summaryrefslogtreecommitdiffstats
path: root/fs/ext4/xattr.c
blob: 22bfb6221a2dd0870fb273d12b030c75c22880ff (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
/*
 * linux/fs/ext4/xattr.c
 *
 * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
 *
 * Fix by Harrison Xing <harrison@mountainviewdata.com>.
 * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>.
 * Extended attributes for symlinks and special files added per
 *  suggestion of Luka Renko <luka.renko@hermes.si>.
 * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
 *  Red Hat Inc.
 * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz
 *  and Andreas Gruenbacher <agruen@suse.de>.
 */

/*
 * Extended attributes are stored directly in inodes (on file systems with
 * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
 * field contains the block number if an inode uses an additional block. All
 * attributes must fit in the inode and one additional block. Blocks that
 * contain the identical set of attributes may be shared among several inodes.
 * Identical blocks are detected by keeping a cache of blocks that have
 * recently been accessed.
 *
 * The attributes in inodes and on blocks have a different header; the entries
 * are stored in the same format:
 *
 *   +------------------+
 *   | header           |
 *   | entry 1          | |
 *   | entry 2          | | growing downwards
 *   | entry 3          | v
 *   | four null bytes  |
 *   | . . .            |
 *   | value 1          | ^
 *   | value 3          | | growing upwards
 *   | value 2          | |
 *   +------------------+
 *
 * The header is followed by multiple entry descriptors. In disk blocks, the
 * entry descriptors are kept sorted. In inodes, they are unsorted. The
 * attribute values are aligned to the end of the block in no specific order.
 *
 * Locking strategy
 * ----------------
 * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
 * EA blocks are only changed if they are exclusive to an inode, so
 * holding xattr_sem also means that nothing but the EA block's reference
 * count can change. Multiple writers to the same block are synchronized
 * by the buffer lock.
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
#include "acl.h"

#ifdef EXT4_XATTR_DEBUG
# define ea_idebug(inode, fmt, ...)					\
	printk(KERN_DEBUG "inode %s:%lu: " fmt "\n",			\
	       inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...)					\
	printk(KERN_DEBUG "block %pg:%lu: " fmt "\n",			\
	       bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__)
#else
# define ea_idebug(inode, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
#endif

static void ext4_xattr_block_cache_insert(struct mb_cache *,
					  struct buffer_head *);
static struct buffer_head *
ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
			    struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
			      struct ext4_xattr_entry *);

static const struct xattr_handler * const ext4_xattr_handler_map[] = {
	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &posix_acl_access_xattr_handler,
	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
	[EXT4_XATTR_INDEX_TRUSTED]	     = &ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_SECURITY
	[EXT4_XATTR_INDEX_SECURITY]	     = &ext4_xattr_security_handler,
#endif
};

const struct xattr_handler *ext4_xattr_handlers[] = {
	&ext4_xattr_user_handler,
	&ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
	&posix_acl_access_xattr_handler,
	&posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_EXT4_FS_SECURITY
	&ext4_xattr_security_handler,
#endif
	NULL
};

#define EA_BLOCK_CACHE(inode)	(((struct ext4_sb_info *) \
				inode->i_sb->s_fs_info)->s_ea_block_cache)

#define EA_INODE_CACHE(inode)	(((struct ext4_sb_info *) \
				inode->i_sb->s_fs_info)->s_ea_inode_cache)

static int
ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
			struct inode *inode);

#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
{
	lockdep_set_subclass(&ea_inode->i_rwsem, 1);
}
#endif

static __le32 ext4_xattr_block_csum(struct inode *inode,
				    sector_t block_nr,
				    struct ext4_xattr_header *hdr)
{
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	__u32 csum;
	__le64 dsk_block_nr = cpu_to_le64(block_nr);
	__u32 dummy_csum = 0;
	int offset = offsetof(struct ext4_xattr_header, h_checksum);

	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
			   sizeof(dsk_block_nr));
	csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
	offset += sizeof(dummy_csum);
	csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
			   EXT4_BLOCK_SIZE(inode->i_sb) - offset);

	return cpu_to_le32(csum);
}

static int ext4_xattr_block_csum_verify(struct inode *inode,
					struct buffer_head *bh)
{
	struct ext4_xattr_header *hdr = BHDR(bh);
	int ret = 1;

	if (ext4_has_metadata_csum(inode->i_sb)) {
		lock_buffer(bh);
		ret = (hdr->h_checksum == ext4_xattr_block_csum(inode,
							bh->b_blocknr, hdr));
		unlock_buffer(bh);
	}
	return ret;
}

static void ext4_xattr_block_csum_set(struct inode *inode,
				      struct buffer_head *bh)
{
	if (ext4_has_metadata_csum(inode->i_sb))
		BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode,
						bh->b_blocknr, BHDR(bh));
}

static inline const struct xattr_handler *
ext4_xattr_handler(int name_index)
{
	const struct xattr_handler *handler = NULL;

	if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
		handler = ext4_xattr_handler_map[name_index];
	return handler;
}

static int
ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
			 void *value_start)
{
	struct ext4_xattr_entry *e = entry;

	/* Find the end of the names list */
	while (!IS_LAST_ENTRY(e)) {
		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
		if ((void *)next >= end)
			return -EFSCORRUPTED;
		e = next;
	}

	/* Check the values */
	while (!IS_LAST_ENTRY(entry)) {
		if (entry->e_value_size != 0 &&
		    entry->e_value_inum == 0) {
			u16 offs = le16_to_cpu(entry->e_value_offs);
			u32 size = le32_to_cpu(entry->e_value_size);
			void *value;

			/*
			 * The value cannot overlap the names, and the value
			 * with padding cannot extend beyond 'end'.  Check both
			 * the padded and unpadded sizes, since the size may
			 * overflow to 0 when adding padding.
			 */
			if (offs > end - value_start)
				return -EFSCORRUPTED;
			value = value_start + offs;
			if (value < (void *)e + sizeof(u32) ||
			    size > end - value ||
			    EXT4_XATTR_SIZE(size) > end - value)
				return -EFSCORRUPTED;
		}
		entry = EXT4_XATTR_NEXT(entry);
	}

	return 0;
}

static inline int
ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
{
	int error;

	if (buffer_verified(bh))
		return 0;

	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
	    BHDR(bh)->h_blocks != cpu_to_le32(1))
		return -EFSCORRUPTED;
	if (!ext4_xattr_block_csum_verify(inode, bh))
		return -EFSBADCRC;
	error = ext4_xattr_check_entries(BFIRST(bh), bh->b_data + bh->b_size,
					 bh->b_data);
	if (!error)
		set_buffer_verified(bh);
	return error;
}

static int
__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
			 void *end, const char *function, unsigned int line)
{
	int error = -EFSCORRUPTED;

	if (end - (void *)header < sizeof(*header) + sizeof(u32) ||
	    (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
		goto errout;
	error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header));
errout:
	if (error)
		__ext4_error_inode(inode, function, line, 0,
				   "corrupted in-inode xattr");
	return error;
}

#define xattr_check_inode(inode, header, end) \
	__xattr_check_inode((inode), (header), (end), __func__, __LINE__)

static int
ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
		      const char *name, int sorted)
{
	struct ext4_xattr_entry *entry;
	size_t name_len;
	int cmp = 1;

	if (name == NULL)
		return -EINVAL;
	name_len = strlen(name);
	entry = *pentry;
	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
		cmp = name_index - entry->e_name_index;
		if (!cmp)
			cmp = name_len - entry->e_name_len;
		if (!cmp)
			cmp = memcmp(name, entry->e_name, name_len);
		if (cmp <= 0 && (sorted || cmp == 0))
			break;
	}
	*pentry = entry;
	return cmp ? -ENODATA : 0;
}

static u32
ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size)
{
	return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size);
}

static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode)
{
	return ((u64)ea_inode->i_ctime.tv_sec << 32) |
	       ((u32)ea_inode->i_version);
}

static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count)
{
	ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32);
	ea_inode->i_version = (u32)ref_count;
}

static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode)
{
	return (u32)ea_inode->i_atime.tv_sec;
}

static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash)
{
	ea_inode->i_atime.tv_sec = hash;
}

/*
 * Read the EA value from an inode.
 */
static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
{
	unsigned long block = 0;
	struct buffer_head *bh;
	int blocksize = ea_inode->i_sb->s_blocksize;
	size_t csize, copied = 0;
	void *copy_pos = buf;

	while (copied < size) {
		csize = (size - copied) > blocksize ? blocksize : size - copied;
		bh = ext4_bread(NULL, ea_inode, block, 0);
		if (IS_ERR(bh))
			return PTR_ERR(bh);
		if (!bh)
			return -EFSCORRUPTED;

		memcpy(copy_pos, bh->b_data, csize);
		brelse(bh);

		copy_pos += csize;
		block += 1;
		copied += csize;
	}
	return 0;
}

static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
				 struct inode **ea_inode)
{
	struct inode *inode;
	int err;

	inode = ext4_iget(parent->i_sb, ea_ino);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		ext4_error(parent->i_sb,
			   "error while reading EA inode %lu err=%d", ea_ino,
			   err);
		return err;
	}

	if (is_bad_inode(inode)) {
		ext4_error(parent->i_sb,
			   "error while reading EA inode %lu is_bad_inode",
			   ea_ino);
		err = -EIO;
		goto error;
	}

	if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
		ext4_error(parent->i_sb,
			   "EA inode %lu does not have EXT4_EA_INODE_FL flag",
			    ea_ino);
		err = -EINVAL;
		goto error;
	}

	*ea_inode = inode;
	return 0;
error:
	iput(inode);
	return err;
}

static int
ext4_xattr_inode_verify_hash(struct inode *ea_inode, void *buffer, size_t size)
{
	u32 hash;

	/* Verify stored hash matches calculated hash. */
	hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size);
	if (hash != ext4_xattr_inode_get_hash(ea_inode))
		return -EFSCORRUPTED;
	return 0;
}

#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec)

