summaryrefslogtreecommitdiff
path: root/fs/gfs2/ops_file.c
blob: 00522fc927cdd745809d95dc83da117d6c321aab (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) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License v.2.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/ext2_fs.h>
#include <linux/crc32.h>
#include <linux/iflags.h>
#include <asm/uaccess.h>

#include "gfs2.h"
#include "lm_interface.h"
#include "incore.h"
#include "bmap.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "lm.h"
#include "log.h"
#include "meta_io.h"
#include "ops_file.h"
#include "ops_vm.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "eaops.h"

/* "bad" is for NFS support */
struct filldir_bad_entry {
	char *fbe_name;
	unsigned int fbe_length;
	uint64_t fbe_offset;
	struct gfs2_inum fbe_inum;
	unsigned int fbe_type;
};

struct filldir_bad {
	struct gfs2_sbd *fdb_sbd;

	struct filldir_bad_entry *fdb_entry;
	unsigned int fdb_entry_num;
	unsigned int fdb_entry_off;

	char *fdb_name;
	unsigned int fdb_name_size;
	unsigned int fdb_name_off;
};

/* For regular, non-NFS */
struct filldir_reg {
	struct gfs2_sbd *fdr_sbd;
	int fdr_prefetch;

	filldir_t fdr_filldir;
	void *fdr_opaque;
};

/*
 * Most fields left uninitialised to catch anybody who tries to
 * use them. f_flags set to prevent file_accessed() from touching
 * any other part of this. Its use is purely as a flag so that we
 * know (in readpage()) whether or not do to locking.
 */
struct file gfs2_internal_file_sentinal = {
	.f_flags = O_NOATIME|O_RDONLY,
};

static int gfs2_read_actor(read_descriptor_t *desc, struct page *page,
			   unsigned long offset, unsigned long size)
{
	char *kaddr;
	unsigned long count = desc->count;

	if (size > count)
		size = count;

	kaddr = kmap(page);
	memcpy(desc->arg.buf, kaddr + offset, size);
        kunmap(page);

        desc->count = count - size;
        desc->written += size;
        desc->arg.buf += size;
        return size;
}

int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
		       char *buf, loff_t *pos, unsigned size)
{
	struct inode *inode = ip->i_vnode;
	read_descriptor_t desc;
	desc.written = 0;
	desc.arg.buf = buf;
	desc.count = size;
	desc.error = 0;
	do_generic_mapping_read(inode->i_mapping, ra_state,
				&gfs2_internal_file_sentinal, pos, &desc,
				gfs2_read_actor);
	return desc.written ? desc.written : desc.error;
}

/**
 * gfs2_llseek - seek to a location in a file
 * @file: the file
 * @offset: the offset
 * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
 *
 * SEEK_END requires the glock for the file because it references the
 * file's size.
 *
 * Returns: The new offset, or errno
 */

static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
{
	struct gfs2_inode *ip = file->f_mapping->host->u.generic_ip;
	struct gfs2_holder i_gh;
	loff_t error;

	if (origin == 2) {
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
					   &i_gh);
		if (!error) {
			error = remote_llseek(file, offset, origin);
			gfs2_glock_dq_uninit(&i_gh);
		}
	} else
		error = remote_llseek(file, offset, origin);

	return error;
}


static ssize_t gfs2_direct_IO_read(struct kiocb *iocb, const struct iovec *iov,
				   loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	ssize_t retval;

	retval = filemap_write_and_wait(mapping);
	if (retval == 0) {
		retval = mapping->a_ops->direct_IO(READ, iocb, iov, offset,
						   nr_segs);
	}
	return retval;
}

/**
 * __gfs2_file_aio_read - The main GFS2 read function
 * 
 * N.B. This is almost, but not quite the same as __generic_file_aio_read()
 * the important subtle different being that inode->i_size isn't valid
 * unless we are holding a lock, and we do this _only_ on the O_DIRECT
 * path since otherwise locking is done entirely at the page cache
 * layer.
 */
static ssize_t __gfs2_file_aio_read(struct kiocb *iocb,
				    const struct iovec *iov,
				    unsigned long nr_segs, loff_t *ppos)
{
	struct file *filp = iocb->ki_filp;
	struct gfs2_inode *ip = filp->f_mapping->host->u.generic_ip;
	struct gfs2_holder gh;
	ssize_t retval;
	unsigned long seg;
	size_t count;

	count = 0;
	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *iv = &iov[seg];

