proc_sysctl.c 37.4 KB
Newer Older
1 2 3
/*
 * /proc/sys support
 */
A
Alexey Dobriyan 已提交
4
#include <linux/init.h>
5
#include <linux/sysctl.h>
L
Lucas De Marchi 已提交
6
#include <linux/poll.h>
7 8
#include <linux/proc_fs.h>
#include <linux/security.h>
9
#include <linux/namei.h>
10
#include <linux/module.h>
11 12
#include "internal.h"

A
Al Viro 已提交
13
static const struct dentry_operations proc_sys_dentry_operations;
14
static const struct file_operations proc_sys_file_operations;
15
static const struct inode_operations proc_sys_inode_operations;
A
Al Viro 已提交
16 17
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
18

L
Lucas De Marchi 已提交
19 20 21 22 23 24 25 26 27
void proc_sys_poll_notify(struct ctl_table_poll *poll)
{
	if (!poll)
		return;

	atomic_inc(&poll->event);
	wake_up_interruptible(&poll->wait);
}

28 29 30
static struct ctl_table root_table[] = {
	{
		.procname = "",
31
		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
32 33 34
	},
	{ }
};
35 36
static struct ctl_table_root sysctl_table_root = {
	.default_set.dir.header = {
37 38
		{{.count = 1,
		  .nreg = 1,
39
		  .ctl_table = root_table }},
40
		.ctl_table_arg = root_table,
41 42 43
		.root = &sysctl_table_root,
		.set = &sysctl_table_root.default_set,
	},
44 45 46 47
};

static DEFINE_SPINLOCK(sysctl_lock);

48
static void drop_sysctl_table(struct ctl_table_header *header);
49 50 51 52
static int sysctl_follow_link(struct ctl_table_header **phead,
	struct ctl_table **pentry, struct nsproxy *namespaces);
static int insert_links(struct ctl_table_header *head);
static void put_links(struct ctl_table_header *header);
53

54 55 56 57 58 59 60
static void sysctl_print_dir(struct ctl_dir *dir)
{
	if (dir->header.parent)
		sysctl_print_dir(dir->header.parent);
	printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
}

61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
static int namecmp(const char *name1, int len1, const char *name2, int len2)
{
	int minlen;
	int cmp;

	minlen = len1;
	if (minlen > len2)
		minlen = len2;

	cmp = memcmp(name1, name2, minlen);
	if (cmp == 0)
		cmp = len1 - len2;
	return cmp;
}

static struct ctl_table *find_entry(struct ctl_table_header **phead,
77
	struct ctl_dir *dir, const char *name, int namelen)
78 79 80
{
	struct ctl_table_header *head;
	struct ctl_table *entry;
81
	struct rb_node *node = dir->root.rb_node;
82

83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
	while (node)
	{
		struct ctl_node *ctl_node;
		const char *procname;
		int cmp;

		ctl_node = rb_entry(node, struct ctl_node, node);
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
		procname = entry->procname;

		cmp = namecmp(name, namelen, procname, strlen(procname));
		if (cmp < 0)
			node = node->rb_left;
		else if (cmp > 0)
			node = node->rb_right;
		else {
			*phead = head;
			return entry;
102 103 104 105 106
		}
	}
	return NULL;
}

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
static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
{
	struct rb_node *node = &head->node[entry - head->ctl_table].node;
	struct rb_node **p = &head->parent->root.rb_node;
	struct rb_node *parent = NULL;
	const char *name = entry->procname;
	int namelen = strlen(name);

	while (*p) {
		struct ctl_table_header *parent_head;
		struct ctl_table *parent_entry;
		struct ctl_node *parent_node;
		const char *parent_name;
		int cmp;

		parent = *p;
		parent_node = rb_entry(parent, struct ctl_node, node);
		parent_head = parent_node->header;
		parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
		parent_name = parent_entry->procname;

		cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
		if (cmp < 0)
			p = &(*p)->rb_left;
		else if (cmp > 0)
			p = &(*p)->rb_right;
		else {
			printk(KERN_ERR "sysctl duplicate entry: ");
			sysctl_print_dir(head->parent);
			printk(KERN_CONT "/%s\n", entry->procname);
			return -EEXIST;
		}
	}

	rb_link_node(node, parent, p);
	return 0;
}

static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
{
	struct rb_node *node = &head->node[entry - head->ctl_table].node;

	rb_erase(node, &head->parent->root);
}

152 153
static void init_header(struct ctl_table_header *head,
	struct ctl_table_root *root, struct ctl_table_set *set,
154
	struct ctl_node *node, struct ctl_table *table)
155
{
156
	head->ctl_table = table;
157 158 159 160 161 162 163 164
	head->ctl_table_arg = table;
	head->used = 0;
	head->count = 1;
	head->nreg = 1;
	head->unregistering = NULL;
	head->root = root;
	head->set = set;
	head->parent = NULL;
165 166 167 168 169 170 171 172
	head->node = node;
	if (node) {
		struct ctl_table *entry;
		for (entry = table; entry->procname; entry++, node++) {
			rb_init_node(&node->node);
			node->header = head;
		}
	}
173 174
}

175 176
static void erase_header(struct ctl_table_header *head)
{
177 178 179
	struct ctl_table *entry;
	for (entry = head->ctl_table; entry->procname; entry++)
		erase_entry(head, entry);
180 181
}

182
static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
183
{
184
	struct ctl_table *entry;
185 186 187
	int err;

	dir->header.nreg++;
188
	header->parent = dir;
189 190 191
	err = insert_links(header);
	if (err)
		goto fail_links;
192 193 194 195 196
	for (entry = header->ctl_table; entry->procname; entry++) {
		err = insert_entry(header, entry);
		if (err)
			goto fail;
	}
197
	return 0;
198 199 200
fail:
	erase_header(header);
	put_links(header);
201 202 203 204
fail_links:
	header->parent = NULL;
	drop_sysctl_table(&dir->header);
	return err;
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
/* called under sysctl_lock */
static int use_table(struct ctl_table_header *p)
{
	if (unlikely(p->unregistering))
		return 0;
	p->used++;
	return 1;
}

