summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs/xfs_ialloc.c
blob: 5118dedf9267b2dbc71308eaeeae3c62d5cdeafc (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_icreate_item.h"
#include "xfs_icache.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"

/*
 * Lookup a record by ino in the btree given by cur.
 */
int					/* error */
xfs_inobt_lookup(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agino_t		ino,	/* starting inode of chunk */
	xfs_lookup_t		dir,	/* <=, >=, == */
	int			*stat)	/* success/failure */
{
	cur->bc_rec.i.ir_startino = ino;
	cur->bc_rec.i.ir_holemask = 0;
	cur->bc_rec.i.ir_count = 0;
	cur->bc_rec.i.ir_freecount = 0;
	cur->bc_rec.i.ir_free = 0;
	return xfs_btree_lookup(cur, dir, stat);
}

/*
 * Update the record referred to by cur to the value given.
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int				/* error */
xfs_inobt_update(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_inobt_rec_incore_t	*irec)	/* btree record */
{
	union xfs_btree_rec	rec;

	rec.inobt.ir_startino = cpu_to_be32(irec->ir_startino);
	if (xfs_has_sparseinodes(cur->bc_mp)) {
		rec.inobt.ir_u.sp.ir_holemask = cpu_to_be16(irec->ir_holemask);
		rec.inobt.ir_u.sp.ir_count = irec->ir_count;
		rec.inobt.ir_u.sp.ir_freecount = irec->ir_freecount;
	} else {
		/* ir_holemask/ir_count not supported on-disk */
		rec.inobt.ir_u.f.ir_freecount = cpu_to_be32(irec->ir_freecount);
	}
	rec.inobt.ir_free = cpu_to_be64(irec->ir_free);
	return xfs_btree_update(cur, &rec);
}

/* Convert on-disk btree record to incore inobt record. */
void
xfs_inobt_btrec_to_irec(
	struct xfs_mount		*mp,
	const union xfs_btree_rec	*rec,
	struct xfs_inobt_rec_incore	*irec)
{
	irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino);
	if (xfs_has_sparseinodes(mp)) {
		irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask);
		irec->ir_count = rec->inobt.ir_u.sp.ir_count;
		irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount;
	} else {
		/*
		 * ir_holemask/ir_count not supported on-disk. Fill in hardcoded
		 * values for full inode chunks.
		 */
		irec->ir_holemask = XFS_INOBT_HOLEMASK_FULL;
		irec->ir_count = XFS_INODES_PER_CHUNK;
		irec->ir_freecount =
				be32_to_cpu(rec->inobt.ir_u.f.ir_freecount);
	}
	irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
}

/*
 * Get the data from the pointed-to record.
 */
int
xfs_inobt_get_rec(
	struct xfs_btree_cur		*cur,
	struct xfs_inobt_rec_incore	*irec,
	int				*stat)
{
	struct xfs_mount		*mp = cur->bc_mp;
	union xfs_btree_rec		*rec;
	int				error;
	uint64_t			realfree;

	error = xfs_btree_get_rec(cur, &rec, stat);
	if (error || *stat == 0)
		return error;

	xfs_inobt_btrec_to_irec(mp, rec, irec);

	if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino))
		goto out_bad_rec;
	if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT ||
	    irec->ir_count > XFS_INODES_PER_CHUNK)
		goto out_bad_rec;
	if (irec->ir_freecount > XFS_INODES_PER_CHUNK)
		goto out_bad_rec;

	/* if there are no holes, return the first available offset */
	if (!xfs_inobt_issparse(irec->ir_holemask))
		realfree = irec->ir_free;
	else
		realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec);
	if (hweight64(realfree) != irec->ir_freecount)
		goto out_bad_rec;

	return 0;

out_bad_rec:
	xfs_warn(mp,
		"%s Inode BTree record corruption in AG %d detected!",
		cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
		cur->bc_ag.pag->pag_agno);
	xfs_warn(mp,
"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
		irec->ir_startino, irec->ir_count, irec->ir_freecount,
		irec->ir_free, irec->ir_holemask);
	return -EFSCORRUPTED;
}

/*
 * Insert a single inobt record. Cursor must already point to desired location.
 */
int
xfs_inobt_insert_rec(
	struct xfs_btree_cur	*cur,
	uint16_t		holemask,
	uint8_t			count,
	int32_t			freecount,
	xfs_inofree_t		free,
	int			*stat)
{
	cur->bc_rec.i.ir_holemask = holemask;
	cur->bc_rec.i.ir_count = count;
	cur->bc_rec.i.ir_freecount = freecount;
	cur->bc_rec.i.ir_free = free;
	return xfs_btree_insert(cur, stat);
}

/*
 * Insert records describing a newly allocated inode chunk into the inobt.
 */
STATIC int
xfs_inobt_insert(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_perag	*pag,
	xfs_agino_t		newino,
	xfs_agino_t		newlen,
	xfs_btnum_t		btnum)
{
	struct xfs_btree_cur	*cur;
	xfs_agino_t		thisino;
	int			i;
	int			error;

	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum);

	for (thisino = newino;
	     thisino < newino + newlen;
	     thisino += XFS_INODES_PER_CHUNK) {
		error = xfs_inobt_lookup(cur, thisino, XFS_LOOKUP_EQ, &i);
		if (error) {
			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
			return error;
		}
		ASSERT(i == 0);

		error = xfs_inobt_insert_rec(cur, XFS_INOBT_HOLEMASK_FULL,
					     XFS_INODES_PER_CHUNK,
					     XFS_INODES_PER_CHUNK,
					     XFS_INOBT_ALL_FREE, &i);
		if (error) {
			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
			return error;
		}
		ASSERT(i == 1);
	}

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);

	return 0;
}

/*
 * Verify that the number of free inodes in the AGI is correct.
 */
#ifdef DEBUG
static int
xfs_check_agi_freecount(
	struct xfs_btree_cur	*cur)
{
	if (cur->bc_nlevels == 1) {
		xfs_inobt_rec_incore_t rec;
		int		freecount = 0;
		int		error;
		int		i;

		error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
		if (error)
			return error;

		do {
			error = xfs_inobt_get_rec(cur, &rec, &i);
			if (error)
				return error;

			if (i) {
				freecount += rec.ir_freecount;
				error = xfs_btree_increment(cur, 0, &i);
				if (error)
					return error;
			}
		} while (i == 1);

		if (!xfs_is_shutdown(cur->bc_mp))
			ASSERT(freecount == cur->bc_ag.pag->pagi_freecount);
	}
	return 0;
}
#else
#define xfs_check_agi_freecount(cur)	0
#endif

/*
 * Initialise a new set of inodes. When called without a transaction context
 * (e.g. from recovery) we initiate a delayed write of the inode buffers rather
 * than logging them (which in a transaction context puts them into the AIL
 * for writeback rather than the xfsbufd queue).
 */
int
xfs_ialloc_inode_init(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct list_head	*buffer_list,
	int			icount,
	xfs_agnumber_t		agno,
	xfs_agblock_t		agbno,
	xfs_agblock_t		length,
	unsigned int		gen)
{
	struct xfs_buf		*fbuf;
	struct xfs_dinode	*free;
	int			nbufs;
	int			version;
	int			i, j;
	xfs_daddr_t		d;
	xfs_ino_t		ino = 0;
	int			error;

	/*
	 * Loop over the new block(s), filling in the inodes.  For small block
	 * sizes, manipulate the inodes in buffers  which are multiples of the
	 * blocks size.
	 */
	nbufs = length / M_IGEO(mp)->blocks_per_cluster;

	/*
	 * Figure out what version number to use in the inodes we create.  If
	 * the superblock version has caught up to the one that supports the new
	 * inode format, then use the new inode version.  Otherwise use the old
	 * version so that old kernels will continue to be able to use the file
	 * system.
	 *
	 * For v3 inodes, we also need to write the inode number into the inode,
	 * so calculate the first inode number of the chunk here as
	 * XFS_AGB_TO_AGINO() only works within a filesystem block, not
	 * across multiple filesystem blocks (such as a cluster) and so cannot
	 * be used in the cluster buffer loop below.
	 *
	 * Further, because we are writing the inode directly into the buffer
	 * and calculating a CRC on the entire inode, we have ot log the entire
	 * inode so that the entire range the CRC covers is present in the log.
	 * That means for v3 inode we log the entire buffer rather than just the
	 * inode cores.
	 */
	if (xfs_has_v3inodes(mp)) {
		version = 3;
		ino = XFS_AGINO_TO_INO(mp, agno, XFS_AGB_TO_AGINO(mp, agbno));

		/*
		 * log the initialisation that is about to take place as an
		 * logical operation. This means the transaction does not
		 * need to log the physical changes to the inode buffers as log
		 * recovery will know what initialisation is actually needed.
		 * Hence we only need to log the buffers as "ordered" buffers so
		 * they track in the AIL as if they were physically logged.
		 */
		if (tp)
			xfs_icreate_log(tp, agno, agbno, icount,
					mp->m_sb.sb_inodesize, length, gen);
	} else
		version = 2;

	for (j = 0; j < nbufs; j++) {
		/*
		 * Get the block.
		 */
		d = XFS_AGB_TO_DADDR(mp, agno, agbno +
				(j * M_IGEO(mp)->blocks_per_cluster));
		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
				mp->m_bsize * M_IGEO(mp)->blocks_per_cluster,
				XBF_UNMAPPED, &fbuf);
		if (error)
			return error;

		/* Initialize the inode buffers and log them appropriately. */
		fbuf->b_ops = &xfs_inode_buf_ops;
		xfs_buf_zero(fbuf, 0, BBTOB(fbuf->b_length));
		for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) {
			int	ioffset = i << mp->m_sb.sb_inodelog;

			free = xfs_make_iptr(mp, fbuf, i);
			free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
			free->di_version = version;
			free->di_gen = cpu_to_be32(gen);
			free->di_next_unlinked = cpu_to_be32(NULLAGINO);

			if (version == 3) {
				free->di_ino = cpu_to_be64(ino);
				ino++;
				uuid_copy(&free->di_uuid,
					  &mp->m_sb.sb_meta_uuid);
				xfs_dinode_calc_crc(mp, free);
			} else if (tp) {
				/* just log the inode core */
				xfs_trans_log_buf(tp, fbuf, ioffset,
					  ioffset + XFS_DINODE_SIZE(mp) - 1);
			}
		}

		if (tp) {
			/*
			 * Mark the buffer as an inode allocation buffer so it
			 * sticks in AIL at the point of this allocation
			 * transaction. This ensures the they are on disk before
			 * the tail of the log can be moved past this
			 * transaction (i.e. by preventing relogging from moving
			 * it forward in the log).
			 */
			xfs_trans_inode_alloc_buf(tp, fbuf);
			if (version == 3) {
				/*
				 * Mark the buffer as ordered so that they are
				 * not physically logged in the transaction but
				 * still tracked in the AIL as part of the
				 * transaction and pin the log appropriately.
				 */
				xfs_trans_ordered_buf(tp, fbuf);
			}
		} else {
			fbuf->b_flags |= XBF_DONE;
			xfs_buf_delwri_queue(fbuf, buffer_list);
			xfs_buf_relse(fbuf);
		}
	}
	return 0;
}

