summaryrefslogtreecommitdiffstats
path: root/fs/libfs.c
blob: a6d89f151771ff8046e463e543680306f59b46e8 (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
/*
 *	fs/libfs.c
 *	Library for filesystems writers.
 */

#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/quotaops.h>
#include <linux/mutex.h>
#include <linux/namei.h>
#include <linux/exportfs.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h> /* sync_mapping_buffers */

#include <asm/uaccess.h>

#include "internal.h"

int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
		   struct kstat *stat)
{
	struct inode *inode = d_inode(dentry);
	generic_fillattr(inode, stat);
	stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
	return 0;
}
EXPORT_SYMBOL(simple_getattr);

int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	buf->f_type = dentry->d_sb->s_magic;
	buf->f_bsize = PAGE_SIZE;
	buf->f_namelen = NAME_MAX;
	return 0;
}
EXPORT_SYMBOL(simple_statfs);

/*
 * Retaining negative dentries for an in-memory filesystem just wastes
 * memory and lookup time: arrange for them to be deleted immediately.
 */
int always_delete_dentry(const struct dentry *dentry)
{
	return 1;
}
EXPORT_SYMBOL(always_delete_dentry);

const struct dentry_operations simple_dentry_operations = {
	.d_delete = always_delete_dentry,
};
EXPORT_SYMBOL(simple_dentry_operations);

/*
 * Lookup the data. This is trivial - if the dentry didn't already
 * exist, we know it is negative.  Set d_op to delete negative dentries.
 */
struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
	if (dentry->d_name.len > NAME_MAX)
		return ERR_PTR(-ENAMETOOLONG);
	if (!dentry->d_sb->s_d_op)
		d_set_d_op(dentry, &simple_dentry_operations);
	d_add(dentry, NULL);
	return NULL;
}
EXPORT_SYMBOL(simple_lookup);

int dcache_dir_open(struct inode *inode, struct file *file)
{
	file->private_data = d_alloc_cursor(file->f_path.dentry);

	return file->private_data ? 0 : -ENOMEM;
}
EXPORT_SYMBOL(dcache_dir_open);

int dcache_dir_close(struct inode *inode, struct file *file)
{
	dput(file->private_data);
	return 0;
}
EXPORT_SYMBOL(dcache_dir_close);

/* parent is locked at least shared */
static struct dentry *next_positive(struct dentry *parent,
				    struct list_head *from,
				    int count)
{
	unsigned *seq = &parent->d_inode->i_dir_seq, n;
	struct dentry *res;
	struct list_head *p;
	bool skipped;
	int i;

retry:
	i = count;
	skipped = false;
	n = smp_load_acquire(seq) & ~1;
	res = NULL;
	rcu_read_lock();
	for (p = from->next; p != &parent->d_subdirs; p = p->next) {
		struct dentry *d = list_entry(p, struct dentry, d_child);
		if (!simple_positive(d)) {
			skipped = true;
		} else if (!--i) {
			res = d;
			break;
		}
	}
	rcu_read_unlock();
	if (skipped) {
		smp_rmb();
		if (unlikely(*seq != n))
			goto retry;
	}
	return res;
}

static void move_cursor(struct dentry *cursor, struct list_head *after)
{
	struct dentry *parent = cursor->d_parent;
	unsigned n, *seq = &parent->d_inode->i_dir_seq;
	spin_lock(&parent->d_lock);
	for (;;) {
		n = *seq;
		if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
			break;
		cpu_relax();
	}
	__list_del(cursor->d_child.prev, cursor->d_child.next);
	if (after)
		list_add(&cursor->d_child, after);
	else
		list_add_tail(&cursor->d_child, &parent->d_subdirs);
	smp_store_release(seq, n + 2);
	spin_unlock(&parent->d_lock);
}

loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
	struct dentry *dentry = file->f_path.dentry;
	switch (whence) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
			return -EINVAL;
	}
	if (offset != file->f_pos) {
		file->f_pos = offset;
		if (file->f_pos >= 2) {
			struct dentry *cursor = file->private_data;
			struct dentry *to;
			loff_t n = file->f_pos - 2;

			inode_lock_shared(dentry->d_inode);
			to = next_positive(dentry, &dentry->d_subdirs, n);
			move_cursor(cursor, to ? &to->d_child : NULL);
			inode_unlock_shared(dentry->d_inode);
		}
	}
	return offset;
}
EXPORT_SYMBOL(dcache_dir_lseek);