/*
 * Read the value from the EA inode.
 */
static int
ext4_xattr_inode_get(struct inode *inode, unsigned long ea_ino, void *buffer,
		     size_t size)
{
	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
	struct inode *ea_inode;
	int err;

	err = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
	if (err) {
		ea_inode = NULL;
		goto out;
	}

	if (i_size_read(ea_inode) != size) {
		ext4_warning_inode(ea_inode,
				   "ea_inode file size=%llu entry size=%zu",
				   i_size_read(ea_inode), size);
		err = -EFSCORRUPTED;
		goto out;
	}

	err = ext4_xattr_inode_read(ea_inode, buffer, size);
	if (err)
		goto out;

	err = ext4_xattr_inode_verify_hash(ea_inode, buffer, size);
	/*
	 * Compatibility check for old Lustre ea_inode implementation. Old
	 * version does not have hash validation, but it has a backpointer
	 * from ea_inode to the parent inode.
	 */
	if (err == -EFSCORRUPTED) {
		if (EXT4_XATTR_INODE_GET_PARENT(ea_inode) != inode->i_ino ||
		    ea_inode->i_generation != inode->i_generation) {
			ext4_warning_inode(ea_inode,
					   "EA inode hash validation failed");
			goto out;
		}
		/* Do not add ea_inode to the cache. */
		ea_inode_cache = NULL;
	} else if (err)
		goto out;

	if (ea_inode_cache)
		mb_cache_entry_create(ea_inode_cache, GFP_NOFS,
				      ext4_xattr_inode_get_hash(ea_inode),
				      ea_inode->i_ino, true /* reusable */);
out:
	iput(ea_inode);
	return err;
}

static int
ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
		     void *buffer, size_t buffer_size)
{
	struct buffer_head *bh = NULL;
	struct ext4_xattr_entry *entry;
	size_t size;
	int error;
	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);

	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
		  name_index, name, buffer, (long)buffer_size);

	error = -ENODATA;
	if (!EXT4_I(inode)->i_file_acl)
		goto cleanup;
	ea_idebug(inode, "reading block %llu",
		  (unsigned long long)EXT4_I(inode)->i_file_acl);
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	if (!bh)
		goto cleanup;
	ea_bdebug(bh, "b_count=%d, refcount=%d",
		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
	if (ext4_xattr_check_block(inode, bh)) {
		EXT4_ERROR_INODE(inode, "bad block %llu",
				 EXT4_I(inode)->i_file_acl);
		error = -EFSCORRUPTED;
		goto cleanup;
	}
	ext4_xattr_block_cache_insert(ea_block_cache, bh);
	entry = BFIRST(bh);
	error = ext4_xattr_find_entry(&entry, name_index, name, 1);
	if (error)
		goto cleanup;
	size = le32_to_cpu(entry->e_value_size);
	if (buffer) {
		error = -ERANGE;
		if (size > buffer_size)
			goto cleanup;
		if (entry->e_value_inum) {
			error = ext4_xattr_inode_get(inode,
					     le32_to_cpu(entry->e_value_inum),
					     buffer, size);
			if (error)
				goto cleanup;
		} else {
			memcpy(buffer, bh->b_data +
			       le16_to_cpu(entry->e_value_offs), size);
		}
	}
	error = size;

cleanup:
	brelse(bh);
	return error;
}

int
ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
		     void *buffer, size_t buffer_size)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_entry *entry;
	struct ext4_inode *raw_inode;
	struct ext4_iloc iloc;
	size_t size;
	void *end;
	int error;

	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
		return -ENODATA;
	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;
	raw_inode = ext4_raw_inode(&iloc);
	header = IHDR(inode, raw_inode);
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	error = xattr_check_inode(inode, header, end);
	if (error)
		goto cleanup;
	entry = IFIRST(header);
	error = ext4_xattr_find_entry(&entry, name_index, name, 0);
	if (error)
		goto cleanup;
	size = le32_to_cpu(entry->e_value_size);
	if (buffer) {
		error = -ERANGE;
		if (size > buffer_size)
			goto cleanup;
		if (entry->e_value_inum) {
			error = ext4_xattr_inode_get(inode,
					     le32_to_cpu(entry->e_value_inum),
					     buffer, size);
			if (error)
				goto cleanup;
		} else {
			memcpy(buffer, (void *)IFIRST(header) +
			       le16_to_cpu(entry->e_value_offs), size);
		}
	}
	error = size;

cleanup:
	brelse(iloc.bh);
	return error;
}

/*
 * ext4_xattr_get()
 *
 * Copy an extended attribute into the buffer
 * provided, or compute the buffer size required.
 * Buffer is NULL to compute the size of the buffer required.
 *
 * Returns a negative error number on failure, or the number of bytes
 * used / required on success.
 */
int
ext4_xattr_get(struct inode *inode, int name_index, const char *name,
	       void *buffer, size_t buffer_size)
{
	int error;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	if (strlen(name) > 255)
		return -ERANGE;

	down_read(&EXT4_I(inode)->xattr_sem);
	error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
				     buffer_size);
	if (error == -ENODATA)
		error = ext4_xattr_block_get(inode, name_index, name, buffer,
					     buffer_size);
	up_read(&EXT4_I(inode)->xattr_sem);
	return error;
}

static int
ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
			char *buffer, size_t buffer_size)
{
	size_t rest = buffer_size;

	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
		const struct xattr_handler *handler =
			ext4_xattr_handler(entry->e_name_index);

		if (handler && (!handler->list || handler->list(dentry))) {
			const char *prefix = handler->prefix ?: handler->name;
			size_t prefix_len = strlen(prefix);
			size_t size = prefix_len + entry->e_name_len + 1;

			if (buffer) {
				if (size > rest)
					return -ERANGE;
				memcpy(buffer, prefix, prefix_len);
				buffer += prefix_len;
				memcpy(buffer, entry->e_name, entry->e_name_len);
				buffer += entry->e_name_len;
				*buffer++ = 0;
			}
			rest -= size;
		}
	}
	return buffer_size - rest;  /* total size */
}

static int
ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
	struct inode *inode = d_inode(dentry);
	struct buffer_head *bh = NULL;
	int error;

	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
		  buffer, (long)buffer_size);

	error = 0;
	if (!EXT4_I(inode)->i_file_acl)
		goto cleanup;
	ea_idebug(inode, "reading block %llu",
		  (unsigned long long)EXT4_I(inode)->i_file_acl);
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	error = -EIO;
	if (!bh)
		goto cleanup;
	ea_bdebug(bh, "b_count=%d, refcount=%d",
		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
	if (ext4_xattr_check_block(inode, bh)) {
		EXT4_ERROR_INODE(inode, "bad block %llu",
				 EXT4_I(inode)->i_file_acl);
		error = -EFSCORRUPTED;
		goto cleanup;
	}
	ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh);
	error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);

cleanup:
	brelse(bh);

	return error;
}

static int
ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
	struct inode *inode = d_inode(dentry);
	struct ext4_xattr_ibody_header *header;
	struct ext4_inode *raw_inode;
	struct ext4_iloc iloc;
	void *end;
	int error;

	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
		return 0;
	error = ext4_get_inode_loc(inode, &iloc);
	if (error)
		return error;
	raw_inode = ext4_raw_inode(&iloc);
	header = IHDR(inode, raw_inode);
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	error = xattr_check_inode(inode, header, end);
	if (error)
		goto cleanup;
	error = ext4_xattr_list_entries(dentry, IFIRST(header),
					buffer, buffer_size);

cleanup:
	brelse(iloc.bh);
	return error;
}

/*
 * Inode operation listxattr()
 *
 * d_inode(dentry)->i_rwsem: don't care
 *
 * Copy a list of attribute names into the buffer
 * provided, or compute the buffer size required.
 * Buffer is NULL to compute the size of the buffer required.
 *
 * Returns a negative error number on failure, or the number of bytes
 * used / required on success.
 */
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
	int ret, ret2;

	down_read(&EXT4_I(d_inode(dentry))->xattr_sem);
	ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
	if (ret < 0)
		goto errout;
	if (buffer) {
		buffer += ret;
		buffer_size -= ret;
	}
	ret = ext4_xattr_block_list(dentry, buffer, buffer_size);
	if (ret < 0)
		goto errout;
	ret += ret2;
errout:
	up_read(&EXT4_I(d_inode(dentry))->xattr_sem);
	return ret;
}

/*
 * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
 * not set, set it.
 */
static void ext4_xattr_update_super_block(handle_t *handle,
					  struct super_block *sb)
{
	if (ext4_has_feature_xattr(sb))
		return;

	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
		ext4_set_feature_xattr(sb);
		ext4_handle_dirty_super(handle, sb);
	}
}

int ext4_get_inode_usage(struct inode *inode, qsize_t *usage)
{
	struct ext4_iloc iloc = { .bh = NULL };
	struct buffer_head *bh = NULL;
	struct ext4_inode *raw_inode;
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_entry *entry;
	qsize_t ea_inode_refs = 0;
	void *end;
	int ret;

	lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem);

	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
		ret = ext4_get_inode_loc(inode, &iloc);
		if (ret)
			goto out;
		raw_inode = ext4_raw_inode(&iloc);
		header = IHDR(inode, raw_inode);
		end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
		ret = xattr_check_inode(inode, header, end);
		if (ret)
			goto out;

		for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
		     entry = EXT4_XATTR_NEXT(entry))
			if (entry->e_value_inum)
				ea_inode_refs++;
	}

	if (EXT4_I(inode)->i_file_acl) {
		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
		if (!bh) {
			ret = -EIO;
			goto out;
		}

		if (ext4_xattr_check_block(inode, bh)) {
			ret = -EFSCORRUPTED;
			goto out;
		}

		for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
		     entry = EXT4_XATTR_NEXT(entry))
			if (entry->e_value_inum)
				ea_inode_refs++;
	}
	*usage = ea_inode_refs + 1;
	ret = 0;
out:
	brelse(iloc.bh);
	brelse(bh);
	return ret;
}

static inline size_t round_up_cluster(struct inode *inode, size_t length)
{
	struct super_block *sb = inode->i_sb;
	size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits +
				    inode->i_blkbits);
	size_t mask = ~(cluster_size - 1);

	return (length + cluster_size - 1) & mask;
}

static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len)
{
	int err;

	err = dquot_alloc_inode(inode);
	if (err)
		return err;
	err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len));
	if (err)
		dquot_free_inode(inode);
	return err;
}

static void ext4_xattr_inode_free_quota(struct inode *inode, size_t len)
{
	dquot_free_space_nodirty(inode, round_up_cluster(inode, len));
	dquot_free_inode(inode);
}

static int __ext4_xattr_set_credits(struct inode *inode,
				    struct buffer_head *block_bh,
				    size_t value_len)
{
	struct super_block *sb = inode->i_sb;
	int credits;
	int blocks;