/* called under sysctl_lock */
static void unuse_table(struct ctl_table_header *p)
{
	if (!--p->used)
		if (unlikely(p->unregistering))
			complete(p->unregistering);
}

/* called under sysctl_lock, will reacquire if has to wait */
static void start_unregistering(struct ctl_table_header *p)
{
	/*
	 * if p->used is 0, nobody will ever touch that entry again;
	 * we'll eliminate all paths to it before dropping sysctl_lock
	 */
	if (unlikely(p->used)) {
		struct completion wait;
		init_completion(&wait);
		p->unregistering = &wait;
		spin_unlock(&sysctl_lock);
		wait_for_completion(&wait);
		spin_lock(&sysctl_lock);
	} else {
		/* anything non-NULL; we'll never dereference it */
		p->unregistering = ERR_PTR(-EINVAL);
	}
	/*
	 * do not remove from the list until nobody holds it; walking the
	 * list in do_sysctl() relies on that.
	 */
246
	erase_header(p);
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
}

static void sysctl_head_get(struct ctl_table_header *head)
{
	spin_lock(&sysctl_lock);
	head->count++;
	spin_unlock(&sysctl_lock);
}

void sysctl_head_put(struct ctl_table_header *head)
{
	spin_lock(&sysctl_lock);
	if (!--head->count)
		kfree_rcu(head, rcu);
	spin_unlock(&sysctl_lock);
}

static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
{
	if (!head)
		BUG();
	spin_lock(&sysctl_lock);
	if (!use_table(head))
		head = ERR_PTR(-ENOENT);
	spin_unlock(&sysctl_lock);
	return head;
}

static void sysctl_head_finish(struct ctl_table_header *head)
{
	if (!head)
		return;
	spin_lock(&sysctl_lock);
	unuse_table(head);
	spin_unlock(&sysctl_lock);
}

static struct ctl_table_set *
lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
{
	struct ctl_table_set *set = &root->default_set;
	if (root->lookup)
		set = root->lookup(root, namespaces);
	return set;
}

293
static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
294
				      struct ctl_dir *dir,
295 296 297 298 299 300
				      const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;

	spin_lock(&sysctl_lock);
301 302 303 304 305
	entry = find_entry(&head, dir, name, namelen);
	if (entry && use_table(head))
		*phead = head;
	else
		entry = NULL;
306 307 308 309
	spin_unlock(&sysctl_lock);
	return entry;
}

310
static struct ctl_node *first_usable_entry(struct rb_node *node)
311
{
312
	struct ctl_node *ctl_node;
313

314 315 316 317
	for (;node; node = rb_next(node)) {
		ctl_node = rb_entry(node, struct ctl_node, node);
		if (use_table(ctl_node->header))
			return ctl_node;
318 319 320 321
	}
	return NULL;
}

322
static void first_entry(struct ctl_dir *dir,
323 324
	struct ctl_table_header **phead, struct ctl_table **pentry)
{
325
	struct ctl_table_header *head = NULL;
326
	struct ctl_table *entry = NULL;
327
	struct ctl_node *ctl_node;
328 329

	spin_lock(&sysctl_lock);
330
	ctl_node = first_usable_entry(rb_first(&dir->root));
331
	spin_unlock(&sysctl_lock);
332 333 334 335
	if (ctl_node) {
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
	}
336 337 338 339
	*phead = head;
	*pentry = entry;
}

340
static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
341
{
342 343
	struct ctl_table_header *head = *phead;
	struct ctl_table *entry = *pentry;
344
	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
345

346 347 348 349 350 351 352 353 354
	spin_lock(&sysctl_lock);
	unuse_table(head);

	ctl_node = first_usable_entry(rb_next(&ctl_node->node));
	spin_unlock(&sysctl_lock);
	head = NULL;
	if (ctl_node) {
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
355 356 357
	}
	*phead = head;
	*pentry = entry;
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
}

void register_sysctl_root(struct ctl_table_root *root)
{
}

/*
 * sysctl_perm does NOT grant the superuser all rights automatically, because
 * some sysctl variables are readonly even to root.
 */

static int test_perm(int mode, int op)
{
	if (!current_euid())
		mode >>= 6;
	else if (in_egroup_p(0))
		mode >>= 3;
	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
		return 0;
	return -EACCES;
}

static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
{
	int mode;

	if (root->permissions)
		mode = root->permissions(root, current->nsproxy, table);
	else
		mode = table->mode;

	return test_perm(mode, op);
}

A
Al Viro 已提交
392 393
static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
394 395
{
	struct inode *inode;
A
Al Viro 已提交
396
	struct proc_inode *ei;
397

A
Al Viro 已提交
398
	inode = new_inode(sb);
399 400 401
	if (!inode)
		goto out;

402 403
	inode->i_ino = get_next_ino();

A
Al Viro 已提交
404
	sysctl_head_get(head);
405
	ei = PROC_I(inode);
A
Al Viro 已提交
406 407 408
	ei->sysctl = head;
	ei->sysctl_entry = table;

409
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
A
Al Viro 已提交
410
	inode->i_mode = table->mode;
411
	if (!S_ISDIR(table->mode)) {
A
Al Viro 已提交
412 413 414 415 416 417 418 419
		inode->i_mode |= S_IFREG;
		inode->i_op = &proc_sys_inode_operations;
		inode->i_fop = &proc_sys_file_operations;
	} else {
		inode->i_mode |= S_IFDIR;
		inode->i_op = &proc_sys_dir_operations;
		inode->i_fop = &proc_sys_dir_file_operations;
	}
420 421 422 423
out:
	return inode;
}

