aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_file.c
blob: 51fc2cf07d5e42633f7a4273c837fb15bfe430ed (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
/*
 * 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_log.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_trans.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_vnodeops.h"
#include "xfs_da_btree.h"
#include "xfs_ioctl.h"
#include "xfs_trace.h"

#include <linux/dcache.h>
#include <linux/falloc.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
 *
 *	xfs_iozero clears the specified range of buffer supplied,
 *	and marks all the affected blocks as valid and modified.  If
 *	an affected block is not allocated, it will be allocated.  If
 *	an affected block is not completely overwritten, and is not
 *	valid before the operation, it will be read from disk before
 *	being partially zeroed.
 */
STATIC 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;

	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;

		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! */
		pos += bytes;
		count -= bytes;
		status = 0;
	} while (count);

	return (-status);
}

/*
 * 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 -XFS_ERROR(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.
	 */
	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_ipincount(ip)) {
		if (!datasync ||
		    (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
			lsn = ip->i_itemp->ili_last_lsn;
	}
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	if (lsn)
		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);

	/*
	 * 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_aio_read(
	struct kiocb		*iocb,
	const struct iovec	*iovp,
	unsigned long		nr_segs,
	loff_t			pos)
{
	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 = 0;
	ssize_t			ret = 0;
	int			ioflags = 0;
	xfs_fsize_t		n;
	unsigned long		seg;

	XFS_STATS_INC(xs_read_calls);

	BUG_ON(iocb->ki_pos != pos);

	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	if (file->f_mode & FMODE_NOCMTIME)
		ioflags |= IO_INVIS;

	/* START copy & waste from filemap.c */
	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *iv = &iovp[seg];

		/*
		 * If any segment has a negative length, or the cumulative
		 * length ever wraps negative then return -EINVAL.
		 */
		size += iv->iov_len;
		if (unlikely((ssize_t)(size|iv->iov_len) < 0))
			return XFS_ERROR(-EINVAL);
	}
	/* END copy & waste from filemap.c */

	if (unlikely(ioflags & IO_ISDIRECT)) {
		xfs_buftarg_t	*target =
			XFS_IS_REALTIME_INODE(ip) ?
				mp->m_rtdev_targp : mp->m_ddev_targp;
		if ((iocb->ki_pos & target->bt_smask) ||
		    (size & target->bt_smask)) {
			if (iocb->ki_pos == i_size_read(inode))
				return 0;
			return -XFS_ERROR(EINVAL);
		}
	}

	n = XFS_MAXIOFFSET(mp) - iocb->ki_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 & IO_ISDIRECT) && inode->i_mapping->nrpages) {
		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);

		if (inode->i_mapping->nrpages) {
			ret = -xfs_flushinval_pages(ip,
					(iocb->ki_pos & PAGE_CACHE_MASK),
					-1, FI_REMAPF_LOCKED);
			if (ret) {
				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
				return ret;
			}
		}
		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
	}

	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);

	ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
	if (ret > 0)
		XFS_STATS_ADD(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(xs_read_calls);

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

	ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
	if (ret > 0)
		XFS_STATS_ADD(xs_read_bytes, ret);

	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
	return ret;
}

/*
 * xfs_file_splice_write() does not use xfs_rw_ilock() because
 * generic_file_splice_write() takes the i_mutex itself. This, in theory,
 * couuld cause lock inversions between the aio_write path and the splice path
 * if someone is doing concurrent splice(2) based writes and write(2) based
 * writes to the same inode. The only real way to fix this is to re-implement
 * the generic code here with correct locking orders.
 */
STATIC ssize_t
xfs_file_splice_write(
	struct pipe_inode_info	*pipe,
	struct file		*outfilp,
	loff_t			*ppos,
	size_t			count,
	unsigned int		flags)
{
	struct inode		*inode = outfilp->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	int			ioflags = 0;
	ssize_t			ret;

	XFS_STATS_INC(xs_write_calls);

	if (outfilp->f_mode & FMODE_NOCMTIME)
		ioflags |= IO_INVIS;

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

	xfs_ilock(ip, XFS_IOLOCK_EXCL);

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

	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
	if (ret > 0)
		XFS_STATS_ADD(xs_write_bytes, ret);

	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	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)
{
	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;
	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 */
{
	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);

	/*
	 * 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);
		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;

		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 file		*file,
	loff_t			*pos,
	size_t			*count,
	int			*iolock)
{
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	int			error = 0;

restart:
	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
	if (error)
		return error;

	/*
	 * 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.
	 */
	if (*pos > i_size_read(inode)) {
		if (*iolock == XFS_IOLOCK_SHARED) {
			xfs_rw_iunlock(ip, *iolock);
			*iolock = XFS_IOLOCK_EXCL;
			xfs_rw_ilock(ip, *iolock);
			goto restart;
		}
		error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
		if (error)
			return error;
	}