/* Relationship between i_mode and the DT_xxx types */
static inline unsigned char dt_type(struct inode *inode)
{
	return (inode->i_mode >> 12) & 15;
}

/*
 * Directory is locked and all positive dentries in it are safe, since
 * for ramfs-type trees they can't go away without unlink() or rmdir(),
 * both impossible due to the lock on directory.
 */

int dcache_readdir(struct file *file, struct dir_context *ctx)
{
	struct dentry *dentry = file->f_path.dentry;
	struct dentry *cursor = file->private_data;
	struct list_head *p = &cursor->d_child;
	struct dentry *next;
	bool moved = false;

	if (!dir_emit_dots(file, ctx))
		return 0;

	if (ctx->pos == 2)
		p = &dentry->d_subdirs;
	while ((next = next_positive(dentry, p, 1)) != NULL) {
		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
			      d_inode(next)->i_ino, dt_type(d_inode(next))))
			break;
		moved = true;
		p = &next->d_child;
		ctx->pos++;
	}
	if (moved)
		move_cursor(cursor, p);
	return 0;
}
EXPORT_SYMBOL(dcache_readdir);

ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos)
{
	return -EISDIR;
}
EXPORT_SYMBOL(generic_read_dir);

const struct file_operations simple_dir_operations = {
	.open		= dcache_dir_open,
	.release	= dcache_dir_close,
	.llseek		= dcache_dir_lseek,
	.read		= generic_read_dir,
	.iterate_shared	= dcache_readdir,
	.fsync		= noop_fsync,
};
EXPORT_SYMBOL(simple_dir_operations);

const struct inode_operations simple_dir_inode_operations = {
	.lookup		= simple_lookup,
};
EXPORT_SYMBOL(simple_dir_inode_operations);

static const struct super_operations simple_super_operations = {
	.statfs		= simple_statfs,
};

/*
 * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
 * will never be mountable)
 */
struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name,
	const struct super_operations *ops, const struct xattr_handler **xattr,
	const struct dentry_operations *dops, unsigned long magic)
{
	struct super_block *s;
	struct dentry *dentry;
	struct inode *root;
	struct qstr d_name = QSTR_INIT(name, strlen(name));

	s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL);
	if (IS_ERR(s))
		return ERR_CAST(s);

	s->s_maxbytes = MAX_LFS_FILESIZE;
	s->s_blocksize = PAGE_SIZE;
	s->s_blocksize_bits = PAGE_SHIFT;
	s->s_magic = magic;
	s->s_op = ops ? ops : &simple_super_operations;
	s->s_xattr = xattr;
	s->s_time_gran = 1;
	root = new_inode(s);
	if (!root)
		goto Enomem;
	/*
	 * since this is the first inode, make it number 1. New inodes created
	 * after this must take care not to collide with it (by passing
	 * max_reserved of 1 to iunique).
	 */
	root->i_ino = 1;
	root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
	root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME;
	dentry = __d_alloc(s, &d_name);
	if (!dentry) {
		iput(root);
		goto Enomem;
	}
	d_instantiate(dentry, root);
	s->s_root = dentry;
	s->s_d_op = dops;
	s->s_flags |= MS_ACTIVE;
	return dget(s->s_root);

Enomem:
	deactivate_locked_super(s);
	return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(mount_pseudo_xattr);

int simple_open(struct inode *inode, struct file *file)
{
	if (inode->i_private)
		file->private_data = inode->i_private;
	return 0;
}
EXPORT_SYMBOL(simple_open);

int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(old_dentry);

