aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/xattr.c
blob: dfc51c305bb9e83bc8d12a2a3e3985745277f2ad (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * xattr.c
 *
 * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
 *
 * CREDITS:
 * Lots of code in this file is copy from linux/fs/ext3/xattr.c.
 * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License version 2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */

#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/sched.h>
#include <linux/splice.h>
#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/sort.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/security.h>

#define MLOG_MASK_PREFIX ML_XATTR
#include <cluster/masklog.h>

#include "ocfs2.h"
#include "alloc.h"
#include "dlmglue.h"
#include "file.h"
#include "symlink.h"
#include "sysfile.h"
#include "inode.h"
#include "journal.h"
#include "ocfs2_fs.h"
#include "suballoc.h"
#include "uptodate.h"
#include "buffer_head_io.h"
#include "super.h"
#include "xattr.h"


struct ocfs2_xattr_def_value_root {
	struct ocfs2_xattr_value_root	xv;
	struct ocfs2_extent_rec		er;
};

struct ocfs2_xattr_bucket {
	/* The inode these xattrs are associated with */
	struct inode *bu_inode;

	/* The actual buffers that make up the bucket */
	struct buffer_head *bu_bhs[OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET];

	/* How many blocks make up one bucket for this filesystem */
	int bu_blocks;
};

struct ocfs2_xattr_set_ctxt {
	handle_t *handle;
	struct ocfs2_alloc_context *meta_ac;
	struct ocfs2_alloc_context *data_ac;
	struct ocfs2_cached_dealloc_ctxt dealloc;
};

#define OCFS2_XATTR_ROOT_SIZE	(sizeof(struct ocfs2_xattr_def_value_root))
#define OCFS2_XATTR_INLINE_SIZE	80
#define OCFS2_XATTR_FREE_IN_IBODY	(OCFS2_MIN_XATTR_INLINE_SIZE \
					 - sizeof(struct ocfs2_xattr_header) \
					 - sizeof(__u32))
#define OCFS2_XATTR_FREE_IN_BLOCK(ptr)	((ptr)->i_sb->s_blocksize \
					 - sizeof(struct ocfs2_xattr_block) \
					 - sizeof(struct ocfs2_xattr_header) \
					 - sizeof(__u32))

static struct ocfs2_xattr_def_value_root def_xv = {
	.xv.xr_list.l_count = cpu_to_le16(1),
};

struct xattr_handler *ocfs2_xattr_handlers[] = {
	&ocfs2_xattr_user_handler,
#ifdef CONFIG_OCFS2_FS_POSIX_ACL
	&ocfs2_xattr_acl_access_handler,
	&ocfs2_xattr_acl_default_handler,
#endif
	&ocfs2_xattr_trusted_handler,
	&ocfs2_xattr_security_handler,
	NULL
};

static struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = {
	[OCFS2_XATTR_INDEX_USER]	= &ocfs2_xattr_user_handler,
#ifdef CONFIG_OCFS2_FS_POSIX_ACL
	[OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS]
					= &ocfs2_xattr_acl_access_handler,
	[OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT]
					= &ocfs2_xattr_acl_default_handler,
#endif
	[OCFS2_XATTR_INDEX_TRUSTED]	= &ocfs2_xattr_trusted_handler,
	[OCFS2_XATTR_INDEX_SECURITY]	= &ocfs2_xattr_security_handler,
};

struct ocfs2_xattr_info {
	int name_index;
	const char *name;
	const void *value;
	size_t value_len;
};

struct ocfs2_xattr_search {
	struct buffer_head *inode_bh;
	/*
	 * xattr_bh point to the block buffer head which has extended attribute
	 * when extended attribute in inode, xattr_bh is equal to inode_bh.
	 */
	struct buffer_head *xattr_bh;
	struct ocfs2_xattr_header *header;
	struct ocfs2_xattr_bucket *bucket;
	void *base;
	void *end;
	struct ocfs2_xattr_entry *here;
	int not_found;
};

static int ocfs2_xattr_bucket_get_name_value(struct inode *inode,
					     struct ocfs2_xattr_header *xh,
					     int index,
					     int *block_off,
					     int *new_offset);

static int ocfs2_xattr_block_find(struct inode *inode,
				  int name_index,
				  const char *name,
				  struct ocfs2_xattr_search *xs);
static int ocfs2_xattr_index_block_find(struct inode *inode,
					struct buffer_head *root_bh,
					int name_index,
					const char *name,
					struct ocfs2_xattr_search *xs);

static int ocfs2_xattr_tree_list_index_block(struct inode *inode,
					struct ocfs2_xattr_tree_root *xt,
					char *buffer,
					size_t buffer_size);

static int ocfs2_xattr_create_index_block(struct inode *inode,
					  struct ocfs2_xattr_search *xs,
					  struct ocfs2_xattr_set_ctxt *ctxt);

static int ocfs2_xattr_set_entry_index_block(struct inode *inode,
					     struct ocfs2_xattr_info *xi,
					     struct ocfs2_xattr_search *xs,
					     struct ocfs2_xattr_set_ctxt *ctxt);

static int ocfs2_delete_xattr_index_block(struct inode *inode,
					  struct buffer_head *xb_bh);
static int ocfs2_mv_xattr_buckets(struct inode *inode, handle_t *handle,
				  u64 src_blk, u64 last_blk, u64 to_blk,
				  unsigned int start_bucket,
				  u32 *first_hash);

static inline u16 ocfs2_xattr_buckets_per_cluster(struct ocfs2_super *osb)
{
	return (1 << osb->s_clustersize_bits) / OCFS2_XATTR_BUCKET_SIZE;
}

static inline u16 ocfs2_blocks_per_xattr_bucket(struct super_block *sb)
{
	return OCFS2_XATTR_BUCKET_SIZE / (1 << sb->s_blocksize_bits);
}

static inline u16 ocfs2_xattr_max_xe_in_bucket(struct super_block *sb)
{
	u16 len = sb->s_blocksize -
		 offsetof(struct ocfs2_xattr_header, xh_entries);

	return len / sizeof(struct ocfs2_xattr_entry);
}

#define bucket_blkno(_b) ((_b)->bu_bhs[0]->b_blocknr)
#define bucket_block(_b, _n) ((_b)->bu_bhs[(_n)]->b_data)
#define bucket_xh(_b) ((struct ocfs2_xattr_header *)bucket_block((_b), 0))

static struct ocfs2_xattr_bucket *ocfs2_xattr_bucket_new(struct inode *inode)
{
	struct ocfs2_xattr_bucket *bucket;
	int blks = ocfs2_blocks_per_xattr_bucket(inode->i_sb);

	BUG_ON(blks > OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET);

	bucket = kzalloc(sizeof(struct ocfs2_xattr_bucket), GFP_NOFS);
	if (bucket) {
		bucket->bu_inode = inode;
		bucket->bu_blocks = blks;
	}

	return bucket;
}

static void ocfs2_xattr_bucket_relse(struct ocfs2_xattr_bucket *bucket)
{
	int i;

	for (i = 0; i < bucket->bu_blocks; i++) {
		brelse(bucket->bu_bhs[i]);
		bucket->bu_bhs[i] = NULL;
	}
}

static void ocfs2_xattr_bucket_free(struct ocfs2_xattr_bucket *bucket)
{
	if (bucket) {
		ocfs2_xattr_bucket_relse(bucket);
		bucket->bu_inode = NULL;
		kfree(bucket);
	}
}

/*
 * A bucket that has never been written to disk doesn't need to be
 * read.  We just need the buffer_heads.  Don't call this for
 * buckets that are already on disk.  ocfs2_read_xattr_bucket() initializes
 * them fully.
 */
static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket,
				   u64 xb_blkno)
{
	int i, rc = 0;

	for (i = 0; i < bucket->bu_blocks; i++) {
		bucket->bu_bhs[i] = sb_getblk(bucket->bu_inode->i_sb,
					      xb_blkno + i);
		if (!bucket->bu_bhs[i]) {
			rc = -EIO;
			mlog_errno(rc);
			break;
		}

		if (!ocfs2_buffer_uptodate(bucket->bu_inode,
					   bucket->bu_bhs[i]))
			ocfs2_set_new_buffer_uptodate(bucket->bu_inode,
						      bucket->bu_bhs[i]);
	}

	if (rc)
		ocfs2_xattr_bucket_relse(bucket);
	return rc;
}

/* Read the xattr bucket at xb_blkno */
static int ocfs2_read_xattr_bucket(struct ocfs2_xattr_bucket *bucket,
				   u64 xb_blkno)
{
	int rc;

	rc = ocfs2_read_blocks(bucket->bu_inode, xb_blkno,
			       bucket->bu_blocks, bucket->bu_bhs, 0,
			       NULL);
	if (rc)
		ocfs2_xattr_bucket_relse(bucket);
	return rc;
}

static int ocfs2_xattr_bucket_journal_access(handle_t *handle,
					     struct ocfs2_xattr_bucket *bucket,
					     int type)
{
	int i, rc = 0;

	for (i = 0; i < bucket->bu_blocks; i++) {
		rc = ocfs2_journal_access(handle, bucket->bu_inode,
					  bucket->bu_bhs[i], type);
		if (rc) {
			mlog_errno(rc);
			break;
		}
	}

	return rc;
}

static void ocfs2_xattr_bucket_journal_dirty(handle_t *handle,
					     struct ocfs2_xattr_bucket *bucket)
{
	int i;

	for (i = 0; i < bucket->bu_blocks; i++)
		ocfs2_journal_dirty(handle, bucket->bu_bhs[i]);
}

static void ocfs2_xattr_bucket_copy_data(struct ocfs2_xattr_bucket *dest,
					 struct ocfs2_xattr_bucket *src)
{
	int i;
	int blocksize = src->bu_inode->i_sb->s_blocksize;

	BUG_ON(dest->bu_blocks != src->bu_blocks);
	BUG_ON(dest->bu_inode != src->bu_inode);

	for (i = 0; i < src->bu_blocks; i++) {
		memcpy(bucket_block(dest, i), bucket_block(src, i),
		       blocksize);
	}
}

static int ocfs2_validate_xattr_block(struct super_block *sb,
				      struct buffer_head *bh)
{
	struct ocfs2_xattr_block *xb =
		(struct ocfs2_xattr_block *)bh->b_data;

	mlog(0, "Validating xattr block %llu\n",
	     (unsigned long long)bh->b_blocknr);

	if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
		ocfs2_error(sb,
			    "Extended attribute block #%llu has bad "
			    "signature %.*s",
			    (unsigned long long)bh->b_blocknr, 7,
			    xb->xb_signature);
		return -EINVAL;
	}

	if (le64_to_cpu(xb->xb_blkno) != bh->b_blocknr) {
		ocfs2_error(sb,
			    "Extended attribute block #%llu has an "
			    "invalid xb_blkno of %llu",
			    (unsigned long long)bh->b_blocknr,
			    (unsigned long long)le64_to_cpu(xb->xb_blkno));
		return -EINVAL;
	}

	if (le32_to_cpu(xb->xb_fs_generation) != OCFS2_SB(sb)->fs_generation) {
		ocfs2_error(sb,
			    "Extended attribute block #%llu has an invalid "
			    "xb_fs_generation of #%u",
			    (unsigned long long)bh->b_blocknr,
			    le32_to_cpu(xb->xb_fs_generation));
		return -EINVAL;
	}

	return 0;
}

static int ocfs2_read_xattr_block(struct inode *inode, u64 xb_blkno,
				  struct buffer_head **bh)
{
	int rc;
	struct buffer_head *tmp = *bh;

	rc = ocfs2_read_block(inode, xb_blkno, &tmp,
			      ocfs2_validate_xattr_block);

	/* If ocfs2_read_block() got us a new bh, pass it up. */
	if (!rc && !*bh)
		*bh = tmp;

	return rc;
}

static inline const char *ocfs2_xattr_prefix(int name_index)
{
	struct xattr_handler *handler = NULL;

	if (name_index > 0 && name_index < OCFS2_XATTR_MAX)
		handler = ocfs2_xattr_handler_map[name_index];

	return handler ? handler->prefix : NULL;
}

static u32 ocfs2_xattr_name_hash(struct inode *inode,
				 const char *name,
				 int name_len)
{
	/* Get hash value of uuid from super block */
	u32 hash = OCFS2_SB(inode->i_sb)->uuid_hash;
	int i;

	/* hash extended attribute name */
	for (i = 0; i < name_len; i++) {
		hash = (hash << OCFS2_HASH_SHIFT) ^
		       (hash >> (8*sizeof(hash) - OCFS2_HASH_SHIFT)) ^
		       *name++;
	}

	return hash;
}

/*
 * ocfs2_xattr_hash_entry()
 *
 * Compute the hash of an extended attribute.
 */
static void ocfs2_xattr_hash_entry(struct inode *inode,
				   struct ocfs2_xattr_header *header,
				   struct ocfs2_xattr_entry *entry)
{
	u32 hash = 0;
	char *name = (char *)header + le16_to_cpu(entry->xe_name_offset);

	hash = ocfs2_xattr_name_hash(inode, name, entry->xe_name_len);
	entry->xe_name_hash = cpu_to_le32(hash);

	return;
}

static int ocfs2_xattr_entry_real_size(int name_len, size_t value_len)
{
	int size = 0;

	if (value_len <= OCFS2_XATTR_INLINE_SIZE)
		size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_SIZE(value_len);
	else
		size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
	size += sizeof(struct ocfs2_xattr_entry);

	return size;
}

int ocfs2_calc_security_init(struct inode *dir,
			     struct ocfs2_security_xattr_info *si,
			     int *want_clusters,
			     int *xattr_credits,
			     struct ocfs2_alloc_context **xattr_ac)
{
	int ret = 0;
	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
	int s_size = ocfs2_xattr_entry_real_size(strlen(si->name),
						 si->value_len);

	/*
	 * The max space of security xattr taken inline is
	 * 256(name) + 80(value) + 16(entry) = 352 bytes,
	 * So reserve one metadata block for it is ok.
	 */
	if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE ||
	    s_size > OCFS2_XATTR_FREE_IN_IBODY) {
		ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac);
		if (ret) {
			mlog_errno(ret);
			return ret;
		}
		*xattr_credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
	}

	/* reserve clusters for xattr value which will be set in B tree*/
	if (si->value_len > OCFS2_XATTR_INLINE_SIZE)
		*want_clusters += ocfs2_clusters_for_bytes(dir->i_sb,
							   si->value_len);
	return ret;
}

int ocfs2_calc_xattr_init(struct inode *dir,
			  struct buffer_head *dir_bh,
			  int mode,
			  struct ocfs2_security_xattr_info *si,
			  int *want_clusters,
			  int *xattr_credits,
			  struct ocfs2_alloc_context **xattr_ac)
{
	int ret = 0;
	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
	int s_size = 0;
	int a_size = 0;
	int acl_len = 0;

	if (si->enable)
		s_size = ocfs2_xattr_entry_real_size(strlen(si->name),
						     si->value_len);

	if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
		acl_len = ocfs2_xattr_get_nolock(dir, dir_bh,
					OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT,
					"", NULL, 0);
		if (acl_len > 0) {
			a_size = ocfs2_xattr_entry_real_size(0, acl_len);
			if (S_ISDIR(mode))
				a_size <<= 1;
		} else if (acl_len != 0 && acl_len != -ENODATA) {
			mlog_errno(ret);
			return ret;
		}
	}

	if (!(s_size + a_size))
		return ret;

	/*
	 * The max space of security xattr taken inline is
	 * 256(name) + 80(value) + 16(entry) = 352 bytes,
	 * The max space of acl xattr taken inline is
	 * 80(value) + 16(entry) * 2(if directory) = 192 bytes,
	 * when blocksize = 512, may reserve one more cluser for
	 * xattr bucket, otherwise reserve one metadata block
	 * for them is ok.
	 */
	if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE ||
	    (s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) {
		ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac);
		if (ret) {
			mlog_errno(ret);
			return ret;
		}
		*xattr_credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
	}

	if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE &&
	    (s_size + a_size) > OCFS2_XATTR_FREE_IN_BLOCK(dir)) {
		*want_clusters += 1;
		*xattr_credits += ocfs2_blocks_per_xattr_bucket(dir->i_sb);
	}

	/* reserve clusters for xattr value which will be set in B tree*/
	if (si->enable && si->value_len > OCFS2_XATTR_INLINE_SIZE)
		*want_clusters += ocfs2_clusters_for_bytes(dir->i_sb,
							   si->value_len);
	if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL &&
	    acl_len > OCFS2_XATTR_INLINE_SIZE) {
		*want_clusters += ocfs2_clusters_for_bytes(dir->i_sb, acl_len);
		if (S_ISDIR(mode))
			*want_clusters += ocfs2_clusters_for_bytes(dir->i_sb,
								   acl_len);
	}

	return ret;
}

static int ocfs2_xattr_extend_allocation(struct inode *inode,
					 u32 clusters_to_add,
					 struct buffer_head *xattr_bh,
					 struct ocfs2_xattr_value_root *xv,
					 struct ocfs2_xattr_set_ctxt *ctxt)
{
	int status = 0;
	handle_t *handle = ctxt->handle;
	enum ocfs2_alloc_restarted why;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	u32 prev_clusters, logical_start = le32_to_cpu(xv->xr_clusters);
	struct ocfs2_extent_tree et;

	mlog(0, "(clusters_to_add for xattr= %u)\n", clusters_to_add);

	ocfs2_init_xattr_value_extent_tree(&et, inode, xattr_bh, xv);

	status = ocfs2_journal_access(handle, inode, xattr_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	prev_clusters = le32_to_cpu(xv->xr_clusters);
	status = ocfs2_add_clusters_in_btree(osb,
					     inode,
					     &logical_start,
					     clusters_to_add,
					     0,
					     &et,
					     handle,
					     ctxt->data_ac,
					     ctxt->meta_ac,
					     &why);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_journal_dirty(handle, xattr_bh);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	clusters_to_add -= le32_to_cpu(xv->xr_clusters) - prev_clusters;

	/*
	 * We should have already allocated enough space before the transaction,
	 * so no need to restart.
	 */
	BUG_ON(why != RESTART_NONE || clusters_to_add);

leave:

	return status;
}

static int __ocfs2_remove_xattr_range(struct inode *inode,
				      struct buffer_head *root_bh,
				      struct ocfs2_xattr_value_root *xv,
				      u32 cpos, u32 phys_cpos, u32 len,
				      struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret;
	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
	handle_t *handle = ctxt->handle;
	struct ocfs2_extent_tree et;

	ocfs2_init_xattr_value_extent_tree(&et, inode, root_bh, xv);

	ret = ocfs2_journal_access(handle, inode, root_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, ctxt->meta_ac,
				  &ctxt->dealloc);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	le32_add_cpu(&xv->xr_clusters, -len);

	ret = ocfs2_journal_dirty(handle, root_bh);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_cache_cluster_dealloc(&ctxt->dealloc, phys_blkno, len);
	if (ret)
		mlog_errno(ret);

out:
	return ret;
}

static int ocfs2_xattr_shrink_size(struct inode *inode,
				   u32 old_clusters,
				   u32 new_clusters,
				   struct buffer_head *root_bh,
				   struct ocfs2_xattr_value_root *xv,
				   struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret = 0;
	u32 trunc_len, cpos, phys_cpos, alloc_size;
	u64 block;

	if (old_clusters <= new_clusters)
		return 0;

	cpos = new_clusters;
	trunc_len = old_clusters - new_clusters;
	while (trunc_len) {
		ret = ocfs2_xattr_get_clusters(inode, cpos, &phys_cpos,
					       &alloc_size, &xv->xr_list);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		if (alloc_size > trunc_len)
			alloc_size = trunc_len;

		ret = __ocfs2_remove_xattr_range(inode, root_bh, xv, cpos,
						 phys_cpos, alloc_size,
						 ctxt);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		block = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
		ocfs2_remove_xattr_clusters_from_cache(inode, block,
						       alloc_size);
		cpos += alloc_size;
		trunc_len -= alloc_size;
	}

out:
	return ret;
}

static int ocfs2_xattr_value_truncate(struct inode *inode,
				      struct buffer_head *root_bh,
				      struct ocfs2_xattr_value_root *xv,
				      int len,
				      struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret;
	u32 new_clusters = ocfs2_clusters_for_bytes(inode->i_sb, len);
	u32 old_clusters = le32_to_cpu(xv->xr_clusters);

	if (new_clusters == old_clusters)
		return 0;

	if (new_clusters > old_clusters)
		ret = ocfs2_xattr_extend_allocation(inode,
						    new_clusters - old_clusters,
						    root_bh, xv, ctxt);
	else
		ret = ocfs2_xattr_shrink_size(inode,
					      old_clusters, new_clusters,
					      root_bh, xv, ctxt);

	return ret;
}

static int ocfs2_xattr_list_entry(char *buffer, size_t size,
				  size_t *result, const char *prefix,
				  const char *name, int name_len)
{
	char *p = buffer + *result;
	int prefix_len = strlen(prefix);
	int total_len = prefix_len + name_len + 1;