	/*
	 * 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)))
		file_update_time(file);

	/*
	 * 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.
	 */
	return file_remove_suid(file);
}

/*
 * 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,
	const struct iovec	*iovp,
	unsigned long		nr_segs,
	loff_t			pos,
	size_t			ocount)
{
	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;
	size_t			count = ocount;
	int			unaligned_io = 0;
	int			iolock;
	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
					mp->m_rtdev_targp : mp->m_ddev_targp;

	if ((pos & target->bt_smask) || (count & target->bt_smask))
		return -XFS_ERROR(EINVAL);

	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(file, &pos, &count, &iolock);
	if (ret)
		goto out;

	if (mapping->nrpages) {
		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
							FI_REMAPF_LOCKED);
		if (ret)
			goto out;
	}

	/*
	 * 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);
	ret = generic_file_direct_write(iocb, iovp,
			&nr_segs, pos, &iocb->ki_pos, count, ocount);

out:
	xfs_rw_iunlock(ip, iolock);

	/* No fallback to buffered IO on errors for XFS. */
	ASSERT(ret < 0 || ret == count);
	return ret;
}

STATIC ssize_t
xfs_file_buffered_aio_write(
	struct kiocb		*iocb,
	const struct iovec	*iovp,
	unsigned long		nr_segs,
	loff_t			pos,
	size_t			ocount)
{
	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;
	size_t			count = ocount;

	xfs_rw_ilock(ip, iolock);

	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
	if (ret)
		goto out;

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = mapping->backing_dev_info;

write_retry:
	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
			pos, &iocb->ki_pos, count, ret);
	/*
	 * if we just got an ENOSPC, flush the inode now we aren't holding any
	 * page locks and retry *once*
	 */
	if (ret == -ENOSPC && !enospc) {
		enospc = 1;
		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
		if (!ret)
			goto write_retry;
	}

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

STATIC ssize_t
xfs_file_aio_write(
	struct kiocb		*iocb,
	const struct iovec	*iovp,
	unsigned long		nr_segs,
	loff_t			pos)
{
	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 = 0;

	XFS_STATS_INC(xs_write_calls);

	BUG_ON(iocb->ki_pos != pos);

	ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
	if (ret)
		return ret;

	if (ocount == 0)
		return 0;

	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);

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

	if (unlikely(file->f_flags & O_DIRECT))
		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
	else
		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
						  ocount);

	if (ret > 0) {
		ssize_t err;

		XFS_STATS_ADD(xs_write_bytes, ret);

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

	return ret;
}

STATIC long
xfs_file_fallocate(
	struct file	*file,
	int		mode,
	loff_t		offset,
	loff_t		len)
{
	struct inode	*inode = file->f_path.dentry->d_inode;
	long		error;
	loff_t		new_size = 0;
	xfs_flock64_t	bf;
	xfs_inode_t	*ip = XFS_I(inode);
	int		cmd = XFS_IOC_RESVSP;
	int		attr_flags = XFS_ATTR_NOLOCK;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	bf.l_whence = 0;
	bf.l_start = offset;
	bf.l_len = len;

	xfs_ilock(ip, XFS_IOLOCK_EXCL);

	if (mode & FALLOC_FL_PUNCH_HOLE)
		cmd = XFS_IOC_UNRESVSP;

	/* check the new inode size is valid before allocating */
	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 (file->f_flags & O_DSYNC)
		attr_flags |= XFS_ATTR_SYNC;

	error = -xfs_change_file_space(ip, cmd, &bf, 0, attr_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, XFS_ATTR_NOLOCK);
	}

out_unlock:
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	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_map_shared(ip);
	if (ip->i_d.di_nextents > 0)
		xfs_da_reada_buf(NULL, ip, 0, XFS_DATA_FORK);
	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	*filp,
	void		*dirent,
	filldir_t	filldir)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;
	xfs_inode_t	*ip = XFS_I(inode);
	int		error;
	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);

	error = xfs_readdir(ip, dirent, bufsize,
				(xfs_off_t *)&filp->f_pos, filldir);
	if (error)
		return -error;
	return 0;
}

STATIC int
xfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	vma->vm_ops = &xfs_file_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;

	file_accessed(filp);
	return 0;
}

/*
 * 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_vm_page_mkwrite(
	struct vm_area_struct	*vma,
	struct vm_fault		*vmf)
{
	return block_page_mkwrite(vma, vmf, xfs_get_blocks);
}

const struct file_operations xfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= xfs_file_aio_read,
	.aio_write	= xfs_file_aio_write,
	.splice_read	= xfs_file_splice_read,
	.splice_write	= xfs_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,
	.readdir	= 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,
};

static const struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite	= xfs_vm_page_mkwrite,
};