		/*
		 * If any segment has a negative length, or the cumulative
		 * length ever wraps negative then return -EINVAL.
		 */
		count += iv->iov_len;
		if (unlikely((ssize_t)(count|iv->iov_len) < 0))
			return -EINVAL;
		if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
			continue;
		if (seg == 0)
			return -EFAULT;
		nr_segs = seg;
		count -= iv->iov_len;   /* This segment is no good */
		break;
	}

	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
	if (filp->f_flags & O_DIRECT) {
		loff_t pos = *ppos, size;
		struct address_space *mapping;
		struct inode *inode;

		mapping = filp->f_mapping;
		inode = mapping->host;
		retval = 0;
		if (!count)
			goto out; /* skip atime */

		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
		retval = gfs2_glock_nq_m_atime(1, &gh);
		if (retval)
			goto out;
		if (gfs2_is_stuffed(ip)) {
			gfs2_glock_dq_m(1, &gh);
			gfs2_holder_uninit(&gh);
			goto fallback_to_normal;
		}
		size = i_size_read(inode);
		if (pos < size) {
			retval = gfs2_direct_IO_read(iocb, iov, pos, nr_segs);
			if (retval > 0 && !is_sync_kiocb(iocb))
				retval = -EIOCBQUEUED;
			if (retval > 0)
				*ppos = pos + retval;
		}
		file_accessed(filp);
		gfs2_glock_dq_m(1, &gh);
		gfs2_holder_uninit(&gh);
		goto out;
	}

fallback_to_normal:
	retval = 0;
	if (count) {
		for (seg = 0; seg < nr_segs; seg++) {
			read_descriptor_t desc;

			desc.written = 0;
			desc.arg.buf = iov[seg].iov_base;
			desc.count = iov[seg].iov_len;
			if (desc.count == 0)
				continue;
			desc.error = 0;
			do_generic_file_read(filp,ppos,&desc,file_read_actor);
			retval += desc.written;
			if (desc.error) {
				retval = retval ?: desc.error;
				 break;
			}
		}
	}
out:
	return retval;
}

/**
 * gfs2_read - Read bytes from a file
 * @file: The file to read from
 * @buf: The buffer to copy into
 * @size: The amount of data requested
 * @offset: The current file offset
 *
 * Outputs: Offset - updated according to number of bytes read
 *
 * Returns: The number of bytes read, errno on failure
 */

static ssize_t gfs2_read(struct file *filp, char __user *buf, size_t size,
			 loff_t *offset)
{
	struct iovec local_iov = { .iov_base = buf, .iov_len = size };
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	ret = __gfs2_file_aio_read(&kiocb, &local_iov, 1, offset);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}

static ssize_t gfs2_file_readv(struct file *filp, const struct iovec *iov,
			       unsigned long nr_segs, loff_t *ppos)
{
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	ret = __gfs2_file_aio_read(&kiocb, iov, nr_segs, ppos);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}

static ssize_t gfs2_file_aio_read(struct kiocb *iocb, char __user *buf,
				  size_t count, loff_t pos)
{
        struct iovec local_iov = { .iov_base = buf, .iov_len = count };

        BUG_ON(iocb->ki_pos != pos);
        return __gfs2_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
}