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	inc_nlink(inode);
	ihold(inode);
	dget(dentry);
	d_instantiate(dentry, inode);
	return 0;
}
EXPORT_SYMBOL(simple_link);

int simple_empty(struct dentry *dentry)
{
	struct dentry *child;
	int ret = 0;

	spin_lock(&dentry->d_lock);
	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
		if (simple_positive(child)) {
			spin_unlock(&child->d_lock);
			goto out;
		}
		spin_unlock(&child->d_lock);
	}
	ret = 1;
out:
	spin_unlock(&dentry->d_lock);
	return ret;
}
EXPORT_SYMBOL(simple_empty);

int simple_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	drop_nlink(inode);
	dput(dentry);
	return 0;
}
EXPORT_SYMBOL(simple_unlink);

int simple_rmdir(struct inode *dir, struct dentry *dentry)
{
	if (!simple_empty(dentry))
		return -ENOTEMPTY;

	drop_nlink(d_inode(dentry));
	simple_unlink(dir, dentry);
	drop_nlink(dir);
	return 0;
}
EXPORT_SYMBOL(simple_rmdir);

int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
		struct inode *new_dir, struct dentry *new_dentry)
{
	struct inode *inode = d_inode(old_dentry);
	int they_are_dirs = d_is_dir(old_dentry);

	if (!simple_empty(new_dentry))
		return -ENOTEMPTY;

	if (d_really_is_positive(new_dentry)) {
		simple_unlink(new_dir, new_dentry);
		if (they_are_dirs) {
			drop_nlink(d_inode(new_dentry));
			drop_nlink(old_dir);
		}
	} else if (they_are_dirs) {
		drop_nlink(old_dir);
		inc_nlink(new_dir);
	}

	old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime =
		new_dir->i_mtime = inode->i_ctime = CURRENT_TIME;

	return 0;
}
EXPORT_SYMBOL(simple_rename);

/**
 * simple_setattr - setattr for simple filesystem
 * @dentry: dentry
 * @iattr: iattr structure
 *
 * Returns 0 on success, -error on failure.
 *
 * simple_setattr is a simple ->setattr implementation without a proper
 * implementation of size changes.
 *
 * It can either be used for in-memory filesystems or special files
 * on simple regular filesystems.  Anything that needs to change on-disk
 * or wire state on size changes needs its own setattr method.
 */
int simple_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	int error;

	error = setattr_prepare(dentry, iattr);
	if (error)
		return error;

	if (iattr->ia_valid & ATTR_SIZE)
		truncate_setsize(inode, iattr->ia_size);
	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);
	return 0;
}
EXPORT_SYMBOL(simple_setattr);

int simple_readpage(struct file *file, struct page *page)
{
	clear_highpage(page);
	flush_dcache_page(page);
	SetPageUptodate(page);
	unlock_page(page);
	return 0;
}
EXPORT_SYMBOL(simple_readpage);

int simple_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	struct page *page;
	pgoff_t index;

	index = pos >> PAGE_SHIFT;

	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;

	*pagep = page;

	if (!PageUptodate(page) && (len != PAGE_SIZE)) {
		unsigned from = pos & (PAGE_SIZE - 1);

		zero_user_segments(page, 0, from, from + len, PAGE_SIZE);
	}
	return 0;
}
EXPORT_SYMBOL(simple_write_begin);

/**
 * simple_write_end - .write_end helper for non-block-device FSes
 * @available: See .write_end of address_space_operations
 * @file: 		"
 * @mapping: 		"
 * @pos: 		"
 * @len: 		"
 * @copied: 		"
 * @page: 		"
 * @fsdata: 		"
 *
 * simple_write_end does the minimum needed for updating a page after writing is
 * done. It has the same API signature as the .write_end of
 * address_space_operations vector. So it can just be set onto .write_end for
 * FSes that don't need any other processing. i_mutex is assumed to be held.
 * Block based filesystems should use generic_write_end().
 * NOTE: Even though i_size might get updated by this function, mark_inode_dirty
 * is not called, so a filesystem that actually does store data in .write_inode
 * should extend on what's done here with a call to mark_inode_dirty() in the
 * case that i_size has changed.
 */
int simple_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = page->mapping->host;
	loff_t last_pos = pos + copied;

