proc_sysctl.c 39.2 KB
Newer Older
1 2 3
/*
 * /proc/sys support
 */
Alexey Dobriyan's avatar
Alexey Dobriyan committed
4
#include <linux/init.h>
5
#include <linux/sysctl.h>
6
#include <linux/poll.h>
7
#include <linux/proc_fs.h>
8
#include <linux/printk.h>
9
#include <linux/security.h>
Al Viro's avatar
Al Viro committed
10
#include <linux/sched.h>
11
#include <linux/namei.h>
Al Viro's avatar
Al Viro committed
12
#include <linux/mm.h>
13
#include <linux/module.h>
14 15
#include "internal.h"

16
static const struct dentry_operations proc_sys_dentry_operations;
17
static const struct file_operations proc_sys_file_operations;
18
static const struct inode_operations proc_sys_inode_operations;
Al Viro's avatar
Al Viro committed
19 20
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
21

22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
/* Support for permanently empty directories */

struct ctl_table sysctl_mount_point[] = {
	{ }
};

static bool is_empty_dir(struct ctl_table_header *head)
{
	return head->ctl_table[0].child == sysctl_mount_point;
}

static void set_empty_dir(struct ctl_dir *dir)
{
	dir->header.ctl_table[0].child = sysctl_mount_point;
}

static void clear_empty_dir(struct ctl_dir *dir)

{
	dir->header.ctl_table[0].child = NULL;
}

44 45 46 47 48 49 50 51 52
void proc_sys_poll_notify(struct ctl_table_poll *poll)
{
	if (!poll)
		return;

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

53 54 55
static struct ctl_table root_table[] = {
	{
		.procname = "",
56
		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
57 58 59
	},
	{ }
};
60 61
static struct ctl_table_root sysctl_table_root = {
	.default_set.dir.header = {
62 63
		{{.count = 1,
		  .nreg = 1,
64
		  .ctl_table = root_table }},
65
		.ctl_table_arg = root_table,
66 67 68
		.root = &sysctl_table_root,
		.set = &sysctl_table_root.default_set,
	},
69 70 71 72
};

static DEFINE_SPINLOCK(sysctl_lock);

73
static void drop_sysctl_table(struct ctl_table_header *header);
74 75 76 77
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);
78

79 80 81 82
static void sysctl_print_dir(struct ctl_dir *dir)
{
	if (dir->header.parent)
		sysctl_print_dir(dir->header.parent);
83
	pr_cont("%s/", dir->header.ctl_table[0].procname);
84 85
}

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100
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;
}

101
/* Called under sysctl_lock */
102
static struct ctl_table *find_entry(struct ctl_table_header **phead,
103
	struct ctl_dir *dir, const char *name, int namelen)
104 105 106
{
	struct ctl_table_header *head;
	struct ctl_table *entry;
107
	struct rb_node *node = dir->root.rb_node;
108

109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
	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;
128 129 130 131 132
		}
	}
	return NULL;
}

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
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 {
160
			pr_err("sysctl duplicate entry: ");
161
			sysctl_print_dir(head->parent);
162
			pr_cont("/%s\n", entry->procname);
163 164 165 166 167
			return -EEXIST;
		}
	}

	rb_link_node(node, parent, p);
168
	rb_insert_color(node, &head->parent->root);
169 170 171 172 173 174 175 176 177 178
	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);
}

179 180
static void init_header(struct ctl_table_header *head,
	struct ctl_table_root *root, struct ctl_table_set *set,
181
	struct ctl_node *node, struct ctl_table *table)
182
{
183
	head->ctl_table = table;
184 185 186 187 188 189 190 191
	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;
192 193 194
	head->node = node;
	if (node) {
		struct ctl_table *entry;
195
		for (entry = table; entry->procname; entry++, node++)
196 197
			node->header = head;
	}
198 199
}

200 201
static void erase_header(struct ctl_table_header *head)
{
202 203 204
	struct ctl_table *entry;
	for (entry = head->ctl_table; entry->procname; entry++)
		erase_entry(head, entry);
205 206
}

207
static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
208
{
209
	struct ctl_table *entry;
210 211
	int err;

212 213 214 215 216 217 218 219 220 221 222
	/* Is this a permanently empty directory? */
	if (is_empty_dir(&dir->header))
		return -EROFS;