	*result += total_len;

	/* we are just looking for how big our buffer needs to be */
	if (!size)
		return 0;

	if (*result > size)
		return -ERANGE;

	memcpy(p, prefix, prefix_len);
	memcpy(p + prefix_len, name, name_len);
	p[prefix_len + name_len] = '\0';

	return 0;
}

static int ocfs2_xattr_list_entries(struct inode *inode,
				    struct ocfs2_xattr_header *header,
				    char *buffer, size_t buffer_size)
{
	size_t result = 0;
	int i, type, ret;
	const char *prefix, *name;

	for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) {
		struct ocfs2_xattr_entry *entry = &header->xh_entries[i];
		type = ocfs2_xattr_get_type(entry);
		prefix = ocfs2_xattr_prefix(type);

		if (prefix) {
			name = (const char *)header +
				le16_to_cpu(entry->xe_name_offset);

			ret = ocfs2_xattr_list_entry(buffer, buffer_size,
						     &result, prefix, name,
						     entry->xe_name_len);
			if (ret)
				return ret;
		}
	}

	return result;
}

static int ocfs2_xattr_ibody_list(struct inode *inode,
				  struct ocfs2_dinode *di,
				  char *buffer,
				  size_t buffer_size)
{
	struct ocfs2_xattr_header *header = NULL;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	int ret = 0;

	if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL))
		return ret;

	header = (struct ocfs2_xattr_header *)
		 ((void *)di + inode->i_sb->s_blocksize -
		 le16_to_cpu(di->i_xattr_inline_size));

	ret = ocfs2_xattr_list_entries(inode, header, buffer, buffer_size);

	return ret;
}

static int ocfs2_xattr_block_list(struct inode *inode,
				  struct ocfs2_dinode *di,
				  char *buffer,
				  size_t buffer_size)
{
	struct buffer_head *blk_bh = NULL;
	struct ocfs2_xattr_block *xb;
	int ret = 0;

	if (!di->i_xattr_loc)
		return ret;

	ret = ocfs2_read_xattr_block(inode, le64_to_cpu(di->i_xattr_loc),
				     &blk_bh);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}

	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
		struct ocfs2_xattr_header *header = &xb->xb_attrs.xb_header;
		ret = ocfs2_xattr_list_entries(inode, header,
					       buffer, buffer_size);
	} else {
		struct ocfs2_xattr_tree_root *xt = &xb->xb_attrs.xb_root;
		ret = ocfs2_xattr_tree_list_index_block(inode, xt,
						   buffer, buffer_size);
	}

	brelse(blk_bh);

	return ret;
}

ssize_t ocfs2_listxattr(struct dentry *dentry,
			char *buffer,
			size_t size)
{
	int ret = 0, i_ret = 0, b_ret = 0;
	struct buffer_head *di_bh = NULL;
	struct ocfs2_dinode *di = NULL;
	struct ocfs2_inode_info *oi = OCFS2_I(dentry->d_inode);

	if (!ocfs2_supports_xattr(OCFS2_SB(dentry->d_sb)))
		return -EOPNOTSUPP;

	if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
		return ret;

	ret = ocfs2_inode_lock(dentry->d_inode, &di_bh, 0);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}

	di = (struct ocfs2_dinode *)di_bh->b_data;

	down_read(&oi->ip_xattr_sem);
	i_ret = ocfs2_xattr_ibody_list(dentry->d_inode, di, buffer, size);
	if (i_ret < 0)
		b_ret = 0;
	else {
		if (buffer) {
			buffer += i_ret;
			size -= i_ret;
		}
		b_ret = ocfs2_xattr_block_list(dentry->d_inode, di,
					       buffer, size);
		if (b_ret < 0)
			i_ret = 0;
	}
	up_read(&oi->ip_xattr_sem);
	ocfs2_inode_unlock(dentry->d_inode, 0);

	brelse(di_bh);

	return i_ret + b_ret;
}

static int ocfs2_xattr_find_entry(int name_index,
				  const char *name,
				  struct ocfs2_xattr_search *xs)
{
	struct ocfs2_xattr_entry *entry;
	size_t name_len;
	int i, cmp = 1;

	if (name == NULL)
		return -EINVAL;

	name_len = strlen(name);
	entry = xs->here;
	for (i = 0; i < le16_to_cpu(xs->header->xh_count); i++) {
		cmp = name_index - ocfs2_xattr_get_type(entry);
		if (!cmp)
			cmp = name_len - entry->xe_name_len;
		if (!cmp)
			cmp = memcmp(name, (xs->base +
				     le16_to_cpu(entry->xe_name_offset)),
				     name_len);
		if (cmp == 0)
			break;
		entry += 1;
	}
	xs->here = entry;

	return cmp ? -ENODATA : 0;
}

static int ocfs2_xattr_get_value_outside(struct inode *inode,
					 struct ocfs2_xattr_value_root *xv,
					 void *buffer,
					 size_t len)
{
	u32 cpos, p_cluster, num_clusters, bpc, clusters;
	u64 blkno;
	int i, ret = 0;
	size_t cplen, blocksize;
	struct buffer_head *bh = NULL;
	struct ocfs2_extent_list *el;

	el = &xv->xr_list;
	clusters = le32_to_cpu(xv->xr_clusters);
	bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
	blocksize = inode->i_sb->s_blocksize;

	cpos = 0;
	while (cpos < clusters) {
		ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster,
					       &num_clusters, el);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster);
		/* Copy ocfs2_xattr_value */
		for (i = 0; i < num_clusters * bpc; i++, blkno++) {
			ret = ocfs2_read_block(inode, blkno, &bh, NULL);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			cplen = len >= blocksize ? blocksize : len;
			memcpy(buffer, bh->b_data, cplen);
			len -= cplen;
			buffer += cplen;

			brelse(bh);
			bh = NULL;
			if (len == 0)
				break;
		}
		cpos += num_clusters;
	}
out:
	return ret;
}

static int ocfs2_xattr_ibody_get(struct inode *inode,
				 int name_index,
				 const char *name,
				 void *buffer,
				 size_t buffer_size,
				 struct ocfs2_xattr_search *xs)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
	struct ocfs2_xattr_value_root *xv;
	size_t size;
	int ret = 0;

	if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL))
		return -ENODATA;

	xs->end = (void *)di + inode->i_sb->s_blocksize;
	xs->header = (struct ocfs2_xattr_header *)
			(xs->end - le16_to_cpu(di->i_xattr_inline_size));
	xs->base = (void *)xs->header;
	xs->here = xs->header->xh_entries;

	ret = ocfs2_xattr_find_entry(name_index, name, xs);
	if (ret)
		return ret;
	size = le64_to_cpu(xs->here->xe_value_size);
	if (buffer) {
		if (size > buffer_size)
			return -ERANGE;
		if (ocfs2_xattr_is_local(xs->here)) {
			memcpy(buffer, (void *)xs->base +
			       le16_to_cpu(xs->here->xe_name_offset) +
			       OCFS2_XATTR_SIZE(xs->here->xe_name_len), size);
		} else {
			xv = (struct ocfs2_xattr_value_root *)
				(xs->base + le16_to_cpu(
				 xs->here->xe_name_offset) +
				OCFS2_XATTR_SIZE(xs->here->xe_name_len));
			ret = ocfs2_xattr_get_value_outside(inode, xv,
							    buffer, size);
			if (ret < 0) {
				mlog_errno(ret);
				return ret;
			}
		}
	}

	return size;
}

static int ocfs2_xattr_block_get(struct inode *inode,
				 int name_index,
				 const char *name,
				 void *buffer,
				 size_t buffer_size,
				 struct ocfs2_xattr_search *xs)
{
	struct ocfs2_xattr_block *xb;
	struct ocfs2_xattr_value_root *xv;
	size_t size;
	int ret = -ENODATA, name_offset, name_len, block_off, i;

	xs->bucket = ocfs2_xattr_bucket_new(inode);
	if (!xs->bucket) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto cleanup;
	}

	ret = ocfs2_xattr_block_find(inode, name_index, name, xs);
	if (ret) {
		mlog_errno(ret);
		goto cleanup;
	}

	if (xs->not_found) {
		ret = -ENODATA;
		goto cleanup;
	}

	xb = (struct ocfs2_xattr_block *)xs->xattr_bh->b_data;
	size = le64_to_cpu(xs->here->xe_value_size);
	if (buffer) {
		ret = -ERANGE;
		if (size > buffer_size)
			goto cleanup;

		name_offset = le16_to_cpu(xs->here->xe_name_offset);
		name_len = OCFS2_XATTR_SIZE(xs->here->xe_name_len);
		i = xs->here - xs->header->xh_entries;

		if (le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED) {
			ret = ocfs2_xattr_bucket_get_name_value(inode,
								bucket_xh(xs->bucket),
								i,
								&block_off,
								&name_offset);
			xs->base = bucket_block(xs->bucket, block_off);
		}
		if (ocfs2_xattr_is_local(xs->here)) {
			memcpy(buffer, (void *)xs->base +
			       name_offset + name_len, size);
		} else {
			xv = (struct ocfs2_xattr_value_root *)
				(xs->base + name_offset + name_len);
			ret = ocfs2_xattr_get_value_outside(inode, xv,
							    buffer, size);
			if (ret < 0) {
				mlog_errno(ret);
				goto cleanup;
			}
		}
	}
	ret = size;
cleanup:
	ocfs2_xattr_bucket_free(xs->bucket);

	brelse(xs->xattr_bh);
	xs->xattr_bh = NULL;
	return ret;
}

int ocfs2_xattr_get_nolock(struct inode *inode,
			   struct buffer_head *di_bh,
			   int name_index,
			   const char *name,
			   void *buffer,
			   size_t buffer_size)
{
	int ret;
	struct ocfs2_dinode *di = NULL;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_xattr_search xis = {
		.not_found = -ENODATA,
	};
	struct ocfs2_xattr_search xbs = {
		.not_found = -ENODATA,
	};

	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
		return -EOPNOTSUPP;

	if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
		ret = -ENODATA;

	xis.inode_bh = xbs.inode_bh = di_bh;
	di = (struct ocfs2_dinode *)di_bh->b_data;

	down_read(&oi->ip_xattr_sem);
	ret = ocfs2_xattr_ibody_get(inode, name_index, name, buffer,
				    buffer_size, &xis);
	if (ret == -ENODATA && di->i_xattr_loc)
		ret = ocfs2_xattr_block_get(inode, name_index, name, buffer,
					    buffer_size, &xbs);
	up_read(&oi->ip_xattr_sem);

	return ret;
}

/* ocfs2_xattr_get()
 *
 * Copy an extended attribute into the buffer provided.
 * Buffer is NULL to compute the size of buffer required.
 */
static int ocfs2_xattr_get(struct inode *inode,
			   int name_index,
			   const char *name,
			   void *buffer,
			   size_t buffer_size)
{
	int ret;
	struct buffer_head *di_bh = NULL;

	ret = ocfs2_inode_lock(inode, &di_bh, 0);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}
	ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
				     name, buffer, buffer_size);

	ocfs2_inode_unlock(inode, 0);

	brelse(di_bh);

	return ret;
}

static int __ocfs2_xattr_set_value_outside(struct inode *inode,
					   handle_t *handle,
					   struct ocfs2_xattr_value_root *xv,
					   const void *value,
					   int value_len)
{
	int ret = 0, i, cp_len, credits;
	u16 blocksize = inode->i_sb->s_blocksize;
	u32 p_cluster, num_clusters;
	u32 cpos = 0, bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
	u32 clusters = ocfs2_clusters_for_bytes(inode->i_sb, value_len);
	u64 blkno;
	struct buffer_head *bh = NULL;

	BUG_ON(clusters > le32_to_cpu(xv->xr_clusters));

	/*
	 * In __ocfs2_xattr_set_value_outside has already been dirtied,
	 * so we don't need to worry about whether ocfs2_extend_trans
	 * will create a new transactio for us or not.
	 */
	credits = clusters * bpc;
	ret = ocfs2_extend_trans(handle, credits);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	while (cpos < clusters) {
		ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster,
					       &num_clusters, &xv->xr_list);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster);

		for (i = 0; i < num_clusters * bpc; i++, blkno++) {
			ret = ocfs2_read_block(inode, blkno, &bh, NULL);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			ret = ocfs2_journal_access(handle,
						   inode,
						   bh,
						   OCFS2_JOURNAL_ACCESS_WRITE);
			if (ret < 0) {
				mlog_errno(ret);
				goto out;
			}

			cp_len = value_len > blocksize ? blocksize : value_len;
			memcpy(bh->b_data, value, cp_len);
			value_len -= cp_len;
			value += cp_len;
			if (cp_len < blocksize)
				memset(bh->b_data + cp_len, 0,
				       blocksize - cp_len);

			ret = ocfs2_journal_dirty(handle, bh);
			if (ret < 0) {
				mlog_errno(ret);
				goto out;
			}
			brelse(bh);
			bh = NULL;

			/*
			 * XXX: do we need to empty all the following
			 * blocks in this cluster?
			 */
			if (!value_len)
				break;
		}
		cpos += num_clusters;
	}
out:
	brelse(bh);

	return ret;
}

static int ocfs2_xattr_cleanup(struct inode *inode,
			       handle_t *handle,
			       struct ocfs2_xattr_info *xi,
			       struct ocfs2_xattr_search *xs,
			       size_t offs)
{
	int ret = 0;
	size_t name_len = strlen(xi->name);
	void *val = xs->base + offs;
	size_t size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;

	ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}
	/* Decrease xattr count */
	le16_add_cpu(&xs->header->xh_count, -1);
	/* Remove the xattr entry and tree root which has already be set*/
	memset((void *)xs->here, 0, sizeof(struct ocfs2_xattr_entry));
	memset(val, 0, size);

	ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
	if (ret < 0)
		mlog_errno(ret);
out:
	return ret;
}

static int ocfs2_xattr_update_entry(struct inode *inode,
				    handle_t *handle,
				    struct ocfs2_xattr_info *xi,
				    struct ocfs2_xattr_search *xs,
				    size_t offs)
{
	int ret;

	ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	xs->here->xe_name_offset = cpu_to_le16(offs);
	xs->here->xe_value_size = cpu_to_le64(xi->value_len);
	if (xi->value_len <= OCFS2_XATTR_INLINE_SIZE)
		ocfs2_xattr_set_local(xs->here, 1);
	else
		ocfs2_xattr_set_local(xs->here, 0);
	ocfs2_xattr_hash_entry(inode, xs->header, xs->here);

	ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
	if (ret < 0)
		mlog_errno(ret);
out:
	return ret;
}

/*
 * ocfs2_xattr_set_value_outside()
 *
 * Set large size value in B tree.
 */
static int ocfs2_xattr_set_value_outside(struct inode *inode,
					 struct ocfs2_xattr_info *xi,
					 struct ocfs2_xattr_search *xs,
					 struct ocfs2_xattr_set_ctxt *ctxt,
					 size_t offs)
{
	size_t name_len = strlen(xi->name);
	void *val = xs->base + offs;
	struct ocfs2_xattr_value_root *xv = NULL;
	size_t size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
	int ret = 0;

	memset(val, 0, size);
	memcpy(val, xi->name, name_len);
	xv = (struct ocfs2_xattr_value_root *)
		(val + OCFS2_XATTR_SIZE(name_len));
	xv->xr_clusters = 0;
	xv->xr_last_eb_blk = 0;
	xv->xr_list.l_tree_depth = 0;
	xv->xr_list.l_count = cpu_to_le16(1);
	xv->xr_list.l_next_free_rec = 0;

	ret = ocfs2_xattr_value_truncate(inode, xs->xattr_bh, xv,
					 xi->value_len, ctxt);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}
	ret = ocfs2_xattr_update_entry(inode, ctxt->handle, xi, xs, offs);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}
	ret = __ocfs2_xattr_set_value_outside(inode, ctxt->handle, xv,
					      xi->value, xi->value_len);
	if (ret < 0)
		mlog_errno(ret);

	return ret;
}

/*
 * ocfs2_xattr_set_entry_local()
 *
 * Set, replace or remove extended attribute in local.
 */
static void ocfs2_xattr_set_entry_local(struct inode *inode,
					struct ocfs2_xattr_info *xi,
					struct ocfs2_xattr_search *xs,
					struct ocfs2_xattr_entry *last,
					size_t min_offs)
{
	size_t name_len = strlen(xi->name);
	int i;

	if (xi->value && xs->not_found) {
		/* Insert the new xattr entry. */
		le16_add_cpu(&xs->header->xh_count, 1);
		ocfs2_xattr_set_type(last, xi->name_index);
		ocfs2_xattr_set_local(last, 1);
		last->xe_name_len = name_len;
	} else {
		void *first_val;
		void *val;
		size_t offs, size;

		first_val = xs->base + min_offs;
		offs = le16_to_cpu(xs->here->xe_name_offset);
		val = xs->base + offs;

		if (le64_to_cpu(xs->here->xe_value_size) >
		    OCFS2_XATTR_INLINE_SIZE)
			size = OCFS2_XATTR_SIZE(name_len) +
				OCFS2_XATTR_ROOT_SIZE;
		else
			size = OCFS2_XATTR_SIZE(name_len) +
			OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));

		if (xi->value && size == OCFS2_XATTR_SIZE(name_len) +
				OCFS2_XATTR_SIZE(xi->value_len)) {
			/* The old and the new value have the
			   same size. Just replace the value. */
			ocfs2_xattr_set_local(xs->here, 1);
			xs->here->xe_value_size = cpu_to_le64(xi->value_len);
			/* Clear value bytes. */
			memset(val + OCFS2_XATTR_SIZE(name_len),
			       0,
			       OCFS2_XATTR_SIZE(xi->value_len));
			memcpy(val + OCFS2_XATTR_SIZE(name_len),
			       xi->value,
			       xi->value_len);
			return;
		}
		/* Remove the old name+value. */
		memmove(first_val + size, first_val, val - first_val);
		memset(first_val, 0, size);
		xs->here->xe_name_hash = 0;
		xs->here->xe_name_offset = 0;
		ocfs2_xattr_set_local(xs->here, 1);
		xs->here->xe_value_size = 0;

		min_offs += size;

