Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 3dd47307363fa891b37f32a42de82b39e1e8efa6 (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#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_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_error.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_ioctl.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_icache.h"
#include "xfs_pnfs.h"

#include <linux/dcache.h>
#include <linux/falloc.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>

static const struct vm_operations_struct xfs_file_vm_ops;

/*
 * Locking primitives for read and write IO paths to ensure we consistently use
 * and order the inode->i_mutex, ip->i_lock and ip->i_iolock.
 */
static inline void
xfs_rw_ilock(
	struct xfs_inode	*ip,
	int			type)
{
	if (type & XFS_IOLOCK_EXCL)
		mutex_lock(&VFS_I(ip)->i_mutex);
	xfs_ilock(ip, type);
}

static inline void
xfs_rw_iunlock(
	struct xfs_inode	*ip,
	int			type)
{
	xfs_iunlock(ip, type);
	if (type & XFS_IOLOCK_EXCL)
		mutex_unlock(&VFS_I(ip)->i_mutex);
}

static inline void
xfs_rw_ilock_demote(
	struct xfs_inode	*ip,
	int			type)
{
	xfs_ilock_demote(ip, type);
	if (type & XFS_IOLOCK_EXCL)
		mutex_unlock(&VFS_I(ip)->i_mutex);
}

/*
 * xfs_iozero clears the specified range supplied via the page cache (except in
 * the DAX case). Writes through the page cache will allocate blocks over holes,
 * though the callers usually map the holes first and avoid them. If a block is
 * not completely zeroed, then it will be read from disk before being partially
 * zeroed.
 *
 * In the DAX case, we can just directly write to the underlying pages. This
 * will not allocate blocks, but will avoid holes and unwritten extents and so
 * not do unnecessary work.
 */
int
xfs_iozero(
	struct xfs_inode	*ip,	/* inode			*/
	loff_t			pos,	/* offset in file		*/
	size_t			count)	/* size of data to zero		*/
{
	struct page		*page;
	struct address_space	*mapping;
	int			status = 0;


	mapping = VFS_I(ip)->i_mapping;
	do {
		unsigned offset, bytes;
		void *fsdata;

		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
		bytes = PAGE_CACHE_SIZE - offset;
		if (bytes > count)
			bytes = count;

		if (IS_DAX(VFS_I(ip))) {
			status = dax_zero_page_range(VFS_I(ip), pos, bytes,
						     xfs_get_blocks_direct);
			if (status)
				break;
		} else {
			status = pagecache_write_begin(NULL, mapping, pos, bytes,
						AOP_FLAG_UNINTERRUPTIBLE,
						&page, &fsdata);
			if (status)
				break;

			zero_user(page, offset, bytes);

			status = pagecache_write_end(NULL, mapping, pos, bytes,
						bytes, page, fsdata);
			WARN_ON(status <= 0); /* can't return less than zero! */
			status = 0;
		}
		pos += bytes;
		count -= bytes;
	} while (count);

	return status;
}

int
xfs_update_prealloc_flags(
	struct xfs_inode	*ip,
	enum xfs_prealloc_flags	flags)
{
	struct xfs_trans	*tp;
	int			error;

	tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
	error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
	if (error) {
		xfs_trans_cancel(tp);
		return error;
	}

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

	if (!(flags & XFS_PREALLOC_INVISIBLE)) {
		ip->i_d.di_mode &= ~S_ISUID;
		if (ip->i_d.di_mode & S_IXGRP)
			ip->i_d.di_mode &= ~S_ISGID;
		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	}

	if (flags & XFS_PREALLOC_SET)
		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
	if (flags & XFS_PREALLOC_CLEAR)
		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	if (flags & XFS_PREALLOC_SYNC)
		xfs_trans_set_sync(tp);
	return xfs_trans_commit(tp);
}

/*
 * Fsync operations on directories are much simpler than on regular files,
 * as there is no file data to flush, and thus also no need for explicit
 * cache flush operations, and there are no non-transaction metadata updates
 * on directories either.
 */
STATIC int
xfs_dir_fsync(
	struct file		*file,
	loff_t			start,
	loff_t			end,
	int			datasync)
{
	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_lsn_t		lsn = 0;

	trace_xfs_dir_fsync(ip);

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_ipincount(ip))
		lsn = ip->i_itemp->ili_last_lsn;
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	if (!lsn)
		return 0;
	return _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
}

STATIC int
xfs_file_fsync(
	struct file		*file,
	loff_t			start,
	loff_t			end,
	int			datasync)
{
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	int			error = 0;
	int			log_flushed = 0;
	xfs_lsn_t		lsn = 0;

	trace_xfs_file_fsync(ip);

	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (error)
		return error;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	xfs_iflags_clear(ip, XFS_ITRUNCATED);

	if (mp->m_flags & XFS_MOUNT_BARRIER) {
		/*
		 * If we have an RT and/or log subvolume we need to make sure
		 * to flush the write cache the device used for file data
		 * first.  This is to ensure newly written file data make
		 * it to disk before logging the new inode size in case of
		 * an extending write.
		 */
		if (XFS_IS_REALTIME_INODE(ip))
			xfs_blkdev_issue_flush(mp->m_rtdev_targp);
		else if (mp->m_logdev_targp != mp->m_ddev_targp)
			xfs_blkdev_issue_flush(mp->m_ddev_targp);
	}