	/* Am I creating a permanently empty directory? */
	if (header->ctl_table == sysctl_mount_point) {
		if (!RB_EMPTY_ROOT(&dir->root))
			return -EINVAL;
		set_empty_dir(dir);
	}

223
	dir->header.nreg++;
224
	header->parent = dir;
225 226 227
	err = insert_links(header);
	if (err)
		goto fail_links;
228 229 230 231 232
	for (entry = header->ctl_table; entry->procname; entry++) {
		err = insert_entry(header, entry);
		if (err)
			goto fail;
	}
233
	return 0;
234 235 236
fail:
	erase_header(header);
	put_links(header);
237
fail_links:
238 239
	if (header->ctl_table == sysctl_mount_point)
		clear_empty_dir(dir);
240 241 242
	header->parent = NULL;
	drop_sysctl_table(&dir->header);
	return err;
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
/* 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.
	 */
284
	erase_header(p);
285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303
}

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)
{
304
	BUG_ON(!head);
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
	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;
}

330
static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
331
				      struct ctl_dir *dir,
332 333 334 335 336 337
				      const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;

	spin_lock(&sysctl_lock);
338 339 340 341 342
	entry = find_entry(&head, dir, name, namelen);
	if (entry && use_table(head))
		*phead = head;
	else
		entry = NULL;
343 344 345 346
	spin_unlock(&sysctl_lock);
	return entry;
}

347
static struct ctl_node *first_usable_entry(struct rb_node *node)
348
{
349
	struct ctl_node *ctl_node;
350

351 352 353 354
	for (;node; node = rb_next(node)) {
		ctl_node = rb_entry(node, struct ctl_node, node);
		if (use_table(ctl_node->header))
			return ctl_node;
355 356 357 358
	}
	return NULL;
}

359
static void first_entry(struct ctl_dir *dir,
360 361
	struct ctl_table_header **phead, struct ctl_table **pentry)
{
362
	struct ctl_table_header *head = NULL;
363
	struct ctl_table *entry = NULL;
364
	struct ctl_node *ctl_node;
365 366

	spin_lock(&sysctl_lock);
367
	ctl_node = first_usable_entry(rb_first(&dir->root));
368
	spin_unlock(&sysctl_lock);
369 370 371 372
	if (ctl_node) {
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
	}
373 374 375 376
	*phead = head;
	*pentry = entry;
}

377
static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
378
{
379 380
	struct ctl_table_header *head = *phead;
	struct ctl_table *entry = *pentry;
381
	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
382

383 384 385 386 387 388 389 390 391
	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];
392 393 394
	}
	*phead = head;
	*pentry = entry;
395 396 397 398 399 400 401 402 403 404 405 406 407
}

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)
{
408
	if (uid_eq(current_euid(), GLOBAL_ROOT_UID))
409
		mode >>= 6;
410
	else if (in_egroup_p(GLOBAL_ROOT_GID))
411 412 413 414 415 416
		mode >>= 3;
	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
		return 0;
	return -EACCES;
}

417
static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op)
418
{
419
	struct ctl_table_root *root = head->root;
420 421 422
	int mode;

	if (root->permissions)
423
		mode = root->permissions(head, table);
424 425 426 427 428 429
	else
		mode = table->mode;

	return test_perm(mode, op);
}

Al Viro's avatar
Al Viro committed
430 431
static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
432 433
{
	struct inode *inode;
Al Viro's avatar
Al Viro committed
434
	struct proc_inode *ei;
435

Al Viro's avatar
Al Viro committed
436
	inode = new_inode(sb);
437 438 439
	if (!inode)
		goto out;

440 441
	inode->i_ino = get_next_ino();

Al Viro's avatar
Al Viro committed
442
	sysctl_head_get(head);
443
	ei = PROC_I(inode);
Al Viro's avatar
Al Viro committed
444 445 446
	ei->sysctl = head;
	ei->sysctl_entry = table;

447
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
Al Viro's avatar
Al Viro committed
448
	inode->i_mode = table->mode;
449
	if (!S_ISDIR(table->mode)) {
Al Viro's avatar
Al Viro committed
450 451 452 453 454 455 456
		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;
457 458
		if (is_empty_dir(head))
			make_empty_dir_inode(inode);
Al Viro's avatar
Al Viro committed
459
	}
460 461 462 463
out:
	return inode;
}

