summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_ioctl.c
blob: affa557c233704bc327cff86a851471ccfef586b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_rtalloc.h"
#include "xfs_iwalk.h"
#include "xfs_itable.h"
#include "xfs_error.h"
#include "xfs_attr.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_fsops.h"
#include "xfs_discard.h"
#include "xfs_quota.h"
#include "xfs_export.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_trans.h"
#include "xfs_acl.h"
#include "xfs_btree.h"
#include <linux/fsmap.h>
#include "xfs_fsmap.h"
#include "scrub/xfs_scrub.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_health.h"

#include <linux/mount.h>
#include <linux/namei.h>

/*
 * xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
 * a file or fs handle.
 *
 * XFS_IOC_PATH_TO_FSHANDLE
 *    returns fs handle for a mount point or path within that mount point
 * XFS_IOC_FD_TO_HANDLE
 *    returns full handle for a FD opened in user space
 * XFS_IOC_PATH_TO_HANDLE
 *    returns full handle for a path
 */
int
xfs_find_handle(
	unsigned int		cmd,
	xfs_fsop_handlereq_t	*hreq)
{
	int			hsize;
	xfs_handle_t		handle;
	struct inode		*inode;
	struct fd		f = {NULL};
	struct path		path;
	int			error;
	struct xfs_inode	*ip;

	if (cmd == XFS_IOC_FD_TO_HANDLE) {
		f = fdget(hreq->fd);
		if (!f.file)
			return -EBADF;
		inode = file_inode(f.file);
	} else {
		error = user_path_at(AT_FDCWD, hreq->path, 0, &path);
		if (error)
			return error;
		inode = d_inode(path.dentry);
	}
	ip = XFS_I(inode);

	/*
	 * We can only generate handles for inodes residing on a XFS filesystem,
	 * and only for regular files, directories or symbolic links.
	 */
	error = -EINVAL;
	if (inode->i_sb->s_magic != XFS_SB_MAGIC)
		goto out_put;

	error = -EBADF;
	if (!S_ISREG(inode->i_mode) &&
	    !S_ISDIR(inode->i_mode) &&
	    !S_ISLNK(inode->i_mode))
		goto out_put;


	memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t));

	if (cmd == XFS_IOC_PATH_TO_FSHANDLE) {
		/*
		 * This handle only contains an fsid, zero the rest.
		 */
		memset(&handle.ha_fid, 0, sizeof(handle.ha_fid));
		hsize = sizeof(xfs_fsid_t);
	} else {
		handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
					sizeof(handle.ha_fid.fid_len);
		handle.ha_fid.fid_pad = 0;
		handle.ha_fid.fid_gen = inode->i_generation;
		handle.ha_fid.fid_ino = ip->i_ino;
		hsize = sizeof(xfs_handle_t);
	}

	error = -EFAULT;
	if (copy_to_user(hreq->ohandle, &handle, hsize) ||
	    copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32)))
		goto out_put;

	error = 0;

 out_put:
	if (cmd == XFS_IOC_FD_TO_HANDLE)
		fdput(f);
	else
		path_put(&path);
	return error;
}

/*
 * No need to do permission checks on the various pathname components
 * as the handle operations are privileged.
 */
STATIC int
xfs_handle_acceptable(
	void			*context,
	struct dentry		*dentry)
{
	return 1;
}

/*
 * Convert userspace handle data into a dentry.
 */
struct dentry *
xfs_handle_to_dentry(
	struct file		*parfilp,
	void __user		*uhandle,
	u32			hlen)
{
	xfs_handle_t		handle;
	struct xfs_fid64	fid;

	/*
	 * Only allow handle opens under a directory.
	 */
	if (!S_ISDIR(file_inode(parfilp)->i_mode))
		return ERR_PTR(-ENOTDIR);

	if (hlen != sizeof(xfs_handle_t))
		return ERR_PTR(-EINVAL);
	if (copy_from_user(&handle, uhandle, hlen))
		return ERR_PTR(-EFAULT);
	if (handle.ha_fid.fid_len !=
	    sizeof(handle.ha_fid) - sizeof(handle.ha_fid.fid_len))
		return ERR_PTR(-EINVAL);

	memset(&fid, 0, sizeof(struct fid));
	fid.ino = handle.ha_fid.fid_ino;
	fid.gen = handle.ha_fid.fid_gen;

	return exportfs_decode_fh(parfilp->f_path.mnt, (struct fid *)&fid, 3,
			FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG,
			xfs_handle_acceptable, NULL);
}

STATIC struct dentry *
xfs_handlereq_to_dentry(
	struct file		*parfilp,
	xfs_fsop_handlereq_t	*hreq)
{
	return xfs_handle_to_dentry(parfilp, hreq->ihandle, hreq->ihandlen);
}

int
xfs_open_by_handle(
	struct file		*parfilp,
	xfs_fsop_handlereq_t	*hreq)
{
	const struct cred	*cred = current_cred();
	int			error;
	int			fd;
	int			permflag;
	struct file		*filp;
	struct inode		*inode;
	struct dentry		*dentry;
	fmode_t			fmode;
	struct path		path;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	dentry = xfs_handlereq_to_dentry(parfilp, hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	inode = d_inode(dentry);

	/* Restrict xfs_open_by_handle to directories & regular files. */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
		error = -EPERM;
		goto out_dput;
	}

#if BITS_PER_LONG != 32
	hreq->oflags |= O_LARGEFILE;
#endif

	permflag = hreq->oflags;
	fmode = OPEN_FMODE(permflag);
	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
	    (fmode & FMODE_WRITE) && IS_APPEND(inode)) {
		error = -EPERM;
		goto out_dput;
	}

	if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
		error = -EPERM;
		goto out_dput;
	}

	/* Can't write directories. */
	if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
		error = -EISDIR;
		goto out_dput;
	}

	fd = get_unused_fd_flags(0);
	if (fd < 0) {
		error = fd;
		goto out_dput;
	}

	path.mnt = parfilp->f_path.mnt;
	path.dentry = dentry;
	filp = dentry_open(&path, hreq->oflags, cred);
	dput(dentry);
	if (IS_ERR(filp)) {
		put_unused_fd(fd);
		return PTR_ERR(filp);
	}

	if (S_ISREG(inode->i_mode)) {
		filp->f_flags |= O_NOATIME;
		filp->f_mode |= FMODE_NOCMTIME;
	}

	fd_install(fd, filp);
	return fd;

 out_dput:
	dput(dentry);
	return error;
}

int
xfs_readlink_by_handle(
	struct file		*parfilp,
	xfs_fsop_handlereq_t	*hreq)
{
	struct dentry		*dentry;
	__u32			olen;
	int			error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	dentry = xfs_handlereq_to_dentry(parfilp, hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	/* Restrict this handle operation to symlinks only. */
	if (!d_is_symlink(dentry)) {
		error = -EINVAL;
		goto out_dput;
	}

	if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) {
		error = -EFAULT;
		goto out_dput;
	}

	error = vfs_readlink(dentry, hreq->ohandle, olen);

 out_dput:
	dput(dentry);
	return error;
}

int
xfs_set_dmattrs(
	xfs_inode_t     *ip,
	uint		evmask,
	uint16_t	state)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_trans_t	*tp;
	int		error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		return error;

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

	ip->i_d.di_dmevmask = evmask;
	ip->i_d.di_dmstate  = state;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	error = xfs_trans_commit(tp);

	return error;
}

STATIC int
xfs_fssetdm_by_handle(
	struct file		*parfilp,
	void			__user *arg)
{
	int			error;
	struct fsdmidata	fsd;
	xfs_fsop_setdm_handlereq_t dmhreq;
	struct dentry		*dentry;

	if (!capable(CAP_MKNOD))
		return -EPERM;
	if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
		return -EFAULT;

	error = mnt_want_write_file(parfilp);
	if (error)
		return error;

	dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
	if (IS_ERR(dentry)) {
		mnt_drop_write_file(parfilp);
		return PTR_ERR(dentry);
	}

	if (IS_IMMUTABLE(d_inode(dentry)) || IS_APPEND(d_inode(dentry))) {
		error = -EPERM;
		goto out;
	}

	if (copy_from_user(&fsd, dmhreq.data, sizeof(fsd))) {
		error = -EFAULT;
		goto out;
	}

	error = xfs_set_dmattrs(XFS_I(d_inode(dentry)), fsd.fsd_dmevmask,
				 fsd.fsd_dmstate);

 out:
	mnt_drop_write_file(parfilp);
	dput(dentry);
	return error;
}

STATIC int
xfs_attrlist_by_handle(
	struct file		*parfilp,
	void			__user *arg)
{
	int			error = -ENOMEM;
	attrlist_cursor_kern_t	*cursor;
	struct xfs_fsop_attrlist_handlereq __user	*p = arg;
	xfs_fsop_attrlist_handlereq_t al_hreq;
	struct dentry		*dentry;
	char			*kbuf;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
		return -EFAULT;
	if (al_hreq.buflen < sizeof(struct attrlist) ||
	    al_hreq.buflen > XFS_XATTR_LIST_MAX)
		return -EINVAL;

