aboutsummaryrefslogtreecommitdiffstats
path: root/fs/msdos/namei.c
blob: 1f7f2956412ac9527be5867aa5c5bca8ecc81db6 (plain) (blame)
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
/*
 *  linux/fs/msdos/namei.c
 *
 *  Written 1992,1993 by Werner Almesberger
 *  Hidden files 1995 by Albert Cahalan <albert@ccs.neu.edu> <adc@coe.neu.edu>
 *  Rewritten for constant inumbers 1999 by Al Viro
 */

#include <linux/module.h>
#include <linux/time.h>
#include <linux/buffer_head.h>
#include <linux/msdos_fs.h>
#include <linux/smp_lock.h>

/* Characters that are undesirable in an MS-DOS file name */
static unsigned char bad_chars[] = "*?<>|\"";
static unsigned char bad_if_strict_pc[] = "+=,; ";
/* GEMDOS is less restrictive */
static unsigned char bad_if_strict_atari[] = " ";

#define bad_if_strict(opts) \
	((opts)->atari ? bad_if_strict_atari : bad_if_strict_pc)

/***** Formats an MS-DOS file name. Rejects invalid names. */
static int msdos_format_name(const unsigned char *name, int len,
			     unsigned char *res, struct fat_mount_options *opts)
	/*
	 * name is the proposed name, len is its length, res is
	 * the resulting name, opts->name_check is either (r)elaxed,
	 * (n)ormal or (s)trict, opts->dotsOK allows dots at the
	 * beginning of name (for hidden files)
	 */
{
	unsigned char *walk;
	unsigned char c;
	int space;

	if (name[0] == '.') {	/* dotfile because . and .. already done */
		if (opts->dotsOK) {
			/* Get rid of dot - test for it elsewhere */
			name++;
			len--;
		} else if (!opts->atari)
			return -EINVAL;
	}
	/*
	 * disallow names that _really_ start with a dot for MS-DOS,
	 * GEMDOS does not care
	 */
	space = !opts->atari;
	c = 0;
	for (walk = res; len && walk - res < 8; walk++) {
		c = *name++;
		len--;
		if (opts->name_check != 'r' && strchr(bad_chars, c))
			return -EINVAL;
		if (opts->name_check == 's' && strchr(bad_if_strict(opts), c))
			return -EINVAL;
		if (c >= 'A' && c <= 'Z' && opts->name_check == 's')
			return -EINVAL;
		if (c < ' ' || c == ':' || c == '\\')
			return -EINVAL;
	/*
	 * 0xE5 is legal as a first character, but we must substitute
	 * 0x05 because 0xE5 marks deleted files.  Yes, DOS really
	 * does this.
	 * It seems that Microsoft hacked DOS to support non-US
	 * characters after the 0xE5 character was already in use to
	 * mark deleted files.
	 */
		if ((res == walk) && (c == 0xE5))
			c = 0x05;
		if (c == '.')
			break;
		space = (c == ' ');
		*walk = (!opts->nocase && c >= 'a' && c <= 'z') ? c - 32 : c;
	}
	if (space)
		return -EINVAL;
	if (opts->name_check == 's' && len && c != '.') {
		c = *name++;
		len--;
		if (c != '.')
			return -EINVAL;
	}
	while (c != '.' && len--)
		c = *name++;
	if (c == '.') {
		while (walk - res < 8)
			*walk++ = ' ';
		while (len > 0 && walk - res < MSDOS_NAME) {
			c = *name++;
			len--;
			if (opts->name_check != 'r' && strchr(bad_chars, c))
				return -EINVAL;
			if (opts->name_check == 's' &&
			    strchr(bad_if_strict(opts), c))
				return -EINVAL;
			if (c < ' ' || c == ':' || c == '\\')
				return -EINVAL;
			if (c == '.') {
				if (opts->name_check == 's')
					return -EINVAL;
				break;
			}
			if (c >= 'A' && c <= 'Z' && opts->name_check == 's')
				return -EINVAL;
			space = c == ' ';
			if (!opts->nocase && c >= 'a' && c <= 'z')
				*walk++ = c - 32;
			else
				*walk++ = c;
		}
		if (space)
			return -EINVAL;
		if (opts->name_check == 's' && len)
			return -EINVAL;
	}
	while (walk - res < MSDOS_NAME)
		*walk++ = ' ';

	return 0;
}

/***** Locates a directory entry.  Uses unformatted name. */
static int msdos_find(struct inode *dir, const unsigned char *name, int len,
		      struct fat_slot_info *sinfo)
{
	struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb);
	unsigned char msdos_name[MSDOS_NAME];
	int err;

	err = msdos_format_name(name, len, msdos_name, &sbi->options);
	if (err)
		return -ENOENT;

	err = fat_scan(dir, msdos_name, sinfo);
	if (!err && sbi->options.dotsOK) {
		if (name[0] == '.') {
			if (!(sinfo->de->attr & ATTR_HIDDEN))
				err = -ENOENT;
		} else {
			if (sinfo->de->attr & ATTR_HIDDEN)
				err = -ENOENT;
		}
		if (err)
			brelse(sinfo->bh);
	}
	return err;
}

/*
 * Compute the hash for the msdos name corresponding to the dentry.
 * Note: if the name is invalid, we leave the hash code unchanged so
 * that the existing dentry can be used. The msdos fs routines will
 * return ENOENT or EINVAL as appropriate.
 */
static int msdos_hash(struct dentry *dentry, struct qstr *qstr)
{
	struct fat_mount_options *options = &MSDOS_SB(dentry->d_sb)->options;
	unsigned char msdos_name[MSDOS_NAME];
	int error;

	error = msdos_format_name(qstr->name, qstr->len, msdos_name, options);
	if (!error)
		qstr->hash = full_name_hash(msdos_name, MSDOS_NAME);
	return 0;
}

/*
 * Compare two msdos names. If either of the names are invalid,
 * we fall back to doing the standard name comparison.
 */
static int msdos_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b)
{
	struct fat_mount_options *options = &MSDOS_SB(dentry->d_sb)->options;
	unsigned char a_msdos_name[MSDOS_NAME], b_msdos_name[MSDOS_NAME];
	int error;

	error = msdos_format_name(a->name, a->len, a_msdos_name, options);
	if (error)
		goto old_compare;
	error = msdos_format_name(b->name, b->len, b_msdos_name, options);
	if (error)
		goto old_compare;
	error = memcmp(a_msdos_name, b_msdos_name, MSDOS_NAME);
out:
	return error;

old_compare:
	error = 1;
	if (a->len == b->len)
		error = memcmp(a->name, b->name, a->len);
	goto out;
}

static struct dentry_operations msdos_dentry_operations = {
	.d_hash		= msdos_hash,
	.d_compare	= msdos_cmp,
};

