summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_file.c
blob: 5eaef2c17293095d9505914140f88950e791dfcd (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
// 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_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 "xfs_iomap.h"
#include "xfs_reflink.h"

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

static const struct vm_operations_struct xfs_file_vm_ops;

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

	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
			0, 0, 0, &tp);
	if (error)
		return error;

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

	if (!(flags & XFS_PREALLOC_INVISIBLE)) {
		VFS_I(ip)->i_mode &= ~S_ISUID;
		if (VFS_I(ip)->i_mode & S_IXGRP)
			VFS_I(ip)->i_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 = file_write_and_wait_range(file, start, end);
	if (error)
		return error;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	xfs_iflags_clear(ip, XFS_ITRUNCATED);

	/*
	 * 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 (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
	    mp->m_logdev_targp == mp->m_ddev_targp)
		xfs_blkdev_issue_flush(mp->m_ddev_targp);

	return error;
}

STATIC ssize_t
xfs_file_dio_aio_read(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct xfs_inode	*ip = XFS_I(file_inode(iocb->ki_filp));
	size_t			count = iov_iter_count(to);
	ssize_t			ret;

	trace_xfs_file_direct_read(ip, count, iocb->ki_pos);

	if (!count)
		return 0; /* skip atime */

	file_accessed(iocb->ki_filp);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	return ret;
}

static noinline ssize_t
xfs_file_dax_read(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct xfs_inode	*ip = XFS_I(iocb->ki_filp->f_mapping->host);
	size_t			count = iov_iter_count(to);
	ssize_t			ret = 0;

	trace_xfs_file_dax_read(ip, count, iocb->ki_pos);

	if (!count)
		return 0; /* skip atime */

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
			return -EAGAIN;
	} else {
		xfs_ilock(ip, XFS_IOLOCK_SHARED);
	}

	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	file_accessed(iocb->ki_filp);
	return ret;
}

STATIC ssize_t
xfs_file_buffered_aio_read(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct xfs_inode	*ip = XFS_I(file_inode(iocb->ki_filp));
	ssize_t			ret;

	trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
			return -EAGAIN;
	} else {
		xfs_ilock(ip, XFS_IOLOCK_SHARED);
	}
	ret = generic_file_read_iter(iocb, to);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	return ret;
}

STATIC ssize_t
xfs_file_read_iter(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct inode		*inode = file_inode(iocb->ki_filp);
	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
	ssize_t			ret = 0;

	XFS_STATS_INC(mp, xs_read_calls);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (IS_DAX(inode))
		ret = xfs_file_dax_read(iocb, to);
	else if (iocb->ki_flags & IOCB_DIRECT)
		ret = xfs_file_dio_aio_read(iocb, to);
	else
		ret = xfs_file_buffered_aio_read(iocb, to);

	if (ret > 0)
		XFS_STATS_ADD(mp, xs_read_bytes, ret);
	return ret;
}

/*
 * 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;
	loff_t			isize;

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

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

	/*
	 * For changing security info in file_remove_privs() we need i_rwsem
	 * exclusively.
	 */
	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
		xfs_iunlock(ip, *iolock);
		*iolock = XFS_IOLOCK_EXCL;
		xfs_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);
	isize = i_size_read(inode);
	if (iocb->ki_pos > isize) {
		spin_unlock(&ip->i_flags_lock);
		if (!drained_dio) {
			if (*iolock == XFS_IOLOCK_SHARED) {
				xfs_iunlock(ip, *iolock);
				*iolock = XFS_IOLOCK_EXCL;
				xfs_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;
		}
	
		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
				NULL, &xfs_iomap_ops);
		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;
}

static int
xfs_dio_write_end_io(
	struct kiocb		*iocb,
	ssize_t			size,
	unsigned		flags)
{
	struct inode		*inode = file_inode(iocb->ki_filp);
	struct xfs_inode	*ip = XFS_I(inode);
	loff_t			offset = iocb->ki_pos;
	int			error = 0;

	trace_xfs_end_io_direct_write(ip, offset, size);

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

	if (size <= 0)
		return size;

	/*
	 * Capture amount written on completion as we can't reliably account
	 * for it on submission.
	 */
	XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);

	if (flags & IOMAP_DIO_COW) {
		error = xfs_reflink_end_cow(ip, offset, size);
		if (error)
			return error;
	}