	/* zero the stale part of the page if we did a short copy */
	if (copied < len) {
		unsigned from = pos & (PAGE_SIZE - 1);

		zero_user(page, from + copied, len - copied);
	}

	if (!PageUptodate(page))
		SetPageUptodate(page);
	/*
	 * No need to use i_size_read() here, the i_size
	 * cannot change under us because we hold the i_mutex.
	 */
	if (last_pos > inode->i_size)
		i_size_write(inode, last_pos);

	set_page_dirty(page);
	unlock_page(page);
	put_page(page);

	return copied;
}
EXPORT_SYMBOL(simple_write_end);

/*
 * the inodes created here are not hashed. If you use iunique to generate
 * unique inode values later for this filesystem, then you must take care
 * to pass it an appropriate max_reserved value to avoid collisions.
 */
int simple_fill_super(struct super_block *s, unsigned long magic,
		      struct tree_descr *files)
{
	struct inode *inode;
	struct dentry *root;
	struct dentry *dentry;
	int i;

	s->s_blocksize = PAGE_SIZE;
	s->s_blocksize_bits = PAGE_SHIFT;
	s->s_magic = magic;
	s->s_op = &simple_super_operations;
	s->s_time_gran = 1;

	inode = new_inode(s);
	if (!inode)
		return -ENOMEM;
	/*
	 * because the root inode is 1, the files array must not contain an
	 * entry at index 1
	 */
	inode->i_ino = 1;
	inode->i_mode = S_IFDIR | 0755;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_op = &simple_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
	set_nlink(inode, 2);
	root = d_make_root(inode);
	if (!root)
		return -ENOMEM;
	for (i = 0; !files->name || files->name[0]; i++, files++) {
		if (!files->name)
			continue;

		/* warn if it tries to conflict with the root inode */
		if (unlikely(i == 1))
			printk(KERN_WARNING "%s: %s passed in a files array"
				"with an index of 1!\n", __func__,
				s->s_type->name);

		dentry = d_alloc_name(root, files->name);
		if (!dentry)
			goto out;
		inode = new_inode(s);
		if (!inode) {
			dput(dentry);
			goto out;
		}
		inode->i_mode = S_IFREG | files->mode;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_fop = files->ops;
		inode->i_ino = i;
		d_add(dentry, inode);
	}
	s->s_root = root;
	return 0;
out:
	d_genocide(root);
	shrink_dcache_parent(root);
	dput(root);
	return -ENOMEM;
}
EXPORT_SYMBOL(simple_fill_super);

static DEFINE_SPINLOCK(pin_fs_lock);

int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
{
	struct vfsmount *mnt = NULL;
	spin_lock(&pin_fs_lock);
	if (unlikely(!*mount)) {
		spin_unlock(&pin_fs_lock);
		mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, NULL);
		if (IS_ERR(mnt))
			return PTR_ERR(mnt);
		spin_lock(&pin_fs_lock);
		if (!*mount)
			*mount = mnt;
	}
	mntget(*mount);
	++*count;
	spin_unlock(&pin_fs_lock);
	mntput(mnt);
	return 0;
}
EXPORT_SYMBOL(simple_pin_fs);

void simple_release_fs(struct vfsmount **mount, int *count)
{
	struct vfsmount *mnt;
	spin_lock(&pin_fs_lock);
	mnt = *mount;
	if (!--*count)
		*mount = NULL;
	spin_unlock(&pin_fs_lock);
	mntput(mnt);
}
EXPORT_SYMBOL(simple_release_fs);

