summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_ioctl.c
blob: 857b19428984a3f1c9af16d2e12a9e3717989f57 (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
// 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_da_format.h"
#include "xfs_da_btree.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_trace.h"
#include "xfs_icache.h"
#include "xfs_trans.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 "xfs_reflink.h"
#include "xfs_ioctl.h"
#include "xfs_xattr.h"
#include "xfs_rtbitmap.h"
#include "xfs_file.h"
#include "xfs_exchrange.h"
#include "xfs_handle.h"

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

/* 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(
	struct file		*file,
	unsigned int		cmd,
	void			__user *arg)
{
	struct xfs_mount	*mp = XFS_I(file_inode(file))->i_mount;
	struct xfs_fsop_bulkreq	bulkreq;
	struct xfs_ibulk	breq = {
		.mp		= mp,
		.idmap		= file_mnt_idmap(file),
		.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_is_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; -ECANCELED if there's nothing to do; or the usual
 * negative error code.
 */
static int
xfs_bulk_ireq_setup(
	struct xfs_mount	*mp,
	const 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:
			breq->startino = 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 -ECANCELED;
	} 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 -ECANCELED;

	if (hdr->flags & XFS_BULK_IREQ_NREXT64)
		breq->flags |= XFS_IBULK_NREXT64;

	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 file			*file,
	unsigned int			cmd,
	struct xfs_bulkstat_req __user	*arg)
{
	struct xfs_mount		*mp = XFS_I(file_inode(file))->i_mount;
	struct xfs_bulk_ireq		hdr;
	struct xfs_ibulk		breq = {
		.mp			= mp,
		.idmap			= file_mnt_idmap(file),
	};
	int				error;

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

	if (xfs_is_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 == -ECANCELED)
		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_is_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 == -ECANCELED)
		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, &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_perag	*pag;
	struct xfs_ag_geometry	ageo;
	int			error;

	if (copy_from_user(&ageo, arg, sizeof(ageo)))
		return -EFAULT;
	if (ageo.ag_flags)
		return -EINVAL;
	if (memchr_inv(&ageo.ag_reserved, 0, sizeof(ageo.ag_reserved)))
		return -EINVAL;

	pag = xfs_perag_get(mp, ageo.ag_number);
	if (!pag)
		return -EINVAL;

	error = xfs_ag_get_geometry(pag, &ageo);
	xfs_perag_put(pag);
	if (error)
		return error;

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

/*
 * Linux extended inode flags interface.
 */

static void
xfs_fill_fsxattr(
	struct xfs_inode	*ip,
	int			whichfork,
	struct fileattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);

	fileattr_fill_xflags(fa, xfs_ip2xflags(ip));

	if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) {
		fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
	} else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
		/*
		 * Don't let a misaligned extent size hint on a directory
		 * escape to userspace if it won't pass the setattr checks
		 * later.
		 */
		if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
		    xfs_extlen_to_rtxmod(mp, ip->i_extsize) > 0) {
			fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE |
					    FS_XFLAG_EXTSZINHERIT);
			fa->fsx_extsize = 0;
		} else {
			fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
		}
	}

	if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
		fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize);
	fa->fsx_projid = ip->i_projid;
	if (ifp && !xfs_need_iread_extents(ifp))
		fa->fsx_nextents = xfs_iext_count(ifp);
	else
		fa->fsx_nextents = xfs_ifork_nextents(ifp);
}

STATIC int
xfs_ioc_fsgetxattra(
	xfs_inode_t		*ip,
	void			__user *arg)
{
	struct fileattr		fa;

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

	return copy_fsxattr_to_user(&fa, arg);
}

int
xfs_fileattr_get(
	struct dentry		*dentry,
	struct fileattr		*fa)
{
	struct xfs_inode	*ip = XFS_I(d_inode(dentry));

	if (d_is_special(dentry))
		return -ENOTTY;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	xfs_fill_fsxattr(ip, XFS_DATA_FORK, fa);
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	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_diflags & 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_diflags2 & (XFS_DIFLAG2_REFLINK |
				   XFS_DIFLAG2_BIGTIME |
				   XFS_DIFLAG2_NREXT64));

