summaryrefslogtreecommitdiff
path: root/fs/proc/generic.c
blob: 39f3d65190353cf08604a8765ed47946f1cf6b8e (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
/*
 * 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/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/idr.h>
#include <linux/namei.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <asm/uaccess.h>

#include "internal.h"

static ssize_t proc_file_read(struct file *file, char __user *buf,
			      size_t nbytes, loff_t *ppos);
static ssize_t proc_file_write(struct file *file, const char __user *buffer,
			       size_t count, loff_t *ppos);
static loff_t proc_file_lseek(struct file *, loff_t, int);

DEFINE_SPINLOCK(proc_subdir_lock);

static int proc_match(int len, const char *name, struct proc_dir_entry *de)
{
	if (de->namelen != len)
		return 0;
	return !memcmp(name, de->name, len);
}

static const struct file_operations proc_file_operations = {
	.llseek		= proc_file_lseek,
	.read		= proc_file_read,
	.write		= proc_file_write,
};

/* buffer size is one page but our output routines use some slack for overruns */
#define PROC_BLOCK_SIZE	(PAGE_SIZE - 1024)

static ssize_t
proc_file_read(struct file *file, char __user *buf, size_t nbytes,
	       loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	char 	*page;
	ssize_t	retval=0;
	int	eof=0;
	ssize_t	n, count;
	char	*start;
	struct proc_dir_entry * dp;
	unsigned long long pos;

	/*
	 * Gaah, please just use "seq_file" instead. The legacy /proc
	 * interfaces cut loff_t down to off_t for reads, and ignore
	 * the offset entirely for writes..
	 */
	pos = *ppos;
	if (pos > MAX_NON_LFS)
		return 0;
	if (nbytes > MAX_NON_LFS - pos)
		nbytes = MAX_NON_LFS - pos;

	dp = PDE(inode);
	if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
		return -ENOMEM;

	while ((nbytes > 0) && !eof) {
		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);

		start = NULL;
		if (dp->get_info) {
			/* Handle old net routines */
			n = dp->get_info(page, &start, *ppos, count);
			if (n < count)
				eof = 1;
		} else if (dp->read_proc) {
			/*
			 * How to be a proc read function
			 * ------------------------------
			 * Prototype:
			 *    int f(char *buffer, char **start, off_t offset,
			 *          int count, int *peof, void *dat)
			 *
			 * Assume that the buffer is "count" bytes in size.
			 *
			 * If you know you have supplied all the data you
			 * have, set *peof.
			 *
			 * You have three ways to return data:
			 * 0) Leave *start = NULL.  (This is the default.)
			 *    Put the data of the requested offset at that
			 *    offset within the buffer.  Return the number (n)
			 *    of bytes there are from the beginning of the
			 *    buffer up to the last byte of data.  If the
			 *    number of supplied bytes (= n - offset) is 
			 *    greater than zero and you didn't signal eof
			 *    and the reader is prepared to take more data
			 *    you will be called again with the requested
			 *    offset advanced by the number of bytes 
			 *    absorbed.  This interface is useful for files
			 *    no larger than the buffer.
			 * 1) Set *start = an unsigned long value less than
			 *    the buffer address but greater than zero.
			 *    Put the data of the requested offset at the
			 *    beginning of the buffer.  Return the number of
			 *    bytes of data placed there.  If this number is
			 *    greater than zero and you didn't signal eof
			 *    and the reader is prepared to take more data
			 *    you will be called again with the requested
			 *    offset advanced by *start.  This interface is
			 *    useful when you have a large file consisting
			 *    of a series of blocks which you want to count
			 *    and return as wholes.
			 *    (Hack by Paul.Russell@rustcorp.com.au)
			 * 2) Set *start = an address within the buffer.
			 *    Put the data of the requested offset at *start.
			 *    Return the number of bytes of data placed there.
			 *    If this number is greater than zero and you
			 *    didn't signal eof and the reader is prepared to
			 *    take more data you will be called again with the
			 *    requested offset advanced by the number of bytes
			 *    absorbed.
			 */
			n = dp->read_proc(page, &start, *ppos,
					  count, &eof, dp->data);
		} else
			break;