/**
 * simple_read_from_buffer - copy data from the buffer to user space
 * @to: the user space buffer to read to
 * @count: the maximum number of bytes to read
 * @ppos: the current position in the buffer
 * @from: the buffer to read from
 * @available: the size of the buffer
 *
 * The simple_read_from_buffer() function reads up to @count bytes from the
 * buffer @from at offset @ppos into the user space address starting at @to.
 *
 * On success, the number of bytes read is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
				const void *from, size_t available)
{
	loff_t pos = *ppos;
	size_t ret;

	if (pos < 0)
		return -EINVAL;
	if (pos >= available || !count)
		return 0;
	if (count > available - pos)
		count = available - pos;
	ret = copy_to_user(to, from + pos, count);
	if (ret == count)
		return -EFAULT;
	count -= ret;
	*ppos = pos + count;
	return count;
}
EXPORT_SYMBOL(simple_read_from_buffer);

/**
 * simple_write_to_buffer - copy data from user space to the buffer
 * @to: the buffer to write to
 * @available: the size of the buffer
 * @ppos: the current position in the buffer
 * @from: the user space buffer to read from
 * @count: the maximum number of bytes to read
 *
 * The simple_write_to_buffer() function reads up to @count bytes from the user
 * space address starting at @from into the buffer @to at offset @ppos.
 *
 * On success, the number of bytes written is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
		const void __user *from, size_t count)
{
	loff_t pos = *ppos;
	size_t res;

	if (pos < 0)
		return -EINVAL;
	if (pos >= available || !count)
		return 0;
	if (count > available - pos)
		count = available - pos;
	res = copy_from_user(to + pos, from, count);
	if (res == count)
		return -EFAULT;
	count -= res;
	*ppos = pos + count;
	return count;
}
EXPORT_SYMBOL(simple_write_to_buffer);

/**
 * memory_read_from_buffer - copy data from the buffer
 * @to: the kernel space buffer to read to
 * @count: the maximum number of bytes to read
 * @ppos: the current position in the buffer
 * @from: the buffer to read from
 * @available: the size of the buffer
 *
 * The memory_read_from_buffer() function reads up to @count bytes from the
 * buffer @from at offset @ppos into the kernel space address starting at @to.
 *
 * On success, the number of bytes read is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
				const void *from, size_t available)
{
	loff_t pos = *ppos;

	if (pos < 0)
		return -EINVAL;
	if (pos >= available)
		return 0;
	if (count > available - pos)
		count = available - pos;
	memcpy(to, from + pos, count);
	*ppos = pos + count;

	return count;
}
EXPORT_SYMBOL(memory_read_from_buffer);

/*
 * Transaction based IO.
 * The file expects a single write which triggers the transaction, and then
 * possibly a read which collects the result - which is stored in a
 * file-local buffer.
 */

void simple_transaction_set(struct file *file, size_t n)
{
	struct simple_transaction_argresp *ar = file->private_data;

	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);

	/*
	 * The barrier ensures that ar->size will really remain zero until
	 * ar->data is ready for reading.
	 */
	smp_mb();
	ar->size = n;
}
EXPORT_SYMBOL(simple_transaction_set);

char *simple_transaction_get(struct file *file, const char __user *buf, size_t size)
{
	struct simple_transaction_argresp *ar;
	static DEFINE_SPINLOCK(simple_transaction_lock);

	if (size > SIMPLE_TRANSACTION_LIMIT - 1)
		return ERR_PTR(-EFBIG);

	ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL);
	if (!ar)
		return ERR_PTR(-ENOMEM);

	spin_lock(&simple_transaction_lock);

	/* only one write allowed per open */
	if (file->private_data) {
		spin_unlock(&simple_transaction_lock);
		free_page((unsigned long)ar);
		return ERR_PTR(-EBUSY);
	}

	file->private_data = ar;

	spin_unlock(&simple_transaction_lock);

	if (copy_from_user(ar->data, buf, size))
		return ERR_PTR(-EFAULT);

	return ar->data;
}
EXPORT_SYMBOL(simple_transaction_get);

ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
{
	struct simple_transaction_argresp *ar = file->private_data;

	if (!ar)
		return 0;
	return simple_read_from_buffer(buf, size, pos, ar->data, ar->size);
}
EXPORT_SYMBOL(simple_transaction_read);

int simple_transaction_release(struct inode *inode, struct file *file)
{
	free_page((unsigned long)file->private_data);
	return 0;
}
EXPORT_SYMBOL(simple_transaction_release);

/* Simple attribute files */

struct simple_attr {
	int (*get)(void *, u64 *);
	int (*set)(void *, u64);
	char get_buf[24];	/* enough to store a u64 and "\n\0" */
	char set_buf[24];
	void *data;
	const char *fmt;	/* format for read operation */
	struct mutex mutex;	/* protects access to these buffers */
};

/* simple_attr_open is called by an actual attribute open file operation
 * to set the attribute specific access operations. */
int simple_attr_open(struct inode *inode, struct file *file,
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
		     const char *fmt)
{
	struct simple_attr *attr;

	attr = kmalloc(sizeof(*attr), GFP_KERNEL);
	if (!attr)
		return -ENOMEM;

	attr->get = get;
	attr->set = set;
	attr->data = inode->i_private;
	attr->fmt = fmt;
	mutex_init(&attr->mutex);

	file->private_data = attr;

	return nonseekable_open(inode, file);
}
EXPORT_SYMBOL_GPL(simple_attr_open);

int simple_attr_release(struct inode *inode, struct file *file)
{
	kfree(file->private_data);
	return 0;
}
EXPORT_SYMBOL_GPL(simple_attr_release);	/* GPL-only?  This?  Really? */

/* read from the buffer that is filled with the get function */
ssize_t simple_attr_read(struct file *file, char __user *buf,
			 size_t len, loff_t *ppos)
{
	struct simple_attr *attr;
	size_t size;
	ssize_t ret;

	attr = file->private_data;

	if (!attr->get)
		return -EACCES;

	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

	if (*ppos) {		/* continued read */
		size = strlen(attr->get_buf);
	} else {		/* first read */
		u64 val;
		ret = attr->get(attr->data, &val);
		if (ret)
			goto out;

		size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
				 attr->fmt, (unsigned long long)val);
	}

	ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
out:
	mutex_unlock(&attr->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(simple_attr_read);

/* interpret the buffer as a number to call the set function with */
ssize_t simple_attr_write(struct file *file, const char __user *buf,
			  size_t len, loff_t *ppos)
{
	struct simple_attr *attr;
	u64 val;
	size_t size;
	ssize_t ret;

	attr = file->private_data;
	if (!attr->set)
		return -EACCES;

	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

	ret = -EFAULT;
	size = min(sizeof(attr->set_buf) - 1, len);
	if (copy_from_user(attr->set_buf, buf, size))
		goto out;

	attr->set_buf[size] = '\0';
	val = simple_strtoll(attr->set_buf, NULL, 0);
	ret = attr->set(attr->data, val);
	if (ret == 0)
		ret = len; /* on success, claim we got the whole input */
out:
	mutex_unlock(&attr->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(simple_attr_write);

/**
 * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
 * @sb:		filesystem to do the file handle conversion on
 * @fid:	file handle to convert
 * @fh_len:	length of the file handle in bytes
 * @fh_type:	type of file handle
 * @get_inode:	filesystem callback to retrieve inode
 *
 * This function decodes @fid as long as it has one of the well-known
 * Linux filehandle types and calls @get_inode on it to retrieve the
 * inode for the object specified in the file handle.
 */
struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type, struct inode *(*get_inode)
			(struct super_block *sb, u64 ino, u32 gen))
{
	struct inode *inode = NULL;

	if (fh_len < 2)
		return NULL;

	switch (fh_type) {
	case FILEID_INO32_GEN:
	case FILEID_INO32_GEN_PARENT:
		inode = get_inode(sb, fid->i32.ino, fid->i32.gen);
		break;
	}

	return d_obtain_alias(inode);
}
EXPORT_SYMBOL_GPL(generic_fh_to_dentry);