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

	return di_flags2;
}

static int
xfs_ioctl_setattr_xflags(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	struct fileattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	bool			rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
	uint64_t		i_flags2;

	if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
		/* Can't change realtime flag if any extents are allocated. */
		if (ip->i_df.if_nextents || ip->i_delayed_blks)
			return -EINVAL;
	}

	if (rtflag) {
		/* If realtime flag is set then must have realtime device */
		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
		    xfs_extlen_to_rtxmod(mp, ip->i_extsize))
			return -EINVAL;

		/* Clear reflink if we are actually able to set the rt flag. */
		if (xfs_is_reflink_inode(ip))
			ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
	}

	/* diflags2 only valid for v3 inodes. */
	i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
	if (i_flags2 && !xfs_has_v3inodes(mp))
		return -EINVAL;

	ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
	ip->i_diflags2 = i_flags2;

	xfs_diflags_to_iflags(ip, false);

	/*
	 * Make the stable writes flag match that of the device the inode
	 * resides on when flipping the RT flag.
	 */
	if (rtflag != XFS_IS_REALTIME_INODE(ip) && S_ISREG(VFS_I(ip)->i_mode))
		xfs_update_stable_writes(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;
}

static void
xfs_ioctl_setattr_prepare_dax(
	struct xfs_inode	*ip,
	struct fileattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode            *inode = VFS_I(ip);

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

	if (xfs_has_dax_always(mp) || xfs_has_dax_never(mp))
		return;

	if (((fa->fsx_xflags & FS_XFLAG_DAX) &&
	    !(ip->i_diflags2 & XFS_DIFLAG2_DAX)) ||
	    (!(fa->fsx_xflags & FS_XFLAG_DAX) &&
	     (ip->i_diflags2 & XFS_DIFLAG2_DAX)))
		d_mark_dontcache(inode);
}

/*
 * 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.
 */
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
	struct xfs_inode	*ip,
	struct xfs_dquot	*pdqp)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error = -EROFS;

	if (xfs_is_readonly(mp))
		goto out_error;
	error = -EIO;
	if (xfs_is_shutdown(mp))
		goto out_error;

	error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp,
			has_capability_noaudit(current, CAP_FOWNER), &tp);
	if (error)
		goto out_error;

	if (xfs_has_wsync(mp))
		xfs_trans_set_sync(tp);

	return tp;

out_error:
	return ERR_PTR(error);
}

/*
 * Validate a proposed extent size hint.  For regular files, the hint can only
 * be changed if no extents are allocated.
 */
static int
xfs_ioctl_setattr_check_extsize(
	struct xfs_inode	*ip,
	struct fileattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_failaddr_t		failaddr;
	uint16_t		new_diflags;

	if (!fa->fsx_valid)
		return 0;

	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents &&
	    XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize)
		return -EINVAL;

	if (fa->fsx_extsize & mp->m_blockmask)
		return -EINVAL;

	new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);

	/*
	 * Inode verifiers do not check that the extent size hint is an integer
	 * multiple of the rt extent size on a directory with both rtinherit
	 * and extszinherit flags set.  Don't let sysadmins misconfigure
	 * directories.
	 */
	if ((new_diflags & XFS_DIFLAG_RTINHERIT) &&
	    (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) {
		unsigned int	rtextsize_bytes;

		rtextsize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
		if (fa->fsx_extsize % rtextsize_bytes)
			return -EINVAL;
	}

	failaddr = xfs_inode_validate_extsize(ip->i_mount,
			XFS_B_TO_FSB(mp, fa->fsx_extsize),
			VFS_I(ip)->i_mode, new_diflags);
	return failaddr != NULL ? -EINVAL : 0;
}

static int
xfs_ioctl_setattr_check_cowextsize(
	struct xfs_inode	*ip,
	struct fileattr		*fa)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_failaddr_t		failaddr;
	uint64_t		new_diflags2;
	uint16_t		new_diflags;

	if (!fa->fsx_valid)
		return 0;

	if (fa->fsx_cowextsize & mp->m_blockmask)
		return -EINVAL;

	new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
	new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);

	failaddr = xfs_inode_validate_cowextsize(ip->i_mount,
			XFS_B_TO_FSB(mp, fa->fsx_cowextsize),
			VFS_I(ip)->i_mode, new_diflags, new_diflags2);
	return failaddr != NULL ? -EINVAL : 0;
}

static int
xfs_ioctl_setattr_check_projid(
	struct xfs_inode	*ip,
	struct fileattr		*fa)
{
	if (!fa->fsx_valid)
		return 0;