/*
 * AV. Wrappers for FAT sb operations. Is it wise?
 */

/***** Get inode using directory and name */
static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
				   struct nameidata *nd)
{
	struct super_block *sb = dir->i_sb;
	struct fat_slot_info sinfo;
	struct inode *inode = NULL;
	int res;

	dentry->d_op = &msdos_dentry_operations;

	lock_super(sb);
	res = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
	if (res == -ENOENT)
		goto add;
	if (res < 0)
		goto out;
	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		res = PTR_ERR(inode);
		goto out;
	}
add:
	res = 0;
	dentry = d_splice_alias(inode, dentry);
	if (dentry)
		dentry->d_op = &msdos_dentry_operations;
out:
	unlock_super(sb);
	if (!res)
		return dentry;
	return ERR_PTR(res);
}

/***** Creates a directory entry (name is already formatted). */
static int msdos_add_entry(struct inode *dir, const unsigned char *name,
			   int is_dir, int is_hid, int cluster,
			   struct timespec *ts, struct fat_slot_info *sinfo)
{
	struct msdos_dir_entry de;
	__le16 time, date;
	int err;

	memcpy(de.name, name, MSDOS_NAME);
	de.attr = is_dir ? ATTR_DIR : ATTR_ARCH;
	if (is_hid)
		de.attr |= ATTR_HIDDEN;
	de.lcase = 0;
	fat_date_unix2dos(ts->tv_sec, &time, &date);
	de.cdate = de.adate = 0;
	de.ctime = 0;
	de.ctime_cs = 0;
	de.time = time;
	de.date = date;
	de.start = cpu_to_le16(cluster);
	de.starthi = cpu_to_le16(cluster >> 16);
	de.size = 0;

	err = fat_add_entries(dir, &de, 1, sinfo);
	if (err)
		return err;

	dir->i_ctime = dir->i_mtime = *ts;
	if (IS_DIRSYNC(dir))
		(void)fat_sync_inode(dir);
	else
		mark_inode_dirty(dir);

	return 0;
}

/***** Create a file */
static int msdos_create(struct inode *dir, struct dentry *dentry, int mode,
			struct nameidata *nd)
{
	struct super_block *sb = dir->i_sb;
	struct inode *inode = NULL;
	struct fat_slot_info sinfo;
	struct timespec ts;
	unsigned char msdos_name[MSDOS_NAME];
	int err, is_hid;

	lock_super(sb);

	err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
				msdos_name, &MSDOS_SB(sb)->options);
	if (err)
		goto out;
	is_hid = (dentry->d_name.name[0] == '.') && (msdos_name[0] != '.');
	/* Have to do it due to foo vs. .foo conflicts */
	if (!fat_scan(dir, msdos_name, &sinfo)) {
		brelse(sinfo.bh);
		err = -EINVAL;
		goto out;
	}

	ts = CURRENT_TIME_SEC;
	err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &ts, &sinfo);
	if (err)
		goto out;
	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		goto out;
	}
	inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
	/* timestamp is already written, so mark_inode_dirty() is unneeded. */

	d_instantiate(dentry, inode);
out:
	unlock_super(sb);
	if (!err)
		err = fat_flush_inodes(sb, dir, inode);
	return err;
}

/***** Remove a directory */
static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct super_block *sb = dir->i_sb;
	struct inode *inode = dentry->d_inode;
	struct fat_slot_info sinfo;
	int err;

	lock_super(sb);
	/*
	 * Check whether the directory is not in use, then check
	 * whether it is empty.
	 */
	err = fat_dir_empty(inode);
	if (err)
		goto out;
	err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
	if (err)
		goto out;

	err = fat_remove_entries(dir, &sinfo);	/* and releases bh */
	if (err)
		goto out;
	drop_nlink(dir);

	clear_nlink(inode);
	inode->i_ctime = CURRENT_TIME_SEC;
	fat_detach(inode);
out:
	unlock_super(sb);
	if (!err)
		err = fat_flush_inodes(sb, dir, inode);

	return err;
}

/***** Make a directory */
static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct super_block *sb = dir->i_sb;
	struct fat_slot_info sinfo;
	struct inode *inode;
	unsigned char msdos_name[MSDOS_NAME];
	struct timespec ts;
	int err, is_hid, cluster;

	lock_super(sb);

	err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
				msdos_name, &MSDOS_SB(sb)->options);
	if (err)
		goto out;
	is_hid = (dentry->d_name.name[0] == '.') && (msdos_name[0] != '.');
	/* foo vs .foo situation */
	if (!fat_scan(dir, msdos_name, &sinfo)) {
		brelse(sinfo.bh);
		err = -EINVAL;
		goto out;
	}

	ts = CURRENT_TIME_SEC;
	cluster = fat_alloc_new_dir(dir, &ts);
	if (cluster < 0) {
		err = cluster;
		goto out;
	}
	err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo);
	if (err)
		goto out_free;
	inc_nlink(dir);

	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
	brelse(sinfo.bh);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		/* the directory was completed, just return a error */
		goto out;
	}
	inode->i_nlink = 2;
	inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
	/* timestamp is already written, so mark_inode_dirty() is unneeded. */

	d_instantiate(dentry, inode);

	unlock_super(sb);
	fat_flush_inodes(sb, dir, inode);
	return 0;

out_free:
	fat_free_clusters(dir, cluster);
out:
	unlock_super(sb);
	return err;
}