		if (n == 0)   /* end of file */
			break;
		if (n < 0) {  /* error */
			if (retval == 0)
				retval = n;
			break;
		}

		if (start == NULL) {
			if (n > PAGE_SIZE) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE;
			}
			n -= *ppos;
			if (n <= 0)
				break;
			if (n > count)
				n = count;
			start = page + *ppos;
		} else if (start < page) {
			if (n > PAGE_SIZE) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE;
			}
			if (n > count) {
				/*
				 * Don't reduce n because doing so might
				 * cut off part of a data block.
				 */
				printk(KERN_WARNING
				       "proc_file_read: Read count exceeded\n");
			}
		} else /* start >= page */ {
			unsigned long startoff = (unsigned long)(start - page);
			if (n > (PAGE_SIZE - startoff)) {
				printk(KERN_ERR
				       "proc_file_read: Apparent buffer overflow!\n");
				n = PAGE_SIZE - startoff;
			}
			if (n > count)
				n = count;
		}
		
 		n -= copy_to_user(buf, start < page ? page : start, n);
		if (n == 0) {
			if (retval == 0)
				retval = -EFAULT;
			break;
		}

		*ppos += start < page ? (unsigned long)start : n;
		nbytes -= n;
		buf += n;
		retval += n;
	}
	free_page((unsigned long) page);
	return retval;
}

static ssize_t
proc_file_write(struct file *file, const char __user *buffer,
		size_t count, loff_t *ppos)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct proc_dir_entry * dp;
	
	dp = PDE(inode);

	if (!dp->write_proc)
		return -EIO;

	/* FIXME: does this routine need ppos?  probably... */
	return dp->write_proc(file, buffer, count, dp->data);
}


static loff_t
proc_file_lseek(struct file *file, loff_t offset, int orig)
{
	loff_t retval = -EINVAL;
	switch (orig) {
	case 1:
		offset += file->f_pos;
	/* fallthrough */
	case 0:
		if (offset < 0 || offset > MAX_NON_LFS)
			break;
		file->f_pos = retval = offset;
	}
	return retval;
}

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

	error = inode_change_ok(inode, iattr);
	if (error)
		goto out;

	error = inode_setattr(inode, iattr);
	if (error)
		goto out;
	
	de->uid = inode->i_uid;
	de->gid = inode->i_gid;
	de->mode = inode->i_mode;
out:
	return error;
}

static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
			struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct proc_dir_entry *de = PROC_I(inode)->pde;
	if (de && de->nlink)
		inode->i_nlink = 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;
	int			len;
	int 			rtn = 0;

	spin_lock(&proc_subdir_lock);
	de = &proc_root;
	while (1) {
		next = strchr(cp, '/');
		if (!next)
			break;

		len = next - cp;
		for (de = de->subdir; de ; de = de->next) {
			if (proc_match(len, cp, de))
				break;
		}
		if (!de) {
			rtn = -ENOENT;
			goto out;
		}
		cp += len + 1;
	}
	*residual = cp;
	*ret = de;
out:
	spin_unlock(&proc_subdir_lock);
	return rtn;
}

static DEFINE_IDR(proc_inum_idr);
static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */

#define PROC_DYNAMIC_FIRST 0xF0000000UL

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

retry:
	if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
		return 0;

	spin_lock(&proc_inum_lock);
	error = idr_get_new(&proc_inum_idr, NULL, &i);
	spin_unlock(&proc_inum_lock);
	if (error == -EAGAIN)
		goto retry;
	else if (error)
		return 0;

	inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;

	/* inum will never be more than 0xf0ffffff, so no check
	 * for overflow.
	 */

	return inum;
}

static void release_inode_number(unsigned int inum)
{
	int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;

	spin_lock(&proc_inum_lock);
	idr_remove(&proc_inum_idr, id);
	spin_unlock(&proc_inum_lock);
}

static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	nd_set_link(nd, PDE(dentry->d_inode)->data);
	return NULL;
}

static const struct inode_operations proc_link_inode_operations = {
	.readlink	= generic_readlink,
	.follow_link	= proc_follow_link,
};