	/*
	 * Reject flags, only allow namespaces.
	 */
	if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE))
		return -EINVAL;

	dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	kbuf = kmem_zalloc_large(al_hreq.buflen, KM_SLEEP);
	if (!kbuf)
		goto out_dput;

	cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
	error = xfs_attr_list(XFS_I(d_inode(dentry)), kbuf, al_hreq.buflen,
					al_hreq.flags, cursor);
	if (error)
		goto out_kfree;

	if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
		error = -EFAULT;
		goto out_kfree;
	}

	if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
		error = -EFAULT;

out_kfree:
	kmem_free(kbuf);
out_dput:
	dput(dentry);
	return error;
}

int
xfs_attrmulti_attr_get(
	struct inode		*inode,
	unsigned char		*name,
	unsigned char		__user *ubuf,
	uint32_t		*len,
	uint32_t		flags)
{
	unsigned char		*kbuf;
	int			error = -EFAULT;

	if (*len > XFS_XATTR_SIZE_MAX)
		return -EINVAL;
	kbuf = kmem_zalloc_large(*len, KM_SLEEP);
	if (!kbuf)
		return -ENOMEM;

	error = xfs_attr_get(XFS_I(inode), name, kbuf, (int *)len, flags);
	if (error)
		goto out_kfree;

	if (copy_to_user(ubuf, kbuf, *len))
		error = -EFAULT;

out_kfree:
	kmem_free(kbuf);
	return error;
}

int
xfs_attrmulti_attr_set(
	struct inode		*inode,
	unsigned char		*name,
	const unsigned char	__user *ubuf,
	uint32_t		len,
	uint32_t		flags)
{
	unsigned char		*kbuf;
	int			error;

	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		return -EPERM;
	if (len > XFS_XATTR_SIZE_MAX)
		return -EINVAL;

	kbuf = memdup_user(ubuf, len);
	if (IS_ERR(kbuf))
		return PTR_ERR(kbuf);

	error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
	if (!error)
		xfs_forget_acl(inode, name, flags);
	kfree(kbuf);
	return error;
}

int
xfs_attrmulti_attr_remove(
	struct inode		*inode,
	unsigned char		*name,
	uint32_t		flags)
{
	int			error;

	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		return -EPERM;
	error = xfs_attr_remove(XFS_I(inode), name, flags);
	if (!error)
		xfs_forget_acl(inode, name, flags);
	return error;
}

STATIC int
xfs_attrmulti_by_handle(
	struct file		*parfilp,
	void			__user *arg)
{
	int			error;
	xfs_attr_multiop_t	*ops;
	xfs_fsop_attrmulti_handlereq_t am_hreq;
	struct dentry		*dentry;
	unsigned int		i, size;
	unsigned char		*attr_name;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t)))
		return -EFAULT;

	/* overflow check */
	if (am_hreq.opcount >= INT_MAX / sizeof(xfs_attr_multiop_t))
		return -E2BIG;

	dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	error = -E2BIG;
	size = am_hreq.opcount * sizeof(xfs_attr_multiop_t);
	if (!size || size > 16 * PAGE_SIZE)
		goto out_dput;

	ops = memdup_user(am_hreq.ops, size);
	if (IS_ERR(ops)) {
		error = PTR_ERR(ops);
		goto out_dput;
	}

	error = -ENOMEM;
	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
	if (!attr_name)
		goto out_kfree_ops;

	error = 0;
	for (i = 0; i < am_hreq.opcount; i++) {
		ops[i].am_error = strncpy_from_user((char *)attr_name,
				ops[i].am_attrname, MAXNAMELEN);
		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
			error = -ERANGE;
		if (ops[i].am_error < 0)
			break;

		switch (ops[i].am_opcode) {
		case ATTR_OP_GET:
			ops[i].am_error = xfs_attrmulti_attr_get(
					d_inode(dentry), attr_name,
					ops[i].am_attrvalue, &ops[i].am_length,
					ops[i].am_flags);
			break;
		case ATTR_OP_SET:
			ops[i].am_error = mnt_want_write_file(parfilp);
			if (ops[i].am_error)
				break;
			ops[i].am_error = xfs_attrmulti_attr_set(
					d_inode(dentry), attr_name,
					ops[i].am_attrvalue, ops[i].am_length,
					ops[i].am_flags);
			mnt_drop_write_file(parfilp);
			break;
		case ATTR_OP_REMOVE:
			ops[i].am_error = mnt_want_write_file(parfilp);
			if (ops[i].am_error)
				break;
			ops[i].am_error = xfs_attrmulti_attr_remove(
					d_inode(dentry), attr_name,
					ops[i].am_flags);
			mnt_drop_write_file(parfilp);
			break;
		default:
			ops[i].am_error = -EINVAL;
		}
	}

	if (copy_to_user(am_hreq.ops, ops, size))
		error = -EFAULT;

	kfree(attr_name);
 out_kfree_ops:
	kfree(ops);
 out_dput:
	dput(dentry);
	return error;
}

int
xfs_ioc_space(
	struct file		*filp,
	unsigned int		cmd,
	xfs_flock64_t		*bf)
{
	struct inode		*inode = file_inode(filp);
	struct xfs_inode	*ip = XFS_I(inode);
	struct iattr		iattr;
	enum xfs_prealloc_flags	flags = 0;
	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
	int			error;

	if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
		return -EPERM;

	if (!(filp->f_mode & FMODE_WRITE))
		return -EBADF;

	if (!S_ISREG(inode->i_mode))
		return -EINVAL;

	if (filp->f_flags & O_DSYNC)
		flags |= XFS_PREALLOC_SYNC;
	if (filp->f_mode & FMODE_NOCMTIME)
		flags |= XFS_PREALLOC_INVISIBLE;

	error = mnt_want_write_file(filp);
	if (error)
		return error;

	xfs_ilock(ip, iolock);
	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
	if (error)
		goto out_unlock;

	switch (bf->l_whence) {
	case 0: /*SEEK_SET*/
		break;
	case 1: /*SEEK_CUR*/
		bf->l_start += filp->f_pos;
		break;
	case 2: /*SEEK_END*/
		bf->l_start += XFS_ISIZE(ip);
		break;
	default:
		error = -EINVAL;
		goto out_unlock;
	}

	/*
	 * length of <= 0 for resv/unresv/zero is invalid.  length for
	 * alloc/free is ignored completely and we have no idea what userspace
	 * might have set it to, so set it to zero to allow range
	 * checks to pass.
	 */
	switch (cmd) {
	case XFS_IOC_ZERO_RANGE:
	case XFS_IOC_RESVSP:
	case XFS_IOC_RESVSP64:
	case XFS_IOC_UNRESVSP:
	case XFS_IOC_UNRESVSP64:
		if (bf->l_len <= 0) {
			error = -EINVAL;
			goto out_unlock;
		}
		break;
	default:
		bf->l_len = 0;
		break;
	}

	if (bf->l_start < 0 ||
	    bf->l_start > inode->i_sb->s_maxbytes ||
	    bf->l_start + bf->l_len < 0 ||
	    bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
		error = -EINVAL;
		goto out_unlock;
	}

	switch (cmd) {
	case XFS_IOC_ZERO_RANGE:
		flags |= XFS_PREALLOC_SET;
		error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
		break;
	case XFS_IOC_RESVSP:
	case XFS_IOC_RESVSP64:
		flags |= XFS_PREALLOC_SET;
		error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
						XFS_BMAPI_PREALLOC);
		break;
	case XFS_IOC_UNRESVSP:
	case XFS_IOC_UNRESVSP64:
		error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
		break;
	case XFS_IOC_ALLOCSP:
	case XFS_IOC_ALLOCSP64:
	case XFS_IOC_FREESP:
	case XFS_IOC_FREESP64:
		flags |= XFS_PREALLOC_CLEAR;
		if (bf->l_start > XFS_ISIZE(ip)) {
			error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
					bf->l_start - XFS_ISIZE(ip), 0);
			if (error)
				goto out_unlock;
		}

		iattr.ia_valid = ATTR_SIZE;
		iattr.ia_size = bf->l_start;

		error = xfs_vn_setattr_size(file_dentry(filp), &iattr);
		break;
	default:
		ASSERT(0);
		error = -EINVAL;
	}

	if (error)
		goto out_unlock;

	error = xfs_update_prealloc_flags(ip, flags);

out_unlock:
	xfs_iunlock(ip, iolock);
	mnt_drop_write_file(filp);
	return error;
}