/**
 * generic_fh_to_parent - generic helper for the fh_to_parent export operation
 * @sb:		filesystem to do the file handle conversion on
 * @fid:	file handle to convert
 * @fh_len:	length of the file handle in bytes
 * @fh_type:	type of file handle
 * @get_inode:	filesystem callback to retrieve inode
 *
 * This function decodes @fid as long as it has one of the well-known
 * Linux filehandle types and calls @get_inode on it to retrieve the
 * inode for the _parent_ object specified in the file handle if it
 * is specified in the file handle, or NULL otherwise.
 */
struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type, struct inode *(*get_inode)
			(struct super_block *sb, u64 ino, u32 gen))
{
	struct inode *inode = NULL;

	if (fh_len <= 2)
		return NULL;

	switch (fh_type) {
	case FILEID_INO32_GEN_PARENT:
		inode = get_inode(sb, fid->i32.parent_ino,
				  (fh_len > 3 ? fid->i32.parent_gen : 0));
		break;
	}

	return d_obtain_alias(inode);
}
EXPORT_SYMBOL_GPL(generic_fh_to_parent);

/**
 * __generic_file_fsync - generic fsync implementation for simple filesystems
 *
 * @file:	file to synchronize
 * @start:	start offset in bytes
 * @end:	end offset in bytes (inclusive)
 * @datasync:	only synchronize essential metadata if true
 *
 * This is a generic implementation of the fsync method for simple
 * filesystems which track all non-inode metadata in the buffers list
 * hanging off the address_space structure.
 */
int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
				 int datasync)
{
	struct inode *inode = file->f_mapping->host;
	int err;
	int ret;

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

	inode_lock(inode);
	ret = sync_mapping_buffers(inode->i_mapping);
	if (!(inode->i_state & I_DIRTY_ALL))
		goto out;
	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
		goto out;

	err = sync_inode_metadata(inode, 1);
	if (ret == 0)
		ret = err;

out:
	inode_unlock(inode);
	return ret;
}
EXPORT_SYMBOL(__generic_file_fsync);

/**
 * generic_file_fsync - generic fsync implementation for simple filesystems
 *			with flush
 * @file:	file to synchronize
 * @start:	start offset in bytes
 * @end:	end offset in bytes (inclusive)
 * @datasync:	only synchronize essential metadata if true
 *
 */

int generic_file_fsync(struct file *file, loff_t start, loff_t end,
		       int datasync)
{
	struct inode *inode = file->f_mapping->host;
	int err;

	err = __generic_file_fsync(file, start, end, datasync);
	if (err)
		return err;
	return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
}
EXPORT_SYMBOL(generic_file_fsync);

/**
 * generic_check_addressable - Check addressability of file system
 * @blocksize_bits:	log of file system block size
 * @num_blocks:		number of blocks in file system
 *
 * Determine whether a file system with @num_blocks blocks (and a
 * block size of 2**@blocksize_bits) is addressable by the sector_t
 * and page cache of the system.  Return 0 if so and -EFBIG otherwise.
 */
int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
{
	u64 last_fs_block = num_blocks - 1;
	u64 last_fs_page =
		last_fs_block >> (PAGE_SHIFT - blocksize_bits);

	if (unlikely(num_blocks == 0))
		return 0;

	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT))
		return -EINVAL;

	if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
	    (last_fs_page > (pgoff_t)(~0ULL))) {
		return -EFBIG;
	}
	return 0;
}
EXPORT_SYMBOL(generic_check_addressable);

/*
 * No-op implementation of ->fsync for in-memory filesystems.
 */
int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	return 0;
}
EXPORT_SYMBOL(noop_fsync);

/* Because kfree isn't assignment-compatible with void(void*) ;-/ */
void kfree_link(void *p)
{
	kfree(p);
}
EXPORT_SYMBOL(kfree_link);

