summaryrefslogtreecommitdiffstats
path: root/fs/proc/generic.c
blob: 7b4d9714f2485a5c53397bf9dc198419b8b30464 (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
/*
 * proc/fs/generic.c --- generic routines for the proc-fs
 *
 * This file contains generic proc-fs routines for handling
 * directories and files.
 * 
 * Copyright (C) 1991, 1992 Linus Torvalds.
 * Copyright (C) 1997 Theodore Ts'o
 */

#include <linux/cache.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/printk.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/idr.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>

#include "internal.h"

static DEFINE_RWLOCK(proc_subdir_lock);

struct kmem_cache *proc_dir_entry_cache __ro_after_init;

void pde_free(struct proc_dir_entry *pde)
{
	if (S_ISLNK(pde->mode))
		kfree(pde->data);
	if (pde->name != pde->inline_name)
		kfree(pde->name);
	kmem_cache_free(proc_dir_entry_cache, pde);
}

static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len)
{
	if (len < de->namelen)
		return -1;
	if (len > de->namelen)
		return 1;

	return memcmp(name, de->name, len);
}

static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
{
	return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
			     subdir_node);
}

static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
{
	return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
			     subdir_node);
}

static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
					      const char *name,
					      unsigned int len)
{
	struct rb_node *node = dir->subdir.rb_node;

	while (node) {
		struct proc_dir_entry *de = rb_entry(node,
						     struct proc_dir_entry,
						     subdir_node);
		int result = proc_match(name, de, len);

		if (result < 0)
			node = node->rb_left;
		else if (result > 0)
			node = node->rb_right;
		else
			return de;
	}
	return NULL;
}

static bool pde_subdir_insert(struct proc_dir_entry *dir,
			      struct proc_dir_entry *de)
{
	struct rb_root *root = &dir->subdir;
	struct rb_node **new = &root->rb_node, *parent = NULL;

	/* Figure out where to put new node */
	while (*new) {
		struct proc_dir_entry *this = rb_entry(*new,
						       struct proc_dir_entry,
						       subdir_node);
		int result = proc_match(de->name, this, de->namelen);

		parent = *new;
		if (result < 0)
			new = &(*new)->rb_left;
		else if (result > 0)
			new = &(*new)->rb_right;
		else
			return false;
	}

	/* Add new node and rebalance tree. */
	rb_link_node(&de->subdir_node, parent, new);
	rb_insert_color(&de->subdir_node, root);
	return true;
}

static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	struct proc_dir_entry *de = PDE(inode);
	int error;

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

	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);

	proc_set_user(de, inode->i_uid, inode->i_gid);
	de->mode = inode->i_mode;
	return 0;
}

static int proc_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int query_flags)
{
	struct inode *inode = d_inode(path->dentry);
	struct proc_dir_entry *de = PDE(inode);
	if (de && de->nlink)
		set_nlink(inode, de->nlink);

	generic_fillattr(inode, stat);
	return 0;
}

static const struct inode_operations proc_file_inode_operations = {
	.setattr	= proc_notify_change,
};

/*
 * This function parses a name such as "tty/driver/serial", and
 * returns the struct proc_dir_entry for "/proc/tty/driver", and
 * returns "serial" in residual.
 */
static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
			     const char **residual)
{
	const char     		*cp = name, *next;
	struct proc_dir_entry	*de;
	unsigned int		len;

	de = *ret;
	if (!de)
		de = &proc_root;

	while (1) {
		next = strchr(cp, '/');
		if (!next)
			break;

		len = next - cp;
		de = pde_subdir_find(de, cp, len);
		if (!de) {
			WARN(1, "name '%s'\n", name);
			return -ENOENT;
		}
		cp += len + 1;
	}
	*residual = cp;
	*ret = de;
	return 0;
}

static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
			   const char **residual)
{
	int rv;

	read_lock(&proc_subdir_lock);
	rv = __xlate_proc_name(name, ret, residual);
	read_unlock(&proc_subdir_lock);
	return rv;
}

static DEFINE_IDA(proc_inum_ida);

#define PROC_DYNAMIC_FIRST 0xF0000000U

/*
 * Return an inode number between PROC_DYNAMIC_FIRST and
 * 0xffffffff, or zero on failure.
 */
int proc_alloc_inum(unsigned int *inum)
{
	int i;

	i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1,
			   GFP_KERNEL);
	if (i < 0)
		return i;

