.
 *
 * ntfs_read_locked_attr_inode() maps, pins and locks the base inode for
 * reading and looks up the attribute described by @vi before setting up the
 * necessary fields in @vi as well as initializing the ntfs inode.
 *
 * Q: What locks are held when the function is called?
 * A: i_state has I_NEW set, hence the inode is locked, also
 *    i_count is set to 1, so it is not going to go away
 *
 * Return 0 on success and -errno on error.  In the error case, the inode will
 * have had make_bad_inode() executed on it.
 *
 * Note this cannot be called for AT_INDEX_ALLOCATION.
 */
static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
{
	ntfs_volume *vol = NTFS_SB(vi->i_sb);
	ntfs_inode *ni, *base_ni;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	ntfs_attr_search_ctx *ctx;
	int err = 0;

	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);

	ntfs_init_big_inode(vi);

	ni	= NTFS_I(vi);
	base_ni = NTFS_I(base_vi);

	/* Just mirror the values from the base inode. */
	vi->i_uid	= base_vi->i_uid;
	vi->i_gid	= base_vi->i_gid;
	set_nlink(vi, base_vi->i_nlink);
	vi->i_mtime	= base_vi->i_mtime;
	vi->i_ctime	= base_vi->i_ctime;
	vi->i_atime	= base_vi->i_atime;
	vi->i_generation = ni->seq_no = base_ni->seq_no;

	/* Set inode type to zero but preserve permissions. */
	vi->i_mode	= base_vi->i_mode & ~S_IFMT;

	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (!ctx) {
		err = -ENOMEM;
		goto unm_err_out;
	}
	/* Find the attribute. */
	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err))
		goto unm_err_out;
	a = ctx->attr;
	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
		if (a->flags & ATTR_COMPRESSION_MASK) {
			NInoSetCompressed(ni);
			if ((ni->type != AT_DATA) || (ni->type == AT_DATA &&
					ni->name_len)) {
				ntfs_error(vi->i_sb, "Found compressed "
						"non-data or named data "
						"attribute.  Please report "
						"you saw this message to "
						"linux-ntfs-dev@lists."
						"sourceforge.net");
				goto unm_err_out;
			}
			if (vol->cluster_size > 4096) {
				ntfs_error(vi->i_sb, "Found compressed "
						"attribute but compression is "
						"disabled due to cluster size "
						"(%i) > 4kiB.",
						vol->cluster_size);
				goto unm_err_out;
			}
			if ((a->flags & ATTR_COMPRESSION_MASK) !=
					ATTR_IS_COMPRESSED) {
				ntfs_error(vi->i_sb, "Found unknown "
						"compression method.");
				goto unm_err_out;
			}
		}
		/*
		 * The compressed/sparse flag set in an index root just means
		 * to compress all files.
		 */
		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
			ntfs_error(vi->i_sb, "Found mst protected attribute "
					"but the attribute is %s.  Please "
					"report you saw this message to "
					"linux-ntfs-dev@lists.sourceforge.net",
					NInoCompressed(ni) ? "compressed" :
					"sparse");
			goto unm_err_out;
		}
		if (a->flags & ATTR_IS_SPARSE)
			NInoSetSparse(ni);
	}
	if (a->flags & ATTR_IS_ENCRYPTED) {
		if (NInoCompressed(ni)) {
			ntfs_error(vi->i_sb, "Found encrypted and compressed "
					"data.");
			goto unm_err_out;
		}
		/*
		 * The encryption flag set in an index root just means to
		 * encrypt all files.
		 */
		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
			ntfs_error(vi->i_sb, "Found mst protected attribute "
					"but the attribute is encrypted.  "
					"Please report you saw this message "
					"to linux-ntfs-dev@lists.sourceforge."
					"net");
			goto unm_err_out;
		}
		if (ni->type != AT_DATA) {
			ntfs_error(vi->i_sb, "Found encrypted non-data "
					"attribute.");
			goto unm_err_out;
		}
		NInoSetEncrypted(ni);
	}
	if (!a->non_resident) {
		/* Ensure the attribute name is placed before the value. */
		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
				le16_to_cpu(a->data.resident.value_offset)))) {
			ntfs_error(vol->sb, "Attribute name is placed after "
					"the attribute value.");
			goto unm_err_out;
		}
		if (NInoMstProtected(ni)) {
			ntfs_error(vi->i_sb, "Found mst protected attribute "
					"but the attribute is resident.  "
					"Please report you saw this message to "
					"linux-ntfs-dev@lists.sourceforge.net");
			goto unm_err_out;
		}
		vi->i_size = ni->initialized_size = le32_to_cpu(
				a->data.resident.value_length);
		ni->allocated_size = le32_to_cpu(a->length) -
				le16_to_cpu(a->data.resident.value_offset);
		if (vi->i_size > ni->allocated_size) {
			ntfs_error(vi->i_sb, "Resident attribute is corrupt "
					"(size exceeds allocation).");
			goto unm_err_out;
		}
	} else {
		NInoSetNonResident(ni);
		/*
		 * Ensure the attribute name is placed before the mapping pairs
		 * array.
		 */
		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
				le16_to_cpu(
				a->data.non_resident.mapping_pairs_offset)))) {
			ntfs_error(vol->sb, "Attribute name is placed after "
					"the mapping pairs array.");
			goto unm_err_out;
		}
		if (NInoCompressed(ni) || NInoSparse(ni)) {
			if (NInoCompressed(ni) && a->data.non_resident.
					compression_unit != 4) {
				ntfs_error(vi->i_sb, "Found non-standard "
						"compression unit (%u instead "
						"of 4).  Cannot handle this.",
						a->data.non_resident.
						compression_unit);
				err = -EOPNOTSUPP;
				goto unm_err_out;
			}
			if (a->data.non_resident.compression_unit) {
				ni->itype.compressed.block_size = 1U <<
						(a->data.non_resident.
						compression_unit +
						vol->cluster_size_bits);
				ni->itype.compressed.block_size_bits =
						ffs(ni->itype.compressed.
						block_size) - 1;
				ni->itype.compressed.block_clusters = 1U <<
						a->data.non_resident.
						compression_unit;
			} else {
				ni->itype.compressed.block_size = 0;
				ni->itype.compressed.block_size_bits = 0;
				ni->itype.compressed.block_clusters = 0;
			}
			ni->itype.compressed.size = sle64_to_cpu(
					a->data.non_resident.compressed_size);
		}
		if (a->data.non_resident.lowest_vcn) {
			ntfs_error(vi->i_sb, "First extent of attribute has "
					"non-zero lowest_vcn.");
			goto unm_err_out;
		}
		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
		ni->initialized_size = sle64_to_cpu(
				a->data.non_resident.initialized_size);
		ni->allocated_size = sle64_to_cpu(
				a->data.non_resident.allocated_size);
	}
	vi->i_mapping->a_ops = &ntfs_normal_aops;
	if (NInoMstProtected(ni))
		vi->i_mapping->a_ops = &ntfs_mst_aops;
	else if (NInoCompressed(ni))
		vi->i_mapping->a_ops = &ntfs_compressed_aops;
	if ((NInoCompressed(ni) || NInoSparse(ni)) && ni->type != AT_INDEX_ROOT)
		vi->i_blocks = ni->itype.compressed.size >> 9;
	else
		vi->i_blocks = ni->allocated_size >> 9;
	/*
	 * Make sure the base inode does not go away and attach it to the
	 * attribute inode.
	 */
	igrab(base_vi);
	ni->ext.base_ntfs_ino = base_ni;
	ni->nr_extents = -1;

	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);

	ntfs_debug("Done.");
	return 0;

unm_err_out:
	if (!err)
		err = -EIO;
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
err_out:
	ntfs_error(vol->sb, "Failed with error code %i while reading attribute "
			"inode (mft_no 0x%lx, type 0x%x, name_len %i).  "
			"Marking corrupt inode and base inode 0x%lx as bad.  "
			"Run chkdsk.", err, vi->i_ino, ni->type, ni->name_len,
			base_vi->i_ino);
	make_bad_inode(vi);
	if (err != -ENOMEM)
		NVolSetErrors(vol);
	return err;
}