	/* Disallow 32bit project ids if 32bit IDs are not enabled. */
	if (fa->fsx_projid > (uint16_t)-1 &&
	    !xfs_has_projid32(ip->i_mount))
		return -EINVAL;
	return 0;
}

int
xfs_fileattr_set(
	struct mnt_idmap	*idmap,
	struct dentry		*dentry,
	struct fileattr		*fa)
{
	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	struct xfs_dquot	*pdqp = NULL;
	struct xfs_dquot	*olddquot = NULL;
	int			error;

	trace_xfs_ioctl_setattr(ip);

	if (d_is_special(dentry))
		return -ENOTTY;

	if (!fa->fsx_valid) {
		if (fa->flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL |
				  FS_NOATIME_FL | FS_NODUMP_FL |
				  FS_SYNC_FL | FS_DAX_FL | FS_PROJINHERIT_FL))
			return -EOPNOTSUPP;
	}

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

	/*
	 * 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 (fa->fsx_valid && XFS_IS_QUOTA_ON(mp)) {
		error = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid,
				VFS_I(ip)->i_gid, fa->fsx_projid,
				XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp);
		if (error)
			return error;
	}

	xfs_ioctl_setattr_prepare_dax(ip, fa);

	tp = xfs_ioctl_setattr_get_trans(ip, pdqp);
	if (IS_ERR(tp)) {
		error = PTR_ERR(tp);
		goto error_free_dquots;
	}

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

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

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

	if (!fa->fsx_valid)
		goto skip_xattr;
	/*
	 * 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(idmap, VFS_I(ip), CAP_FSETID))
		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);

	/* Change the ownerships and register project quota modifications */
	if (ip->i_projid != fa->fsx_projid) {
		if (XFS_IS_PQUOTA_ON(mp)) {
			olddquot = xfs_qm_vop_chown(tp, ip,
						&ip->i_pdquot, pdqp);
		}
		ip->i_projid = 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_diflags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
		ip->i_extsize = XFS_B_TO_FSB(mp, fa->fsx_extsize);
	else
		ip->i_extsize = 0;

	if (xfs_has_v3inodes(mp)) {
		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
			ip->i_cowextsize = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
		else
			ip->i_cowextsize = 0;
	}

skip_xattr:
	error = xfs_trans_commit(tp);

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

	return error;

error_trans_cancel:
	xfs_trans_cancel(tp);
error_free_dquots:
	xfs_qm_dqrele(pdqp);
	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;
		fallthrough;
	case XFS_IOC_GETBMAP:
		/* 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 >= INT_MAX / recsize)
		return -ENOMEM;

	buf = kvcalloc(bmx.bmv_count, sizeof(*buf), GFP_KERNEL);
	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:
	kvfree(buf);
	return error;
}

STATIC int
xfs_ioc_getfsmap(
	struct xfs_inode	*ip,
	struct fsmap_head	__user *arg)
{
	struct xfs_fsmap_head	xhead = {0};
	struct fsmap_head	head;
	struct fsmap		*recs;
	unsigned int		count;
	__u32			last_flags = 0;
	bool			done = 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;

	/*
	 * Use an internal memory buffer so that we don't have to copy fsmap
	 * data to userspace while holding locks.  Start by trying to allocate
	 * up to 128k for the buffer, but fall back to a single page if needed.
	 */
	count = min_t(unsigned int, head.fmh_count,
			131072 / sizeof(struct fsmap));
	recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
	if (!recs) {
		count = min_t(unsigned int, head.fmh_count,
				PAGE_SIZE / sizeof(struct fsmap));
		recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
		if (!recs)
			return -ENOMEM;
	}

	xhead.fmh_iflags = head.fmh_iflags;
	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]);

	head.fmh_entries = 0;
	do {
		struct fsmap __user	*user_recs;
		struct fsmap		*last_rec;

		user_recs = &arg->fmh_recs[head.fmh_entries];
		xhead.fmh_entries = 0;
		xhead.fmh_count = min_t(unsigned int, count,
					head.fmh_count - head.fmh_entries);