		/* Adjust all value offsets. */
		last = xs->header->xh_entries;
		for (i = 0 ; i < le16_to_cpu(xs->header->xh_count); i++) {
			size_t o = le16_to_cpu(last->xe_name_offset);

			if (o < offs)
				last->xe_name_offset = cpu_to_le16(o + size);
			last += 1;
		}

		if (!xi->value) {
			/* Remove the old entry. */
			last -= 1;
			memmove(xs->here, xs->here + 1,
				(void *)last - (void *)xs->here);
			memset(last, 0, sizeof(struct ocfs2_xattr_entry));
			le16_add_cpu(&xs->header->xh_count, -1);
		}
	}
	if (xi->value) {
		/* Insert the new name+value. */
		size_t size = OCFS2_XATTR_SIZE(name_len) +
				OCFS2_XATTR_SIZE(xi->value_len);
		void *val = xs->base + min_offs - size;

		xs->here->xe_name_offset = cpu_to_le16(min_offs - size);
		memset(val, 0, size);
		memcpy(val, xi->name, name_len);
		memcpy(val + OCFS2_XATTR_SIZE(name_len),
		       xi->value,
		       xi->value_len);
		xs->here->xe_value_size = cpu_to_le64(xi->value_len);
		ocfs2_xattr_set_local(xs->here, 1);
		ocfs2_xattr_hash_entry(inode, xs->header, xs->here);
	}

	return;
}

/*
 * ocfs2_xattr_set_entry()
 *
 * Set extended attribute entry into inode or block.
 *
 * If extended attribute value size > OCFS2_XATTR_INLINE_SIZE,
 * We first insert tree root(ocfs2_xattr_value_root) with set_entry_local(),
 * then set value in B tree with set_value_outside().
 */
static int ocfs2_xattr_set_entry(struct inode *inode,
				 struct ocfs2_xattr_info *xi,
				 struct ocfs2_xattr_search *xs,
				 struct ocfs2_xattr_set_ctxt *ctxt,
				 int flag)
{
	struct ocfs2_xattr_entry *last;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
	size_t min_offs = xs->end - xs->base, name_len = strlen(xi->name);
	size_t size_l = 0;
	handle_t *handle = ctxt->handle;
	int free, i, ret;
	struct ocfs2_xattr_info xi_l = {
		.name_index = xi->name_index,
		.name = xi->name,
		.value = xi->value,
		.value_len = xi->value_len,
	};

	/* Compute min_offs, last and free space. */
	last = xs->header->xh_entries;

	for (i = 0 ; i < le16_to_cpu(xs->header->xh_count); i++) {
		size_t offs = le16_to_cpu(last->xe_name_offset);
		if (offs < min_offs)
			min_offs = offs;
		last += 1;
	}

	free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
	if (free < 0)
		return -EIO;

	if (!xs->not_found) {
		size_t size = 0;
		if (ocfs2_xattr_is_local(xs->here))
			size = OCFS2_XATTR_SIZE(name_len) +
			OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));
		else
			size = OCFS2_XATTR_SIZE(name_len) +
				OCFS2_XATTR_ROOT_SIZE;
		free += (size + sizeof(struct ocfs2_xattr_entry));
	}
	/* Check free space in inode or block */
	if (xi->value && xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
		if (free < sizeof(struct ocfs2_xattr_entry) +
			   OCFS2_XATTR_SIZE(name_len) +
			   OCFS2_XATTR_ROOT_SIZE) {
			ret = -ENOSPC;
			goto out;
		}
		size_l = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
		xi_l.value = (void *)&def_xv;
		xi_l.value_len = OCFS2_XATTR_ROOT_SIZE;
	} else if (xi->value) {
		if (free < sizeof(struct ocfs2_xattr_entry) +
			   OCFS2_XATTR_SIZE(name_len) +
			   OCFS2_XATTR_SIZE(xi->value_len)) {
			ret = -ENOSPC;
			goto out;
		}
	}

	if (!xs->not_found) {
		/* For existing extended attribute */
		size_t size = OCFS2_XATTR_SIZE(name_len) +
			OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));
		size_t offs = le16_to_cpu(xs->here->xe_name_offset);
		void *val = xs->base + offs;

		if (ocfs2_xattr_is_local(xs->here) && size == size_l) {
			/* Replace existing local xattr with tree root */
			ret = ocfs2_xattr_set_value_outside(inode, xi, xs,
							    ctxt, offs);
			if (ret < 0)
				mlog_errno(ret);
			goto out;
		} else if (!ocfs2_xattr_is_local(xs->here)) {
			/* For existing xattr which has value outside */
			struct ocfs2_xattr_value_root *xv = NULL;
			xv = (struct ocfs2_xattr_value_root *)(val +
				OCFS2_XATTR_SIZE(name_len));

			if (xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
				/*
				 * If new value need set outside also,
				 * first truncate old value to new value,
				 * then set new value with set_value_outside().
				 */
				ret = ocfs2_xattr_value_truncate(inode,
								 xs->xattr_bh,
								 xv,
								 xi->value_len,
								 ctxt);
				if (ret < 0) {
					mlog_errno(ret);
					goto out;
				}

				ret = ocfs2_xattr_update_entry(inode,
							       handle,
							       xi,
							       xs,
							       offs);
				if (ret < 0) {
					mlog_errno(ret);
					goto out;
				}

				ret = __ocfs2_xattr_set_value_outside(inode,
								handle,
								xv,
								xi->value,
								xi->value_len);
				if (ret < 0)
					mlog_errno(ret);
				goto out;
			} else {
				/*
				 * If new value need set in local,
				 * just trucate old value to zero.
				 */
				 ret = ocfs2_xattr_value_truncate(inode,
								  xs->xattr_bh,
								  xv,
								  0,
								  ctxt);
				if (ret < 0)
					mlog_errno(ret);
			}
		}
	}

	ret = ocfs2_journal_access(handle, inode, xs->inode_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	if (!(flag & OCFS2_INLINE_XATTR_FL)) {
		ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
					   OCFS2_JOURNAL_ACCESS_WRITE);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	/*
	 * Set value in local, include set tree root in local.
	 * This is the first step for value size >INLINE_SIZE.
	 */
	ocfs2_xattr_set_entry_local(inode, &xi_l, xs, last, min_offs);

	if (!(flag & OCFS2_INLINE_XATTR_FL)) {
		ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) &&
	    (flag & OCFS2_INLINE_XATTR_FL)) {
		struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
		unsigned int xattrsize = osb->s_xattr_inline_size;

		/*
		 * Adjust extent record count or inline data size
		 * to reserve space for extended attribute.
		 */
		if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
			struct ocfs2_inline_data *idata = &di->id2.i_data;
			le16_add_cpu(&idata->id_count, -xattrsize);
		} else if (!(ocfs2_inode_is_fast_symlink(inode))) {
			struct ocfs2_extent_list *el = &di->id2.i_list;
			le16_add_cpu(&el->l_count, -(xattrsize /
					sizeof(struct ocfs2_extent_rec)));
		}
		di->i_xattr_inline_size = cpu_to_le16(xattrsize);
	}
	/* Update xattr flag */
	spin_lock(&oi->ip_lock);
	oi->ip_dyn_features |= flag;
	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
	spin_unlock(&oi->ip_lock);
	/* Update inode ctime */
	inode->i_ctime = CURRENT_TIME;
	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);

	ret = ocfs2_journal_dirty(handle, xs->inode_bh);
	if (ret < 0)
		mlog_errno(ret);

	if (!ret && xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
		/*
		 * Set value outside in B tree.
		 * This is the second step for value size > INLINE_SIZE.
		 */
		size_t offs = le16_to_cpu(xs->here->xe_name_offset);
		ret = ocfs2_xattr_set_value_outside(inode, xi, xs, ctxt, offs);
		if (ret < 0) {
			int ret2;

			mlog_errno(ret);
			/*
			 * If set value outside failed, we have to clean
			 * the junk tree root we have already set in local.
			 */
			ret2 = ocfs2_xattr_cleanup(inode, ctxt->handle,
						   xi, xs, offs);
			if (ret2 < 0)
				mlog_errno(ret2);
		}
	}
out:
	return ret;
}

static int ocfs2_remove_value_outside(struct inode*inode,
				      struct buffer_head *bh,
				      struct ocfs2_xattr_header *header)
{
	int ret = 0, i;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, };

	ocfs2_init_dealloc_ctxt(&ctxt.dealloc);

	ctxt.handle = ocfs2_start_trans(osb,
					ocfs2_remove_extent_credits(osb->sb));
	if (IS_ERR(ctxt.handle)) {
		ret = PTR_ERR(ctxt.handle);
		mlog_errno(ret);
		goto out;
	}

	for (i = 0; i < le16_to_cpu(header->xh_count); i++) {
		struct ocfs2_xattr_entry *entry = &header->xh_entries[i];

		if (!ocfs2_xattr_is_local(entry)) {
			struct ocfs2_xattr_value_root *xv;
			void *val;

			val = (void *)header +
				le16_to_cpu(entry->xe_name_offset);
			xv = (struct ocfs2_xattr_value_root *)
				(val + OCFS2_XATTR_SIZE(entry->xe_name_len));
			ret = ocfs2_xattr_value_truncate(inode, bh, xv,
							 0, &ctxt);
			if (ret < 0) {
				mlog_errno(ret);
				break;
			}
		}
	}

	ocfs2_commit_trans(osb, ctxt.handle);
	ocfs2_schedule_truncate_log_flush(osb, 1);
	ocfs2_run_deallocs(osb, &ctxt.dealloc);
out:
	return ret;
}

static int ocfs2_xattr_ibody_remove(struct inode *inode,
				    struct buffer_head *di_bh)
{

	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
	struct ocfs2_xattr_header *header;
	int ret;

	header = (struct ocfs2_xattr_header *)
		 ((void *)di + inode->i_sb->s_blocksize -
		 le16_to_cpu(di->i_xattr_inline_size));

	ret = ocfs2_remove_value_outside(inode, di_bh, header);

	return ret;
}

static int ocfs2_xattr_block_remove(struct inode *inode,
				    struct buffer_head *blk_bh)
{
	struct ocfs2_xattr_block *xb;
	int ret = 0;

	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
		struct ocfs2_xattr_header *header = &(xb->xb_attrs.xb_header);
		ret = ocfs2_remove_value_outside(inode, blk_bh, header);
	} else
		ret = ocfs2_delete_xattr_index_block(inode, blk_bh);

	return ret;
}

static int ocfs2_xattr_free_block(struct inode *inode,
				  u64 block)
{
	struct inode *xb_alloc_inode;
	struct buffer_head *xb_alloc_bh = NULL;
	struct buffer_head *blk_bh = NULL;
	struct ocfs2_xattr_block *xb;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	handle_t *handle;
	int ret = 0;
	u64 blk, bg_blkno;
	u16 bit;

	ret = ocfs2_read_xattr_block(inode, block, &blk_bh);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_block_remove(inode, blk_bh);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
	blk = le64_to_cpu(xb->xb_blkno);
	bit = le16_to_cpu(xb->xb_suballoc_bit);
	bg_blkno = ocfs2_which_suballoc_group(blk, bit);

	xb_alloc_inode = ocfs2_get_system_file_inode(osb,
				EXTENT_ALLOC_SYSTEM_INODE,
				le16_to_cpu(xb->xb_suballoc_slot));
	if (!xb_alloc_inode) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}
	mutex_lock(&xb_alloc_inode->i_mutex);

	ret = ocfs2_inode_lock(xb_alloc_inode, &xb_alloc_bh, 1);
	if (ret < 0) {
		mlog_errno(ret);
		goto out_mutex;
	}

	handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out_unlock;
	}

	ret = ocfs2_free_suballoc_bits(handle, xb_alloc_inode, xb_alloc_bh,
				       bit, bg_blkno, 1);
	if (ret < 0)
		mlog_errno(ret);

	ocfs2_commit_trans(osb, handle);
out_unlock:
	ocfs2_inode_unlock(xb_alloc_inode, 1);
	brelse(xb_alloc_bh);
out_mutex:
	mutex_unlock(&xb_alloc_inode->i_mutex);
	iput(xb_alloc_inode);
out:
	brelse(blk_bh);
	return ret;
}

/*
 * ocfs2_xattr_remove()
 *
 * Free extended attribute resources associated with this inode.
 */
int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
	handle_t *handle;
	int ret;

	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
		return 0;

	if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
		return 0;

	if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
		ret = ocfs2_xattr_ibody_remove(inode, di_bh);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	if (di->i_xattr_loc) {
		ret = ocfs2_xattr_free_block(inode,
					     le64_to_cpu(di->i_xattr_loc));
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)),
				   OCFS2_INODE_UPDATE_CREDITS);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out;
	}
	ret = ocfs2_journal_access(handle, inode, di_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	di->i_xattr_loc = 0;

	spin_lock(&oi->ip_lock);
	oi->ip_dyn_features &= ~(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL);
	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
	spin_unlock(&oi->ip_lock);

	ret = ocfs2_journal_dirty(handle, di_bh);
	if (ret < 0)
		mlog_errno(ret);
out_commit:
	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
out:
	return ret;
}

static int ocfs2_xattr_has_space_inline(struct inode *inode,
					struct ocfs2_dinode *di)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	unsigned int xattrsize = OCFS2_SB(inode->i_sb)->s_xattr_inline_size;
	int free;

	if (xattrsize < OCFS2_MIN_XATTR_INLINE_SIZE)
		return 0;

	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
		struct ocfs2_inline_data *idata = &di->id2.i_data;
		free = le16_to_cpu(idata->id_count) - le64_to_cpu(di->i_size);
	} else if (ocfs2_inode_is_fast_symlink(inode)) {
		free = ocfs2_fast_symlink_chars(inode->i_sb) -
			le64_to_cpu(di->i_size);
	} else {
		struct ocfs2_extent_list *el = &di->id2.i_list;
		free = (le16_to_cpu(el->l_count) -
			le16_to_cpu(el->l_next_free_rec)) *
			sizeof(struct ocfs2_extent_rec);
	}
	if (free >= xattrsize)
		return 1;

	return 0;
}

/*
 * ocfs2_xattr_ibody_find()
 *
 * Find extended attribute in inode block and
 * fill search info into struct ocfs2_xattr_search.
 */
static int ocfs2_xattr_ibody_find(struct inode *inode,
				  int name_index,
				  const char *name,
				  struct ocfs2_xattr_search *xs)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
	int ret;
	int has_space = 0;

	if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE)
		return 0;

	if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
		down_read(&oi->ip_alloc_sem);
		has_space = ocfs2_xattr_has_space_inline(inode, di);
		up_read(&oi->ip_alloc_sem);
		if (!has_space)
			return 0;
	}

	xs->xattr_bh = xs->inode_bh;
	xs->end = (void *)di + inode->i_sb->s_blocksize;
	if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)
		xs->header = (struct ocfs2_xattr_header *)
			(xs->end - le16_to_cpu(di->i_xattr_inline_size));
	else
		xs->header = (struct ocfs2_xattr_header *)
			(xs->end - OCFS2_SB(inode->i_sb)->s_xattr_inline_size);
	xs->base = (void *)xs->header;
	xs->here = xs->header->xh_entries;

	/* Find the named attribute. */
	if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
		ret = ocfs2_xattr_find_entry(name_index, name, xs);
		if (ret && ret != -ENODATA)
			return ret;
		xs->not_found = ret;
	}

	return 0;
}

/*
 * ocfs2_xattr_ibody_set()
 *
 * Set, replace or remove an extended attribute into inode block.
 *
 */
static int ocfs2_xattr_ibody_set(struct inode *inode,
				 struct ocfs2_xattr_info *xi,
				 struct ocfs2_xattr_search *xs,
				 struct ocfs2_xattr_set_ctxt *ctxt)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
	int ret;

	if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE)
		return -ENOSPC;

	down_write(&oi->ip_alloc_sem);
	if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
		if (!ocfs2_xattr_has_space_inline(inode, di)) {
			ret = -ENOSPC;
			goto out;
		}
	}

	ret = ocfs2_xattr_set_entry(inode, xi, xs, ctxt,
				(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL));
out:
	up_write(&oi->ip_alloc_sem);

	return ret;
}

/*
 * ocfs2_xattr_block_find()
 *
 * Find extended attribute in external block and
 * fill search info into struct ocfs2_xattr_search.
 */
static int ocfs2_xattr_block_find(struct inode *inode,
				  int name_index,
				  const char *name,
				  struct ocfs2_xattr_search *xs)
{
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
	struct buffer_head *blk_bh = NULL;
	struct ocfs2_xattr_block *xb;
	int ret = 0;

	if (!di->i_xattr_loc)
		return ret;

	ret = ocfs2_read_xattr_block(inode, le64_to_cpu(di->i_xattr_loc),
				     &blk_bh);
	if (ret < 0) {
		mlog_errno(ret);
		return ret;
	}

	xs->xattr_bh = blk_bh;
	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;

	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
		xs->header = &xb->xb_attrs.xb_header;
		xs->base = (void *)xs->header;
		xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
		xs->here = xs->header->xh_entries;

		ret = ocfs2_xattr_find_entry(name_index, name, xs);
	} else
		ret = ocfs2_xattr_index_block_find(inode, blk_bh,
						   name_index,
						   name, xs);

	if (ret && ret != -ENODATA) {
		xs->xattr_bh = NULL;
		goto cleanup;
	}
	xs->not_found = ret;
	return 0;
cleanup:
	brelse(blk_bh);

	return ret;
}

/*
 * ocfs2_xattr_block_set()
 *
 * Set, replace or remove an extended attribute into external block.
 *
 */
static int ocfs2_xattr_block_set(struct inode *inode,
				 struct ocfs2_xattr_info *xi,
				 struct ocfs2_xattr_search *xs,
				 struct ocfs2_xattr_set_ctxt *ctxt)
{
	struct buffer_head *new_bh = NULL;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_dinode *di =  (struct ocfs2_dinode *)xs->inode_bh->b_data;
	handle_t *handle = ctxt->handle;
	struct ocfs2_xattr_block *xblk = NULL;
	u16 suballoc_bit_start;
	u32 num_got;
	u64 first_blkno;
	int ret;

	if (!xs->xattr_bh) {
		ret = ocfs2_journal_access(handle, inode, xs->inode_bh,
					   OCFS2_JOURNAL_ACCESS_CREATE);
		if (ret < 0) {
			mlog_errno(ret);
			goto end;
		}

		ret = ocfs2_claim_metadata(osb, handle, ctxt->meta_ac, 1,
					   &suballoc_bit_start, &num_got,
					   &first_blkno);
		if (ret < 0) {
			mlog_errno(ret);
			goto end;
		}

		new_bh = sb_getblk(inode->i_sb, first_blkno);
		ocfs2_set_new_buffer_uptodate(inode, new_bh);

		ret = ocfs2_journal_access(handle, inode, new_bh,
					   OCFS2_JOURNAL_ACCESS_CREATE);
		if (ret < 0) {
			mlog_errno(ret);
			goto end;
		}

		/* Initialize ocfs2_xattr_block */
		xs->xattr_bh = new_bh;
		xblk = (struct ocfs2_xattr_block *)new_bh->b_data;
		memset(xblk, 0, inode->i_sb->s_blocksize);
		strcpy((void *)xblk, OCFS2_XATTR_BLOCK_SIGNATURE);
		xblk->xb_suballoc_slot = cpu_to_le16(osb->slot_num);
		xblk->xb_suballoc_bit = cpu_to_le16(suballoc_bit_start);
		xblk->xb_fs_generation = cpu_to_le32(osb->fs_generation);
		xblk->xb_blkno = cpu_to_le64(first_blkno);

		xs->header = &xblk->xb_attrs.xb_header;
		xs->base = (void *)xs->header;
		xs->end = (void *)xblk + inode->i_sb->s_blocksize;
		xs->here = xs->header->xh_entries;

		ret = ocfs2_journal_dirty(handle, new_bh);
		if (ret < 0) {
			mlog_errno(ret);
			goto end;
		}
		di->i_xattr_loc = cpu_to_le64(first_blkno);
		ocfs2_journal_dirty(handle, xs->inode_bh);
	} else
		xblk = (struct ocfs2_xattr_block *)xs->xattr_bh->b_data;

	if (!(le16_to_cpu(xblk->xb_flags) & OCFS2_XATTR_INDEXED)) {
		/* Set extended attribute into external block */
		ret = ocfs2_xattr_set_entry(inode, xi, xs, ctxt,
					    OCFS2_HAS_XATTR_FL);
		if (!ret || ret != -ENOSPC)
			goto end;

		ret = ocfs2_xattr_create_index_block(inode, xs, ctxt);
		if (ret)
			goto end;
	}

	ret = ocfs2_xattr_set_entry_index_block(inode, xi, xs, ctxt);

end:

	return ret;
}

/* Check whether the new xattr can be inserted into the inode. */
static int ocfs2_xattr_can_be_in_inode(struct inode *inode,
				       struct ocfs2_xattr_info *xi,
				       struct ocfs2_xattr_search *xs)
{
	u64 value_size;
	struct ocfs2_xattr_entry *last;
	int free, i;
	size_t min_offs = xs->end - xs->base;

	if (!xs->header)
		return 0;

	last = xs->header->xh_entries;

	for (i = 0; i < le16_to_cpu(xs->header->xh_count); i++) {
		size_t offs = le16_to_cpu(last->xe_name_offset);
		if (offs < min_offs)
			min_offs = offs;
		last += 1;
	}

	free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
	if (free < 0)
		return 0;