/* Return 0 on success or positive error */
int
xfs_fsbulkstat_one_fmt(
	struct xfs_ibulk		*breq,
	const struct xfs_bulkstat	*bstat)
{
	struct xfs_bstat		bs1;

	xfs_bulkstat_to_bstat(breq->mp, &bs1, bstat);
	if (copy_to_user(breq->ubuffer, &bs1, sizeof(bs1)))
		return -EFAULT;
	return xfs_ibulk_advance(breq, sizeof(struct xfs_bstat));
}

int
xfs_fsinumbers_fmt(
	struct xfs_ibulk		*breq,
	const struct xfs_inumbers	*igrp)
{
	struct xfs_inogrp		ig1;

	xfs_inumbers_to_inogrp(&ig1, igrp);
	if (copy_to_user(breq->ubuffer, &ig1, sizeof(struct xfs_inogrp)))
		return -EFAULT;
	return xfs_ibulk_advance(breq, sizeof(struct xfs_inogrp));
}

STATIC int
xfs_ioc_fsbulkstat(
	xfs_mount_t		*mp,
	unsigned int		cmd,
	void			__user *arg)
{
	struct xfs_fsop_bulkreq	bulkreq;
	struct xfs_ibulk	breq = {
		.mp		= mp,
		.ocount		= 0,
	};
	xfs_ino_t		lastino;
	int			error;

	/* done = 1 if there are more stats to get and if bulkstat */
	/* should be called again (unused here, but used in dmapi) */

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (copy_from_user(&bulkreq, arg, sizeof(struct xfs_fsop_bulkreq)))
		return -EFAULT;

	if (copy_from_user(&lastino, bulkreq.lastip, sizeof(__s64)))
		return -EFAULT;

	if (bulkreq.icount <= 0)
		return -EINVAL;

	if (bulkreq.ubuffer == NULL)
		return -EINVAL;

	breq.ubuffer = bulkreq.ubuffer;
	breq.icount = bulkreq.icount;

	/*
	 * FSBULKSTAT_SINGLE expects that *lastip contains the inode number
	 * that we want to stat.  However, FSINUMBERS and FSBULKSTAT expect
	 * that *lastip contains either zero or the number of the last inode to
	 * be examined by the previous call and return results starting with
	 * the next inode after that.  The new bulk request back end functions
	 * take the inode to start with, so we have to compute the startino
	 * parameter from lastino to maintain correct function.  lastino == 0
	 * is a special case because it has traditionally meant "first inode
	 * in filesystem".
	 */
	if (cmd == XFS_IOC_FSINUMBERS) {
		breq.startino = lastino ? lastino + 1 : 0;
		error = xfs_inumbers(&breq, xfs_fsinumbers_fmt);
		lastino = breq.startino - 1;
	} else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) {
		breq.startino = lastino;
		breq.icount = 1;
		error = xfs_bulkstat_one(&breq, xfs_fsbulkstat_one_fmt);
	} else {	/* XFS_IOC_FSBULKSTAT */
		breq.startino = lastino ? lastino + 1 : 0;
		error = xfs_bulkstat(&breq, xfs_fsbulkstat_one_fmt);
		lastino = breq.startino - 1;
	}

	if (error)
		return error;

	if (bulkreq.lastip != NULL &&
	    copy_to_user(bulkreq.lastip, &lastino, sizeof(xfs_ino_t)))
		return -EFAULT;

	if (bulkreq.ocount != NULL &&
	    copy_to_user(bulkreq.ocount, &breq.ocount, sizeof(__s32)))
		return -EFAULT;

	return 0;
}

/* Return 0 on success or positive error */
static int
xfs_bulkstat_fmt(
	struct xfs_ibulk		*breq,
	const struct xfs_bulkstat	*bstat)
{
	if (copy_to_user(breq->ubuffer, bstat, sizeof(struct xfs_bulkstat)))
		return -EFAULT;
	return xfs_ibulk_advance(breq, sizeof(struct xfs_bulkstat));
}

/*
 * Check the incoming bulk request @hdr from userspace and initialize the
 * internal @breq bulk request appropriately.  Returns 0 if the bulk request
 * should proceed; XFS_ITER_ABORT if there's nothing to do; or the usual
 * negative error code.
 */
static int
xfs_bulk_ireq_setup(
	struct xfs_mount	*mp,
	struct xfs_bulk_ireq	*hdr,
	struct xfs_ibulk	*breq,
	void __user		*ubuffer)
{
	if (hdr->icount == 0 ||
	    (hdr->flags & ~XFS_BULK_IREQ_FLAGS_ALL) ||
	    memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
		return -EINVAL;

	breq->startino = hdr->ino;
	breq->ubuffer = ubuffer;
	breq->icount = hdr->icount;
	breq->ocount = 0;
	breq->flags = 0;

	/*
	 * The @ino parameter is a special value, so we must look it up here.
	 * We're not allowed to have IREQ_AGNO, and we only return one inode
	 * worth of data.
	 */
	if (hdr->flags & XFS_BULK_IREQ_SPECIAL) {
		if (hdr->flags & XFS_BULK_IREQ_AGNO)
			return -EINVAL;

		switch (hdr->ino) {
		case XFS_BULK_IREQ_SPECIAL_ROOT:
			hdr->ino = mp->m_sb.sb_rootino;
			break;
		default:
			return -EINVAL;
		}
		breq->icount = 1;
	}

	/*
	 * The IREQ_AGNO flag means that we only want results from a given AG.
	 * If @hdr->ino is zero, we start iterating in that AG.  If @hdr->ino is
	 * beyond the specified AG then we return no results.
	 */
	if (hdr->flags & XFS_BULK_IREQ_AGNO) {
		if (hdr->agno >= mp->m_sb.sb_agcount)
			return -EINVAL;

		if (breq->startino == 0)
			breq->startino = XFS_AGINO_TO_INO(mp, hdr->agno, 0);
		else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno)
			return -EINVAL;

		breq->flags |= XFS_IBULK_SAME_AG;

		/* Asking for an inode past the end of the AG?  We're done! */
		if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno)
			return XFS_ITER_ABORT;
	} else if (hdr->agno)
		return -EINVAL;

	/* Asking for an inode past the end of the FS?  We're done! */
	if (XFS_INO_TO_AGNO(mp, breq->startino) >= mp->m_sb.sb_agcount)
		return XFS_ITER_ABORT;

	return 0;
}

/*
 * Update the userspace bulk request @hdr to reflect the end state of the
 * internal bulk request @breq.
 */
static void
xfs_bulk_ireq_teardown(
	struct xfs_bulk_ireq	*hdr,
	struct xfs_ibulk	*breq)
{
	hdr->ino = breq->startino;
	hdr->ocount = breq->ocount;
}