	/*
	 * 1) Owner inode update
	 * 2) Ref count update on old xattr block
	 * 3) new xattr block
	 * 4) block bitmap update for new xattr block
	 * 5) group descriptor for new xattr block
	 * 6) block bitmap update for old xattr block
	 * 7) group descriptor for old block
	 *
	 * 6 & 7 can happen if we have two racing threads T_a and T_b
	 * which are each trying to set an xattr on inodes I_a and I_b
	 * which were both initially sharing an xattr block.
	 */
	credits = 7;

	/* Quota updates. */
	credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb);

	/*
	 * In case of inline data, we may push out the data to a block,
	 * so we need to reserve credits for this eventuality
	 */
	if (ext4_has_inline_data(inode))
		credits += ext4_writepage_trans_blocks(inode) + 1;

	/* We are done if ea_inode feature is not enabled. */
	if (!ext4_has_feature_ea_inode(sb))
		return credits;

	/* New ea_inode, inode map, block bitmap, group descriptor. */
	credits += 4;

	/* Data blocks. */
	blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits;

	/* Indirection block or one level of extent tree. */
	blocks += 1;

	/* Block bitmap and group descriptor updates for each block. */
	credits += blocks * 2;

	/* Blocks themselves. */
	credits += blocks;

	/* Dereference ea_inode holding old xattr value.
	 * Old ea_inode, inode map, block bitmap, group descriptor.
	 */
	credits += 4;

	/* Data blocks for old ea_inode. */
	blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits;

	/* Indirection block or one level of extent tree for old ea_inode. */
	blocks += 1;

	/* Block bitmap and group descriptor updates for each block. */
	credits += blocks * 2;

	/* We may need to clone the existing xattr block in which case we need
	 * to increment ref counts for existing ea_inodes referenced by it.
	 */
	if (block_bh) {
		struct ext4_xattr_entry *entry = BFIRST(block_bh);

		for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry))
			if (entry->e_value_inum)
				/* Ref count update on ea_inode. */
				credits += 1;
	}
	return credits;
}

static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
				     int credits, struct buffer_head *bh,
				     bool dirty, bool block_csum)
{
	int error;

	if (!ext4_handle_valid(handle))
		return 0;

	if (handle->h_buffer_credits >= credits)
		return 0;

	error = ext4_journal_extend(handle, credits - handle->h_buffer_credits);
	if (!error)
		return 0;
	if (error < 0) {
		ext4_warning(inode->i_sb, "Extend journal (error %d)", error);
		return error;
	}

	if (bh && dirty) {
		if (block_csum)
			ext4_xattr_block_csum_set(inode, bh);
		error = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (error) {
			ext4_warning(inode->i_sb, "Handle metadata (error %d)",
				     error);
			return error;
		}
	}

	error = ext4_journal_restart(handle, credits);
	if (error) {
		ext4_warning(inode->i_sb, "Restart journal (error %d)", error);
		return error;
	}

	if (bh) {
		error = ext4_journal_get_write_access(handle, bh);
		if (error) {
			ext4_warning(inode->i_sb,
				     "Get write access failed (error %d)",
				     error);
			return error;
		}
	}
	return 0;
}

static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
				       int ref_change)
{
	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
	struct ext4_iloc iloc;
	s64 ref_count;
	u32 hash;
	int ret;

	inode_lock(ea_inode);

	ret = ext4_reserve_inode_write(handle, ea_inode, &iloc);
	if (ret) {
		iloc.bh = NULL;
		goto out;
	}

	ref_count = ext4_xattr_inode_get_ref(ea_inode);
	ref_count += ref_change;
	ext4_xattr_inode_set_ref(ea_inode, ref_count);

	if (ref_change > 0) {
		WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld",
			  ea_inode->i_ino, ref_count);

		if (ref_count == 1) {
			WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u",
				  ea_inode->i_ino, ea_inode->i_nlink);

			set_nlink(ea_inode, 1);
			ext4_orphan_del(handle, ea_inode);

			hash = ext4_xattr_inode_get_hash(ea_inode);
			mb_cache_entry_create(ea_inode_cache, GFP_NOFS, hash,
					      ea_inode->i_ino,
					      true /* reusable */);
		}
	} else {
		WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
			  ea_inode->i_ino, ref_count);

		if (ref_count == 0) {
			WARN_ONCE(ea_inode->i_nlink != 1,
				  "EA inode %lu i_nlink=%u",
				  ea_inode->i_ino, ea_inode->i_nlink);

			clear_nlink(ea_inode);
			ext4_orphan_add(handle, ea_inode);

			hash = ext4_xattr_inode_get_hash(ea_inode);
			mb_cache_entry_delete(ea_inode_cache, hash,
					      ea_inode->i_ino);
		}
	}

	ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc);
	iloc.bh = NULL;
	if (ret)
		ext4_warning_inode(ea_inode,
				   "ext4_mark_iloc_dirty() failed ret=%d", ret);
out:
	brelse(iloc.bh);
	inode_unlock(ea_inode);
	return ret;
}

static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode)
{
	return ext4_xattr_inode_update_ref(handle, ea_inode, 1);
}

static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode)
{
	return ext4_xattr_inode_update_ref(handle, ea_inode, -1);
}

static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent,
					struct ext4_xattr_entry *first)
{
	struct inode *ea_inode;
	struct ext4_xattr_entry *entry;
	struct ext4_xattr_entry *failed_entry;
	unsigned int ea_ino;
	int err, saved_err;

	for (entry = first; !IS_LAST_ENTRY(entry);
	     entry = EXT4_XATTR_NEXT(entry)) {
		if (!entry->e_value_inum)
			continue;
		ea_ino = le32_to_cpu(entry->e_value_inum);
		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
		if (err)
			goto cleanup;
		err = ext4_xattr_inode_inc_ref(handle, ea_inode);
		if (err) {
			ext4_warning_inode(ea_inode, "inc ref error %d", err);
			iput(ea_inode);
			goto cleanup;
		}
		iput(ea_inode);
	}
	return 0;

cleanup:
	saved_err = err;
	failed_entry = entry;

	for (entry = first; entry != failed_entry;
	     entry = EXT4_XATTR_NEXT(entry)) {
		if (!entry->e_value_inum)
			continue;
		ea_ino = le32_to_cpu(entry->e_value_inum);
		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
		if (err) {
			ext4_warning(parent->i_sb,
				     "cleanup ea_ino %u iget error %d", ea_ino,
				     err);
			continue;
		}
		err = ext4_xattr_inode_dec_ref(handle, ea_inode);
		if (err)
			ext4_warning_inode(ea_inode, "cleanup dec ref error %d",
					   err);
		iput(ea_inode);
	}
	return saved_err;
}

static void
ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent,
			     struct buffer_head *bh,
			     struct ext4_xattr_entry *first, bool block_csum,
			     struct ext4_xattr_inode_array **ea_inode_array,
			     int extra_credits, bool skip_quota)
{
	struct inode *ea_inode;
	struct ext4_xattr_entry *entry;
	bool dirty = false;
	unsigned int ea_ino;
	int err;
	int credits;

	/* One credit for dec ref on ea_inode, one for orphan list addition, */
	credits = 2 + extra_credits;

	for (entry = first; !IS_LAST_ENTRY(entry);
	     entry = EXT4_XATTR_NEXT(entry)) {
		if (!entry->e_value_inum)
			continue;
		ea_ino = le32_to_cpu(entry->e_value_inum);
		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
		if (err)
			continue;

		err = ext4_expand_inode_array(ea_inode_array, ea_inode);
		if (err) {
			ext4_warning_inode(ea_inode,
					   "Expand inode array err=%d", err);
			iput(ea_inode);
			continue;
		}

		err = ext4_xattr_ensure_credits(handle, parent, credits, bh,
						dirty, block_csum);
		if (err) {
			ext4_warning_inode(ea_inode, "Ensure credits err=%d",
					   err);
			continue;
		}

		err = ext4_xattr_inode_dec_ref(handle, ea_inode);
		if (err) {
			ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d",
					   err);
			continue;
		}

		if (!skip_quota)
			ext4_xattr_inode_free_quota(parent,
					      le32_to_cpu(entry->e_value_size));

		/*
		 * Forget about ea_inode within the same transaction that
		 * decrements the ref count. This avoids duplicate decrements in
		 * case the rest of the work spills over to subsequent
		 * transactions.
		 */
		entry->e_value_inum = 0;
		entry->e_value_size = 0;

		dirty = true;
	}

	if (dirty) {
		/*
		 * Note that we are deliberately skipping csum calculation for
		 * the final update because we do not expect any journal
		 * restarts until xattr block is freed.
		 */

		err = ext4_handle_dirty_metadata(handle, NULL, bh);
		if (err)
			ext4_warning_inode(parent,
					   "handle dirty metadata err=%d", err);
	}
}

/*
 * Release the xattr block BH: If the reference count is > 1, decrement it;
 * otherwise free the block.
 */
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
			 struct buffer_head *bh,
			 struct ext4_xattr_inode_array **ea_inode_array,
			 int extra_credits)
{
	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
	u32 hash, ref;
	int error = 0;