A
Adrian Bunk 已提交
424
static struct ctl_table_header *grab_header(struct inode *inode)
425
{
426 427
	struct ctl_table_header *head = PROC_I(inode)->sysctl;
	if (!head)
428
		head = &sysctl_table_root.default_set.dir.header;
429
	return sysctl_head_grab(head);
A
Al Viro 已提交
430
}
431

A
Al Viro 已提交
432 433 434 435 436 437 438 439 440
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
					struct nameidata *nd)
{
	struct ctl_table_header *head = grab_header(dir);
	struct ctl_table_header *h = NULL;
	struct qstr *name = &dentry->d_name;
	struct ctl_table *p;
	struct inode *inode;
	struct dentry *err = ERR_PTR(-ENOENT);
441
	struct ctl_dir *ctl_dir;
442
	int ret;
443

A
Al Viro 已提交
444 445
	if (IS_ERR(head))
		return ERR_CAST(head);
446

447
	ctl_dir = container_of(head, struct ctl_dir, header);
448

449
	p = lookup_entry(&h, ctl_dir, name->name, name->len);
A
Al Viro 已提交
450
	if (!p)
451 452
		goto out;

453 454 455 456 457
	ret = sysctl_follow_link(&h, &p, current->nsproxy);
	err = ERR_PTR(ret);
	if (ret)
		goto out;

458
	err = ERR_PTR(-ENOMEM);
A
Al Viro 已提交
459 460 461 462
	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
	if (h)
		sysctl_head_finish(h);

463 464 465 466
	if (!inode)
		goto out;

	err = NULL;
467
	d_set_d_op(dentry, &proc_sys_dentry_operations);
468 469 470 471 472 473 474
	d_add(dentry, inode);

out:
	sysctl_head_finish(head);
	return err;
}

475 476
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
		size_t count, loff_t *ppos, int write)
477
{
A
Al Viro 已提交
478 479 480
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
481 482
	ssize_t error;
	size_t res;
483

A
Al Viro 已提交
484 485
	if (IS_ERR(head))
		return PTR_ERR(head);
486 487 488 489 490 491

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
492
	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
493 494
		goto out;

A
Al Viro 已提交
495 496 497 498 499
	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

500 501
	/* careful: calling conventions are nasty here */
	res = count;
502
	error = table->proc_handler(table, write, buf, &res, ppos);
503 504 505 506 507 508 509 510
	if (!error)
		error = res;
out:
	sysctl_head_finish(head);

	return error;
}

511
static ssize_t proc_sys_read(struct file *filp, char __user *buf,
512 513
				size_t count, loff_t *ppos)
{
514 515
	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
}
516

517 518 519 520
static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
				size_t count, loff_t *ppos)
{
	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
521 522
}

L
Lucas De Marchi 已提交
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
static int proc_sys_open(struct inode *inode, struct file *filp)
{
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	if (table->poll)
		filp->private_data = proc_sys_poll_event(table->poll);

	return 0;
}

static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	unsigned long event = (unsigned long)filp->private_data;
	unsigned int ret = DEFAULT_POLLMASK;

	if (!table->proc_handler)
		goto out;

	if (!table->poll)
		goto out;

	poll_wait(filp, &table->poll->wait, wait);

	if (event != atomic_read(&table->poll->event)) {
		filp->private_data = proc_sys_poll_event(table->poll);
		ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
	}

out:
	return ret;
}
556 557

static int proc_sys_fill_cache(struct file *filp, void *dirent,
A
Al Viro 已提交
558 559 560
				filldir_t filldir,
				struct ctl_table_header *head,
				struct ctl_table *table)
561 562 563 564 565 566 567 568 569 570 571 572 573
{
	struct dentry *child, *dir = filp->f_path.dentry;
	struct inode *inode;
	struct qstr qname;
	ino_t ino = 0;
	unsigned type = DT_UNKNOWN;

	qname.name = table->procname;
	qname.len  = strlen(table->procname);
	qname.hash = full_name_hash(qname.name, qname.len);

	child = d_lookup(dir, &qname);
	if (!child) {
A
Al Viro 已提交
574 575 576 577 578 579 580
		child = d_alloc(dir, &qname);
		if (child) {
			inode = proc_sys_make_inode(dir->d_sb, head, table);
			if (!inode) {
				dput(child);
				return -ENOMEM;
			} else {
581
				d_set_d_op(child, &proc_sys_dentry_operations);
A
Al Viro 已提交
582
				d_add(child, inode);
583
			}
A
Al Viro 已提交
584 585
		} else {
			return -ENOMEM;
586 587 588
		}
	}
	inode = child->d_inode;
A
Al Viro 已提交
589 590
	ino  = inode->i_ino;
	type = inode->i_mode >> 12;
591
	dput(child);
A
Al Viro 已提交
592 593 594
	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
}

595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613
static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
				    filldir_t filldir,
				    struct ctl_table_header *head,
				    struct ctl_table *table)
{
	int err, ret = 0;
	head = sysctl_head_grab(head);

	/* It is not an error if we can not follow the link ignore it */
	err = sysctl_follow_link(&head, &table, current->nsproxy);
	if (err)
		goto out;

	ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
out:
	sysctl_head_finish(head);
	return ret;
}

A
Al Viro 已提交
614 615 616 617
static int scan(struct ctl_table_header *head, ctl_table *table,
		unsigned long *pos, struct file *file,
		void *dirent, filldir_t filldir)
{
618
	int res;
A
Al Viro 已提交
619

