proc_sysctl.c 33.3 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 31 32 33 34 35
static struct ctl_table root_table[] = {
	{
		.procname = "",
		.mode = S_IRUGO|S_IXUGO,
		.child = &root_table[1],
	},
	{ }
};
36 37 38
static struct ctl_table_root sysctl_table_root;
static struct ctl_table_header root_table_header = {
	{{.count = 1,
39 40 41
	  .nreg = 1,
	  .ctl_table = root_table,
	  .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
42 43 44 45 46 47 48 49 50 51
	.root = &sysctl_table_root,
	.set = &sysctl_table_root.default_set,
};
static struct ctl_table_root sysctl_table_root = {
	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
	.default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
};

static DEFINE_SPINLOCK(sysctl_lock);

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
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,
	struct ctl_table_set *set,
	struct ctl_table_header *dir_head, struct ctl_table *dir,
	const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;

	if (dir_head->set == set) {
		for (entry = dir; entry->procname; entry++) {
			const char *procname = entry->procname;
			if (namecmp(procname, strlen(procname), name, namelen) == 0) {
				*phead = dir_head;
				return entry;
			}
		}
	}

	list_for_each_entry(head, &set->list, ctl_entry) {
		if (head->unregistering)
			continue;
		if (head->attached_to != dir)
			continue;
		for (entry = head->attached_by; entry->procname; entry++) {
			const char *procname = entry->procname;
			if (namecmp(procname, strlen(procname), name, namelen) == 0) {
				*phead = head;
				return entry;
			}
		}
	}
	return NULL;
}

101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
static void init_header(struct ctl_table_header *head,
	struct ctl_table_root *root, struct ctl_table_set *set,
	struct ctl_table *table)
{
	head->ctl_table_arg = table;
	INIT_LIST_HEAD(&head->ctl_entry);
	head->used = 0;
	head->count = 1;
	head->nreg = 1;
	head->unregistering = NULL;
	head->root = root;
	head->set = set;
	head->parent = NULL;
}

116 117 118 119 120 121 122 123 124 125 126
static void erase_header(struct ctl_table_header *head)
{
	list_del_init(&head->ctl_entry);
}

static void insert_header(struct ctl_table_header *header)
{
	header->parent->count++;
	list_add_tail(&header->ctl_entry, &header->set->list);
}

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
/* 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.
	 */
166
	erase_header(p);
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
}

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;
}

static struct list_head *
lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
{
	struct ctl_table_set *set = lookup_header_set(root, namespaces);
	return &set->list;
}

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
static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
				      struct ctl_table_header *dir_head,
				      struct ctl_table *dir,
				      const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;
	struct ctl_table_root *root;
	struct ctl_table_set *set;

	spin_lock(&sysctl_lock);
	root = &sysctl_table_root;
	do {
		set = lookup_header_set(root, current->nsproxy);
		entry = find_entry(&head, set, dir_head, dir, name, namelen);
		if (entry && use_table(head))
			*phead = head;
		else
			entry = NULL;
		root = list_entry(root->root_list.next,
				  struct ctl_table_root, root_list);
	} while (!entry && root != &sysctl_table_root);
	spin_unlock(&sysctl_lock);
	return entry;
}

246 247
static struct ctl_table_header *next_usable_entry(struct ctl_table *dir,
	struct ctl_table_root *root, struct list_head *tmp)
248
{
249
	struct nsproxy *namespaces = current->nsproxy;
250 251 252
	struct list_head *header_list;
	struct ctl_table_header *head;

253
	goto next;
254 255
	for (;;) {
		head = list_entry(tmp, struct ctl_table_header, ctl_entry);
256
		root = head->root;
257

258 259 260
		if (head->attached_to != dir ||
		    !head->attached_by->procname ||
		    !use_table(head))
261
			goto next;
262

263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
		return head;
	next:
		tmp = tmp->next;
		header_list = lookup_header_list(root, namespaces);
		if (tmp != header_list)
			continue;

		do {
			root = list_entry(root->root_list.next,
					struct ctl_table_root, root_list);
			if (root == &sysctl_table_root)
				goto out;
			header_list = lookup_header_list(root, namespaces);
		} while (list_empty(header_list));
		tmp = header_list->next;
	}
out:
	return NULL;
}