	BUFFER_TRACE(bh, "get_write_access");
	error = ext4_journal_get_write_access(handle, bh);
	if (error)
		goto out;

	lock_buffer(bh);
	hash = le32_to_cpu(BHDR(bh)->h_hash);
	ref = le32_to_cpu(BHDR(bh)->h_refcount);
	if (ref == 1) {
		ea_bdebug(bh, "refcount now=0; freeing");
		/*
		 * This must happen under buffer lock for
		 * ext4_xattr_block_set() to reliably detect freed block
		 */
		mb_cache_entry_delete(ea_block_cache, hash, bh->b_blocknr);
		get_bh(bh);
		unlock_buffer(bh);

		if (ext4_has_feature_ea_inode(inode->i_sb))
			ext4_xattr_inode_dec_ref_all(handle, inode, bh,
						     BFIRST(bh),
						     true /* block_csum */,
						     ea_inode_array,
						     extra_credits,
						     true /* skip_quota */);
		ext4_free_blocks(handle, inode, bh, 0, 1,
				 EXT4_FREE_BLOCKS_METADATA |
				 EXT4_FREE_BLOCKS_FORGET);
	} else {
		ref--;
		BHDR(bh)->h_refcount = cpu_to_le32(ref);
		if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
			struct mb_cache_entry *ce;

			ce = mb_cache_entry_get(ea_block_cache, hash,
						bh->b_blocknr);
			if (ce) {
				ce->e_reusable = 1;
				mb_cache_entry_put(ea_block_cache, ce);
			}
		}

		ext4_xattr_block_csum_set(inode, bh);
		/*
		 * Beware of this ugliness: Releasing of xattr block references
		 * from different inodes can race and so we have to protect
		 * from a race where someone else frees the block (and releases
		 * its journal_head) before we are done dirtying the buffer. In
		 * nojournal mode this race is harmless and we actually cannot
		 * call ext4_handle_dirty_metadata() with locked buffer as
		 * that function can call sync_dirty_buffer() so for that case
		 * we handle the dirtying after unlocking the buffer.
		 */
		if (ext4_handle_valid(handle))
			error = ext4_handle_dirty_metadata(handle, inode, bh);
		unlock_buffer(bh);
		if (!ext4_handle_valid(handle))
			error = ext4_handle_dirty_metadata(handle, inode, bh);
		if (IS_SYNC(inode))
			ext4_handle_sync(handle);
		dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
		ea_bdebug(bh, "refcount now=%d; releasing",
			  le32_to_cpu(BHDR(bh)->h_refcount));
	}
out:
	ext4_std_error(inode->i_sb, error);
	return;
}

/*
 * Find the available free space for EAs. This also returns the total number of
 * bytes used by EA entries.
 */
static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
				    size_t *min_offs, void *base, int *total)
{
	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
		if (!last->e_value_inum && last->e_value_size) {
			size_t offs = le16_to_cpu(last->e_value_offs);
			if (offs < *min_offs)
				*min_offs = offs;
		}
		if (total)
			*total += EXT4_XATTR_LEN(last->e_name_len);
	}
	return (*min_offs - ((void *)last - base) - sizeof(__u32));
}

/*
 * Write the value of the EA in an inode.
 */
static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
				  const void *buf, int bufsize)
{
	struct buffer_head *bh = NULL;
	unsigned long block = 0;
	int blocksize = ea_inode->i_sb->s_blocksize;
	int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
	int csize, wsize = 0;
	int ret = 0;
	int retries = 0;

retry:
	while (ret >= 0 && ret < max_blocks) {
		struct ext4_map_blocks map;
		map.m_lblk = block += ret;
		map.m_len = max_blocks -= ret;

		ret = ext4_map_blocks(handle, ea_inode, &map,
				      EXT4_GET_BLOCKS_CREATE);
		if (ret <= 0) {
			ext4_mark_inode_dirty(handle, ea_inode);
			if (ret == -ENOSPC &&
			    ext4_should_retry_alloc(ea_inode->i_sb, &retries)) {
				ret = 0;
				goto retry;
			}
			break;
		}
	}

	if (ret < 0)
		return ret;

	block = 0;
	while (wsize < bufsize) {
		if (bh != NULL)
			brelse(bh);
		csize = (bufsize - wsize) > blocksize ? blocksize :
								bufsize - wsize;
		bh = ext4_getblk(handle, ea_inode, block, 0);
		if (IS_ERR(bh))
			return PTR_ERR(bh);
		ret = ext4_journal_get_write_access(handle, bh);
		if (ret)
			goto out;

		memcpy(bh->b_data, buf, csize);
		set_buffer_uptodate(bh);
		ext4_handle_dirty_metadata(handle, ea_inode, bh);

		buf += csize;
		wsize += csize;
		block += 1;
	}

	inode_lock(ea_inode);
	i_size_write(ea_inode, wsize);
	ext4_update_i_disksize(ea_inode, wsize);
	inode_unlock(ea_inode);

	ext4_mark_inode_dirty(handle, ea_inode);

out:
	brelse(bh);

	return ret;
}

/*
 * Create an inode to store the value of a large EA.
 */
static struct inode *ext4_xattr_inode_create(handle_t *handle,
					     struct inode *inode, u32 hash)
{
	struct inode *ea_inode = NULL;
	uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
	int err;

	/*
	 * Let the next inode be the goal, so we try and allocate the EA inode
	 * in the same group, or nearby one.
	 */
	ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
				  S_IFREG | 0600, NULL, inode->i_ino + 1, owner,
				  EXT4_EA_INODE_FL);
	if (!IS_ERR(ea_inode)) {
		ea_inode->i_op = &ext4_file_inode_operations;
		ea_inode->i_fop = &ext4_file_operations;
		ext4_set_aops(ea_inode);
		ext4_xattr_inode_set_class(ea_inode);
		unlock_new_inode(ea_inode);
		ext4_xattr_inode_set_ref(ea_inode, 1);
		ext4_xattr_inode_set_hash(ea_inode, hash);
		err = ext4_mark_inode_dirty(handle, ea_inode);
		if (!err)
			err = ext4_inode_attach_jinode(ea_inode);
		if (err) {
			iput(ea_inode);
			return ERR_PTR(err);
		}

		/*
		 * Xattr inodes are shared therefore quota charging is performed
		 * at a higher level.
		 */
		dquot_free_inode(ea_inode);
		dquot_drop(ea_inode);
		inode_lock(ea_inode);
		ea_inode->i_flags |= S_NOQUOTA;
		inode_unlock(ea_inode);
	}

	return ea_inode;
}

static struct inode *
ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
			    size_t value_len, u32 hash)
{
	struct inode *ea_inode;
	struct mb_cache_entry *ce;
	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
	void *ea_data;

	ce = mb_cache_entry_find_first(ea_inode_cache, hash);
	if (!ce)
		return NULL;

	ea_data = ext4_kvmalloc(value_len, GFP_NOFS);
	if (!ea_data) {
		mb_cache_entry_put(ea_inode_cache, ce);
		return NULL;
	}

	while (ce) {
		ea_inode = ext4_iget(inode->i_sb, ce->e_value);
		if (!IS_ERR(ea_inode) &&
		    !is_bad_inode(ea_inode) &&
		    (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) &&
		    i_size_read(ea_inode) == value_len &&
		    !ext4_xattr_inode_read(ea_inode, ea_data, value_len) &&
		    !ext4_xattr_inode_verify_hash(ea_inode, ea_data,
						  value_len) &&
		    !memcmp(value, ea_data, value_len)) {
			mb_cache_entry_touch(ea_inode_cache, ce);
			mb_cache_entry_put(ea_inode_cache, ce);
			kvfree(ea_data);
			return ea_inode;
		}

		if (!IS_ERR(ea_inode))
			iput(ea_inode);
		ce = mb_cache_entry_find_next(ea_inode_cache, ce);
	}
	kvfree(ea_data);
	return NULL;
}

/*
 * Add value of the EA in an inode.
 */
static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
					  const void *value, size_t value_len,
					  struct inode **ret_inode)
{
	struct inode *ea_inode;
	u32 hash;
	int err;

	hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len);
	ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash);
	if (ea_inode) {
		err = ext4_xattr_inode_inc_ref(handle, ea_inode);
		if (err) {
			iput(ea_inode);
			return err;
		}

		*ret_inode = ea_inode;
		return 0;
	}

	/* Create an inode for the EA value */
	ea_inode = ext4_xattr_inode_create(handle, inode, hash);
	if (IS_ERR(ea_inode))
		return PTR_ERR(ea_inode);

	err = ext4_xattr_inode_write(handle, ea_inode, value, value_len);
	if (err) {
		ext4_xattr_inode_dec_ref(handle, ea_inode);
		iput(ea_inode);
		return err;
	}

	mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
			      ea_inode->i_ino, true /* reusable */);

	*ret_inode = ea_inode;
	return 0;
}

static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
				struct ext4_xattr_search *s,
				handle_t *handle, struct inode *inode)
{
	struct ext4_xattr_entry *last;
	struct ext4_xattr_entry *here = s->here;
	size_t min_offs = s->end - s->base, name_len = strlen(i->name);
	int in_inode = i->in_inode;
	struct inode *old_ea_inode = NULL;
	struct inode *new_ea_inode = NULL;
	size_t old_size, new_size;
	int ret;

	/* Space used by old and new values. */
	old_size = (!s->not_found && !here->e_value_inum) ?
			EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0;
	new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0;

	/*
	 * Optimization for the simple case when old and new values have the
	 * same padded sizes. Not applicable if external inodes are involved.
	 */
	if (new_size && new_size == old_size) {
		size_t offs = le16_to_cpu(here->e_value_offs);
		void *val = s->base + offs;

		here->e_value_size = cpu_to_le32(i->value_len);
		if (i->value == EXT4_ZERO_XATTR_VALUE) {
			memset(val, 0, new_size);
		} else {
			memcpy(val, i->value, i->value_len);
			/* Clear padding bytes. */
			memset(val + i->value_len, 0, new_size - i->value_len);
		}
		return 0;
	}

	/* Compute min_offs and last. */
	last = s->first;
	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
		if (!last->e_value_inum && last->e_value_size) {
			size_t offs = le16_to_cpu(last->e_value_offs);
			if (offs < min_offs)
				min_offs = offs;
		}
	}

	/* Check whether we have enough space. */
	if (i->value) {
		size_t free;

		free = min_offs - ((void *)last - s->base) - sizeof(__u32);
		if (!s->not_found)
			free += EXT4_XATTR_LEN(name_len) + old_size;

		if (free < EXT4_XATTR_LEN(name_len) + new_size) {
			ret = -ENOSPC;
			goto out;
		}
	}