	/*
	 * All metadata updates are logged, which means that we just have to
	 * flush the log up to the latest LSN that touched the inode. If we have
	 * concurrent fsync/fdatasync() calls, we need them to all block on the
	 * log force before we clear the ili_fsync_fields field. This ensures
	 * that we don't get a racing sync operation that does not wait for the
	 * metadata to hit the journal before returning. If we race with
	 * clearing the ili_fsync_fields, then all that will happen is the log
	 * force will do nothing as the lsn will already be on disk. We can't
	 * race with setting ili_fsync_fields because that is done under
	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
	 * until after the ili_fsync_fields is cleared.
	 */
	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_ipincount(ip)) {
		if (!datasync ||
		    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
			lsn = ip->i_itemp->ili_last_lsn;
	}

	if (lsn) {
		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
		ip->i_itemp->ili_fsync_fields = 0;
	}
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	/*
	 * If we only have a single device, and the log force about was
	 * a no-op we might have to flush the data device cache here.
	 * This can only happen for fdatasync/O_DSYNC if we were overwriting
	 * an already allocated file and thus do not have any metadata to
	 * commit.
	 */
	if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
	    mp->m_logdev_targp == mp->m_ddev_targp &&
	    !XFS_IS_REALTIME_INODE(ip) &&
	    !log_flushed)
		xfs_blkdev_issue_flush(mp->m_ddev_targp);

	return error;
}

STATIC ssize_t
xfs_file_read_iter(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct file		*file = iocb->ki_filp;
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	size_t			size = iov_iter_count(to);
	ssize_t			ret = 0;
	int			ioflags = 0;
	xfs_fsize_t		n;
	loff_t			pos = iocb->ki_pos;

	XFS_STATS_INC(mp, xs_read_calls);

	if (unlikely(iocb->ki_flags & IOCB_DIRECT))
		ioflags |= XFS_IO_ISDIRECT;
	if (file->f_mode & FMODE_NOCMTIME)
		ioflags |= XFS_IO_INVIS;

	if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
		xfs_buftarg_t	*target =
			XFS_IS_REALTIME_INODE(ip) ?
				mp->m_rtdev_targp : mp->m_ddev_targp;
		/* DIO must be aligned to device logical sector size */
		if ((pos | size) & target->bt_logical_sectormask) {
			if (pos == i_size_read(inode))
				return 0;
			return -EINVAL;
		}
	}

	n = mp->m_super->s_maxbytes - pos;
	if (n <= 0 || size == 0)
		return 0;

	if (n < size)
		size = n;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	/*
	 * Locking is a bit tricky here. If we take an exclusive lock for direct
	 * IO, we effectively serialise all new concurrent read IO to this file
	 * and block it behind IO that is currently in progress because IO in
	 * progress holds the IO lock shared. We only need to hold the lock
	 * exclusive to blow away the page cache, so only take lock exclusively
	 * if the page cache needs invalidation. This allows the normal direct
	 * IO case of no page cache pages to proceeed concurrently without
	 * serialisation.
	 */
	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
	if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);

		/*
		 * The generic dio code only flushes the range of the particular
		 * I/O. Because we take an exclusive lock here, this whole
		 * sequence is considerably more expensive for us. This has a
		 * noticeable performance impact for any file with cached pages,
		 * even when outside of the range of the particular I/O.
		 *
		 * Hence, amortize the cost of the lock against a full file
		 * flush and reduce the chances of repeated iolock cycles going
		 * forward.
		 */
		if (inode->i_mapping->nrpages) {
			ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
			if (ret) {
				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
				return ret;
			}

			/*
			 * Invalidate whole pages. This can return an error if
			 * we fail to invalidate a page, but this should never
			 * happen on XFS. Warn if it does fail.
			 */
			ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
			WARN_ON_ONCE(ret);
			ret = 0;
		}
		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
	}

	trace_xfs_file_read(ip, size, pos, ioflags);

	ret = generic_file_read_iter(iocb, to);
	if (ret > 0)
		XFS_STATS_ADD(mp, xs_read_bytes, ret);

	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
	return ret;
}

STATIC ssize_t
xfs_file_splice_read(
	struct file		*infilp,
	loff_t			*ppos,
	struct pipe_inode_info	*pipe,
	size_t			count,
	unsigned int		flags)
{
	struct xfs_inode	*ip = XFS_I(infilp->f_mapping->host);
	int			ioflags = 0;
	ssize_t			ret;

	XFS_STATS_INC(ip->i_mount, xs_read_calls);

	if (infilp->f_mode & FMODE_NOCMTIME)
		ioflags |= XFS_IO_INVIS;

	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return -EIO;

	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);

	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);

	/* for dax, we need to avoid the page cache */
	if (IS_DAX(VFS_I(ip)))
		ret = default_file_splice_read(infilp, ppos, pipe, count, flags);
	else
		ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
	if (ret > 0)
		XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);

	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
	return ret;
}

/*
 * This routine is called to handle zeroing any space in the last block of the
 * file that is beyond the EOF.  We do this since the size is being increased
 * without writing anything to that block and we don't want to read the
 * garbage on the disk.
 */
STATIC int				/* error (positive) */
xfs_zero_last_block(
	struct xfs_inode	*ip,
	xfs_fsize_t		offset,
	xfs_fsize_t		isize,
	bool			*did_zeroing)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
	int			zero_offset = XFS_B_FSB_OFFSET(mp, isize);
	int			zero_len;
	int			nimaps = 1;
	int			error = 0;
	struct xfs_bmbt_irec	imap;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	if (error)
		return error;