/* Handle the v5 bulkstat ioctl. */
STATIC int
xfs_ioc_bulkstat(
	struct xfs_mount		*mp,
	unsigned int			cmd,
	struct xfs_bulkstat_req __user	*arg)
{
	struct xfs_bulk_ireq		hdr;
	struct xfs_ibulk		breq = {
		.mp			= mp,
	};
	int				error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr)))
		return -EFAULT;

	error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->bulkstat);
	if (error == XFS_ITER_ABORT)
		goto out_teardown;
	if (error < 0)
		return error;

	error = xfs_bulkstat(&breq, xfs_bulkstat_fmt);
	if (error)
		return error;

out_teardown:
	xfs_bulk_ireq_teardown(&hdr, &breq);
	if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr)))
		return -EFAULT;

	return 0;
}

STATIC int
xfs_inumbers_fmt(
	struct xfs_ibulk		*breq,
	const struct xfs_inumbers	*igrp)
{
	if (copy_to_user(breq->ubuffer, igrp, sizeof(struct xfs_inumbers)))
		return -EFAULT;
	return xfs_ibulk_advance(breq, sizeof(struct xfs_inumbers));
}

/* Handle the v5 inumbers ioctl. */
STATIC int
xfs_ioc_inumbers(
	struct xfs_mount		*mp,
	unsigned int			cmd,
	struct xfs_inumbers_req __user	*arg)
{
	struct xfs_bulk_ireq		hdr;
	struct xfs_ibulk		breq = {
		.mp			= mp,
	};
	int				error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr)))
		return -EFAULT;

	error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers);
	if (error == XFS_ITER_ABORT)
		goto out_teardown;
	if (error < 0)
		return error;

	error = xfs_inumbers(&breq, xfs_inumbers_fmt);
	if (error)
		return error;

out_teardown:
	xfs_bulk_ireq_teardown(&hdr, &breq);
	if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr)))
		return -EFAULT;

	return 0;
}

STATIC int
xfs_ioc_fsgeometry(
	struct xfs_mount	*mp,
	void			__user *arg,
	int			struct_version)
{
	struct xfs_fsop_geom	fsgeo;
	size_t			len;

	xfs_fs_geometry(&mp->m_sb, &fsgeo, struct_version);

	if (struct_version <= 3)
		len = sizeof(struct xfs_fsop_geom_v1);
	else if (struct_version == 4)
		len = sizeof(struct xfs_fsop_geom_v4);
	else {
		xfs_fsop_geom_health(mp, &fsgeo);
		len = sizeof(fsgeo);
	}

	if (copy_to_user(arg, &fsgeo, len))
		return -EFAULT;
	return 0;
}

STATIC int
xfs_ioc_ag_geometry(
	struct xfs_mount	*mp,
	void			__user *arg)
{
	struct xfs_ag_geometry	ageo;
	int			error;

	if (copy_from_user(&ageo, arg, sizeof(ageo)))
		return -EFAULT;

	error = xfs_ag_get_geometry(mp, ageo.ag_number, &ageo);
	if (error)
		return error;

	if (copy_to_user(arg, &ageo, sizeof(ageo)))
		return -EFAULT;
	return 0;
}

/*
 * Linux extended inode flags interface.
 */

STATIC unsigned int
xfs_merge_ioc_xflags(
	unsigned int	flags,
	unsigned int	start)
{
	unsigned int	xflags = start;

	if (flags & FS_IMMUTABLE_FL)
		xflags |= FS_XFLAG_IMMUTABLE;
	else
		xflags &= ~FS_XFLAG_IMMUTABLE;
	if (flags & FS_APPEND_FL)
		xflags |= FS_XFLAG_APPEND;
	else
		xflags &= ~FS_XFLAG_APPEND;
	if (flags & FS_SYNC_FL)
		xflags |= FS_XFLAG_SYNC;
	else
		xflags &= ~FS_XFLAG_SYNC;
	if (flags & FS_NOATIME_FL)
		xflags |= FS_XFLAG_NOATIME;
	else
		xflags &= ~FS_XFLAG_NOATIME;
	if (flags & FS_NODUMP_FL)
		xflags |= FS_XFLAG_NODUMP;
	else
		xflags &= ~FS_XFLAG_NODUMP;

	return xflags;
}

STATIC unsigned int
xfs_di2lxflags(
	uint16_t	di_flags)
{
	unsigned int	flags = 0;

	if (di_flags & XFS_DIFLAG_IMMUTABLE)
		flags |= FS_IMMUTABLE_FL;
	if (di_flags & XFS_DIFLAG_APPEND)
		flags |= FS_APPEND_FL;
	if (di_flags & XFS_DIFLAG_SYNC)
		flags |= FS_SYNC_FL;
	if (di_flags & XFS_DIFLAG_NOATIME)
		flags |= FS_NOATIME_FL;
	if (di_flags & XFS_DIFLAG_NODUMP)
		flags |= FS_NODUMP_FL;
	return flags;
}

static void
xfs_fill_fsxattr(
	struct xfs_inode	*ip,
	bool			attr,
	struct fsxattr		*fa)
{
	simple_fill_fsxattr(fa, xfs_ip2xflags(ip));
	fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
	fa->fsx_cowextsize = ip->i_d.di_cowextsize <<
			ip->i_mount->m_sb.sb_blocklog;
	fa->fsx_projid = xfs_get_projid(ip);

	if (attr) {
		if (ip->i_afp) {
			if (ip->i_afp->if_flags & XFS_IFEXTENTS)
				fa->fsx_nextents = xfs_iext_count(ip->i_afp);
			else
				fa->fsx_nextents = ip->i_d.di_anextents;
		} else
			fa->fsx_nextents = 0;
	} else {
		if (ip->i_df.if_flags & XFS_IFEXTENTS)
			fa->fsx_nextents = xfs_iext_count(&ip->i_df);
		else
			fa->fsx_nextents = ip->i_d.di_nextents;
	}
}

STATIC int
xfs_ioc_fsgetxattr(
	xfs_inode_t		*ip,
	int			attr,
	void			__user *arg)
{
	struct fsxattr		fa;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	xfs_fill_fsxattr(ip, attr, &fa);
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	if (copy_to_user(arg, &fa, sizeof(fa)))
		return -EFAULT;
	return 0;
}

STATIC uint16_t
xfs_flags2diflags(
	struct xfs_inode	*ip,
	unsigned int		xflags)
{
	/* can't set PREALLOC this way, just preserve it */
	uint16_t		di_flags =
		(ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);

	if (xflags & FS_XFLAG_IMMUTABLE)
		di_flags |= XFS_DIFLAG_IMMUTABLE;
	if (xflags & FS_XFLAG_APPEND)
		di_flags |= XFS_DIFLAG_APPEND;
	if (xflags & FS_XFLAG_SYNC)
		di_flags |= XFS_DIFLAG_SYNC;
	if (xflags & FS_XFLAG_NOATIME)
		di_flags |= XFS_DIFLAG_NOATIME;
	if (xflags & FS_XFLAG_NODUMP)
		di_flags |= XFS_DIFLAG_NODUMP;
	if (xflags & FS_XFLAG_NODEFRAG)
		di_flags |= XFS_DIFLAG_NODEFRAG;
	if (xflags & FS_XFLAG_FILESTREAM)
		di_flags |= XFS_DIFLAG_FILESTREAM;
	if (S_ISDIR(VFS_I(ip)->i_mode)) {
		if (xflags & FS_XFLAG_RTINHERIT)
			di_flags |= XFS_DIFLAG_RTINHERIT;
		if (xflags & FS_XFLAG_NOSYMLINKS)
			di_flags |= XFS_DIFLAG_NOSYMLINKS;
		if (xflags & FS_XFLAG_EXTSZINHERIT)
			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
		if (xflags & FS_XFLAG_PROJINHERIT)
			di_flags |= XFS_DIFLAG_PROJINHERIT;
	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
		if (xflags & FS_XFLAG_REALTIME)
			di_flags |= XFS_DIFLAG_REALTIME;
		if (xflags & FS_XFLAG_EXTSIZE)
			di_flags |= XFS_DIFLAG_EXTSIZE;
	}

	return di_flags;
}

STATIC uint64_t
xfs_flags2diflags2(
	struct xfs_inode	*ip,
	unsigned int		xflags)
{
	uint64_t		di_flags2 =
		(ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK);

	if (xflags & FS_XFLAG_DAX)
		di_flags2 |= XFS_DIFLAG2_DAX;
	if (xflags & FS_XFLAG_COWEXTSIZE)
		di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;

	return di_flags2;
}

STATIC void
xfs_diflags_to_linux(
	struct xfs_inode	*ip)
{
	struct inode		*inode = VFS_I(ip);
	unsigned int		xflags = xfs_ip2xflags(ip);

	if (xflags & FS_XFLAG_IMMUTABLE)
		inode->i_flags |= S_IMMUTABLE;
	else
		inode->i_flags &= ~S_IMMUTABLE;
	if (xflags & FS_XFLAG_APPEND)
		inode->i_flags |= S_APPEND;
	else
		inode->i_flags &= ~S_APPEND;
	if (xflags & FS_XFLAG_SYNC)
		inode->i_flags |= S_SYNC;
	else
		inode->i_flags &= ~S_SYNC;
	if (xflags & FS_XFLAG_NOATIME)
		inode->i_flags |= S_NOATIME;
	else
		inode->i_flags &= ~S_NOATIME;
#if 0	/* disabled until the flag switching races are sorted out */
	if (xflags & FS_XFLAG_DAX)
		inode->i_flags |= S_DAX;
	else
		inode->i_flags &= ~S_DAX;
#endif
}

static int
xfs_ioctl_setattr_xflags(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	struct fsxattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	uint64_t		di_flags2;