/**
 * filldir_reg_func - Report a directory entry to the caller of gfs2_dir_read()
 * @opaque: opaque data used by the function
 * @name: the name of the directory entry
 * @length: the length of the name
 * @offset: the entry's offset in the directory
 * @inum: the inode number the entry points to
 * @type: the type of inode the entry points to
 *
 * Returns: 0 on success, 1 if buffer full
 */

static int filldir_reg_func(void *opaque, const char *name, unsigned int length,
			    uint64_t offset, struct gfs2_inum *inum,
			    unsigned int type)
{
	struct filldir_reg *fdr = (struct filldir_reg *)opaque;
	struct gfs2_sbd *sdp = fdr->fdr_sbd;
	int error;

	error = fdr->fdr_filldir(fdr->fdr_opaque, name, length, offset,
				 inum->no_formal_ino, type);
	if (error)
		return 1;

	if (fdr->fdr_prefetch && !(length == 1 && *name == '.')) {
		gfs2_glock_prefetch_num(sdp,
				       inum->no_addr, &gfs2_inode_glops,
				       LM_ST_SHARED, LM_FLAG_TRY | LM_FLAG_ANY);
		gfs2_glock_prefetch_num(sdp,
				       inum->no_addr, &gfs2_iopen_glops,
				       LM_ST_SHARED, LM_FLAG_TRY);
	}

	return 0;
}

/**
 * readdir_reg - Read directory entries from a directory
 * @file: The directory to read from
 * @dirent: Buffer for dirents
 * @filldir: Function used to do the copying
 *
 * Returns: errno
 */

static int readdir_reg(struct file *file, void *dirent, filldir_t filldir)
{
	struct inode *dir = file->f_mapping->host;
	struct gfs2_inode *dip = dir->u.generic_ip;
	struct filldir_reg fdr;
	struct gfs2_holder d_gh;
	uint64_t offset = file->f_pos;
	int error;

	fdr.fdr_sbd = dip->i_sbd;
	fdr.fdr_prefetch = 1;
	fdr.fdr_filldir = filldir;
	fdr.fdr_opaque = dirent;

	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
	error = gfs2_glock_nq_atime(&d_gh);
	if (error) {
		gfs2_holder_uninit(&d_gh);
		return error;
	}

	error = gfs2_dir_read(dir, &offset, &fdr, filldir_reg_func);

	gfs2_glock_dq_uninit(&d_gh);

	file->f_pos = offset;

	return error;
}

/**
 * filldir_bad_func - Report a directory entry to the caller of gfs2_dir_read()
 * @opaque: opaque data used by the function
 * @name: the name of the directory entry
 * @length: the length of the name
 * @offset: the entry's offset in the directory
 * @inum: the inode number the entry points to
 * @type: the type of inode the entry points to
 *
 * For supporting NFS.
 *
 * Returns: 0 on success, 1 if buffer full
 */

static int filldir_bad_func(void *opaque, const char *name, unsigned int length,
			    uint64_t offset, struct gfs2_inum *inum,
			    unsigned int type)
{
	struct filldir_bad *fdb = (struct filldir_bad *)opaque;
	struct gfs2_sbd *sdp = fdb->fdb_sbd;
	struct filldir_bad_entry *fbe;

	if (fdb->fdb_entry_off == fdb->fdb_entry_num ||
	    fdb->fdb_name_off + length > fdb->fdb_name_size)
		return 1;

	fbe = &fdb->fdb_entry[fdb->fdb_entry_off];
	fbe->fbe_name = fdb->fdb_name + fdb->fdb_name_off;
	memcpy(fbe->fbe_name, name, length);
	fbe->fbe_length = length;
	fbe->fbe_offset = offset;
	fbe->fbe_inum = *inum;
	fbe->fbe_type = type;

	fdb->fdb_entry_off++;
	fdb->fdb_name_off += length;

	if (!(length == 1 && *name == '.')) {
		gfs2_glock_prefetch_num(sdp,
				       inum->no_addr, &gfs2_inode_glops,
				       LM_ST_SHARED, LM_FLAG_TRY | LM_FLAG_ANY);
		gfs2_glock_prefetch_num(sdp,
				       inum->no_addr, &gfs2_iopen_glops,
				       LM_ST_SHARED, LM_FLAG_TRY);
	}

	return 0;
}

/**
 * readdir_bad - Read directory entries from a directory
 * @file: The directory to read from
 * @dirent: Buffer for dirents
 * @filldir: Function used to do the copying
 *
 * For supporting NFS.
 *
 * Returns: errno
 */