/**
 * ntfs_read_locked_index_inode - read an index inode from its base inode
 * @base_vi:	base inode
 * @vi:		index inode to read
 *
 * ntfs_read_locked_index_inode() is called from ntfs_index_iget() to read the
 * index inode described by @vi into memory from the base mft record described
 * by @base_ni.
 *
 * ntfs_read_locked_index_inode() maps, pins and locks the base inode for
 * reading and looks up the attributes relating to the index described by @vi
 * before setting up the necessary fields in @vi as well as initializing the
 * ntfs inode.
 *
 * Note, index inodes are essentially attribute inodes (NInoAttr() is true)
 * with the attribute type set to AT_INDEX_ALLOCATION.  Apart from that, they
 * are setup like directory inodes since directories are a special case of
 * indices ao they need to be treated in much the same way.  Most importantly,
 * for small indices the index allocation attribute might not actually exist.
 * However, the index root attribute always exists but this does not need to
 * have an inode associated with it and this is why we define a new inode type
 * index.  Also, like for directories, we need to have an attribute inode for
 * the bitmap attribute corresponding to the index allocation attribute and we
 * can store this in the appropriate field of the inode, just like we do for
 * normal directory inodes.
 *
 * Q: What locks are held when the function is called?
 * A: i_state has I_NEW set, hence the inode is locked, also
 *    i_count is set to 1, so it is not going to go away
 *
 * Return 0 on success and -errno on error.  In the error case, the inode will
 * have had make_bad_inode() executed on it.
 */
static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
{
	loff_t bvi_size;
	ntfs_volume *vol = NTFS_SB(vi->i_sb);
	ntfs_inode *ni, *base_ni, *bni;
	struct inode *bvi;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	ntfs_attr_search_ctx *ctx;
	INDEX_ROOT *ir;
	u8 *ir_end, *index_end;
	int err = 0;

	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
	ntfs_init_big_inode(vi);
	ni	= NTFS_I(vi);
	base_ni = NTFS_I(base_vi);
	/* Just mirror the values from the base inode. */
	vi->i_uid	= base_vi->i_uid;
	vi->i_gid	= base_vi->i_gid;
	set_nlink(vi, base_vi->i_nlink);
	vi->i_mtime	= base_vi->i_mtime;
	vi->i_ctime	= base_vi->i_ctime;
	vi->i_atime	= base_vi->i_atime;
	vi->i_generation = ni->seq_no = base_ni->seq_no;
	/* Set inode type to zero but preserve permissions. */
	vi->i_mode	= base_vi->i_mode & ~S_IFMT;
	/* Map the mft record for the base inode. */
	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (!ctx) {
		err = -ENOMEM;
		goto unm_err_out;
	}
	/* Find the index root attribute. */
	err = ntfs_attr_lookup(AT_INDEX_ROOT, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err)) {
		if (err == -ENOENT)
			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
					"missing.");
		goto unm_err_out;
	}
	a = ctx->attr;
	/* Set up the state. */
	if (unlikely(a->non_resident)) {
		ntfs_error(vol->sb, "$INDEX_ROOT attribute is not resident.");
		goto unm_err_out;
	}
	/* Ensure the attribute name is placed before the value. */
	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
			le16_to_cpu(a->data.resident.value_offset)))) {
		ntfs_error(vol->sb, "$INDEX_ROOT attribute name is placed "
				"after the attribute value.");
		goto unm_err_out;
	}
	/*
	 * Compressed/encrypted/sparse index root is not allowed, except for
	 * directories of course but those are not dealt with here.
	 */
	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_ENCRYPTED |
			ATTR_IS_SPARSE)) {
		ntfs_error(vi->i_sb, "Found compressed/encrypted/sparse index "
				"root attribute.");
		goto unm_err_out;
	}
	ir = (INDEX_ROOT*)((u8*)a + le16_to_cpu(a->data.resident.value_offset));
	ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
	if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
		ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is corrupt.");
		goto unm_err_out;
	}
	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
	if (index_end > ir_end) {
		ntfs_error(vi->i_sb, "Index is corrupt.");
		goto unm_err_out;
	}
	if (ir->type) {
		ntfs_error(vi->i_sb, "Index type is not 0 (type is 0x%x).",
				le32_to_cpu(ir->type));
		goto unm_err_out;
	}
	ni->itype.index.collation_rule = ir->collation_rule;
	ntfs_debug("Index collation rule is 0x%x.",
			le32_to_cpu(ir->collation_rule));
	ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
	if (!is_power_of_2(ni->itype.index.block_size)) {
		ntfs_error(vi->i_sb, "Index block size (%u) is not a power of "
				"two.", ni->itype.index.block_size);
		goto unm_err_out;
	}
	if (ni->itype.index.block_size > PAGE_SIZE) {
		ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_SIZE "
				"(%ld) is not supported.  Sorry.",
				ni->itype.index.block_size, PAGE_SIZE);
		err = -EOPNOTSUPP;
		goto unm_err_out;
	}
	if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
		ntfs_error(vi->i_sb, "Index block size (%u) < NTFS_BLOCK_SIZE "
				"(%i) is not supported.  Sorry.",
				ni->itype.index.block_size, NTFS_BLOCK_SIZE);
		err = -EOPNOTSUPP;
		goto unm_err_out;
	}
	ni->itype.index.block_size_bits = ffs(ni->itype.index.block_size) - 1;
	/* Determine the size of a vcn in the index. */
	if (vol->cluster_size <= ni->itype.index.block_size) {
		ni->itype.index.vcn_size = vol->cluster_size;
		ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
	} else {
		ni->itype.index.vcn_size = vol->sector_size;
		ni->itype.index.vcn_size_bits = vol->sector_size_bits;
	}
	/* Check for presence of index allocation attribute. */
	if (!(ir->index.flags & LARGE_INDEX)) {
		/* No index allocation. */
		vi->i_size = ni->initialized_size = ni->allocated_size = 0;
		/* We are done with the mft record, so we release it. */
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
		m = NULL;
		ctx = NULL;
		goto skip_large_index_stuff;
	} /* LARGE_INDEX:  Index allocation present.  Setup state. */
	NInoSetIndexAllocPresent(ni);
	/* Find index allocation attribute. */
	ntfs_attr_reinit_search_ctx(ctx);
	err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err)) {
		if (err == -ENOENT)
			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
					"not present but $INDEX_ROOT "
					"indicated it is.");
		else
			ntfs_error(vi->i_sb, "Failed to lookup "
					"$INDEX_ALLOCATION attribute.");
		goto unm_err_out;
	}
	a = ctx->attr;
	if (!a->non_resident) {
		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
				"resident.");
		goto unm_err_out;
	}
	/*
	 * Ensure the attribute name is placed before the mapping pairs array.
	 */
	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
			le16_to_cpu(
			a->data.non_resident.mapping_pairs_offset)))) {
		ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name is "
				"placed after the mapping pairs array.");
		goto unm_err_out;
	}
	if (a->flags & ATTR_IS_ENCRYPTED) {
		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
				"encrypted.");
		goto unm_err_out;
	}
	if (a->flags & ATTR_IS_SPARSE) {
		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is sparse.");
		goto unm_err_out;
	}
	if (a->flags & ATTR_COMPRESSION_MASK) {
		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
				"compressed.");
		goto unm_err_out;
	}
	if (a->data.non_resident.lowest_vcn) {
		ntfs_error(vi->i_sb, "First extent of $INDEX_ALLOCATION "
				"attribute has non zero lowest_vcn.");
		goto unm_err_out;
	}
	vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
	ni->initialized_size = sle64_to_cpu(
			a->data.non_resident.initialized_size);
	ni->allocated_size = sle64_to_cpu(a->data.non_resident.allocated_size);
	/*
	 * We are done with the mft record, so we release it.  Otherwise
	 * we would deadlock in ntfs_attr_iget().
	 */
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	m = NULL;
	ctx = NULL;
	/* Get the index bitmap attribute inode. */
	bvi = ntfs_attr_iget(base_vi, AT_BITMAP, ni->name, ni->name_len);
	if (IS_ERR(bvi)) {
		ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
		err = PTR_ERR(bvi);
		goto unm_err_out;
	}
	bni = NTFS_I(bvi);
	if (NInoCompressed(bni) || NInoEncrypted(bni) ||
			NInoSparse(bni)) {
		ntfs_error(vi->i_sb, "$BITMAP attribute is compressed and/or "
				"encrypted and/or sparse.");
		goto iput_unm_err_out;
	}
	/* Consistency check bitmap size vs. index allocation size. */
	bvi_size = i_size_read(bvi);
	if ((bvi_size << 3) < (vi->i_size >> ni->itype.index.block_size_bits)) {
		ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) for "
				"index allocation (0x%llx).", bvi_size << 3,
				vi->i_size);
		goto iput_unm_err_out;
	}
	iput(bvi);
skip_large_index_stuff:
	/* Setup the operations for this index inode. */
	vi->i_mapping->a_ops = &ntfs_mst_aops;
	vi->i_blocks = ni->allocated_size >> 9;
	/*
	 * Make sure the base inode doesn't go away and attach it to the
	 * index inode.
	 */
	igrab(base_vi);
	ni->ext.base_ntfs_ino = base_ni;
	ni->nr_extents = -1;

	ntfs_debug("Done.");
	return 0;
iput_unm_err_out:
	iput(bvi);
unm_err_out:
	if (!err)
		err = -EIO;
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
err_out:
	ntfs_error(vi->i_sb, "Failed with error code %i while reading index "
			"inode (mft_no 0x%lx, name_len %i.", err, vi->i_ino,
			ni->name_len);
	make_bad_inode(vi);
	if (err != -EOPNOTSUPP && err != -ENOMEM)
		NVolSetErrors(vol);
	return err;
}