464
static struct ctl_table_header *grab_header(struct inode *inode)
465
{
466 467
	struct ctl_table_header *head = PROC_I(inode)->sysctl;
	if (!head)
468
		head = &sysctl_table_root.default_set.dir.header;
469
	return sysctl_head_grab(head);
Al Viro's avatar
Al Viro committed
470
}
471

Al Viro's avatar
Al Viro committed
472
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
473
					unsigned int flags)
Al Viro's avatar
Al Viro committed
474 475 476
{
	struct ctl_table_header *head = grab_header(dir);
	struct ctl_table_header *h = NULL;
477
	const struct qstr *name = &dentry->d_name;
Al Viro's avatar
Al Viro committed
478 479 480
	struct ctl_table *p;
	struct inode *inode;
	struct dentry *err = ERR_PTR(-ENOENT);
481
	struct ctl_dir *ctl_dir;
482
	int ret;
483

Al Viro's avatar
Al Viro committed
484 485
	if (IS_ERR(head))
		return ERR_CAST(head);
486

487
	ctl_dir = container_of(head, struct ctl_dir, header);
488

489
	p = lookup_entry(&h, ctl_dir, name->name, name->len);
Al Viro's avatar
Al Viro committed
490
	if (!p)
491 492
		goto out;

493 494 495 496 497 498
	if (S_ISLNK(p->mode)) {
		ret = sysctl_follow_link(&h, &p, current->nsproxy);
		err = ERR_PTR(ret);
		if (ret)
			goto out;
	}
499

500
	err = ERR_PTR(-ENOMEM);
Al Viro's avatar
Al Viro committed
501
	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
502 503 504 505
	if (!inode)
		goto out;

	err = NULL;
506
	d_set_d_op(dentry, &proc_sys_dentry_operations);
507 508 509
	d_add(dentry, inode);

out:
510 511
	if (h)
		sysctl_head_finish(h);
512 513 514 515
	sysctl_head_finish(head);
	return err;
}

516 517
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
		size_t count, loff_t *ppos, int write)
518
{
Al Viro's avatar
Al Viro committed
519
	struct inode *inode = file_inode(filp);
Al Viro's avatar
Al Viro committed
520 521
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
522 523
	ssize_t error;
	size_t res;
524

Al Viro's avatar
Al Viro committed
525 526
	if (IS_ERR(head))
		return PTR_ERR(head);
527 528 529 530 531 532

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
533
	if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ))
534 535
		goto out;

Al Viro's avatar
Al Viro committed
536 537 538 539 540
	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

541 542
	/* careful: calling conventions are nasty here */
	res = count;
543
	error = table->proc_handler(table, write, buf, &res, ppos);
544 545 546 547 548 549 550 551
	if (!error)
		error = res;
out:
	sysctl_head_finish(head);

	return error;
}

552
static ssize_t proc_sys_read(struct file *filp, char __user *buf,
553 554
				size_t count, loff_t *ppos)
{
555 556
	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
}
557

558 559 560 561
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);
562 563
}

564 565
static int proc_sys_open(struct inode *inode, struct file *filp)
{
566
	struct ctl_table_header *head = grab_header(inode);
567 568
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

569 570 571 572
	/* sysctl was unregistered */
	if (IS_ERR(head))
		return PTR_ERR(head);

573 574 575
	if (table->poll)
		filp->private_data = proc_sys_poll_event(table->poll);

576 577
	sysctl_head_finish(head);

578 579 580 581 582
	return 0;
}

static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
{
Al Viro's avatar
Al Viro committed
583
	struct inode *inode = file_inode(filp);
584
	struct ctl_table_header *head = grab_header(inode);
585 586
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	unsigned int ret = DEFAULT_POLLMASK;
587 588 589 590 591
	unsigned long event;

	/* sysctl was unregistered */
	if (IS_ERR(head))
		return POLLERR | POLLHUP;
592 593 594 595 596 597 598

	if (!table->proc_handler)
		goto out;

	if (!table->poll)
		goto out;