	*inum = PROC_DYNAMIC_FIRST + (unsigned int)i;
	return 0;
}

void proc_free_inum(unsigned int inum)
{
	ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
}

static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
{
	if (flags & LOOKUP_RCU)
		return -ECHILD;

	if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0)
		return 0; /* revalidate */
	return 1;
}

static int proc_misc_d_delete(const struct dentry *dentry)
{
	return atomic_read(&PDE(d_inode(dentry))->in_use) < 0;
}

static const struct dentry_operations proc_misc_dentry_ops = {
	.d_revalidate	= proc_misc_d_revalidate,
	.d_delete	= proc_misc_d_delete,
};

/*
 * Don't create negative dentries here, return -ENOENT by hand
 * instead.
 */
struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
			      struct proc_dir_entry *de)
{
	struct inode *inode;

	read_lock(&proc_subdir_lock);
	de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
	if (de) {
		pde_get(de);
		read_unlock(&proc_subdir_lock);
		inode = proc_get_inode(dir->i_sb, de);
		if (!inode)
			return ERR_PTR(-ENOMEM);
		d_set_d_op(dentry, &proc_misc_dentry_ops);
		return d_splice_alias(inode, dentry);
	}
	read_unlock(&proc_subdir_lock);
	return ERR_PTR(-ENOENT);
}

struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
		unsigned int flags)
{
	return proc_lookup_de(dir, dentry, PDE(dir));
}

/*
 * This returns non-zero if at EOF, so that the /proc
 * root directory can use this and check if it should
 * continue with the <pid> entries..
 *
 * Note that the VFS-layer doesn't care about the return
 * value of the readdir() call, as long as it's non-negative
 * for success..
 */
int proc_readdir_de(struct file *file, struct dir_context *ctx,
		    struct proc_dir_entry *de)
{
	int i;

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

	read_lock(&proc_subdir_lock);
	de = pde_subdir_first(de);
	i = ctx->pos - 2;
	for (;;) {
		if (!de) {
			read_unlock(&proc_subdir_lock);
			return 0;
		}
		if (!i)
			break;
		de = pde_subdir_next(de);
		i--;
	}

	do {
		struct proc_dir_entry *next;
		pde_get(de);
		read_unlock(&proc_subdir_lock);
		if (!dir_emit(ctx, de->name, de->namelen,
			    de->low_ino, de->mode >> 12)) {
			pde_put(de);
			return 0;
		}
		read_lock(&proc_subdir_lock);
		ctx->pos++;
		next = pde_subdir_next(de);
		pde_put(de);
		de = next;
	} while (de);
	read_unlock(&proc_subdir_lock);
	return 1;
}

int proc_readdir(struct file *file, struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);

	return proc_readdir_de(file, ctx, PDE(inode));
}

/*
 * These are the generic /proc directory operations. They
 * use the in-memory "struct proc_dir_entry" tree to parse
 * the /proc directory.
 */
static const struct file_operations proc_dir_operations = {
	.llseek			= generic_file_llseek,
	.read			= generic_read_dir,
	.iterate_shared		= proc_readdir,
};

/*
 * proc directories can do almost nothing..
 */
static const struct inode_operations proc_dir_inode_operations = {
	.lookup		= proc_lookup,
	.getattr	= proc_getattr,
	.setattr	= proc_notify_change,
};

/* returns the registered entry, or frees dp and returns NULL on failure */
struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
		struct proc_dir_entry *dp)
{
	if (proc_alloc_inum(&dp->low_ino))
		goto out_free_entry;

	write_lock(&proc_subdir_lock);
	dp->parent = dir;
	if (pde_subdir_insert(dir, dp) == false) {
		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
		     dir->name, dp->name);
		write_unlock(&proc_subdir_lock);
		goto out_free_inum;
	}
	write_unlock(&proc_subdir_lock);

	return dp;
out_free_inum:
	proc_free_inum(dp->low_ino);
out_free_entry:
	pde_free(dp);
	return NULL;
}

static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
					  const char *name,
					  umode_t mode,
					  nlink_t nlink)
{
	struct proc_dir_entry *ent = NULL;
	const char *fn;
	struct qstr qstr;

	if (xlate_proc_name(name, parent, &fn) != 0)
		goto out;
	qstr.name = fn;
	qstr.len = strlen(fn);
	if (qstr.len == 0 || qstr.len >= 256) {
		WARN(1, "name len %u\n", qstr.len);
		return NULL;
	}
	if (qstr.len == 1 && fn[0] == '.') {
		WARN(1, "name '.'\n");
		return NULL;
	}
	if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') {
		WARN(1, "name '..'\n");
		return NULL;
	}
	if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
		return NULL;
	}
	if (is_empty_pde(*parent)) {
		WARN(1, "attempt to add to permanently empty directory");
		return NULL;
	}

	ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
	if (!ent)
		goto out;

	if (qstr.len + 1 <= sizeof(ent->inline_name)) {
		ent->name = ent->inline_name;
	} else {
		ent->name = kmalloc(qstr.len + 1, GFP_KERNEL);
		if (!ent->name) {
			pde_free(ent);
			return NULL;
		}
	}

	memcpy(ent->name, fn, qstr.len + 1);
	ent->namelen = qstr.len;
	ent->mode = mode;
	ent->nlink = nlink;
	ent->subdir = RB_ROOT;
	refcount_set(&ent->refcnt, 1);
	spin_lock_init(&ent->pde_unload_lock);
	INIT_LIST_HEAD(&ent->pde_openers);
	proc_set_user(ent, (*parent)->uid, (*parent)->gid);

out:
	return ent;
}

struct proc_dir_entry *proc_symlink(const char *name,
		struct proc_dir_entry *parent, const char *dest)
{
	struct proc_dir_entry *ent;

	ent = __proc_create(&parent, name,
			  (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);

	if (ent) {
		ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL);
		if (ent->data) {
			strcpy((char*)ent->data,dest);
			ent->proc_iops = &proc_link_inode_operations;
			ent = proc_register(parent, ent);
		} else {
			pde_free(ent);
			ent = NULL;
		}
	}
	return ent;
}
EXPORT_SYMBOL(proc_symlink);

struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
		struct proc_dir_entry *parent, void *data)
{
	struct proc_dir_entry *ent;

	if (mode == 0)
		mode = S_IRUGO | S_IXUGO;

	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
	if (ent) {
		ent->data = data;
		ent->proc_fops = &proc_dir_operations;
		ent->proc_iops = &proc_dir_inode_operations;
		parent->nlink++;
		ent = proc_register(parent, ent);
		if (!ent)
			parent->nlink--;
	}
	return ent;
}
EXPORT_SYMBOL_GPL(proc_mkdir_data);

struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
				       struct proc_dir_entry *parent)
{
	return proc_mkdir_data(name, mode, parent, NULL);
}
EXPORT_SYMBOL(proc_mkdir_mode);

struct proc_dir_entry *proc_mkdir(const char *name,
		struct proc_dir_entry *parent)
{
	return proc_mkdir_data(name, 0, parent, NULL);
}
EXPORT_SYMBOL(proc_mkdir);

struct proc_dir_entry *proc_create_mount_point(const char *name)
{
	umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO;
	struct proc_dir_entry *ent, *parent = NULL;

	ent = __proc_create(&parent, name, mode, 2);
	if (ent) {
		ent->data = NULL;
		ent->proc_fops = NULL;
		ent->proc_iops = NULL;
		parent->nlink++;
		ent = proc_register(parent, ent);
		if (!ent)
			parent->nlink--;
	}
	return ent;
}
EXPORT_SYMBOL(proc_create_mount_point);

struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
		struct proc_dir_entry **parent, void *data)
{
	struct proc_dir_entry *p;

	if ((mode & S_IFMT) == 0)
		mode |= S_IFREG;
	if ((mode & S_IALLUGO) == 0)
		mode |= S_IRUGO;
	if (WARN_ON_ONCE(!S_ISREG(mode)))
		return NULL;

	p = __proc_create(parent, name, mode, 1);
	if (p) {
		p->proc_iops = &proc_file_inode_operations;
		p->data = data;
	}
	return p;
}

struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
		struct proc_dir_entry *parent,
		const struct file_operations *proc_fops, void *data)
{
	struct proc_dir_entry *p;