/*
 * Align startino and allocmask for a recently allocated sparse chunk such that
 * they are fit for insertion (or merge) into the on-disk inode btrees.
 *
 * Background:
 *
 * When enabled, sparse inode support increases the inode alignment from cluster
 * size to inode chunk size. This means that the minimum range between two
 * non-adjacent inode records in the inobt is large enough for a full inode
 * record. This allows for cluster sized, cluster aligned block allocation
 * without need to worry about whether the resulting inode record overlaps with
 * another record in the tree. Without this basic rule, we would have to deal
 * with the consequences of overlap by potentially undoing recent allocations in
 * the inode allocation codepath.
 *
 * Because of this alignment rule (which is enforced on mount), there are two
 * inobt possibilities for newly allocated sparse chunks. One is that the
 * aligned inode record for the chunk covers a range of inodes not already
 * covered in the inobt (i.e., it is safe to insert a new sparse record). The
 * other is that a record already exists at the aligned startino that considers
 * the newly allocated range as sparse. In the latter case, record content is
 * merged in hope that sparse inode chunks fill to full chunks over time.
 */
STATIC void
xfs_align_sparse_ino(
	struct xfs_mount		*mp,
	xfs_agino_t			*startino,
	uint16_t			*allocmask)
{
	xfs_agblock_t			agbno;
	xfs_agblock_t			mod;
	int				offset;

	agbno = XFS_AGINO_TO_AGBNO(mp, *startino);
	mod = agbno % mp->m_sb.sb_inoalignmt;
	if (!mod)
		return;

	/* calculate the inode offset and align startino */
	offset = XFS_AGB_TO_AGINO(mp, mod);
	*startino -= offset;

	/*
	 * Since startino has been aligned down, left shift allocmask such that
	 * it continues to represent the same physical inodes relative to the
	 * new startino.
	 */
	*allocmask <<= offset / XFS_INODES_PER_HOLEMASK_BIT;
}

/*
 * Determine whether the source inode record can merge into the target. Both
 * records must be sparse, the inode ranges must match and there must be no
 * allocation overlap between the records.
 */
STATIC bool
__xfs_inobt_can_merge(
	struct xfs_inobt_rec_incore	*trec,	/* tgt record */
	struct xfs_inobt_rec_incore	*srec)	/* src record */
{
	uint64_t			talloc;
	uint64_t			salloc;

	/* records must cover the same inode range */
	if (trec->ir_startino != srec->ir_startino)
		return false;

	/* both records must be sparse */
	if (!xfs_inobt_issparse(trec->ir_holemask) ||
	    !xfs_inobt_issparse(srec->ir_holemask))
		return false;

	/* both records must track some inodes */
	if (!trec->ir_count || !srec->ir_count)
		return false;

	/* can't exceed capacity of a full record */
	if (trec->ir_count + srec->ir_count > XFS_INODES_PER_CHUNK)
		return false;

	/* verify there is no allocation overlap */
	talloc = xfs_inobt_irec_to_allocmask(trec);
	salloc = xfs_inobt_irec_to_allocmask(srec);
	if (talloc & salloc)
		return false;

	return true;
}

/*
 * Merge the source inode record into the target. The caller must call
 * __xfs_inobt_can_merge() to ensure the merge is valid.
 */
STATIC void
__xfs_inobt_rec_merge(
	struct xfs_inobt_rec_incore	*trec,	/* target */
	struct xfs_inobt_rec_incore	*srec)	/* src */
{
	ASSERT(trec->ir_startino == srec->ir_startino);

	/* combine the counts */
	trec->ir_count += srec->ir_count;
	trec->ir_freecount += srec->ir_freecount;

	/*
	 * Merge the holemask and free mask. For both fields, 0 bits refer to
	 * allocated inodes. We combine the allocated ranges with bitwise AND.
	 */
	trec->ir_holemask &= srec->ir_holemask;
	trec->ir_free &= srec->ir_free;
}

/*
 * Insert a new sparse inode chunk into the associated inode btree. The inode
 * record for the sparse chunk is pre-aligned to a startino that should match
 * any pre-existing sparse inode record in the tree. This allows sparse chunks
 * to fill over time.
 *
 * This function supports two modes of handling preexisting records depending on
 * the merge flag. If merge is true, the provided record is merged with the
 * existing record and updated in place. The merged record is returned in nrec.
 * If merge is false, an existing record is replaced with the provided record.
 * If no preexisting record exists, the provided record is always inserted.
 *
 * It is considered corruption if a merge is requested and not possible. Given
 * the sparse inode alignment constraints, this should never happen.
 */
STATIC int
xfs_inobt_insert_sprec(
	struct xfs_mount		*mp,
	struct xfs_trans		*tp,
	struct xfs_buf			*agbp,
	struct xfs_perag		*pag,
	int				btnum,
	struct xfs_inobt_rec_incore	*nrec,	/* in/out: new/merged rec. */
	bool				merge)	/* merge or replace */
{
	struct xfs_btree_cur		*cur;
	int				error;
	int				i;
	struct xfs_inobt_rec_incore	rec;

	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum);

	/* the new record is pre-aligned so we know where to look */
	error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
	if (error)
		goto error;
	/* if nothing there, insert a new record and return */
	if (i == 0) {
		error = xfs_inobt_insert_rec(cur, nrec->ir_holemask,
					     nrec->ir_count, nrec->ir_freecount,
					     nrec->ir_free, &i);
		if (error)
			goto error;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error;
		}

		goto out;
	}

	/*
	 * A record exists at this startino. Merge or replace the record
	 * depending on what we've been asked to do.
	 */
	if (merge) {
		error = xfs_inobt_get_rec(cur, &rec, &i);
		if (error)
			goto error;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error;
		}
		if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
			error = -EFSCORRUPTED;
			goto error;
		}

		/*
		 * This should never fail. If we have coexisting records that
		 * cannot merge, something is seriously wrong.
		 */
		if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
			error = -EFSCORRUPTED;
			goto error;
		}

		trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
					 rec.ir_holemask, nrec->ir_startino,
					 nrec->ir_holemask);

		/* merge to nrec to output the updated record */
		__xfs_inobt_rec_merge(nrec, &rec);

		trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
					  nrec->ir_holemask);

		error = xfs_inobt_rec_check_count(mp, nrec);
		if (error)
			goto error;
	}

	error = xfs_inobt_update(cur, nrec);
	if (error)
		goto error;

out:
	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	return 0;
error:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Allocate new inodes in the allocation group specified by agbp.  Returns 0 if
 * inodes were allocated in this AG; -EAGAIN if there was no space in this AG so
 * the caller knows it can try another AG, a hard -ENOSPC when over the maximum
 * inode count threshold, or the usual negative error code for other errors.
 */
STATIC int
xfs_ialloc_ag_alloc(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_perag	*pag)
{
	struct xfs_agi		*agi;
	struct xfs_alloc_arg	args;
	int			error;
	xfs_agino_t		newino;		/* new first inode's number */
	xfs_agino_t		newlen;		/* new number of inodes */
	int			isaligned = 0;	/* inode allocation at stripe */
						/* unit boundary */
	/* init. to full chunk */
	struct xfs_inobt_rec_incore rec;
	struct xfs_ino_geometry	*igeo = M_IGEO(tp->t_mountp);
	uint16_t		allocmask = (uint16_t) -1;
	int			do_sparse = 0;

	memset(&args, 0, sizeof(args));
	args.tp = tp;
	args.mp = tp->t_mountp;
	args.fsbno = NULLFSBLOCK;
	args.oinfo = XFS_RMAP_OINFO_INODES;

#ifdef DEBUG
	/* randomly do sparse inode allocations */
	if (xfs_has_sparseinodes(tp->t_mountp) &&
	    igeo->ialloc_min_blks < igeo->ialloc_blks)
		do_sparse = get_random_u32_below(2);
#endif

	/*
	 * Locking will ensure that we don't have two callers in here
	 * at one time.
	 */
	newlen = igeo->ialloc_inos;
	if (igeo->maxicount &&
	    percpu_counter_read_positive(&args.mp->m_icount) + newlen >
							igeo->maxicount)
		return -ENOSPC;
	args.minlen = args.maxlen = igeo->ialloc_blks;
	/*
	 * First try to allocate inodes contiguous with the last-allocated
	 * chunk of inodes.  If the filesystem is striped, this will fill
	 * an entire stripe unit with inodes.
	 */
	agi = agbp->b_addr;
	newino = be32_to_cpu(agi->agi_newino);
	args.agbno = XFS_AGINO_TO_AGBNO(args.mp, newino) +
		     igeo->ialloc_blks;
	if (do_sparse)
		goto sparse_alloc;
	if (likely(newino != NULLAGINO &&
		  (args.agbno < be32_to_cpu(agi->agi_length)))) {
		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
		args.type = XFS_ALLOCTYPE_THIS_BNO;
		args.prod = 1;

		/*
		 * We need to take into account alignment here to ensure that
		 * we don't modify the free list if we fail to have an exact
		 * block. If we don't have an exact match, and every oher
		 * attempt allocation attempt fails, we'll end up cancelling
		 * a dirty transaction and shutting down.
		 *
		 * For an exact allocation, alignment must be 1,
		 * however we need to take cluster alignment into account when
		 * fixing up the freelist. Use the minalignslop field to
		 * indicate that extra blocks might be required for alignment,
		 * but not to use them in the actual exact allocation.
		 */
		args.alignment = 1;
		args.minalignslop = igeo->cluster_align - 1;

		/* Allow space for the inode btree to split. */
		args.minleft = igeo->inobt_maxlevels;
		if ((error = xfs_alloc_vextent(&args)))
			return error;