599
	event = (unsigned long)filp->private_data;
600 601 602 603 604 605 606 607
	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:
608 609
	sysctl_head_finish(head);

610 611
	return ret;
}
612

Al Viro's avatar
Al Viro committed
613 614
static bool proc_sys_fill_cache(struct file *file,
				struct dir_context *ctx,
Al Viro's avatar
Al Viro committed
615 616
				struct ctl_table_header *head,
				struct ctl_table *table)
617
{
Al Viro's avatar
Al Viro committed
618
	struct dentry *child, *dir = file->f_path.dentry;
619 620 621 622 623 624 625
	struct inode *inode;
	struct qstr qname;
	ino_t ino = 0;
	unsigned type = DT_UNKNOWN;

	qname.name = table->procname;
	qname.len  = strlen(table->procname);
626
	qname.hash = full_name_hash(dir, qname.name, qname.len);
627 628 629

	child = d_lookup(dir, &qname);
	if (!child) {
630 631 632 633 634
		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
		child = d_alloc_parallel(dir, &qname, &wq);
		if (IS_ERR(child))
			return false;
		if (d_in_lookup(child)) {
Al Viro's avatar
Al Viro committed
635 636
			inode = proc_sys_make_inode(dir->d_sb, head, table);
			if (!inode) {
637
				d_lookup_done(child);
Al Viro's avatar
Al Viro committed
638
				dput(child);
Al Viro's avatar
Al Viro committed
639
				return false;
640
			}
641 642
			d_set_d_op(child, &proc_sys_dentry_operations);
			d_add(child, inode);
643 644
		}
	}
645
	inode = d_inode(child);
Al Viro's avatar
Al Viro committed
646 647
	ino  = inode->i_ino;
	type = inode->i_mode >> 12;
648
	dput(child);
Al Viro's avatar
Al Viro committed
649
	return dir_emit(ctx, qname.name, qname.len, ino, type);
Al Viro's avatar
Al Viro committed
650 651
}

Al Viro's avatar
Al Viro committed
652 653
static bool proc_sys_link_fill_cache(struct file *file,
				    struct dir_context *ctx,
654 655 656
				    struct ctl_table_header *head,
				    struct ctl_table *table)
{
Al Viro's avatar
Al Viro committed
657
	bool ret = true;
658 659
	head = sysctl_head_grab(head);

660 661
	if (S_ISLNK(table->mode)) {
		/* It is not an error if we can not follow the link ignore it */
Al Viro's avatar
Al Viro committed
662
		int err = sysctl_follow_link(&head, &table, current->nsproxy);
663 664 665
		if (err)
			goto out;
	}
666

Al Viro's avatar
Al Viro committed
667
	ret = proc_sys_fill_cache(file, ctx, head, table);
668 669 670 671 672
out:
	sysctl_head_finish(head);
	return ret;
}

673
static int scan(struct ctl_table_header *head, struct ctl_table *table,
Al Viro's avatar
Al Viro committed
674
		unsigned long *pos, struct file *file,
Al Viro's avatar
Al Viro committed
675
		struct dir_context *ctx)
Al Viro's avatar
Al Viro committed
676
{
Al Viro's avatar
Al Viro committed
677
	bool res;
Al Viro's avatar
Al Viro committed
678

Al Viro's avatar
Al Viro committed
679 680
	if ((*pos)++ < ctx->pos)
		return true;
Al Viro's avatar
Al Viro committed
681

682
	if (unlikely(S_ISLNK(table->mode)))
Al Viro's avatar
Al Viro committed
683
		res = proc_sys_link_fill_cache(file, ctx, head, table);
684
	else
Al Viro's avatar
Al Viro committed
685
		res = proc_sys_fill_cache(file, ctx, head, table);
Al Viro's avatar
Al Viro committed
686

Al Viro's avatar
Al Viro committed
687 688
	if (res)
		ctx->pos = *pos;
Al Viro's avatar
Al Viro committed
689