	/*
	 * Unwritten conversion updates the in-core isize after extent
	 * conversion but before updating the on-disk size. Updating isize any
	 * earlier allows a racing dio read to find unwritten extents before
	 * they are converted.
	 */
	if (flags & IOMAP_DIO_UNWRITTEN)
		return xfs_iomap_write_unwritten(ip, offset, size, true);

	/*
	 * We need to update the in-core inode size here so that we don't end up
	 * with the on-disk inode size being outside the in-core inode size. We
	 * have no other method of updating EOF for AIO, so always do it here
	 * if necessary.
	 *
	 * We need to lock the test/set EOF update as we can be racing with
	 * other IO completions here to update the EOF. Failing to serialise
	 * here can result in EOF moving backwards and Bad Things Happen when
	 * that occurs.
	 */
	spin_lock(&ip->i_flags_lock);
	if (offset + size > i_size_read(inode)) {
		i_size_write(inode, offset + size);
		spin_unlock(&ip->i_flags_lock);
		error = xfs_setfilesize(ip, offset, size);
	} else {
		spin_unlock(&ip->i_flags_lock);
	}

	return error;
}

/*
 * 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);
	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 ((iocb->ki_pos | count) & target->bt_logical_sectormask)
		return -EINVAL;

	/*
	 * Don't take the exclusive iolock here unless the I/O is unaligned to
	 * the file system block size.  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 ((iocb->ki_pos & mp->m_blockmask) ||
	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
		unaligned_io = 1;

		/*
		 * We can't properly handle unaligned direct I/O to reflink
		 * files yet, as we can't unshare a partial block.
		 */
		if (xfs_is_reflink_inode(ip)) {
			trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
			return -EREMCHG;
		}
		iolock = XFS_IOLOCK_EXCL;
	} else {
		iolock = XFS_IOLOCK_SHARED;
	}

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!xfs_ilock_nowait(ip, iolock))
			return -EAGAIN;
	} else {
		xfs_ilock(ip, iolock);
	}

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

	/*
	 * If we are doing unaligned IO, wait for all other IO to drain,
	 * otherwise demote the lock if we had to take the exclusive lock
	 * for other reasons in xfs_file_aio_write_checks.
	 */
	if (unaligned_io) {
		/* If we are going to wait for other DIO to finish, bail */
		if (iocb->ki_flags & IOCB_NOWAIT) {
			if (atomic_read(&inode->i_dio_count))
				return -EAGAIN;
		} else {
			inode_dio_wait(inode);
		}
	} else if (iolock == XFS_IOLOCK_EXCL) {
		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
		iolock = XFS_IOLOCK_SHARED;
	}

	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
out:
	xfs_iunlock(ip, iolock);

	/*
	 * No fallback to buffered IO on errors for XFS, direct IO will either
	 * complete fully or fail.
	 */
	ASSERT(ret < 0 || ret == count);
	return ret;
}

static noinline ssize_t
xfs_file_dax_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct inode		*inode = iocb->ki_filp->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	int			iolock = XFS_IOLOCK_EXCL;
	ssize_t			ret, error = 0;
	size_t			count;
	loff_t			pos;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!xfs_ilock_nowait(ip, iolock))
			return -EAGAIN;
	} else {
		xfs_ilock(ip, iolock);
	}

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

	pos = iocb->ki_pos;
	count = iov_iter_count(from);

	trace_xfs_file_dax_write(ip, count, pos);
	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
		i_size_write(inode, iocb->ki_pos);
		error = xfs_setfilesize(ip, pos, ret);
	}
out:
	xfs_iunlock(ip, iolock);
	if (error)
		return error;

	if (ret > 0) {
		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);