	BUG_ON(!xs->not_found);

	if (xi->value_len > OCFS2_XATTR_INLINE_SIZE)
		value_size = OCFS2_XATTR_ROOT_SIZE;
	else
		value_size = OCFS2_XATTR_SIZE(xi->value_len);

	if (free >= sizeof(struct ocfs2_xattr_entry) +
		   OCFS2_XATTR_SIZE(strlen(xi->name)) + value_size)
		return 1;

	return 0;
}

static int ocfs2_calc_xattr_set_need(struct inode *inode,
				     struct ocfs2_dinode *di,
				     struct ocfs2_xattr_info *xi,
				     struct ocfs2_xattr_search *xis,
				     struct ocfs2_xattr_search *xbs,
				     int *clusters_need,
				     int *meta_need,
				     int *credits_need)
{
	int ret = 0, old_in_xb = 0;
	int clusters_add = 0, meta_add = 0, credits = 0;
	struct buffer_head *bh = NULL;
	struct ocfs2_xattr_block *xb = NULL;
	struct ocfs2_xattr_entry *xe = NULL;
	struct ocfs2_xattr_value_root *xv = NULL;
	char *base = NULL;
	int name_offset, name_len = 0;
	u32 new_clusters = ocfs2_clusters_for_bytes(inode->i_sb,
						    xi->value_len);
	u64 value_size;

	if (xis->not_found && xbs->not_found) {
		credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);

		if (xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
			clusters_add += new_clusters;
			credits += ocfs2_calc_extend_credits(inode->i_sb,
							&def_xv.xv.xr_list,
							new_clusters);
		}

		goto meta_guess;
	}

	if (!xis->not_found) {
		xe = xis->here;
		name_offset = le16_to_cpu(xe->xe_name_offset);
		name_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
		base = xis->base;
		credits += OCFS2_INODE_UPDATE_CREDITS;
	} else {
		int i, block_off = 0;
		xb = (struct ocfs2_xattr_block *)xbs->xattr_bh->b_data;
		xe = xbs->here;
		name_offset = le16_to_cpu(xe->xe_name_offset);
		name_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
		i = xbs->here - xbs->header->xh_entries;
		old_in_xb = 1;

		if (le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED) {
			ret = ocfs2_xattr_bucket_get_name_value(inode,
							bucket_xh(xbs->bucket),
							i, &block_off,
							&name_offset);
			base = bucket_block(xbs->bucket, block_off);
			credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
		} else {
			base = xbs->base;
			credits += OCFS2_XATTR_BLOCK_UPDATE_CREDITS;
		}
	}

	/*
	 * delete a xattr doesn't need metadata and cluster allocation.
	 * so just calculate the credits and return.
	 *
	 * The credits for removing the value tree will be extended
	 * by ocfs2_remove_extent itself.
	 */
	if (!xi->value) {
		if (!ocfs2_xattr_is_local(xe))
			credits += ocfs2_remove_extent_credits(inode->i_sb);

		goto out;
	}

	/* do cluster allocation guess first. */
	value_size = le64_to_cpu(xe->xe_value_size);

	if (old_in_xb) {
		/*
		 * In xattr set, we always try to set the xe in inode first,
		 * so if it can be inserted into inode successfully, the old
		 * one will be removed from the xattr block, and this xattr
		 * will be inserted into inode as a new xattr in inode.
		 */
		if (ocfs2_xattr_can_be_in_inode(inode, xi, xis)) {
			clusters_add += new_clusters;
			credits += ocfs2_remove_extent_credits(inode->i_sb) +
				    OCFS2_INODE_UPDATE_CREDITS;
			if (!ocfs2_xattr_is_local(xe))
				credits += ocfs2_calc_extend_credits(
							inode->i_sb,
							&def_xv.xv.xr_list,
							new_clusters);
			goto out;
		}
	}

	if (xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
		/* the new values will be stored outside. */
		u32 old_clusters = 0;

		if (!ocfs2_xattr_is_local(xe)) {
			old_clusters =	ocfs2_clusters_for_bytes(inode->i_sb,
								 value_size);
			xv = (struct ocfs2_xattr_value_root *)
			     (base + name_offset + name_len);
			value_size = OCFS2_XATTR_ROOT_SIZE;
		} else
			xv = &def_xv.xv;

		if (old_clusters >= new_clusters) {
			credits += ocfs2_remove_extent_credits(inode->i_sb);
			goto out;
		} else {
			meta_add += ocfs2_extend_meta_needed(&xv->xr_list);
			clusters_add += new_clusters - old_clusters;
			credits += ocfs2_calc_extend_credits(inode->i_sb,
							     &xv->xr_list,
							     new_clusters -
							     old_clusters);
			if (value_size >= OCFS2_XATTR_ROOT_SIZE)
				goto out;
		}
	} else {
		/*
		 * Now the new value will be stored inside. So if the new
		 * value is smaller than the size of value root or the old
		 * value, we don't need any allocation, otherwise we have
		 * to guess metadata allocation.
		 */
		if ((ocfs2_xattr_is_local(xe) && value_size >= xi->value_len) ||
		    (!ocfs2_xattr_is_local(xe) &&
		     OCFS2_XATTR_ROOT_SIZE >= xi->value_len))
			goto out;
	}

meta_guess:
	/* calculate metadata allocation. */
	if (di->i_xattr_loc) {
		if (!xbs->xattr_bh) {
			ret = ocfs2_read_xattr_block(inode,
						     le64_to_cpu(di->i_xattr_loc),
						     &bh);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			xb = (struct ocfs2_xattr_block *)bh->b_data;
		} else
			xb = (struct ocfs2_xattr_block *)xbs->xattr_bh->b_data;

		if (le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED) {
			struct ocfs2_extent_list *el =
				 &xb->xb_attrs.xb_root.xt_list;
			meta_add += ocfs2_extend_meta_needed(el);
			credits += ocfs2_calc_extend_credits(inode->i_sb,
							     el, 1);
		}

		/*
		 * This cluster will be used either for new bucket or for
		 * new xattr block.
		 * If the cluster size is the same as the bucket size, one
		 * more is needed since we may need to extend the bucket
		 * also.
		 */
		clusters_add += 1;
		credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
		if (OCFS2_XATTR_BUCKET_SIZE ==
			OCFS2_SB(inode->i_sb)->s_clustersize) {
			credits += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
			clusters_add += 1;
		}
	} else {
		meta_add += 1;
		credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
	}
out:
	if (clusters_need)
		*clusters_need = clusters_add;
	if (meta_need)
		*meta_need = meta_add;
	if (credits_need)
		*credits_need = credits;
	brelse(bh);
	return ret;
}

static int ocfs2_init_xattr_set_ctxt(struct inode *inode,
				     struct ocfs2_dinode *di,
				     struct ocfs2_xattr_info *xi,
				     struct ocfs2_xattr_search *xis,
				     struct ocfs2_xattr_search *xbs,
				     struct ocfs2_xattr_set_ctxt *ctxt,
				     int *credits)
{
	int clusters_add, meta_add, ret;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	memset(ctxt, 0, sizeof(struct ocfs2_xattr_set_ctxt));

	ocfs2_init_dealloc_ctxt(&ctxt->dealloc);

	ret = ocfs2_calc_xattr_set_need(inode, di, xi, xis, xbs,
					&clusters_add, &meta_add, credits);
	if (ret) {
		mlog_errno(ret);
		return ret;
	}

	mlog(0, "Set xattr %s, reserve meta blocks = %d, clusters = %d, "
	     "credits = %d\n", xi->name, meta_add, clusters_add, *credits);

	if (meta_add) {
		ret = ocfs2_reserve_new_metadata_blocks(osb, meta_add,
							&ctxt->meta_ac);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	if (clusters_add) {
		ret = ocfs2_reserve_clusters(osb, clusters_add, &ctxt->data_ac);
		if (ret)
			mlog_errno(ret);
	}
out:
	if (ret) {
		if (ctxt->meta_ac) {
			ocfs2_free_alloc_context(ctxt->meta_ac);
			ctxt->meta_ac = NULL;
		}

		/*
		 * We cannot have an error and a non null ctxt->data_ac.
		 */
	}

	return ret;
}

static int __ocfs2_xattr_set_handle(struct inode *inode,
				    struct ocfs2_dinode *di,
				    struct ocfs2_xattr_info *xi,
				    struct ocfs2_xattr_search *xis,
				    struct ocfs2_xattr_search *xbs,
				    struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret = 0, credits, old_found;

	if (!xi->value) {
		/* Remove existing extended attribute */
		if (!xis->not_found)
			ret = ocfs2_xattr_ibody_set(inode, xi, xis, ctxt);
		else if (!xbs->not_found)
			ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
	} else {
		/* We always try to set extended attribute into inode first*/
		ret = ocfs2_xattr_ibody_set(inode, xi, xis, ctxt);
		if (!ret && !xbs->not_found) {
			/*
			 * If succeed and that extended attribute existing in
			 * external block, then we will remove it.
			 */
			xi->value = NULL;
			xi->value_len = 0;

			old_found = xis->not_found;
			xis->not_found = -ENODATA;
			ret = ocfs2_calc_xattr_set_need(inode,
							di,
							xi,
							xis,
							xbs,
							NULL,
							NULL,
							&credits);
			xis->not_found = old_found;
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			ret = ocfs2_extend_trans(ctxt->handle, credits +
					ctxt->handle->h_buffer_credits);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}
			ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
		} else if (ret == -ENOSPC) {
			if (di->i_xattr_loc && !xbs->xattr_bh) {
				ret = ocfs2_xattr_block_find(inode,
							     xi->name_index,
							     xi->name, xbs);
				if (ret)
					goto out;

				old_found = xis->not_found;
				xis->not_found = -ENODATA;
				ret = ocfs2_calc_xattr_set_need(inode,
								di,
								xi,
								xis,
								xbs,
								NULL,
								NULL,
								&credits);
				xis->not_found = old_found;
				if (ret) {
					mlog_errno(ret);
					goto out;
				}

				ret = ocfs2_extend_trans(ctxt->handle, credits +
					ctxt->handle->h_buffer_credits);
				if (ret) {
					mlog_errno(ret);
					goto out;
				}
			}
			/*
			 * If no space in inode, we will set extended attribute
			 * into external block.
			 */
			ret = ocfs2_xattr_block_set(inode, xi, xbs, ctxt);
			if (ret)
				goto out;
			if (!xis->not_found) {
				/*
				 * If succeed and that extended attribute
				 * existing in inode, we will remove it.
				 */
				xi->value = NULL;
				xi->value_len = 0;
				xbs->not_found = -ENODATA;
				ret = ocfs2_calc_xattr_set_need(inode,
								di,
								xi,
								xis,
								xbs,
								NULL,
								NULL,
								&credits);
				if (ret) {
					mlog_errno(ret);
					goto out;
				}

				ret = ocfs2_extend_trans(ctxt->handle, credits +
						ctxt->handle->h_buffer_credits);
				if (ret) {
					mlog_errno(ret);
					goto out;
				}
				ret = ocfs2_xattr_ibody_set(inode, xi,
							    xis, ctxt);
			}
		}
	}

out:
	return ret;
}

/*
 * This function only called duing creating inode
 * for init security/acl xattrs of the new inode.
 * The xattrs could be put into ibody or extent block,
 * xattr bucket would not be use in this case.
 * transanction credits also be reserved in here.
 */
int ocfs2_xattr_set_handle(handle_t *handle,
			   struct inode *inode,
			   struct buffer_head *di_bh,
			   int name_index,
			   const char *name,
			   const void *value,
			   size_t value_len,
			   int flags,
			   struct ocfs2_alloc_context *meta_ac,
			   struct ocfs2_alloc_context *data_ac)
{
	struct ocfs2_dinode *di;
	int ret;

	struct ocfs2_xattr_info xi = {
		.name_index = name_index,
		.name = name,
		.value = value,
		.value_len = value_len,
	};

	struct ocfs2_xattr_search xis = {
		.not_found = -ENODATA,
	};

	struct ocfs2_xattr_search xbs = {
		.not_found = -ENODATA,
	};

	struct ocfs2_xattr_set_ctxt ctxt = {
		.handle = handle,
		.meta_ac = meta_ac,
		.data_ac = data_ac,
	};

	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
		return -EOPNOTSUPP;

	xis.inode_bh = xbs.inode_bh = di_bh;
	di = (struct ocfs2_dinode *)di_bh->b_data;

	down_write(&OCFS2_I(inode)->ip_xattr_sem);

	ret = ocfs2_xattr_ibody_find(inode, name_index, name, &xis);
	if (ret)
		goto cleanup;
	if (xis.not_found) {
		ret = ocfs2_xattr_block_find(inode, name_index, name, &xbs);
		if (ret)
			goto cleanup;
	}

	ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);

cleanup:
	up_write(&OCFS2_I(inode)->ip_xattr_sem);
	brelse(xbs.xattr_bh);

	return ret;
}

/*
 * ocfs2_xattr_set()
 *
 * Set, replace or remove an extended attribute for this inode.
 * value is NULL to remove an existing extended attribute, else either
 * create or replace an extended attribute.
 */
int ocfs2_xattr_set(struct inode *inode,
		    int name_index,
		    const char *name,
		    const void *value,
		    size_t value_len,
		    int flags)
{
	struct buffer_head *di_bh = NULL;
	struct ocfs2_dinode *di;
	int ret, credits;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct inode *tl_inode = osb->osb_tl_inode;
	struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, };

	struct ocfs2_xattr_info xi = {
		.name_index = name_index,
		.name = name,
		.value = value,
		.value_len = value_len,
	};

	struct ocfs2_xattr_search xis = {
		.not_found = -ENODATA,
	};

	struct ocfs2_xattr_search xbs = {
		.not_found = -ENODATA,
	};

	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
		return -EOPNOTSUPP;

	/*
	 * Only xbs will be used on indexed trees.  xis doesn't need a
	 * bucket.
	 */
	xbs.bucket = ocfs2_xattr_bucket_new(inode);
	if (!xbs.bucket) {
		mlog_errno(-ENOMEM);
		return -ENOMEM;
	}

	ret = ocfs2_inode_lock(inode, &di_bh, 1);
	if (ret < 0) {
		mlog_errno(ret);
		goto cleanup_nolock;
	}
	xis.inode_bh = xbs.inode_bh = di_bh;
	di = (struct ocfs2_dinode *)di_bh->b_data;

	down_write(&OCFS2_I(inode)->ip_xattr_sem);
	/*
	 * Scan inode and external block to find the same name
	 * extended attribute and collect search infomation.
	 */
	ret = ocfs2_xattr_ibody_find(inode, name_index, name, &xis);
	if (ret)
		goto cleanup;
	if (xis.not_found) {
		ret = ocfs2_xattr_block_find(inode, name_index, name, &xbs);
		if (ret)
			goto cleanup;
	}

	if (xis.not_found && xbs.not_found) {
		ret = -ENODATA;
		if (flags & XATTR_REPLACE)
			goto cleanup;
		ret = 0;
		if (!value)
			goto cleanup;
	} else {
		ret = -EEXIST;
		if (flags & XATTR_CREATE)
			goto cleanup;
	}


	mutex_lock(&tl_inode->i_mutex);

	if (ocfs2_truncate_log_needs_flush(osb)) {
		ret = __ocfs2_flush_truncate_log(osb);
		if (ret < 0) {
			mutex_unlock(&tl_inode->i_mutex);
			mlog_errno(ret);
			goto cleanup;
		}
	}
	mutex_unlock(&tl_inode->i_mutex);

	ret = ocfs2_init_xattr_set_ctxt(inode, di, &xi, &xis,
					&xbs, &ctxt, &credits);
	if (ret) {
		mlog_errno(ret);
		goto cleanup;
	}

	ctxt.handle = ocfs2_start_trans(osb, credits);
	if (IS_ERR(ctxt.handle)) {
		ret = PTR_ERR(ctxt.handle);
		mlog_errno(ret);
		goto cleanup;
	}

	ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);

	ocfs2_commit_trans(osb, ctxt.handle);

	if (ctxt.data_ac)
		ocfs2_free_alloc_context(ctxt.data_ac);
	if (ctxt.meta_ac)
		ocfs2_free_alloc_context(ctxt.meta_ac);
	if (ocfs2_dealloc_has_cluster(&ctxt.dealloc))
		ocfs2_schedule_truncate_log_flush(osb, 1);
	ocfs2_run_deallocs(osb, &ctxt.dealloc);
cleanup:
	up_write(&OCFS2_I(inode)->ip_xattr_sem);
	ocfs2_inode_unlock(inode, 1);
cleanup_nolock:
	brelse(di_bh);
	brelse(xbs.xattr_bh);
	ocfs2_xattr_bucket_free(xbs.bucket);

	return ret;
}

/*
 * Find the xattr extent rec which may contains name_hash.
 * e_cpos will be the first name hash of the xattr rec.
 * el must be the ocfs2_xattr_header.xb_attrs.xb_root.xt_list.
 */
static int ocfs2_xattr_get_rec(struct inode *inode,
			       u32 name_hash,
			       u64 *p_blkno,
			       u32 *e_cpos,
			       u32 *num_clusters,
			       struct ocfs2_extent_list *el)
{
	int ret = 0, i;
	struct buffer_head *eb_bh = NULL;
	struct ocfs2_extent_block *eb;
	struct ocfs2_extent_rec *rec = NULL;
	u64 e_blkno = 0;

	if (el->l_tree_depth) {
		ret = ocfs2_find_leaf(inode, el, name_hash, &eb_bh);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		eb = (struct ocfs2_extent_block *) eb_bh->b_data;
		el = &eb->h_list;

		if (el->l_tree_depth) {
			ocfs2_error(inode->i_sb,
				    "Inode %lu has non zero tree depth in "
				    "xattr tree block %llu\n", inode->i_ino,
				    (unsigned long long)eb_bh->b_blocknr);
			ret = -EROFS;
			goto out;
		}
	}

	for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
		rec = &el->l_recs[i];

		if (le32_to_cpu(rec->e_cpos) <= name_hash) {
			e_blkno = le64_to_cpu(rec->e_blkno);
			break;
		}
	}

	if (!e_blkno) {
		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
			    "record (%u, %u, 0) in xattr", inode->i_ino,
			    le32_to_cpu(rec->e_cpos),
			    ocfs2_rec_clusters(el, rec));
		ret = -EROFS;
		goto out;
	}