static int readdir_bad(struct file *file, void *dirent, filldir_t filldir)
{
	struct inode *dir = file->f_mapping->host;
	struct gfs2_inode *dip = dir->u.generic_ip;
	struct gfs2_sbd *sdp = dip->i_sbd;
	struct filldir_reg fdr;
	unsigned int entries, size;
	struct filldir_bad *fdb;
	struct gfs2_holder d_gh;
	uint64_t offset = file->f_pos;
	unsigned int x;
	struct filldir_bad_entry *fbe;
	int error;

	entries = gfs2_tune_get(sdp, gt_entries_per_readdir);
	size = sizeof(struct filldir_bad) +
	    entries * (sizeof(struct filldir_bad_entry) + GFS2_FAST_NAME_SIZE);

	fdb = kzalloc(size, GFP_KERNEL);
	if (!fdb)
		return -ENOMEM;

	fdb->fdb_sbd = sdp;
	fdb->fdb_entry = (struct filldir_bad_entry *)(fdb + 1);
	fdb->fdb_entry_num = entries;
	fdb->fdb_name = ((char *)fdb) + sizeof(struct filldir_bad) +
		entries * sizeof(struct filldir_bad_entry);
	fdb->fdb_name_size = entries * GFS2_FAST_NAME_SIZE;

	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
	error = gfs2_glock_nq_atime(&d_gh);
	if (error) {
		gfs2_holder_uninit(&d_gh);
		goto out;
	}

	error = gfs2_dir_read(dir, &offset, fdb, filldir_bad_func);

	gfs2_glock_dq_uninit(&d_gh);

	fdr.fdr_sbd = sdp;
	fdr.fdr_prefetch = 0;
	fdr.fdr_filldir = filldir;
	fdr.fdr_opaque = dirent;

	for (x = 0; x < fdb->fdb_entry_off; x++) {
		fbe = &fdb->fdb_entry[x];

		error = filldir_reg_func(&fdr,
					 fbe->fbe_name, fbe->fbe_length,
					 fbe->fbe_offset,
					 &fbe->fbe_inum, fbe->fbe_type);
		if (error) {
			file->f_pos = fbe->fbe_offset;
			error = 0;
			goto out;
		}
	}

	file->f_pos = offset;

 out:
	kfree(fdb);

	return error;
}

/**
 * gfs2_readdir - Read directory entries from a directory
 * @file: The directory to read from
 * @dirent: Buffer for dirents
 * @filldir: Function used to do the copying
 *
 * Returns: errno
 */

static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
{
	int error;

	if (strcmp(current->comm, "nfsd") != 0)
		error = readdir_reg(file, dirent, filldir);
	else
		error = readdir_bad(file, dirent, filldir);

	return error;
}

static const u32 iflags_to_gfs2[32] = {
	[iflag_Sync] = GFS2_DIF_SYNC,
	[iflag_Immutable] = GFS2_DIF_IMMUTABLE,
	[iflag_Append] = GFS2_DIF_APPENDONLY,
	[iflag_NoAtime] = GFS2_DIF_NOATIME,
	[iflag_Index] = GFS2_DIF_EXHASH,
	[iflag_JournalData] = GFS2_DIF_JDATA,
	[iflag_DirectIO] = GFS2_DIF_DIRECTIO,
};

static const u32 gfs2_to_iflags[32] = {
	[gfs2fl_Sync] = IFLAG_SYNC,
	[gfs2fl_Immutable] = IFLAG_IMMUTABLE,
	[gfs2fl_AppendOnly] = IFLAG_APPEND,
	[gfs2fl_NoAtime] = IFLAG_NOATIME,
	[gfs2fl_ExHash] = IFLAG_INDEX,
	[gfs2fl_Jdata] = IFLAG_JOURNAL_DATA,
	[gfs2fl_Directio] = IFLAG_DIRECTIO,
	[gfs2fl_InheritDirectio] = IFLAG_DIRECTIO,
	[gfs2fl_InheritJdata] = IFLAG_JOURNAL_DATA,
};