		/*
		 * This request might have dirtied the transaction if the AG can
		 * satisfy the request, but the exact block was not available.
		 * If the allocation did fail, subsequent requests will relax
		 * the exact agbno requirement and increase the alignment
		 * instead. It is critical that the total size of the request
		 * (len + alignment + slop) does not increase from this point
		 * on, so reset minalignslop to ensure it is not included in
		 * subsequent requests.
		 */
		args.minalignslop = 0;
	}

	if (unlikely(args.fsbno == NULLFSBLOCK)) {
		/*
		 * Set the alignment for the allocation.
		 * If stripe alignment is turned on then align at stripe unit
		 * boundary.
		 * If the cluster size is smaller than a filesystem block
		 * then we're doing I/O for inodes in filesystem block size
		 * pieces, so don't need alignment anyway.
		 */
		isaligned = 0;
		if (igeo->ialloc_align) {
			ASSERT(!xfs_has_noalign(args.mp));
			args.alignment = args.mp->m_dalign;
			isaligned = 1;
		} else
			args.alignment = igeo->cluster_align;
		/*
		 * Need to figure out where to allocate the inode blocks.
		 * Ideally they should be spaced out through the a.g.
		 * For now, just allocate blocks up front.
		 */
		args.agbno = be32_to_cpu(agi->agi_root);
		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
		/*
		 * Allocate a fixed-size extent of inodes.
		 */
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.prod = 1;
		/*
		 * Allow space for the inode btree to split.
		 */
		args.minleft = igeo->inobt_maxlevels;
		if ((error = xfs_alloc_vextent(&args)))
			return error;
	}

	/*
	 * If stripe alignment is turned on, then try again with cluster
	 * alignment.
	 */
	if (isaligned && args.fsbno == NULLFSBLOCK) {
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.agbno = be32_to_cpu(agi->agi_root);
		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
		args.alignment = igeo->cluster_align;
		if ((error = xfs_alloc_vextent(&args)))
			return error;
	}

	/*
	 * Finally, try a sparse allocation if the filesystem supports it and
	 * the sparse allocation length is smaller than a full chunk.
	 */
	if (xfs_has_sparseinodes(args.mp) &&
	    igeo->ialloc_min_blks < igeo->ialloc_blks &&
	    args.fsbno == NULLFSBLOCK) {
sparse_alloc:
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.agbno = be32_to_cpu(agi->agi_root);
		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
		args.alignment = args.mp->m_sb.sb_spino_align;
		args.prod = 1;

		args.minlen = igeo->ialloc_min_blks;
		args.maxlen = args.minlen;

		/*
		 * The inode record will be aligned to full chunk size. We must
		 * prevent sparse allocation from AG boundaries that result in
		 * invalid inode records, such as records that start at agbno 0
		 * or extend beyond the AG.
		 *
		 * Set min agbno to the first aligned, non-zero agbno and max to
		 * the last aligned agbno that is at least one full chunk from
		 * the end of the AG.
		 */
		args.min_agbno = args.mp->m_sb.sb_inoalignmt;
		args.max_agbno = round_down(args.mp->m_sb.sb_agblocks,
					    args.mp->m_sb.sb_inoalignmt) -
				 igeo->ialloc_blks;

		error = xfs_alloc_vextent(&args);
		if (error)
			return error;

		newlen = XFS_AGB_TO_AGINO(args.mp, args.len);
		ASSERT(newlen <= XFS_INODES_PER_CHUNK);
		allocmask = (1 << (newlen / XFS_INODES_PER_HOLEMASK_BIT)) - 1;
	}

	if (args.fsbno == NULLFSBLOCK)
		return -EAGAIN;

	ASSERT(args.len == args.minlen);

	/*
	 * Stamp and write the inode buffers.
	 *
	 * Seed the new inode cluster with a random generation number. This
	 * prevents short-term reuse of generation numbers if a chunk is
	 * freed and then immediately reallocated. We use random numbers
	 * rather than a linear progression to prevent the next generation
	 * number from being easily guessable.
	 */
	error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno,
			args.agbno, args.len, get_random_u32());

	if (error)
		return error;
	/*
	 * Convert the results.
	 */
	newino = XFS_AGB_TO_AGINO(args.mp, args.agbno);

	if (xfs_inobt_issparse(~allocmask)) {
		/*
		 * We've allocated a sparse chunk. Align the startino and mask.
		 */
		xfs_align_sparse_ino(args.mp, &newino, &allocmask);

		rec.ir_startino = newino;
		rec.ir_holemask = ~allocmask;
		rec.ir_count = newlen;
		rec.ir_freecount = newlen;
		rec.ir_free = XFS_INOBT_ALL_FREE;

		/*
		 * Insert the sparse record into the inobt and allow for a merge
		 * if necessary. If a merge does occur, rec is updated to the
		 * merged record.
		 */
		error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag,
				XFS_BTNUM_INO, &rec, true);
		if (error == -EFSCORRUPTED) {
			xfs_alert(args.mp,
	"invalid sparse inode record: ino 0x%llx holemask 0x%x count %u",
				  XFS_AGINO_TO_INO(args.mp, pag->pag_agno,
						   rec.ir_startino),
				  rec.ir_holemask, rec.ir_count);
			xfs_force_shutdown(args.mp, SHUTDOWN_CORRUPT_INCORE);
		}
		if (error)
			return error;

		/*
		 * We can't merge the part we've just allocated as for the inobt
		 * due to finobt semantics. The original record may or may not
		 * exist independent of whether physical inodes exist in this
		 * sparse chunk.
		 *
		 * We must update the finobt record based on the inobt record.
		 * rec contains the fully merged and up to date inobt record
		 * from the previous call. Set merge false to replace any
		 * existing record with this one.
		 */
		if (xfs_has_finobt(args.mp)) {
			error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag,
				       XFS_BTNUM_FINO, &rec, false);
			if (error)
				return error;
		}
	} else {
		/* full chunk - insert new records to both btrees */
		error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino, newlen,
					 XFS_BTNUM_INO);
		if (error)
			return error;

		if (xfs_has_finobt(args.mp)) {
			error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino,
						 newlen, XFS_BTNUM_FINO);
			if (error)
				return error;
		}
	}

	/*
	 * Update AGI counts and newino.
	 */
	be32_add_cpu(&agi->agi_count, newlen);
	be32_add_cpu(&agi->agi_freecount, newlen);
	pag->pagi_freecount += newlen;
	pag->pagi_count += newlen;
	agi->agi_newino = cpu_to_be32(newino);

	/*
	 * Log allocation group header fields
	 */
	xfs_ialloc_log_agi(tp, agbp,
		XFS_AGI_COUNT | XFS_AGI_FREECOUNT | XFS_AGI_NEWINO);
	/*
	 * Modify/log superblock values for inode count and inode free count.
	 */
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, (long)newlen);
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, (long)newlen);
	return 0;
}

/*
 * Try to retrieve the next record to the left/right from the current one.
 */
STATIC int
xfs_ialloc_next_rec(
	struct xfs_btree_cur	*cur,
	xfs_inobt_rec_incore_t	*rec,
	int			*done,
	int			left)
{
	int                     error;
	int			i;

	if (left)
		error = xfs_btree_decrement(cur, 0, &i);
	else
		error = xfs_btree_increment(cur, 0, &i);

	if (error)
		return error;
	*done = !i;
	if (i) {
		error = xfs_inobt_get_rec(cur, rec, &i);
		if (error)
			return error;
		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
			return -EFSCORRUPTED;
	}

	return 0;
}

STATIC int
xfs_ialloc_get_rec(
	struct xfs_btree_cur	*cur,
	xfs_agino_t		agino,
	xfs_inobt_rec_incore_t	*rec,
	int			*done)
{
	int                     error;
	int			i;

	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_EQ, &i);
	if (error)
		return error;
	*done = !i;
	if (i) {
		error = xfs_inobt_get_rec(cur, rec, &i);
		if (error)
			return error;
		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
			return -EFSCORRUPTED;
	}

	return 0;
}

/*
 * Return the offset of the first free inode in the record. If the inode chunk
 * is sparsely allocated, we convert the record holemask to inode granularity
 * and mask off the unallocated regions from the inode free mask.
 */
STATIC int
xfs_inobt_first_free_inode(
	struct xfs_inobt_rec_incore	*rec)
{
	xfs_inofree_t			realfree;

	/* if there are no holes, return the first available offset */
	if (!xfs_inobt_issparse(rec->ir_holemask))
		return xfs_lowbit64(rec->ir_free);

	realfree = xfs_inobt_irec_to_allocmask(rec);
	realfree &= rec->ir_free;

	return xfs_lowbit64(realfree);
}

/*
 * Allocate an inode using the inobt-only algorithm.
 */
STATIC int
xfs_dialloc_ag_inobt(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_perag	*pag,
	xfs_ino_t		parent,
	xfs_ino_t		*inop)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_agi		*agi = agbp->b_addr;
	xfs_agnumber_t		pagno = XFS_INO_TO_AGNO(mp, parent);
	xfs_agino_t		pagino = XFS_INO_TO_AGINO(mp, parent);
	struct xfs_btree_cur	*cur, *tcur;
	struct xfs_inobt_rec_incore rec, trec;
	xfs_ino_t		ino;
	int			error;
	int			offset;
	int			i, j;
	int			searchdistance = 10;

	ASSERT(pag->pagi_init);
	ASSERT(pag->pagi_inodeok);
	ASSERT(pag->pagi_freecount > 0);

 restart_pagno:
	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
	/*
	 * If pagino is 0 (this is the root inode allocation) use newino.
	 * This must work because we've just allocated some.
	 */
	if (!pagino)
		pagino = be32_to_cpu(agi->agi_newino);

	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error0;

	/*
	 * If in the same AG as the parent, try to get near the parent.
	 */
	if (pagno == pag->pag_agno) {
		int		doneleft;	/* done, to the left */
		int		doneright;	/* done, to the right */

		error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
		if (error)
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}

		error = xfs_inobt_get_rec(cur, &rec, &j);
		if (error)
			goto error0;
		if (XFS_IS_CORRUPT(mp, j != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}

		if (rec.ir_freecount > 0) {
			/*
			 * Found a free inode in the same chunk
			 * as the parent, done.
			 */
			goto alloc_inode;
		}


		/*
		 * In the same AG as parent, but parent's chunk is full.
		 */

		/* duplicate the cursor, search left & right simultaneously */
		error = xfs_btree_dup_cursor(cur, &tcur);
		if (error)
			goto error0;

		/*
		 * Skip to last blocks looked up if same parent inode.
		 */
		if (pagino != NULLAGINO &&
		    pag->pagl_pagino == pagino &&
		    pag->pagl_leftrec != NULLAGINO &&
		    pag->pagl_rightrec != NULLAGINO) {
			error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec,
						   &trec, &doneleft);
			if (error)
				goto error1;

			error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec,
						   &rec, &doneright);
			if (error)
				goto error1;
		} else {
			/* search left with tcur, back up 1 record */
			error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1);
			if (error)
				goto error1;

			/* search right with cur, go forward 1 record. */
			error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0);
			if (error)
				goto error1;
		}