/*
 * The MFT inode has special locking, so teach the lock validator
 * about this by splitting off the locking rules of the MFT from
 * the locking rules of other inodes. The MFT inode can never be
 * accessed from the VFS side (or even internally), only by the
 * map_mft functions.
 */
static struct lock_class_key mft_ni_runlist_lock_key, mft_ni_mrec_lock_key;

/**
 * ntfs_read_inode_mount - special read_inode for mount time use only
 * @vi:		inode to read
 *
 * Read inode FILE_MFT at mount time, only called with super_block lock
 * held from within the read_super() code path.
 *
 * This function exists because when it is called the page cache for $MFT/$DATA
 * is not initialized and hence we cannot get at the contents of mft records
 * by calling map_mft_record*().
 *
 * Further it needs to cope with the circular references problem, i.e. cannot
 * load any attributes other than $ATTRIBUTE_LIST until $DATA is loaded, because
 * we do not know where the other extent mft records are yet and again, because
 * we cannot call map_mft_record*() yet.  Obviously this applies only when an
 * attribute list is actually present in $MFT inode.
 *
 * We solve these problems by starting with the $DATA attribute before anything
 * else and iterating using ntfs_attr_lookup($DATA) over all extents.  As each
 * extent is found, we ntfs_mapping_pairs_decompress() including the implied
 * ntfs_runlists_merge().  Each step of the iteration necessarily provides
 * sufficient information for the next step to complete.
 *
 * This should work but there are two possible pit falls (see inline comments
 * below), but only time will tell if they are real pits or just smoke...
 */
int ntfs_read_inode_mount(struct inode *vi)
{
	VCN next_vcn, last_vcn, highest_vcn;
	s64 block;
	struct super_block *sb = vi->i_sb;
	ntfs_volume *vol = NTFS_SB(sb);
	struct buffer_head *bh;
	ntfs_inode *ni;
	MFT_RECORD *m = NULL;
	ATTR_RECORD *a;
	ntfs_attr_search_ctx *ctx;
	unsigned int i, nr_blocks;
	int err;

	ntfs_debug("Entering.");

	/* Initialize the ntfs specific part of @vi. */
	ntfs_init_big_inode(vi);

	ni = NTFS_I(vi);

	/* Setup the data attribute. It is special as it is mst protected. */
	NInoSetNonResident(ni);
	NInoSetMstProtected(ni);
	NInoSetSparseDisabled(ni);
	ni->type = AT_DATA;
	ni->name = NULL;
	ni->name_len = 0;
	/*
	 * This sets up our little cheat allowing us to reuse the async read io
	 * completion handler for directories.
	 */
	ni->itype.index.block_size = vol->mft_record_size;
	ni->itype.index.block_size_bits = vol->mft_record_size_bits;

	/* Very important! Needed to be able to call map_mft_record*(). */
	vol->mft_ino = vi;

	/* Allocate enough memory to read the first mft record. */
	if (vol->mft_record_size > 64 * 1024) {
		ntfs_error(sb, "Unsupported mft record size %i (max 64kiB).",
				vol->mft_record_size);
		goto err_out;
	}
	i = vol->mft_record_size;
	if (i < sb->s_blocksize)
		i = sb->s_blocksize;
	m = (MFT_RECORD*)ntfs_malloc_nofs(i);
	if (!m) {
		ntfs_error(sb, "Failed to allocate buffer for $MFT record 0.");
		goto err_out;
	}

	/* Determine the first block of the $MFT/$DATA attribute. */
	block = vol->mft_lcn << vol->cluster_size_bits >>
			sb->s_blocksize_bits;
	nr_blocks = vol->mft_record_size >> sb->s_blocksize_bits;
	if (!nr_blocks)
		nr_blocks = 1;

	/* Load $MFT/$DATA's first mft record. */
	for (i = 0; i < nr_blocks; i++) {
		bh = sb_bread(sb, block++);
		if (!bh) {
			ntfs_error(sb, "Device read failed.");
			goto err_out;
		}
		memcpy((char*)m + (i << sb->s_blocksize_bits), bh->b_data,
				sb->s_blocksize);
		brelse(bh);
	}

	if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) {
		ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.",
				le32_to_cpu(m->bytes_allocated), vol->mft_record_size);
		goto err_out;
	}

	/* Apply the mst fixups. */
	if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) {
		/* FIXME: Try to use the $MFTMirr now. */
		ntfs_error(sb, "MST fixup failed. $MFT is corrupt.");
		goto err_out;
	}

	/* Need this to sanity check attribute list references to $MFT. */
	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);

	/* Provides readpage() for map_mft_record(). */
	vi->i_mapping->a_ops = &ntfs_mst_aops;

	ctx = ntfs_attr_get_search_ctx(ni, m);
	if (!ctx) {
		err = -ENOMEM;
		goto err_out;
	}

	/* Find the attribute list attribute if present. */
	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
	if (err) {
		if (unlikely(err != -ENOENT)) {
			ntfs_error(sb, "Failed to lookup attribute list "
					"attribute. You should run chkdsk.");
			goto put_err_out;
		}
	} else /* if (!err) */ {
		ATTR_LIST_ENTRY *al_entry, *next_al_entry;
		u8 *al_end;
		static const char *es = "  Not allowed.  $MFT is corrupt.  "
				"You should run chkdsk.";