static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct gfs2_inode *ip = inode->u.generic_ip;
	struct gfs2_holder gh;
	int error;
	u32 iflags;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
	error = gfs2_glock_nq_m_atime(1, &gh);
	if (error)
		return error;
	
	iflags = iflags_cvt(gfs2_to_iflags, ip->i_di.di_flags);
	if (put_user(iflags, ptr))
		error = -EFAULT;

	gfs2_glock_dq_m(1, &gh);
	gfs2_holder_uninit(&gh);
	return error;
}

/* Flags that can be set by user space */
#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
			     GFS2_DIF_DIRECTIO|			\
			     GFS2_DIF_IMMUTABLE|		\
			     GFS2_DIF_APPENDONLY|		\
			     GFS2_DIF_NOATIME|			\
			     GFS2_DIF_SYNC|			\
			     GFS2_DIF_SYSTEM|			\
			     GFS2_DIF_INHERIT_DIRECTIO|		\
			     GFS2_DIF_INHERIT_JDATA)

/**
 * gfs2_set_flags - set flags on an inode
 * @inode: The inode
 * @flags: The flags to set
 * @mask: Indicates which flags are valid
 *
 */
static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct gfs2_inode *ip = inode->u.generic_ip;
	struct gfs2_sbd *sdp = ip->i_sbd;
	struct buffer_head *bh;
	struct gfs2_holder gh;
	int error;
	u32 new_flags, flags;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	if (error) {
		gfs2_holder_uninit(&gh);
		return error;
	}

	flags = ip->i_di.di_flags;
	new_flags = (flags & ~mask) | (reqflags & mask);
	if ((new_flags ^ flags) == 0)
		goto out;

	if (S_ISDIR(inode->i_mode)) {
		if ((new_flags ^ flags) & GFS2_DIF_JDATA)
			new_flags ^= (GFS2_DIF_JDATA|GFS2_DIF_INHERIT_JDATA);
		if ((new_flags ^ flags) & GFS2_DIF_DIRECTIO)
			new_flags ^= (GFS2_DIF_DIRECTIO|GFS2_DIF_INHERIT_DIRECTIO);
	}

	error = -EINVAL;
	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
		goto out;

	error = -EPERM;
	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
		goto out;
	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
		goto out;
	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) && 
	    !capable(CAP_LINUX_IMMUTABLE))
		goto out;
	if (!IS_IMMUTABLE(inode)) {
		error = gfs2_repermission(inode, MAY_WRITE, NULL);
		if (error)
			goto out;
	}

	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (error)
		goto out;
	error = gfs2_meta_inode_buffer(ip, &bh);
	if (error)
		goto out_trans_end;
	gfs2_trans_add_bh(ip->i_gl, bh, 1);
	ip->i_di.di_flags = new_flags;
	gfs2_dinode_out(&ip->i_di, bh->b_data);
	brelse(bh);
out_trans_end:
	gfs2_trans_end(sdp);
out:
	gfs2_glock_dq_uninit(&gh);
	return error;
}

static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
{
	u32 iflags, gfsflags;
	if (get_user(iflags, ptr))
		return -EFAULT;
	gfsflags = iflags_cvt(iflags_to_gfs2, iflags);
	return do_gfs2_set_flags(filp, gfsflags, ~0);
}

static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	switch(cmd) {
	case IFLAGS_GET_IOC:
		return gfs2_get_flags(filp, (u32 __user *)arg);
	case IFLAGS_SET_IOC:
		return gfs2_set_flags(filp, (u32 __user *)arg);
	}
	return -ENOTTY;
}


/**
 * gfs2_mmap -
 * @file: The file to map
 * @vma: The VMA which described the mapping
 *
 * Returns: 0 or error code
 */

static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct gfs2_inode *ip = file->f_mapping->host->u.generic_ip;
	struct gfs2_holder i_gh;
	int error;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
	error = gfs2_glock_nq_atime(&i_gh);
	if (error) {
		gfs2_holder_uninit(&i_gh);
		return error;
	}