	ASSERT(nimaps > 0);

	/*
	 * If the block underlying isize is just a hole, then there
	 * is nothing to zero.
	 */
	if (imap.br_startblock == HOLESTARTBLOCK)
		return 0;

	zero_len = mp->m_sb.sb_blocksize - zero_offset;
	if (isize + zero_len > offset)
		zero_len = offset - isize;
	*did_zeroing = true;
	return xfs_iozero(ip, isize, zero_len);
}

/*
 * Zero any on disk space between the current EOF and the new, larger EOF.
 *
 * This handles the normal case of zeroing the remainder of the last block in
 * the file and the unusual case of zeroing blocks out beyond the size of the
 * file.  This second case only happens with fixed size extents and when the
 * system crashes before the inode size was updated but after blocks were
 * allocated.
 *
 * Expects the iolock to be held exclusive, and will take the ilock internally.
 */
int					/* error (positive) */
xfs_zero_eof(
	struct xfs_inode	*ip,
	xfs_off_t		offset,		/* starting I/O offset */
	xfs_fsize_t		isize,		/* current inode size */
	bool			*did_zeroing)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		start_zero_fsb;
	xfs_fileoff_t		end_zero_fsb;
	xfs_fileoff_t		zero_count_fsb;
	xfs_fileoff_t		last_fsb;
	xfs_fileoff_t		zero_off;
	xfs_fsize_t		zero_len;
	int			nimaps;
	int			error = 0;
	struct xfs_bmbt_irec	imap;

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(offset > isize);

	trace_xfs_zero_eof(ip, isize, offset - isize);

	/*
	 * First handle zeroing the block on which isize resides.
	 *
	 * We only zero a part of that block so it is handled specially.
	 */
	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
		error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
		if (error)
			return error;
	}

	/*
	 * Calculate the range between the new size and the old where blocks
	 * needing to be zeroed may exist.
	 *
	 * To get the block where the last byte in the file currently resides,
	 * we need to subtract one from the size and truncate back to a block
	 * boundary.  We subtract 1 in case the size is exactly on a block
	 * boundary.
	 */
	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
	end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
	ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
	if (last_fsb == end_zero_fsb) {
		/*
		 * The size was only incremented on its last block.
		 * We took care of that above, so just return.
		 */
		return 0;
	}

	ASSERT(start_zero_fsb <= end_zero_fsb);
	while (start_zero_fsb <= end_zero_fsb) {
		nimaps = 1;
		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;

		xfs_ilock(ip, XFS_ILOCK_EXCL);
		error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
					  &imap, &nimaps, 0);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error)
			return error;

		ASSERT(nimaps > 0);

		if (imap.br_state == XFS_EXT_UNWRITTEN ||
		    imap.br_startblock == HOLESTARTBLOCK) {
			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
			continue;
		}

		/*
		 * There are blocks we need to zero.
		 */
		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);

		if ((zero_off + zero_len) > offset)
			zero_len = offset - zero_off;

		error = xfs_iozero(ip, zero_off, zero_len);
		if (error)
			return error;

		*did_zeroing = true;
		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
	}

	return 0;
}

/*
 * Common pre-write limit and setup checks.
 *
 * Called with the iolocked held either shared and exclusive according to
 * @iolock, and returns with it held.  Might upgrade the iolock to exclusive
 * if called for a direct write beyond i_size.
 */
STATIC ssize_t
xfs_file_aio_write_checks(
	struct kiocb		*iocb,
	struct iov_iter		*from,
	int			*iolock)
{
	struct file		*file = iocb->ki_filp;
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			error = 0;
	size_t			count = iov_iter_count(from);
	bool			drained_dio = false;

restart:
	error = generic_write_checks(iocb, from);
	if (error <= 0)
		return error;

	error = xfs_break_layouts(inode, iolock, true);
	if (error)
		return error;

	/* For changing security info in file_remove_privs() we need i_mutex */
	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
		xfs_rw_iunlock(ip, *iolock);
		*iolock = XFS_IOLOCK_EXCL;
		xfs_rw_ilock(ip, *iolock);
		goto restart;
	}
	/*
	 * If the offset is beyond the size of the file, we need to zero any
	 * blocks that fall between the existing EOF and the start of this
	 * write.  If zeroing is needed and we are currently holding the
	 * iolock shared, we need to update it to exclusive which implies
	 * having to redo all checks before.
	 *
	 * We need to serialise against EOF updates that occur in IO
	 * completions here. We want to make sure that nobody is changing the
	 * size while we do this check until we have placed an IO barrier (i.e.
	 * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
	 * The spinlock effectively forms a memory barrier once we have the
	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
	 * and hence be able to correctly determine if we need to run zeroing.
	 */
	spin_lock(&ip->i_flags_lock);
	if (iocb->ki_pos > i_size_read(inode)) {
		bool	zero = false;

		spin_unlock(&ip->i_flags_lock);
		if (!drained_dio) {
			if (*iolock == XFS_IOLOCK_SHARED) {
				xfs_rw_iunlock(ip, *iolock);
				*iolock = XFS_IOLOCK_EXCL;
				xfs_rw_ilock(ip, *iolock);
				iov_iter_reexpand(from, count);
			}
			/*
			 * We now have an IO submission barrier in place, but
			 * AIO can do EOF updates during IO completion and hence
			 * we now need to wait for all of them to drain. Non-AIO
			 * DIO will have drained before we are given the
			 * XFS_IOLOCK_EXCL, and so for most cases this wait is a
			 * no-op.
			 */
			inode_dio_wait(inode);
			drained_dio = true;
			goto restart;
		}
		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
		if (error)
			return error;
	} else
		spin_unlock(&ip->i_flags_lock);