283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
static void first_entry(
	struct ctl_table_header *dir_head, struct ctl_table *dir,
	struct ctl_table_header **phead, struct ctl_table **pentry)
{
	struct ctl_table_header *head = dir_head;
	struct ctl_table *entry = dir;

	spin_lock(&sysctl_lock);
	if (entry->procname) {
		use_table(head);
	} else {
		head = next_usable_entry(dir, &sysctl_table_root,
					 &sysctl_table_root.default_set.list);
		if (head)
			entry = head->attached_by;
	}
	spin_unlock(&sysctl_lock);
	*phead = head;
	*pentry = entry;
}

static void next_entry(struct ctl_table *dir,
	struct ctl_table_header **phead, struct ctl_table **pentry)
306
{
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
	struct ctl_table_header *head = *phead;
	struct ctl_table *entry = *pentry;

	entry++;
	if (!entry->procname) {
		struct ctl_table_root *root = head->root;
		struct list_head *tmp = &head->ctl_entry;
		if (head->attached_to != dir) {
			root = &sysctl_table_root;
			tmp = &sysctl_table_root.default_set.list;
		}
		spin_lock(&sysctl_lock);
		unuse_table(head);
		head = next_usable_entry(dir, root, tmp);
		spin_unlock(&sysctl_lock);
		if (head)
			entry = head->attached_by;
	}
	*phead = head;
	*pentry = entry;
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
}

void register_sysctl_root(struct ctl_table_root *root)
{
	spin_lock(&sysctl_lock);
	list_add_tail(&root->root_list, &sysctl_table_root.root_list);
	spin_unlock(&sysctl_lock);
}

/*
 * 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
364 365
static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
366 367
{
	struct inode *inode;
A
Al Viro 已提交
368
	struct proc_inode *ei;
369

A
Al Viro 已提交
370
	inode = new_inode(sb);
371 372 373
	if (!inode)
		goto out;

374 375
	inode->i_ino = get_next_ino();

A
Al Viro 已提交
376
	sysctl_head_get(head);
377
	ei = PROC_I(inode);
A
Al Viro 已提交
378 379 380
	ei->sysctl = head;
	ei->sysctl_entry = table;

381
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
A
Al Viro 已提交
382 383 384 385 386 387 388 389 390 391
	inode->i_mode = table->mode;
	if (!table->child) {
		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;
	}
392 393 394 395
out:
	return inode;
}

A
Adrian Bunk 已提交
396
static struct ctl_table_header *grab_header(struct inode *inode)
397
{
398 399 400 401
	struct ctl_table_header *head = PROC_I(inode)->sysctl;
	if (!head)
		head = &root_table_header;
	return sysctl_head_grab(head);
A
Al Viro 已提交
402
}
403

A
Al Viro 已提交
404 405 406 407 408 409 410 411 412 413
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 *table = PROC_I(dir)->sysctl_entry;
	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);
414

A
Al Viro 已提交
415 416
	if (IS_ERR(head))
		return ERR_CAST(head);
417

A
Al Viro 已提交
418 419 420
	if (table && !table->child) {
		WARN_ON(1);
		goto out;
421 422
	}

423
	table = table ? table->child : &head->ctl_table[1];
424

425
	p = lookup_entry(&h, head, table, name->name, name->len);
A
Al Viro 已提交
426
	if (!p)
427 428 429
		goto out;

	err = ERR_PTR(-ENOMEM);
A
Al Viro 已提交
430 431 432 433
	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
	if (h)
		sysctl_head_finish(h);

434 435 436 437
	if (!inode)
		goto out;

	err = NULL;
438
	d_set_d_op(dentry, &proc_sys_dentry_operations);
439 440 441 442 443 444 445
	d_add(dentry, inode);

out:
	sysctl_head_finish(head);
	return err;
}

446 447
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
		size_t count, loff_t *ppos, int write)
448
{
A
Al Viro 已提交
449 450 451
	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;
452 453
	ssize_t error;
	size_t res;
454

A
Al Viro 已提交
455 456
	if (IS_ERR(head))
		return PTR_ERR(head);
457 458 459 460 461 462

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
463
	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
464 465
		goto out;