	*p_blkno = le64_to_cpu(rec->e_blkno);
	*num_clusters = le16_to_cpu(rec->e_leaf_clusters);
	if (e_cpos)
		*e_cpos = le32_to_cpu(rec->e_cpos);
out:
	brelse(eb_bh);
	return ret;
}

typedef int (xattr_bucket_func)(struct inode *inode,
				struct ocfs2_xattr_bucket *bucket,
				void *para);

static int ocfs2_find_xe_in_bucket(struct inode *inode,
				   struct ocfs2_xattr_bucket *bucket,
				   int name_index,
				   const char *name,
				   u32 name_hash,
				   u16 *xe_index,
				   int *found)
{
	int i, ret = 0, cmp = 1, block_off, new_offset;
	struct ocfs2_xattr_header *xh = bucket_xh(bucket);
	size_t name_len = strlen(name);
	struct ocfs2_xattr_entry *xe = NULL;
	char *xe_name;

	/*
	 * We don't use binary search in the bucket because there
	 * may be multiple entries with the same name hash.
	 */
	for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
		xe = &xh->xh_entries[i];

		if (name_hash > le32_to_cpu(xe->xe_name_hash))
			continue;
		else if (name_hash < le32_to_cpu(xe->xe_name_hash))
			break;

		cmp = name_index - ocfs2_xattr_get_type(xe);
		if (!cmp)
			cmp = name_len - xe->xe_name_len;
		if (cmp)
			continue;

		ret = ocfs2_xattr_bucket_get_name_value(inode,
							xh,
							i,
							&block_off,
							&new_offset);
		if (ret) {
			mlog_errno(ret);
			break;
		}


		xe_name = bucket_block(bucket, block_off) + new_offset;
		if (!memcmp(name, xe_name, name_len)) {
			*xe_index = i;
			*found = 1;
			ret = 0;
			break;
		}
	}

	return ret;
}

/*
 * Find the specified xattr entry in a series of buckets.
 * This series start from p_blkno and last for num_clusters.
 * The ocfs2_xattr_header.xh_num_buckets of the first bucket contains
 * the num of the valid buckets.
 *
 * Return the buffer_head this xattr should reside in. And if the xattr's
 * hash is in the gap of 2 buckets, return the lower bucket.
 */
static int ocfs2_xattr_bucket_find(struct inode *inode,
				   int name_index,
				   const char *name,
				   u32 name_hash,
				   u64 p_blkno,
				   u32 first_hash,
				   u32 num_clusters,
				   struct ocfs2_xattr_search *xs)
{
	int ret, found = 0;
	struct ocfs2_xattr_header *xh = NULL;
	struct ocfs2_xattr_entry *xe = NULL;
	u16 index = 0;
	u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
	int low_bucket = 0, bucket, high_bucket;
	struct ocfs2_xattr_bucket *search;
	u32 last_hash;
	u64 blkno, lower_blkno = 0;

	search = ocfs2_xattr_bucket_new(inode);
	if (!search) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_xattr_bucket(search, p_blkno);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	xh = bucket_xh(search);
	high_bucket = le16_to_cpu(xh->xh_num_buckets) - 1;
	while (low_bucket <= high_bucket) {
		ocfs2_xattr_bucket_relse(search);

		bucket = (low_bucket + high_bucket) / 2;
		blkno = p_blkno + bucket * blk_per_bucket;
		ret = ocfs2_read_xattr_bucket(search, blkno);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		xh = bucket_xh(search);
		xe = &xh->xh_entries[0];
		if (name_hash < le32_to_cpu(xe->xe_name_hash)) {
			high_bucket = bucket - 1;
			continue;
		}

		/*
		 * Check whether the hash of the last entry in our
		 * bucket is larger than the search one. for an empty
		 * bucket, the last one is also the first one.
		 */
		if (xh->xh_count)
			xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1];

		last_hash = le32_to_cpu(xe->xe_name_hash);

		/* record lower_blkno which may be the insert place. */
		lower_blkno = blkno;

		if (name_hash > le32_to_cpu(xe->xe_name_hash)) {
			low_bucket = bucket + 1;
			continue;
		}

		/* the searched xattr should reside in this bucket if exists. */
		ret = ocfs2_find_xe_in_bucket(inode, search,
					      name_index, name, name_hash,
					      &index, &found);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
		break;
	}

	/*
	 * Record the bucket we have found.
	 * When the xattr's hash value is in the gap of 2 buckets, we will
	 * always set it to the previous bucket.
	 */
	if (!lower_blkno)
		lower_blkno = p_blkno;

	/* This should be in cache - we just read it during the search */
	ret = ocfs2_read_xattr_bucket(xs->bucket, lower_blkno);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	xs->header = bucket_xh(xs->bucket);
	xs->base = bucket_block(xs->bucket, 0);
	xs->end = xs->base + inode->i_sb->s_blocksize;

	if (found) {
		xs->here = &xs->header->xh_entries[index];
		mlog(0, "find xattr %s in bucket %llu, entry = %u\n", name,
		     (unsigned long long)bucket_blkno(xs->bucket), index);
	} else
		ret = -ENODATA;

out:
	ocfs2_xattr_bucket_free(search);
	return ret;
}

static int ocfs2_xattr_index_block_find(struct inode *inode,
					struct buffer_head *root_bh,
					int name_index,
					const char *name,
					struct ocfs2_xattr_search *xs)
{
	int ret;
	struct ocfs2_xattr_block *xb =
			(struct ocfs2_xattr_block *)root_bh->b_data;
	struct ocfs2_xattr_tree_root *xb_root = &xb->xb_attrs.xb_root;
	struct ocfs2_extent_list *el = &xb_root->xt_list;
	u64 p_blkno = 0;
	u32 first_hash, num_clusters = 0;
	u32 name_hash = ocfs2_xattr_name_hash(inode, name, strlen(name));

	if (le16_to_cpu(el->l_next_free_rec) == 0)
		return -ENODATA;

	mlog(0, "find xattr %s, hash = %u, index = %d in xattr tree\n",
	     name, name_hash, name_index);

	ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno, &first_hash,
				  &num_clusters, el);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	BUG_ON(p_blkno == 0 || num_clusters == 0 || first_hash > name_hash);

	mlog(0, "find xattr extent rec %u clusters from %llu, the first hash "
	     "in the rec is %u\n", num_clusters, (unsigned long long)p_blkno,
	     first_hash);

	ret = ocfs2_xattr_bucket_find(inode, name_index, name, name_hash,
				      p_blkno, first_hash, num_clusters, xs);

out:
	return ret;
}

static int ocfs2_iterate_xattr_buckets(struct inode *inode,
				       u64 blkno,
				       u32 clusters,
				       xattr_bucket_func *func,
				       void *para)
{
	int i, ret = 0;
	u32 bpc = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb));
	u32 num_buckets = clusters * bpc;
	struct ocfs2_xattr_bucket *bucket;

	bucket = ocfs2_xattr_bucket_new(inode);
	if (!bucket) {
		mlog_errno(-ENOMEM);
		return -ENOMEM;
	}

	mlog(0, "iterating xattr buckets in %u clusters starting from %llu\n",
	     clusters, (unsigned long long)blkno);

	for (i = 0; i < num_buckets; i++, blkno += bucket->bu_blocks) {
		ret = ocfs2_read_xattr_bucket(bucket, blkno);
		if (ret) {
			mlog_errno(ret);
			break;
		}

		/*
		 * The real bucket num in this series of blocks is stored
		 * in the 1st bucket.
		 */
		if (i == 0)
			num_buckets = le16_to_cpu(bucket_xh(bucket)->xh_num_buckets);

		mlog(0, "iterating xattr bucket %llu, first hash %u\n",
		     (unsigned long long)blkno,
		     le32_to_cpu(bucket_xh(bucket)->xh_entries[0].xe_name_hash));
		if (func) {
			ret = func(inode, bucket, para);
			if (ret)
				mlog_errno(ret);
			/* Fall through to bucket_relse() */
		}

		ocfs2_xattr_bucket_relse(bucket);
		if (ret)
			break;
	}

	ocfs2_xattr_bucket_free(bucket);
	return ret;
}

struct ocfs2_xattr_tree_list {
	char *buffer;
	size_t buffer_size;
	size_t result;
};

static int ocfs2_xattr_bucket_get_name_value(struct inode *inode,
					     struct ocfs2_xattr_header *xh,
					     int index,
					     int *block_off,
					     int *new_offset)
{
	u16 name_offset;

	if (index < 0 || index >= le16_to_cpu(xh->xh_count))
		return -EINVAL;

	name_offset = le16_to_cpu(xh->xh_entries[index].xe_name_offset);

	*block_off = name_offset >> inode->i_sb->s_blocksize_bits;
	*new_offset = name_offset % inode->i_sb->s_blocksize;

	return 0;
}

static int ocfs2_list_xattr_bucket(struct inode *inode,
				   struct ocfs2_xattr_bucket *bucket,
				   void *para)
{
	int ret = 0, type;
	struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para;
	int i, block_off, new_offset;
	const char *prefix, *name;

	for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) {
		struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i];
		type = ocfs2_xattr_get_type(entry);
		prefix = ocfs2_xattr_prefix(type);

		if (prefix) {
			ret = ocfs2_xattr_bucket_get_name_value(inode,
								bucket_xh(bucket),
								i,
								&block_off,
								&new_offset);
			if (ret)
				break;

			name = (const char *)bucket_block(bucket, block_off) +
				new_offset;
			ret = ocfs2_xattr_list_entry(xl->buffer,
						     xl->buffer_size,
						     &xl->result,
						     prefix, name,
						     entry->xe_name_len);
			if (ret)
				break;
		}
	}

	return ret;
}

static int ocfs2_xattr_tree_list_index_block(struct inode *inode,
					     struct ocfs2_xattr_tree_root *xt,
					     char *buffer,
					     size_t buffer_size)
{
	struct ocfs2_extent_list *el = &xt->xt_list;
	int ret = 0;
	u32 name_hash = UINT_MAX, e_cpos = 0, num_clusters = 0;
	u64 p_blkno = 0;
	struct ocfs2_xattr_tree_list xl = {
		.buffer = buffer,
		.buffer_size = buffer_size,
		.result = 0,
	};

	if (le16_to_cpu(el->l_next_free_rec) == 0)
		return 0;

	while (name_hash > 0) {
		ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno,
					  &e_cpos, &num_clusters, el);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		ret = ocfs2_iterate_xattr_buckets(inode, p_blkno, num_clusters,
						  ocfs2_list_xattr_bucket,
						  &xl);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		if (e_cpos == 0)
			break;

		name_hash = e_cpos - 1;
	}

	ret = xl.result;
out:
	return ret;
}

static int cmp_xe(const void *a, const void *b)
{
	const struct ocfs2_xattr_entry *l = a, *r = b;
	u32 l_hash = le32_to_cpu(l->xe_name_hash);
	u32 r_hash = le32_to_cpu(r->xe_name_hash);

	if (l_hash > r_hash)
		return 1;
	if (l_hash < r_hash)
		return -1;
	return 0;
}

static void swap_xe(void *a, void *b, int size)
{
	struct ocfs2_xattr_entry *l = a, *r = b, tmp;

	tmp = *l;
	memcpy(l, r, sizeof(struct ocfs2_xattr_entry));
	memcpy(r, &tmp, sizeof(struct ocfs2_xattr_entry));
}

/*
 * When the ocfs2_xattr_block is filled up, new bucket will be created
 * and all the xattr entries will be moved to the new bucket.
 * The header goes at the start of the bucket, and the names+values are
 * filled from the end.  This is why *target starts as the last buffer.
 * Note: we need to sort the entries since they are not saved in order
 * in the ocfs2_xattr_block.
 */
static void ocfs2_cp_xattr_block_to_bucket(struct inode *inode,
					   struct buffer_head *xb_bh,
					   struct ocfs2_xattr_bucket *bucket)
{
	int i, blocksize = inode->i_sb->s_blocksize;
	int blks = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
	u16 offset, size, off_change;
	struct ocfs2_xattr_entry *xe;
	struct ocfs2_xattr_block *xb =
				(struct ocfs2_xattr_block *)xb_bh->b_data;
	struct ocfs2_xattr_header *xb_xh = &xb->xb_attrs.xb_header;
	struct ocfs2_xattr_header *xh = bucket_xh(bucket);
	u16 count = le16_to_cpu(xb_xh->xh_count);
	char *src = xb_bh->b_data;
	char *target = bucket_block(bucket, blks - 1);

	mlog(0, "cp xattr from block %llu to bucket %llu\n",
	     (unsigned long long)xb_bh->b_blocknr,
	     (unsigned long long)bucket_blkno(bucket));

	for (i = 0; i < blks; i++)
		memset(bucket_block(bucket, i), 0, blocksize);

	/*
	 * Since the xe_name_offset is based on ocfs2_xattr_header,
	 * there is a offset change corresponding to the change of
	 * ocfs2_xattr_header's position.
	 */
	off_change = offsetof(struct ocfs2_xattr_block, xb_attrs.xb_header);
	xe = &xb_xh->xh_entries[count - 1];
	offset = le16_to_cpu(xe->xe_name_offset) + off_change;
	size = blocksize - offset;

	/* copy all the names and values. */
	memcpy(target + offset, src + offset, size);

	/* Init new header now. */
	xh->xh_count = xb_xh->xh_count;
	xh->xh_num_buckets = cpu_to_le16(1);
	xh->xh_name_value_len = cpu_to_le16(size);
	xh->xh_free_start = cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE - size);

	/* copy all the entries. */
	target = bucket_block(bucket, 0);
	offset = offsetof(struct ocfs2_xattr_header, xh_entries);
	size = count * sizeof(struct ocfs2_xattr_entry);
	memcpy(target + offset, (char *)xb_xh + offset, size);

	/* Change the xe offset for all the xe because of the move. */
	off_change = OCFS2_XATTR_BUCKET_SIZE - blocksize +
		 offsetof(struct ocfs2_xattr_block, xb_attrs.xb_header);
	for (i = 0; i < count; i++)
		le16_add_cpu(&xh->xh_entries[i].xe_name_offset, off_change);

	mlog(0, "copy entry: start = %u, size = %u, offset_change = %u\n",
	     offset, size, off_change);

	sort(target + offset, count, sizeof(struct ocfs2_xattr_entry),
	     cmp_xe, swap_xe);
}

/*
 * After we move xattr from block to index btree, we have to
 * update ocfs2_xattr_search to the new xe and base.
 *
 * When the entry is in xattr block, xattr_bh indicates the storage place.
 * While if the entry is in index b-tree, "bucket" indicates the
 * real place of the xattr.
 */
static void ocfs2_xattr_update_xattr_search(struct inode *inode,
					    struct ocfs2_xattr_search *xs,
					    struct buffer_head *old_bh)
{
	char *buf = old_bh->b_data;
	struct ocfs2_xattr_block *old_xb = (struct ocfs2_xattr_block *)buf;
	struct ocfs2_xattr_header *old_xh = &old_xb->xb_attrs.xb_header;
	int i;

	xs->header = bucket_xh(xs->bucket);
	xs->base = bucket_block(xs->bucket, 0);
	xs->end = xs->base + inode->i_sb->s_blocksize;

	if (xs->not_found)
		return;

	i = xs->here - old_xh->xh_entries;
	xs->here = &xs->header->xh_entries[i];
}

static int ocfs2_xattr_create_index_block(struct inode *inode,
					  struct ocfs2_xattr_search *xs,
					  struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret;
	u32 bit_off, len;
	u64 blkno;
	handle_t *handle = ctxt->handle;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct buffer_head *xb_bh = xs->xattr_bh;
	struct ocfs2_xattr_block *xb =
			(struct ocfs2_xattr_block *)xb_bh->b_data;
	struct ocfs2_xattr_tree_root *xr;
	u16 xb_flags = le16_to_cpu(xb->xb_flags);

	mlog(0, "create xattr index block for %llu\n",
	     (unsigned long long)xb_bh->b_blocknr);

	BUG_ON(xb_flags & OCFS2_XATTR_INDEXED);
	BUG_ON(!xs->bucket);

	/*
	 * XXX:
	 * We can use this lock for now, and maybe move to a dedicated mutex
	 * if performance becomes a problem later.
	 */
	down_write(&oi->ip_alloc_sem);

	ret = ocfs2_journal_access(handle, inode, xb_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = __ocfs2_claim_clusters(osb, handle, ctxt->data_ac,
				     1, 1, &bit_off, &len);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * The bucket may spread in many blocks, and
	 * we will only touch the 1st block and the last block
	 * in the whole bucket(one for entry and one for data).
	 */
	blkno = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);

	mlog(0, "allocate 1 cluster from %llu to xattr block\n",
	     (unsigned long long)blkno);

	ret = ocfs2_init_xattr_bucket(xs->bucket, blkno);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_bucket_journal_access(handle, xs->bucket,
						OCFS2_JOURNAL_ACCESS_CREATE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ocfs2_cp_xattr_block_to_bucket(inode, xb_bh, xs->bucket);
	ocfs2_xattr_bucket_journal_dirty(handle, xs->bucket);

	ocfs2_xattr_update_xattr_search(inode, xs, xb_bh);

	/* Change from ocfs2_xattr_header to ocfs2_xattr_tree_root */
	memset(&xb->xb_attrs, 0, inode->i_sb->s_blocksize -
	       offsetof(struct ocfs2_xattr_block, xb_attrs));

	xr = &xb->xb_attrs.xb_root;
	xr->xt_clusters = cpu_to_le32(1);
	xr->xt_last_eb_blk = 0;
	xr->xt_list.l_tree_depth = 0;
	xr->xt_list.l_count = cpu_to_le16(ocfs2_xattr_recs_per_xb(inode->i_sb));
	xr->xt_list.l_next_free_rec = cpu_to_le16(1);

	xr->xt_list.l_recs[0].e_cpos = 0;
	xr->xt_list.l_recs[0].e_blkno = cpu_to_le64(blkno);
	xr->xt_list.l_recs[0].e_leaf_clusters = cpu_to_le16(1);

	xb->xb_flags = cpu_to_le16(xb_flags | OCFS2_XATTR_INDEXED);

	ocfs2_journal_dirty(handle, xb_bh);

out:
	up_write(&oi->ip_alloc_sem);

	return ret;
}

static int cmp_xe_offset(const void *a, const void *b)
{
	const struct ocfs2_xattr_entry *l = a, *r = b;
	u32 l_name_offset = le16_to_cpu(l->xe_name_offset);
	u32 r_name_offset = le16_to_cpu(r->xe_name_offset);

	if (l_name_offset < r_name_offset)
		return 1;
	if (l_name_offset > r_name_offset)
		return -1;
	return 0;
}

/*
 * defrag a xattr bucket if we find that the bucket has some
 * holes beteen name/value pairs.
 * We will move all the name/value pairs to the end of the bucket
 * so that we can spare some space for insertion.
 */
static int ocfs2_defrag_xattr_bucket(struct inode *inode,
				     handle_t *handle,
				     struct ocfs2_xattr_bucket *bucket)
{
	int ret, i;
	size_t end, offset, len, value_len;
	struct ocfs2_xattr_header *xh;
	char *entries, *buf, *bucket_buf = NULL;
	u64 blkno = bucket_blkno(bucket);
	u16 xh_free_start;
	size_t blocksize = inode->i_sb->s_blocksize;
	struct ocfs2_xattr_entry *xe;

	/*
	 * In order to make the operation more efficient and generic,
	 * we copy all the blocks into a contiguous memory and do the
	 * defragment there, so if anything is error, we will not touch
	 * the real block.
	 */
	bucket_buf = kmalloc(OCFS2_XATTR_BUCKET_SIZE, GFP_NOFS);
	if (!bucket_buf) {
		ret = -EIO;
		goto out;
	}

	buf = bucket_buf;
	for (i = 0; i < bucket->bu_blocks; i++, buf += blocksize)
		memcpy(buf, bucket_block(bucket, i), blocksize);

	ret = ocfs2_xattr_bucket_journal_access(handle, bucket,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	xh = (struct ocfs2_xattr_header *)bucket_buf;
	entries = (char *)xh->xh_entries;
	xh_free_start = le16_to_cpu(xh->xh_free_start);

	mlog(0, "adjust xattr bucket in %llu, count = %u, "
	     "xh_free_start = %u, xh_name_value_len = %u.\n",
	     (unsigned long long)blkno, le16_to_cpu(xh->xh_count),
	     xh_free_start, le16_to_cpu(xh->xh_name_value_len));