620 621
	if ((*pos)++ < file->f_pos)
		return 0;
A
Al Viro 已提交
622

623 624 625 626
	if (unlikely(S_ISLNK(table->mode)))
		res = proc_sys_link_fill_cache(file, dirent, filldir, head, table);
	else
		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
A
Al Viro 已提交
627

628 629
	if (res == 0)
		file->f_pos = *pos;
A
Al Viro 已提交
630

631
	return res;
632 633 634 635
}

static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
A
Al Viro 已提交
636
	struct dentry *dentry = filp->f_path.dentry;
637
	struct inode *inode = dentry->d_inode;
A
Al Viro 已提交
638 639
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table_header *h = NULL;
640
	struct ctl_table *entry;
641
	struct ctl_dir *ctl_dir;
642
	unsigned long pos;
A
Al Viro 已提交
643 644 645 646
	int ret = -EINVAL;

	if (IS_ERR(head))
		return PTR_ERR(head);
647

648
	ctl_dir = container_of(head, struct ctl_dir, header);
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665

	ret = 0;
	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
	if (filp->f_pos == 0) {
		if (filldir(dirent, ".", 1, filp->f_pos,
				inode->i_ino, DT_DIR) < 0)
			goto out;
		filp->f_pos++;
	}
	if (filp->f_pos == 1) {
		if (filldir(dirent, "..", 2, filp->f_pos,
				parent_ino(dentry), DT_DIR) < 0)
			goto out;
		filp->f_pos++;
	}
	pos = 2;

666
	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
667
		ret = scan(h, entry, &pos, filp, dirent, filldir);
A
Al Viro 已提交
668 669 670
		if (ret) {
			sysctl_head_finish(h);
			break;
671 672 673 674 675 676 677 678
		}
	}
	ret = 1;
out:
	sysctl_head_finish(head);
	return ret;
}

679
static int proc_sys_permission(struct inode *inode, int mask)
680 681 682 683 684
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
685 686
	struct ctl_table_header *head;
	struct ctl_table *table;
687 688
	int error;

689 690 691 692 693
	/* Executable files are not allowed under /proc/sys/ */
	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
		return -EACCES;

	head = grab_header(inode);
A
Al Viro 已提交
694 695
	if (IS_ERR(head))
		return PTR_ERR(head);
696

697
	table = PROC_I(inode)->sysctl_entry;
A
Al Viro 已提交
698 699 700
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
701
		error = sysctl_perm(head->root, table, mask & ~MAY_NOT_BLOCK);
702 703 704 705 706 707 708 709 710 711 712 713 714 715

	sysctl_head_finish(head);
	return error;
}

static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	int error;

	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
		return -EPERM;

	error = inode_change_ok(inode, attr);
C
Christoph Hellwig 已提交
716 717 718 719 720 721 722 723 724
	if (error)
		return error;

	if ((attr->ia_valid & ATTR_SIZE) &&
	    attr->ia_size != i_size_read(inode)) {
		error = vmtruncate(inode, attr->ia_size);
		if (error)
			return error;
	}
725

C
Christoph Hellwig 已提交
726 727 728
	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
729 730
}

A
Al Viro 已提交
731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747
static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	if (IS_ERR(head))
		return PTR_ERR(head);

	generic_fillattr(inode, stat);
	if (table)
		stat->mode = (stat->mode & S_IFMT) | table->mode;

	sysctl_head_finish(head);
	return 0;
}

748
static const struct file_operations proc_sys_file_operations = {
L
Lucas De Marchi 已提交
749 750
	.open		= proc_sys_open,
	.poll		= proc_sys_poll,
751 752
	.read		= proc_sys_read,
	.write		= proc_sys_write,
753
	.llseek		= default_llseek,
A
Al Viro 已提交
754 755 756
};

static const struct file_operations proc_sys_dir_file_operations = {
757
	.read		= generic_read_dir,
758
	.readdir	= proc_sys_readdir,
759
	.llseek		= generic_file_llseek,
760 761
};

762
static const struct inode_operations proc_sys_inode_operations = {
A
Al Viro 已提交
763 764 765 766 767 768
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static const struct inode_operations proc_sys_dir_operations = {
769 770 771
	.lookup		= proc_sys_lookup,
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
A
Al Viro 已提交
772
	.getattr	= proc_sys_getattr,
773 774 775 776
};

static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
{
777 778
	if (nd->flags & LOOKUP_RCU)
		return -ECHILD;
A
Al Viro 已提交
779 780 781
	return !PROC_I(dentry->d_inode)->sysctl->unregistering;
}

N
Nick Piggin 已提交
782
static int proc_sys_delete(const struct dentry *dentry)
A
Al Viro 已提交
783 784 785 786
{
	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
}

787 788 789 790 791 792 793 794 795 796 797 798 799 800 801
static int sysctl_is_seen(struct ctl_table_header *p)
{
	struct ctl_table_set *set = p->set;
	int res;
	spin_lock(&sysctl_lock);
	if (p->unregistering)
		res = 0;
	else if (!set->is_seen)
		res = 1;
	else
		res = set->is_seen(set);
	spin_unlock(&sysctl_lock);
	return res;
}

N
Nick Piggin 已提交
802 803 804 805
static int proc_sys_compare(const struct dentry *parent,
		const struct inode *pinode,
		const struct dentry *dentry, const struct inode *inode,
		unsigned int len, const char *str, const struct qstr *name)
A
Al Viro 已提交
806
{
A
Al Viro 已提交
807
	struct ctl_table_header *head;
N
Nick Piggin 已提交
808 809
	/* Although proc doesn't have negative dentries, rcu-walk means
	 * that inode here can be NULL */
A
Al Viro 已提交
810
	/* AV: can it, indeed? */
N
Nick Piggin 已提交
811
	if (!inode)
A
Al Viro 已提交
812
		return 1;
N
Nick Piggin 已提交
813
	if (name->len != len)
A
Al Viro 已提交
814
		return 1;
N
Nick Piggin 已提交
815
	if (memcmp(name->name, str, len))
A
Al Viro 已提交
816
		return 1;
A
Al Viro 已提交
817 818
	head = rcu_dereference(PROC_I(inode)->sysctl);
	return !head || !sysctl_is_seen(head);
819 820
}