A
Al Viro 已提交
466 467 468 469 470
	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

471 472
	/* careful: calling conventions are nasty here */
	res = count;
473
	error = table->proc_handler(table, write, buf, &res, ppos);
474 475 476 477 478 479 480 481
	if (!error)
		error = res;
out:
	sysctl_head_finish(head);

	return error;
}

482
static ssize_t proc_sys_read(struct file *filp, char __user *buf,
483 484
				size_t count, loff_t *ppos)
{
485 486
	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
}
487

488 489 490 491
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);
492 493
}

L
Lucas De Marchi 已提交
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
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;
}
527 528

static int proc_sys_fill_cache(struct file *filp, void *dirent,
A
Al Viro 已提交
529 530 531
				filldir_t filldir,
				struct ctl_table_header *head,
				struct ctl_table *table)
532 533 534 535 536 537 538 539 540 541 542 543 544
{
	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
545 546 547 548 549 550 551
		child = d_alloc(dir, &qname);
		if (child) {
			inode = proc_sys_make_inode(dir->d_sb, head, table);
			if (!inode) {
				dput(child);
				return -ENOMEM;
			} else {
552
				d_set_d_op(child, &proc_sys_dentry_operations);
A
Al Viro 已提交
553
				d_add(child, inode);
554
			}
A
Al Viro 已提交
555 556
		} else {
			return -ENOMEM;
557 558 559
		}
	}
	inode = child->d_inode;
A
Al Viro 已提交
560 561
	ino  = inode->i_ino;
	type = inode->i_mode >> 12;
562
	dput(child);
A
Al Viro 已提交
563 564 565 566 567 568 569
	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
}

static int scan(struct ctl_table_header *head, ctl_table *table,
		unsigned long *pos, struct file *file,
		void *dirent, filldir_t filldir)
{
570
	int res;
A
Al Viro 已提交
571

572 573
	if ((*pos)++ < file->f_pos)
		return 0;
A
Al Viro 已提交
574

575
	res = proc_sys_fill_cache(file, dirent, filldir, head, table);
A
Al Viro 已提交
576

577 578
	if (res == 0)
		file->f_pos = *pos;
A
Al Viro 已提交
579

580
	return res;
581 582 583 584
}

static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
A
Al Viro 已提交
585
	struct dentry *dentry = filp->f_path.dentry;
586
	struct inode *inode = dentry->d_inode;
A
Al Viro 已提交
587 588 589
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	struct ctl_table_header *h = NULL;
590
	struct ctl_table *entry;
591
	unsigned long pos;
A
Al Viro 已提交
592 593 594 595
	int ret = -EINVAL;

	if (IS_ERR(head))
		return PTR_ERR(head);
596

A
Al Viro 已提交
597 598
	if (table && !table->child) {
		WARN_ON(1);
599
		goto out;
A
Al Viro 已提交
600 601
	}

602
	table = table ? table->child : &head->ctl_table[1];
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619

	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;

620 621
	for (first_entry(head, table, &h, &entry); h; next_entry(table, &h, &entry)) {
		ret = scan(h, entry, &pos, filp, dirent, filldir);
A
Al Viro 已提交
622 623 624
		if (ret) {
			sysctl_head_finish(h);
			break;
625 626 627 628 629 630 631 632
		}
	}
	ret = 1;
out:
	sysctl_head_finish(head);
	return ret;
}

633
static int proc_sys_permission(struct inode *inode, int mask)
634 635 636 637 638
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
639 640
	struct ctl_table_header *head;
	struct ctl_table *table;
641 642
	int error;

643 644 645 646 647
	/* 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
648 649
	if (IS_ERR(head))
		return PTR_ERR(head);
650

651
	table = PROC_I(inode)->sysctl_entry;
A
Al Viro 已提交
652 653 654
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
655
		error = sysctl_perm(head->root, table, mask & ~MAY_NOT_BLOCK);
656 657 658 659 660 661 662 663 664 665 666 667 668 669

	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
670 671 672 673 674 675 676 677 678
	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;
	}
679

C
Christoph Hellwig 已提交
680 681 682
	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
683 684
}

A
Al Viro 已提交
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701
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;
}