/***** Unlink a file */
static int msdos_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;
	struct super_block *sb= inode->i_sb;
	struct fat_slot_info sinfo;
	int err;

	lock_super(sb);
	err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
	if (err)
		goto out;

	err = fat_remove_entries(dir, &sinfo);	/* and releases bh */
	if (err)
		goto out;
	clear_nlink(inode);
	inode->i_ctime = CURRENT_TIME_SEC;
	fat_detach(inode);
out:
	unlock_super(sb);
	if (!err)
		err = fat_flush_inodes(sb, dir, inode);

	return err;
}

static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
			   struct dentry *old_dentry,
			   struct inode *new_dir, unsigned char *new_name,
			   struct dentry *new_dentry, int is_hid)
{
	struct buffer_head *dotdot_bh;
	struct msdos_dir_entry *dotdot_de;
	struct inode *old_inode, *new_inode;
	struct fat_slot_info old_sinfo, sinfo;
	struct timespec ts;
	loff_t dotdot_i_pos, new_i_pos;
	int err, old_attrs, is_dir, update_dotdot, corrupt = 0;

	old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
	old_inode = old_dentry->d_inode;
	new_inode = new_dentry->d_inode;

	err = fat_scan(old_dir, old_name, &old_sinfo);
	if (err) {
		err = -EIO;
		goto out;
	}

	is_dir = S_ISDIR(old_inode->i_mode);
	update_dotdot = (is_dir && old_dir != new_dir);
	if (update_dotdot) {
		if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de,
					 &dotdot_i_pos) < 0) {
			err = -EIO;
			goto out;
		}
	}

	old_attrs = MSDOS_I(old_inode)->i_attrs;
	err = fat_scan(new_dir, new_name, &sinfo);
	if (!err) {
		if (!new_inode) {
			/* "foo" -> ".foo" case. just change the ATTR_HIDDEN */
			if (sinfo.de != old_sinfo.de) {
				err = -EINVAL;
				goto out;
			}
			if (is_hid)
				MSDOS_I(old_inode)->i_attrs |= ATTR_HIDDEN;
			else
				MSDOS_I(old_inode)->i_attrs &= ~ATTR_HIDDEN;
			if (IS_DIRSYNC(old_dir)) {
				err = fat_sync_inode(old_inode);
				if (err) {
					MSDOS_I(old_inode)->i_attrs = old_attrs;
					goto out;
				}
			} else
				mark_inode_dirty(old_inode);

			old_dir->i_version++;
			old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC;
			if (IS_DIRSYNC(old_dir))
				(void)fat_sync_inode(old_dir);
			else
				mark_inode_dirty(old_dir);
			goto out;
		}
	}

	ts = CURRENT_TIME_SEC;
	if (new_inode) {
		if (err)
			goto out;
		if (is_dir) {
			err = fat_dir_empty(new_inode);
			if (err)
				goto out;
		}
		new_i_pos = MSDOS_I(new_inode)->i_pos;
		fat_detach(new_inode);
	} else {
		err = msdos_add_entry(new_dir, new_name, is_dir, is_hid, 0,
				      &ts, &sinfo);
		if (err)
			goto out;
		new_i_pos = sinfo.i_pos;
	}
	new_dir->i_version++;

	fat_detach(old_inode);
	fat_attach(old_inode, new_i_pos);
	if (is_hid)
		MSDOS_I(old_inode)->i_attrs |= ATTR_HIDDEN;
	else
		MSDOS_I(old_inode)->i_attrs &= ~ATTR_HIDDEN;
	if (IS_DIRSYNC(new_dir)) {
		err = fat_sync_inode(old_inode);
		if (err)
			goto error_inode;
	} else
		mark_inode_dirty(old_inode);

	if (update_dotdot) {
		int start = MSDOS_I(new_dir)->i_logstart;
		dotdot_de->start = cpu_to_le16(start);
		dotdot_de->starthi = cpu_to_le16(start >> 16);
		mark_buffer_dirty(dotdot_bh);
		if (IS_DIRSYNC(new_dir)) {
			err = sync_dirty_buffer(dotdot_bh);
			if (err)
				goto error_dotdot;
		}
		drop_nlink(old_dir);
		if (!new_inode)
			inc_nlink(new_dir);
	}

	err = fat_remove_entries(old_dir, &old_sinfo);	/* and releases bh */
	old_sinfo.bh = NULL;
	if (err)
		goto error_dotdot;
	old_dir->i_version++;
	old_dir->i_ctime = old_dir->i_mtime = ts;
	if (IS_DIRSYNC(old_dir))
		(void)fat_sync_inode(old_dir);
	else
		mark_inode_dirty(old_dir);

	if (new_inode) {
		drop_nlink(new_inode);
		if (is_dir)
			drop_nlink(new_inode);
		new_inode->i_ctime = ts;
	}
out:
	brelse(sinfo.bh);
	brelse(dotdot_bh);
	brelse(old_sinfo.bh);
	return err;

error_dotdot:
	/* data cluster is shared, serious corruption */
	corrupt = 1;

	if (update_dotdot) {
		int start = MSDOS_I(old_dir)->i_logstart;
		dotdot_de->start = cpu_to_le16(start);
		dotdot_de->starthi = cpu_to_le16(start >> 16);
		mark_buffer_dirty(dotdot_bh);
		corrupt |= sync_dirty_buffer(dotdot_bh);
	}
error_inode:
	fat_detach(old_inode);
	fat_attach(old_inode, old_sinfo.i_pos);
	MSDOS_I(old_inode)->i_attrs = old_attrs;
	if (new_inode) {
		fat_attach(new_inode, new_i_pos);
		if (corrupt)
			corrupt |= fat_sync_inode(new_inode);
	} else {
		/*
		 * If new entry was not sharing the data cluster, it
		 * shouldn't be serious corruption.
		 */
		int err2 = fat_remove_entries(new_dir, &sinfo);
		if (corrupt)
			corrupt |= err2;
		sinfo.bh = NULL;
	}
	if (corrupt < 0) {
		fat_fs_panic(new_dir->i_sb,
			     "%s: Filesystem corrupted (i_pos %lld)",
			     __func__, sinfo.i_pos);
	}
	goto out;
}

/***** Rename, a wrapper for rename_same_dir & rename_diff_dir */
static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
			struct inode *new_dir, struct dentry *new_dentry)
{
	struct super_block *sb = old_dir->i_sb;
	unsigned char old_msdos_name[MSDOS_NAME], new_msdos_name[MSDOS_NAME];
	int err, is_hid;

	lock_super(sb);

	err = msdos_format_name(old_dentry->d_name.name,
				old_dentry->d_name.len, old_msdos_name,
				&MSDOS_SB(old_dir->i_sb)->options);
	if (err)
		goto out;
	err = msdos_format_name(new_dentry->d_name.name,
				new_dentry->d_name.len, new_msdos_name,
				&MSDOS_SB(new_dir->i_sb)->options);
	if (err)
		goto out;

	is_hid =
	     (new_dentry->d_name.name[0] == '.') && (new_msdos_name[0] != '.');

	err = do_msdos_rename(old_dir, old_msdos_name, old_dentry,
			      new_dir, new_msdos_name, new_dentry, is_hid);
out:
	unlock_super(sb);
	if (!err)
		err = fat_flush_inodes(sb, old_dir, new_dir);
	return err;
}