A
Al Viro 已提交
821
static const struct dentry_operations proc_sys_dentry_operations = {
822
	.d_revalidate	= proc_sys_revalidate,
A
Al Viro 已提交
823 824
	.d_delete	= proc_sys_delete,
	.d_compare	= proc_sys_compare,
825 826
};

827 828
static struct ctl_dir *find_subdir(struct ctl_dir *dir,
				   const char *name, int namelen)
829
{
830 831
	struct ctl_table_header *head;
	struct ctl_table *entry;
832

833
	entry = find_entry(&head, dir, name, namelen);
834 835 836 837 838 839 840 841
	if (!entry)
		return ERR_PTR(-ENOENT);
	if (S_ISDIR(entry->mode))
		return container_of(head, struct ctl_dir, header);
	return ERR_PTR(-ENOTDIR);
}

static struct ctl_dir *new_dir(struct ctl_table_set *set,
842
			       const char *name, int namelen)
843 844 845
{
	struct ctl_table *table;
	struct ctl_dir *new;
846
	struct ctl_node *node;
847
	char *new_name;
848

849 850 851
	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
		      sizeof(struct ctl_table)*2 +  namelen + 1,
		      GFP_KERNEL);
852
	if (!new)
853 854
		return NULL;

855 856
	node = (struct ctl_node *)(new + 1);
	table = (struct ctl_table *)(node + 1);
857 858 859 860 861
	new_name = (char *)(table + 2);
	memcpy(new_name, name, namelen);
	new_name[namelen] = '\0';
	table[0].procname = new_name;
	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
862
	init_header(&new->header, set->dir.header.root, set, node, table);
863 864

	return new;
865 866
}

867 868
static struct ctl_dir *get_subdir(struct ctl_dir *dir,
				  const char *name, int namelen)
869
{
870
	struct ctl_table_set *set = dir->header.set;
871
	struct ctl_dir *subdir, *new = NULL;
872

873
	spin_lock(&sysctl_lock);
874
	subdir = find_subdir(dir, name, namelen);
875 876 877 878 879 880 881 882 883 884 885 886
	if (!IS_ERR(subdir))
		goto found;
	if (PTR_ERR(subdir) != -ENOENT)
		goto failed;

	spin_unlock(&sysctl_lock);
	new = new_dir(set, name, namelen);
	spin_lock(&sysctl_lock);
	subdir = ERR_PTR(-ENOMEM);
	if (!new)
		goto failed;

887
	subdir = find_subdir(dir, name, namelen);
888 889 890 891 892
	if (!IS_ERR(subdir))
		goto found;
	if (PTR_ERR(subdir) != -ENOENT)
		goto failed;

893 894
	if (insert_header(dir, &new->header))
		goto failed;
895 896 897 898 899
	subdir = new;
found:
	subdir->header.nreg++;
failed:
	if (unlikely(IS_ERR(subdir))) {
900 901 902
		printk(KERN_ERR "sysctl could not get directory: ");
		sysctl_print_dir(dir);
		printk(KERN_CONT "/%*.*s %ld\n",
903
			namelen, namelen, name, PTR_ERR(subdir));
904
	}
905 906 907 908 909
	drop_sysctl_table(&dir->header);
	if (new)
		drop_sysctl_table(&new->header);
	spin_unlock(&sysctl_lock);
	return subdir;
910 911
}

912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962
static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
{
	struct ctl_dir *parent;
	const char *procname;
	if (!dir->header.parent)
		return &set->dir;
	parent = xlate_dir(set, dir->header.parent);
	if (IS_ERR(parent))
		return parent;
	procname = dir->header.ctl_table[0].procname;
	return find_subdir(parent, procname, strlen(procname));
}

static int sysctl_follow_link(struct ctl_table_header **phead,
	struct ctl_table **pentry, struct nsproxy *namespaces)
{
	struct ctl_table_header *head;
	struct ctl_table_root *root;
	struct ctl_table_set *set;
	struct ctl_table *entry;
	struct ctl_dir *dir;
	int ret;

	/* Get out quickly if not a link */
	if (!S_ISLNK((*pentry)->mode))
		return 0;

	ret = 0;
	spin_lock(&sysctl_lock);
	root = (*pentry)->data;
	set = lookup_header_set(root, namespaces);
	dir = xlate_dir(set, (*phead)->parent);
	if (IS_ERR(dir))
		ret = PTR_ERR(dir);
	else {
		const char *procname = (*pentry)->procname;
		head = NULL;
		entry = find_entry(&head, dir, procname, strlen(procname));
		ret = -ENOENT;
		if (entry && use_table(head)) {
			unuse_table(*phead);
			*phead = head;
			*pentry = entry;
			ret = 0;
		}
	}

	spin_unlock(&sysctl_lock);
	return ret;
}

963
static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
964
{
965 966
	struct va_format vaf;
	va_list args;
967

968 969 970 971 972 973
	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;

	printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
		path, table->procname, &vaf);
974