	/*
	 * sort all the entries by their offset.
	 * the largest will be the first, so that we can
	 * move them to the end one by one.
	 */
	sort(entries, le16_to_cpu(xh->xh_count),
	     sizeof(struct ocfs2_xattr_entry),
	     cmp_xe_offset, swap_xe);

	/* Move all name/values to the end of the bucket. */
	xe = xh->xh_entries;
	end = OCFS2_XATTR_BUCKET_SIZE;
	for (i = 0; i < le16_to_cpu(xh->xh_count); i++, xe++) {
		offset = le16_to_cpu(xe->xe_name_offset);
		if (ocfs2_xattr_is_local(xe))
			value_len = OCFS2_XATTR_SIZE(
					le64_to_cpu(xe->xe_value_size));
		else
			value_len = OCFS2_XATTR_ROOT_SIZE;
		len = OCFS2_XATTR_SIZE(xe->xe_name_len) + value_len;

		/*
		 * We must make sure that the name/value pair
		 * exist in the same block. So adjust end to
		 * the previous block end if needed.
		 */
		if (((end - len) / blocksize !=
			(end - 1) / blocksize))
			end = end - end % blocksize;

		if (end > offset + len) {
			memmove(bucket_buf + end - len,
				bucket_buf + offset, len);
			xe->xe_name_offset = cpu_to_le16(end - len);
		}

		mlog_bug_on_msg(end < offset + len, "Defrag check failed for "
				"bucket %llu\n", (unsigned long long)blkno);

		end -= len;
	}

	mlog_bug_on_msg(xh_free_start > end, "Defrag check failed for "
			"bucket %llu\n", (unsigned long long)blkno);

	if (xh_free_start == end)
		goto out;

	memset(bucket_buf + xh_free_start, 0, end - xh_free_start);
	xh->xh_free_start = cpu_to_le16(end);

	/* sort the entries by their name_hash. */
	sort(entries, le16_to_cpu(xh->xh_count),
	     sizeof(struct ocfs2_xattr_entry),
	     cmp_xe, swap_xe);

	buf = bucket_buf;
	for (i = 0; i < bucket->bu_blocks; i++, buf += blocksize)
		memcpy(bucket_block(bucket, i), buf, blocksize);
	ocfs2_xattr_bucket_journal_dirty(handle, bucket);

out:
	kfree(bucket_buf);
	return ret;
}

/*
 * prev_blkno points to the start of an existing extent.  new_blkno
 * points to a newly allocated extent.  Because we know each of our
 * clusters contains more than bucket, we can easily split one cluster
 * at a bucket boundary.  So we take the last cluster of the existing
 * extent and split it down the middle.  We move the last half of the
 * buckets in the last cluster of the existing extent over to the new
 * extent.
 *
 * first_bh is the buffer at prev_blkno so we can update the existing
 * extent's bucket count.  header_bh is the bucket were we were hoping
 * to insert our xattr.  If the bucket move places the target in the new
 * extent, we'll update first_bh and header_bh after modifying the old
 * extent.
 *
 * first_hash will be set as the 1st xe's name_hash in the new extent.
 */
static int ocfs2_mv_xattr_bucket_cross_cluster(struct inode *inode,
					       handle_t *handle,
					       struct ocfs2_xattr_bucket *first,
					       struct ocfs2_xattr_bucket *target,
					       u64 new_blkno,
					       u32 num_clusters,
					       u32 *first_hash)
{
	int ret;
	struct super_block *sb = inode->i_sb;
	int blks_per_bucket = ocfs2_blocks_per_xattr_bucket(sb);
	int num_buckets = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(sb));
	int to_move = num_buckets / 2;
	u64 src_blkno;
	u64 last_cluster_blkno = bucket_blkno(first) +
		((num_clusters - 1) * ocfs2_clusters_to_blocks(sb, 1));

	BUG_ON(le16_to_cpu(bucket_xh(first)->xh_num_buckets) < num_buckets);
	BUG_ON(OCFS2_XATTR_BUCKET_SIZE == OCFS2_SB(sb)->s_clustersize);

	mlog(0, "move half of xattrs in cluster %llu to %llu\n",
	     (unsigned long long)last_cluster_blkno, (unsigned long long)new_blkno);

	ret = ocfs2_mv_xattr_buckets(inode, handle, bucket_blkno(first),
				     last_cluster_blkno, new_blkno,
				     to_move, first_hash);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/* This is the first bucket that got moved */
	src_blkno = last_cluster_blkno + (to_move * blks_per_bucket);

	/*
	 * If the target bucket was part of the moved buckets, we need to
	 * update first and target.
	 */
	if (bucket_blkno(target) >= src_blkno) {
		/* Find the block for the new target bucket */
		src_blkno = new_blkno +
			(bucket_blkno(target) - src_blkno);

		ocfs2_xattr_bucket_relse(first);
		ocfs2_xattr_bucket_relse(target);

		/*
		 * These shouldn't fail - the buffers are in the
		 * journal from ocfs2_cp_xattr_bucket().
		 */
		ret = ocfs2_read_xattr_bucket(first, new_blkno);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
		ret = ocfs2_read_xattr_bucket(target, src_blkno);
		if (ret)
			mlog_errno(ret);

	}

out:
	return ret;
}

/*
 * Find the suitable pos when we divide a bucket into 2.
 * We have to make sure the xattrs with the same hash value exist
 * in the same bucket.
 *
 * If this ocfs2_xattr_header covers more than one hash value, find a
 * place where the hash value changes.  Try to find the most even split.
 * The most common case is that all entries have different hash values,
 * and the first check we make will find a place to split.
 */
static int ocfs2_xattr_find_divide_pos(struct ocfs2_xattr_header *xh)
{
	struct ocfs2_xattr_entry *entries = xh->xh_entries;
	int count = le16_to_cpu(xh->xh_count);
	int delta, middle = count / 2;

	/*
	 * We start at the middle.  Each step gets farther away in both
	 * directions.  We therefore hit the change in hash value
	 * nearest to the middle.  Note that this loop does not execute for
	 * count < 2.
	 */
	for (delta = 0; delta < middle; delta++) {
		/* Let's check delta earlier than middle */
		if (cmp_xe(&entries[middle - delta - 1],
			   &entries[middle - delta]))
			return middle - delta;

		/* For even counts, don't walk off the end */
		if ((middle + delta + 1) == count)
			continue;

		/* Now try delta past middle */
		if (cmp_xe(&entries[middle + delta],
			   &entries[middle + delta + 1]))
			return middle + delta + 1;
	}

	/* Every entry had the same hash */
	return count;
}

/*
 * Move some xattrs in old bucket(blk) to new bucket(new_blk).
 * first_hash will record the 1st hash of the new bucket.
 *
 * Normally half of the xattrs will be moved.  But we have to make
 * sure that the xattrs with the same hash value are stored in the
 * same bucket. If all the xattrs in this bucket have the same hash
 * value, the new bucket will be initialized as an empty one and the
 * first_hash will be initialized as (hash_value+1).
 */
static int ocfs2_divide_xattr_bucket(struct inode *inode,
				    handle_t *handle,
				    u64 blk,
				    u64 new_blk,
				    u32 *first_hash,
				    int new_bucket_head)
{
	int ret, i;
	int count, start, len, name_value_len = 0, xe_len, name_offset = 0;
	struct ocfs2_xattr_bucket *s_bucket = NULL, *t_bucket = NULL;
	struct ocfs2_xattr_header *xh;
	struct ocfs2_xattr_entry *xe;
	int blocksize = inode->i_sb->s_blocksize;

	mlog(0, "move some of xattrs from bucket %llu to %llu\n",
	     (unsigned long long)blk, (unsigned long long)new_blk);

	s_bucket = ocfs2_xattr_bucket_new(inode);
	t_bucket = ocfs2_xattr_bucket_new(inode);
	if (!s_bucket || !t_bucket) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_xattr_bucket(s_bucket, blk);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_bucket_journal_access(handle, s_bucket,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * Even if !new_bucket_head, we're overwriting t_bucket.  Thus,
	 * there's no need to read it.
	 */
	ret = ocfs2_init_xattr_bucket(t_bucket, new_blk);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * Hey, if we're overwriting t_bucket, what difference does
	 * ACCESS_CREATE vs ACCESS_WRITE make?  See the comment in the
	 * same part of ocfs2_cp_xattr_bucket().
	 */
	ret = ocfs2_xattr_bucket_journal_access(handle, t_bucket,
						new_bucket_head ?
						OCFS2_JOURNAL_ACCESS_CREATE :
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	xh = bucket_xh(s_bucket);
	count = le16_to_cpu(xh->xh_count);
	start = ocfs2_xattr_find_divide_pos(xh);

	if (start == count) {
		xe = &xh->xh_entries[start-1];

		/*
		 * initialized a new empty bucket here.
		 * The hash value is set as one larger than
		 * that of the last entry in the previous bucket.
		 */
		for (i = 0; i < t_bucket->bu_blocks; i++)
			memset(bucket_block(t_bucket, i), 0, blocksize);

		xh = bucket_xh(t_bucket);
		xh->xh_free_start = cpu_to_le16(blocksize);
		xh->xh_entries[0].xe_name_hash = xe->xe_name_hash;
		le32_add_cpu(&xh->xh_entries[0].xe_name_hash, 1);

		goto set_num_buckets;
	}

	/* copy the whole bucket to the new first. */
	ocfs2_xattr_bucket_copy_data(t_bucket, s_bucket);

	/* update the new bucket. */
	xh = bucket_xh(t_bucket);

	/*
	 * Calculate the total name/value len and xh_free_start for
	 * the old bucket first.
	 */
	name_offset = OCFS2_XATTR_BUCKET_SIZE;
	name_value_len = 0;
	for (i = 0; i < start; i++) {
		xe = &xh->xh_entries[i];
		xe_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
		if (ocfs2_xattr_is_local(xe))
			xe_len +=
			   OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
		else
			xe_len += OCFS2_XATTR_ROOT_SIZE;
		name_value_len += xe_len;
		if (le16_to_cpu(xe->xe_name_offset) < name_offset)
			name_offset = le16_to_cpu(xe->xe_name_offset);
	}

	/*
	 * Now begin the modification to the new bucket.
	 *
	 * In the new bucket, We just move the xattr entry to the beginning
	 * and don't touch the name/value. So there will be some holes in the
	 * bucket, and they will be removed when ocfs2_defrag_xattr_bucket is
	 * called.
	 */
	xe = &xh->xh_entries[start];
	len = sizeof(struct ocfs2_xattr_entry) * (count - start);
	mlog(0, "mv xattr entry len %d from %d to %d\n", len,
	     (int)((char *)xe - (char *)xh),
	     (int)((char *)xh->xh_entries - (char *)xh));
	memmove((char *)xh->xh_entries, (char *)xe, len);
	xe = &xh->xh_entries[count - start];
	len = sizeof(struct ocfs2_xattr_entry) * start;
	memset((char *)xe, 0, len);

	le16_add_cpu(&xh->xh_count, -start);
	le16_add_cpu(&xh->xh_name_value_len, -name_value_len);

	/* Calculate xh_free_start for the new bucket. */
	xh->xh_free_start = cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE);
	for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
		xe = &xh->xh_entries[i];
		xe_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
		if (ocfs2_xattr_is_local(xe))
			xe_len +=
			   OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
		else
			xe_len += OCFS2_XATTR_ROOT_SIZE;
		if (le16_to_cpu(xe->xe_name_offset) <
		    le16_to_cpu(xh->xh_free_start))
			xh->xh_free_start = xe->xe_name_offset;
	}

set_num_buckets:
	/* set xh->xh_num_buckets for the new xh. */
	if (new_bucket_head)
		xh->xh_num_buckets = cpu_to_le16(1);
	else
		xh->xh_num_buckets = 0;

	ocfs2_xattr_bucket_journal_dirty(handle, t_bucket);

	/* store the first_hash of the new bucket. */
	if (first_hash)
		*first_hash = le32_to_cpu(xh->xh_entries[0].xe_name_hash);

	/*
	 * Now only update the 1st block of the old bucket.  If we
	 * just added a new empty bucket, there is no need to modify
	 * it.
	 */
	if (start == count)
		goto out;

	xh = bucket_xh(s_bucket);
	memset(&xh->xh_entries[start], 0,
	       sizeof(struct ocfs2_xattr_entry) * (count - start));
	xh->xh_count = cpu_to_le16(start);
	xh->xh_free_start = cpu_to_le16(name_offset);
	xh->xh_name_value_len = cpu_to_le16(name_value_len);

	ocfs2_xattr_bucket_journal_dirty(handle, s_bucket);

out:
	ocfs2_xattr_bucket_free(s_bucket);
	ocfs2_xattr_bucket_free(t_bucket);

	return ret;
}

/*
 * Copy xattr from one bucket to another bucket.
 *
 * The caller must make sure that the journal transaction
 * has enough space for journaling.
 */
static int ocfs2_cp_xattr_bucket(struct inode *inode,
				 handle_t *handle,
				 u64 s_blkno,
				 u64 t_blkno,
				 int t_is_new)
{
	int ret;
	struct ocfs2_xattr_bucket *s_bucket = NULL, *t_bucket = NULL;

	BUG_ON(s_blkno == t_blkno);

	mlog(0, "cp bucket %llu to %llu, target is %d\n",
	     (unsigned long long)s_blkno, (unsigned long long)t_blkno,
	     t_is_new);

	s_bucket = ocfs2_xattr_bucket_new(inode);
	t_bucket = ocfs2_xattr_bucket_new(inode);
	if (!s_bucket || !t_bucket) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_xattr_bucket(s_bucket, s_blkno);
	if (ret)
		goto out;

	/*
	 * Even if !t_is_new, we're overwriting t_bucket.  Thus,
	 * there's no need to read it.
	 */
	ret = ocfs2_init_xattr_bucket(t_bucket, t_blkno);
	if (ret)
		goto out;

	/*
	 * Hey, if we're overwriting t_bucket, what difference does
	 * ACCESS_CREATE vs ACCESS_WRITE make?  Well, if we allocated a new
	 * cluster to fill, we came here from
	 * ocfs2_mv_xattr_buckets(), and it is really new -
	 * ACCESS_CREATE is required.  But we also might have moved data
	 * out of t_bucket before extending back into it.
	 * ocfs2_add_new_xattr_bucket() can do this - its call to
	 * ocfs2_add_new_xattr_cluster() may have created a new extent
	 * and copied out the end of the old extent.  Then it re-extends
	 * the old extent back to create space for new xattrs.  That's
	 * how we get here, and the bucket isn't really new.
	 */
	ret = ocfs2_xattr_bucket_journal_access(handle, t_bucket,
						t_is_new ?
						OCFS2_JOURNAL_ACCESS_CREATE :
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret)
		goto out;

	ocfs2_xattr_bucket_copy_data(t_bucket, s_bucket);
	ocfs2_xattr_bucket_journal_dirty(handle, t_bucket);

out:
	ocfs2_xattr_bucket_free(t_bucket);
	ocfs2_xattr_bucket_free(s_bucket);

	return ret;
}

/*
 * src_blk points to the start of an existing extent.  last_blk points to
 * last cluster in that extent.  to_blk points to a newly allocated
 * extent.  We copy the buckets from the cluster at last_blk to the new
 * extent.  If start_bucket is non-zero, we skip that many buckets before
 * we start copying.  The new extent's xh_num_buckets gets set to the
 * number of buckets we copied.  The old extent's xh_num_buckets shrinks
 * by the same amount.
 */
static int ocfs2_mv_xattr_buckets(struct inode *inode, handle_t *handle,
				  u64 src_blk, u64 last_blk, u64 to_blk,
				  unsigned int start_bucket,
				  u32 *first_hash)
{
	int i, ret, credits;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	int blks_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
	int num_buckets = ocfs2_xattr_buckets_per_cluster(osb);
	struct ocfs2_xattr_bucket *old_first, *new_first;

	mlog(0, "mv xattrs from cluster %llu to %llu\n",
	     (unsigned long long)last_blk, (unsigned long long)to_blk);

	BUG_ON(start_bucket >= num_buckets);
	if (start_bucket) {
		num_buckets -= start_bucket;
		last_blk += (start_bucket * blks_per_bucket);
	}

	/* The first bucket of the original extent */
	old_first = ocfs2_xattr_bucket_new(inode);
	/* The first bucket of the new extent */
	new_first = ocfs2_xattr_bucket_new(inode);
	if (!old_first || !new_first) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_xattr_bucket(old_first, src_blk);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * We need to update the first bucket of the old extent and all
	 * the buckets going to the new extent.
	 */
	credits = ((num_buckets + 1) * blks_per_bucket) +
		handle->h_buffer_credits;
	ret = ocfs2_extend_trans(handle, credits);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_bucket_journal_access(handle, old_first,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	for (i = 0; i < num_buckets; i++) {
		ret = ocfs2_cp_xattr_bucket(inode, handle,
					    last_blk + (i * blks_per_bucket),
					    to_blk + (i * blks_per_bucket),
					    1);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	/*
	 * Get the new bucket ready before we dirty anything
	 * (This actually shouldn't fail, because we already dirtied
	 * it once in ocfs2_cp_xattr_bucket()).
	 */
	ret = ocfs2_read_xattr_bucket(new_first, to_blk);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}
	ret = ocfs2_xattr_bucket_journal_access(handle, new_first,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/* Now update the headers */
	le16_add_cpu(&bucket_xh(old_first)->xh_num_buckets, -num_buckets);
	ocfs2_xattr_bucket_journal_dirty(handle, old_first);

	bucket_xh(new_first)->xh_num_buckets = cpu_to_le16(num_buckets);
	ocfs2_xattr_bucket_journal_dirty(handle, new_first);

	if (first_hash)
		*first_hash = le32_to_cpu(bucket_xh(new_first)->xh_entries[0].xe_name_hash);

out:
	ocfs2_xattr_bucket_free(new_first);
	ocfs2_xattr_bucket_free(old_first);
	return ret;
}

/*
 * Move some xattrs in this cluster to the new cluster.
 * This function should only be called when bucket size == cluster size.
 * Otherwise ocfs2_mv_xattr_bucket_cross_cluster should be used instead.
 */
static int ocfs2_divide_xattr_cluster(struct inode *inode,
				      handle_t *handle,
				      u64 prev_blk,
				      u64 new_blk,
				      u32 *first_hash)
{
	u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
	int ret, credits = 2 * blk_per_bucket + handle->h_buffer_credits;

	BUG_ON(OCFS2_XATTR_BUCKET_SIZE < OCFS2_SB(inode->i_sb)->s_clustersize);

	ret = ocfs2_extend_trans(handle, credits);
	if (ret) {
		mlog_errno(ret);
		return ret;
	}

	/* Move half of the xattr in start_blk to the next bucket. */
	return  ocfs2_divide_xattr_bucket(inode, handle, prev_blk,
					  new_blk, first_hash, 1);
}