/*
 * As some entries in /proc are volatile, we want to 
 * get rid of unused dentries.  This could be made 
 * smarter: we could keep a "volatile" flag in the 
 * inode to indicate which ones to keep.
 */
static int proc_delete_dentry(struct dentry * dentry)
{
	return 1;
}

static struct dentry_operations proc_dentry_operations =
{
	.d_delete	= proc_delete_dentry,
};

/*
 * Don't create negative dentries here, return -ENOENT by hand
 * instead.
 */
struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = NULL;
	struct proc_dir_entry * de;
	int error = -ENOENT;

	lock_kernel();
	spin_lock(&proc_subdir_lock);
	de = PDE(dir);
	if (de) {
		for (de = de->subdir; de ; de = de->next) {
			if (de->namelen != dentry->d_name.len)
				continue;
			if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
				unsigned int ino = de->low_ino;

				de_get(de);
				spin_unlock(&proc_subdir_lock);
				error = -EINVAL;
				inode = proc_get_inode(dir->i_sb, ino, de);
				spin_lock(&proc_subdir_lock);
				break;
			}
		}
	}
	spin_unlock(&proc_subdir_lock);
	unlock_kernel();

	if (inode) {
		dentry->d_op = &proc_dentry_operations;
		d_add(dentry, inode);
		return NULL;
	}
	de_put(de);
	return ERR_PTR(error);
}

/*
 * 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(struct file * filp,
	void * dirent, filldir_t filldir)
{
	struct proc_dir_entry * de;
	unsigned int ino;
	int i;
	struct inode *inode = filp->f_path.dentry->d_inode;
	int ret = 0;

	lock_kernel();

	ino = inode->i_ino;
	de = PDE(inode);
	if (!de) {
		ret = -EINVAL;
		goto out;
	}
	i = filp->f_pos;
	switch (i) {
		case 0:
			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
				goto out;
			i++;
			filp->f_pos++;
			/* fall through */
		case 1:
			if (filldir(dirent, "..", 2, i,
				    parent_ino(filp->f_path.dentry),
				    DT_DIR) < 0)
				goto out;
			i++;
			filp->f_pos++;
			/* fall through */
		default:
			spin_lock(&proc_subdir_lock);
			de = de->subdir;
			i -= 2;
			for (;;) {
				if (!de) {
					ret = 1;
					spin_unlock(&proc_subdir_lock);
					goto out;
				}
				if (!i)
					break;
				de = de->next;
				i--;
			}

			do {
				struct proc_dir_entry *next;

				/* filldir passes info to user space */
				de_get(de);
				spin_unlock(&proc_subdir_lock);
				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
					    de->low_ino, de->mode >> 12) < 0) {
					de_put(de);
					goto out;
				}
				spin_lock(&proc_subdir_lock);
				filp->f_pos++;
				next = de->next;
				de_put(de);
				de = next;
			} while (de);
			spin_unlock(&proc_subdir_lock);
	}
	ret = 1;
out:	unlock_kernel();
	return ret;	
}

/*
 * 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 = {
	.read			= generic_read_dir,
	.readdir		= 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,
};

static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
{
	unsigned int i;
	
	i = get_inode_number();
	if (i == 0)
		return -EAGAIN;
	dp->low_ino = i;

	if (S_ISDIR(dp->mode)) {
		if (dp->proc_iops == NULL) {
			dp->proc_fops = &proc_dir_operations;
			dp->proc_iops = &proc_dir_inode_operations;
		}
		dir->nlink++;
	} else if (S_ISLNK(dp->mode)) {
		if (dp->proc_iops == NULL)
			dp->proc_iops = &proc_link_inode_operations;
	} else if (S_ISREG(dp->mode)) {
		if (dp->proc_fops == NULL)
			dp->proc_fops = &proc_file_operations;
		if (dp->proc_iops == NULL)
			dp->proc_iops = &proc_file_inode_operations;
	}

	spin_lock(&proc_subdir_lock);
	dp->next = dir->subdir;
	dp->parent = dir;
	dir->subdir = dp;
	spin_unlock(&proc_subdir_lock);

	return 0;
}

static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent,
					  const char *name,
					  mode_t mode,
					  nlink_t nlink)
{
	struct proc_dir_entry *ent = NULL;
	const char *fn = name;
	int len;