	/*
	 * Updating the timestamps will grab the ilock again from
	 * xfs_fs_dirty_inode, so we have to call it after dropping the
	 * lock above.  Eventually we should look into a way to avoid
	 * the pointless lock roundtrip.
	 */
	if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
		error = file_update_time(file);
		if (error)
			return error;
	}

	/*
	 * If we're writing the file then make sure to clear the setuid and
	 * setgid bits if the process is not being run by root.  This keeps
	 * people from modifying setuid and setgid binaries.
	 */
	if (!IS_NOSEC(inode))
		return file_remove_privs(file);
	return 0;
}

/*
 * xfs_file_dio_aio_write - handle direct IO writes
 *
 * Lock the inode appropriately to prepare for and issue a direct IO write.
 * By separating it from the buffered write path we remove all the tricky to
 * follow locking changes and looping.
 *
 * If there are cached pages or we're extending the file, we need IOLOCK_EXCL
 * until we're sure the bytes at the new EOF have been zeroed and/or the cached
 * pages are flushed out.
 *
 * In most cases the direct IO writes will be done holding IOLOCK_SHARED
 * allowing them to be done in parallel with reads and other direct IO writes.
 * However, if the IO is not aligned to filesystem blocks, the direct IO layer
 * needs to do sub-block zeroing and that requires serialisation against other
 * direct IOs to the same block. In this case we need to serialise the
 * submission of the unaligned IOs so that we don't get racing block zeroing in
 * the dio layer.  To avoid the problem with aio, we also need to wait for
 * outstanding IOs to complete so that unwritten extent conversion is completed
 * before we try to map the overlapping block. This is currently implemented by
 * hitting it with a big hammer (i.e. inode_dio_wait()).
 *
 * Returns with locks held indicated by @iolock and errors indicated by
 * negative return values.
 */
STATIC ssize_t
xfs_file_dio_aio_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	ssize_t			ret = 0;
	int			unaligned_io = 0;
	int			iolock;
	size_t			count = iov_iter_count(from);
	loff_t			pos = iocb->ki_pos;
	loff_t			end;
	struct iov_iter		data;
	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
					mp->m_rtdev_targp : mp->m_ddev_targp;

	/* DIO must be aligned to device logical sector size */
	if (!IS_DAX(inode) && ((pos | count) & target->bt_logical_sectormask))
		return -EINVAL;

	/* "unaligned" here means not aligned to a filesystem block */
	if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
		unaligned_io = 1;

	/*
	 * We don't need to take an exclusive lock unless there page cache needs
	 * to be invalidated or unaligned IO is being executed. We don't need to
	 * consider the EOF extension case here because
	 * xfs_file_aio_write_checks() will relock the inode as necessary for
	 * EOF zeroing cases and fill out the new inode size as appropriate.
	 */
	if (unaligned_io || mapping->nrpages)
		iolock = XFS_IOLOCK_EXCL;
	else
		iolock = XFS_IOLOCK_SHARED;
	xfs_rw_ilock(ip, iolock);

	/*
	 * Recheck if there are cached pages that need invalidate after we got
	 * the iolock to protect against other threads adding new pages while
	 * we were waiting for the iolock.
	 */
	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
		xfs_rw_iunlock(ip, iolock);
		iolock = XFS_IOLOCK_EXCL;
		xfs_rw_ilock(ip, iolock);
	}

	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;
	count = iov_iter_count(from);
	pos = iocb->ki_pos;
	end = pos + count - 1;

	/*
	 * See xfs_file_read_iter() for why we do a full-file flush here.
	 */
	if (mapping->nrpages) {
		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
		if (ret)
			goto out;
		/*
		 * Invalidate whole pages. This can return an error if we fail
		 * to invalidate a page, but this should never happen on XFS.
		 * Warn if it does fail.
		 */
		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
		WARN_ON_ONCE(ret);
		ret = 0;
	}

	/*
	 * If we are doing unaligned IO, wait for all other IO to drain,
	 * otherwise demote the lock if we had to flush cached pages
	 */
	if (unaligned_io)
		inode_dio_wait(inode);
	else if (iolock == XFS_IOLOCK_EXCL) {
		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
		iolock = XFS_IOLOCK_SHARED;
	}

	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);

	data = *from;
	ret = mapping->a_ops->direct_IO(iocb, &data, pos);

	/* see generic_file_direct_write() for why this is necessary */
	if (mapping->nrpages) {
		invalidate_inode_pages2_range(mapping,
					      pos >> PAGE_CACHE_SHIFT,
					      end >> PAGE_CACHE_SHIFT);
	}

	if (ret > 0) {
		pos += ret;
		iov_iter_advance(from, ret);
		iocb->ki_pos = pos;
	}
out:
	xfs_rw_iunlock(ip, iolock);