static const struct inode_operations msdos_dir_inode_operations = {
	.create		= msdos_create,
	.lookup		= msdos_lookup,
	.unlink		= msdos_unlink,
	.mkdir		= msdos_mkdir,
	.rmdir		= msdos_rmdir,
	.rename		= msdos_rename,
	.setattr	= fat_setattr,
	.getattr	= fat_getattr,
};

static int msdos_fill_super(struct super_block *sb, void *data, int silent)
{
	int res;

	res = fat_fill_super(sb, data, silent, &msdos_dir_inode_operations, 0);
	if (res)
		return res;

	sb->s_flags |= MS_NOATIME;
	sb->s_root->d_op = &msdos_dentry_operations;
	return 0;
}

static int msdos_get_sb(struct file_system_type *fs_type,
			int flags, const char *dev_name,
			void *data, struct vfsmount *mnt)
{
	return get_sb_bdev(fs_type, flags, dev_name, data, msdos_fill_super,
			   mnt);
}

static struct file_system_type msdos_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "msdos",
	.get_sb		= msdos_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init init_msdos_fs(void)
{
	return register_filesystem(&msdos_fs_type);
}

static void __exit exit_msdos_fs(void)
{
	unregister_filesystem(&msdos_fs_type);
}

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Werner Almesberger");
MODULE_DESCRIPTION("MS-DOS filesystem support");