	/* Can't change realtime flag if any extents are allocated. */
	if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
		return -EINVAL;

	/* If realtime flag is set then must have realtime device */
	if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
		    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
			return -EINVAL;
	}

	/* Clear reflink if we are actually able to set the rt flag. */
	if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;

	/* Don't allow us to set DAX mode for a reflinked file for now. */
	if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
		return -EINVAL;

	/* diflags2 only valid for v3 inodes. */
	di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
	if (di_flags2 && ip->i_d.di_version < 3)
		return -EINVAL;

	ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags);
	ip->i_d.di_flags2 = di_flags2;

	xfs_diflags_to_linux(ip);
	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	XFS_STATS_INC(mp, xs_ig_attrchg);
	return 0;
}

/*
 * If we are changing DAX flags, we have to ensure the file is clean and any
 * cached objects in the address space are invalidated and removed. This
 * requires us to lock out other IO and page faults similar to a truncate
 * operation. The locks need to be held until the transaction has been committed
 * so that the cache invalidation is atomic with respect to the DAX flag
 * manipulation.
 */
static int
xfs_ioctl_setattr_dax_invalidate(
	struct xfs_inode	*ip,
	struct fsxattr		*fa,
	int			*join_flags)
{
	struct inode		*inode = VFS_I(ip);
	struct super_block	*sb = inode->i_sb;
	int			error;

	*join_flags = 0;

	/*
	 * It is only valid to set the DAX flag on regular files and
	 * directories on filesystems where the block size is equal to the page
	 * size. On directories it serves as an inherited hint so we don't
	 * have to check the device for dax support or flush pagecache.
	 */
	if (fa->fsx_xflags & FS_XFLAG_DAX) {
		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
			return -EINVAL;
		if (S_ISREG(inode->i_mode) &&
		    !bdev_dax_supported(xfs_find_bdev_for_inode(VFS_I(ip)),
				sb->s_blocksize))
			return -EINVAL;
	}

	/* If the DAX state is not changing, we have nothing to do here. */
	if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
		return 0;
	if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
		return 0;

	if (S_ISDIR(inode->i_mode))
		return 0;

	/* lock, flush and invalidate mapping in preparation for flag change */
	xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
	error = filemap_write_and_wait(inode->i_mapping);
	if (error)
		goto out_unlock;
	error = invalidate_inode_pages2(inode->i_mapping);
	if (error)
		goto out_unlock;

	*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
	return 0;

out_unlock:
	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
	return error;

}

/*
 * Set up the transaction structure for the setattr operation, checking that we
 * have permission to do so. On success, return a clean transaction and the
 * inode locked exclusively ready for further operation specific checks. On
 * failure, return an error without modifying or locking the inode.
 *
 * The inode might already be IO locked on call. If this is the case, it is
 * indicated in @join_flags and we take full responsibility for ensuring they
 * are unlocked from now on. Hence if we have an error here, we still have to
 * unlock them. Otherwise, once they are joined to the transaction, they will
 * be unlocked on commit/cancel.
 */
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
	struct xfs_inode	*ip,
	int			join_flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error = -EROFS;

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		goto out_unlock;
	error = -EIO;
	if (XFS_FORCED_SHUTDOWN(mp))
		goto out_unlock;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		goto out_unlock;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
	join_flags = 0;

	/*
	 * CAP_FOWNER overrides the following restrictions:
	 *
	 * The user ID of the calling process must be equal to the file owner
	 * ID, except in cases where the CAP_FSETID capability is applicable.
	 */
	if (!inode_owner_or_capable(VFS_I(ip))) {
		error = -EPERM;
		goto out_cancel;
	}

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

	return tp;

out_cancel:
	xfs_trans_cancel(tp);
out_unlock:
	if (join_flags)
		xfs_iunlock(ip, join_flags);
	return ERR_PTR(error);
}

/*
 * extent size hint validation is somewhat cumbersome. Rules are:
 *
 * 1. extent size hint is only valid for directories and regular files
 * 2. FS_XFLAG_EXTSIZE is only valid for regular files
 * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories.
 * 4. can only be changed on regular files if no extents are allocated
 * 5. can be changed on directories at any time
 * 6. extsize hint of 0 turns off hints, clears inode flags.
 * 7. Extent size must be a multiple of the appropriate block size.
 * 8. for non-realtime files, the extent size hint must be limited
 *    to half the AG size to avoid alignment extending the extent beyond the
 *    limits of the AG.
 *
 * Please keep this function in sync with xfs_scrub_inode_extsize.
 */
static int
xfs_ioctl_setattr_check_extsize(
	struct xfs_inode	*ip,
	struct fsxattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_extlen_t		size;
	xfs_fsblock_t		extsize_fsb;

	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
		return -EINVAL;

	if (fa->fsx_extsize == 0)
		return 0;

	extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
	if (extsize_fsb > MAXEXTLEN)
		return -EINVAL;

	if (XFS_IS_REALTIME_INODE(ip) ||
	    (fa->fsx_xflags & FS_XFLAG_REALTIME)) {
		size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
	} else {
		size = mp->m_sb.sb_blocksize;
		if (extsize_fsb > mp->m_sb.sb_agblocks / 2)
			return -EINVAL;
	}

	if (fa->fsx_extsize % size)
		return -EINVAL;

	return 0;
}

/*
 * CoW extent size hint validation rules are:
 *
 * 1. CoW extent size hint can only be set if reflink is enabled on the fs.
 *    The inode does not have to have any shared blocks, but it must be a v3.
 * 2. FS_XFLAG_COWEXTSIZE is only valid for directories and regular files;
 *    for a directory, the hint is propagated to new files.
 * 3. Can be changed on files & directories at any time.
 * 4. CoW extsize hint of 0 turns off hints, clears inode flags.
 * 5. Extent size must be a multiple of the appropriate block size.
 * 6. The extent size hint must be limited to half the AG size to avoid
 *    alignment extending the extent beyond the limits of the AG.
 *
 * Please keep this function in sync with xfs_scrub_inode_cowextsize.
 */
static int
xfs_ioctl_setattr_check_cowextsize(
	struct xfs_inode	*ip,
	struct fsxattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_extlen_t		size;
	xfs_fsblock_t		cowextsize_fsb;

	if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE))
		return 0;

	if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb) ||
	    ip->i_d.di_version != 3)
		return -EINVAL;

	if (fa->fsx_cowextsize == 0)
		return 0;

	cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
	if (cowextsize_fsb > MAXEXTLEN)
		return -EINVAL;

	size = mp->m_sb.sb_blocksize;
	if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2)
		return -EINVAL;

	if (fa->fsx_cowextsize % size)
		return -EINVAL;

	return 0;
}

static int
xfs_ioctl_setattr_check_projid(
	struct xfs_inode	*ip,
	struct fsxattr		*fa)
{
	/* Disallow 32bit project ids if projid32bit feature is not enabled. */
	if (fa->fsx_projid > (uint16_t)-1 &&
	    !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
		return -EINVAL;
	return 0;
}