	/* This is VM_MAYWRITE instead of VM_WRITE because a call
	   to mprotect() can turn on VM_WRITE later. */

	if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) ==
	    (VM_MAYSHARE | VM_MAYWRITE))
		vma->vm_ops = &gfs2_vm_ops_sharewrite;
	else
		vma->vm_ops = &gfs2_vm_ops_private;

	gfs2_glock_dq_uninit(&i_gh);

	return error;
}

/**
 * gfs2_open - open a file
 * @inode: the inode to open
 * @file: the struct file for this opening
 *
 * Returns: errno
 */

static int gfs2_open(struct inode *inode, struct file *file)
{
	struct gfs2_inode *ip = inode->u.generic_ip;
	struct gfs2_holder i_gh;
	struct gfs2_file *fp;
	int error;

	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
	if (!fp)
		return -ENOMEM;

	mutex_init(&fp->f_fl_mutex);

	gfs2_assert_warn(ip->i_sbd, !file->private_data);
	file->private_data = fp;

	if (S_ISREG(ip->i_di.di_mode)) {
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
					   &i_gh);
		if (error)
			goto fail;

		if (!(file->f_flags & O_LARGEFILE) &&
		    ip->i_di.di_size > MAX_NON_LFS) {
			error = -EFBIG;
			goto fail_gunlock;
		}

		/* Listen to the Direct I/O flag */

		if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
			file->f_flags |= O_DIRECT;

		gfs2_glock_dq_uninit(&i_gh);
	}

	return 0;

 fail_gunlock:
	gfs2_glock_dq_uninit(&i_gh);

 fail:
	file->private_data = NULL;
	kfree(fp);

	return error;
}

/**
 * gfs2_close - called to close a struct file
 * @inode: the inode the struct file belongs to
 * @file: the struct file being closed
 *
 * Returns: errno
 */

static int gfs2_close(struct inode *inode, struct file *file)
{
	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
	struct gfs2_file *fp;

	fp = file->private_data;
	file->private_data = NULL;

	if (gfs2_assert_warn(sdp, fp))
		return -EIO;

	kfree(fp);

	return 0;
}

/**
 * gfs2_fsync - sync the dirty data for a file (across the cluster)
 * @file: the file that points to the dentry (we ignore this)
 * @dentry: the dentry that points to the inode to sync
 *
 * Returns: errno
 */

static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	struct gfs2_inode *ip = dentry->d_inode->u.generic_ip;

	gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);

	return 0;
}

/**
 * gfs2_lock - acquire/release a posix lock on a file
 * @file: the file pointer
 * @cmd: either modify or retrieve lock state, possibly wait
 * @fl: type and range of lock
 *
 * Returns: errno
 */

static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
{
	struct gfs2_inode *ip = file->f_mapping->host->u.generic_ip;
	struct gfs2_sbd *sdp = ip->i_sbd;
	struct lm_lockname name =
		{ .ln_number = ip->i_num.no_addr,
		  .ln_type = LM_TYPE_PLOCK };

	if (!(fl->fl_flags & FL_POSIX))
		return -ENOLCK;
	if ((ip->i_di.di_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
		return -ENOLCK;

	if (sdp->sd_args.ar_localflocks) {
		if (IS_GETLK(cmd)) {
			struct file_lock tmp;
			int ret;
			ret = posix_test_lock(file, fl, &tmp);
			fl->fl_type = F_UNLCK;
			if (ret)
				memcpy(fl, &tmp, sizeof(struct file_lock));
			return 0;
		} else {
			return posix_lock_file_wait(file, fl);
		}
	}

	if (IS_GETLK(cmd))
		return gfs2_lm_plock_get(sdp, &name, file, fl);
	else if (fl->fl_type == F_UNLCK)
		return gfs2_lm_punlock(sdp, &name, file, fl);
	else
		return gfs2_lm_plock(sdp, &name, file, cmd, fl);
}