690
	return res;
691 692
}

Al Viro's avatar
Al Viro committed
693
static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
694
{
Al Viro's avatar
Al Viro committed
695
	struct ctl_table_header *head = grab_header(file_inode(file));
Al Viro's avatar
Al Viro committed
696
	struct ctl_table_header *h = NULL;
697
	struct ctl_table *entry;
698
	struct ctl_dir *ctl_dir;
699
	unsigned long pos;
Al Viro's avatar
Al Viro committed
700 701 702

	if (IS_ERR(head))
		return PTR_ERR(head);
703

704
	ctl_dir = container_of(head, struct ctl_dir, header);
705

Al Viro's avatar
Al Viro committed
706 707 708
	if (!dir_emit_dots(file, ctx))
		return 0;

709 710
	pos = 2;

711
	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
Al Viro's avatar
Al Viro committed
712
		if (!scan(h, entry, &pos, file, ctx)) {
Al Viro's avatar
Al Viro committed
713 714
			sysctl_head_finish(h);
			break;
715 716 717
		}
	}
	sysctl_head_finish(head);
Al Viro's avatar
Al Viro committed
718
	return 0;
719 720
}

721
static int proc_sys_permission(struct inode *inode, int mask)
722 723 724 725 726
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
727 728
	struct ctl_table_header *head;
	struct ctl_table *table;
729 730
	int error;

731 732 733 734 735
	/* Executable files are not allowed under /proc/sys/ */
	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
		return -EACCES;

	head = grab_header(inode);
Al Viro's avatar
Al Viro committed
736 737
	if (IS_ERR(head))
		return PTR_ERR(head);
738

739
	table = PROC_I(inode)->sysctl_entry;
Al Viro's avatar
Al Viro committed
740 741 742
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
743
		error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK);
744 745 746 747 748 749 750

	sysctl_head_finish(head);
	return error;
}

static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
{
751
	struct inode *inode = d_inode(dentry);
752 753 754 755 756 757
	int error;

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

	error = inode_change_ok(inode, attr);
Christoph Hellwig's avatar
Christoph Hellwig committed
758 759 760 761 762 763
	if (error)
		return error;

	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
764 765
}

Al Viro's avatar
Al Viro committed
766 767
static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
768
	struct inode *inode = d_inode(dentry);
Al Viro's avatar
Al Viro committed
769 770 771 772 773 774 775 776 777 778 779 780 781 782
	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;
}

783
static const struct file_operations proc_sys_file_operations = {
784 785
	.open		= proc_sys_open,
	.poll		= proc_sys_poll,
786 787
	.read		= proc_sys_read,
	.write		= proc_sys_write,
788
	.llseek		= default_llseek,
Al Viro's avatar
Al Viro committed
789 790 791
};

static const struct file_operations proc_sys_dir_file_operations = {
792
	.read		= generic_read_dir,
793
	.iterate_shared	= proc_sys_readdir,
794
	.llseek		= generic_file_llseek,
795 796
};

797
static const struct inode_operations proc_sys_inode_operations = {
Al Viro's avatar
Al Viro committed
798 799 800 801 802 803
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static const struct inode_operations proc_sys_dir_operations = {
804 805 806
	.lookup		= proc_sys_lookup,
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
Al Viro's avatar
Al Viro committed
807
	.getattr	= proc_sys_getattr,
808 809
};

810
static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
811
{
812
	if (flags & LOOKUP_RCU)
813
		return -ECHILD;
814
	return !PROC_I(d_inode(dentry))->sysctl->unregistering;
Al Viro's avatar
Al Viro committed
815 816
}

817
static int proc_sys_delete(const struct dentry *dentry)
Al Viro's avatar
Al Viro committed
818
{
819
	return !!PROC_I(d_inode(dentry))->sysctl->unregistering;
Al Viro's avatar
Al Viro committed
820 821
}

822 823 824 825 826 827 828 829 830 831 832 833 834 835 836
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;
}

837
static int proc_sys_compare(const struct dentry *dentry,
838
		unsigned int len, const char *str, const struct qstr *name)
Al Viro's avatar
Al Viro committed
839
{
840
	struct ctl_table_header *head;
841 842
	struct inode *inode;

843 844
	/* Although proc doesn't have negative dentries, rcu-walk means
	 * that inode here can be NULL */
845
	/* AV: can it, indeed? */
846
	inode = d_inode_rcu(dentry);
847
	if (!inode)
848
		return 1;
849
	if (name->len != len)
Al Viro's avatar
Al Viro committed
850
		return 1;
851
	if (memcmp(name->name, str, len))
Al Viro's avatar
Al Viro committed
852
		return 1;
853 854
	head = rcu_dereference(PROC_I(inode)->sysctl);
	return !head || !sysctl_is_seen(head);
855 856
}