		ntfs_debug("Attribute list attribute found in $MFT.");
		NInoSetAttrList(ni);
		a = ctx->attr;
		if (a->flags & ATTR_COMPRESSION_MASK) {
			ntfs_error(sb, "Attribute list attribute is "
					"compressed.%s", es);
			goto put_err_out;
		}
		if (a->flags & ATTR_IS_ENCRYPTED ||
				a->flags & ATTR_IS_SPARSE) {
			if (a->non_resident) {
				ntfs_error(sb, "Non-resident attribute list "
						"attribute is encrypted/"
						"sparse.%s", es);
				goto put_err_out;
			}
			ntfs_warning(sb, "Resident attribute list attribute "
					"in $MFT system file is marked "
					"encrypted/sparse which is not true.  "
					"However, Windows allows this and "
					"chkdsk does not detect or correct it "
					"so we will just ignore the invalid "
					"flags and pretend they are not set.");
		}
		/* Now allocate memory for the attribute list. */
		ni->attr_list_size = (u32)ntfs_attr_size(a);
		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
		if (!ni->attr_list) {
			ntfs_error(sb, "Not enough memory to allocate buffer "
					"for attribute list.");
			goto put_err_out;
		}
		if (a->non_resident) {
			NInoSetAttrListNonResident(ni);
			if (a->data.non_resident.lowest_vcn) {
				ntfs_error(sb, "Attribute list has non zero "
						"lowest_vcn. $MFT is corrupt. "
						"You should run chkdsk.");
				goto put_err_out;
			}
			/* Setup the runlist. */
			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
					a, NULL);
			if (IS_ERR(ni->attr_list_rl.rl)) {
				err = PTR_ERR(ni->attr_list_rl.rl);
				ni->attr_list_rl.rl = NULL;
				ntfs_error(sb, "Mapping pairs decompression "
						"failed with error code %i.",
						-err);
				goto put_err_out;
			}
			/* Now load the attribute list. */
			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
					ni->attr_list, ni->attr_list_size,
					sle64_to_cpu(a->data.
					non_resident.initialized_size)))) {
				ntfs_error(sb, "Failed to load attribute list "
						"attribute with error code %i.",
						-err);
				goto put_err_out;
			}
		} else /* if (!ctx.attr->non_resident) */ {
			if ((u8*)a + le16_to_cpu(
					a->data.resident.value_offset) +
					le32_to_cpu(
					a->data.resident.value_length) >
					(u8*)ctx->mrec + vol->mft_record_size) {
				ntfs_error(sb, "Corrupt attribute list "
						"attribute.");
				goto put_err_out;
			}
			/* Now copy the attribute list. */
			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
					a->data.resident.value_offset),
					le32_to_cpu(
					a->data.resident.value_length));
		}
		/* The attribute list is now setup in memory. */
		/*
		 * FIXME: I don't know if this case is actually possible.
		 * According to logic it is not possible but I have seen too
		 * many weird things in MS software to rely on logic... Thus we
		 * perform a manual search and make sure the first $MFT/$DATA
		 * extent is in the base inode. If it is not we abort with an
		 * error and if we ever see a report of this error we will need
		 * to do some magic in order to have the necessary mft record
		 * loaded and in the right place in the page cache. But
		 * hopefully logic will prevail and this never happens...
		 */
		al_entry = (ATTR_LIST_ENTRY*)ni->attr_list;
		al_end = (u8*)al_entry + ni->attr_list_size;
		for (;; al_entry = next_al_entry) {
			/* Out of bounds check. */
			if ((u8*)al_entry < ni->attr_list ||
					(u8*)al_entry > al_end)
				goto em_put_err_out;
			/* Catch the end of the attribute list. */
			if ((u8*)al_entry == al_end)
				goto em_put_err_out;
			if (!al_entry->length)
				goto em_put_err_out;
			if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
					le16_to_cpu(al_entry->length) > al_end)
				goto em_put_err_out;
			next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
					le16_to_cpu(al_entry->length));
			if (le32_to_cpu(al_entry->type) > le32_to_cpu(AT_DATA))
				goto em_put_err_out;
			if (AT_DATA != al_entry->type)
				continue;
			/* We want an unnamed attribute. */
			if (al_entry->name_length)
				goto em_put_err_out;
			/* Want the first entry, i.e. lowest_vcn == 0. */
			if (al_entry->lowest_vcn)
				goto em_put_err_out;
			/* First entry has to be in the base mft record. */
			if (MREF_LE(al_entry->mft_reference) != vi->i_ino) {
				/* MFT references do not match, logic fails. */
				ntfs_error(sb, "BUG: The first $DATA extent "
						"of $MFT is not in the base "
						"mft record. Please report "
						"you saw this message to "
						"linux-ntfs-dev@lists."
						"sourceforge.net");
				goto put_err_out;
			} else {
				/* Sequence numbers must match. */
				if (MSEQNO_LE(al_entry->mft_reference) !=
						ni->seq_no)
					goto em_put_err_out;
				/* Got it. All is ok. We can stop now. */
				break;
			}
		}
	}

	ntfs_attr_reinit_search_ctx(ctx);

	/* Now load all attribute extents. */
	a = NULL;
	next_vcn = last_vcn = highest_vcn = 0;
	while (!(err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, next_vcn, NULL, 0,
			ctx))) {
		runlist_element *nrl;

		/* Cache the current attribute. */
		a = ctx->attr;
		/* $MFT must be non-resident. */
		if (!a->non_resident) {
			ntfs_error(sb, "$MFT must be non-resident but a "
					"resident extent was found. $MFT is "
					"corrupt. Run chkdsk.");
			goto put_err_out;
		}
		/* $MFT must be uncompressed and unencrypted. */
		if (a->flags & ATTR_COMPRESSION_MASK ||
				a->flags & ATTR_IS_ENCRYPTED ||
				a->flags & ATTR_IS_SPARSE) {
			ntfs_error(sb, "$MFT must be uncompressed, "
					"non-sparse, and unencrypted but a "
					"compressed/sparse/encrypted extent "
					"was found. $MFT is corrupt. Run "
					"chkdsk.");
			goto put_err_out;
		}
		/*
		 * Decompress the mapping pairs array of this extent and merge
		 * the result into the existing runlist. No need for locking
		 * as we have exclusive access to the inode at this time and we
		 * are a mount in progress task, too.
		 */
		nrl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
		if (IS_ERR(nrl)) {
			ntfs_error(sb, "ntfs_mapping_pairs_decompress() "
					"failed with error code %ld.  $MFT is "
					"corrupt.", PTR_ERR(nrl));
			goto put_err_out;
		}
		ni->runlist.rl = nrl;

		/* Are we in the first extent? */
		if (!next_vcn) {
			if (a->data.non_resident.lowest_vcn) {
				ntfs_error(sb, "First extent of $DATA "
						"attribute has non zero "
						"lowest_vcn. $MFT is corrupt. "
						"You should run chkdsk.");
				goto put_err_out;
			}
			/* Get the last vcn in the $DATA attribute. */
			last_vcn = sle64_to_cpu(
					a->data.non_resident.allocated_size)
					>> vol->cluster_size_bits;
			/* Fill in the inode size. */
			vi->i_size = sle64_to_cpu(
					a->data.non_resident.data_size);
			ni->initialized_size = sle64_to_cpu(
					a->data.non_resident.initialized_size);
			ni->allocated_size = sle64_to_cpu(
					a->data.non_resident.allocated_size);
			/*
			 * Verify the number of mft records does not exceed
			 * 2^32 - 1.
			 */
			if ((vi->i_size >> vol->mft_record_size_bits) >=
					(1ULL << 32)) {
				ntfs_error(sb, "$MFT is too big! Aborting.");
				goto put_err_out;
			}
			/*
			 * We have got the first extent of the runlist for
			 * $MFT which means it is now relatively safe to call
			 * the normal ntfs_read_inode() function.
			 * Complete reading the inode, this will actually
			 * re-read the mft record for $MFT, this time entering
			 * it into the page cache with which we complete the
			 * kick start of the volume. It should be safe to do
			 * this now as the first extent of $MFT/$DATA is
			 * already known and we would hope that we don't need
			 * further extents in order to find the other
			 * attributes belonging to $MFT. Only time will tell if
			 * this is really the case. If not we will have to play
			 * magic at this point, possibly duplicating a lot of
			 * ntfs_read_inode() at this point. We will need to
			 * ensure we do enough of its work to be able to call
			 * ntfs_read_inode() on extents of $MFT/$DATA. But lets
			 * hope this never happens...
			 */
			ntfs_read_locked_inode(vi);
			if (is_bad_inode(vi)) {
				ntfs_error(sb, "ntfs_read_inode() of $MFT "
						"failed. BUG or corrupt $MFT. "
						"Run chkdsk and if no errors "
						"are found, please report you "
						"saw this message to "
						"linux-ntfs-dev@lists."
						"sourceforge.net");
				ntfs_attr_put_search_ctx(ctx);
				/* Revert to the safe super operations. */
				ntfs_free(m);
				return -1;
			}
			/*
			 * Re-initialize some specifics about $MFT's inode as
			 * ntfs_read_inode() will have set up the default ones.
			 */
			/* Set uid and gid to root. */
			vi->i_uid = GLOBAL_ROOT_UID;
			vi->i_gid = GLOBAL_ROOT_GID;
			/* Regular file. No access for anyone. */
			vi->i_mode = S_IFREG;
			/* No VFS initiated operations allowed for $MFT. */
			vi->i_op = &ntfs_empty_inode_ops;
			vi->i_fop = &ntfs_empty_file_ops;
		}

		/* Get the lowest vcn for the next extent. */
		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
		next_vcn = highest_vcn + 1;

		/* Only one extent or error, which we catch below. */
		if (next_vcn <= 0)
			break;

		/* Avoid endless loops due to corruption. */
		if (next_vcn < sle64_to_cpu(
				a->data.non_resident.lowest_vcn)) {
			ntfs_error(sb, "$MFT has corrupt attribute list "
					"attribute. Run chkdsk.");
			goto put_err_out;
		}
	}
	if (err != -ENOENT) {
		ntfs_error(sb, "Failed to lookup $MFT/$DATA attribute extent. "
				"$MFT is corrupt. Run chkdsk.");
		goto put_err_out;
	}
	if (!a) {
		ntfs_error(sb, "$MFT/$DATA attribute not found. $MFT is "
				"corrupt. Run chkdsk.");
		goto put_err_out;
	}
	if (highest_vcn && highest_vcn != last_vcn - 1) {
		ntfs_error(sb, "Failed to load the complete runlist for "
				"$MFT/$DATA. Driver bug or corrupt $MFT. "
				"Run chkdsk.");
		ntfs_debug("highest_vcn = 0x%llx, last_vcn - 1 = 0x%llx",
				(unsigned long long)highest_vcn,
				(unsigned long long)last_vcn - 1);
		goto put_err_out;
	}
	ntfs_attr_put_search_ctx(ctx);
	ntfs_debug("Done.");
	ntfs_free(m);