		/* Run query, record how many entries we got. */
		error = xfs_getfsmap(ip->i_mount, &xhead, recs);
		switch (error) {
		case 0:
			/*
			 * There are no more records in the result set.  Copy
			 * whatever we got to userspace and break out.
			 */
			done = true;
			break;
		case -ECANCELED:
			/*
			 * The internal memory buffer is full.  Copy whatever
			 * records we got to userspace and go again if we have
			 * not yet filled the userspace buffer.
			 */
			error = 0;
			break;
		default:
			goto out_free;
		}
		head.fmh_entries += xhead.fmh_entries;
		head.fmh_oflags = xhead.fmh_oflags;

		/*
		 * If the caller wanted a record count or there aren't any
		 * new records to return, we're done.
		 */
		if (head.fmh_count == 0 || xhead.fmh_entries == 0)
			break;

		/* Copy all the records we got out to userspace. */
		if (copy_to_user(user_recs, recs,
				 xhead.fmh_entries * sizeof(struct fsmap))) {
			error = -EFAULT;
			goto out_free;
		}

		/* Remember the last record flags we copied to userspace. */
		last_rec = &recs[xhead.fmh_entries - 1];
		last_flags = last_rec->fmr_flags;

		/* Set up the low key for the next iteration. */
		xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec);
		trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
	} while (!done && head.fmh_entries < head.fmh_count);

	/*
	 * If there are no more records in the query result set and we're not
	 * in counting mode, mark the last record returned with the LAST flag.
	 */
	if (done && head.fmh_count > 0 && head.fmh_entries > 0) {
		struct fsmap __user	*user_rec;

		last_flags |= FMR_OF_LAST;
		user_rec = &arg->fmh_recs[head.fmh_entries - 1];

		if (copy_to_user(&user_rec->fmr_flags, &last_flags,
					sizeof(last_flags))) {
			error = -EFAULT;
			goto out_free;
		}
	}

	/* copy back header */
	if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) {
		error = -EFAULT;
		goto out_free;
	}

out_free:
	kvfree(recs);
	return error;
}

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_is_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;
}

static inline int
xfs_fs_eofblocks_from_user(
	struct xfs_fs_eofblocks		*src,
	struct xfs_icwalk		*dst)
{
	if (src->eof_version != XFS_EOFBLOCKS_VERSION)
		return -EINVAL;

	if (src->eof_flags & ~XFS_EOF_FLAGS_VALID)
		return -EINVAL;

	if (memchr_inv(&src->pad32, 0, sizeof(src->pad32)) ||
	    memchr_inv(src->pad64, 0, sizeof(src->pad64)))
		return -EINVAL;

	dst->icw_flags = 0;
	if (src->eof_flags & XFS_EOF_FLAGS_SYNC)
		dst->icw_flags |= XFS_ICWALK_FLAG_SYNC;
	if (src->eof_flags & XFS_EOF_FLAGS_UID)
		dst->icw_flags |= XFS_ICWALK_FLAG_UID;
	if (src->eof_flags & XFS_EOF_FLAGS_GID)
		dst->icw_flags |= XFS_ICWALK_FLAG_GID;
	if (src->eof_flags & XFS_EOF_FLAGS_PRID)
		dst->icw_flags |= XFS_ICWALK_FLAG_PRID;
	if (src->eof_flags & XFS_EOF_FLAGS_MINFILESIZE)
		dst->icw_flags |= XFS_ICWALK_FLAG_MINFILESIZE;

	dst->icw_prid = src->eof_prid;
	dst->icw_min_file_size = src->eof_min_file_size;