	/*
	 * No fallback to buffered IO on errors for XFS. DAX can result in
	 * partial writes, but direct IO will either complete fully or fail.
	 */
	ASSERT(ret < 0 || ret == count || IS_DAX(VFS_I(ip)));
	return ret;
}

STATIC ssize_t
xfs_file_buffered_aio_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			ret;
	int			enospc = 0;
	int			iolock = XFS_IOLOCK_EXCL;

	xfs_rw_ilock(ip, iolock);

	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = inode_to_bdi(inode);

write_retry:
	trace_xfs_file_buffered_write(ip, iov_iter_count(from),
				      iocb->ki_pos, 0);
	ret = generic_perform_write(file, from, iocb->ki_pos);
	if (likely(ret >= 0))
		iocb->ki_pos += ret;

	/*
	 * If we hit a space limit, try to free up some lingering preallocated
	 * space before returning an error. In the case of ENOSPC, first try to
	 * write back all dirty inodes to free up some of the excess reserved
	 * metadata space. This reduces the chances that the eofblocks scan
	 * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
	 * also behaves as a filter to prevent too many eofblocks scans from
	 * running at the same time.
	 */
	if (ret == -EDQUOT && !enospc) {
		enospc = xfs_inode_free_quota_eofblocks(ip);
		if (enospc)
			goto write_retry;
	} else if (ret == -ENOSPC && !enospc) {
		struct xfs_eofblocks eofb = {0};

		enospc = 1;
		xfs_flush_inodes(ip->i_mount);
		eofb.eof_scan_owner = ip->i_ino; /* for locking */
		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
		goto write_retry;
	}

	current->backing_dev_info = NULL;
out:
	xfs_rw_iunlock(ip, iolock);
	return ret;
}

STATIC ssize_t
xfs_file_write_iter(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			ret;
	size_t			ocount = iov_iter_count(from);

	XFS_STATS_INC(ip->i_mount, xs_write_calls);

	if (ocount == 0)
		return 0;

	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return -EIO;

	if ((iocb->ki_flags & IOCB_DIRECT) || IS_DAX(inode))
		ret = xfs_file_dio_aio_write(iocb, from);
	else
		ret = xfs_file_buffered_aio_write(iocb, from);

	if (ret > 0) {
		ssize_t err;

		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);

		/* Handle various SYNC-type writes */
		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}

#define	XFS_FALLOC_FL_SUPPORTED						\
		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
		 FALLOC_FL_INSERT_RANGE)

STATIC long
xfs_file_fallocate(
	struct file		*file,
	int			mode,
	loff_t			offset,
	loff_t			len)
{
	struct inode		*inode = file_inode(file);
	struct xfs_inode	*ip = XFS_I(inode);
	long			error;
	enum xfs_prealloc_flags	flags = 0;
	uint			iolock = XFS_IOLOCK_EXCL;
	loff_t			new_size = 0;
	bool			do_file_insert = 0;

	if (!S_ISREG(inode->i_mode))
		return -EINVAL;
	if (mode & ~XFS_FALLOC_FL_SUPPORTED)
		return -EOPNOTSUPP;

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

	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
	iolock |= XFS_MMAPLOCK_EXCL;

	if (mode & FALLOC_FL_PUNCH_HOLE) {
		error = xfs_free_file_space(ip, offset, len);
		if (error)
			goto out_unlock;
	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
		unsigned int blksize_mask = i_blocksize(inode) - 1;

		if (offset & blksize_mask || len & blksize_mask) {
			error = -EINVAL;
			goto out_unlock;
		}

		/*
		 * There is no need to overlap collapse range with EOF,
		 * in which case it is effectively a truncate operation
		 */
		if (offset + len >= i_size_read(inode)) {
			error = -EINVAL;
			goto out_unlock;
		}

		new_size = i_size_read(inode) - len;

		error = xfs_collapse_file_space(ip, offset, len);
		if (error)
			goto out_unlock;
	} else if (mode & FALLOC_FL_INSERT_RANGE) {
		unsigned int blksize_mask = i_blocksize(inode) - 1;

		new_size = i_size_read(inode) + len;
		if (offset & blksize_mask || len & blksize_mask) {
			error = -EINVAL;
			goto out_unlock;
		}

		/* check the new inode size does not wrap through zero */
		if (new_size > inode->i_sb->s_maxbytes) {
			error = -EFBIG;
			goto out_unlock;
		}

		/* Offset should be less than i_size */
		if (offset >= i_size_read(inode)) {
			error = -EINVAL;
			goto out_unlock;
		}
		do_file_insert = 1;
	} else {
		flags |= XFS_PREALLOC_SET;

		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		    offset + len > i_size_read(inode)) {
			new_size = offset + len;
			error = inode_newsize_ok(inode, new_size);
			if (error)
				goto out_unlock;
		}

		if (mode & FALLOC_FL_ZERO_RANGE)
			error = xfs_zero_file_space(ip, offset, len);
		else
			error = xfs_alloc_file_space(ip, offset, len,
						     XFS_BMAPI_PREALLOC);
		if (error)
			goto out_unlock;
	}

	if (file->f_flags & O_DSYNC)
		flags |= XFS_PREALLOC_SYNC;

	error = xfs_update_prealloc_flags(ip, flags);
	if (error)
		goto out_unlock;