	BUG_ON(proc_fops == NULL);

	p = proc_create_reg(name, mode, &parent, data);
	if (!p)
		return NULL;
	p->proc_fops = proc_fops;
	return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_data);
 
struct proc_dir_entry *proc_create(const char *name, umode_t mode,
				   struct proc_dir_entry *parent,
				   const struct file_operations *proc_fops)
{
	return proc_create_data(name, mode, parent, proc_fops, NULL);
}
EXPORT_SYMBOL(proc_create);

static int proc_seq_open(struct inode *inode, struct file *file)
{
	struct proc_dir_entry *de = PDE(inode);

	if (de->state_size)
		return seq_open_private(file, de->seq_ops, de->state_size);
	return seq_open(file, de->seq_ops);
}

static const struct file_operations proc_seq_fops = {
	.open		= proc_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
		struct proc_dir_entry *parent, const struct seq_operations *ops,
		unsigned int state_size, void *data)
{
	struct proc_dir_entry *p;

	p = proc_create_reg(name, mode, &parent, data);
	if (!p)
		return NULL;
	p->proc_fops = &proc_seq_fops;
	p->seq_ops = ops;
	p->state_size = state_size;
	return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_seq_private);

static int proc_single_open(struct inode *inode, struct file *file)
{
	struct proc_dir_entry *de = PDE(inode);

	return single_open(file, de->single_show, de->data);
}

static const struct file_operations proc_single_fops = {
	.open		= proc_single_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
		struct proc_dir_entry *parent,
		int (*show)(struct seq_file *, void *), void *data)
{
	struct proc_dir_entry *p;

	p = proc_create_reg(name, mode, &parent, data);
	if (!p)
		return NULL;
	p->proc_fops = &proc_single_fops;
	p->single_show = show;
	return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_single_data);

void proc_set_size(struct proc_dir_entry *de, loff_t size)
{
	de->size = size;
}
EXPORT_SYMBOL(proc_set_size);

void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
{
	de->uid = uid;
	de->gid = gid;
}
EXPORT_SYMBOL(proc_set_user);

void pde_put(struct proc_dir_entry *pde)
{
	if (refcount_dec_and_test(&pde->refcnt)) {
		proc_free_inum(pde->low_ino);
		pde_free(pde);
	}
}

/*
 * Remove a /proc entry and free it if it's not currently in use.
 */
void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
{
	struct proc_dir_entry *de = NULL;
	const char *fn = name;
	unsigned int len;

	write_lock(&proc_subdir_lock);
	if (__xlate_proc_name(name, &parent, &fn) != 0) {
		write_unlock(&proc_subdir_lock);
		return;
	}
	len = strlen(fn);

	de = pde_subdir_find(parent, fn, len);
	if (de)
		rb_erase(&de->subdir_node, &parent->subdir);
	write_unlock(&proc_subdir_lock);
	if (!de) {
		WARN(1, "name '%s'\n", name);
		return;
	}

	proc_entry_rundown(de);

	if (S_ISDIR(de->mode))
		parent->nlink--;
	de->nlink = 0;
	WARN(pde_subdir_first(de),
	     "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
	     __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
	pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);

int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
{
	struct proc_dir_entry *root = NULL, *de, *next;
	const char *fn = name;
	unsigned int len;

	write_lock(&proc_subdir_lock);
	if (__xlate_proc_name(name, &parent, &fn) != 0) {
		write_unlock(&proc_subdir_lock);
		return -ENOENT;
	}
	len = strlen(fn);

	root = pde_subdir_find(parent, fn, len);
	if (!root) {
		write_unlock(&proc_subdir_lock);
		return -ENOENT;
	}
	rb_erase(&root->subdir_node, &parent->subdir);

	de = root;
	while (1) {
		next = pde_subdir_first(de);
		if (next) {
			rb_erase(&next->subdir_node, &de->subdir);
			de = next;
			continue;
		}
		write_unlock(&proc_subdir_lock);

		proc_entry_rundown(de);
		next = de->parent;
		if (S_ISDIR(de->mode))
			next->nlink--;
		de->nlink = 0;
		if (de == root)
			break;
		pde_put(de);

		write_lock(&proc_subdir_lock);
		de = next;
	}
	pde_put(root);
	return 0;
}
EXPORT_SYMBOL(remove_proc_subtree);

void *proc_get_parent_data(const struct inode *inode)
{
	struct proc_dir_entry *de = PDE(inode);
	return de->parent->data;
}
EXPORT_SYMBOL_GPL(proc_get_parent_data);

void proc_remove(struct proc_dir_entry *de)
{
	if (de)
		remove_proc_subtree(de->name, de->parent);
}
EXPORT_SYMBOL(proc_remove);

void *PDE_DATA(const struct inode *inode)
{
	return __PDE_DATA(inode);
}
EXPORT_SYMBOL(PDE_DATA);