		/*
		 * Loop until we find an inode chunk with a free inode.
		 */
		while (--searchdistance > 0 && (!doneleft || !doneright)) {
			int	useleft;  /* using left inode chunk this time */

			/* figure out the closer block if both are valid. */
			if (!doneleft && !doneright) {
				useleft = pagino -
				 (trec.ir_startino + XFS_INODES_PER_CHUNK - 1) <
				  rec.ir_startino - pagino;
			} else {
				useleft = !doneleft;
			}

			/* free inodes to the left? */
			if (useleft && trec.ir_freecount) {
				xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
				cur = tcur;

				pag->pagl_leftrec = trec.ir_startino;
				pag->pagl_rightrec = rec.ir_startino;
				pag->pagl_pagino = pagino;
				rec = trec;
				goto alloc_inode;
			}

			/* free inodes to the right? */
			if (!useleft && rec.ir_freecount) {
				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);

				pag->pagl_leftrec = trec.ir_startino;
				pag->pagl_rightrec = rec.ir_startino;
				pag->pagl_pagino = pagino;
				goto alloc_inode;
			}

			/* get next record to check */
			if (useleft) {
				error = xfs_ialloc_next_rec(tcur, &trec,
								 &doneleft, 1);
			} else {
				error = xfs_ialloc_next_rec(cur, &rec,
								 &doneright, 0);
			}
			if (error)
				goto error1;
		}

		if (searchdistance <= 0) {
			/*
			 * Not in range - save last search
			 * location and allocate a new inode
			 */
			xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
			pag->pagl_leftrec = trec.ir_startino;
			pag->pagl_rightrec = rec.ir_startino;
			pag->pagl_pagino = pagino;

		} else {
			/*
			 * We've reached the end of the btree. because
			 * we are only searching a small chunk of the
			 * btree each search, there is obviously free
			 * inodes closer to the parent inode than we
			 * are now. restart the search again.
			 */
			pag->pagl_pagino = NULLAGINO;
			pag->pagl_leftrec = NULLAGINO;
			pag->pagl_rightrec = NULLAGINO;
			xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
			goto restart_pagno;
		}
	}

	/*
	 * In a different AG from the parent.
	 * See if the most recently allocated block has any free.
	 */
	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
		error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
					 XFS_LOOKUP_EQ, &i);
		if (error)
			goto error0;

		if (i == 1) {
			error = xfs_inobt_get_rec(cur, &rec, &j);
			if (error)
				goto error0;

			if (j == 1 && rec.ir_freecount > 0) {
				/*
				 * The last chunk allocated in the group
				 * still has a free inode.
				 */
				goto alloc_inode;
			}
		}
	}

	/*
	 * None left in the last group, search the whole AG
	 */
	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
	if (error)
		goto error0;
	if (XFS_IS_CORRUPT(mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error0;
	}

	for (;;) {
		error = xfs_inobt_get_rec(cur, &rec, &i);
		if (error)
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		if (rec.ir_freecount > 0)
			break;
		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
	}

alloc_inode:
	offset = xfs_inobt_first_free_inode(&rec);
	ASSERT(offset >= 0);
	ASSERT(offset < XFS_INODES_PER_CHUNK);
	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
				   XFS_INODES_PER_CHUNK) == 0);
	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
	rec.ir_free &= ~XFS_INOBT_MASK(offset);
	rec.ir_freecount--;
	error = xfs_inobt_update(cur, &rec);
	if (error)
		goto error0;
	be32_add_cpu(&agi->agi_freecount, -1);
	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
	pag->pagi_freecount--;

	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error0;

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
	*inop = ino;
	return 0;
error1:
	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Use the free inode btree to allocate an inode based on distance from the
 * parent. Note that the provided cursor may be deleted and replaced.
 */
STATIC int
xfs_dialloc_ag_finobt_near(
	xfs_agino_t			pagino,
	struct xfs_btree_cur		**ocur,
	struct xfs_inobt_rec_incore	*rec)
{
	struct xfs_btree_cur		*lcur = *ocur;	/* left search cursor */
	struct xfs_btree_cur		*rcur;	/* right search cursor */
	struct xfs_inobt_rec_incore	rrec;
	int				error;
	int				i, j;

	error = xfs_inobt_lookup(lcur, pagino, XFS_LOOKUP_LE, &i);
	if (error)
		return error;

	if (i == 1) {
		error = xfs_inobt_get_rec(lcur, rec, &i);
		if (error)
			return error;
		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1))
			return -EFSCORRUPTED;

		/*
		 * See if we've landed in the parent inode record. The finobt
		 * only tracks chunks with at least one free inode, so record
		 * existence is enough.
		 */
		if (pagino >= rec->ir_startino &&
		    pagino < (rec->ir_startino + XFS_INODES_PER_CHUNK))
			return 0;
	}

	error = xfs_btree_dup_cursor(lcur, &rcur);
	if (error)
		return error;

	error = xfs_inobt_lookup(rcur, pagino, XFS_LOOKUP_GE, &j);
	if (error)
		goto error_rcur;
	if (j == 1) {
		error = xfs_inobt_get_rec(rcur, &rrec, &j);
		if (error)
			goto error_rcur;
		if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) {
			error = -EFSCORRUPTED;
			goto error_rcur;
		}
	}

	if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) {
		error = -EFSCORRUPTED;
		goto error_rcur;
	}
	if (i == 1 && j == 1) {
		/*
		 * Both the left and right records are valid. Choose the closer
		 * inode chunk to the target.
		 */
		if ((pagino - rec->ir_startino + XFS_INODES_PER_CHUNK - 1) >
		    (rrec.ir_startino - pagino)) {
			*rec = rrec;
			xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
			*ocur = rcur;
		} else {
			xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
		}
	} else if (j == 1) {
		/* only the right record is valid */
		*rec = rrec;
		xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
		*ocur = rcur;
	} else if (i == 1) {
		/* only the left record is valid */
		xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
	}

	return 0;

error_rcur:
	xfs_btree_del_cursor(rcur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Use the free inode btree to find a free inode based on a newino hint. If
 * the hint is NULL, find the first free inode in the AG.
 */
STATIC int
xfs_dialloc_ag_finobt_newino(
	struct xfs_agi			*agi,
	struct xfs_btree_cur		*cur,
	struct xfs_inobt_rec_incore	*rec)
{
	int error;
	int i;

	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
		error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
					 XFS_LOOKUP_EQ, &i);
		if (error)
			return error;
		if (i == 1) {
			error = xfs_inobt_get_rec(cur, rec, &i);
			if (error)
				return error;
			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
				return -EFSCORRUPTED;
			return 0;
		}
	}

	/*
	 * Find the first inode available in the AG.
	 */
	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
	if (error)
		return error;
	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
		return -EFSCORRUPTED;

	error = xfs_inobt_get_rec(cur, rec, &i);
	if (error)
		return error;
	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
		return -EFSCORRUPTED;

	return 0;
}

/*
 * Update the inobt based on a modification made to the finobt. Also ensure that
 * the records from both trees are equivalent post-modification.
 */
STATIC int
xfs_dialloc_ag_update_inobt(
	struct xfs_btree_cur		*cur,	/* inobt cursor */
	struct xfs_inobt_rec_incore	*frec,	/* finobt record */
	int				offset) /* inode offset */
{
	struct xfs_inobt_rec_incore	rec;
	int				error;
	int				i;

	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
	if (error)
		return error;
	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
		return -EFSCORRUPTED;

	error = xfs_inobt_get_rec(cur, &rec, &i);
	if (error)
		return error;
	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
		return -EFSCORRUPTED;
	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
				   XFS_INODES_PER_CHUNK) == 0);

	rec.ir_free &= ~XFS_INOBT_MASK(offset);
	rec.ir_freecount--;

	if (XFS_IS_CORRUPT(cur->bc_mp,
			   rec.ir_free != frec->ir_free ||
			   rec.ir_freecount != frec->ir_freecount))
		return -EFSCORRUPTED;

	return xfs_inobt_update(cur, &rec);
}

/*
 * Allocate an inode using the free inode btree, if available. Otherwise, fall
 * back to the inobt search algorithm.
 *
 * The caller selected an AG for us, and made sure that free inodes are
 * available.
 */
static int
xfs_dialloc_ag(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_perag	*pag,
	xfs_ino_t		parent,
	xfs_ino_t		*inop)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_agi			*agi = agbp->b_addr;
	xfs_agnumber_t			pagno = XFS_INO_TO_AGNO(mp, parent);
	xfs_agino_t			pagino = XFS_INO_TO_AGINO(mp, parent);
	struct xfs_btree_cur		*cur;	/* finobt cursor */
	struct xfs_btree_cur		*icur;	/* inobt cursor */
	struct xfs_inobt_rec_incore	rec;
	xfs_ino_t			ino;
	int				error;
	int				offset;
	int				i;

	if (!xfs_has_finobt(mp))
		return xfs_dialloc_ag_inobt(tp, agbp, pag, parent, inop);

	/*
	 * If pagino is 0 (this is the root inode allocation) use newino.
	 * This must work because we've just allocated some.
	 */
	if (!pagino)
		pagino = be32_to_cpu(agi->agi_newino);

	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO);

	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error_cur;

	/*
	 * The search algorithm depends on whether we're in the same AG as the
	 * parent. If so, find the closest available inode to the parent. If
	 * not, consider the agi hint or find the first free inode in the AG.
	 */
	if (pag->pag_agno == pagno)
		error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
	else
		error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
	if (error)
		goto error_cur;

	offset = xfs_inobt_first_free_inode(&rec);
	ASSERT(offset >= 0);
	ASSERT(offset < XFS_INODES_PER_CHUNK);
	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
				   XFS_INODES_PER_CHUNK) == 0);
	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);

	/*
	 * Modify or remove the finobt record.
	 */
	rec.ir_free &= ~XFS_INOBT_MASK(offset);
	rec.ir_freecount--;
	if (rec.ir_freecount)
		error = xfs_inobt_update(cur, &rec);
	else
		error = xfs_btree_delete(cur, &i);
	if (error)
		goto error_cur;

	/*
	 * The finobt has now been updated appropriately. We haven't updated the
	 * agi and superblock yet, so we can create an inobt cursor and validate
	 * the original freecount. If all is well, make the equivalent update to
	 * the inobt using the finobt record and offset information.
	 */
	icur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);

	error = xfs_check_agi_freecount(icur);
	if (error)
		goto error_icur;

	error = xfs_dialloc_ag_update_inobt(icur, &rec, offset);
	if (error)
		goto error_icur;