975 976
	va_end(args);
	return -EINVAL;
977 978
}

979
static int sysctl_check_table(const char *path, struct ctl_table *table)
980
{
981
	int err = 0;
982 983
	for (; table->procname; table++) {
		if (table->child)
984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004
			err = sysctl_err(path, table, "Not a file");

		if ((table->proc_handler == proc_dostring) ||
		    (table->proc_handler == proc_dointvec) ||
		    (table->proc_handler == proc_dointvec_minmax) ||
		    (table->proc_handler == proc_dointvec_jiffies) ||
		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
		    (table->proc_handler == proc_dointvec_ms_jiffies) ||
		    (table->proc_handler == proc_doulongvec_minmax) ||
		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
			if (!table->data)
				err = sysctl_err(path, table, "No data");
			if (!table->maxlen)
				err = sysctl_err(path, table, "No maxlen");
		}
		if (!table->proc_handler)
			err = sysctl_err(path, table, "No proc_handler");

		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
			err = sysctl_err(path, table, "bogus .mode 0%o",
				table->mode);
1005
	}
1006
	return err;
1007 1008
}

1009 1010 1011 1012 1013
static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
	struct ctl_table_root *link_root)
{
	struct ctl_table *link_table, *entry, *link;
	struct ctl_table_header *links;
1014
	struct ctl_node *node;
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
	char *link_name;
	int nr_entries, name_bytes;

	name_bytes = 0;
	nr_entries = 0;
	for (entry = table; entry->procname; entry++) {
		nr_entries++;
		name_bytes += strlen(entry->procname) + 1;
	}

	links = kzalloc(sizeof(struct ctl_table_header) +
1026
			sizeof(struct ctl_node)*nr_entries +
1027 1028 1029 1030 1031 1032 1033
			sizeof(struct ctl_table)*(nr_entries + 1) +
			name_bytes,
			GFP_KERNEL);

	if (!links)
		return NULL;

1034 1035
	node = (struct ctl_node *)(links + 1);
	link_table = (struct ctl_table *)(node + nr_entries);
1036 1037 1038 1039 1040 1041 1042 1043 1044 1045
	link_name = (char *)&link_table[nr_entries + 1];

	for (link = link_table, entry = table; entry->procname; link++, entry++) {
		int len = strlen(entry->procname) + 1;
		memcpy(link_name, entry->procname, len);
		link->procname = link_name;
		link->mode = S_IFLNK|S_IRWXUGO;
		link->data = link_root;
		link_name += len;
	}
1046
	init_header(links, dir->header.root, dir->header.set, node, link_table);
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
	links->nreg = nr_entries;

	return links;
}

static bool get_links(struct ctl_dir *dir,
	struct ctl_table *table, struct ctl_table_root *link_root)
{
	struct ctl_table_header *head;
	struct ctl_table *entry, *link;

	/* Are there links available for every entry in table? */
	for (entry = table; entry->procname; entry++) {
		const char *procname = entry->procname;
		link = find_entry(&head, dir, procname, strlen(procname));
		if (!link)
			return false;
		if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
			continue;
		if (S_ISLNK(link->mode) && (link->data == link_root))
			continue;
		return false;
	}

	/* The checks passed.  Increase the registration count on the links */
	for (entry = table; entry->procname; entry++) {
		const char *procname = entry->procname;
		link = find_entry(&head, dir, procname, strlen(procname));
		head->nreg++;
	}
	return true;
}

static int insert_links(struct ctl_table_header *head)
{
	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
	struct ctl_dir *core_parent = NULL;
	struct ctl_table_header *links;
	int err;

	if (head->set == root_set)
		return 0;

	core_parent = xlate_dir(root_set, head->parent);
	if (IS_ERR(core_parent))
		return 0;

	if (get_links(core_parent, head->ctl_table, head->root))
		return 0;

	core_parent->header.nreg++;
	spin_unlock(&sysctl_lock);

	links = new_links(core_parent, head->ctl_table, head->root);

	spin_lock(&sysctl_lock);
	err = -ENOMEM;
	if (!links)
		goto out;

	err = 0;
	if (get_links(core_parent, head->ctl_table, head->root)) {
		kfree(links);
		goto out;
	}

	err = insert_header(core_parent, links);
	if (err)
		kfree(links);
out:
	drop_sysctl_table(&core_parent->header);
	return err;
}

1121
/**
1122
 * __register_sysctl_table - register a leaf sysctl table
1123
 * @set: Sysctl tree to register on
1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138
 * @path: The path to the directory the sysctl table is in.
 * @table: the top-level table structure
 *
 * Register a sysctl table hierarchy. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * The members of the &struct ctl_table structure are used as follows:
 *
 * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
 *            enter a sysctl file
 *
 * data - a pointer to data for use by proc_handler
 *
 * maxlen - the maximum size in bytes of the data
 *
1139
 * mode - the file permissions for the /proc/sys file
1140
 *
1141
 * child - must be %NULL.
1142 1143 1144 1145 1146 1147 1148 1149
 *
 * proc_handler - the text handler routine (described below)
 *
 * extra1, extra2 - extra pointers usable by the proc handler routines
 *
 * Leaf nodes in the sysctl tree will be represented by a single file
 * under /proc; non-leaf nodes will be represented by directories.
 *
1150 1151
 * There must be a proc_handler routine for any terminal nodes.
 * Several default handlers are available to cover common cases -
1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162
 *
 * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
 * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
 * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
 *
 * It is the handler's job to read the input buffer from user memory
 * and process it. The handler should return 0 on success.
 *
 * This routine returns %NULL on a failure to register, and a pointer
 * to the table header on success.
 */
1163
struct ctl_table_header *__register_sysctl_table(
1164
	struct ctl_table_set *set,
1165
	const char *path, struct ctl_table *table)
1166
{
1167
	struct ctl_table_root *root = set->dir.header.root;
1168
	struct ctl_table_header *links = NULL;
1169
	struct ctl_table_header *header;
1170
	const char *name, *nextname;
1171
	struct ctl_dir *dir;
1172 1173 1174 1175 1176 1177
	struct ctl_table *entry;
	struct ctl_node *node;
	int nr_entries = 0;

	for (entry = table; entry->procname; entry++)
		nr_entries++;
1178

1179 1180
	header = kzalloc(sizeof(struct ctl_table_header) +
			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
1181 1182 1183
	if (!header)
		return NULL;