857
static const struct dentry_operations proc_sys_dentry_operations = {
858
	.d_revalidate	= proc_sys_revalidate,
Al Viro's avatar
Al Viro committed
859 860
	.d_delete	= proc_sys_delete,
	.d_compare	= proc_sys_compare,
861 862
};

863 864
static struct ctl_dir *find_subdir(struct ctl_dir *dir,
				   const char *name, int namelen)
865
{
866 867
	struct ctl_table_header *head;
	struct ctl_table *entry;
868

869
	entry = find_entry(&head, dir, name, namelen);
870 871
	if (!entry)
		return ERR_PTR(-ENOENT);
872 873 874
	if (!S_ISDIR(entry->mode))
		return ERR_PTR(-ENOTDIR);
	return container_of(head, struct ctl_dir, header);
875 876 877
}

static struct ctl_dir *new_dir(struct ctl_table_set *set,
878
			       const char *name, int namelen)
879 880 881
{
	struct ctl_table *table;
	struct ctl_dir *new;
882
	struct ctl_node *node;
883
	char *new_name;
884

885 886 887
	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
		      sizeof(struct ctl_table)*2 +  namelen + 1,
		      GFP_KERNEL);
888
	if (!new)
889 890
		return NULL;

891 892
	node = (struct ctl_node *)(new + 1);
	table = (struct ctl_table *)(node + 1);
893 894 895 896 897
	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;
898
	init_header(&new->header, set->dir.header.root, set, node, table);
899 900

	return new;
901 902
}

903 904 905 906 907 908 909 910 911 912 913 914
/**
 * get_subdir - find or create a subdir with the specified name.
 * @dir:  Directory to create the subdirectory in
 * @name: The name of the subdirectory to find or create
 * @namelen: The length of name
 *
 * Takes a directory with an elevated reference count so we know that
 * if we drop the lock the directory will not go away.  Upon success
 * the reference is moved from @dir to the returned subdirectory.
 * Upon error an error code is returned and the reference on @dir is
 * simply dropped.
 */
915 916
static struct ctl_dir *get_subdir(struct ctl_dir *dir,
				  const char *name, int namelen)
917
{
918
	struct ctl_table_set *set = dir->header.set;
919
	struct ctl_dir *subdir, *new = NULL;
920
	int err;
921

922
	spin_lock(&sysctl_lock);
923
	subdir = find_subdir(dir, name, namelen);
924 925 926 927 928 929 930 931 932 933 934 935
	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;

936
	/* Was the subdir added while we dropped the lock? */
937
	subdir = find_subdir(dir, name, namelen);
938 939 940 941 942
	if (!IS_ERR(subdir))
		goto found;
	if (PTR_ERR(subdir) != -ENOENT)
		goto failed;

943
	/* Nope.  Use the our freshly made directory entry. */
944 945 946
	err = insert_header(dir, &new->header);
	subdir = ERR_PTR(err);
	if (err)
947
		goto failed;
948 949 950 951
	subdir = new;
found:
	subdir->header.nreg++;
failed:
952
	if (IS_ERR(subdir)) {
953
		pr_err("sysctl could not get directory: ");
954
		sysctl_print_dir(dir);
955
		pr_cont("/%*.*s %ld\n",
956
			namelen, namelen, name, PTR_ERR(subdir));
957
	}
958 959 960 961 962
	drop_sysctl_table(&dir->header);
	if (new)
		drop_sysctl_table(&new->header);
	spin_unlock(&sysctl_lock);
	return subdir;
963 964
}

965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
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;

	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;
}

1012
static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
1013
{
1014 1015
	struct va_format vaf;
	va_list args;
1016

1017 1018 1019 1020
	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;

1021 1022
	pr_err("sysctl table check failed: %s/%s %pV\n",
	       path, table->procname, &vaf);
1023

1024 1025
	va_end(args);
	return -EINVAL;
1026 1027
}

1028
static int sysctl_check_table(const char *path, struct ctl_table *table)
1029
{
1030
	int err = 0;
1031 1032
	for (; table->procname; table++) {
		if (table->child)
1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053
			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);
1054
	}
1055
	return err;
1056 1057
}