	/*
	 * Both trees have now been updated. We must update the perag and
	 * superblock before we can check the freecount for each btree.
	 */
	be32_add_cpu(&agi->agi_freecount, -1);
	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
	pag->pagi_freecount--;

	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);

	error = xfs_check_agi_freecount(icur);
	if (error)
		goto error_icur;
	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error_icur;

	xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	*inop = ino;
	return 0;

error_icur:
	xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
error_cur:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

static int
xfs_dialloc_roll(
	struct xfs_trans	**tpp,
	struct xfs_buf		*agibp)
{
	struct xfs_trans	*tp = *tpp;
	struct xfs_dquot_acct	*dqinfo;
	int			error;

	/*
	 * Hold to on to the agibp across the commit so no other allocation can
	 * come in and take the free inodes we just allocated for our caller.
	 */
	xfs_trans_bhold(tp, agibp);

	/*
	 * We want the quota changes to be associated with the next transaction,
	 * NOT this one. So, detach the dqinfo from this and attach it to the
	 * next transaction.
	 */
	dqinfo = tp->t_dqinfo;
	tp->t_dqinfo = NULL;

	error = xfs_trans_roll(&tp);

	/* Re-attach the quota info that we detached from prev trx. */
	tp->t_dqinfo = dqinfo;

	/*
	 * Join the buffer even on commit error so that the buffer is released
	 * when the caller cancels the transaction and doesn't have to handle
	 * this error case specially.
	 */
	xfs_trans_bjoin(tp, agibp);
	*tpp = tp;
	return error;
}

static xfs_agnumber_t
xfs_ialloc_next_ag(
	xfs_mount_t	*mp)
{
	xfs_agnumber_t	agno;

	spin_lock(&mp->m_agirotor_lock);
	agno = mp->m_agirotor;
	if (++mp->m_agirotor >= mp->m_maxagi)
		mp->m_agirotor = 0;
	spin_unlock(&mp->m_agirotor_lock);

	return agno;
}

static bool
xfs_dialloc_good_ag(
	struct xfs_trans	*tp,
	struct xfs_perag	*pag,
	umode_t			mode,
	int			flags,
	bool			ok_alloc)
{
	struct xfs_mount	*mp = tp->t_mountp;
	xfs_extlen_t		ineed;
	xfs_extlen_t		longest = 0;
	int			needspace;
	int			error;

	if (!pag->pagi_inodeok)
		return false;

	if (!pag->pagi_init) {
		error = xfs_ialloc_read_agi(pag, tp, NULL);
		if (error)
			return false;
	}

	if (pag->pagi_freecount)
		return true;
	if (!ok_alloc)
		return false;

	if (!pag->pagf_init) {
		error = xfs_alloc_read_agf(pag, tp, flags, NULL);
		if (error)
			return false;
	}

	/*
	 * Check that there is enough free space for the file plus a chunk of
	 * inodes if we need to allocate some. If this is the first pass across
	 * the AGs, take into account the potential space needed for alignment
	 * of inode chunks when checking the longest contiguous free space in
	 * the AG - this prevents us from getting ENOSPC because we have free
	 * space larger than ialloc_blks but alignment constraints prevent us
	 * from using it.
	 *
	 * If we can't find an AG with space for full alignment slack to be
	 * taken into account, we must be near ENOSPC in all AGs.  Hence we
	 * don't include alignment for the second pass and so if we fail
	 * allocation due to alignment issues then it is most likely a real
	 * ENOSPC condition.
	 *
	 * XXX(dgc): this calculation is now bogus thanks to the per-ag
	 * reservations that xfs_alloc_fix_freelist() now does via
	 * xfs_alloc_space_available(). When the AG fills up, pagf_freeblks will
	 * be more than large enough for the check below to succeed, but
	 * xfs_alloc_space_available() will fail because of the non-zero
	 * metadata reservation and hence we won't actually be able to allocate
	 * more inodes in this AG. We do soooo much unnecessary work near ENOSPC
	 * because of this.
	 */
	ineed = M_IGEO(mp)->ialloc_min_blks;
	if (flags && ineed > 1)
		ineed += M_IGEO(mp)->cluster_align;
	longest = pag->pagf_longest;
	if (!longest)
		longest = pag->pagf_flcount > 0;
	needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);

	if (pag->pagf_freeblks < needspace + ineed || longest < ineed)
		return false;
	return true;
}

static int
xfs_dialloc_try_ag(
	struct xfs_trans	**tpp,
	struct xfs_perag	*pag,
	xfs_ino_t		parent,
	xfs_ino_t		*new_ino,
	bool			ok_alloc)
{
	struct xfs_buf		*agbp;
	xfs_ino_t		ino;
	int			error;

	/*
	 * Then read in the AGI buffer and recheck with the AGI buffer
	 * lock held.
	 */
	error = xfs_ialloc_read_agi(pag, *tpp, &agbp);
	if (error)
		return error;

	if (!pag->pagi_freecount) {
		if (!ok_alloc) {
			error = -EAGAIN;
			goto out_release;
		}

		error = xfs_ialloc_ag_alloc(*tpp, agbp, pag);
		if (error < 0)
			goto out_release;

		/*
		 * We successfully allocated space for an inode cluster in this
		 * AG.  Roll the transaction so that we can allocate one of the
		 * new inodes.
		 */
		ASSERT(pag->pagi_freecount > 0);
		error = xfs_dialloc_roll(tpp, agbp);
		if (error)
			goto out_release;
	}

	/* Allocate an inode in the found AG */
	error = xfs_dialloc_ag(*tpp, agbp, pag, parent, &ino);
	if (!error)
		*new_ino = ino;
	return error;

out_release:
	xfs_trans_brelse(*tpp, agbp);
	return error;
}

/*
 * Allocate an on-disk inode.
 *
 * Mode is used to tell whether the new inode is a directory and hence where to
 * locate it. The on-disk inode that is allocated will be returned in @new_ino
 * on success, otherwise an error will be set to indicate the failure (e.g.
 * -ENOSPC).
 */
int
xfs_dialloc(
	struct xfs_trans	**tpp,
	xfs_ino_t		parent,
	umode_t			mode,
	xfs_ino_t		*new_ino)
{
	struct xfs_mount	*mp = (*tpp)->t_mountp;
	xfs_agnumber_t		agno;
	int			error = 0;
	xfs_agnumber_t		start_agno;
	struct xfs_perag	*pag;
	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
	bool			ok_alloc = true;
	int			flags;
	xfs_ino_t		ino;

	/*
	 * Directories, symlinks, and regular files frequently allocate at least
	 * one block, so factor that potential expansion when we examine whether
	 * an AG has enough space for file creation.
	 */
	if (S_ISDIR(mode))
		start_agno = xfs_ialloc_next_ag(mp);
	else {
		start_agno = XFS_INO_TO_AGNO(mp, parent);
		if (start_agno >= mp->m_maxagi)
			start_agno = 0;
	}

	/*
	 * If we have already hit the ceiling of inode blocks then clear
	 * ok_alloc so we scan all available agi structures for a free
	 * inode.
	 *
	 * Read rough value of mp->m_icount by percpu_counter_read_positive,
	 * which will sacrifice the preciseness but improve the performance.
	 */
	if (igeo->maxicount &&
	    percpu_counter_read_positive(&mp->m_icount) + igeo->ialloc_inos
							> igeo->maxicount) {
		ok_alloc = false;
	}

	/*
	 * Loop until we find an allocation group that either has free inodes
	 * or in which we can allocate some inodes.  Iterate through the
	 * allocation groups upward, wrapping at the end.
	 */
	agno = start_agno;
	flags = XFS_ALLOC_FLAG_TRYLOCK;
	for (;;) {
		pag = xfs_perag_get(mp, agno);
		if (xfs_dialloc_good_ag(*tpp, pag, mode, flags, ok_alloc)) {
			error = xfs_dialloc_try_ag(tpp, pag, parent,
					&ino, ok_alloc);
			if (error != -EAGAIN)
				break;
		}

		if (xfs_is_shutdown(mp)) {
			error = -EFSCORRUPTED;
			break;
		}
		if (++agno == mp->m_maxagi)
			agno = 0;
		if (agno == start_agno) {
			if (!flags) {
				error = -ENOSPC;
				break;
			}
			flags = 0;
		}
		xfs_perag_put(pag);
	}

	if (!error)
		*new_ino = ino;
	xfs_perag_put(pag);
	return error;
}

/*
 * Free the blocks of an inode chunk. We must consider that the inode chunk
 * might be sparse and only free the regions that are allocated as part of the
 * chunk.
 */
STATIC void
xfs_difree_inode_chunk(
	struct xfs_trans		*tp,
	xfs_agnumber_t			agno,
	struct xfs_inobt_rec_incore	*rec)
{
	struct xfs_mount		*mp = tp->t_mountp;
	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
							rec->ir_startino);
	int				startidx, endidx;
	int				nextbit;
	xfs_agblock_t			agbno;
	int				contigblk;
	DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);

	if (!xfs_inobt_issparse(rec->ir_holemask)) {
		/* not sparse, calculate extent info directly */
		xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
				  M_IGEO(mp)->ialloc_blks,
				  &XFS_RMAP_OINFO_INODES);
		return;
	}

	/* holemask is only 16-bits (fits in an unsigned long) */
	ASSERT(sizeof(rec->ir_holemask) <= sizeof(holemask[0]));
	holemask[0] = rec->ir_holemask;

	/*
	 * Find contiguous ranges of zeroes (i.e., allocated regions) in the
	 * holemask and convert the start/end index of each range to an extent.
	 * We start with the start and end index both pointing at the first 0 in
	 * the mask.
	 */
	startidx = endidx = find_first_zero_bit(holemask,
						XFS_INOBT_HOLEMASK_BITS);
	nextbit = startidx + 1;
	while (startidx < XFS_INOBT_HOLEMASK_BITS) {
		nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS,
					     nextbit);
		/*
		 * If the next zero bit is contiguous, update the end index of
		 * the current range and continue.
		 */
		if (nextbit != XFS_INOBT_HOLEMASK_BITS &&
		    nextbit == endidx + 1) {
			endidx = nextbit;
			goto next;
		}

		/*
		 * nextbit is not contiguous with the current end index. Convert
		 * the current start/end to an extent and add it to the free
		 * list.
		 */
		agbno = sagbno + (startidx * XFS_INODES_PER_HOLEMASK_BIT) /
				  mp->m_sb.sb_inopblock;
		contigblk = ((endidx - startidx + 1) *
			     XFS_INODES_PER_HOLEMASK_BIT) /
			    mp->m_sb.sb_inopblock;

		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
		xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
				  contigblk, &XFS_RMAP_OINFO_INODES);