module_init(init_msdos_fs)
module_exit(exit_msdos_fs)
pan class="hl opt">|| ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } /** * move_addr_to_user - copy an address to user space * @kaddr: kernel space address * @klen: length of address in kernel * @uaddr: user space address * @ulen: pointer to user length field * * The value pointed to by ulen on entry is the buffer length available. * This is overwritten with the buffer space used. -EINVAL is returned * if an overlong buffer is specified or a negative buffer size. -EFAULT * is returned if either the buffer or the length field are not * accessible. * After copying the data up to the limit the user specifies, the true * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr, int __user *ulen) { int err; int len; err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; if (len < 0 || len > sizeof(struct sockaddr_storage)) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } /* * "fromlen shall refer to the value before truncation.." * 1003.1g */ return __put_user(klen, ulen); } #define SOCKFS_MAGIC 0x534F434B static struct kmem_cache *sock_inode_cachep __read_mostly; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wait); ei->socket.fasync_list = NULL; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; ei->socket.sk = NULL; ei->socket.file = NULL; return &ei->vfs_inode; } static void sock_destroy_inode(struct inode *inode) { kmem_cache_free(sock_inode_cachep, container_of(inode, struct socket_alloc, vfs_inode)); } static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; inode_init_once(&ei->vfs_inode); } static int init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", sizeof(struct socket_alloc), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD), init_once); if (sock_inode_cachep == NULL) return -ENOMEM; return 0; } static struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .destroy_inode =sock_destroy_inode, .statfs = simple_statfs, }; static int sockfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { return get_sb_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC, mnt); } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", .get_sb = sockfs_get_sb, .kill_sb = kill_anon_super, }; static int sockfs_delete_dentry(struct dentry *dentry) { /* * At creation time, we pretended this dentry was hashed * (by clearing DCACHE_UNHASHED bit in d_flags) * At delete time, we restore the truth : not hashed. * (so that dput() can proceed correctly) */ dentry->d_flags |= DCACHE_UNHASHED; return 0; } /* * sockfs_dname() is called from d_path(). */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]", dentry->d_inode->i_ino); } static struct dentry_operations sockfs_dentry_operations = { .d_delete = sockfs_delete_dentry, .d_dname = sockfs_dname, }; /* * Obtains the first available file descriptor and sets it up for use. * * These functions create file structures and maps them to fd space * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer * to socket after mapping. If one day we will need it, this * function will increment ref. count on file by 1. * * In any case returned fd MAY BE not valid! * This race condition is unavoidable * with shared fd spaces, we cannot solve it inside kernel, * but we take care of internal coherence yet. */ static int sock_alloc_fd(struct file **filep, int flags) { int fd; fd = get_unused_fd_flags(flags); if (likely(fd >= 0)) { struct file *file = get_empty_filp(); *filep = file; if (unlikely(!file)) { put_unused_fd(fd); return -ENFILE; } } else *filep = NULL; return fd; } static int sock_attach_fd(struct socket *sock, struct file *file, int flags) { struct dentry *dentry; struct qstr name = { .name = "" }; dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name); if (unlikely(!dentry)) return -ENOMEM; dentry->d_op = &sockfs_dentry_operations; /* * We dont want to push this dentry into global dentry hash table. * We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED * This permits a working /proc/$pid/fd/XXX on sockets */ dentry->d_flags &= ~DCACHE_UNHASHED; d_instantiate(dentry, SOCK_INODE(sock)); sock->file = file; init_file(file, sock_mnt, dentry, FMODE_READ | FMODE_WRITE, &socket_file_ops); SOCK_INODE(sock)->i_fop = &socket_file_ops; file->f_flags = O_RDWR | (flags & O_NONBLOCK); file->f_pos = 0; file->private_data = sock; return 0; } int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = sock_alloc_fd(&newfile, flags); if (likely(fd >= 0)) { int err = sock_attach_fd(sock, newfile, flags); if (unlikely(err < 0)) { put_filp(newfile); put_unused_fd(fd); return err; } fd_install(fd, newfile); } return fd; } static struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) return file->private_data; /* set in sock_map_fd */ *err = -ENOTSOCK; return NULL; } /** * sockfd_lookup - Go from a file number to its socket slot * @fd: file handle * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound * too is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * * On a success the socket object pointer is returned. */ struct socket *sockfd_lookup(int fd, int *err) { struct file *file; struct socket *sock; file = fget(fd); if (!file) { *err = -EBADF; return NULL; } sock = sock_from_file(file, err); if (!sock) fput(file); return sock; } static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) { struct file *file; struct socket *sock; *err = -EBADF; file = fget_light(fd, fput_needed); if (file) { sock = sock_from_file(file, err); if (sock) return sock; fput_light(file, *fput_needed); } return NULL; } /** * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. */ static struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; get_cpu_var(sockets_in_use)++; put_cpu_var(sockets_in_use); return sock; } /* * In theory you can't get an open on this inode, but /proc provides * a back door. Remember to keep it shut otherwise you'll let the * creepy crawlies in. */ static int sock_no_open(struct inode *irrelevant, struct file *dontcare) { return -ENXIO; } const struct file_operations bad_sock_fops = { .owner = THIS_MODULE, .open = sock_no_open, }; /** * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to * an inode not a file. */ void sock_release(struct socket *sock) { if (sock->ops) { struct module *owner = sock->ops->owner; sock->ops->release(sock); sock->ops = NULL; module_put(owner); } if (sock->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); get_cpu_var(sockets_in_use)--; put_cpu_var(sockets_in_use); if (!sock->file) { iput(SOCK_INODE(sock)); return; } sock->file = NULL; } static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size) { struct sock_iocb *si = kiocb_to_siocb(iocb); int err; si->sock = sock; si->scm = NULL; si->msg = msg; si->size = size; err = security_socket_sendmsg(sock, msg, size); if (err) return err; return sock->ops->sendmsg(iocb, sock, msg, size); } int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct kiocb iocb; struct sock_iocb siocb; int ret; init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; ret = __sock_sendmsg(&iocb, sock, msg, size); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { mm_segment_t oldfs = get_fs(); int result; set_fs(KERNEL_DS); /* * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ msg->msg_iov = (struct iovec *)vec; msg->msg_iovlen = num; result = sock_sendmsg(sock, msg, size); set_fs(oldfs); return result; } /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { ktime_t kt = skb->tstamp; if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { struct timeval tv; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (kt.tv64 == 0) kt = ktime_get_real(); skb->tstamp = kt; tv = ktime_to_timeval(kt); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, sizeof(tv), &tv); } else { struct timespec ts; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (kt.tv64 == 0) kt = ktime_get_real(); skb->tstamp = kt; ts = ktime_to_timespec(kt); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, sizeof(ts), &ts); } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { int err; struct sock_iocb *si = kiocb_to_siocb(iocb); si->sock = sock; si->scm = NULL; si->msg = msg; si->size = size; si->flags = flags; err = security_socket_recvmsg(sock, msg, size, flags); if (err) return err; return sock->ops->recvmsg(iocb, sock, msg, size, flags); } int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct kiocb iocb; struct sock_iocb siocb; int ret; init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; ret = __sock_recvmsg(&iocb, sock, msg, size, flags); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { mm_segment_t oldfs = get_fs(); int result; set_fs(KERNEL_DS); /* * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num; result = sock_recvmsg(sock, msg, size, flags); set_fs(oldfs); return result; } static void sock_aio_dtor(struct kiocb *iocb) { kfree(iocb->private); } static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more) { struct socket *sock; int flags; sock = file->private_data; flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT; if (more) flags |= MSG_MORE; return sock->ops->sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct socket *sock = file->private_data; if (unlikely(!sock->ops->splice_read)) return -EINVAL; return sock->ops->splice_read(sock, ppos, pipe, len, flags); } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { siocb = kmalloc(sizeof(*siocb), GFP_KERNEL); if (!siocb) return NULL; iocb->ki_dtor = sock_aio_dtor; } siocb->kiocb = iocb; iocb->private = siocb; return siocb; } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, struct file *file, const struct iovec *iov, unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; int i; for (i = 0; i < nr_segs; i++) size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; msg->msg_iov = (struct iovec *)iov; msg->msg_iovlen = nr_segs; msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); } static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, struct file *file, const struct iovec *iov, unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; int i; for (i = 0; i < nr_segs; i++) size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; msg->msg_iov = (struct iovec *)iov; msg->msg_iovlen = nr_segs; msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; if (sock->type == SOCK_SEQPACKET) msg->msg_flags |= MSG_EOR; return __sock_sendmsg(iocb, sock, msg, size); } static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg) = NULL; void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); static DEFINE_MUTEX(dlci_ioctl_mutex); static int (*dlci_ioctl_hook) (unsigned int, void __user *); void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) { mutex_lock(&dlci_ioctl_mutex); dlci_ioctl_hook = hook; mutex_unlock(&dlci_ioctl_mutex); } EXPORT_SYMBOL(dlci_ioctl_set); /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. */ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; int pid, err; struct net *net; sock = file->private_data; sk = sock->sk; net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { err = dev_ioctl(net, cmd, argp); } else #ifdef CONFIG_WIRELESS_EXT if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = dev_ioctl(net, cmd, argp); } else #endif /* CONFIG_WIRELESS_EXT */ switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: err = -ENOPKG; if (!br_ioctl_hook) request_module("bridge"); mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(net, cmd, argp); mutex_unlock(&br_ioctl_mutex); break; case SIOCGIFVLAN: case SIOCSIFVLAN: err = -ENOPKG; if (!vlan_ioctl_hook) request_module("8021q"); mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; case SIOCADDDLCI: case SIOCDELDLCI: err = -ENOPKG; if (!dlci_ioctl_hook) request_module("dlci"); mutex_lock(&dlci_ioctl_mutex); if (dlci_ioctl_hook) err = dlci_ioctl_hook(cmd, argp); mutex_unlock(&dlci_ioctl_mutex); break; default: err = sock->ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down * to the NIC driver. */ if (err == -ENOIOCTLCMD) err = dev_ioctl(net, cmd, argp); break; } return err; } int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; err = security_socket_create(family, type, protocol, 1); if (err) goto out; sock = sock_alloc(); if (!sock) { err = -ENOMEM; goto out; } sock->type = type; err = security_socket_post_create(sock, family, type, protocol, 1); if (err) goto out_release; out: *res = sock; return err; out_release: sock_release(sock); sock = NULL; goto out; } /* No kernel lock held - perfect */ static unsigned int sock_poll(struct file *file, poll_table *wait) { struct socket *sock; /* * We can't return errors to poll, so it's either yes or no. */ sock = file->private_data; return sock->ops->poll(file, sock, wait); } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; return sock->ops->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { /* * It was possible the inode is NULL we were * closing an unfinished socket. */ if (!inode) { printk(KERN_DEBUG "sock_close: NULL inode\n"); return 0; } sock_fasync(-1, filp, 0); sock_release(SOCKET_I(inode)); return 0; } /* * Update the socket async list * * Fasync_list locking strategy. * * 1. fasync_list is modified only under process context socket lock * i.e. under semaphore. * 2. fasync_list is used under read_lock(&sk->sk_callback_lock) * or under socket lock. * 3. fasync_list can be used from softirq context, so that * modification under socket lock have to be enhanced with * write_lock_bh(&sk->sk_callback_lock). * --ANK (990710) */ static int sock_fasync(int fd, struct file *filp, int on) { struct fasync_struct *fa, *fna = NULL, **prev; struct socket *sock; struct sock *sk; if (on) { fna = kmalloc(sizeof(struct fasync_struct), GFP_KERNEL); if (fna == NULL) return -ENOMEM; } sock = filp->private_data; sk = sock->sk; if (sk == NULL) { kfree(fna); return -EINVAL; } lock_sock(sk); prev = &(sock->fasync_list); for (fa = *prev; fa != NULL; prev = &fa->fa_next, fa = *prev) if (fa->fa_file == filp) break; if (on) { if (fa != NULL) { write_lock_bh(&sk->sk_callback_lock); fa->fa_fd = fd; write_unlock_bh(&sk->sk_callback_lock); kfree(fna); goto out; } fna->fa_file = filp; fna->fa_fd = fd; fna->magic = FASYNC_MAGIC; fna->fa_next = sock->fasync_list; write_lock_bh(&sk->sk_callback_lock); sock->fasync_list = fna; write_unlock_bh(&sk->sk_callback_lock); } else { if (fa != NULL) { write_lock_bh(&sk->sk_callback_lock); *prev = fa->fa_next; write_unlock_bh(&sk->sk_callback_lock); kfree(fa); } } out: release_sock(sock->sk); return 0; } /* This function may be called only under socket lock or callback_lock */ int sock_wake_async(struct socket *sock, int how, int band) { if (!sock || !sock->fasync_list) return -1; switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags)) break; /* fall through */ case SOCK_WAKE_IO: call_kill: __kill_fasync(sock->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: __kill_fasync(sock->fasync_list, SIGURG, band); } return 0; } static int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { static int warned; if (!warned) { warned = 1; printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); } family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc(); if (!sock) { if (net_ratelimit()) printk(KERN_WARNING "socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (net_families[family] == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol); if (err < 0) goto out_module_put; /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } int sock_create_kern(int family, int type, int protocol, struct socket **res) { return __sock_create(&init_net, family, type, protocol, res, 1); } asmlinkage long sys_socket(int family, int type, int protocol) { int retval; struct socket *sock; int flags; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) goto out; retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); if (retval < 0) goto out_release; out: /* It may be already another descriptor 8) Not kernel problem. */ return retval; out_release: sock_release(sock); return retval; } /* * Create a pair of connected sockets. */ asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; int flags; flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); if (err < 0) goto out; err = sock_create(family, type, protocol, &sock2); if (err < 0) goto out_release_1; err = sock1->ops->socketpair(sock1, sock2); if (err < 0) goto out_release_both; fd1 = sock_alloc_fd(&newfile1, flags & O_CLOEXEC); if (unlikely(fd1 < 0)) { err = fd1; goto out_release_both; } fd2 = sock_alloc_fd(&newfile2, flags & O_CLOEXEC); if (unlikely(fd2 < 0)) { err = fd2; put_filp(newfile1); put_unused_fd(fd1); goto out_release_both; } err = sock_attach_fd(sock1, newfile1, flags & O_NONBLOCK); if (unlikely(err < 0)) { goto out_fd2; } err = sock_attach_fd(sock2, newfile2, flags & O_NONBLOCK); if (unlikely(err < 0)) { fput(newfile1); goto out_fd1; } err = audit_fd_pair(fd1, fd2); if (err < 0) { fput(newfile1); fput(newfile2); goto out_fd; } fd_install(fd1, newfile1); fd_install(fd2, newfile2); /* fd1 and fd2 may be already another descriptors. * Not kernel problem. */ err = put_user(fd1, &usockvec[0]); if (!err) err = put_user(fd2, &usockvec[1]); if (!err) return 0; sys_close(fd2); sys_close(fd1); return err; out_release_both: sock_release(sock2); out_release_1: sock_release(sock1); out: return err; out_fd2: put_filp(newfile1); sock_release(sock1); out_fd1: put_filp(newfile2); sock_release(sock2); out_fd: put_unused_fd(fd1); put_unused_fd(fd2); goto out; } /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. * * We move the socket address to kernel space before we call * the protocol layer (having also checked the address is ok). */ asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address); if (err >= 0) { err = security_socket_bind(sock, (struct sockaddr *)&address, addrlen); if (!err) err = sock->ops->bind(sock, (struct sockaddr *) &address, addrlen); } fput_light(sock->file, fput_needed); } return err; } /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ asmlinkage long sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; int somaxconn; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; if ((unsigned)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); if (!err) err = sock->ops->listen(sock, backlog); fput_light(sock->file, fput_needed); } return err; } /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new * connected fd. We collect the address of the connector in kernel * space and move it to user at the very end. This is unclean because * we open the socket then return an error. * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats * clean when we restucture accept also. */ long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; struct sockaddr_storage address; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = -ENFILE; if (!