	/*
	 * Split the locking rules of the MFT inode from the
	 * locking rules of other inodes:
	 */
	lockdep_set_class(&ni->runlist.lock, &mft_ni_runlist_lock_key);
	lockdep_set_class(&ni->mrec_lock, &mft_ni_mrec_lock_key);

	return 0;

em_put_err_out:
	ntfs_error(sb, "Couldn't find first extent of $DATA attribute in "
			"attribute list. $MFT is corrupt. Run chkdsk.");
put_err_out:
	ntfs_attr_put_search_ctx(ctx);
err_out:
	ntfs_error(sb, "Failed. Marking inode as bad.");
	make_bad_inode(vi);
	ntfs_free(m);
	return -1;
}

static void __ntfs_clear_inode(ntfs_inode *ni)
{
	/* Free all alocated memory. */
	down_write(&ni->runlist.lock);
	if (ni->runlist.rl) {
		ntfs_free(ni->runlist.rl);
		ni->runlist.rl = NULL;
	}
	up_write(&ni->runlist.lock);

	if (ni->attr_list) {
		ntfs_free(ni->attr_list);
		ni->attr_list = NULL;
	}

	down_write(&ni->attr_list_rl.lock);
	if (ni->attr_list_rl.rl) {
		ntfs_free(ni->attr_list_rl.rl);
		ni->attr_list_rl.rl = NULL;
	}
	up_write(&ni->attr_list_rl.lock);

	if (ni->name_len && ni->name != I30) {
		/* Catch bugs... */
		BUG_ON(!ni->name);
		kfree(ni->name);
	}
}

void ntfs_clear_extent_inode(ntfs_inode *ni)
{
	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);

	BUG_ON(NInoAttr(ni));
	BUG_ON(ni->nr_extents != -1);

#ifdef NTFS_RW
	if (NInoDirty(ni)) {
		if (!is_bad_inode(VFS_I(ni->ext.base_ntfs_ino)))
			ntfs_error(ni->vol->sb, "Clearing dirty extent inode!  "
					"Losing data!  This is a BUG!!!");
		// FIXME:  Do something!!!
	}
#endif /* NTFS_RW */

	__ntfs_clear_inode(ni);

	/* Bye, bye... */
	ntfs_destroy_extent_inode(ni);
}

/**
 * ntfs_evict_big_inode - clean up the ntfs specific part of an inode
 * @vi:		vfs inode pending annihilation
 *
 * When the VFS is going to remove an inode from memory, ntfs_clear_big_inode()
 * is called, which deallocates all memory belonging to the NTFS specific part
 * of the inode and returns.
 *
 * If the MFT record is dirty, we commit it before doing anything else.
 */
void ntfs_evict_big_inode(struct inode *vi)
{
	ntfs_inode *ni = NTFS_I(vi);

	truncate_inode_pages_final(&vi->i_data);
	clear_inode(vi);

#ifdef NTFS_RW
	if (NInoDirty(ni)) {
		bool was_bad = (is_bad_inode(vi));

		/* Committing the inode also commits all extent inodes. */
		ntfs_commit_inode(vi);

		if (!was_bad && (is_bad_inode(vi) || NInoDirty(ni))) {
			ntfs_error(vi->i_sb, "Failed to commit dirty inode "
					"0x%lx.  Losing data!", vi->i_ino);
			// FIXME:  Do something!!!
		}
	}
#endif /* NTFS_RW */

	/* No need to lock at this stage as no one else has a reference. */
	if (ni->nr_extents > 0) {
		int i;

		for (i = 0; i < ni->nr_extents; i++)
			ntfs_clear_extent_inode(ni->ext.extent_ntfs_inos[i]);
		kfree(ni->ext.extent_ntfs_inos);
	}

	__ntfs_clear_inode(ni);

	if (NInoAttr(ni)) {
		/* Release the base inode if we are holding it. */
		if (ni->nr_extents == -1) {
			iput(VFS_I(ni->ext.base_ntfs_ino));
			ni->nr_extents = 0;
			ni->ext.base_ntfs_ino = NULL;
		}
	}
	BUG_ON(ni->page);
	if (!atomic_dec_and_test(&ni->count))
		BUG();
	return;
}

/**
 * ntfs_show_options - show mount options in /proc/mounts
 * @sf:		seq_file in which to write our mount options
 * @root:	root of the mounted tree whose mount options to display
 *
 * Called by the VFS once for each mounted ntfs volume when someone reads
 * /proc/mounts in order to display the NTFS specific mount options of each
 * mount. The mount options of fs specified by @root are written to the seq file
 * @sf and success is returned.
 */
int ntfs_show_options(struct seq_file *sf, struct dentry *root)
{
	ntfs_volume *vol = NTFS_SB(root->d_sb);
	int i;

	seq_printf(sf, ",uid=%i", from_kuid_munged(&init_user_ns, vol->uid));
	seq_printf(sf, ",gid=%i", from_kgid_munged(&init_user_ns, vol->gid));
	if (vol->fmask == vol->dmask)
		seq_printf(sf, ",umask=0%o", vol->fmask);
	else {
		seq_printf(sf, ",fmask=0%o", vol->fmask);
		seq_printf(sf, ",dmask=0%o", vol->dmask);
	}
	seq_printf(sf, ",nls=%s", vol->nls_map->charset);
	if (NVolCaseSensitive(vol))
		seq_printf(sf, ",case_sensitive");
	if (NVolShowSystemFiles(vol))
		seq_printf(sf, ",show_sys_files");
	if (!NVolSparseEnabled(vol))
		seq_printf(sf, ",disable_sparse");
	for (i = 0; on_errors_arr[i].val; i++) {
		if (on_errors_arr[i].val & vol->on_errors)
			seq_printf(sf, ",errors=%s", on_errors_arr[i].str);
	}
	seq_printf(sf, ",mft_zone_multiplier=%i", vol->mft_zone_multiplier);
	return 0;
}

#ifdef NTFS_RW

static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
		"chkdsk.";

/**
 * ntfs_truncate - called when the i_size of an ntfs inode is changed
 * @vi:		inode for which the i_size was changed
 *
 * We only support i_size changes for normal files at present, i.e. not
 * compressed and not encrypted.  This is enforced in ntfs_setattr(), see
 * below.
 *
 * The kernel guarantees that @vi is a regular file (S_ISREG() is true) and
 * that the change is allowed.
 *
 * This implies for us that @vi is a file inode rather than a directory, index,
 * or attribute inode as well as that @vi is a base inode.
 *
 * Returns 0 on success or -errno on error.
 *
 * Called with ->i_mutex held.
 */
int ntfs_truncate(struct inode *vi)
{
	s64 new_size, old_size, nr_freed, new_alloc_size, old_alloc_size;
	VCN highest_vcn;
	unsigned long flags;
	ntfs_inode *base_ni, *ni = NTFS_I(vi);
	ntfs_volume *vol = ni->vol;
	ntfs_attr_search_ctx *ctx;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	const char *te = "  Leaving file length out of sync with i_size.";
	int err, mp_size, size_change, alloc_change;