	/* Change file size if needed */
	if (new_size) {
		struct iattr iattr;

		iattr.ia_valid = ATTR_SIZE;
		iattr.ia_size = new_size;
		error = xfs_setattr_size(ip, &iattr);
		if (error)
			goto out_unlock;
	}

	/*
	 * Perform hole insertion now that the file size has been
	 * updated so that if we crash during the operation we don't
	 * leave shifted extents past EOF and hence losing access to
	 * the data that is contained within them.
	 */
	if (do_file_insert)
		error = xfs_insert_file_space(ip, offset, len);

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


STATIC int
xfs_file_open(
	struct inode	*inode,
	struct file	*file)
{
	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
		return -EFBIG;
	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
		return -EIO;
	return 0;
}

STATIC int
xfs_dir_open(
	struct inode	*inode,
	struct file	*file)
{
	struct xfs_inode *ip = XFS_I(inode);
	int		mode;
	int		error;

	error = xfs_file_open(inode, file);
	if (error)
		return error;

	/*
	 * If there are any blocks, read-ahead block 0 as we're almost
	 * certain to have the next operation be a read there.
	 */
	mode = xfs_ilock_data_map_shared(ip);
	if (ip->i_d.di_nextents > 0)
		xfs_dir3_data_readahead(ip, 0, -1);
	xfs_iunlock(ip, mode);
	return 0;
}

STATIC int
xfs_file_release(
	struct inode	*inode,
	struct file	*filp)
{
	return xfs_release(XFS_I(inode));
}

STATIC int
xfs_file_readdir(
	struct file	*file,
	struct dir_context *ctx)
{
	struct inode	*inode = file_inode(file);
	xfs_inode_t	*ip = XFS_I(inode);
	size_t		bufsize;

	/*
	 * The Linux API doesn't pass down the total size of the buffer
	 * we read into down to the filesystem.  With the filldir concept
	 * it's not needed for correct information, but the XFS dir2 leaf
	 * code wants an estimate of the buffer size to calculate it's
	 * readahead window and size the buffers used for mapping to
	 * physical blocks.
	 *
	 * Try to give it an estimate that's good enough, maybe at some
	 * point we can change the ->readdir prototype to include the
	 * buffer size.  For now we use the current glibc buffer size.
	 */
	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);

	return xfs_readdir(ip, ctx, bufsize);
}

/*
 * This type is designed to indicate the type of offset we would like
 * to search from page cache for xfs_seek_hole_data().
 */
enum {
	HOLE_OFF = 0,
	DATA_OFF,
};

/*
 * Lookup the desired type of offset from the given page.
 *
 * On success, return true and the offset argument will point to the
 * start of the region that was found.  Otherwise this function will
 * return false and keep the offset argument unchanged.
 */
STATIC bool
xfs_lookup_buffer_offset(
	struct page		*page,
	loff_t			*offset,
	unsigned int		type)
{
	loff_t			lastoff = page_offset(page);
	bool			found = false;
	struct buffer_head	*bh, *head;

	bh = head = page_buffers(page);
	do {
		/*
		 * Unwritten extents that have data in the page
		 * cache covering them can be identified by the
		 * BH_Unwritten state flag.  Pages with multiple
		 * buffers might have a mix of holes, data and
		 * unwritten extents - any buffer with valid
		 * data in it should have BH_Uptodate flag set
		 * on it.
		 */
		if (buffer_unwritten(bh) ||
		    buffer_uptodate(bh)) {
			if (type == DATA_OFF)
				found = true;
		} else {
			if (type == HOLE_OFF)
				found = true;
		}

		if (found) {
			*offset = lastoff;
			break;
		}
		lastoff += bh->b_size;
	} while ((bh = bh->b_this_page) != head);

	return found;
}

/*
 * This routine is called to find out and return a data or hole offset
 * from the page cache for unwritten extents according to the desired
 * type for xfs_seek_hole_data().
 *
 * The argument offset is used to tell where we start to search from the
 * page cache.  Map is used to figure out the end points of the range to
 * lookup pages.
 *
 * Return true if the desired type of offset was found, and the argument
 * offset is filled with that address.  Otherwise, return false and keep
 * offset unchanged.
 */
STATIC bool
xfs_find_get_desired_pgoff(
	struct inode		*inode,
	struct xfs_bmbt_irec	*map,
	unsigned int		type,
	loff_t			*offset)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct pagevec		pvec;
	pgoff_t			index;
	pgoff_t			end;
	loff_t			endoff;
	loff_t			startoff = *offset;
	loff_t			lastoff = startoff;
	bool			found = false;

	pagevec_init(&pvec, 0);

	index = startoff >> PAGE_CACHE_SHIFT;
	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
	end = endoff >> PAGE_CACHE_SHIFT;
	do {
		int		want;
		unsigned	nr_pages;
		unsigned int	i;

		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
					  want);
		/*
		 * No page mapped into given range.  If we are searching holes
		 * and if this is the first time we got into the loop, it means
		 * that the given offset is landed in a hole, return it.
		 *
		 * If we have already stepped through some block buffers to find
		 * holes but they all contains data.  In this case, the last
		 * offset is already updated and pointed to the end of the last
		 * mapped page, if it does not reach the endpoint to search,
		 * that means there should be a hole between them.
		 */
		if (nr_pages == 0) {
			/* Data search found nothing */
			if (type == DATA_OFF)
				break;