/*
 * nop .set_page_dirty method so that people can use .page_mkwrite on
 * anon inodes.
 */
static int anon_set_page_dirty(struct page *page)
{
	return 0;
};

/*
 * A single inode exists for all anon_inode files. Contrary to pipes,
 * anon_inode inodes have no associated per-instance data, so we need
 * only allocate one of them.
 */
struct inode *alloc_anon_inode(struct super_block *s)
{
	static const struct address_space_operations anon_aops = {
		.set_page_dirty = anon_set_page_dirty,
	};
	struct inode *inode = new_inode_pseudo(s);

	if (!inode)
		return ERR_PTR(-ENOMEM);

	inode->i_ino = get_next_ino();
	inode->i_mapping->a_ops = &anon_aops;

	/*
	 * Mark the inode dirty from the very beginning,
	 * that way it will never be moved to the dirty
	 * list because mark_inode_dirty() will think
	 * that it already _is_ on the dirty list.
	 */
	inode->i_state = I_DIRTY;
	inode->i_mode = S_IRUSR | S_IWUSR;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_flags |= S_PRIVATE;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	return inode;
}
EXPORT_SYMBOL(alloc_anon_inode);

/**
 * simple_nosetlease - generic helper for prohibiting leases
 * @filp: file pointer
 * @arg: type of lease to obtain
 * @flp: new lease supplied for insertion
 * @priv: private data for lm_setup operation
 *
 * Generic helper for filesystems that do not wish to allow leases to be set.
 * All arguments are ignored and it just returns -EINVAL.
 */
int
simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
		  void **priv)
{
	return -EINVAL;
}
EXPORT_SYMBOL(simple_nosetlease);

const char *simple_get_link(struct dentry *dentry, struct inode *inode,
			    struct delayed_call *done)
{
	return inode->i_link;
}
EXPORT_SYMBOL(simple_get_link);

const struct inode_operations simple_symlink_inode_operations = {
	.get_link = simple_get_link,
	.readlink = generic_readlink
};
EXPORT_SYMBOL(simple_symlink_inode_operations);

/*
 * Operations for a permanently empty directory.
 */
static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
	return ERR_PTR(-ENOENT);
}

static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
				 struct kstat *stat)
{
	struct inode *inode = d_inode(dentry);
	generic_fillattr(inode, stat);
	return 0;
}

static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
{
	return -EPERM;
}

static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size)
{
	return -EOPNOTSUPP;
}

static const struct inode_operations empty_dir_inode_operations = {
	.lookup		= empty_dir_lookup,
	.permission	= generic_permission,
	.setattr	= empty_dir_setattr,
	.getattr	= empty_dir_getattr,
	.listxattr	= empty_dir_listxattr,
};

static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence)
{
	/* An empty directory has two entries . and .. at offsets 0 and 1 */
	return generic_file_llseek_size(file, offset, whence, 2, 2);
}

static int empty_dir_readdir(struct file *file, struct dir_context *ctx)
{
	dir_emit_dots(file, ctx);
	return 0;
}

static const struct file_operations empty_dir_operations = {
	.llseek		= empty_dir_llseek,
	.read		= generic_read_dir,
	.iterate_shared	= empty_dir_readdir,
	.fsync		= noop_fsync,
};


void make_empty_dir_inode(struct inode *inode)
{
	set_nlink(inode, 2);
	inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
	inode->i_uid = GLOBAL_ROOT_UID;
	inode->i_gid = GLOBAL_ROOT_GID;
	inode->i_rdev = 0;
	inode->i_size = 0;
	inode->i_blkbits = PAGE_SHIFT;
	inode->i_blocks = 0;

	inode->i_op = &empty_dir_inode_operations;
	inode->i_opflags &= ~IOP_XATTR;
	inode->i_fop = &empty_dir_operations;
}

bool is_empty_dir_inode(struct inode *inode)
{
	return (inode->i_fop == &empty_dir_operations) &&
		(inode->i_op == &empty_dir_inode_operations);
}