	/*
	 * Getting access to old and new ea inodes is subject to failures.
	 * Finish that work before doing any modifications to the xattr data.
	 */
	if (!s->not_found && here->e_value_inum) {
		ret = ext4_xattr_inode_iget(inode,
					    le32_to_cpu(here->e_value_inum),
					    &old_ea_inode);
		if (ret) {
			old_ea_inode = NULL;
			goto out;
		}
	}
	if (i->value && in_inode) {
		WARN_ON_ONCE(!i->value_len);

		ret = ext4_xattr_inode_alloc_quota(inode, i->value_len);
		if (ret)
			goto out;

		ret = ext4_xattr_inode_lookup_create(handle, inode, i->value,
						     i->value_len,
						     &new_ea_inode);
		if (ret) {
			new_ea_inode = NULL;
			ext4_xattr_inode_free_quota(inode, i->value_len);
			goto out;
		}
	}

	if (old_ea_inode) {
		/* We are ready to release ref count on the old_ea_inode. */
		ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode);
		if (ret) {
			/* Release newly required ref count on new_ea_inode. */
			if (new_ea_inode) {
				int err;

				err = ext4_xattr_inode_dec_ref(handle,
							       new_ea_inode);
				if (err)
					ext4_warning_inode(new_ea_inode,
						  "dec ref new_ea_inode err=%d",
						  err);
				ext4_xattr_inode_free_quota(inode,
							    i->value_len);
			}
			goto out;
		}

		ext4_xattr_inode_free_quota(inode,
					    le32_to_cpu(here->e_value_size));
	}

	/* No failures allowed past this point. */

	if (!s->not_found && here->e_value_offs) {
		/* Remove the old value. */
		void *first_val = s->base + min_offs;
		size_t offs = le16_to_cpu(here->e_value_offs);
		void *val = s->base + offs;

		memmove(first_val + old_size, first_val, val - first_val);
		memset(first_val, 0, old_size);
		min_offs += old_size;

		/* Adjust all value offsets. */
		last = s->first;
		while (!IS_LAST_ENTRY(last)) {
			size_t o = le16_to_cpu(last->e_value_offs);

			if (!last->e_value_inum &&
			    last->e_value_size && o < offs)
				last->e_value_offs = cpu_to_le16(o + old_size);
			last = EXT4_XATTR_NEXT(last);
		}
	}

	if (!i->value) {
		/* Remove old name. */
		size_t size = EXT4_XATTR_LEN(name_len);

		last = ENTRY((void *)last - size);
		memmove(here, (void *)here + size,
			(void *)last - (void *)here + sizeof(__u32));
		memset(last, 0, size);
	} else if (s->not_found) {
		/* Insert new name. */
		size_t size = EXT4_XATTR_LEN(name_len);
		size_t rest = (void *)last - (void *)here + sizeof(__u32);

		memmove((void *)here + size, here, rest);
		memset(here, 0, size);
		here->e_name_index = i->name_index;
		here->e_name_len = name_len;
		memcpy(here->e_name, i->name, name_len);
	} else {
		/* This is an update, reset value info. */
		here->e_value_inum = 0;
		here->e_value_offs = 0;
		here->e_value_size = 0;
	}

	if (i->value) {
		/* Insert new value. */
		if (in_inode) {
			here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino);
		} else if (i->value_len) {
			void *val = s->base + min_offs - new_size;

			here->e_value_offs = cpu_to_le16(min_offs - new_size);
			if (i->value == EXT4_ZERO_XATTR_VALUE) {
				memset(val, 0, new_size);
			} else {
				memcpy(val, i->value, i->value_len);
				/* Clear padding bytes. */
				memset(val + i->value_len, 0,
				       new_size - i->value_len);
			}
		}
		here->e_value_size = cpu_to_le32(i->value_len);
	}
	ret = 0;
out:
	iput(old_ea_inode);
	iput(new_ea_inode);
	return ret;
}

struct ext4_xattr_block_find {
	struct ext4_xattr_search s;
	struct buffer_head *bh;
};

static int
ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
		      struct ext4_xattr_block_find *bs)
{
	struct super_block *sb = inode->i_sb;
	int error;

	ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
		  i->name_index, i->name, i->value, (long)i->value_len);

	if (EXT4_I(inode)->i_file_acl) {
		/* The inode already has an extended attribute block. */
		bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl);
		error = -EIO;
		if (!bs->bh)
			goto cleanup;
		ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
			atomic_read(&(bs->bh->b_count)),
			le32_to_cpu(BHDR(bs->bh)->h_refcount));
		if (ext4_xattr_check_block(inode, bs->bh)) {
			EXT4_ERROR_INODE(inode, "bad block %llu",
					 EXT4_I(inode)->i_file_acl);
			error = -EFSCORRUPTED;
			goto cleanup;
		}
		/* Find the named attribute. */
		bs->s.base = BHDR(bs->bh);
		bs->s.first = BFIRST(bs->bh);
		bs->s.end = bs->bh->b_data + bs->bh->b_size;
		bs->s.here = bs->s.first;
		error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
					      i->name, 1);
		if (error && error != -ENODATA)
			goto cleanup;
		bs->s.not_found = error;
	}
	error = 0;

cleanup:
	return error;
}

static int
ext4_xattr_block_set(handle_t *handle, struct inode *inode,
		     struct ext4_xattr_info *i,
		     struct ext4_xattr_block_find *bs)
{
	struct super_block *sb = inode->i_sb;
	struct buffer_head *new_bh = NULL;
	struct ext4_xattr_search s_copy = bs->s;
	struct ext4_xattr_search *s = &s_copy;
	struct mb_cache_entry *ce = NULL;
	int error = 0;
	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
	struct inode *ea_inode = NULL;
	size_t old_ea_inode_size = 0;

#define header(x) ((struct ext4_xattr_header *)(x))

	if (s->base) {
		BUFFER_TRACE(bs->bh, "get_write_access");
		error = ext4_journal_get_write_access(handle, bs->bh);
		if (error)
			goto cleanup;
		lock_buffer(bs->bh);

		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
			__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);

			/*
			 * This must happen under buffer lock for
			 * ext4_xattr_block_set() to reliably detect modified
			 * block
			 */
			mb_cache_entry_delete(ea_block_cache, hash,
					      bs->bh->b_blocknr);
			ea_bdebug(bs->bh, "modifying in-place");
			error = ext4_xattr_set_entry(i, s, handle, inode);
			if (!error) {
				if (!IS_LAST_ENTRY(s->first))
					ext4_xattr_rehash(header(s->base),
							  s->here);
				ext4_xattr_block_cache_insert(ea_block_cache,
							      bs->bh);
			}
			ext4_xattr_block_csum_set(inode, bs->bh);
			unlock_buffer(bs->bh);
			if (error == -EFSCORRUPTED)
				goto bad_block;
			if (!error)
				error = ext4_handle_dirty_metadata(handle,
								   inode,
								   bs->bh);
			if (error)
				goto cleanup;
			goto inserted;
		} else {
			int offset = (char *)s->here - bs->bh->b_data;

			unlock_buffer(bs->bh);
			ea_bdebug(bs->bh, "cloning");
			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
			error = -ENOMEM;
			if (s->base == NULL)
				goto cleanup;
			memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
			s->first = ENTRY(header(s->base)+1);
			header(s->base)->h_refcount = cpu_to_le32(1);
			s->here = ENTRY(s->base + offset);
			s->end = s->base + bs->bh->b_size;

			/*
			 * If existing entry points to an xattr inode, we need
			 * to prevent ext4_xattr_set_entry() from decrementing
			 * ref count on it because the reference belongs to the
			 * original block. In this case, make the entry look
			 * like it has an empty value.
			 */
			if (!s->not_found && s->here->e_value_inum) {
				/*
				 * Defer quota free call for previous inode
				 * until success is guaranteed.
				 */
				old_ea_inode_size = le32_to_cpu(
							s->here->e_value_size);
				s->here->e_value_inum = 0;
				s->here->e_value_size = 0;
			}
		}
	} else {
		/* Allocate a buffer where we construct the new block. */
		s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
		/* assert(header == s->base) */
		error = -ENOMEM;
		if (s->base == NULL)
			goto cleanup;
		header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
		header(s->base)->h_blocks = cpu_to_le32(1);
		header(s->base)->h_refcount = cpu_to_le32(1);
		s->first = ENTRY(header(s->base)+1);
		s->here = ENTRY(header(s->base)+1);
		s->end = s->base + sb->s_blocksize;
	}

	error = ext4_xattr_set_entry(i, s, handle, inode);
	if (error == -EFSCORRUPTED)
		goto bad_block;
	if (error)
		goto cleanup;

	if (i->value && s->here->e_value_inum) {
		unsigned int ea_ino;

		/*
		 * A ref count on ea_inode has been taken as part of the call to
		 * ext4_xattr_set_entry() above. We would like to drop this
		 * extra ref but we have to wait until the xattr block is
		 * initialized and has its own ref count on the ea_inode.
		 */
		ea_ino = le32_to_cpu(s->here->e_value_inum);
		error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
		if (error) {
			ea_inode = NULL;
			goto cleanup;
		}
	}

	if (!IS_LAST_ENTRY(s->first))
		ext4_xattr_rehash(header(s->base), s->here);

inserted:
	if (!IS_LAST_ENTRY(s->first)) {
		new_bh = ext4_xattr_block_cache_find(inode, header(s->base),
						     &ce);
		if (new_bh) {
			/* We found an identical block in the cache. */
			if (new_bh == bs->bh)
				ea_bdebug(new_bh, "keeping");
			else {
				u32 ref;

				WARN_ON_ONCE(dquot_initialize_needed(inode));

				/* The old block is released after updating
				   the inode. */
				error = dquot_alloc_block(inode,
						EXT4_C2B(EXT4_SB(sb), 1));
				if (error)
					goto cleanup;
				BUFFER_TRACE(new_bh, "get_write_access");
				error = ext4_journal_get_write_access(handle,
								      new_bh);
				if (error)
					goto cleanup_dquot;
				lock_buffer(new_bh);
				/*
				 * We have to be careful about races with
				 * freeing, rehashing or adding references to
				 * xattr block. Once we hold buffer lock xattr
				 * block's state is stable so we can check
				 * whether the block got freed / rehashed or
				 * not.  Since we unhash mbcache entry under
				 * buffer lock when freeing / rehashing xattr
				 * block, checking whether entry is still
				 * hashed is reliable. Same rules hold for
				 * e_reusable handling.
				 */
				if (hlist_bl_unhashed(&ce->e_hash_list) ||
				    !ce->e_reusable) {
					/*
					 * Undo everything and check mbcache
					 * again.
					 */
					unlock_buffer(new_bh);
					dquot_free_block(inode,
							 EXT4_C2B(EXT4_SB(sb),
								  1));
					brelse(new_bh);
					mb_cache_entry_put(ea_block_cache, ce);
					ce = NULL;
					new_bh = NULL;
					goto inserted;
				}
				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
				BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
				if (ref >= EXT4_XATTR_REFCOUNT_MAX)
					ce->e_reusable = 0;
				ea_bdebug(new_bh, "reusing; refcount now=%d",
					  ref);
				ext4_xattr_block_csum_set(inode, new_bh);
				unlock_buffer(new_bh);
				error = ext4_handle_dirty_metadata(handle,
								   inode,
								   new_bh);
				if (error)
					goto cleanup_dquot;
			}
			mb_cache_entry_touch(ea_block_cache, ce);
			mb_cache_entry_put(ea_block_cache, ce);
			ce = NULL;
		} else if (bs->bh && s->base == bs->bh->b_data) {
			/* We were modifying this block in-place. */
			ea_bdebug(bs->bh, "keeping this block");
			new_bh = bs->bh;
			get_bh(new_bh);
		} else {
			/* We need to allocate a new block */
			ext4_fsblk_t goal, block;