1184 1185
	node = (struct ctl_node *)(header + 1);
	init_header(header, root, set, node, table);
1186 1187 1188 1189
	if (sysctl_check_table(path, table))
		goto fail;

	spin_lock(&sysctl_lock);
1190
	dir = &set->dir;
1191 1192
	dir->header.nreg++;
	spin_unlock(&sysctl_lock);
1193

1194
	/* Find the directory for the ctl_table */
1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205
	for (name = path; name; name = nextname) {
		int namelen;
		nextname = strchr(name, '/');
		if (nextname) {
			namelen = nextname - name;
			nextname++;
		} else {
			namelen = strlen(name);
		}
		if (namelen == 0)
			continue;
1206

1207
		dir = get_subdir(dir, name, namelen);
1208 1209
		if (IS_ERR(dir))
			goto fail;
1210
	}
1211

1212
	spin_lock(&sysctl_lock);
1213
	if (insert_header(dir, header))
1214
		goto fail_put_dir_locked;
1215

1216
	drop_sysctl_table(&dir->header);
1217 1218 1219
	spin_unlock(&sysctl_lock);

	return header;
1220

1221 1222
fail_put_dir_locked:
	drop_sysctl_table(&dir->header);
1223 1224
	spin_unlock(&sysctl_lock);
fail:
1225
	kfree(links);
1226 1227 1228
	kfree(header);
	dump_stack();
	return NULL;
1229 1230
}

1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243
static char *append_path(const char *path, char *pos, const char *name)
{
	int namelen;
	namelen = strlen(name);
	if (((pos - path) + namelen + 2) >= PATH_MAX)
		return NULL;
	memcpy(pos, name, namelen);
	pos[namelen] = '/';
	pos[namelen + 1] = '\0';
	pos += namelen + 1;
	return pos;
}

1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263
static int count_subheaders(struct ctl_table *table)
{
	int has_files = 0;
	int nr_subheaders = 0;
	struct ctl_table *entry;

	/* special case: no directory and empty directory */
	if (!table || !table->procname)
		return 1;

	for (entry = table; entry->procname; entry++) {
		if (entry->child)
			nr_subheaders += count_subheaders(entry->child);
		else
			has_files = 1;
	}
	return nr_subheaders + has_files;
}

static int register_leaf_sysctl_tables(const char *path, char *pos,
1264
	struct ctl_table_header ***subheader, struct ctl_table_set *set,
1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300
	struct ctl_table *table)
{
	struct ctl_table *ctl_table_arg = NULL;
	struct ctl_table *entry, *files;
	int nr_files = 0;
	int nr_dirs = 0;
	int err = -ENOMEM;

	for (entry = table; entry->procname; entry++) {
		if (entry->child)
			nr_dirs++;
		else
			nr_files++;
	}

	files = table;
	/* If there are mixed files and directories we need a new table */
	if (nr_dirs && nr_files) {
		struct ctl_table *new;
		files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1),
				GFP_KERNEL);
		if (!files)
			goto out;

		ctl_table_arg = files;
		for (new = files, entry = table; entry->procname; entry++) {
			if (entry->child)
				continue;
			*new = *entry;
			new++;
		}
	}

	/* Register everything except a directory full of subdirectories */
	if (nr_files || !nr_dirs) {
		struct ctl_table_header *header;
1301
		header = __register_sysctl_table(set, path, files);
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325
		if (!header) {
			kfree(ctl_table_arg);
			goto out;
		}

		/* Remember if we need to free the file table */
		header->ctl_table_arg = ctl_table_arg;
		**subheader = header;
		(*subheader)++;
	}

	/* Recurse into the subdirectories. */
	for (entry = table; entry->procname; entry++) {
		char *child_pos;

		if (!entry->child)
			continue;

		err = -ENAMETOOLONG;
		child_pos = append_path(path, pos, entry->procname);
		if (!child_pos)
			goto out;

		err = register_leaf_sysctl_tables(path, child_pos, subheader,
1326
						  set, entry->child);
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
		pos[0] = '\0';
		if (err)
			goto out;
	}
	err = 0;
out:
	/* On failure our caller will unregister all registered subheaders */
	return err;
}

1337 1338
/**
 * __register_sysctl_paths - register a sysctl table hierarchy
1339
 * @set: Sysctl tree to register on
1340 1341 1342 1343 1344 1345 1346 1347 1348
 * @path: The path to the directory the sysctl table is in.
 * @table: the top-level table structure
 *
 * Register a sysctl table hierarchy. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * See __register_sysctl_table for more details.
 */
struct ctl_table_header *__register_sysctl_paths(
1349
	struct ctl_table_set *set,
1350 1351
	const struct ctl_path *path, struct ctl_table *table)
{
1352
	struct ctl_table *ctl_table_arg = table;
1353 1354
	int nr_subheaders = count_subheaders(table);
	struct ctl_table_header *header = NULL, **subheaders, **subheader;
1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
	const struct ctl_path *component;
	char *new_path, *pos;

	pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL);
	if (!new_path)
		return NULL;

	pos[0] = '\0';
	for (component = path; component->procname; component++) {
		pos = append_path(new_path, pos, component->procname);
		if (!pos)
			goto out;
	}
1368 1369 1370 1371 1372 1373
	while (table->procname && table->child && !table[1].procname) {
		pos = append_path(new_path, pos, table->procname);
		if (!pos)
			goto out;
		table = table->child;
	}
1374
	if (nr_subheaders == 1) {
1375
		header = __register_sysctl_table(set, new_path, table);
1376 1377 1378 1379 1380 1381 1382 1383 1384 1385
		if (header)
			header->ctl_table_arg = ctl_table_arg;
	} else {
		header = kzalloc(sizeof(*header) +
				 sizeof(*subheaders)*nr_subheaders, GFP_KERNEL);
		if (!header)
			goto out;

		subheaders = (struct ctl_table_header **) (header + 1);
		subheader = subheaders;
1386
		header->ctl_table_arg = ctl_table_arg;
1387 1388

		if (register_leaf_sysctl_tables(new_path, pos, &subheader,
1389
						set, table))
1390 1391 1392
			goto err_register_leaves;
	}