/*
 * Move some xattrs from the old cluster to the new one since they are not
 * contiguous in ocfs2 xattr tree.
 *
 * new_blk starts a new separate cluster, and we will move some xattrs from
 * prev_blk to it. v_start will be set as the first name hash value in this
 * new cluster so that it can be used as e_cpos during tree insertion and
 * don't collide with our original b-tree operations. first_bh and header_bh
 * will also be updated since they will be used in ocfs2_extend_xattr_bucket
 * to extend the insert bucket.
 *
 * The problem is how much xattr should we move to the new one and when should
 * we update first_bh and header_bh?
 * 1. If cluster size > bucket size, that means the previous cluster has more
 *    than 1 bucket, so just move half nums of bucket into the new cluster and
 *    update the first_bh and header_bh if the insert bucket has been moved
 *    to the new cluster.
 * 2. If cluster_size == bucket_size:
 *    a) If the previous extent rec has more than one cluster and the insert
 *       place isn't in the last cluster, copy the entire last cluster to the
 *       new one. This time, we don't need to upate the first_bh and header_bh
 *       since they will not be moved into the new cluster.
 *    b) Otherwise, move the bottom half of the xattrs in the last cluster into
 *       the new one. And we set the extend flag to zero if the insert place is
 *       moved into the new allocated cluster since no extend is needed.
 */
static int ocfs2_adjust_xattr_cross_cluster(struct inode *inode,
					    handle_t *handle,
					    struct ocfs2_xattr_bucket *first,
					    struct ocfs2_xattr_bucket *target,
					    u64 new_blk,
					    u32 prev_clusters,
					    u32 *v_start,
					    int *extend)
{
	int ret;

	mlog(0, "adjust xattrs from cluster %llu len %u to %llu\n",
	     (unsigned long long)bucket_blkno(first), prev_clusters,
	     (unsigned long long)new_blk);

	if (ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb)) > 1) {
		ret = ocfs2_mv_xattr_bucket_cross_cluster(inode,
							  handle,
							  first, target,
							  new_blk,
							  prev_clusters,
							  v_start);
		if (ret)
			mlog_errno(ret);
	} else {
		/* The start of the last cluster in the first extent */
		u64 last_blk = bucket_blkno(first) +
			((prev_clusters - 1) *
			 ocfs2_clusters_to_blocks(inode->i_sb, 1));

		if (prev_clusters > 1 && bucket_blkno(target) != last_blk) {
			ret = ocfs2_mv_xattr_buckets(inode, handle,
						     bucket_blkno(first),
						     last_blk, new_blk, 0,
						     v_start);
			if (ret)
				mlog_errno(ret);
		} else {
			ret = ocfs2_divide_xattr_cluster(inode, handle,
							 last_blk, new_blk,
							 v_start);
			if (ret)
				mlog_errno(ret);

			if ((bucket_blkno(target) == last_blk) && extend)
				*extend = 0;
		}
	}

	return ret;
}

/*
 * Add a new cluster for xattr storage.
 *
 * If the new cluster is contiguous with the previous one, it will be
 * appended to the same extent record, and num_clusters will be updated.
 * If not, we will insert a new extent for it and move some xattrs in
 * the last cluster into the new allocated one.
 * We also need to limit the maximum size of a btree leaf, otherwise we'll
 * lose the benefits of hashing because we'll have to search large leaves.
 * So now the maximum size is OCFS2_MAX_XATTR_TREE_LEAF_SIZE(or clustersize,
 * if it's bigger).
 *
 * first_bh is the first block of the previous extent rec and header_bh
 * indicates the bucket we will insert the new xattrs. They will be updated
 * when the header_bh is moved into the new cluster.
 */
static int ocfs2_add_new_xattr_cluster(struct inode *inode,
				       struct buffer_head *root_bh,
				       struct ocfs2_xattr_bucket *first,
				       struct ocfs2_xattr_bucket *target,
				       u32 *num_clusters,
				       u32 prev_cpos,
				       int *extend,
				       struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret;
	u16 bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
	u32 prev_clusters = *num_clusters;
	u32 clusters_to_add = 1, bit_off, num_bits, v_start = 0;
	u64 block;
	handle_t *handle = ctxt->handle;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_extent_tree et;

	mlog(0, "Add new xattr cluster for %llu, previous xattr hash = %u, "
	     "previous xattr blkno = %llu\n",
	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
	     prev_cpos, (unsigned long long)bucket_blkno(first));

	ocfs2_init_xattr_tree_extent_tree(&et, inode, root_bh);

	ret = ocfs2_journal_access(handle, inode, root_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret < 0) {
		mlog_errno(ret);
		goto leave;
	}

	ret = __ocfs2_claim_clusters(osb, handle, ctxt->data_ac, 1,
				     clusters_to_add, &bit_off, &num_bits);
	if (ret < 0) {
		if (ret != -ENOSPC)
			mlog_errno(ret);
		goto leave;
	}

	BUG_ON(num_bits > clusters_to_add);

	block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
	mlog(0, "Allocating %u clusters at block %u for xattr in inode %llu\n",
	     num_bits, bit_off, (unsigned long long)OCFS2_I(inode)->ip_blkno);

	if (bucket_blkno(first) + (prev_clusters * bpc) == block &&
	    (prev_clusters + num_bits) << osb->s_clustersize_bits <=
	     OCFS2_MAX_XATTR_TREE_LEAF_SIZE) {
		/*
		 * If this cluster is contiguous with the old one and
		 * adding this new cluster, we don't surpass the limit of
		 * OCFS2_MAX_XATTR_TREE_LEAF_SIZE, cool. We will let it be
		 * initialized and used like other buckets in the previous
		 * cluster.
		 * So add it as a contiguous one. The caller will handle
		 * its init process.
		 */
		v_start = prev_cpos + prev_clusters;
		*num_clusters = prev_clusters + num_bits;
		mlog(0, "Add contiguous %u clusters to previous extent rec.\n",
		     num_bits);
	} else {
		ret = ocfs2_adjust_xattr_cross_cluster(inode,
						       handle,
						       first,
						       target,
						       block,
						       prev_clusters,
						       &v_start,
						       extend);
		if (ret) {
			mlog_errno(ret);
			goto leave;
		}
	}

	mlog(0, "Insert %u clusters at block %llu for xattr at %u\n",
	     num_bits, (unsigned long long)block, v_start);
	ret = ocfs2_insert_extent(osb, handle, inode, &et, v_start, block,
				  num_bits, 0, ctxt->meta_ac);
	if (ret < 0) {
		mlog_errno(ret);
		goto leave;
	}

	ret = ocfs2_journal_dirty(handle, root_bh);
	if (ret < 0)
		mlog_errno(ret);

leave:
	return ret;
}

/*
 * We are given an extent.  'first' is the bucket at the very front of
 * the extent.  The extent has space for an additional bucket past
 * bucket_xh(first)->xh_num_buckets.  'target_blkno' is the block number
 * of the target bucket.  We wish to shift every bucket past the target
 * down one, filling in that additional space.  When we get back to the
 * target, we split the target between itself and the now-empty bucket
 * at target+1 (aka, target_blkno + blks_per_bucket).
 */
static int ocfs2_extend_xattr_bucket(struct inode *inode,
				     handle_t *handle,
				     struct ocfs2_xattr_bucket *first,
				     u64 target_blk,
				     u32 num_clusters)
{
	int ret, credits;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
	u64 end_blk;
	u16 new_bucket = le16_to_cpu(bucket_xh(first)->xh_num_buckets);

	mlog(0, "extend xattr bucket in %llu, xattr extend rec starting "
	     "from %llu, len = %u\n", (unsigned long long)target_blk,
	     (unsigned long long)bucket_blkno(first), num_clusters);

	/* The extent must have room for an additional bucket */
	BUG_ON(new_bucket >=
	       (num_clusters * ocfs2_xattr_buckets_per_cluster(osb)));

	/* end_blk points to the last existing bucket */
	end_blk = bucket_blkno(first) + ((new_bucket - 1) * blk_per_bucket);

	/*
	 * end_blk is the start of the last existing bucket.
	 * Thus, (end_blk - target_blk) covers the target bucket and
	 * every bucket after it up to, but not including, the last
	 * existing bucket.  Then we add the last existing bucket, the
	 * new bucket, and the first bucket (3 * blk_per_bucket).
	 */
	credits = (end_blk - target_blk) + (3 * blk_per_bucket) +
		  handle->h_buffer_credits;
	ret = ocfs2_extend_trans(handle, credits);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_bucket_journal_access(handle, first,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	while (end_blk != target_blk) {
		ret = ocfs2_cp_xattr_bucket(inode, handle, end_blk,
					    end_blk + blk_per_bucket, 0);
		if (ret)
			goto out;
		end_blk -= blk_per_bucket;
	}

	/* Move half of the xattr in target_blkno to the next bucket. */
	ret = ocfs2_divide_xattr_bucket(inode, handle, target_blk,
					target_blk + blk_per_bucket, NULL, 0);

	le16_add_cpu(&bucket_xh(first)->xh_num_buckets, 1);
	ocfs2_xattr_bucket_journal_dirty(handle, first);

out:
	return ret;
}

/*
 * Add new xattr bucket in an extent record and adjust the buckets
 * accordingly.  xb_bh is the ocfs2_xattr_block, and target is the
 * bucket we want to insert into.
 *
 * In the easy case, we will move all the buckets after target down by
 * one. Half of target's xattrs will be moved to the next bucket.
 *
 * If current cluster is full, we'll allocate a new one.  This may not
 * be contiguous.  The underlying calls will make sure that there is
 * space for the insert, shifting buckets around if necessary.
 * 'target' may be moved by those calls.
 */
static int ocfs2_add_new_xattr_bucket(struct inode *inode,
				      struct buffer_head *xb_bh,
				      struct ocfs2_xattr_bucket *target,
				      struct ocfs2_xattr_set_ctxt *ctxt)
{
	struct ocfs2_xattr_block *xb =
			(struct ocfs2_xattr_block *)xb_bh->b_data;
	struct ocfs2_xattr_tree_root *xb_root = &xb->xb_attrs.xb_root;
	struct ocfs2_extent_list *el = &xb_root->xt_list;
	u32 name_hash =
		le32_to_cpu(bucket_xh(target)->xh_entries[0].xe_name_hash);
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	int ret, num_buckets, extend = 1;
	u64 p_blkno;
	u32 e_cpos, num_clusters;
	/* The bucket at the front of the extent */
	struct ocfs2_xattr_bucket *first;

	mlog(0, "Add new xattr bucket starting from %llu\n",
	     (unsigned long long)bucket_blkno(target));

	/* The first bucket of the original extent */
	first = ocfs2_xattr_bucket_new(inode);
	if (!first) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno, &e_cpos,
				  &num_clusters, el);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_xattr_bucket(first, p_blkno);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	num_buckets = ocfs2_xattr_buckets_per_cluster(osb) * num_clusters;
	if (num_buckets == le16_to_cpu(bucket_xh(first)->xh_num_buckets)) {
		/*
		 * This can move first+target if the target bucket moves
		 * to the new extent.
		 */
		ret = ocfs2_add_new_xattr_cluster(inode,
						  xb_bh,
						  first,
						  target,
						  &num_clusters,
						  e_cpos,
						  &extend,
						  ctxt);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	if (extend) {
		ret = ocfs2_extend_xattr_bucket(inode,
						ctxt->handle,
						first,
						bucket_blkno(target),
						num_clusters);
		if (ret)
			mlog_errno(ret);
	}

out:
	ocfs2_xattr_bucket_free(first);

	return ret;
}

static inline char *ocfs2_xattr_bucket_get_val(struct inode *inode,
					struct ocfs2_xattr_bucket *bucket,
					int offs)
{
	int block_off = offs >> inode->i_sb->s_blocksize_bits;

	offs = offs % inode->i_sb->s_blocksize;
	return bucket_block(bucket, block_off) + offs;
}

/*
 * Handle the normal xattr set, including replace, delete and new.
 *
 * Note: "local" indicates the real data's locality. So we can't
 * just its bucket locality by its length.
 */
static void ocfs2_xattr_set_entry_normal(struct inode *inode,
					 struct ocfs2_xattr_info *xi,
					 struct ocfs2_xattr_search *xs,
					 u32 name_hash,
					 int local)
{
	struct ocfs2_xattr_entry *last, *xe;
	int name_len = strlen(xi->name);
	struct ocfs2_xattr_header *xh = xs->header;
	u16 count = le16_to_cpu(xh->xh_count), start;
	size_t blocksize = inode->i_sb->s_blocksize;
	char *val;
	size_t offs, size, new_size;

	last = &xh->xh_entries[count];
	if (!xs->not_found) {
		xe = xs->here;
		offs = le16_to_cpu(xe->xe_name_offset);
		if (ocfs2_xattr_is_local(xe))
			size = OCFS2_XATTR_SIZE(name_len) +
			OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
		else
			size = OCFS2_XATTR_SIZE(name_len) +
			OCFS2_XATTR_SIZE(OCFS2_XATTR_ROOT_SIZE);

		/*
		 * If the new value will be stored outside, xi->value has been
		 * initalized as an empty ocfs2_xattr_value_root, and the same
		 * goes with xi->value_len, so we can set new_size safely here.
		 * See ocfs2_xattr_set_in_bucket.
		 */
		new_size = OCFS2_XATTR_SIZE(name_len) +
			   OCFS2_XATTR_SIZE(xi->value_len);

		le16_add_cpu(&xh->xh_name_value_len, -size);
		if (xi->value) {
			if (new_size > size)
				goto set_new_name_value;

			/* Now replace the old value with new one. */
			if (local)
				xe->xe_value_size = cpu_to_le64(xi->value_len);
			else
				xe->xe_value_size = 0;

			val = ocfs2_xattr_bucket_get_val(inode,
							 xs->bucket, offs);
			memset(val + OCFS2_XATTR_SIZE(name_len), 0,
			       size - OCFS2_XATTR_SIZE(name_len));
			if (OCFS2_XATTR_SIZE(xi->value_len) > 0)
				memcpy(val + OCFS2_XATTR_SIZE(name_len),
				       xi->value, xi->value_len);

			le16_add_cpu(&xh->xh_name_value_len, new_size);
			ocfs2_xattr_set_local(xe, local);
			return;
		} else {
			/*
			 * Remove the old entry if there is more than one.
			 * We don't remove the last entry so that we can
			 * use it to indicate the hash value of the empty
			 * bucket.
			 */
			last -= 1;
			le16_add_cpu(&xh->xh_count, -1);
			if (xh->xh_count) {
				memmove(xe, xe + 1,
					(void *)last - (void *)xe);
				memset(last, 0,
				       sizeof(struct ocfs2_xattr_entry));
			} else
				xh->xh_free_start =
					cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE);

			return;
		}
	} else {
		/* find a new entry for insert. */
		int low = 0, high = count - 1, tmp;
		struct ocfs2_xattr_entry *tmp_xe;

		while (low <= high && count) {
			tmp = (low + high) / 2;
			tmp_xe = &xh->xh_entries[tmp];

			if (name_hash > le32_to_cpu(tmp_xe->xe_name_hash))
				low = tmp + 1;
			else if (name_hash <
				 le32_to_cpu(tmp_xe->xe_name_hash))
				high = tmp - 1;
			else {
				low = tmp;
				break;
			}
		}

		xe = &xh->xh_entries[low];
		if (low != count)
			memmove(xe + 1, xe, (void *)last - (void *)xe);

		le16_add_cpu(&xh->xh_count, 1);
		memset(xe, 0, sizeof(struct ocfs2_xattr_entry));
		xe->xe_name_hash = cpu_to_le32(name_hash);
		xe->xe_name_len = name_len;
		ocfs2_xattr_set_type(xe, xi->name_index);
	}

set_new_name_value:
	/* Insert the new name+value. */
	size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_SIZE(xi->value_len);

	/*
	 * We must make sure that the name/value pair
	 * exists in the same block.
	 */
	offs = le16_to_cpu(xh->xh_free_start);
	start = offs - size;

	if (start >> inode->i_sb->s_blocksize_bits !=
	    (offs - 1) >> inode->i_sb->s_blocksize_bits) {
		offs = offs - offs % blocksize;
		xh->xh_free_start = cpu_to_le16(offs);
	}

	val = ocfs2_xattr_bucket_get_val(inode, xs->bucket, offs - size);
	xe->xe_name_offset = cpu_to_le16(offs - size);

	memset(val, 0, size);
	memcpy(val, xi->name, name_len);
	memcpy(val + OCFS2_XATTR_SIZE(name_len), xi->value, xi->value_len);

	xe->xe_value_size = cpu_to_le64(xi->value_len);
	ocfs2_xattr_set_local(xe, local);
	xs->here = xe;
	le16_add_cpu(&xh->xh_free_start, -size);
	le16_add_cpu(&xh->xh_name_value_len, size);

	return;
}

/*
 * Set the xattr entry in the specified bucket.
 * The bucket is indicated by xs->bucket and it should have the enough
 * space for the xattr insertion.
 */
static int ocfs2_xattr_set_entry_in_bucket(struct inode *inode,
					   handle_t *handle,
					   struct ocfs2_xattr_info *xi,
					   struct ocfs2_xattr_search *xs,
					   u32 name_hash,
					   int local)
{
	int ret;
	u64 blkno;

	mlog(0, "Set xattr entry len = %lu index = %d in bucket %llu\n",
	     (unsigned long)xi->value_len, xi->name_index,
	     (unsigned long long)bucket_blkno(xs->bucket));

	if (!xs->bucket->bu_bhs[1]) {
		blkno = bucket_blkno(xs->bucket);
		ocfs2_xattr_bucket_relse(xs->bucket);
		ret = ocfs2_read_xattr_bucket(xs->bucket, blkno);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	ret = ocfs2_xattr_bucket_journal_access(handle, xs->bucket,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	ocfs2_xattr_set_entry_normal(inode, xi, xs, name_hash, local);
	ocfs2_xattr_bucket_journal_dirty(handle, xs->bucket);

out:
	return ret;
}

/*
 * Truncate the specified xe_off entry in xattr bucket.
 * bucket is indicated by header_bh and len is the new length.
 * Both the ocfs2_xattr_value_root and the entry will be updated here.
 *
 * Copy the new updated xe and xe_value_root to new_xe and new_xv if needed.
 */
static int ocfs2_xattr_bucket_value_truncate(struct inode *inode,
					     struct ocfs2_xattr_bucket *bucket,
					     int xe_off,
					     int len,
					     struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret, offset;
	u64 value_blk;
	struct buffer_head *value_bh = NULL;
	struct ocfs2_xattr_value_root *xv;
	struct ocfs2_xattr_entry *xe;
	struct ocfs2_xattr_header *xh = bucket_xh(bucket);
	size_t blocksize = inode->i_sb->s_blocksize;

	xe = &xh->xh_entries[xe_off];

	BUG_ON(!xe || ocfs2_xattr_is_local(xe));

	offset = le16_to_cpu(xe->xe_name_offset) +
		 OCFS2_XATTR_SIZE(xe->xe_name_len);

	value_blk = offset / blocksize;

	/* We don't allow ocfs2_xattr_value to be stored in different block. */
	BUG_ON(value_blk != (offset + OCFS2_XATTR_ROOT_SIZE - 1) / blocksize);

	value_bh = bucket->bu_bhs[value_blk];
	BUG_ON(!value_bh);

	xv = (struct ocfs2_xattr_value_root *)
		(value_bh->b_data + offset % blocksize);

	ret = ocfs2_xattr_bucket_journal_access(ctxt->handle, bucket,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * From here on out we have to dirty the bucket.  The generic
	 * value calls only modify one of the bucket's bhs, but we need
	 * to send the bucket at once.  So if they error, they *could* have
	 * modified something.  We have to assume they did, and dirty
	 * the whole bucket.  This leaves us in a consistent state.
	 */
	mlog(0, "truncate %u in xattr bucket %llu to %d bytes.\n",
	     xe_off, (unsigned long long)bucket_blkno(bucket), len);
	ret = ocfs2_xattr_value_truncate(inode, value_bh, xv, len, ctxt);
	if (ret) {
		mlog_errno(ret);
		goto out_dirty;
	}

	xe->xe_value_size = cpu_to_le64(len);

out_dirty:
	ocfs2_xattr_bucket_journal_dirty(ctxt->handle, bucket);

out:
	return ret;
}

static int ocfs2_xattr_bucket_value_truncate_xs(struct inode *inode,
					struct ocfs2_xattr_search *xs,
					int len,
					struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret, offset;
	struct ocfs2_xattr_entry *xe = xs->here;
	struct ocfs2_xattr_header *xh = (struct ocfs2_xattr_header *)xs->base;