			ASSERT(type == HOLE_OFF);
			if (lastoff == startoff || lastoff < endoff) {
				found = true;
				*offset = lastoff;
			}
			break;
		}

		for (i = 0; i < nr_pages; i++) {
			struct page	*page = pvec.pages[i];
			loff_t		b_offset;

			/*
			 * At this point, the page may be truncated or
			 * invalidated (changing page->mapping to NULL),
			 * or even swizzled back from swapper_space to tmpfs
			 * file mapping. However, page->index will not change
			 * because we have a reference on the page.
			 *
			 * If current page offset is beyond where we've ended,
			 * we've found a hole.
			 */
			if (type == HOLE_OFF && lastoff < endoff &&
			    lastoff < page_offset(pvec.pages[i])) {
				found = true;
				*offset = lastoff;
				goto out;
			}
			/* Searching done if the page index is out of range. */
			if (page->index > end)
				goto out;

			lock_page(page);
			/*
			 * Page truncated or invalidated(page->mapping == NULL).
			 * We can freely skip it and proceed to check the next
			 * page.
			 */
			if (unlikely(page->mapping != inode->i_mapping)) {
				unlock_page(page);
				continue;
			}

			if (!page_has_buffers(page)) {
				unlock_page(page);
				continue;
			}

			found = xfs_lookup_buffer_offset(page, &b_offset, type);
			if (found) {
				/*
				 * The found offset may be less than the start
				 * point to search if this is the first time to
				 * come here.
				 */
				*offset = max_t(loff_t, startoff, b_offset);
				unlock_page(page);
				goto out;
			}

			/*
			 * We either searching data but nothing was found, or
			 * searching hole but found a data buffer.  In either
			 * case, probably the next page contains the desired
			 * things, update the last offset to it so.
			 */
			lastoff = page_offset(page) + PAGE_SIZE;
			unlock_page(page);
		}

		/*
		 * The number of returned pages less than our desired, search
		 * done.  In this case, nothing was found for searching data,
		 * but we found a hole behind the last offset.
		 */
		if (nr_pages < want) {
			if (type == HOLE_OFF) {
				*offset = lastoff;
				found = true;
			}
			break;
		}

		index = pvec.pages[i - 1]->index + 1;
		pagevec_release(&pvec);
	} while (index <= end);

out:
	pagevec_release(&pvec);
	return found;
}

STATIC loff_t
xfs_seek_hole_data(
	struct file		*file,
	loff_t			start,
	int			whence)
{
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	loff_t			uninitialized_var(offset);
	xfs_fsize_t		isize;
	xfs_fileoff_t		fsbno;
	xfs_filblks_t		end;
	uint			lock;
	int			error;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	lock = xfs_ilock_data_map_shared(ip);

	isize = i_size_read(inode);
	if (start >= isize) {
		error = -ENXIO;
		goto out_unlock;
	}

	/*
	 * Try to read extents from the first block indicated
	 * by fsbno to the end block of the file.
	 */
	fsbno = XFS_B_TO_FSBT(mp, start);
	end = XFS_B_TO_FSB(mp, isize);

	for (;;) {
		struct xfs_bmbt_irec	map[2];
		int			nmap = 2;
		unsigned int		i;

		error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
				       XFS_BMAPI_ENTIRE);
		if (error)
			goto out_unlock;

		/* No extents at given offset, must be beyond EOF */
		if (nmap == 0) {
			error = -ENXIO;
			goto out_unlock;
		}

		for (i = 0; i < nmap; i++) {
			offset = max_t(loff_t, start,
				       XFS_FSB_TO_B(mp, map[i].br_startoff));

			/* Landed in the hole we wanted? */
			if (whence == SEEK_HOLE &&
			    map[i].br_startblock == HOLESTARTBLOCK)
				goto out;

			/* Landed in the data extent we wanted? */
			if (whence == SEEK_DATA &&
			    (map[i].br_startblock == DELAYSTARTBLOCK ||
			     (map[i].br_state == XFS_EXT_NORM &&
			      !isnullstartblock(map[i].br_startblock))))
				goto out;

			/*
			 * Landed in an unwritten extent, try to search
			 * for hole or data from page cache.
			 */
			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
				if (xfs_find_get_desired_pgoff(inode, &map[i],
				      whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
							&offset))
					goto out;
			}
		}

		/*
		 * We only received one extent out of the two requested. This
		 * means we've hit EOF and didn't find what we are looking for.
		 */
		if (nmap == 1) {
			/*
			 * If we were looking for a hole, set offset to
			 * the end of the file (i.e., there is an implicit
			 * hole at the end of any file).
		 	 */
			if (whence == SEEK_HOLE) {
				offset = isize;
				break;
			}
			/*
			 * If we were looking for data, it's nowhere to be found
			 */
			ASSERT(whence == SEEK_DATA);
			error = -ENXIO;
			goto out_unlock;
		}

		ASSERT(i > 1);