			WARN_ON_ONCE(dquot_initialize_needed(inode));

			goal = ext4_group_first_block_no(sb,
						EXT4_I(inode)->i_block_group);

			/* non-extent files can't have physical blocks past 2^32 */
			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;

			block = ext4_new_meta_blocks(handle, inode, goal, 0,
						     NULL, &error);
			if (error)
				goto cleanup;

			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);

			ea_idebug(inode, "creating block %llu",
				  (unsigned long long)block);

			new_bh = sb_getblk(sb, block);
			if (unlikely(!new_bh)) {
				error = -ENOMEM;
getblk_failed:
				ext4_free_blocks(handle, inode, NULL, block, 1,
						 EXT4_FREE_BLOCKS_METADATA);
				goto cleanup;
			}
			error = ext4_xattr_inode_inc_ref_all(handle, inode,
						      ENTRY(header(s->base)+1));
			if (error)
				goto getblk_failed;
			if (ea_inode) {
				/* Drop the extra ref on ea_inode. */
				error = ext4_xattr_inode_dec_ref(handle,
								 ea_inode);
				if (error)
					ext4_warning_inode(ea_inode,
							   "dec ref error=%d",
							   error);
				iput(ea_inode);
				ea_inode = NULL;
			}

			lock_buffer(new_bh);
			error = ext4_journal_get_create_access(handle, new_bh);
			if (error) {
				unlock_buffer(new_bh);
				error = -EIO;
				goto getblk_failed;
			}
			memcpy(new_bh->b_data, s->base, new_bh->b_size);
			ext4_xattr_block_csum_set(inode, new_bh);
			set_buffer_uptodate(new_bh);
			unlock_buffer(new_bh);
			ext4_xattr_block_cache_insert(ea_block_cache, new_bh);
			error = ext4_handle_dirty_metadata(handle, inode,
							   new_bh);
			if (error)
				goto cleanup;
		}
	}

	if (old_ea_inode_size)
		ext4_xattr_inode_free_quota(inode, old_ea_inode_size);

	/* Update the inode. */
	EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;

	/* Drop the previous xattr block. */
	if (bs->bh && bs->bh != new_bh) {
		struct ext4_xattr_inode_array *ea_inode_array = NULL;

		ext4_xattr_release_block(handle, inode, bs->bh,
					 &ea_inode_array,
					 0 /* extra_credits */);
		ext4_xattr_inode_array_free(ea_inode_array);
	}
	error = 0;

cleanup:
	if (ea_inode) {
		int error2;

		error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
		if (error2)
			ext4_warning_inode(ea_inode, "dec ref error=%d",
					   error2);

		/* If there was an error, revert the quota charge. */
		if (error)
			ext4_xattr_inode_free_quota(inode,
						    i_size_read(ea_inode));
		iput(ea_inode);
	}
	if (ce)
		mb_cache_entry_put(ea_block_cache, ce);
	brelse(new_bh);
	if (!(bs->bh && s->base == bs->bh->b_data))
		kfree(s->base);

	return error;

cleanup_dquot:
	dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1));
	goto cleanup;

bad_block:
	EXT4_ERROR_INODE(inode, "bad block %llu",
			 EXT4_I(inode)->i_file_acl);
	goto cleanup;

#undef header
}

int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
			  struct ext4_xattr_ibody_find *is)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_inode *raw_inode;
	int error;

	if (EXT4_I(inode)->i_extra_isize == 0)
		return 0;
	raw_inode = ext4_raw_inode(&is->iloc);
	header = IHDR(inode, raw_inode);
	is->s.base = is->s.first = IFIRST(header);
	is->s.here = is->s.first;
	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
		error = xattr_check_inode(inode, header, is->s.end);
		if (error)
			return error;
		/* Find the named attribute. */
		error = ext4_xattr_find_entry(&is->s.here, i->name_index,
					      i->name, 0);
		if (error && error != -ENODATA)
			return error;
		is->s.not_found = error;
	}
	return 0;
}

int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
				struct ext4_xattr_info *i,
				struct ext4_xattr_ibody_find *is)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_search *s = &is->s;
	int error;

	if (EXT4_I(inode)->i_extra_isize == 0)
		return -ENOSPC;
	error = ext4_xattr_set_entry(i, s, handle, inode);
	if (error) {
		if (error == -ENOSPC &&
		    ext4_has_inline_data(inode)) {
			error = ext4_try_to_evict_inline_data(handle, inode,
					EXT4_XATTR_LEN(strlen(i->name) +
					EXT4_XATTR_SIZE(i->value_len)));
			if (error)
				return error;
			error = ext4_xattr_ibody_find(inode, i, is);
			if (error)
				return error;
			error = ext4_xattr_set_entry(i, s, handle, inode);
		}
		if (error)
			return error;
	}
	header = IHDR(inode, ext4_raw_inode(&is->iloc));
	if (!IS_LAST_ENTRY(s->first)) {
		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
	} else {
		header->h_magic = cpu_to_le32(0);
		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
	}
	return 0;
}

static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
				struct ext4_xattr_info *i,
				struct ext4_xattr_ibody_find *is)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_search *s = &is->s;
	int error;

	if (EXT4_I(inode)->i_extra_isize == 0)
		return -ENOSPC;
	error = ext4_xattr_set_entry(i, s, handle, inode);
	if (error)
		return error;
	header = IHDR(inode, ext4_raw_inode(&is->iloc));
	if (!IS_LAST_ENTRY(s->first)) {
		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
	} else {
		header->h_magic = cpu_to_le32(0);
		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
	}
	return 0;
}

static int ext4_xattr_value_same(struct ext4_xattr_search *s,
				 struct ext4_xattr_info *i)
{
	void *value;

	/* When e_value_inum is set the value is stored externally. */
	if (s->here->e_value_inum)
		return 0;
	if (le32_to_cpu(s->here->e_value_size) != i->value_len)
		return 0;
	value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs);
	return !memcmp(value, i->value, i->value_len);
}

static struct buffer_head *ext4_xattr_get_block(struct inode *inode)
{
	struct buffer_head *bh;
	int error;

	if (!EXT4_I(inode)->i_file_acl)
		return NULL;
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	if (!bh)
		return ERR_PTR(-EIO);
	error = ext4_xattr_check_block(inode, bh);
	if (error)
		return ERR_PTR(error);
	return bh;
}

/*
 * ext4_xattr_set_handle()
 *
 * Create, replace or remove an extended attribute for this inode.  Value
 * is NULL to remove an existing extended attribute, and non-NULL to
 * either replace an existing extended attribute, or create a new extended
 * attribute. The flags XATTR_REPLACE and XATTR_CREATE
 * specify that an extended attribute must exist and must not exist
 * previous to the call, respectively.
 *
 * Returns 0, or a negative error number on failure.
 */
int
ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
		      const char *name, const void *value, size_t value_len,
		      int flags)
{
	struct ext4_xattr_info i = {
		.name_index = name_index,
		.name = name,
		.value = value,
		.value_len = value_len,
		.in_inode = 0,
	};
	struct ext4_xattr_ibody_find is = {
		.s = { .not_found = -ENODATA, },
	};
	struct ext4_xattr_block_find bs = {
		.s = { .not_found = -ENODATA, },
	};
	int no_expand;
	int error;

	if (!name)
		return -EINVAL;
	if (strlen(name) > 255)
		return -ERANGE;

	ext4_write_lock_xattr(inode, &no_expand);

	/* Check journal credits under write lock. */
	if (ext4_handle_valid(handle)) {
		struct buffer_head *bh;
		int credits;

		bh = ext4_xattr_get_block(inode);
		if (IS_ERR(bh)) {
			error = PTR_ERR(bh);
			goto cleanup;
		}

		credits = __ext4_xattr_set_credits(inode, bh, value_len);
		brelse(bh);

		if (!ext4_handle_has_enough_credits(handle, credits)) {
			error = -ENOSPC;
			goto cleanup;
		}
	}

	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
	if (error)
		goto cleanup;

	if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
		struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
		ext4_clear_inode_state(inode, EXT4_STATE_NEW);
	}

	error = ext4_xattr_ibody_find(inode, &i, &is);
	if (error)
		goto cleanup;
	if (is.s.not_found)
		error = ext4_xattr_block_find(inode, &i, &bs);
	if (error)
		goto cleanup;
	if (is.s.not_found && bs.s.not_found) {
		error = -ENODATA;
		if (flags & XATTR_REPLACE)
			goto cleanup;
		error = 0;
		if (!value)
			goto cleanup;
	} else {
		error = -EEXIST;
		if (flags & XATTR_CREATE)
			goto cleanup;
	}

	if (!value) {
		if (!is.s.not_found)
			error = ext4_xattr_ibody_set(handle, inode, &i, &is);
		else if (!bs.s.not_found)
			error = ext4_xattr_block_set(handle, inode, &i, &bs);
	} else {
		error = 0;
		/* Xattr value did not change? Save us some work and bail out */
		if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i))
			goto cleanup;
		if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
			goto cleanup;

		if (ext4_has_feature_ea_inode(inode->i_sb) &&
		    (EXT4_XATTR_SIZE(i.value_len) >
			EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize)))
			i.in_inode = 1;
retry_inode:
		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
		if (!error && !bs.s.not_found) {
			i.value = NULL;
			error = ext4_xattr_block_set(handle, inode, &i, &bs);
		} else if (error == -ENOSPC) {
			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
				error = ext4_xattr_block_find(inode, &i, &bs);
				if (error)
					goto cleanup;
			}
			error = ext4_xattr_block_set(handle, inode, &i, &bs);
			if (!error && !is.s.not_found) {
				i.value = NULL;
				error = ext4_xattr_ibody_set(handle, inode, &i,
							     &is);
			} else if (error == -ENOSPC) {
				/*
				 * Xattr does not fit in the block, store at
				 * external inode if possible.
				 */
				if (ext4_has_feature_ea_inode(inode->i_sb) &&
				    !i.in_inode) {
					i.in_inode = 1;
					goto retry_inode;
				}
			}
		}
	}
	if (!error) {
		ext4_xattr_update_super_block(handle, inode->i_sb);
		inode->i_ctime = current_time(inode);
		if (!value)
			no_expand = 0;
		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
		/*
		 * The bh is consumed by ext4_mark_iloc_dirty, even with
		 * error != 0.
		 */
		is.iloc.bh = NULL;
		if (IS_SYNC(inode))
			ext4_handle_sync(handle);
	}

cleanup:
	brelse(is.iloc.bh);
	brelse(bs.bh);
	ext4_write_unlock_xattr(inode, &no_expand);
	return error;
}

int ext4_xattr_set_credits(struct inode *inode, size_t value_len, int *credits)
{
	struct buffer_head *bh;
	int err;