	/* make sure name is valid */
	if (!name || !strlen(name)) goto out;

	if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0)
		goto out;

	/* At this point there must not be any '/' characters beyond *fn */
	if (strchr(fn, '/'))
		goto out;

	len = strlen(fn);

	ent = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
	if (!ent) goto out;

	memset(ent, 0, sizeof(struct proc_dir_entry));
	memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1);
	ent->name = ((char *) ent) + sizeof(*ent);
	ent->namelen = len;
	ent->mode = mode;
	ent->nlink = nlink;
	ent->pde_users = 0;
	spin_lock_init(&ent->pde_unload_lock);
	ent->pde_unload_completion = NULL;
 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);
			if (proc_register(parent, ent) < 0) {
				kfree(ent->data);
				kfree(ent);
				ent = NULL;
			}
		} else {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}

struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
		struct proc_dir_entry *parent)
{
	struct proc_dir_entry *ent;

	ent = proc_create(&parent, name, S_IFDIR | mode, 2);
	if (ent) {
		if (proc_register(parent, ent) < 0) {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}

struct proc_dir_entry *proc_mkdir(const char *name,
		struct proc_dir_entry *parent)
{
	return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
}

struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
					 struct proc_dir_entry *parent)
{
	struct proc_dir_entry *ent;
	nlink_t nlink;

	if (S_ISDIR(mode)) {
		if ((mode & S_IALLUGO) == 0)
			mode |= S_IRUGO | S_IXUGO;
		nlink = 2;
	} else {
		if ((mode & S_IFMT) == 0)
			mode |= S_IFREG;
		if ((mode & S_IALLUGO) == 0)
			mode |= S_IRUGO;
		nlink = 1;
	}

	ent = proc_create(&parent,name,mode,nlink);
	if (ent) {
		if (proc_register(parent, ent) < 0) {
			kfree(ent);
			ent = NULL;
		}
	}
	return ent;
}

void free_proc_entry(struct proc_dir_entry *de)
{
	unsigned int ino = de->low_ino;

	if (ino < PROC_DYNAMIC_FIRST)
		return;

	release_inode_number(ino);

	if (S_ISLNK(de->mode) && de->data)
		kfree(de->data);
	kfree(de);
}

/*
 * Remove a /proc entry and free it if it's not currently in use.
 * If it is in use, we set the 'deleted' flag.
 */
void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
{
	struct proc_dir_entry **p;
	struct proc_dir_entry *de;
	const char *fn = name;
	int len;

	if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
		goto out;
	len = strlen(fn);

	spin_lock(&proc_subdir_lock);
	for (p = &parent->subdir; *p; p=&(*p)->next ) {
		if (!proc_match(len, fn, *p))
			continue;
		de = *p;
		*p = de->next;
		de->next = NULL;

		spin_lock(&de->pde_unload_lock);
		/*
		 * Stop accepting new callers into module. If you're
		 * dynamically allocating ->proc_fops, save a pointer somewhere.
		 */
		de->proc_fops = NULL;
		/* Wait until all existing callers into module are done. */
		if (de->pde_users > 0) {
			DECLARE_COMPLETION_ONSTACK(c);

			if (!de->pde_unload_completion)
				de->pde_unload_completion = &c;

			spin_unlock(&de->pde_unload_lock);
			spin_unlock(&proc_subdir_lock);

			wait_for_completion(de->pde_unload_completion);

			spin_lock(&proc_subdir_lock);
			goto continue_removing;
		}
		spin_unlock(&de->pde_unload_lock);

continue_removing:
		if (S_ISDIR(de->mode))
			parent->nlink--;
		de->nlink = 0;
		WARN_ON(de->subdir);
		if (!atomic_read(&de->count))
			free_proc_entry(de);
		else {
			de->deleted = 1;
			printk("remove_proc_entry: %s/%s busy, count=%d\n",
				parent->name, de->name, atomic_read(&de->count));
		}
		break;
	}
	spin_unlock(&proc_subdir_lock);
out:
	return;
}