	BUG_ON(!xs->bucket->bu_bhs[0] || !xe || ocfs2_xattr_is_local(xe));

	offset = xe - xh->xh_entries;
	ret = ocfs2_xattr_bucket_value_truncate(inode, xs->bucket,
						offset, len, ctxt);
	if (ret)
		mlog_errno(ret);

	return ret;
}

static int ocfs2_xattr_bucket_set_value_outside(struct inode *inode,
						handle_t *handle,
						struct ocfs2_xattr_search *xs,
						char *val,
						int value_len)
{
	int offset;
	struct ocfs2_xattr_value_root *xv;
	struct ocfs2_xattr_entry *xe = xs->here;

	BUG_ON(!xs->base || !xe || ocfs2_xattr_is_local(xe));

	offset = le16_to_cpu(xe->xe_name_offset) +
		 OCFS2_XATTR_SIZE(xe->xe_name_len);

	xv = (struct ocfs2_xattr_value_root *)(xs->base + offset);

	return __ocfs2_xattr_set_value_outside(inode, handle,
					       xv, val, value_len);
}

static int ocfs2_rm_xattr_cluster(struct inode *inode,
				  struct buffer_head *root_bh,
				  u64 blkno,
				  u32 cpos,
				  u32 len)
{
	int ret;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct inode *tl_inode = osb->osb_tl_inode;
	handle_t *handle;
	struct ocfs2_xattr_block *xb =
			(struct ocfs2_xattr_block *)root_bh->b_data;
	struct ocfs2_alloc_context *meta_ac = NULL;
	struct ocfs2_cached_dealloc_ctxt dealloc;
	struct ocfs2_extent_tree et;

	ocfs2_init_xattr_tree_extent_tree(&et, inode, root_bh);

	ocfs2_init_dealloc_ctxt(&dealloc);

	mlog(0, "rm xattr extent rec at %u len = %u, start from %llu\n",
	     cpos, len, (unsigned long long)blkno);

	ocfs2_remove_xattr_clusters_from_cache(inode, blkno, len);

	ret = ocfs2_lock_allocators(inode, &et, 0, 1, NULL, &meta_ac);
	if (ret) {
		mlog_errno(ret);
		return ret;
	}

	mutex_lock(&tl_inode->i_mutex);

	if (ocfs2_truncate_log_needs_flush(osb)) {
		ret = __ocfs2_flush_truncate_log(osb);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	handle = ocfs2_start_trans(osb, ocfs2_remove_extent_credits(osb->sb));
	if (IS_ERR(handle)) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_journal_access(handle, inode, root_bh,
				   OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, meta_ac,
				  &dealloc);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	le32_add_cpu(&xb->xb_attrs.xb_root.xt_clusters, -len);

	ret = ocfs2_journal_dirty(handle, root_bh);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	ret = ocfs2_truncate_log_append(osb, handle, blkno, len);
	if (ret)
		mlog_errno(ret);

out_commit:
	ocfs2_commit_trans(osb, handle);
out:
	ocfs2_schedule_truncate_log_flush(osb, 1);

	mutex_unlock(&tl_inode->i_mutex);

	if (meta_ac)
		ocfs2_free_alloc_context(meta_ac);

	ocfs2_run_deallocs(osb, &dealloc);

	return ret;
}

static void ocfs2_xattr_bucket_remove_xs(struct inode *inode,
					 handle_t *handle,
					 struct ocfs2_xattr_search *xs)
{
	struct ocfs2_xattr_header *xh = bucket_xh(xs->bucket);
	struct ocfs2_xattr_entry *last = &xh->xh_entries[
						le16_to_cpu(xh->xh_count) - 1];
	int ret = 0;

	ret = ocfs2_xattr_bucket_journal_access(handle, xs->bucket,
						OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		return;
	}

	/* Remove the old entry. */
	memmove(xs->here, xs->here + 1,
		(void *)last - (void *)xs->here);
	memset(last, 0, sizeof(struct ocfs2_xattr_entry));
	le16_add_cpu(&xh->xh_count, -1);

	ocfs2_xattr_bucket_journal_dirty(handle, xs->bucket);
}

/*
 * Set the xattr name/value in the bucket specified in xs.
 *
 * As the new value in xi may be stored in the bucket or in an outside cluster,
 * we divide the whole process into 3 steps:
 * 1. insert name/value in the bucket(ocfs2_xattr_set_entry_in_bucket)
 * 2. truncate of the outside cluster(ocfs2_xattr_bucket_value_truncate_xs)
 * 3. Set the value to the outside cluster(ocfs2_xattr_bucket_set_value_outside)
 * 4. If the clusters for the new outside value can't be allocated, we need
 *    to free the xattr we allocated in set.
 */
static int ocfs2_xattr_set_in_bucket(struct inode *inode,
				     struct ocfs2_xattr_info *xi,
				     struct ocfs2_xattr_search *xs,
				     struct ocfs2_xattr_set_ctxt *ctxt)
{
	int ret, local = 1;
	size_t value_len;
	char *val = (char *)xi->value;
	struct ocfs2_xattr_entry *xe = xs->here;
	u32 name_hash = ocfs2_xattr_name_hash(inode, xi->name,
					      strlen(xi->name));

	if (!xs->not_found && !ocfs2_xattr_is_local(xe)) {
		/*
		 * We need to truncate the xattr storage first.
		 *
		 * If both the old and new value are stored to
		 * outside block, we only need to truncate
		 * the storage and then set the value outside.
		 *
		 * If the new value should be stored within block,
		 * we should free all the outside block first and
		 * the modification to the xattr block will be done
		 * by following steps.
		 */
		if (xi->value_len > OCFS2_XATTR_INLINE_SIZE)
			value_len = xi->value_len;
		else
			value_len = 0;

		ret = ocfs2_xattr_bucket_value_truncate_xs(inode, xs,
							   value_len,
							   ctxt);
		if (ret)
			goto out;

		if (value_len)
			goto set_value_outside;
	}

	value_len = xi->value_len;
	/* So we have to handle the inside block change now. */
	if (value_len > OCFS2_XATTR_INLINE_SIZE) {
		/*
		 * If the new value will be stored outside of block,
		 * initalize a new empty value root and insert it first.
		 */
		local = 0;
		xi->value = &def_xv;
		xi->value_len = OCFS2_XATTR_ROOT_SIZE;
	}

	ret = ocfs2_xattr_set_entry_in_bucket(inode, ctxt->handle, xi, xs,
					      name_hash, local);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	if (value_len <= OCFS2_XATTR_INLINE_SIZE)
		goto out;

	/* allocate the space now for the outside block storage. */
	ret = ocfs2_xattr_bucket_value_truncate_xs(inode, xs,
						   value_len, ctxt);
	if (ret) {
		mlog_errno(ret);

		if (xs->not_found) {
			/*
			 * We can't allocate enough clusters for outside
			 * storage and we have allocated xattr already,
			 * so need to remove it.
			 */
			ocfs2_xattr_bucket_remove_xs(inode, ctxt->handle, xs);
		}
		goto out;
	}

set_value_outside:
	ret = ocfs2_xattr_bucket_set_value_outside(inode, ctxt->handle,
						   xs, val, value_len);
out:
	return ret;
}

/*
 * check whether the xattr bucket is filled up with the same hash value.
 * If we want to insert the xattr with the same hash, return -ENOSPC.
 * If we want to insert a xattr with different hash value, go ahead
 * and ocfs2_divide_xattr_bucket will handle this.
 */
static int ocfs2_check_xattr_bucket_collision(struct inode *inode,
					      struct ocfs2_xattr_bucket *bucket,
					      const char *name)
{
	struct ocfs2_xattr_header *xh = bucket_xh(bucket);
	u32 name_hash = ocfs2_xattr_name_hash(inode, name, strlen(name));

	if (name_hash != le32_to_cpu(xh->xh_entries[0].xe_name_hash))
		return 0;

	if (xh->xh_entries[le16_to_cpu(xh->xh_count) - 1].xe_name_hash ==
	    xh->xh_entries[0].xe_name_hash) {
		mlog(ML_ERROR, "Too much hash collision in xattr bucket %llu, "
		     "hash = %u\n",
		     (unsigned long long)bucket_blkno(bucket),
		     le32_to_cpu(xh->xh_entries[0].xe_name_hash));
		return -ENOSPC;
	}

	return 0;
}

static int ocfs2_xattr_set_entry_index_block(struct inode *inode,
					     struct ocfs2_xattr_info *xi,
					     struct ocfs2_xattr_search *xs,
					     struct ocfs2_xattr_set_ctxt *ctxt)
{
	struct ocfs2_xattr_header *xh;
	struct ocfs2_xattr_entry *xe;
	u16 count, header_size, xh_free_start;
	int free, max_free, need, old;
	size_t value_size = 0, name_len = strlen(xi->name);
	size_t blocksize = inode->i_sb->s_blocksize;
	int ret, allocation = 0;

	mlog_entry("Set xattr %s in xattr index block\n", xi->name);

try_again:
	xh = xs->header;
	count = le16_to_cpu(xh->xh_count);
	xh_free_start = le16_to_cpu(xh->xh_free_start);
	header_size = sizeof(struct ocfs2_xattr_header) +
			count * sizeof(struct ocfs2_xattr_entry);
	max_free = OCFS2_XATTR_BUCKET_SIZE -
		le16_to_cpu(xh->xh_name_value_len) - header_size;

	mlog_bug_on_msg(header_size > blocksize, "bucket %llu has header size "
			"of %u which exceed block size\n",
			(unsigned long long)bucket_blkno(xs->bucket),
			header_size);

	if (xi->value && xi->value_len > OCFS2_XATTR_INLINE_SIZE)
		value_size = OCFS2_XATTR_ROOT_SIZE;
	else if (xi->value)
		value_size = OCFS2_XATTR_SIZE(xi->value_len);

	if (xs->not_found)
		need = sizeof(struct ocfs2_xattr_entry) +
			OCFS2_XATTR_SIZE(name_len) + value_size;
	else {
		need = value_size + OCFS2_XATTR_SIZE(name_len);

		/*
		 * We only replace the old value if the new length is smaller
		 * than the old one. Otherwise we will allocate new space in the
		 * bucket to store it.
		 */
		xe = xs->here;
		if (ocfs2_xattr_is_local(xe))
			old = OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
		else
			old = OCFS2_XATTR_SIZE(OCFS2_XATTR_ROOT_SIZE);

		if (old >= value_size)
			need = 0;
	}

	free = xh_free_start - header_size;
	/*
	 * We need to make sure the new name/value pair
	 * can exist in the same block.
	 */
	if (xh_free_start % blocksize < need)
		free -= xh_free_start % blocksize;

	mlog(0, "xs->not_found = %d, in xattr bucket %llu: free = %d, "
	     "need = %d, max_free = %d, xh_free_start = %u, xh_name_value_len ="
	     " %u\n", xs->not_found,
	     (unsigned long long)bucket_blkno(xs->bucket),
	     free, need, max_free, le16_to_cpu(xh->xh_free_start),
	     le16_to_cpu(xh->xh_name_value_len));

	if (free < need ||
	    (xs->not_found &&
	     count == ocfs2_xattr_max_xe_in_bucket(inode->i_sb))) {
		if (need <= max_free &&
		    count < ocfs2_xattr_max_xe_in_bucket(inode->i_sb)) {
			/*
			 * We can create the space by defragment. Since only the
			 * name/value will be moved, the xe shouldn't be changed
			 * in xs.
			 */
			ret = ocfs2_defrag_xattr_bucket(inode, ctxt->handle,
							xs->bucket);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			xh_free_start = le16_to_cpu(xh->xh_free_start);
			free = xh_free_start - header_size;
			if (xh_free_start % blocksize < need)
				free -= xh_free_start % blocksize;

			if (free >= need)
				goto xattr_set;

			mlog(0, "Can't get enough space for xattr insert by "
			     "defragment. Need %u bytes, but we have %d, so "
			     "allocate new bucket for it.\n", need, free);
		}

		/*
		 * We have to add new buckets or clusters and one
		 * allocation should leave us enough space for insert.
		 */
		BUG_ON(allocation);

		/*
		 * We do not allow for overlapping ranges between buckets. And
		 * the maximum number of collisions we will allow for then is
		 * one bucket's worth, so check it here whether we need to
		 * add a new bucket for the insert.
		 */
		ret = ocfs2_check_xattr_bucket_collision(inode,
							 xs->bucket,
							 xi->name);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		ret = ocfs2_add_new_xattr_bucket(inode,
						 xs->xattr_bh,
						 xs->bucket,
						 ctxt);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		/*
		 * ocfs2_add_new_xattr_bucket() will have updated
		 * xs->bucket if it moved, but it will not have updated
		 * any of the other search fields.  Thus, we drop it and
		 * re-search.  Everything should be cached, so it'll be
		 * quick.
		 */
		ocfs2_xattr_bucket_relse(xs->bucket);
		ret = ocfs2_xattr_index_block_find(inode, xs->xattr_bh,
						   xi->name_index,
						   xi->name, xs);
		if (ret && ret != -ENODATA)
			goto out;
		xs->not_found = ret;
		allocation = 1;
		goto try_again;
	}

xattr_set:
	ret = ocfs2_xattr_set_in_bucket(inode, xi, xs, ctxt);
out:
	mlog_exit(ret);
	return ret;
}

static int ocfs2_delete_xattr_in_bucket(struct inode *inode,
					struct ocfs2_xattr_bucket *bucket,
					void *para)
{
	int ret = 0;
	struct ocfs2_xattr_header *xh = bucket_xh(bucket);
	u16 i;
	struct ocfs2_xattr_entry *xe;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_xattr_set_ctxt ctxt = {NULL, NULL,};
	int credits = ocfs2_remove_extent_credits(osb->sb) +
		ocfs2_blocks_per_xattr_bucket(inode->i_sb);


	ocfs2_init_dealloc_ctxt(&ctxt.dealloc);

	for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
		xe = &xh->xh_entries[i];
		if (ocfs2_xattr_is_local(xe))
			continue;

		ctxt.handle = ocfs2_start_trans(osb, credits);
		if (IS_ERR(ctxt.handle)) {
			ret = PTR_ERR(ctxt.handle);
			mlog_errno(ret);
			break;
		}

		ret = ocfs2_xattr_bucket_value_truncate(inode, bucket,
							i, 0, &ctxt);

		ocfs2_commit_trans(osb, ctxt.handle);
		if (ret) {
			mlog_errno(ret);
			break;
		}
	}

	ocfs2_schedule_truncate_log_flush(osb, 1);
	ocfs2_run_deallocs(osb, &ctxt.dealloc);
	return ret;
}

static int ocfs2_delete_xattr_index_block(struct inode *inode,
					  struct buffer_head *xb_bh)
{
	struct ocfs2_xattr_block *xb =
			(struct ocfs2_xattr_block *)xb_bh->b_data;
	struct ocfs2_extent_list *el = &xb->xb_attrs.xb_root.xt_list;
	int ret = 0;
	u32 name_hash = UINT_MAX, e_cpos, num_clusters;
	u64 p_blkno;

	if (le16_to_cpu(el->l_next_free_rec) == 0)
		return 0;

	while (name_hash > 0) {
		ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno,
					  &e_cpos, &num_clusters, el);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		ret = ocfs2_iterate_xattr_buckets(inode, p_blkno, num_clusters,
						  ocfs2_delete_xattr_in_bucket,
						  NULL);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		ret = ocfs2_rm_xattr_cluster(inode, xb_bh,
					     p_blkno, e_cpos, num_clusters);
		if (ret) {
			mlog_errno(ret);
			break;
		}

		if (e_cpos == 0)
			break;

		name_hash = e_cpos - 1;
	}

out:
	return ret;
}

/*
 * 'security' attributes support
 */
static size_t ocfs2_xattr_security_list(struct inode *inode, char *list,
					size_t list_size, const char *name,
					size_t name_len)
{
	const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
	const size_t total_len = prefix_len + name_len + 1;

	if (list && total_len <= list_size) {
		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
		memcpy(list + prefix_len, name, name_len);
		list[prefix_len + name_len] = '\0';
	}
	return total_len;
}

static int ocfs2_xattr_security_get(struct inode *inode, const char *name,
				    void *buffer, size_t size)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_SECURITY, name,
			       buffer, size);
}

static int ocfs2_xattr_security_set(struct inode *inode, const char *name,
				    const void *value, size_t size, int flags)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;

	return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, name, value,
			       size, flags);
}

int ocfs2_init_security_get(struct inode *inode,
			    struct inode *dir,
			    struct ocfs2_security_xattr_info *si)
{
	return security_inode_init_security(inode, dir, &si->name, &si->value,
					    &si->value_len);
}

int ocfs2_init_security_set(handle_t *handle,
			    struct inode *inode,
			    struct buffer_head *di_bh,
			    struct ocfs2_security_xattr_info *si,
			    struct ocfs2_alloc_context *xattr_ac,
			    struct ocfs2_alloc_context *data_ac)
{
	return ocfs2_xattr_set_handle(handle, inode, di_bh,
				     OCFS2_XATTR_INDEX_SECURITY,
				     si->name, si->value, si->value_len, 0,
				     xattr_ac, data_ac);
}

struct xattr_handler ocfs2_xattr_security_handler = {
	.prefix	= XATTR_SECURITY_PREFIX,
	.list	= ocfs2_xattr_security_list,
	.get	= ocfs2_xattr_security_get,
	.set	= ocfs2_xattr_security_set,
};

/*
 * 'trusted' attributes support
 */
static size_t ocfs2_xattr_trusted_list(struct inode *inode, char *list,
				       size_t list_size, const char *name,
				       size_t name_len)
{
	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
	const size_t total_len = prefix_len + name_len + 1;

	if (list && total_len <= list_size) {
		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
		memcpy(list + prefix_len, name, name_len);
		list[prefix_len + name_len] = '\0';
	}
	return total_len;
}

static int ocfs2_xattr_trusted_get(struct inode *inode, const char *name,
				   void *buffer, size_t size)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_TRUSTED, name,
			       buffer, size);
}

static int ocfs2_xattr_trusted_set(struct inode *inode, const char *name,
				   const void *value, size_t size, int flags)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;

	return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_TRUSTED, name, value,
			       size, flags);
}

struct xattr_handler ocfs2_xattr_trusted_handler = {
	.prefix	= XATTR_TRUSTED_PREFIX,
	.list	= ocfs2_xattr_trusted_list,
	.get	= ocfs2_xattr_trusted_get,
	.set	= ocfs2_xattr_trusted_set,
};

/*
 * 'user' attributes support
 */
static size_t ocfs2_xattr_user_list(struct inode *inode, char *list,
				    size_t list_size, const char *name,
				    size_t name_len)
{
	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
	const size_t total_len = prefix_len + name_len + 1;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
		return 0;

	if (list && total_len <= list_size) {
		memcpy(list, XATTR_USER_PREFIX, prefix_len);
		memcpy(list + prefix_len, name, name_len);
		list[prefix_len + name_len] = '\0';
	}
	return total_len;
}

static int ocfs2_xattr_user_get(struct inode *inode, const char *name,
				void *buffer, size_t size)
{
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	if (strcmp(name, "") == 0)
		return -EINVAL;
	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
		return -EOPNOTSUPP;
	return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_USER, name,
			       buffer, size);
}

static int ocfs2_xattr_user_set(struct inode *inode, const char *name,
				const void *value, size_t size, int flags)
{
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	if (strcmp(name, "") == 0)
		return -EINVAL;
	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
		return -EOPNOTSUPP;

	return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_USER, name, value,
			       size, flags);
}

struct xattr_handler ocfs2_xattr_user_handler = {
	.prefix	= XATTR_USER_PREFIX,
	.list	= ocfs2_xattr_user_list,
	.get	= ocfs2_xattr_user_get,
	.set	= ocfs2_xattr_user_set,
};