	*credits = 0;

	if (!EXT4_SB(inode->i_sb)->s_journal)
		return 0;

	down_read(&EXT4_I(inode)->xattr_sem);

	bh = ext4_xattr_get_block(inode);
	if (IS_ERR(bh)) {
		err = PTR_ERR(bh);
	} else {
		*credits = __ext4_xattr_set_credits(inode, bh, value_len);
		brelse(bh);
		err = 0;
	}

	up_read(&EXT4_I(inode)->xattr_sem);
	return err;
}

/*
 * ext4_xattr_set()
 *
 * Like ext4_xattr_set_handle, but start from an inode. This extended
 * attribute modification is a filesystem transaction by itself.
 *
 * Returns 0, or a negative error number on failure.
 */
int
ext4_xattr_set(struct inode *inode, int name_index, const char *name,
	       const void *value, size_t value_len, int flags)
{
	handle_t *handle;
	struct super_block *sb = inode->i_sb;
	int error, retries = 0;
	int credits;

	error = dquot_initialize(inode);
	if (error)
		return error;

retry:
	error = ext4_xattr_set_credits(inode, value_len, &credits);
	if (error)
		return error;

	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
	if (IS_ERR(handle)) {
		error = PTR_ERR(handle);
	} else {
		int error2;

		error = ext4_xattr_set_handle(handle, inode, name_index, name,
					      value, value_len, flags);
		error2 = ext4_journal_stop(handle);
		if (error == -ENOSPC &&
		    ext4_should_retry_alloc(sb, &retries))
			goto retry;
		if (error == 0)
			error = error2;
	}

	return error;
}

/*
 * Shift the EA entries in the inode to create space for the increased
 * i_extra_isize.
 */
static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
				     int value_offs_shift, void *to,
				     void *from, size_t n)
{
	struct ext4_xattr_entry *last = entry;
	int new_offs;

	/* We always shift xattr headers further thus offsets get lower */
	BUG_ON(value_offs_shift > 0);

	/* Adjust the value offsets of the entries */
	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
		if (!last->e_value_inum && last->e_value_size) {
			new_offs = le16_to_cpu(last->e_value_offs) +
							value_offs_shift;
			last->e_value_offs = cpu_to_le16(new_offs);
		}
	}
	/* Shift the entries by n bytes */
	memmove(to, from, n);
}

/*
 * Move xattr pointed to by 'entry' from inode into external xattr block
 */
static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
				    struct ext4_inode *raw_inode,
				    struct ext4_xattr_entry *entry)
{
	struct ext4_xattr_ibody_find *is = NULL;
	struct ext4_xattr_block_find *bs = NULL;
	char *buffer = NULL, *b_entry_name = NULL;
	size_t value_size = le32_to_cpu(entry->e_value_size);
	struct ext4_xattr_info i = {
		.value = NULL,
		.value_len = 0,
		.name_index = entry->e_name_index,
		.in_inode = !!entry->e_value_inum,
	};
	struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
	int error;

	is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
	bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
	buffer = kmalloc(value_size, GFP_NOFS);
	b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
	if (!is || !bs || !buffer || !b_entry_name) {
		error = -ENOMEM;
		goto out;
	}

	is->s.not_found = -ENODATA;
	bs->s.not_found = -ENODATA;
	is->iloc.bh = NULL;
	bs->bh = NULL;

	/* Save the entry name and the entry value */
	if (entry->e_value_inum) {
		error = ext4_xattr_inode_get(inode,
					     le32_to_cpu(entry->e_value_inum),
					     buffer, value_size);
		if (error)
			goto out;
	} else {
		size_t value_offs = le16_to_cpu(entry->e_value_offs);
		memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
	}

	memcpy(b_entry_name, entry->e_name, entry->e_name_len);
	b_entry_name[entry->e_name_len] = '\0';
	i.name = b_entry_name;

	error = ext4_get_inode_loc(inode, &is->iloc);
	if (error)
		goto out;

	error = ext4_xattr_ibody_find(inode, &i, is);
	if (error)
		goto out;

	/* Remove the chosen entry from the inode */
	error = ext4_xattr_ibody_set(handle, inode, &i, is);
	if (error)
		goto out;

	i.value = buffer;
	i.value_len = value_size;
	error = ext4_xattr_block_find(inode, &i, bs);
	if (error)
		goto out;

	/* Add entry which was removed from the inode into the block */
	error = ext4_xattr_block_set(handle, inode, &i, bs);
	if (error)
		goto out;
	error = 0;
out:
	kfree(b_entry_name);
	kfree(buffer);
	if (is)
		brelse(is->iloc.bh);
	kfree(is);
	kfree(bs);

	return error;
}

static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
				       struct ext4_inode *raw_inode,
				       int isize_diff, size_t ifree,
				       size_t bfree, int *total_ino)
{
	struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
	struct ext4_xattr_entry *small_entry;
	struct ext4_xattr_entry *entry;
	struct ext4_xattr_entry *last;
	unsigned int entry_size;	/* EA entry size */
	unsigned int total_size;	/* EA entry size + value size */
	unsigned int min_total_size;
	int error;

	while (isize_diff > ifree) {
		entry = NULL;
		small_entry = NULL;
		min_total_size = ~0U;
		last = IFIRST(header);
		/* Find the entry best suited to be pushed into EA block */
		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
			total_size = EXT4_XATTR_LEN(last->e_name_len);
			if (!last->e_value_inum)
				total_size += EXT4_XATTR_SIZE(
					       le32_to_cpu(last->e_value_size));
			if (total_size <= bfree &&
			    total_size < min_total_size) {
				if (total_size + ifree < isize_diff) {
					small_entry = last;
				} else {
					entry = last;
					min_total_size = total_size;
				}
			}
		}

		if (entry == NULL) {
			if (small_entry == NULL)
				return -ENOSPC;
			entry = small_entry;
		}

		entry_size = EXT4_XATTR_LEN(entry->e_name_len);
		total_size = entry_size;
		if (!entry->e_value_inum)
			total_size += EXT4_XATTR_SIZE(
					      le32_to_cpu(entry->e_value_size));
		error = ext4_xattr_move_to_block(handle, inode, raw_inode,
						 entry);
		if (error)
			return error;

		*total_ino -= entry_size;
		ifree += total_size;
		bfree -= total_size;
	}

	return 0;
}

/*
 * Expand an inode by new_extra_isize bytes when EAs are present.
 * Returns 0 on success or negative error number on failure.
 */
int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
			       struct ext4_inode *raw_inode, handle_t *handle)
{
	struct ext4_xattr_ibody_header *header;
	struct buffer_head *bh = NULL;
	size_t min_offs;
	size_t ifree, bfree;
	int total_ino;
	void *base, *end;
	int error = 0, tried_min_extra_isize = 0;
	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
	int isize_diff;	/* How much do we need to grow i_extra_isize */
	int no_expand;

	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
		return 0;

retry:
	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
		goto out;

	header = IHDR(inode, raw_inode);

	/*
	 * Check if enough free space is available in the inode to shift the
	 * entries ahead by new_extra_isize.
	 */

	base = IFIRST(header);
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	min_offs = end - base;
	total_ino = sizeof(struct ext4_xattr_ibody_header);

	error = xattr_check_inode(inode, header, end);
	if (error)
		goto cleanup;

	ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino);
	if (ifree >= isize_diff)
		goto shift;

	/*
	 * Enough free space isn't available in the inode, check if
	 * EA block can hold new_extra_isize bytes.
	 */
	if (EXT4_I(inode)->i_file_acl) {
		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
		error = -EIO;
		if (!bh)
			goto cleanup;
		if (ext4_xattr_check_block(inode, bh)) {
			EXT4_ERROR_INODE(inode, "bad block %llu",
					 EXT4_I(inode)->i_file_acl);
			error = -EFSCORRUPTED;
			goto cleanup;
		}
		base = BHDR(bh);
		end = bh->b_data + bh->b_size;
		min_offs = end - base;
		bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base,
					      NULL);
		if (bfree + ifree < isize_diff) {
			if (!tried_min_extra_isize && s_min_extra_isize) {
				tried_min_extra_isize++;
				new_extra_isize = s_min_extra_isize;
				brelse(bh);
				goto retry;
			}
			error = -ENOSPC;
			goto cleanup;
		}
	} else {
		bfree = inode->i_sb->s_blocksize;
	}

	error = ext4_xattr_make_inode_space(handle, inode, raw_inode,
					    isize_diff, ifree, bfree,
					    &total_ino);
	if (error) {
		if (error == -ENOSPC && !tried_min_extra_isize &&
		    s_min_extra_isize) {
			tried_min_extra_isize++;
			new_extra_isize = s_min_extra_isize;
			brelse(bh);
			goto retry;
		}
		goto cleanup;
	}
shift:
	/* Adjust the offsets and shift the remaining entries ahead */
	ext4_xattr_shift_entries(IFIRST(header), EXT4_I(inode)->i_extra_isize
			- new_extra_isize, (void *)raw_inode +
			EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
			(void *)header, total_ino);
	EXT4_I(inode)->i_extra_isize = new_extra_isize;
	brelse(bh);
out:
	ext4_write_unlock_xattr(inode, &no_expand);
	return 0;

cleanup:
	brelse(bh);
	/*
	 * Inode size expansion failed; don't try again
	 */
	no_expand = 1;
	ext4_write_unlock_xattr(inode, &no_expand);
	return error;
}