		/* Handle various SYNC-type writes */
		ret = generic_write_sync(iocb, ret);
	}
	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;

	if (iocb->ki_flags & IOCB_NOWAIT)
		return -EOPNOTSUPP;

write_retry:
	iolock = XFS_IOLOCK_EXCL;
	xfs_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);

	trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos);
	ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
	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) {
		xfs_iunlock(ip, iolock);
		enospc = xfs_inode_free_quota_eofblocks(ip);
		if (enospc)
			goto write_retry;
		enospc = xfs_inode_free_quota_cowblocks(ip);
		if (enospc)
			goto write_retry;
		iolock = 0;
	} else if (ret == -ENOSPC && !enospc) {
		struct xfs_eofblocks eofb = {0};

		enospc = 1;
		xfs_flush_inodes(ip->i_mount);

		xfs_iunlock(ip, iolock);
		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
		goto write_retry;
	}

	current->backing_dev_info = NULL;
out:
	if (iolock)
		xfs_iunlock(ip, iolock);

	if (ret > 0) {
		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
		/* Handle various SYNC-type writes */
		ret = generic_write_sync(iocb, ret);
	}
	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 (IS_DAX(inode))
		return xfs_file_dax_write(iocb, from);

	if (iocb->ki_flags & IOCB_DIRECT) {
		/*
		 * Allow a directio write to fall back to a buffered
		 * write *only* in the case that we're doing a reflink
		 * CoW.  In all other directio scenarios we do not
		 * allow an operation to fall back to buffered mode.
		 */
		ret = xfs_file_dio_aio_write(iocb, from);
		if (ret != -EREMCHG)
			return ret;
	}

	return xfs_file_buffered_aio_write(iocb, from);
}

static void
xfs_wait_dax_page(
	struct inode		*inode)
{
	struct xfs_inode        *ip = XFS_I(inode);

	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
	schedule();
	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
}

static int
xfs_break_dax_layouts(
	struct inode		*inode,
	bool			*retry)
{
	struct page		*page;

	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));

	page = dax_layout_busy_page(inode->i_mapping);
	if (!page)
		return 0;

	*retry = true;
	return ___wait_var_event(&page->_refcount,
			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
			0, 0, xfs_wait_dax_page(inode));
}

int
xfs_break_layouts(
	struct inode		*inode,
	uint			*iolock,
	enum layout_break_reason reason)
{
	bool			retry;
	int			error;

	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));

	do {
		retry = false;
		switch (reason) {
		case BREAK_UNMAP:
			error = xfs_break_dax_layouts(inode, &retry);
			if (error || retry)
				break;
			/* fall through */
		case BREAK_WRITE:
			error = xfs_break_leased_layouts(inode, iolock, &retry);
			break;
		default:
			WARN_ON_ONCE(1);
			error = -EINVAL;
		}
	} while (error == 0 && retry);

	return error;
}

#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 | FALLOC_FL_UNSHARE_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 | XFS_MMAPLOCK_EXCL;
	loff_t			new_size = 0;
	bool			do_file_insert = false;

	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, BREAK_UNMAP);
	if (error)
		goto out_unlock;

	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;
		loff_t		isize = i_size_read(inode);

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

		/*
		 * New inode size must not exceed ->s_maxbytes, accounting for
		 * possible signed overflow.
		 */
		if (inode->i_sb->s_maxbytes - isize < len) {
			error = -EFBIG;
			goto out_unlock;
		}
		new_size = isize + len;

		/* Offset should be less than i_size */
		if (offset >= isize) {
			error = -EINVAL;
			goto out_unlock;
		}
		do_file_insert = true;
	} 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 {
			if (mode & FALLOC_FL_UNSHARE_RANGE) {
				error = xfs_reflink_unshare(ip, offset, len);
				if (error)
					goto out_unlock;
			}
			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_vn_setattr_size(file_dentry(file), &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_clone_range(
	struct file	*file_in,
	loff_t		pos_in,
	struct file	*file_out,
	loff_t		pos_out,
	u64		len)
{
	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
				     len, false);
}

STATIC ssize_t
xfs_file_dedupe_range(
	struct file	*src_file,
	u64		loff,
	u64		len,
	struct file	*dst_file,
	u64		dst_loff)
{
	struct inode	*srci = file_inode(src_file);
	u64		max_dedupe;
	int		error;

	/*
	 * Since we have to read all these pages in to compare them, cut
	 * it off at MAX_RW_COUNT/2 rounded down to the nearest block.
	 * That means we won't do more than MAX_RW_COUNT IO per request.
	 */
	max_dedupe = (MAX_RW_COUNT >> 1) & ~(i_blocksize(srci) - 1);
	if (len > max_dedupe)
		len = max_dedupe;
	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
				     len, true);
	if (error)
		return error;
	return len;
}