(newsock = sock_alloc())) goto out_put; newsock->type = sock->type; newsock->ops = sock->ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ __module_get(newsock->ops->owner); newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); goto out_put; } err = sock_attach_fd(newsock, newfile, flags & O_NONBLOCK); if (err < 0) goto out_fd_simple; err = security_socket_accept(sock, newsock); if (err) goto out_fd; err = sock->ops->accept(sock, newsock, sock->file->f_flags); if (err < 0) goto out_fd; if (upeer_sockaddr) { if (newsock->ops->getname(newsock, (struct sockaddr *)&address, &len, 2) < 0) { err = -ECONNABORTED; goto out_fd; } err = move_addr_to_user((struct sockaddr *)&address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ fd_install(newfd, newfile); err = newfd; security_socket_post_accept(sock, newsock); out_put: fput_light(sock->file, fput_needed); out: return err; out_fd_simple: sock_release(newsock); put_filp(newfile); put_unused_fd(newfd); goto out_put; out_fd: fput(newfile); put_unused_fd(newfd); goto out_put; } #if 0 #ifdef HAVE_SET_RESTORE_SIGMASK asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, const sigset_t __user *sigmask, size_t sigsetsize, int flags) { sigset_t ksigmask, sigsaved; int ret; if (sigmask) { /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) return -EFAULT; sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); if (ret < 0 && signal_pending(current)) { /* * Don't restore the signal mask yet. Let do_signal() deliver * the signal on the way back to userspace, before the signal * mask is restored. */ if (sigmask) { memcpy(&current->saved_sigmask, &sigsaved, sizeof(sigsaved)); set_restore_sigmask(); } } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); return ret; } #else asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, const sigset_t __user *sigmask, size_t sigsetsize, int flags) { /* The platform does not support restoring the signal mask in the * return path. So we do not allow using paccept() with a signal * mask. */ if (sigmask) return -EINVAL; return do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); } #endif #endif asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen) { return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0); } /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. * * For 1003.1g we need to add clean support for a bind to AF_UNSPEC to * break bindings * * NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and * other SEQPACKET protocols that take time to connect() as it doesn't * include the -EINPROGRESS status for such sockets. */ asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = move_addr_to_kernel(uservaddr, addrlen, (struct sockaddr *)&address); if (err < 0) goto out_put; err = security_socket_connect(sock, (struct sockaddr *)&address, addrlen); if (err) goto out_put; err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, sock->file->f_flags); out_put: fput_light(sock->file, fput_needed); out: return err; } /* * Get the local address ('name') of a socket object. Move the obtained * name to user space. */ asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int len, err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = security_socket_getsockname(sock); if (err) goto out_put; err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0); if (err) goto out_put; err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); out: return err; } /* * Get the remote address ('name') of a socket object. Move the obtained * name to user space. */ asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int len, err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_getpeername(sock); if (err) { fput_light(sock->file, fput_needed); return err; } err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 1); if (!err) err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } return err; } /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ asmlinkage long sys_sendto(int fd, void __user *buff, size_t len, unsigned flags, struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; struct iovec iov; int fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; iov.iov_base = buff; iov.iov_len = len; msg.msg_name = NULL; msg.msg_iov = &iov; msg.msg_iovlen = 1; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; if (addr) { err = move_addr_to_kernel(addr, addr_len, (struct sockaddr *)&address); if (err < 0) goto out_put; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; err = sock_sendmsg(sock, &msg, len); out_put: fput_light(sock->file, fput_needed); out: return err; } /* * Send a datagram down a socket. */ asmlinkage long sys_send(int fd, void __user *buff, size_t len, unsigned flags) { return sys_sendto(fd, buff, len, flags, NULL, 0); } /* * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ asmlinkage long sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned flags, struct sockaddr __user *addr, int __user *addr_len) { struct socket *sock; struct iovec iov; struct msghdr msg; struct sockaddr_storage address; int err, err2; int fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_iovlen = 1; msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = sizeof(address); if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, size, flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user((struct sockaddr *)&address, msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } fput_light(sock->file, fput_needed); out: return err; } /* * Receive a datagram from a socket. */ asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size, unsigned flags) { return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } /* * Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ asmlinkage long sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { int err, fput_needed; struct socket *sock; if (optlen < 0) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, optlen); else err = sock->ops->setsockopt(sock, level, optname, optval, optlen); out_put: fput_light(sock->file, fput_needed); } return err; } /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ asmlinkage long sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { int err, fput_needed; struct socket *sock; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_getsockopt(sock, level, optname); if (err) goto out_put; if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, optlen); else err = sock->ops->getsockopt(sock, level, optname, optval, optlen); out_put: fput_light(sock->file, fput_needed); } return err; } /* * Shutdown a socket. */ asmlinkage long sys_shutdown(int fd, int how) { int err, fput_needed; struct socket *sock; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_shutdown(sock, how); if (!err) err = sock->ops->shutdown(sock, how); fput_light(sock->file, fput_needed); } return err; } /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) /* * BSD sendmsg interface */ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; struct socket *sock; struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] __attribute__ ((aligned(sizeof(__kernel_size_t)))); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; struct msghdr msg_sys; int err, ctl_len, iov_size, total_len; int fput_needed; err = -EFAULT; if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(&msg_sys, msg_compat)) return -EFAULT; } else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; /* do not move before msg_sys is valid */ err = -EMSGSIZE; if (msg_sys.msg_iovlen > UIO_MAXIOV) goto out_put; /* Check whether to allocate the iovec area */ err = -ENOMEM; iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); if (msg_sys.msg_iovlen > UIO_FASTIOV) { iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); if (!iov) goto out_put; } /* This will also move the address data into kernel space */ if (MSG_CMSG_COMPAT & flags) { err = verify_compat_iovec(&msg_sys, iov, (struct sockaddr *)&address, VERIFY_READ); } else err = verify_iovec(&msg_sys, iov, (struct sockaddr *)&address, VERIFY_READ); if (err < 0) goto out_freeiov; total_len = err; err = -ENOBUFS; if (msg_sys.msg_controllen > INT_MAX) goto out_freeiov; ctl_len = msg_sys.msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out_freeiov; ctl_buf = msg_sys.msg_control; ctl_len = msg_sys.msg_controllen; } else if (ctl_len) { if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) goto out_freeiov; } err = -EFAULT; /* * Careful! Before this, msg_sys.msg_control contains a user pointer. * Afterwards, it will be a kernel pointer. Thus the compiler-assisted * checking falls