	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
	BUG_ON(NInoAttr(ni));
	BUG_ON(S_ISDIR(vi->i_mode));
	BUG_ON(NInoMstProtected(ni));
	BUG_ON(ni->nr_extents < 0);
retry_truncate:
	/*
	 * Lock the runlist for writing and map the mft record to ensure it is
	 * safe to mess with the attribute runlist and sizes.
	 */
	down_write(&ni->runlist.lock);
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		ntfs_error(vi->i_sb, "Failed to map mft record for inode 0x%lx "
				"(error code %d).%s", vi->i_ino, err, te);
		ctx = NULL;
		m = NULL;
		goto old_bad_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (unlikely(!ctx)) {
		ntfs_error(vi->i_sb, "Failed to allocate a search context for "
				"inode 0x%lx (not enough memory).%s",
				vi->i_ino, te);
		err = -ENOMEM;
		goto old_bad_out;
	}
	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err)) {
		if (err == -ENOENT) {
			ntfs_error(vi->i_sb, "Open attribute is missing from "
					"mft record.  Inode 0x%lx is corrupt.  "
					"Run chkdsk.%s", vi->i_ino, te);
			err = -EIO;
		} else
			ntfs_error(vi->i_sb, "Failed to lookup attribute in "
					"inode 0x%lx (error code %d).%s",
					vi->i_ino, err, te);
		goto old_bad_out;
	}
	m = ctx->mrec;
	a = ctx->attr;
	/*
	 * The i_size of the vfs inode is the new size for the attribute value.
	 */
	new_size = i_size_read(vi);
	/* The current size of the attribute value is the old size. */
	old_size = ntfs_attr_size(a);
	/* Calculate the new allocated size. */
	if (NInoNonResident(ni))
		new_alloc_size = (new_size + vol->cluster_size - 1) &
				~(s64)vol->cluster_size_mask;
	else
		new_alloc_size = (new_size + 7) & ~7;
	/* The current allocated size is the old allocated size. */
	read_lock_irqsave(&ni->size_lock, flags);
	old_alloc_size = ni->allocated_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	/*
	 * The change in the file size.  This will be 0 if no change, >0 if the
	 * size is growing, and <0 if the size is shrinking.
	 */
	size_change = -1;
	if (new_size - old_size >= 0) {
		size_change = 1;
		if (new_size == old_size)
			size_change = 0;
	}
	/* As above for the allocated size. */
	alloc_change = -1;
	if (new_alloc_size - old_alloc_size >= 0) {
		alloc_change = 1;
		if (new_alloc_size == old_alloc_size)
			alloc_change = 0;
	}
	/*
	 * If neither the size nor the allocation are being changed there is
	 * nothing to do.
	 */
	if (!size_change && !alloc_change)
		goto unm_done;
	/* If the size is changing, check if new size is allowed in $AttrDef. */
	if (size_change) {
		err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
		if (unlikely(err)) {
			if (err == -ERANGE) {
				ntfs_error(vol->sb, "Truncate would cause the "
						"inode 0x%lx to %simum size "
						"for its attribute type "
						"(0x%x).  Aborting truncate.",
						vi->i_ino,
						new_size > old_size ? "exceed "
						"the max" : "go under the min",
						le32_to_cpu(ni->type));
				err = -EFBIG;
			} else {
				ntfs_error(vol->sb, "Inode 0x%lx has unknown "
						"attribute type 0x%x.  "
						"Aborting truncate.",
						vi->i_ino,
						le32_to_cpu(ni->type));
				err = -EIO;
			}
			/* Reset the vfs inode size to the old size. */
			i_size_write(vi, old_size);
			goto err_out;
		}
	}
	if (NInoCompressed(ni) || NInoEncrypted(ni)) {
		ntfs_warning(vi->i_sb, "Changes in inode size are not "
				"supported yet for %s files, ignoring.",
				NInoCompressed(ni) ? "compressed" :
				"encrypted");
		err = -EOPNOTSUPP;
		goto bad_out;
	}
	if (a->non_resident)
		goto do_non_resident_truncate;
	BUG_ON(NInoNonResident(ni));
	/* Resize the attribute record to best fit the new attribute size. */
	if (new_size < vol->mft_record_size &&
			!ntfs_resident_attr_value_resize(m, a, new_size)) {
		/* The resize succeeded! */
		flush_dcache_mft_record_page(ctx->ntfs_ino);
		mark_mft_record_dirty(ctx->ntfs_ino);
		write_lock_irqsave(&ni->size_lock, flags);
		/* Update the sizes in the ntfs inode and all is done. */
		ni->allocated_size = le32_to_cpu(a->length) -
				le16_to_cpu(a->data.resident.value_offset);
		/*
		 * Note ntfs_resident_attr_value_resize() has already done any
		 * necessary data clearing in the attribute record.  When the
		 * file is being shrunk vmtruncate() will already have cleared
		 * the top part of the last partial page, i.e. since this is
		 * the resident case this is the page with index 0.  However,
		 * when the file is being expanded, the page cache page data
		 * between the old data_size, i.e. old_size, and the new_size
		 * has not been zeroed.  Fortunately, we do not need to zero it
		 * either since on one hand it will either already be zero due
		 * to both readpage and writepage clearing partial page data
		 * beyond i_size in which case there is nothing to do or in the
		 * case of the file being mmap()ped at the same time, POSIX
		 * specifies that the behaviour is unspecified thus we do not
		 * have to do anything.  This means that in our implementation
		 * in the rare case that the file is mmap()ped and a write
		 * occurred into the mmap()ped region just beyond the file size
		 * and writepage has not yet been called to write out the page
		 * (which would clear the area beyond the file size) and we now
		 * extend the file size to incorporate this dirty region
		 * outside the file size, a write of the page would result in
		 * this data being written to disk instead of being cleared.
		 * Given both POSIX and the Linux mmap(2) man page specify that
		 * this corner case is undefined, we choose to leave it like
		 * that as this is much simpler for us as we cannot lock the
		 * relevant page now since we are holding too many ntfs locks
		 * which would result in a lock reversal deadlock.
		 */
		ni->initialized_size = new_size;
		write_unlock_irqrestore(&ni->size_lock, flags);
		goto unm_done;
	}
	/* If the above resize failed, this must be an attribute extension. */
	BUG_ON(size_change < 0);
	/*
	 * We have to drop all the locks so we can call
	 * ntfs_attr_make_non_resident().  This could be optimised by try-
	 * locking the first page cache page and only if that fails dropping
	 * the locks, locking the page, and redoing all the locking and
	 * lookups.  While this would be a huge optimisation, it is not worth
	 * it as this is definitely a slow code path as it only ever can happen
	 * once for any given file.
	 */
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
	/*
	 * Not enough space in the mft record, try to make the attribute
	 * non-resident and if successful restart the truncation process.
	 */
	err = ntfs_attr_make_non_resident(ni, old_size);
	if (likely(!err))
		goto retry_truncate;
	/*
	 * Could not make non-resident.  If this is due to this not being
	 * permitted for this attribute type or there not being enough space,
	 * try to make other attributes non-resident.  Otherwise fail.
	 */
	if (unlikely(err != -EPERM && err != -ENOSPC)) {
		ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, attribute "
				"type 0x%x, because the conversion from "
				"resident to non-resident attribute failed "
				"with error code %i.", vi->i_ino,
				(unsigned)le32_to_cpu(ni->type), err);
		if (err != -ENOMEM)
			err = -EIO;
		goto conv_err_out;
	}
	/* TODO: Not implemented from here, abort. */
	if (err == -ENOSPC)
		ntfs_error(vol->sb, "Not enough space in the mft record/on "
				"disk for the non-resident attribute value.  "
				"This case is not implemented yet.");
	else /* if (err == -EPERM) */
		ntfs_error(vol->sb, "This attribute type may not be "
				"non-resident.  This case is not implemented "
				"yet.");
	err = -EOPNOTSUPP;
	goto conv_err_out;
#if 0
	// TODO: Attempt to make other attributes non-resident.
	if (!err)
		goto do_resident_extend;
	/*
	 * Both the attribute list attribute and the standard information
	 * attribute must remain in the base inode.  Thus, if this is one of
	 * these attributes, we have to try to move other attributes out into
	 * extent mft records instead.
	 */
	if (ni->type == AT_ATTRIBUTE_LIST ||
			ni->type == AT_STANDARD_INFORMATION) {
		// TODO: Attempt to move other attributes into extent mft
		// records.
		err = -EOPNOTSUPP;
		if (!err)
			goto do_resident_extend;
		goto err_out;
	}
	// TODO: Attempt to move this attribute to an extent mft record, but
	// only if it is not already the only attribute in an mft record in
	// which case there would be nothing to gain.
	err = -EOPNOTSUPP;
	if (!err)
		goto do_resident_extend;
	/* There is nothing we can do to make enough space. )-: */
	goto err_out;
#endif
do_non_resident_truncate:
	BUG_ON(!NInoNonResident(ni));
	if (alloc_change < 0) {
		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
		if (highest_vcn > 0 &&
				old_alloc_size >> vol->cluster_size_bits >
				highest_vcn + 1) {
			/*
			 * This attribute has multiple extents.  Not yet
			 * supported.
			 */
			ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, "
					"attribute type 0x%x, because the "
					"attribute is highly fragmented (it "
					"consists of multiple extents) and "
					"this case is not implemented yet.",
					vi->i_ino,
					(unsigned)le32_to_cpu(ni->type));
			err = -EOPNOTSUPP;
			goto bad_out;
		}
	}
	/*
	 * If the size is shrinking, need to reduce the initialized_size and
	 * the data_size before reducing the allocation.
	 */
	if (size_change < 0) {
		/*
		 * Make the valid size smaller (i_size is already up-to-date).
		 */
		write_lock_irqsave(&ni->size_lock, flags);
		if (new_size < ni->initialized_size) {
			ni->initialized_size = new_size;
			a->data.non_resident.initialized_size =
					cpu_to_sle64(new_size);
		}
		a->data.non_resident.data_size = cpu_to_sle64(new_size);
		write_unlock_irqrestore(&ni->size_lock, flags);
		flush_dcache_mft_record_page(ctx->ntfs_ino);
		mark_mft_record_dirty(ctx->ntfs_ino);
		/* If the allocated size is not changing, we are done. */
		if (!alloc_change)
			goto unm_done;
		/*
		 * If the size is shrinking it makes no sense for the
		 * allocation to be growing.
		 */
		BUG_ON(alloc_change > 0);
	} else /* if (size_change >= 0) */ {
		/*
		 * The file size is growing or staying the same but the
		 * allocation can be shrinking, growing or staying the same.
		 */
		if (alloc_change > 0) {
			/*
			 * We need to extend the allocation and possibly update
			 * the data size.  If we are updating the data size,
			 * since we are not touching the initialized_size we do
			 * not need to worry about the actual data on disk.
			 * And as far as the page cache is concerned, there
			 * will be no pages beyond the old data size and any
			 * partial region in the last page between the old and
			 * new data size (or the end of the page if the new
			 * data size is outside the page) does not need to be
			 * modified as explained above for the resident
			 * attribute truncate case.  To do this, we simply drop
			 * the locks we hold and leave all the work to our
			 * friendly helper ntfs_attr_extend_allocation().
			 */
			ntfs_attr_put_search_ctx(ctx);
			unmap_mft_record(base_ni);
			up_write(&ni->runlist.lock);
			err = ntfs_attr_extend_allocation(ni, new_size,
					size_change > 0 ? new_size : -1, -1);
			/*
			 * ntfs_attr_extend_allocation() will have done error
			 * output already.
			 */
			goto done;
		}
		if (!alloc_change)
			goto alloc_done;
	}
	/* alloc_change < 0 */
	/* Free the clusters. */
	nr_freed = ntfs_cluster_free(ni, new_alloc_size >>
			vol->cluster_size_bits, -1, ctx);
	m = ctx->mrec;
	a = ctx->attr;
	if (unlikely(nr_freed < 0)) {
		ntfs_error(vol->sb, "Failed to release cluster(s) (error code "
				"%lli).  Unmount and run chkdsk to recover "
				"the lost cluster(s).", (long long)nr_freed);
		NVolSetErrors(vol);
		nr_freed = 0;
	}
	/* Truncate the runlist. */
	err = ntfs_rl_truncate_nolock(vol, &ni->runlist,
			new_alloc_size >> vol->cluster_size_bits);
	/*
	 * If the runlist truncation failed and/or the search context is no
	 * longer valid, we cannot resize the attribute record or build the
	 * mapping pairs array thus we mark the inode bad so that no access to
	 * the freed clusters can happen.
	 */
	if (unlikely(err || IS_ERR(m))) {
		ntfs_error(vol->sb, "Failed to %s (error code %li).%s",
				IS_ERR(m) ?
				"restore attribute search context" :
				"truncate attribute runlist",
				IS_ERR(m) ? PTR_ERR(m) : err, es);
		err = -EIO;
		goto bad_out;
	}
	/* Get the size for the shrunk mapping pairs array for the runlist. */
	mp_size = ntfs_get_size_for_mapping_pairs(vol, ni->runlist.rl, 0, -1);
	if (unlikely(mp_size <= 0)) {
		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
				"attribute type 0x%x, because determining the "
				"size for the mapping pairs failed with error "
				"code %i.%s", vi->i_ino,
				(unsigned)le32_to_cpu(ni->type), mp_size, es);
		err = -EIO;
		goto bad_out;
	}
	/*
	 * Shrink the attribute record for the new mapping pairs array.  Note,
	 * this cannot fail since we are making the attribute smaller thus by
	 * definition there is enough space to do so.
	 */
	err = ntfs_attr_record_resize(m, a, mp_size +
			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
	BUG_ON(err);
	/*
	 * Generate the mapping pairs array directly into the attribute record.
	 */
	err = ntfs_mapping_pairs_build(vol, (u8*)a +
			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
			mp_size, ni->runlist.rl, 0, -1, NULL);
	if (unlikely(err)) {
		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
				"attribute type 0x%x, because building the "
				"mapping pairs failed with error code %i.%s",
				vi->i_ino, (unsigned)le32_to_cpu(ni->type),
				err, es);
		err = -EIO;
		goto bad_out;
	}
	/* Update the allocated/compressed size as well as the highest vcn. */
	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
			vol->cluster_size_bits) - 1);
	write_lock_irqsave(&ni->size_lock, flags);
	ni->allocated_size = new_alloc_size;
	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
	if (NInoSparse(ni) || NInoCompressed(ni)) {
		if (nr_freed) {
			ni->itype.compressed.size -= nr_freed <<
					vol->cluster_size_bits;
			BUG_ON(ni->itype.compressed.size < 0);
			a->data.non_resident.compressed_size = cpu_to_sle64(
					ni->itype.compressed.size);
			vi->i_blocks = ni->itype.compressed.size >> 9;
		}
	} else
		vi->i_blocks = new_alloc_size >> 9;
	write_unlock_irqrestore(&ni->size_lock, flags);
	/*
	 * We have shrunk the allocation.  If this is a shrinking truncate we
	 * have already dealt with the initialized_size and the data_size above
	 * and we are done.  If the truncate is only changing the allocation
	 * and not the data_size, we are also done.  If this is an extending
	 * truncate, need to extend the data_size now which is ensured by the
	 * fact that @size_change is positive.
	 */
alloc_done:
	/*
	 * If the size is growing, need to update it now.  If it is shrinking,
	 * we have already updated it above (before the allocation change).
	 */
	if (size_change > 0)
		a->data.non_resident.data_size = cpu_to_sle64(new_size);
	/* Ensure the modified mft record is written out. */
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	mark_mft_record_dirty(ctx->ntfs_ino);
unm_done:
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
done:
	/* Update the mtime and ctime on the base inode. */
	/* normally ->truncate shouldn't update ctime or mtime,
	 * but ntfs did before so it got a copy & paste version
	 * of file_update_time.  one day someone should fix this
	 * for real.
	 */
	if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) {
		struct timespec64 now = current_time(VFS_I(base_ni));
		int sync_it = 0;