/**
 * gfs2_sendfile - Send bytes to a file or socket
 * @in_file: The file to read from
 * @out_file: The file to write to
 * @count: The amount of data
 * @offset: The beginning file offset
 *
 * Outputs: offset - updated according to number of bytes read
 *
 * Returns: The number of bytes sent, errno on failure
 */

static ssize_t gfs2_sendfile(struct file *in_file, loff_t *offset, size_t count,
			     read_actor_t actor, void *target)
{
	return generic_file_sendfile(in_file, offset, count, actor, target);
}

static int do_flock(struct file *file, int cmd, struct file_lock *fl)
{
	struct gfs2_file *fp = file->private_data;
	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
	struct gfs2_inode *ip = file->f_dentry->d_inode->u.generic_ip;
	struct gfs2_glock *gl;
	unsigned int state;
	int flags;
	int error = 0;

	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
	flags = ((IS_SETLKW(cmd)) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;

	mutex_lock(&fp->f_fl_mutex);

	gl = fl_gh->gh_gl;
	if (gl) {
		if (fl_gh->gh_state == state)
			goto out;
		gfs2_glock_hold(gl);
		flock_lock_file_wait(file,
				     &(struct file_lock){.fl_type = F_UNLCK});		
		gfs2_glock_dq_uninit(fl_gh);
	} else {
		error = gfs2_glock_get(ip->i_sbd,
				      ip->i_num.no_addr, &gfs2_flock_glops,
				      CREATE, &gl);
		if (error)
			goto out;
	}

	gfs2_holder_init(gl, state, flags, fl_gh);
	gfs2_glock_put(gl);

	error = gfs2_glock_nq(fl_gh);
	if (error) {
		gfs2_holder_uninit(fl_gh);
		if (error == GLR_TRYFAILED)
			error = -EAGAIN;
	} else {
		error = flock_lock_file_wait(file, fl);
		gfs2_assert_warn(ip->i_sbd, !error);
	}

 out:
	mutex_unlock(&fp->f_fl_mutex);

	return error;
}

static void do_unflock(struct file *file, struct file_lock *fl)
{
	struct gfs2_file *fp = file->private_data;
	struct gfs2_holder *fl_gh = &fp->f_fl_gh;

	mutex_lock(&fp->f_fl_mutex);
	flock_lock_file_wait(file, fl);
	if (fl_gh->gh_gl)
		gfs2_glock_dq_uninit(fl_gh);
	mutex_unlock(&fp->f_fl_mutex);
}

/**
 * gfs2_flock - acquire/release a flock lock on a file
 * @file: the file pointer
 * @cmd: either modify or retrieve lock state, possibly wait
 * @fl: type and range of lock
 *
 * Returns: errno
 */

static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
{
	struct gfs2_inode *ip = file->f_mapping->host->u.generic_ip;
	struct gfs2_sbd *sdp = ip->i_sbd;

	if (!(fl->fl_flags & FL_FLOCK))
		return -ENOLCK;
	if ((ip->i_di.di_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
		return -ENOLCK;

	if (sdp->sd_args.ar_localflocks)
		return flock_lock_file_wait(file, fl);

	if (fl->fl_type == F_UNLCK) {
		do_unflock(file, fl);
		return 0;
	} else
		return do_flock(file, cmd, fl);
}

struct file_operations gfs2_file_fops = {
	.llseek = gfs2_llseek,
	.read = gfs2_read,
	.readv = gfs2_file_readv,
	.aio_read = gfs2_file_aio_read,
	.write = generic_file_write,
	.writev = generic_file_writev,
	.aio_write = generic_file_aio_write,
	.unlocked_ioctl = gfs2_ioctl,
	.mmap = gfs2_mmap,
	.open = gfs2_open,
	.release = gfs2_close,
	.fsync = gfs2_fsync,
	.lock = gfs2_lock,
	.sendfile = gfs2_sendfile,
	.flock = gfs2_flock,
	.splice_read = generic_file_splice_read,
	.splice_write = generic_file_splice_write,
};

struct file_operations gfs2_dir_fops = {
	.readdir = gfs2_readdir,
	.unlocked_ioctl = gfs2_ioctl,
	.open = gfs2_open,
	.release = gfs2_close,
	.fsync = gfs2_fsync,
	.lock = gfs2_lock,
	.flock = gfs2_flock,
};