down on this. */ if (copy_from_user(ctl_buf, (void __user *)msg_sys.msg_control, ctl_len)) goto out_freectl; msg_sys.msg_control = ctl_buf; } msg_sys.msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) msg_sys.msg_flags |= MSG_DONTWAIT; err = sock_sendmsg(sock, &msg_sys, total_len); out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); out_put: fput_light(sock->file, fput_needed); out: return err; } /* * BSD recvmsg interface */ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flags) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; struct socket *sock; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct msghdr msg_sys; unsigned long cmsg_ptr; int err, iov_size, total_len, len; int fput_needed; /* kernel mode address */ struct sockaddr_storage addr; /* user mode address pointers */ struct sockaddr __user *uaddr; int __user *uaddr_len; if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(&msg_sys, msg_compat)) return -EFAULT; } else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = -EMSGSIZE; if (msg_sys.msg_iovlen > UIO_MAXIOV) goto out_put; /* Check whether to allocate the iovec area */ err = -ENOMEM; iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); if (msg_sys.msg_iovlen > UIO_FASTIOV) { iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); if (!iov) goto out_put; } /* * Save the user-mode address (verify_iovec will change the * kernel msghdr to use the kernel address space) */ uaddr = (__force void __user *)msg_sys.msg_name; uaddr_len = COMPAT_NAMELEN(msg); if (MSG_CMSG_COMPAT & flags) { err = verify_compat_iovec(&msg_sys, iov, (struct sockaddr *)&addr, VERIFY_WRITE); } else err = verify_iovec(&msg_sys, iov, (struct sockaddr *)&addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; total_len = err; cmsg_ptr = (unsigned long)msg_sys.msg_control; msg_sys.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg_sys, total_len, flags); if (err < 0) goto out_freeiov; len = err; if (uaddr != NULL) { err = move_addr_to_user((struct sockaddr *)&addr, msg_sys.msg_namelen, uaddr, uaddr_len); if (err < 0) goto out_freeiov; } err = __put_user((msg_sys.msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out_freeiov; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, &msg_compat->msg_controllen); else err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out_freeiov; err = len; out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); out_put: fput_light(sock->file, fput_needed); out: return err; } #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) static const unsigned char nargs[19]={ AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), AL(6) }; #undef AL /* * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because * it is set by the callees. */ asmlinkage long sys_socketcall(int call, unsigned long __user *args) { unsigned long a[6]; unsigned long a0, a1; int err; if (call < 1 || call > SYS_PACCEPT) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, nargs[call])) return -EFAULT; err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: err = sys_socket(a0, a1, a[2]); break; case SYS_BIND: err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: err = sys_listen(a0, a1); break; case SYS_ACCEPT: err = do_accept(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_GETPEERNAME: err = sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_SOCKETPAIR: err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: err = sys_send(a0, (void __user *)a1, a[2], a[3]); break; case SYS_SENDTO: err = sys_sendto(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: err = sys_recv(a0, (void __user *)a1, a[2], a[3]); break; case SYS_RECVFROM: err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], (int __user *)a[5]); break; case SYS_SHUTDOWN: err = sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); break; case SYS_GETSOCKOPT: err = sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); break; case SYS_SENDMSG: err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]); break; case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; case SYS_PACCEPT: err = sys_paccept(a0, (struct sockaddr __user *)a1, (int __user *)a[2], (const sigset_t __user *) a[3], a[4], a[5]); break; default: err = -EINVAL; break; } return err; } #endif /* __ARCH_WANT_SYS_SOCKETCALL */ /** * sock_register - add a socket protocol handler * @ops: description of protocol * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the * socket interface. The value ops->family coresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } spin_lock(&net_family_lock); if (net_families[ops->family]) err = -EEXIST; else { net_families[ops->family] = ops; err = 0; } spin_unlock(&net_family_lock); printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family); return err; } /** * sock_unregister - remove a protocol handler * @family: protocol family to remove * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the * new socket creation. * * If protocol handler is a module, then it can use module reference * counts to protect against new references. If protocol handler is not * a module then it needs to provide its own protection in * the ops->create routine. */ void sock_unregister(int family) { BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); net_families[family] = NULL; spin_unlock(&net_family_lock); synchronize_rcu(); printk(KERN_INFO "NET: Unregistered protocol family %d\n", family); } static int __init sock_init(void) { /* * Initialize sock SLAB cache. */ sk_init(); /* * Initialize skbuff SLAB cache */ skb_init(); /* * Initialize the protocols module. */ init_inodecache(); register_filesystem(&sock_fs_type); sock_mnt = kern_mount(&sock_fs_type); /* The real protocol initialization is performed in later initcalls. */ #ifdef CONFIG_NETFILTER netfilter_init(); #endif return 0; } core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { int cpu; int counter = 0; for_each_possible_cpu(cpu) counter += per_cpu(sockets_in_use, cpu); /* It can be negative, by the way. 8) */ if (counter < 0) counter = 0; seq_printf(seq, "sockets: used %d\n", counter); } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock = file->private_data; int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; sk = sock->sk; net = sock_net(sk); if (sock->ops->compat_ioctl) ret = sock->ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) ret = compat_wext_handle_ioctl(net, cmd, arg); return ret; } #endif int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { return sock->ops->bind(sock, addr, addrlen); } int kernel_listen(struct socket *sock, int backlog) { return sock->ops->listen(sock, backlog); } int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, newsock); if (err < 0) goto done; err = sock->ops->accept(sock, *newsock, flags); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } (*newsock)->ops = sock->ops; done: return err; } int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { return sock->ops->connect(sock, addr, addrlen, flags); } int kernel_getsockname(struct socket *sock, struct sockaddr *addr, int *addrlen) { return sock->ops->getname(sock, addr, addrlen, 0); } int kernel_getpeername(struct socket *sock, struct sockaddr *addr, int *addrlen) { return sock->ops->getname(sock, addr, addrlen, 1); } int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen) { mm_segment_t oldfs = get_fs(); int err; set_fs(KERNEL_DS); if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, optlen); else err = sock->ops->getsockopt(sock, level, optname, optval, optlen); set_fs(oldfs); return err; } int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, int optlen) { mm_segment_t oldfs = get_fs(); int err; set_fs(KERNEL_DS); if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, optlen); else err = sock->ops->setsockopt(sock, level, optname, optval, optlen); set_fs(oldfs); return err; } int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { if (sock->ops->sendpage) return sock->ops->sendpage(sock, page, offset, size, flags); return sock_no_sendpage(sock, page, offset, size, flags); } int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg) { mm_segment_t oldfs = get_fs(); int err; set_fs(KERNEL_DS); err = sock->ops->ioctl(sock, cmd, arg); set_fs(oldfs); return err; } int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return sock->ops->shutdown(sock, how); } EXPORT_SYMBOL(sock_create); EXPORT_SYMBOL(sock_create_kern); EXPORT_SYMBOL(sock_create_lite); EXPORT_SYMBOL(sock_map_fd); EXPORT_SYMBOL(sock_recvmsg); EXPORT_SYMBOL(sock_register); EXPORT_SYMBOL(sock_release); EXPORT_SYMBOL(sock_sendmsg); EXPORT_SYMBOL(sock_unregister); EXPORT_SYMBOL(sock_wake_async); EXPORT_SYMBOL(sockfd_lookup); EXPORT_SYMBOL(kernel_sendmsg); EXPORT_SYMBOL(kernel_recvmsg); EXPORT_SYMBOL(kernel_bind); EXPORT_SYMBOL(kernel_listen); EXPORT_SYMBOL(kernel_accept); EXPORT_SYMBOL(kernel_connect); EXPORT_SYMBOL(kernel_getsockname); EXPORT_SYMBOL(kernel_getpeername); EXPORT_SYMBOL(kernel_getsockopt); EXPORT_SYMBOL(kernel_setsockopt); EXPORT_SYMBOL(kernel_sendpage); EXPORT_SYMBOL(kernel_sock_ioctl); EXPORT_SYMBOL(kernel_sock_shutdown);