1058 1059 1060 1061 1062
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;
1063
	struct ctl_node *node;
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
	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) +
1075
			sizeof(struct ctl_node)*nr_entries +
1076 1077 1078 1079 1080 1081 1082
			sizeof(struct ctl_table)*(nr_entries + 1) +
			name_bytes,
			GFP_KERNEL);

	if (!links)
		return NULL;

1083 1084
	node = (struct ctl_node *)(links + 1);
	link_table = (struct ctl_table *)(node + nr_entries);
1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
	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;
	}
1095
	init_header(links, dir->header.root, dir->header.set, node, link_table);
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169
	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;
}

1170
/**
1171
 * __register_sysctl_table - register a leaf sysctl table
1172
 * @set: Sysctl tree to register on
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187
 * @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
 *
1188
 * mode - the file permissions for the /proc/sys file
1189
 *
1190
 * child - must be %NULL.
1191 1192 1193 1194 1195 1196 1197 1198
 *
 * 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.
 *
1199 1200
 * There must be a proc_handler routine for any terminal nodes.
 * Several default handlers are available to cover common cases -
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
 *
 * 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.
 */
1212
struct ctl_table_header *__register_sysctl_table(
1213
	struct ctl_table_set *set,
1214
	const char *path, struct ctl_table *table)
1215
{
1216
	struct ctl_table_root *root = set->dir.header.root;
1217
	struct ctl_table_header *header;
1218
	const char *name, *nextname;
1219
	struct ctl_dir *dir;
1220 1221 1222 1223 1224 1225
	struct ctl_table *entry;
	struct ctl_node *node;
	int nr_entries = 0;

	for (entry = table; entry->procname; entry++)
		nr_entries++;
1226

1227 1228
	header = kzalloc(sizeof(struct ctl_table_header) +
			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
1229 1230 1231
	if (!header)
		return NULL;

1232 1233
	node = (struct ctl_node *)(header + 1);
	init_header(header, root, set, node, table);
1234 1235 1236 1237
	if (sysctl_check_table(path, table))
		goto fail;

	spin_lock(&sysctl_lock);
1238
	dir = &set->dir;
1239
	/* Reference moved down the diretory tree get_subdir */
1240 1241
	dir->header.nreg++;
	spin_unlock(&sysctl_lock);
1242

1243
	/* Find the directory for the ctl_table */
1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254
	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;
1255

1256
		dir = get_subdir(dir, name, namelen);
1257 1258
		if (IS_ERR(dir))
			goto fail;
1259
	}
1260

1261
	spin_lock(&sysctl_lock);
1262
	if (insert_header(dir, header))
1263
		goto fail_put_dir_locked;
1264

1265
	drop_sysctl_table(&dir->header);
1266 1267 1268
	spin_unlock(&sysctl_lock);

	return header;
1269

1270 1271
fail_put_dir_locked:
	drop_sysctl_table(&dir->header);
1272 1273 1274 1275 1276
	spin_unlock(&sysctl_lock);
fail:
	kfree(header);
	dump_stack();
	return NULL;
1277 1278
}

1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295
/**
 * register_sysctl - register a sysctl table
 * @path: The path to the directory the sysctl table is in.
 * @table: the table structure
 *
 * Register a sysctl table. @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(const char *path, struct ctl_table *table)
{
	return __register_sysctl_table(&sysctl_table_root.default_set,
					path, table);
}
EXPORT_SYMBOL(register_sysctl);

1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308
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;
}

1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
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,
1329
	struct ctl_table_header ***subheader, struct ctl_table_set *set,
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
	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;
1366
		header = __register_sysctl_table(set, path, files);
1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390
		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,
1391
						  set, entry->child);
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
		pos[0] = '\0';
		if (err)
			goto out;
	}
	err = 0;
out:
	/* On failure our caller will unregister all registered subheaders */
	return err;
}

1402 1403
/**
 * __register_sysctl_paths - register a sysctl table hierarchy
1404
 * @set: Sysctl tree to register on
1405 1406 1407 1408 1409 1410 1411 1412 1413
 * @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(