		/* reset range to current bit and carry on... */
		startidx = endidx = nextbit;

next:
		nextbit++;
	}
}

STATIC int
xfs_difree_inobt(
	struct xfs_mount		*mp,
	struct xfs_trans		*tp,
	struct xfs_buf			*agbp,
	struct xfs_perag		*pag,
	xfs_agino_t			agino,
	struct xfs_icluster		*xic,
	struct xfs_inobt_rec_incore	*orec)
{
	struct xfs_agi			*agi = agbp->b_addr;
	struct xfs_btree_cur		*cur;
	struct xfs_inobt_rec_incore	rec;
	int				ilen;
	int				error;
	int				i;
	int				off;

	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
	ASSERT(XFS_AGINO_TO_AGBNO(mp, agino) < be32_to_cpu(agi->agi_length));

	/*
	 * Initialize the cursor.
	 */
	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);

	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error0;

	/*
	 * Look for the entry describing this inode.
	 */
	if ((error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i))) {
		xfs_warn(mp, "%s: xfs_inobt_lookup() returned error %d.",
			__func__, error);
		goto error0;
	}
	if (XFS_IS_CORRUPT(mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	error = xfs_inobt_get_rec(cur, &rec, &i);
	if (error) {
		xfs_warn(mp, "%s: xfs_inobt_get_rec() returned error %d.",
			__func__, error);
		goto error0;
	}
	if (XFS_IS_CORRUPT(mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	/*
	 * Get the offset in the inode chunk.
	 */
	off = agino - rec.ir_startino;
	ASSERT(off >= 0 && off < XFS_INODES_PER_CHUNK);
	ASSERT(!(rec.ir_free & XFS_INOBT_MASK(off)));
	/*
	 * Mark the inode free & increment the count.
	 */
	rec.ir_free |= XFS_INOBT_MASK(off);
	rec.ir_freecount++;

	/*
	 * When an inode chunk is free, it becomes eligible for removal. Don't
	 * remove the chunk if the block size is large enough for multiple inode
	 * chunks (that might not be free).
	 */
	if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE &&
	    mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
		struct xfs_perag	*pag = agbp->b_pag;

		xic->deleted = true;
		xic->first_ino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
				rec.ir_startino);
		xic->alloc = xfs_inobt_irec_to_allocmask(&rec);

		/*
		 * Remove the inode cluster from the AGI B+Tree, adjust the
		 * AGI and Superblock inode counts, and mark the disk space
		 * to be freed when the transaction is committed.
		 */
		ilen = rec.ir_freecount;
		be32_add_cpu(&agi->agi_count, -ilen);
		be32_add_cpu(&agi->agi_freecount, -(ilen - 1));
		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
		pag->pagi_freecount -= ilen - 1;
		pag->pagi_count -= ilen;
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen);
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));

		if ((error = xfs_btree_delete(cur, &i))) {
			xfs_warn(mp, "%s: xfs_btree_delete returned error %d.",
				__func__, error);
			goto error0;
		}

		xfs_difree_inode_chunk(tp, pag->pag_agno, &rec);
	} else {
		xic->deleted = false;

		error = xfs_inobt_update(cur, &rec);
		if (error) {
			xfs_warn(mp, "%s: xfs_inobt_update returned error %d.",
				__func__, error);
			goto error0;
		}

		/*
		 * Change the inode free counts and log the ag/sb changes.
		 */
		be32_add_cpu(&agi->agi_freecount, 1);
		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
		pag->pagi_freecount++;
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, 1);
	}

	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error0;

	*orec = rec;
	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	return 0;

error0:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Free an inode in the free inode btree.
 */
STATIC int
xfs_difree_finobt(
	struct xfs_mount		*mp,
	struct xfs_trans		*tp,
	struct xfs_buf			*agbp,
	struct xfs_perag		*pag,
	xfs_agino_t			agino,
	struct xfs_inobt_rec_incore	*ibtrec) /* inobt record */
{
	struct xfs_btree_cur		*cur;
	struct xfs_inobt_rec_incore	rec;
	int				offset = agino - ibtrec->ir_startino;
	int				error;
	int				i;

	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO);

	error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
	if (error)
		goto error;
	if (i == 0) {
		/*
		 * If the record does not exist in the finobt, we must have just
		 * freed an inode in a previously fully allocated chunk. If not,
		 * something is out of sync.
		 */
		if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) {
			error = -EFSCORRUPTED;
			goto error;
		}

		error = xfs_inobt_insert_rec(cur, ibtrec->ir_holemask,
					     ibtrec->ir_count,
					     ibtrec->ir_freecount,
					     ibtrec->ir_free, &i);
		if (error)
			goto error;
		ASSERT(i == 1);

		goto out;
	}

	/*
	 * Read and update the existing record. We could just copy the ibtrec
	 * across here, but that would defeat the purpose of having redundant
	 * metadata. By making the modifications independently, we can catch
	 * corruptions that we wouldn't see if we just copied from one record
	 * to another.
	 */
	error = xfs_inobt_get_rec(cur, &rec, &i);
	if (error)
		goto error;
	if (XFS_IS_CORRUPT(mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error;
	}

	rec.ir_free |= XFS_INOBT_MASK(offset);
	rec.ir_freecount++;

	if (XFS_IS_CORRUPT(mp,
			   rec.ir_free != ibtrec->ir_free ||
			   rec.ir_freecount != ibtrec->ir_freecount)) {
		error = -EFSCORRUPTED;
		goto error;
	}

	/*
	 * The content of inobt records should always match between the inobt
	 * and finobt. The lifecycle of records in the finobt is different from
	 * the inobt in that the finobt only tracks records with at least one
	 * free inode. Hence, if all of the inodes are free and we aren't
	 * keeping inode chunks permanently on disk, remove the record.
	 * Otherwise, update the record with the new information.
	 *
	 * Note that we currently can't free chunks when the block size is large
	 * enough for multiple chunks. Leave the finobt record to remain in sync
	 * with the inobt.
	 */
	if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE &&
	    mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
		error = xfs_btree_delete(cur, &i);
		if (error)
			goto error;
		ASSERT(i == 1);
	} else {
		error = xfs_inobt_update(cur, &rec);
		if (error)
			goto error;
	}

out:
	error = xfs_check_agi_freecount(cur);
	if (error)
		goto error;

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	return 0;

error:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Free disk inode.  Carefully avoids touching the incore inode, all
 * manipulations incore are the caller's responsibility.
 * The on-disk inode is not changed by this operation, only the
 * btree (free inode mask) is changed.
 */
int
xfs_difree(
	struct xfs_trans	*tp,
	struct xfs_perag	*pag,
	xfs_ino_t		inode,
	struct xfs_icluster	*xic)
{
	/* REFERENCED */
	xfs_agblock_t		agbno;	/* block number containing inode */
	struct xfs_buf		*agbp;	/* buffer for allocation group header */
	xfs_agino_t		agino;	/* allocation group inode number */
	int			error;	/* error return value */
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_inobt_rec_incore rec;/* btree record */

	/*
	 * Break up inode number into its components.
	 */
	if (pag->pag_agno != XFS_INO_TO_AGNO(mp, inode)) {
		xfs_warn(mp, "%s: agno != pag->pag_agno (%d != %d).",
			__func__, XFS_INO_TO_AGNO(mp, inode), pag->pag_agno);
		ASSERT(0);
		return -EINVAL;
	}
	agino = XFS_INO_TO_AGINO(mp, inode);
	if (inode != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino))  {
		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
			__func__, (unsigned long long)inode,
			(unsigned long long)XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
		ASSERT(0);
		return -EINVAL;
	}
	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
	if (agbno >= mp->m_sb.sb_agblocks)  {
		xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
			__func__, agbno, mp->m_sb.sb_agblocks);
		ASSERT(0);
		return -EINVAL;
	}
	/*
	 * Get the allocation group header.
	 */
	error = xfs_ialloc_read_agi(pag, tp, &agbp);
	if (error) {
		xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
			__func__, error);
		return error;
	}

	/*
	 * Fix up the inode allocation btree.
	 */
	error = xfs_difree_inobt(mp, tp, agbp, pag, agino, xic, &rec);
	if (error)
		goto error0;

	/*
	 * Fix up the free inode btree.
	 */
	if (xfs_has_finobt(mp)) {
		error = xfs_difree_finobt(mp, tp, agbp, pag, agino, &rec);
		if (error)
			goto error0;
	}

	return 0;

error0:
	return error;
}

STATIC int
xfs_imap_lookup(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_perag	*pag,
	xfs_agino_t		agino,
	xfs_agblock_t		agbno,
	xfs_agblock_t		*chunk_agbno,
	xfs_agblock_t		*offset_agbno,
	int			flags)
{
	struct xfs_inobt_rec_incore rec;
	struct xfs_btree_cur	*cur;
	struct xfs_buf		*agbp;
	int			error;
	int			i;

	error = xfs_ialloc_read_agi(pag, tp, &agbp);
	if (error) {
		xfs_alert(mp,
			"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
			__func__, error, pag->pag_agno);
		return error;
	}

	/*
	 * Lookup the inode record for the given agino. If the record cannot be
	 * found, then it's an invalid inode number and we should abort. Once
	 * we have a record, we need to ensure it contains the inode number
	 * we are looking up.
	 */
	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
	if (!error) {
		if (i)
			error = xfs_inobt_get_rec(cur, &rec, &i);
		if (!error && i == 0)
			error = -EINVAL;
	}

	xfs_trans_brelse(tp, agbp);
	xfs_btree_del_cursor(cur, error);
	if (error)
		return error;

	/* check that the returned record contains the required inode */
	if (rec.ir_startino > agino ||
	    rec.ir_startino + M_IGEO(mp)->ialloc_inos <= agino)
		return -EINVAL;

	/* for untrusted inodes check it is allocated first */
	if ((flags & XFS_IGET_UNTRUSTED) &&
	    (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino)))
		return -EINVAL;

	*chunk_agbno = XFS_AGINO_TO_AGBNO(mp, rec.ir_startino);
	*offset_agbno = agbno - *chunk_agbno;
	return 0;
}

/*
 * Return the location of the inode in imap, for mapping it into a buffer.
 */
int
xfs_imap(
	struct xfs_mount	 *mp,	/* file system mount structure */
	struct xfs_trans	 *tp,	/* transaction pointer */
	xfs_ino_t		ino,	/* inode to locate */
	struct xfs_imap		*imap,	/* location map structure */
	uint			flags)	/* flags for inode btree lookup */
{
	xfs_agblock_t		agbno;	/* block number of inode in the alloc group */
	xfs_agino_t		agino;	/* inode number within alloc group */
	xfs_agblock_t		chunk_agbno;	/* first block in inode chunk */
	xfs_agblock_t		cluster_agbno;	/* first block in inode cluster */
	int			error;	/* error code */
	int			offset;	/* index of inode in its buffer */
	xfs_agblock_t		offset_agbno;	/* blks from chunk start to inode */
	struct xfs_perag	*pag;