STATIC int
xfs_ioctl_setattr(
	xfs_inode_t		*ip,
	struct fsxattr		*fa)
{
	struct fsxattr		old_fa;
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	struct xfs_dquot	*udqp = NULL;
	struct xfs_dquot	*pdqp = NULL;
	struct xfs_dquot	*olddquot = NULL;
	int			code;
	int			join_flags = 0;

	trace_xfs_ioctl_setattr(ip);

	code = xfs_ioctl_setattr_check_projid(ip, fa);
	if (code)
		return code;

	/*
	 * If disk quotas is on, we make sure that the dquots do exist on disk,
	 * before we start any other transactions. Trying to do this later
	 * is messy. We don't care to take a readlock to look at the ids
	 * in inode here, because we can't hold it across the trans_reserve.
	 * If the IDs do change before we take the ilock, we're covered
	 * because the i_*dquot fields will get updated anyway.
	 */
	if (XFS_IS_QUOTA_ON(mp)) {
		code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
					 ip->i_d.di_gid, fa->fsx_projid,
					 XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp);
		if (code)
			return code;
	}

	/*
	 * Changing DAX config may require inode locking for mapping
	 * invalidation. These need to be held all the way to transaction commit
	 * or cancel time, so need to be passed through to
	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
	 * appropriately.
	 */
	code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
	if (code)
		goto error_free_dquots;

	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
	if (IS_ERR(tp)) {
		code = PTR_ERR(tp);
		goto error_free_dquots;
	}

	if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) &&
	    xfs_get_projid(ip) != fa->fsx_projid) {
		code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp,
				capable(CAP_FOWNER) ?  XFS_QMOPT_FORCE_RES : 0);
		if (code)	/* out of quota */
			goto error_trans_cancel;
	}

	xfs_fill_fsxattr(ip, false, &old_fa);
	code = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa);
	if (code)
		goto error_trans_cancel;

	code = xfs_ioctl_setattr_check_extsize(ip, fa);
	if (code)
		goto error_trans_cancel;

	code = xfs_ioctl_setattr_check_cowextsize(ip, fa);
	if (code)
		goto error_trans_cancel;

	code = xfs_ioctl_setattr_xflags(tp, ip, fa);
	if (code)
		goto error_trans_cancel;

	/*
	 * Change file ownership.  Must be the owner or privileged.  CAP_FSETID
	 * overrides the following restrictions:
	 *
	 * The set-user-ID and set-group-ID bits of a file will be cleared upon
	 * successful return from chown()
	 */

	if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);

	/* Change the ownerships and register project quota modifications */
	if (xfs_get_projid(ip) != fa->fsx_projid) {
		if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
			olddquot = xfs_qm_vop_chown(tp, ip,
						&ip->i_pdquot, pdqp);
		}
		ASSERT(ip->i_d.di_version > 1);
		xfs_set_projid(ip, fa->fsx_projid);
	}

	/*
	 * Only set the extent size hint if we've already determined that the
	 * extent size hint should be set on the inode. If no extent size flags
	 * are set on the inode then unconditionally clear the extent size hint.
	 */
	if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
	else
		ip->i_d.di_extsize = 0;
	if (ip->i_d.di_version == 3 &&
	    (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
		ip->i_d.di_cowextsize = fa->fsx_cowextsize >>
				mp->m_sb.sb_blocklog;
	else
		ip->i_d.di_cowextsize = 0;

	code = xfs_trans_commit(tp);

	/*
	 * Release any dquot(s) the inode had kept before chown.
	 */
	xfs_qm_dqrele(olddquot);
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(pdqp);

	return code;

error_trans_cancel:
	xfs_trans_cancel(tp);
error_free_dquots:
	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(pdqp);
	return code;
}

STATIC int
xfs_ioc_fssetxattr(
	xfs_inode_t		*ip,
	struct file		*filp,
	void			__user *arg)
{
	struct fsxattr		fa;
	int error;

	if (copy_from_user(&fa, arg, sizeof(fa)))
		return -EFAULT;

	error = mnt_want_write_file(filp);
	if (error)
		return error;
	error = xfs_ioctl_setattr(ip, &fa);
	mnt_drop_write_file(filp);
	return error;
}

STATIC int
xfs_ioc_getxflags(
	xfs_inode_t		*ip,
	void			__user *arg)
{
	unsigned int		flags;

	flags = xfs_di2lxflags(ip->i_d.di_flags);
	if (copy_to_user(arg, &flags, sizeof(flags)))
		return -EFAULT;
	return 0;
}

STATIC int
xfs_ioc_setxflags(
	struct xfs_inode	*ip,
	struct file		*filp,
	void			__user *arg)
{
	struct xfs_trans	*tp;
	struct fsxattr		fa;
	struct fsxattr		old_fa;
	unsigned int		flags;
	int			join_flags = 0;
	int			error;

	if (copy_from_user(&flags, arg, sizeof(flags)))
		return -EFAULT;

	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
		      FS_NOATIME_FL | FS_NODUMP_FL | \
		      FS_SYNC_FL))
		return -EOPNOTSUPP;

	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));

	error = mnt_want_write_file(filp);
	if (error)
		return error;

	/*
	 * Changing DAX config may require inode locking for mapping
	 * invalidation. These need to be held all the way to transaction commit
	 * or cancel time, so need to be passed through to
	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
	 * appropriately.
	 */
	error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags);
	if (error)
		goto out_drop_write;

	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
	if (IS_ERR(tp)) {
		error = PTR_ERR(tp);
		goto out_drop_write;
	}

	xfs_fill_fsxattr(ip, false, &old_fa);
	error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, &fa);
	if (error) {
		xfs_trans_cancel(tp);
		goto out_drop_write;
	}

	error = xfs_ioctl_setattr_xflags(tp, ip, &fa);
	if (error) {
		xfs_trans_cancel(tp);
		goto out_drop_write;
	}

	error = xfs_trans_commit(tp);
out_drop_write:
	mnt_drop_write_file(filp);
	return error;
}

static bool
xfs_getbmap_format(
	struct kgetbmap		*p,
	struct getbmapx __user	*u,
	size_t			recsize)
{
	if (put_user(p->bmv_offset, &u->bmv_offset) ||
	    put_user(p->bmv_block, &u->bmv_block) ||
	    put_user(p->bmv_length, &u->bmv_length) ||
	    put_user(0, &u->bmv_count) ||
	    put_user(0, &u->bmv_entries))
		return false;
	if (recsize < sizeof(struct getbmapx))
		return true;
	if (put_user(0, &u->bmv_iflags) ||
	    put_user(p->bmv_oflags, &u->bmv_oflags) ||
	    put_user(0, &u->bmv_unused1) ||
	    put_user(0, &u->bmv_unused2))
		return false;
	return true;
}

STATIC int
xfs_ioc_getbmap(
	struct file		*file,
	unsigned int		cmd,
	void			__user *arg)
{
	struct getbmapx		bmx = { 0 };
	struct kgetbmap		*buf;
	size_t			recsize;
	int			error, i;

	switch (cmd) {
	case XFS_IOC_GETBMAPA:
		bmx.bmv_iflags = BMV_IF_ATTRFORK;
		/*FALLTHRU*/
	case XFS_IOC_GETBMAP:
		if (file->f_mode & FMODE_NOCMTIME)
			bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
		/* struct getbmap is a strict subset of struct getbmapx. */
		recsize = sizeof(struct getbmap);
		break;
	case XFS_IOC_GETBMAPX:
		recsize = sizeof(struct getbmapx);
		break;
	default:
		return -EINVAL;
	}

	if (copy_from_user(&bmx, arg, recsize))
		return -EFAULT;

	if (bmx.bmv_count < 2)
		return -EINVAL;
	if (bmx.bmv_count > ULONG_MAX / recsize)
		return -ENOMEM;

	buf = kmem_zalloc_large(bmx.bmv_count * sizeof(*buf), 0);
	if (!buf)
		return -ENOMEM;

	error = xfs_getbmap(XFS_I(file_inode(file)), &bmx, buf);
	if (error)
		goto out_free_buf;

	error = -EFAULT;
	if (copy_to_user(arg, &bmx, recsize))
		goto out_free_buf;
	arg += recsize;

	for (i = 0; i < bmx.bmv_entries; i++) {
		if (!xfs_getbmap_format(buf + i, arg, recsize))
			goto out_free_buf;
		arg += recsize;
	}

	error = 0;
out_free_buf:
	kmem_free(buf);
	return error;
}

struct getfsmap_info {
	struct xfs_mount	*mp;
	struct fsmap_head __user *data;
	unsigned int		idx;
	__u32			last_flags;
};