1393 1394 1395
out:
	kfree(new_path);
	return header;
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406

err_register_leaves:
	while (subheader > subheaders) {
		struct ctl_table_header *subh = *(--subheader);
		struct ctl_table *table = subh->ctl_table_arg;
		unregister_sysctl_table(subh);
		kfree(table);
	}
	kfree(header);
	header = NULL;
	goto out;
1407 1408
}

1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
/**
 * register_sysctl_table_path - register a sysctl table hierarchy
 * @path: The path to the directory the sysctl table is in.
 * @table: the top-level table structure
 *
 * Register a sysctl table hierarchy. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * See __register_sysctl_paths for more details.
 */
struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
						struct ctl_table *table)
{
1422
	return __register_sysctl_paths(&sysctl_table_root.default_set,
1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443
					path, table);
}
EXPORT_SYMBOL(register_sysctl_paths);

/**
 * register_sysctl_table - register a sysctl table hierarchy
 * @table: the top-level table structure
 *
 * Register a sysctl table hierarchy. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * See register_sysctl_paths for more details.
 */
struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
{
	static const struct ctl_path null_path[] = { {} };

	return register_sysctl_paths(null_path, table);
}
EXPORT_SYMBOL(register_sysctl_table);

1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
static void put_links(struct ctl_table_header *header)
{
	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
	struct ctl_table_root *root = header->root;
	struct ctl_dir *parent = header->parent;
	struct ctl_dir *core_parent;
	struct ctl_table *entry;

	if (header->set == root_set)
		return;

	core_parent = xlate_dir(root_set, parent);
	if (IS_ERR(core_parent))
		return;

	for (entry = header->ctl_table; entry->procname; entry++) {
		struct ctl_table_header *link_head;
		struct ctl_table *link;
		const char *name = entry->procname;

		link = find_entry(&link_head, core_parent, name, strlen(name));
		if (link &&
		    ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
		     (S_ISLNK(link->mode) && (link->data == root)))) {
			drop_sysctl_table(link_head);
		}
		else {
			printk(KERN_ERR "sysctl link missing during unregister: ");
			sysctl_print_dir(parent);
			printk(KERN_CONT "/%s\n", name);
		}
	}
}

1478 1479
static void drop_sysctl_table(struct ctl_table_header *header)
{
1480 1481
	struct ctl_dir *parent = header->parent;

1482 1483 1484
	if (--header->nreg)
		return;

1485
	put_links(header);
1486 1487 1488
	start_unregistering(header);
	if (!--header->count)
		kfree_rcu(header, rcu);
1489 1490 1491

	if (parent)
		drop_sysctl_table(&parent->header);
1492 1493
}

1494 1495 1496 1497 1498 1499 1500 1501 1502
/**
 * unregister_sysctl_table - unregister a sysctl table hierarchy
 * @header: the header returned from register_sysctl_table
 *
 * Unregisters the sysctl table and all children. proc entries may not
 * actually be removed until they are no longer used by anyone.
 */
void unregister_sysctl_table(struct ctl_table_header * header)
{
1503
	int nr_subheaders;
1504 1505 1506 1507 1508
	might_sleep();

	if (header == NULL)
		return;

1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524
	nr_subheaders = count_subheaders(header->ctl_table_arg);
	if (unlikely(nr_subheaders > 1)) {
		struct ctl_table_header **subheaders;
		int i;

		subheaders = (struct ctl_table_header **)(header + 1);
		for (i = nr_subheaders -1; i >= 0; i--) {
			struct ctl_table_header *subh = subheaders[i];
			struct ctl_table *table = subh->ctl_table_arg;
			unregister_sysctl_table(subh);
			kfree(table);
		}
		kfree(header);
		return;
	}

1525
	spin_lock(&sysctl_lock);
1526
	drop_sysctl_table(header);
1527 1528 1529 1530
	spin_unlock(&sysctl_lock);
}
EXPORT_SYMBOL(unregister_sysctl_table);

1531
void setup_sysctl_set(struct ctl_table_set *set,
1532
	struct ctl_table_root *root,
1533 1534
	int (*is_seen)(struct ctl_table_set *))
{
1535 1536
	memset(set, sizeof(*set), 0);
	set->is_seen = is_seen;
1537
	init_header(&set->dir.header, root, set, NULL, root_table);
1538 1539
}

1540 1541
void retire_sysctl_set(struct ctl_table_set *set)
{
1542
	WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
1543
}
1544

A
Alexey Dobriyan 已提交
1545
int __init proc_sys_init(void)
1546
{
A
Alexey Dobriyan 已提交
1547 1548
	struct proc_dir_entry *proc_sys_root;

1549
	proc_sys_root = proc_mkdir("sys", NULL);
A
Al Viro 已提交
1550 1551
	proc_sys_root->proc_iops = &proc_sys_dir_operations;
	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
1552
	proc_sys_root->nlink = 0;
1553 1554

	return sysctl_init();
1555
}