	ASSERT(ino != NULLFSINO);

	/*
	 * Split up the inode number into its parts.
	 */
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
	agino = XFS_INO_TO_AGINO(mp, ino);
	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
	if (!pag || agbno >= mp->m_sb.sb_agblocks ||
	    ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
		error = -EINVAL;
#ifdef DEBUG
		/*
		 * Don't output diagnostic information for untrusted inodes
		 * as they can be invalid without implying corruption.
		 */
		if (flags & XFS_IGET_UNTRUSTED)
			goto out_drop;
		if (!pag) {
			xfs_alert(mp,
				"%s: agno (%d) >= mp->m_sb.sb_agcount (%d)",
				__func__, XFS_INO_TO_AGNO(mp, ino),
				mp->m_sb.sb_agcount);
		}
		if (agbno >= mp->m_sb.sb_agblocks) {
			xfs_alert(mp,
		"%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)",
				__func__, (unsigned long long)agbno,
				(unsigned long)mp->m_sb.sb_agblocks);
		}
		if (pag && ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
			xfs_alert(mp,
		"%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
				__func__, ino,
				XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
		}
		xfs_stack_trace();
#endif /* DEBUG */
		goto out_drop;
	}

	/*
	 * For bulkstat and handle lookups, we have an untrusted inode number
	 * that we have to verify is valid. We cannot do this just by reading
	 * the inode buffer as it may have been unlinked and removed leaving
	 * inodes in stale state on disk. Hence we have to do a btree lookup
	 * in all cases where an untrusted inode number is passed.
	 */
	if (flags & XFS_IGET_UNTRUSTED) {
		error = xfs_imap_lookup(mp, tp, pag, agino, agbno,
					&chunk_agbno, &offset_agbno, flags);
		if (error)
			goto out_drop;
		goto out_map;
	}

	/*
	 * If the inode cluster size is the same as the blocksize or
	 * smaller we get to the buffer by simple arithmetics.
	 */
	if (M_IGEO(mp)->blocks_per_cluster == 1) {
		offset = XFS_INO_TO_OFFSET(mp, ino);
		ASSERT(offset < mp->m_sb.sb_inopblock);

		imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, agbno);
		imap->im_len = XFS_FSB_TO_BB(mp, 1);
		imap->im_boffset = (unsigned short)(offset <<
							mp->m_sb.sb_inodelog);
		error = 0;
		goto out_drop;
	}

	/*
	 * If the inode chunks are aligned then use simple maths to
	 * find the location. Otherwise we have to do a btree
	 * lookup to find the location.
	 */
	if (M_IGEO(mp)->inoalign_mask) {
		offset_agbno = agbno & M_IGEO(mp)->inoalign_mask;
		chunk_agbno = agbno - offset_agbno;
	} else {
		error = xfs_imap_lookup(mp, tp, pag, agino, agbno,
					&chunk_agbno, &offset_agbno, flags);
		if (error)
			goto out_drop;
	}

out_map:
	ASSERT(agbno >= chunk_agbno);
	cluster_agbno = chunk_agbno +
		((offset_agbno / M_IGEO(mp)->blocks_per_cluster) *
		 M_IGEO(mp)->blocks_per_cluster);
	offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
		XFS_INO_TO_OFFSET(mp, ino);

	imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, cluster_agbno);
	imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster);
	imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog);

	/*
	 * If the inode number maps to a block outside the bounds
	 * of the file system then return NULL rather than calling
	 * read_buf and panicing when we get an error from the
	 * driver.
	 */
	if ((imap->im_blkno + imap->im_len) >
	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
		xfs_alert(mp,
	"%s: (im_blkno (0x%llx) + im_len (0x%llx)) > sb_dblocks (0x%llx)",
			__func__, (unsigned long long) imap->im_blkno,
			(unsigned long long) imap->im_len,
			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
		error = -EINVAL;
		goto out_drop;
	}
	error = 0;
out_drop:
	if (pag)
		xfs_perag_put(pag);
	return error;
}

/*
 * Log specified fields for the ag hdr (inode section). The growth of the agi
 * structure over time requires that we interpret the buffer as two logical
 * regions delineated by the end of the unlinked list. This is due to the size
 * of the hash table and its location in the middle of the agi.
 *
 * For example, a request to log a field before agi_unlinked and a field after
 * agi_unlinked could cause us to log the entire hash table and use an excessive
 * amount of log space. To avoid this behavior, log the region up through
 * agi_unlinked in one call and the region after agi_unlinked through the end of
 * the structure in another.
 */
void
xfs_ialloc_log_agi(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	uint32_t		fields)
{
	int			first;		/* first byte number */
	int			last;		/* last byte number */
	static const short	offsets[] = {	/* field starting offsets */
					/* keep in sync with bit definitions */
		offsetof(xfs_agi_t, agi_magicnum),
		offsetof(xfs_agi_t, agi_versionnum),
		offsetof(xfs_agi_t, agi_seqno),
		offsetof(xfs_agi_t, agi_length),
		offsetof(xfs_agi_t, agi_count),
		offsetof(xfs_agi_t, agi_root),
		offsetof(xfs_agi_t, agi_level),
		offsetof(xfs_agi_t, agi_freecount),
		offsetof(xfs_agi_t, agi_newino),
		offsetof(xfs_agi_t, agi_dirino),
		offsetof(xfs_agi_t, agi_unlinked),
		offsetof(xfs_agi_t, agi_free_root),
		offsetof(xfs_agi_t, agi_free_level),
		offsetof(xfs_agi_t, agi_iblocks),
		sizeof(xfs_agi_t)
	};
#ifdef DEBUG
	struct xfs_agi		*agi = bp->b_addr;

	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
#endif

	/*
	 * Compute byte offsets for the first and last fields in the first
	 * region and log the agi buffer. This only logs up through
	 * agi_unlinked.
	 */
	if (fields & XFS_AGI_ALL_BITS_R1) {
		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1,
				  &first, &last);
		xfs_trans_log_buf(tp, bp, first, last);
	}

	/*
	 * Mask off the bits in the first region and calculate the first and
	 * last field offsets for any bits in the second region.
	 */
	fields &= ~XFS_AGI_ALL_BITS_R1;
	if (fields) {
		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2,
				  &first, &last);
		xfs_trans_log_buf(tp, bp, first, last);
	}
}

static xfs_failaddr_t
xfs_agi_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_mount;
	struct xfs_agi	*agi = bp->b_addr;
	int		i;

	if (xfs_has_crc(mp)) {
		if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid))
			return __this_address;
		if (!xfs_log_check_lsn(mp, be64_to_cpu(agi->agi_lsn)))
			return __this_address;
	}

	/*
	 * Validate the magic number of the agi block.
	 */
	if (!xfs_verify_magic(bp, agi->agi_magicnum))
		return __this_address;
	if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)))
		return __this_address;

	if (be32_to_cpu(agi->agi_level) < 1 ||
	    be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
		return __this_address;

	if (xfs_has_finobt(mp) &&
	    (be32_to_cpu(agi->agi_free_level) < 1 ||
	     be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
		return __this_address;

	/*
	 * during growfs operations, the perag is not fully initialised,
	 * so we can't use it for any useful checking. growfs ensures we can't
	 * use it by using uncached buffers that don't have the perag attached
	 * so we can detect and avoid this problem.
	 */
	if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno)
		return __this_address;

	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
			continue;
		if (!xfs_verify_ino(mp, be32_to_cpu(agi->agi_unlinked[i])))
			return __this_address;
	}

	return NULL;
}

static void
xfs_agi_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_mount;
	xfs_failaddr_t	fa;

	if (xfs_has_crc(mp) &&
	    !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF))
		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
	else {
		fa = xfs_agi_verify(bp);
		if (XFS_TEST_ERROR(fa, mp, XFS_ERRTAG_IALLOC_READ_AGI))
			xfs_verifier_error(bp, -EFSCORRUPTED, fa);
	}
}

static void
xfs_agi_write_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_mount;
	struct xfs_buf_log_item	*bip = bp->b_log_item;
	struct xfs_agi		*agi = bp->b_addr;
	xfs_failaddr_t		fa;

	fa = xfs_agi_verify(bp);
	if (fa) {
		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
		return;
	}

	if (!xfs_has_crc(mp))
		return;

	if (bip)
		agi->agi_lsn = cpu_to_be64(bip->bli_item.li_lsn);
	xfs_buf_update_cksum(bp, XFS_AGI_CRC_OFF);
}

const struct xfs_buf_ops xfs_agi_buf_ops = {
	.name = "xfs_agi",
	.magic = { cpu_to_be32(XFS_AGI_MAGIC), cpu_to_be32(XFS_AGI_MAGIC) },
	.verify_read = xfs_agi_read_verify,
	.verify_write = xfs_agi_write_verify,
	.verify_struct = xfs_agi_verify,
};

/*
 * Read in the allocation group header (inode allocation section)
 */
int
xfs_read_agi(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	struct xfs_buf		**agibpp)
{
	struct xfs_mount	*mp = pag->pag_mount;
	int			error;

	trace_xfs_read_agi(pag->pag_mount, pag->pag_agno);

	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
	if (error)
		return error;
	if (tp)
		xfs_trans_buf_set_type(tp, *agibpp, XFS_BLFT_AGI_BUF);

	xfs_buf_set_ref(*agibpp, XFS_AGI_REF);
	return 0;
}

/*
 * Read in the agi and initialise the per-ag data. If the caller supplies a
 * @agibpp, return the locked AGI buffer to them, otherwise release it.
 */
int
xfs_ialloc_read_agi(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	struct xfs_buf		**agibpp)
{
	struct xfs_buf		*agibp;
	struct xfs_agi		*agi;
	int			error;

	trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno);

	error = xfs_read_agi(pag, tp, &agibp);
	if (error)
		return error;

	agi = agibp->b_addr;
	if (!pag->pagi_init) {
		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
		pag->pagi_count = be32_to_cpu(agi->agi_count);
		pag->pagi_init = 1;
	}

	/*
	 * It's possible for these to be out of sync if
	 * we are in the middle of a forced shutdown.
	 */
	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
		xfs_is_shutdown(pag->pag_mount));
	if (agibpp)
		*agibpp = agibp;
	else
		xfs_trans_brelse(tp, agibp);
	return 0;
}