STATIC int
xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv)
{
	struct getfsmap_info	*info = priv;
	struct fsmap		fm;

	trace_xfs_getfsmap_mapping(info->mp, xfm);

	info->last_flags = xfm->fmr_flags;
	xfs_fsmap_from_internal(&fm, xfm);
	if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm,
			sizeof(struct fsmap)))
		return -EFAULT;

	return 0;
}

STATIC int
xfs_ioc_getfsmap(
	struct xfs_inode	*ip,
	struct fsmap_head	__user *arg)
{
	struct getfsmap_info	info = { NULL };
	struct xfs_fsmap_head	xhead = {0};
	struct fsmap_head	head;
	bool			aborted = false;
	int			error;

	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
		return -EFAULT;
	if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
	    memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
		       sizeof(head.fmh_keys[0].fmr_reserved)) ||
	    memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
		       sizeof(head.fmh_keys[1].fmr_reserved)))
		return -EINVAL;

	xhead.fmh_iflags = head.fmh_iflags;
	xhead.fmh_count = head.fmh_count;
	xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
	xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);

	trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
	trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);

	info.mp = ip->i_mount;
	info.data = arg;
	error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info);
	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
		error = 0;
		aborted = true;
	} else if (error)
		return error;

	/* If we didn't abort, set the "last" flag in the last fmx */
	if (!aborted && info.idx) {
		info.last_flags |= FMR_OF_LAST;
		if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags,
				&info.last_flags, sizeof(info.last_flags)))
			return -EFAULT;
	}

	/* copy back header */
	head.fmh_entries = xhead.fmh_entries;
	head.fmh_oflags = xhead.fmh_oflags;
	if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
		return -EFAULT;

	return 0;
}

STATIC int
xfs_ioc_scrub_metadata(
	struct xfs_inode		*ip,
	void				__user *arg)
{
	struct xfs_scrub_metadata	scrub;
	int				error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (copy_from_user(&scrub, arg, sizeof(scrub)))
		return -EFAULT;

	error = xfs_scrub_metadata(ip, &scrub);
	if (error)
		return error;

	if (copy_to_user(arg, &scrub, sizeof(scrub)))
		return -EFAULT;

	return 0;
}

int
xfs_ioc_swapext(
	xfs_swapext_t	*sxp)
{
	xfs_inode_t     *ip, *tip;
	struct fd	f, tmp;
	int		error = 0;

	/* Pull information for the target fd */
	f = fdget((int)sxp->sx_fdtarget);
	if (!f.file) {
		error = -EINVAL;
		goto out;
	}

	if (!(f.file->f_mode & FMODE_WRITE) ||
	    !(f.file->f_mode & FMODE_READ) ||
	    (f.file->f_flags & O_APPEND)) {
		error = -EBADF;
		goto out_put_file;
	}

	tmp = fdget((int)sxp->sx_fdtmp);
	if (!tmp.file) {
		error = -EINVAL;
		goto out_put_file;
	}

	if (!(tmp.file->f_mode & FMODE_WRITE) ||
	    !(tmp.file->f_mode & FMODE_READ) ||
	    (tmp.file->f_flags & O_APPEND)) {
		error = -EBADF;
		goto out_put_tmp_file;
	}

	if (IS_SWAPFILE(file_inode(f.file)) ||
	    IS_SWAPFILE(file_inode(tmp.file))) {
		error = -EINVAL;
		goto out_put_tmp_file;
	}

	/*
	 * We need to ensure that the fds passed in point to XFS inodes
	 * before we cast and access them as XFS structures as we have no
	 * control over what the user passes us here.
	 */
	if (f.file->f_op != &xfs_file_operations ||
	    tmp.file->f_op != &xfs_file_operations) {
		error = -EINVAL;
		goto out_put_tmp_file;
	}

	ip = XFS_I(file_inode(f.file));
	tip = XFS_I(file_inode(tmp.file));

	if (ip->i_mount != tip->i_mount) {
		error = -EINVAL;
		goto out_put_tmp_file;
	}

	if (ip->i_ino == tip->i_ino) {
		error = -EINVAL;
		goto out_put_tmp_file;
	}

	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
		error = -EIO;
		goto out_put_tmp_file;
	}

	error = xfs_swap_extents(ip, tip, sxp);

 out_put_tmp_file:
	fdput(tmp);
 out_put_file:
	fdput(f);
 out:
	return error;
}

static int
xfs_ioc_getlabel(
	struct xfs_mount	*mp,
	char			__user *user_label)
{
	struct xfs_sb		*sbp = &mp->m_sb;
	char			label[XFSLABEL_MAX + 1];

	/* Paranoia */
	BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX);

	/* 1 larger than sb_fname, so this ensures a trailing NUL char */
	memset(label, 0, sizeof(label));
	spin_lock(&mp->m_sb_lock);
	strncpy(label, sbp->sb_fname, XFSLABEL_MAX);
	spin_unlock(&mp->m_sb_lock);

	if (copy_to_user(user_label, label, sizeof(label)))
		return -EFAULT;
	return 0;
}

static int
xfs_ioc_setlabel(
	struct file		*filp,
	struct xfs_mount	*mp,
	char			__user *newlabel)
{
	struct xfs_sb		*sbp = &mp->m_sb;
	char			label[XFSLABEL_MAX + 1];
	size_t			len;
	int			error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	/*
	 * The generic ioctl allows up to FSLABEL_MAX chars, but XFS is much
	 * smaller, at 12 bytes.  We copy one more to be sure we find the
	 * (required) NULL character to test the incoming label length.
	 * NB: The on disk label doesn't need to be null terminated.
	 */
	if (copy_from_user(label, newlabel, XFSLABEL_MAX + 1))
		return -EFAULT;
	len = strnlen(label, XFSLABEL_MAX + 1);
	if (len > sizeof(sbp->sb_fname))
		return -EINVAL;

	error = mnt_want_write_file(filp);
	if (error)
		return error;

	spin_lock(&mp->m_sb_lock);
	memset(sbp->sb_fname, 0, sizeof(sbp->sb_fname));
	memcpy(sbp->sb_fname, label, len);
	spin_unlock(&mp->m_sb_lock);

	/*
	 * Now we do several things to satisfy userspace.
	 * In addition to normal logging of the primary superblock, we also
	 * immediately write these changes to sector zero for the primary, then
	 * update all backup supers (as xfs_db does for a label change), then
	 * invalidate the block device page cache.  This is so that any prior
	 * buffered reads from userspace (i.e. from blkid) are invalidated,
	 * and userspace will see the newly-written label.
	 */
	error = xfs_sync_sb_buf(mp);
	if (error)
		goto out;
	/*
	 * growfs also updates backup supers so lock against that.
	 */
	mutex_lock(&mp->m_growlock);
	error = xfs_update_secondary_sbs(mp);
	mutex_unlock(&mp->m_growlock);

	invalidate_bdev(mp->m_ddev_targp->bt_bdev);

out:
	mnt_drop_write_file(filp);
	return error;
}

/*
 * Note: some of the ioctl's return positive numbers as a
 * byte count indicating success, such as readlink_by_handle.
 * So we don't "sign flip" like most other routines.  This means
 * true errors need to be returned as a negative value.
 */
long
xfs_file_ioctl(
	struct file		*filp,
	unsigned int		cmd,
	unsigned long		p)
{
	struct inode		*inode = file_inode(filp);
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	void			__user *arg = (void __user *)p;
	int			error;

	trace_xfs_file_ioctl(ip);

	switch (cmd) {
	case FITRIM:
		return xfs_ioc_trim(mp, arg);
	case FS_IOC_GETFSLABEL:
		return xfs_ioc_getlabel(mp, arg);
	case FS_IOC_SETFSLABEL:
		return xfs_ioc_setlabel(filp, mp, arg);
	case XFS_IOC_ALLOCSP:
	case XFS_IOC_FREESP:
	case XFS_IOC_RESVSP:
	case XFS_IOC_UNRESVSP:
	case XFS_IOC_ALLOCSP64:
	case XFS_IOC_FREESP64:
	case XFS_IOC_RESVSP64:
	case XFS_IOC_UNRESVSP64:
	case XFS_IOC_ZERO_RANGE: {
		xfs_flock64_t		bf;