		if (!timespec64_equal(&VFS_I(base_ni)->i_mtime, &now) ||
		    !timespec64_equal(&VFS_I(base_ni)->i_ctime, &now))
			sync_it = 1;
		VFS_I(base_ni)->i_mtime = now;
		VFS_I(base_ni)->i_ctime = now;

		if (sync_it)
			mark_inode_dirty_sync(VFS_I(base_ni));
	}

	if (likely(!err)) {
		NInoClearTruncateFailed(ni);
		ntfs_debug("Done.");
	}
	return err;
old_bad_out:
	old_size = -1;
bad_out:
	if (err != -ENOMEM && err != -EOPNOTSUPP)
		NVolSetErrors(vol);
	if (err != -EOPNOTSUPP)
		NInoSetTruncateFailed(ni);
	else if (old_size >= 0)
		i_size_write(vi, old_size);
err_out:
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
out:
	ntfs_debug("Failed.  Returning error code %i.", err);
	return err;
conv_err_out:
	if (err != -ENOMEM && err != -EOPNOTSUPP)
		NVolSetErrors(vol);
	if (err != -EOPNOTSUPP)
		NInoSetTruncateFailed(ni);
	else
		i_size_write(vi, old_size);
	goto out;
}

/**
 * ntfs_truncate_vfs - wrapper for ntfs_truncate() that has no return value
 * @vi:		inode for which the i_size was changed
 *
 * Wrapper for ntfs_truncate() that has no return value.
 *
 * See ntfs_truncate() description above for details.
 */
#ifdef NTFS_RW
void ntfs_truncate_vfs(struct inode *vi) {
	ntfs_truncate(vi);
}
#endif