	dst->icw_uid = INVALID_UID;
	if (src->eof_flags & XFS_EOF_FLAGS_UID) {
		dst->icw_uid = make_kuid(current_user_ns(), src->eof_uid);
		if (!uid_valid(dst->icw_uid))
			return -EINVAL;
	}

	dst->icw_gid = INVALID_GID;
	if (src->eof_flags & XFS_EOF_FLAGS_GID) {
		dst->icw_gid = make_kgid(current_user_ns(), src->eof_gid);
		if (!gid_valid(dst->icw_gid))
			return -EINVAL;
	}
	return 0;
}

static int
xfs_ioctl_getset_resblocks(
	struct file		*filp,
	unsigned int		cmd,
	void __user		*arg)
{
	struct xfs_mount	*mp = XFS_I(file_inode(filp))->i_mount;
	struct xfs_fsop_resblks	fsop = { };
	int			error;

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

	if (cmd == XFS_IOC_SET_RESBLKS) {
		if (xfs_is_readonly(mp))
			return -EROFS;

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

		error = mnt_want_write_file(filp);
		if (error)
			return error;
		error = xfs_reserve_blocks(mp, fsop.resblks);
		mnt_drop_write_file(filp);
		if (error)
			return error;
	}

	spin_lock(&mp->m_sb_lock);
	fsop.resblks = mp->m_resblks;
	fsop.resblks_avail = mp->m_resblks_avail;
	spin_unlock(&mp->m_sb_lock);

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

static int
xfs_ioctl_fs_counts(
	struct xfs_mount	*mp,
	struct xfs_fsop_counts __user	*uarg)
{
	struct xfs_fsop_counts	out = {
		.allocino = percpu_counter_read_positive(&mp->m_icount),
		.freeino  = percpu_counter_read_positive(&mp->m_ifree),
		.freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
				xfs_fdblocks_unavailable(mp),
		.freertx  = percpu_counter_read_positive(&mp->m_frextents),
	};

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

/*
 * These long-unused ioctls were removed from the official ioctl API in 5.17,
 * but retain these definitions so that we can log warnings about them.
 */
#define XFS_IOC_ALLOCSP		_IOW ('X', 10, struct xfs_flock64)
#define XFS_IOC_FREESP		_IOW ('X', 11, struct xfs_flock64)
#define XFS_IOC_ALLOCSP64	_IOW ('X', 36, struct xfs_flock64)
#define XFS_IOC_FREESP64	_IOW ('X', 37, struct xfs_flock64)

/*
 * 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_ALLOCSP64:
	case XFS_IOC_FREESP64:
		xfs_warn_once(mp,
	"%s should use fallocate; XFS_IOC_{ALLOC,FREE}SP ioctl unsupported",
				current->comm);
		return -ENOTTY;
	case XFS_IOC_DIOINFO: {
		struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
		struct dioattr		da;

		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(filp, cmd, arg);

	case XFS_IOC_BULKSTAT:
		return xfs_ioc_bulkstat(filp, 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_FSGETXATTRA:
		return xfs_ioc_fsgetxattra(ip, arg);
	case XFS_IOC_GETPARENTS:
		return xfs_ioc_getparents(filp, arg);
	case XFS_IOC_GETPARENTS_BY_HANDLE:
		return xfs_ioc_getparents_by_handle(filp, arg);
	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(filp, 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_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:
		return xfs_ioctl_fs_counts(mp, arg);

	case XFS_IOC_SET_RESBLKS:
	case XFS_IOC_GET_RESBLKS:
		return xfs_ioctl_getset_resblocks(filp, cmd, arg);

	case XFS_IOC_FSGROWFSDATA: {
		struct xfs_growfs_data 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: {
		struct xfs_growfs_log 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_icwalk	icw;

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

		if (xfs_is_readonly(mp))
			return -EROFS;

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

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

		trace_xfs_ioc_free_eofblocks(mp, &icw, _RET_IP_);

		sb_start_write(mp->m_super);
		error = xfs_blockgc_free_space(mp, &icw);
		sb_end_write(mp->m_super);
		return error;
	}

	case XFS_IOC_EXCHANGE_RANGE:
		return xfs_ioc_exchange_range(filp, arg);

	default:
		return -ENOTTY;
	}
}