		/*
		 * Nothing was found, proceed to the next round of search
		 * if the next reading offset is not at or beyond EOF.
		 */
		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
		start = XFS_FSB_TO_B(mp, fsbno);
		if (start >= isize) {
			if (whence == SEEK_HOLE) {
				offset = isize;
				break;
			}
			ASSERT(whence == SEEK_DATA);
			error = -ENXIO;
			goto out_unlock;
		}
	}

out:
	/*
	 * If at this point we have found the hole we wanted, the returned
	 * offset may be bigger than the file size as it may be aligned to
	 * page boundary for unwritten extents.  We need to deal with this
	 * situation in particular.
	 */
	if (whence == SEEK_HOLE)
		offset = min_t(loff_t, offset, isize);
	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);

out_unlock:
	xfs_iunlock(ip, lock);

	if (error)
		return error;
	return offset;
}

STATIC loff_t
xfs_file_llseek(
	struct file	*file,
	loff_t		offset,
	int		whence)
{
	switch (whence) {
	case SEEK_END:
	case SEEK_CUR:
	case SEEK_SET:
		return generic_file_llseek(file, offset, whence);
	case SEEK_HOLE:
	case SEEK_DATA:
		return xfs_seek_hole_data(file, offset, whence);
	default:
		return -EINVAL;
	}
}

/*
 * Locking for serialisation of IO during page faults. This results in a lock
 * ordering of:
 *
 * mmap_sem (MM)
 *   sb_start_pagefault(vfs, freeze)
 *     i_mmaplock (XFS - truncate serialisation)
 *       page_lock (MM)
 *         i_lock (XFS - extent map serialisation)
 */

/*
 * mmap()d file has taken write protection fault and is being made writable. We
 * can set the page state up correctly for a writable page, which means we can
 * do correct delalloc accounting (ENOSPC checking!) and unwritten extent
 * mapping.
 */
STATIC int
xfs_filemap_page_mkwrite(
	struct vm_area_struct	*vma,
	struct vm_fault		*vmf)
{
	struct inode		*inode = file_inode(vma->vm_file);
	int			ret;

	trace_xfs_filemap_page_mkwrite(XFS_I(inode));

	sb_start_pagefault(inode->i_sb);
	file_update_time(vma->vm_file);
	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	if (IS_DAX(inode)) {
		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
	} else {
		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
		ret = block_page_mkwrite_return(ret);
	}

	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	sb_end_pagefault(inode->i_sb);

	return ret;
}

STATIC int
xfs_filemap_fault(
	struct vm_area_struct	*vma,
	struct vm_fault		*vmf)
{
	struct inode		*inode = file_inode(vma->vm_file);
	int			ret;

	trace_xfs_filemap_fault(XFS_I(inode));

	/* DAX can shortcut the normal fault path on write faults! */
	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
		return xfs_filemap_page_mkwrite(vma, vmf);

	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	if (IS_DAX(inode)) {
		/*
		 * we do not want to trigger unwritten extent conversion on read
		 * faults - that is unnecessary overhead and would also require
		 * changes to xfs_get_blocks_direct() to map unwritten extent
		 * ioend for conversion on read-only mappings.
		 */
		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
	} else
		ret = filemap_fault(vma, vmf);
	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	return ret;
}

/*
 * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
 * both read and write faults. Hence we need to handle both cases. There is no
 * ->pmd_mkwrite callout for huge pages, so we have a single function here to
 * handle both cases here. @flags carries the information on the type of fault
 * occuring.
 */
STATIC int
xfs_filemap_pmd_fault(
	struct vm_area_struct	*vma,
	unsigned long		addr,
	pmd_t			*pmd,
	unsigned int		flags)
{
	struct inode		*inode = file_inode(vma->vm_file);
	struct xfs_inode	*ip = XFS_I(inode);
	int			ret;

	if (!IS_DAX(inode))
		return VM_FAULT_FALLBACK;

	trace_xfs_filemap_pmd_fault(ip);

	if (flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(inode->i_sb);
		file_update_time(vma->vm_file);
	}

	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
			      NULL);
	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	if (flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(inode->i_sb);

	return ret;
}

/*
 * pfn_mkwrite was originally inteneded to ensure we capture time stamp
 * updates on write faults. In reality, it's need to serialise against
 * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
 * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
 * barrier in place.
 */
static int
xfs_filemap_pfn_mkwrite(
	struct vm_area_struct	*vma,
	struct vm_fault		*vmf)
{

	struct inode		*inode = file_inode(vma->vm_file);
	struct xfs_inode	*ip = XFS_I(inode);
	int			ret = VM_FAULT_NOPAGE;
	loff_t			size;

	trace_xfs_filemap_pfn_mkwrite(ip);

	sb_start_pagefault(inode->i_sb);
	file_update_time(vma->vm_file);

	/* check if the faulting page hasn't raced with truncate */
	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (vmf->pgoff >= size)
		ret = VM_FAULT_SIGBUS;
	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
	sb_end_pagefault(inode->i_sb);
	return ret;

}

static const struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= xfs_filemap_fault,
	.pmd_fault	= xfs_filemap_pmd_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= xfs_filemap_page_mkwrite,
	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
};

STATIC int
xfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	file_accessed(filp);
	vma->vm_ops = &xfs_file_vm_ops;
	if (IS_DAX(file_inode(filp)))
		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
	return 0;
}

const struct file_operations xfs_file_operations = {
	.llseek		= xfs_file_llseek,
	.read_iter	= xfs_file_read_iter,
	.write_iter	= xfs_file_write_iter,
	.splice_read	= xfs_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
	.fallocate	= xfs_file_fallocate,
};

const struct file_operations xfs_dir_file_operations = {
	.open		= xfs_dir_open,
	.read		= generic_read_dir,
	.iterate	= xfs_file_readdir,
	.llseek		= generic_file_llseek,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.fsync		= xfs_dir_fsync,
};