		if (copy_from_user(&bf, arg, sizeof(bf)))
			return -EFAULT;
		return xfs_ioc_space(filp, cmd, &bf);
	}
	case XFS_IOC_DIOINFO: {
		struct dioattr	da;
		xfs_buftarg_t	*target =
			XFS_IS_REALTIME_INODE(ip) ?
			mp->m_rtdev_targp : mp->m_ddev_targp;

		da.d_mem =  da.d_miniosz = target->bt_logical_sectorsize;
		da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);

		if (copy_to_user(arg, &da, sizeof(da)))
			return -EFAULT;
		return 0;
	}

	case XFS_IOC_FSBULKSTAT_SINGLE:
	case XFS_IOC_FSBULKSTAT:
	case XFS_IOC_FSINUMBERS:
		return xfs_ioc_fsbulkstat(mp, cmd, arg);

	case XFS_IOC_BULKSTAT:
		return xfs_ioc_bulkstat(mp, cmd, arg);
	case XFS_IOC_INUMBERS:
		return xfs_ioc_inumbers(mp, cmd, arg);

	case XFS_IOC_FSGEOMETRY_V1:
		return xfs_ioc_fsgeometry(mp, arg, 3);
	case XFS_IOC_FSGEOMETRY_V4:
		return xfs_ioc_fsgeometry(mp, arg, 4);
	case XFS_IOC_FSGEOMETRY:
		return xfs_ioc_fsgeometry(mp, arg, 5);

	case XFS_IOC_AG_GEOMETRY:
		return xfs_ioc_ag_geometry(mp, arg);

	case XFS_IOC_GETVERSION:
		return put_user(inode->i_generation, (int __user *)arg);

	case XFS_IOC_FSGETXATTR:
		return xfs_ioc_fsgetxattr(ip, 0, arg);
	case XFS_IOC_FSGETXATTRA:
		return xfs_ioc_fsgetxattr(ip, 1, arg);
	case XFS_IOC_FSSETXATTR:
		return xfs_ioc_fssetxattr(ip, filp, arg);
	case XFS_IOC_GETXFLAGS:
		return xfs_ioc_getxflags(ip, arg);
	case XFS_IOC_SETXFLAGS:
		return xfs_ioc_setxflags(ip, filp, arg);

	case XFS_IOC_FSSETDM: {
		struct fsdmidata	dmi;

		if (copy_from_user(&dmi, arg, sizeof(dmi)))
			return -EFAULT;

		error = mnt_want_write_file(filp);
		if (error)
			return error;

		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
				dmi.fsd_dmstate);
		mnt_drop_write_file(filp);
		return error;
	}

	case XFS_IOC_GETBMAP:
	case XFS_IOC_GETBMAPA:
	case XFS_IOC_GETBMAPX:
		return xfs_ioc_getbmap(filp, cmd, arg);

	case FS_IOC_GETFSMAP:
		return xfs_ioc_getfsmap(ip, arg);

	case XFS_IOC_SCRUB_METADATA:
		return xfs_ioc_scrub_metadata(ip, arg);

	case XFS_IOC_FD_TO_HANDLE:
	case XFS_IOC_PATH_TO_HANDLE:
	case XFS_IOC_PATH_TO_FSHANDLE: {
		xfs_fsop_handlereq_t	hreq;

		if (copy_from_user(&hreq, arg, sizeof(hreq)))
			return -EFAULT;
		return xfs_find_handle(cmd, &hreq);
	}
	case XFS_IOC_OPEN_BY_HANDLE: {
		xfs_fsop_handlereq_t	hreq;

		if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
			return -EFAULT;
		return xfs_open_by_handle(filp, &hreq);
	}
	case XFS_IOC_FSSETDM_BY_HANDLE:
		return xfs_fssetdm_by_handle(filp, arg);

	case XFS_IOC_READLINK_BY_HANDLE: {
		xfs_fsop_handlereq_t	hreq;

		if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
			return -EFAULT;
		return xfs_readlink_by_handle(filp, &hreq);
	}
	case XFS_IOC_ATTRLIST_BY_HANDLE:
		return xfs_attrlist_by_handle(filp, arg);

	case XFS_IOC_ATTRMULTI_BY_HANDLE:
		return xfs_attrmulti_by_handle(filp, arg);

	case XFS_IOC_SWAPEXT: {
		struct xfs_swapext	sxp;

		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
			return -EFAULT;
		error = mnt_want_write_file(filp);
		if (error)
			return error;
		error = xfs_ioc_swapext(&sxp);
		mnt_drop_write_file(filp);
		return error;
	}

	case XFS_IOC_FSCOUNTS: {
		xfs_fsop_counts_t out;

		xfs_fs_counts(mp, &out);

		if (copy_to_user(arg, &out, sizeof(out)))
			return -EFAULT;
		return 0;
	}

	case XFS_IOC_SET_RESBLKS: {
		xfs_fsop_resblks_t inout;
		uint64_t	   in;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (mp->m_flags & XFS_MOUNT_RDONLY)
			return -EROFS;

		if (copy_from_user(&inout, arg, sizeof(inout)))
			return -EFAULT;

		error = mnt_want_write_file(filp);
		if (error)
			return error;

		/* input parameter is passed in resblks field of structure */
		in = inout.resblks;
		error = xfs_reserve_blocks(mp, &in, &inout);
		mnt_drop_write_file(filp);
		if (error)
			return error;

		if (copy_to_user(arg, &inout, sizeof(inout)))
			return -EFAULT;
		return 0;
	}

	case XFS_IOC_GET_RESBLKS: {
		xfs_fsop_resblks_t out;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		error = xfs_reserve_blocks(mp, NULL, &out);
		if (error)
			return error;

		if (copy_to_user(arg, &out, sizeof(out)))
			return -EFAULT;

		return 0;
	}

	case XFS_IOC_FSGROWFSDATA: {
		xfs_growfs_data_t in;

		if (copy_from_user(&in, arg, sizeof(in)))
			return -EFAULT;

		error = mnt_want_write_file(filp);
		if (error)
			return error;
		error = xfs_growfs_data(mp, &in);
		mnt_drop_write_file(filp);
		return error;
	}

	case XFS_IOC_FSGROWFSLOG: {
		xfs_growfs_log_t in;

		if (copy_from_user(&in, arg, sizeof(in)))
			return -EFAULT;

		error = mnt_want_write_file(filp);
		if (error)
			return error;
		error = xfs_growfs_log(mp, &in);
		mnt_drop_write_file(filp);
		return error;
	}

	case XFS_IOC_FSGROWFSRT: {
		xfs_growfs_rt_t in;

		if (copy_from_user(&in, arg, sizeof(in)))
			return -EFAULT;

		error = mnt_want_write_file(filp);
		if (error)
			return error;
		error = xfs_growfs_rt(mp, &in);
		mnt_drop_write_file(filp);
		return error;
	}

	case XFS_IOC_GOINGDOWN: {
		uint32_t in;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (get_user(in, (uint32_t __user *)arg))
			return -EFAULT;

		return xfs_fs_goingdown(mp, in);
	}

	case XFS_IOC_ERROR_INJECTION: {
		xfs_error_injection_t in;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (copy_from_user(&in, arg, sizeof(in)))
			return -EFAULT;

		return xfs_errortag_add(mp, in.errtag);
	}

	case XFS_IOC_ERROR_CLEARALL:
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		return xfs_errortag_clearall(mp);

	case XFS_IOC_FREE_EOFBLOCKS: {
		struct xfs_fs_eofblocks eofb;
		struct xfs_eofblocks keofb;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (mp->m_flags & XFS_MOUNT_RDONLY)
			return -EROFS;

		if (copy_from_user(&eofb, arg, sizeof(eofb)))
			return -EFAULT;

		error = xfs_fs_eofblocks_from_user(&eofb, &keofb);
		if (error)
			return error;

		return xfs_icache_free_eofblocks(mp, &keofb);
	}

	default:
		return -ENOTTY;
	}
}