/**
 * ntfs_setattr - called from notify_change() when an attribute is being changed
 * @mnt_userns:	user namespace of the mount the inode was found from
 * @dentry:	dentry whose attributes to change
 * @attr:	structure describing the attributes and the changes
 *
 * We have to trap VFS attempts to truncate the file described by @dentry as
 * soon as possible, because we do not implement changes in i_size yet.  So we
 * abort all i_size changes here.
 *
 * We also abort all changes of user, group, and mode as we do not implement
 * the NTFS ACLs yet.
 *
 * Called with ->i_mutex held.
 */
int ntfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
		 struct iattr *attr)
{
	struct inode *vi = d_inode(dentry);
	int err;
	unsigned int ia_valid = attr->ia_valid;

	err = setattr_prepare(&init_user_ns, dentry, attr);
	if (err)
		goto out;
	/* We do not support NTFS ACLs yet. */
	if (ia_valid & (ATTR_UID | ATTR_GID | ATTR_MODE)) {
		ntfs_warning(vi->i_sb, "Changes in user/group/mode are not "
				"supported yet, ignoring.");
		err = -EOPNOTSUPP;
		goto out;
	}
	if (ia_valid & ATTR_SIZE) {
		if (attr->ia_size != i_size_read(vi)) {
			ntfs_inode *ni = NTFS_I(vi);
			/*
			 * FIXME: For now we do not support resizing of
			 * compressed or encrypted files yet.
			 */
			if (NInoCompressed(ni) || NInoEncrypted(ni)) {
				ntfs_warning(vi->i_sb, "Changes in inode size "
						"are not supported yet for "
						"%s files, ignoring.",
						NInoCompressed(ni) ?
						"compressed" : "encrypted");
				err = -EOPNOTSUPP;
			} else {
				truncate_setsize(vi, attr->ia_size);
				ntfs_truncate_vfs(vi);
			}
			if (err || ia_valid == ATTR_SIZE)
				goto out;
		} else {
			/*
			 * We skipped the truncate but must still update
			 * timestamps.
			 */
			ia_valid |= ATTR_MTIME | ATTR_CTIME;
		}
	}
	if (ia_valid & ATTR_ATIME)
		vi->i_atime = attr->ia_atime;
	if (ia_valid & ATTR_MTIME)
		vi->i_mtime = attr->ia_mtime;
	if (ia_valid & ATTR_CTIME)
		vi->i_ctime = attr->ia_ctime;
	mark_inode_dirty(vi);
out:
	return err;
}

/**
 * ntfs_write_inode - write out a dirty inode
 * @vi:		inode to write out
 * @sync:	if true, write out synchronously
 *
 * Write out a dirty inode to disk including any extent inodes if present.
 *
 * If @sync is true, commit the inode to disk and wait for io completion.  This
 * is done using write_mft_record().
 *
 * If @sync is false, just schedule the write to happen but do not wait for i/o
 * completion.  In 2.6 kernels, scheduling usually happens just by virtue of
 * marking the page (and in this case mft record) dirty but we do not implement
 * this yet as write_mft_record() largely ignores the @sync parameter and
 * always performs synchronous writes.
 *
 * Return 0 on success and -errno on error.
 */
int __ntfs_write_inode(struct inode *vi, int sync)
{
	sle64 nt;
	ntfs_inode *ni = NTFS_I(vi);
	ntfs_attr_search_ctx *ctx;
	MFT_RECORD *m;
	STANDARD_INFORMATION *si;
	int err = 0;
	bool modified = false;

	ntfs_debug("Entering for %sinode 0x%lx.", NInoAttr(ni) ? "attr " : "",
			vi->i_ino);
	/*
	 * Dirty attribute inodes are written via their real inodes so just
	 * clean them here.  Access time updates are taken care off when the
	 * real inode is written.
	 */
	if (NInoAttr(ni)) {
		NInoClearDirty(ni);
		ntfs_debug("Done.");
		return 0;
	}
	/* Map, pin, and lock the mft record belonging to the inode. */
	m = map_mft_record(ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		goto err_out;
	}
	/* Update the access times in the standard information attribute. */
	ctx = ntfs_attr_get_search_ctx(ni, m);
	if (unlikely(!ctx)) {
		err = -ENOMEM;
		goto unm_err_out;
	}
	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err)) {
		ntfs_attr_put_search_ctx(ctx);
		goto unm_err_out;
	}
	si = (STANDARD_INFORMATION*)((u8*)ctx->attr +
			le16_to_cpu(ctx->attr->data.resident.value_offset));
	/* Update the access times if they have changed. */
	nt = utc2ntfs(vi->i_mtime);
	if (si->last_data_change_time != nt) {
		ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, "
				"new = 0x%llx", vi->i_ino, (long long)
				sle64_to_cpu(si->last_data_change_time),
				(long long)sle64_to_cpu(nt));
		si->last_data_change_time = nt;
		modified = true;
	}
	nt = utc2ntfs(vi->i_ctime);
	if (si->last_mft_change_time != nt) {
		ntfs_debug("Updating ctime for inode 0x%lx: old = 0x%llx, "
				"new = 0x%llx", vi->i_ino, (long long)
				sle64_to_cpu(si->last_mft_change_time),
				(long long)sle64_to_cpu(nt));
		si->last_mft_change_time = nt;
		modified = true;
	}
	nt = utc2ntfs(vi->i_atime);
	if (si->last_access_time != nt) {
		ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, "
				"new = 0x%llx", vi->i_ino,
				(long long)sle64_to_cpu(si->last_access_time),
				(long long)sle64_to_cpu(nt));
		si->last_access_time = nt;
		modified = true;
	}
	/*
	 * If we just modified the standard information attribute we need to
	 * mark the mft record it is in dirty.  We do this manually so that
	 * mark_inode_dirty() is not called which would redirty the inode and
	 * hence result in an infinite loop of trying to write the inode.
	 * There is no need to mark the base inode nor the base mft record
	 * dirty, since we are going to write this mft record below in any case
	 * and the base mft record may actually not have been modified so it
	 * might not need to be written out.
	 * NOTE: It is not a problem when the inode for $MFT itself is being
	 * written out as mark_ntfs_record_dirty() will only set I_DIRTY_PAGES
	 * on the $MFT inode and hence ntfs_write_inode() will not be
	 * re-invoked because of it which in turn is ok since the dirtied mft
	 * record will be cleaned and written out to disk below, i.e. before
	 * this function returns.
	 */
	if (modified) {
		flush_dcache_mft_record_page(ctx->ntfs_ino);
		if (!NInoTestSetDirty(ctx->ntfs_ino))
			mark_ntfs_record_dirty(ctx->ntfs_ino->page,
					ctx->ntfs_ino->page_ofs);
	}
	ntfs_attr_put_search_ctx(ctx);
	/* Now the access times are updated, write the base mft record. */
	if (NInoDirty(ni))
		err = write_mft_record(ni, m, sync);
	/* Write all attached extent mft records. */
	mutex_lock(&ni->extent_lock);
	if (ni->nr_extents > 0) {
		ntfs_inode **extent_nis = ni->ext.extent_ntfs_inos;
		int i;

		ntfs_debug("Writing %i extent inodes.", ni->nr_extents);
		for (i = 0; i < ni->nr_extents; i++) {
			ntfs_inode *tni = extent_nis[i];

			if (NInoDirty(tni)) {
				MFT_RECORD *tm = map_mft_record(tni);
				int ret;

				if (IS_ERR(tm)) {
					if (!err || err == -ENOMEM)
						err = PTR_ERR(tm);
					continue;
				}
				ret = write_mft_record(tni, tm, sync);
				unmap_mft_record(tni);
				if (unlikely(ret)) {
					if (!err || err == -ENOMEM)
						err = ret;
				}
			}
		}
	}
	mutex_unlock(&ni->extent_lock);
	unmap_mft_record(ni);
	if (unlikely(err))
		goto err_out;
	ntfs_debug("Done.");
	return 0;
unm_err_out:
	unmap_mft_record(ni);
err_out:
	if (err == -ENOMEM) {
		ntfs_warning(vi->i_sb, "Not enough memory to write inode.  "
				"Marking the inode dirty again, so the VFS "
				"retries later.");
		mark_inode_dirty(vi);
	} else {
		ntfs_error(vi->i_sb, "Failed (error %i):  Run chkdsk.", -err);
		NVolSetErrors(ni->vol);
	}
	return err;
}

#endif /* NTFS_RW */