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;
	file->f_mode |= FMODE_NOWAIT;
	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)
		error = xfs_dir3_data_readahead(ip, 0, -1);
	xfs_iunlock(ip, mode);
	return error;
}

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, XFS_READDIR_BUFSIZE, ip->i_d.di_size);

	return xfs_readdir(NULL, ip, ctx, bufsize);
}

STATIC loff_t
xfs_file_llseek(
	struct file	*file,
	loff_t		offset,
	int		whence)
{
	struct inode		*inode = file->f_mapping->host;

	if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount))
		return -EIO;

	switch (whence) {
	default:
		return generic_file_llseek(file, offset, whence);
	case SEEK_HOLE:
		offset = iomap_seek_hole(inode, offset, &xfs_iomap_ops);
		break;
	case SEEK_DATA:
		offset = iomap_seek_data(inode, offset, &xfs_iomap_ops);
		break;
	}

	if (offset < 0)
		return offset;
	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
}

/*
 * 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)
 */
static vm_fault_t
__xfs_filemap_fault(
	struct vm_fault		*vmf,
	enum page_entry_size	pe_size,
	bool			write_fault)
{
	struct inode		*inode = file_inode(vmf->vma->vm_file);
	struct xfs_inode	*ip = XFS_I(inode);
	vm_fault_t		ret;

	trace_xfs_filemap_fault(ip, pe_size, write_fault);

	if (write_fault) {
		sb_start_pagefault(inode->i_sb);
		file_update_time(vmf->vma->vm_file);
	}

	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	if (IS_DAX(inode)) {
		pfn_t pfn;

		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &xfs_iomap_ops);
		if (ret & VM_FAULT_NEEDDSYNC)
			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
	} else {
		if (write_fault)
			ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
		else
			ret = filemap_fault(vmf);
	}
	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	if (write_fault)
		sb_end_pagefault(inode->i_sb);
	return ret;
}

static vm_fault_t
xfs_filemap_fault(
	struct vm_fault		*vmf)
{
	/* DAX can shortcut the normal fault path on write faults! */
	return __xfs_filemap_fault(vmf, PE_SIZE_PTE,
			IS_DAX(file_inode(vmf->vma->vm_file)) &&
			(vmf->flags & FAULT_FLAG_WRITE));
}

static vm_fault_t
xfs_filemap_huge_fault(
	struct vm_fault		*vmf,
	enum page_entry_size	pe_size)
{
	if (!IS_DAX(file_inode(vmf->vma->vm_file)))
		return VM_FAULT_FALLBACK;

	/* DAX can shortcut the normal fault path on write faults! */
	return __xfs_filemap_fault(vmf, pe_size,
			(vmf->flags & FAULT_FLAG_WRITE));
}

static vm_fault_t
xfs_filemap_page_mkwrite(
	struct vm_fault		*vmf)
{
	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
}

/*
 * pfn_mkwrite was originally intended to ensure we capture time stamp updates
 * on write faults. In reality, it needs to serialise against truncate and
 * prepare memory for writing so handle is as standard write fault.
 */
static vm_fault_t
xfs_filemap_pfn_mkwrite(
	struct vm_fault		*vmf)
{

	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
}

static const struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= xfs_filemap_fault,
	.huge_fault	= xfs_filemap_huge_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)
{
	/*
	 * We don't support synchronous mappings for non-DAX files. At least
	 * until someone comes with a sensible use case.
	 */
	if (!IS_DAX(file_inode(filp)) && (vma->vm_flags & VM_SYNC))
		return -EOPNOTSUPP;

	file_accessed(filp);
	vma->vm_ops = &xfs_file_vm_ops;
	if (IS_DAX(file_inode(filp)))
		vma->vm_flags |= 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	= generic_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,
	.mmap_supported_flags = MAP_SYNC,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
	.get_unmapped_area = thp_get_unmapped_area,
	.fallocate	= xfs_file_fallocate,
	.clone_file_range = xfs_file_clone_range,
	.dedupe_file_range = xfs_file_dedupe_range,
};

const struct file_operations xfs_dir_file_operations = {
	.open		= xfs_dir_open,
	.read		= generic_read_dir,
	.iterate_shared	= 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,
};