/* Is there an inode record covering a given range of inode numbers? */
int
xfs_ialloc_has_inode_record(
	struct xfs_btree_cur	*cur,
	xfs_agino_t		low,
	xfs_agino_t		high,
	bool			*exists)
{
	struct xfs_inobt_rec_incore	irec;
	xfs_agino_t		agino;
	uint16_t		holemask;
	int			has_record;
	int			i;
	int			error;

	*exists = false;
	error = xfs_inobt_lookup(cur, low, XFS_LOOKUP_LE, &has_record);
	while (error == 0 && has_record) {
		error = xfs_inobt_get_rec(cur, &irec, &has_record);
		if (error || irec.ir_startino > high)
			break;

		agino = irec.ir_startino;
		holemask = irec.ir_holemask;
		for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; holemask >>= 1,
				i++, agino += XFS_INODES_PER_HOLEMASK_BIT) {
			if (holemask & 1)
				continue;
			if (agino + XFS_INODES_PER_HOLEMASK_BIT > low &&
					agino <= high) {
				*exists = true;
				return 0;
			}
		}

		error = xfs_btree_increment(cur, 0, &has_record);
	}
	return error;
}

/* Is there an inode record covering a given extent? */
int
xfs_ialloc_has_inodes_at_extent(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	bool			*exists)
{
	xfs_agino_t		low;
	xfs_agino_t		high;

	low = XFS_AGB_TO_AGINO(cur->bc_mp, bno);
	high = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1;

	return xfs_ialloc_has_inode_record(cur, low, high, exists);
}

struct xfs_ialloc_count_inodes {
	xfs_agino_t			count;
	xfs_agino_t			freecount;
};

/* Record inode counts across all inobt records. */
STATIC int
xfs_ialloc_count_inodes_rec(
	struct xfs_btree_cur		*cur,
	const union xfs_btree_rec	*rec,
	void				*priv)
{
	struct xfs_inobt_rec_incore	irec;
	struct xfs_ialloc_count_inodes	*ci = priv;

	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
	ci->count += irec.ir_count;
	ci->freecount += irec.ir_freecount;

	return 0;
}

/* Count allocated and free inodes under an inobt. */
int
xfs_ialloc_count_inodes(
	struct xfs_btree_cur		*cur,
	xfs_agino_t			*count,
	xfs_agino_t			*freecount)
{
	struct xfs_ialloc_count_inodes	ci = {0};
	int				error;

	ASSERT(cur->bc_btnum == XFS_BTNUM_INO);
	error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_rec, &ci);
	if (error)
		return error;

	*count = ci.count;
	*freecount = ci.freecount;
	return 0;
}

/*
 * Initialize inode-related geometry information.
 *
 * Compute the inode btree min and max levels and set maxicount.
 *
 * Set the inode cluster size.  This may still be overridden by the file
 * system block size if it is larger than the chosen cluster size.
 *
 * For v5 filesystems, scale the cluster size with the inode size to keep a
 * constant ratio of inode per cluster buffer, but only if mkfs has set the
 * inode alignment value appropriately for larger cluster sizes.
 *
 * Then compute the inode cluster alignment information.
 */
void
xfs_ialloc_setup_geometry(
	struct xfs_mount	*mp)
{
	struct xfs_sb		*sbp = &mp->m_sb;
	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
	uint64_t		icount;
	uint			inodes;

	igeo->new_diflags2 = 0;
	if (xfs_has_bigtime(mp))
		igeo->new_diflags2 |= XFS_DIFLAG2_BIGTIME;
	if (xfs_has_large_extent_counts(mp))
		igeo->new_diflags2 |= XFS_DIFLAG2_NREXT64;

	/* Compute inode btree geometry. */
	igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
	igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);
	igeo->inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0);
	igeo->inobt_mnr[0] = igeo->inobt_mxr[0] / 2;
	igeo->inobt_mnr[1] = igeo->inobt_mxr[1] / 2;

	igeo->ialloc_inos = max_t(uint16_t, XFS_INODES_PER_CHUNK,
			sbp->sb_inopblock);
	igeo->ialloc_blks = igeo->ialloc_inos >> sbp->sb_inopblog;

	if (sbp->sb_spino_align)
		igeo->ialloc_min_blks = sbp->sb_spino_align;
	else
		igeo->ialloc_min_blks = igeo->ialloc_blks;

	/* Compute and fill in value of m_ino_geo.inobt_maxlevels. */
	inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG;
	igeo->inobt_maxlevels = xfs_btree_compute_maxlevels(igeo->inobt_mnr,
			inodes);
	ASSERT(igeo->inobt_maxlevels <= xfs_iallocbt_maxlevels_ondisk());

	/*
	 * Set the maximum inode count for this filesystem, being careful not
	 * to use obviously garbage sb_inopblog/sb_inopblock values.  Regular
	 * users should never get here due to failing sb verification, but
	 * certain users (xfs_db) need to be usable even with corrupt metadata.
	 */
	if (sbp->sb_imax_pct && igeo->ialloc_blks) {
		/*
		 * Make sure the maximum inode count is a multiple
		 * of the units we allocate inodes in.
		 */
		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
		do_div(icount, 100);
		do_div(icount, igeo->ialloc_blks);
		igeo->maxicount = XFS_FSB_TO_INO(mp,
				icount * igeo->ialloc_blks);
	} else {
		igeo->maxicount = 0;
	}

	/*
	 * Compute the desired size of an inode cluster buffer size, which
	 * starts at 8K and (on v5 filesystems) scales up with larger inode
	 * sizes.
	 *
	 * Preserve the desired inode cluster size because the sparse inodes
	 * feature uses that desired size (not the actual size) to compute the
	 * sparse inode alignment.  The mount code validates this value, so we
	 * cannot change the behavior.
	 */
	igeo->inode_cluster_size_raw = XFS_INODE_BIG_CLUSTER_SIZE;
	if (xfs_has_v3inodes(mp)) {
		int	new_size = igeo->inode_cluster_size_raw;

		new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
		if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
			igeo->inode_cluster_size_raw = new_size;
	}

	/* Calculate inode cluster ratios. */
	if (igeo->inode_cluster_size_raw > mp->m_sb.sb_blocksize)
		igeo->blocks_per_cluster = XFS_B_TO_FSBT(mp,
				igeo->inode_cluster_size_raw);
	else
		igeo->blocks_per_cluster = 1;
	igeo->inode_cluster_size = XFS_FSB_TO_B(mp, igeo->blocks_per_cluster);
	igeo->inodes_per_cluster = XFS_FSB_TO_INO(mp, igeo->blocks_per_cluster);

	/* Calculate inode cluster alignment. */
	if (xfs_has_align(mp) &&
	    mp->m_sb.sb_inoalignmt >= igeo->blocks_per_cluster)
		igeo->cluster_align = mp->m_sb.sb_inoalignmt;
	else
		igeo->cluster_align = 1;
	igeo->inoalign_mask = igeo->cluster_align - 1;
	igeo->cluster_align_inodes = XFS_FSB_TO_INO(mp, igeo->cluster_align);

	/*
	 * If we are using stripe alignment, check whether
	 * the stripe unit is a multiple of the inode alignment
	 */
	if (mp->m_dalign && igeo->inoalign_mask &&
	    !(mp->m_dalign & igeo->inoalign_mask))
		igeo->ialloc_align = mp->m_dalign;
	else
		igeo->ialloc_align = 0;
}

/* Compute the location of the root directory inode that is laid out by mkfs. */
xfs_ino_t
xfs_ialloc_calc_rootino(
	struct xfs_mount	*mp,
	int			sunit)
{
	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
	xfs_agblock_t		first_bno;

	/*
	 * Pre-calculate the geometry of AG 0.  We know what it looks like
	 * because libxfs knows how to create allocation groups now.
	 *
	 * first_bno is the first block in which mkfs could possibly have
	 * allocated the root directory inode, once we factor in the metadata
	 * that mkfs formats before it.  Namely, the four AG headers...
	 */
	first_bno = howmany(4 * mp->m_sb.sb_sectsize, mp->m_sb.sb_blocksize);

	/* ...the two free space btree roots... */
	first_bno += 2;

	/* ...the inode btree root... */
	first_bno += 1;

	/* ...the initial AGFL... */
	first_bno += xfs_alloc_min_freelist(mp, NULL);

	/* ...the free inode btree root... */
	if (xfs_has_finobt(mp))
		first_bno++;

	/* ...the reverse mapping btree root... */
	if (xfs_has_rmapbt(mp))
		first_bno++;

	/* ...the reference count btree... */
	if (xfs_has_reflink(mp))
		first_bno++;

	/*
	 * ...and the log, if it is allocated in the first allocation group.
	 *
	 * This can happen with filesystems that only have a single
	 * allocation group, or very odd geometries created by old mkfs
	 * versions on very small filesystems.
	 */
	if (xfs_ag_contains_log(mp, 0))
		 first_bno += mp->m_sb.sb_logblocks;

	/*
	 * Now round first_bno up to whatever allocation alignment is given
	 * by the filesystem or was passed in.
	 */
	if (xfs_has_dalign(mp) && igeo->ialloc_align > 0)
		first_bno = roundup(first_bno, sunit);
	else if (xfs_has_align(mp) &&
			mp->m_sb.sb_inoalignmt > 1)
		first_bno = roundup(first_bno, mp->m_sb.sb_inoalignmt);

	return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno));
}

/*
 * Ensure there are not sparse inode clusters that cross the new EOAG.
 *
 * This is a no-op for non-spinode filesystems since clusters are always fully
 * allocated and checking the bnobt suffices.  However, a spinode filesystem
 * could have a record where the upper inodes are free blocks.  If those blocks
 * were removed from the filesystem, the inode record would extend beyond EOAG,
 * which will be flagged as corruption.
 */
int
xfs_ialloc_check_shrink(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	struct xfs_buf		*agibp,
	xfs_agblock_t		new_length)
{
	struct xfs_inobt_rec_incore rec;
	struct xfs_btree_cur	*cur;
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_perag	*pag;
	xfs_agino_t		agino = XFS_AGB_TO_AGINO(mp, new_length);
	int			has;
	int			error;

	if (!xfs_has_sparseinodes(mp))
		return 0;

	pag = xfs_perag_get(mp, agno);
	cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO);

	/* Look up the inobt record that would correspond to the new EOFS. */
	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
	if (error || !has)
		goto out;

	error = xfs_inobt_get_rec(cur, &rec, &has);
	if (error)
		goto out;

	if (!has) {
		error = -EFSCORRUPTED;
		goto out;
	}

	/* If the record covers inodes that would be beyond EOFS, bail out. */
	if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) {
		error = -ENOSPC;
		goto out;
	}
out:
	xfs_btree_del_cursor(cur, error);
	xfs_perag_put(pag);
	return error;
}