#define EIA_INCR 16 /* must be 2^n */
#define EIA_MASK (EIA_INCR - 1)

/* Add the large xattr @inode into @ea_inode_array for deferred iput().
 * If @ea_inode_array is new or full it will be grown and the old
 * contents copied over.
 */
static int
ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
			struct inode *inode)
{
	if (*ea_inode_array == NULL) {
		/*
		 * Start with 15 inodes, so it fits into a power-of-two size.
		 * If *ea_inode_array is NULL, this is essentially offsetof()
		 */
		(*ea_inode_array) =
			kmalloc(offsetof(struct ext4_xattr_inode_array,
					 inodes[EIA_MASK]),
				GFP_NOFS);
		if (*ea_inode_array == NULL)
			return -ENOMEM;
		(*ea_inode_array)->count = 0;
	} else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) {
		/* expand the array once all 15 + n * 16 slots are full */
		struct ext4_xattr_inode_array *new_array = NULL;
		int count = (*ea_inode_array)->count;

		/* if new_array is NULL, this is essentially offsetof() */
		new_array = kmalloc(
				offsetof(struct ext4_xattr_inode_array,
					 inodes[count + EIA_INCR]),
				GFP_NOFS);
		if (new_array == NULL)
			return -ENOMEM;
		memcpy(new_array, *ea_inode_array,
		       offsetof(struct ext4_xattr_inode_array, inodes[count]));
		kfree(*ea_inode_array);
		*ea_inode_array = new_array;
	}
	(*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode;
	return 0;
}

/*
 * ext4_xattr_delete_inode()
 *
 * Free extended attribute resources associated with this inode. Traverse
 * all entries and decrement reference on any xattr inodes associated with this
 * inode. This is called immediately before an inode is freed. We have exclusive
 * access to the inode. If an orphan inode is deleted it will also release its
 * references on xattr block and xattr inodes.
 */
int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
			    struct ext4_xattr_inode_array **ea_inode_array,
			    int extra_credits)
{
	struct buffer_head *bh = NULL;
	struct ext4_xattr_ibody_header *header;
	struct ext4_iloc iloc = { .bh = NULL };
	struct ext4_xattr_entry *entry;
	int error;

	error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
					  NULL /* bh */,
					  false /* dirty */,
					  false /* block_csum */);
	if (error) {
		EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error);
		goto cleanup;
	}

	if (ext4_has_feature_ea_inode(inode->i_sb) &&
	    ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {

		error = ext4_get_inode_loc(inode, &iloc);
		if (error) {
			EXT4_ERROR_INODE(inode, "inode loc (error %d)", error);
			goto cleanup;
		}

		error = ext4_journal_get_write_access(handle, iloc.bh);
		if (error) {
			EXT4_ERROR_INODE(inode, "write access (error %d)",
					 error);
			goto cleanup;
		}

		header = IHDR(inode, ext4_raw_inode(&iloc));
		if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC))
			ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh,
						     IFIRST(header),
						     false /* block_csum */,
						     ea_inode_array,
						     extra_credits,
						     false /* skip_quota */);
	}

	if (EXT4_I(inode)->i_file_acl) {
		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
		if (!bh) {
			EXT4_ERROR_INODE(inode, "block %llu read error",
					 EXT4_I(inode)->i_file_acl);
			error = -EIO;
			goto cleanup;
		}
		error = ext4_xattr_check_block(inode, bh);
		if (error) {
			EXT4_ERROR_INODE(inode, "bad block %llu (error %d)",
					 EXT4_I(inode)->i_file_acl, error);
			goto cleanup;
		}

		if (ext4_has_feature_ea_inode(inode->i_sb)) {
			for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
			     entry = EXT4_XATTR_NEXT(entry))
				if (entry->e_value_inum)
					ext4_xattr_inode_free_quota(inode,
					      le32_to_cpu(entry->e_value_size));

		}

		ext4_xattr_release_block(handle, inode, bh, ea_inode_array,
					 extra_credits);
		/*
		 * Update i_file_acl value in the same transaction that releases
		 * block.
		 */
		EXT4_I(inode)->i_file_acl = 0;
		error = ext4_mark_inode_dirty(handle, inode);
		if (error) {
			EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
					 error);
			goto cleanup;
		}
	}
	error = 0;
cleanup:
	brelse(iloc.bh);
	brelse(bh);
	return error;
}

void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array)
{
	int idx;

	if (ea_inode_array == NULL)
		return;

	for (idx = 0; idx < ea_inode_array->count; ++idx)
		iput(ea_inode_array->inodes[idx]);
	kfree(ea_inode_array);
}

/*
 * ext4_xattr_block_cache_insert()
 *
 * Create a new entry in the extended attribute block cache, and insert
 * it unless such an entry is already in the cache.
 *
 * Returns 0, or a negative error number on failure.
 */
static void
ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
			      struct buffer_head *bh)
{
	struct ext4_xattr_header *header = BHDR(bh);
	__u32 hash = le32_to_cpu(header->h_hash);
	int reusable = le32_to_cpu(header->h_refcount) <
		       EXT4_XATTR_REFCOUNT_MAX;
	int error;

	error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash,
				      bh->b_blocknr, reusable);
	if (error) {
		if (error == -EBUSY)
			ea_bdebug(bh, "already in cache");
	} else
		ea_bdebug(bh, "inserting [%x]", (int)hash);
}

/*
 * ext4_xattr_cmp()
 *
 * Compare two extended attribute blocks for equality.
 *
 * Returns 0 if the blocks are equal, 1 if they differ, and
 * a negative error number on errors.
 */
static int
ext4_xattr_cmp(struct ext4_xattr_header *header1,
	       struct ext4_xattr_header *header2)
{
	struct ext4_xattr_entry *entry1, *entry2;

	entry1 = ENTRY(header1+1);
	entry2 = ENTRY(header2+1);
	while (!IS_LAST_ENTRY(entry1)) {
		if (IS_LAST_ENTRY(entry2))
			return 1;
		if (entry1->e_hash != entry2->e_hash ||
		    entry1->e_name_index != entry2->e_name_index ||
		    entry1->e_name_len != entry2->e_name_len ||
		    entry1->e_value_size != entry2->e_value_size ||
		    entry1->e_value_inum != entry2->e_value_inum ||
		    memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
			return 1;
		if (!entry1->e_value_inum &&
		    memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
			   (char *)header2 + le16_to_cpu(entry2->e_value_offs),
			   le32_to_cpu(entry1->e_value_size)))
			return 1;

		entry1 = EXT4_XATTR_NEXT(entry1);
		entry2 = EXT4_XATTR_NEXT(entry2);
	}
	if (!IS_LAST_ENTRY(entry2))
		return 1;
	return 0;
}

/*
 * ext4_xattr_block_cache_find()
 *
 * Find an identical extended attribute block.
 *
 * Returns a pointer to the block found, or NULL if such a block was
 * not found or an error occurred.
 */
static struct buffer_head *
ext4_xattr_block_cache_find(struct inode *inode,
			    struct ext4_xattr_header *header,
			    struct mb_cache_entry **pce)
{
	__u32 hash = le32_to_cpu(header->h_hash);
	struct mb_cache_entry *ce;
	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);

	if (!header->h_hash)
		return NULL;  /* never share */
	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
	ce = mb_cache_entry_find_first(ea_block_cache, hash);
	while (ce) {
		struct buffer_head *bh;

		bh = sb_bread(inode->i_sb, ce->e_value);
		if (!bh) {
			EXT4_ERROR_INODE(inode, "block %lu read error",
					 (unsigned long)ce->e_value);
		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
			*pce = ce;
			return bh;
		}
		brelse(bh);
		ce = mb_cache_entry_find_next(ea_block_cache, ce);
	}
	return NULL;
}

#define NAME_HASH_SHIFT 5
#define VALUE_HASH_SHIFT 16

/*
 * ext4_xattr_hash_entry()
 *
 * Compute the hash of an extended attribute.
 */
static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
					 struct ext4_xattr_entry *entry)
{
	__u32 hash = 0;
	char *name = entry->e_name;
	int n;

	for (n = 0; n < entry->e_name_len; n++) {
		hash = (hash << NAME_HASH_SHIFT) ^
		       (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
		       *name++;
	}

	if (!entry->e_value_inum && entry->e_value_size) {
		__le32 *value = (__le32 *)((char *)header +
			le16_to_cpu(entry->e_value_offs));
		for (n = (le32_to_cpu(entry->e_value_size) +
		     EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
			hash = (hash << VALUE_HASH_SHIFT) ^
			       (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
			       le32_to_cpu(*value++);
		}
	}
	entry->e_hash = cpu_to_le32(hash);
}

#undef NAME_HASH_SHIFT
#undef VALUE_HASH_SHIFT

#define BLOCK_HASH_SHIFT 16

/*
 * ext4_xattr_rehash()
 *
 * Re-compute the extended attribute hash value after an entry has changed.
 */
static void ext4_xattr_rehash(struct ext4_xattr_header *header,
			      struct ext4_xattr_entry *entry)
{
	struct ext4_xattr_entry *here;
	__u32 hash = 0;

	ext4_xattr_hash_entry(header, entry);
	here = ENTRY(header+1);
	while (!IS_LAST_ENTRY(here)) {
		if (!here->e_hash) {
			/* Block is not shared if an entry's hash value == 0 */
			hash = 0;
			break;
		}
		hash = (hash << BLOCK_HASH_SHIFT) ^
		       (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^
		       le32_to_cpu(here->e_hash);
		here = EXT4_XATTR_NEXT(here);
	}
	header->h_hash = cpu_to_le32(hash);
}

#undef BLOCK_HASH_SHIFT

#define	HASH_BUCKET_BITS	10

struct mb_cache *
ext4_xattr_create_cache(void)
{
	return mb_cache_create(HASH_BUCKET_BITS);
}

void ext4_xattr_destroy_cache(struct mb_cache *cache)
{
	if (cache)
		mb_cache_destroy(cache);
}