702
static const struct file_operations proc_sys_file_operations = {
L
Lucas De Marchi 已提交
703 704
	.open		= proc_sys_open,
	.poll		= proc_sys_poll,
705 706
	.read		= proc_sys_read,
	.write		= proc_sys_write,
707
	.llseek		= default_llseek,
A
Al Viro 已提交
708 709 710
};

static const struct file_operations proc_sys_dir_file_operations = {
711
	.read		= generic_read_dir,
712
	.readdir	= proc_sys_readdir,
713
	.llseek		= generic_file_llseek,
714 715
};

716
static const struct inode_operations proc_sys_inode_operations = {
A
Al Viro 已提交
717 718 719 720 721 722
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static const struct inode_operations proc_sys_dir_operations = {
723 724 725
	.lookup		= proc_sys_lookup,
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
A
Al Viro 已提交
726
	.getattr	= proc_sys_getattr,
727 728 729 730
};

static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
{
731 732
	if (nd->flags & LOOKUP_RCU)
		return -ECHILD;
A
Al Viro 已提交
733 734 735
	return !PROC_I(dentry->d_inode)->sysctl->unregistering;
}

N
Nick Piggin 已提交
736
static int proc_sys_delete(const struct dentry *dentry)
A
Al Viro 已提交
737 738 739 740
{
	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
}

741 742 743 744 745 746 747 748 749 750 751 752 753 754 755
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
756 757 758 759
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
760
{
A
Al Viro 已提交
761
	struct ctl_table_header *head;
N
Nick Piggin 已提交
762 763
	/* Although proc doesn't have negative dentries, rcu-walk means
	 * that inode here can be NULL */
A
Al Viro 已提交
764
	/* AV: can it, indeed? */
N
Nick Piggin 已提交
765
	if (!inode)
A
Al Viro 已提交
766
		return 1;
N
Nick Piggin 已提交
767
	if (name->len != len)
A
Al Viro 已提交
768
		return 1;
N
Nick Piggin 已提交
769
	if (memcmp(name->name, str, len))
A
Al Viro 已提交
770
		return 1;
A
Al Viro 已提交
771 772
	head = rcu_dereference(PROC_I(inode)->sysctl);
	return !head || !sysctl_is_seen(head);
773 774
}

A
Al Viro 已提交
775
static const struct dentry_operations proc_sys_dentry_operations = {
776
	.d_revalidate	= proc_sys_revalidate,
A
Al Viro 已提交
777 778
	.d_delete	= proc_sys_delete,
	.d_compare	= proc_sys_compare,
779 780
};

781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828
static struct ctl_table *is_branch_in(struct ctl_table *branch,
				      struct ctl_table *table)
{
	struct ctl_table *p;
	const char *s = branch->procname;

	/* branch should have named subdirectory as its first element */
	if (!s || !branch->child)
		return NULL;

	/* ... and nothing else */
	if (branch[1].procname)
		return NULL;

	/* table should contain subdirectory with the same name */
	for (p = table; p->procname; p++) {
		if (!p->child)
			continue;
		if (p->procname && strcmp(p->procname, s) == 0)
			return p;
	}
	return NULL;
}

/* see if attaching q to p would be an improvement */
static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
{
	struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
	struct ctl_table *next;
	int is_better = 0;
	int not_in_parent = !p->attached_by;

	while ((next = is_branch_in(by, to)) != NULL) {
		if (by == q->attached_by)
			is_better = 1;
		if (to == p->attached_by)
			not_in_parent = 1;
		by = by->child;
		to = next->child;
	}

	if (is_better && not_in_parent) {
		q->attached_by = by;
		q->attached_to = to;
		q->parent = p;
	}
}

829 830
static int sysctl_check_table_dups(const char *path, struct ctl_table *old,
	struct ctl_table *table)
831
{
832 833
	struct ctl_table *entry, *test;
	int error = 0;
834

835 836 837 838 839 840 841 842 843 844
	for (entry = old; entry->procname; entry++) {
		for (test = table; test->procname; test++) {
			if (strcmp(entry->procname, test->procname) == 0) {
				printk(KERN_ERR "sysctl duplicate entry: %s/%s\n",
					path, test->procname);
				error = -EEXIST;
			}
		}
	}
	return error;
845 846
}

847 848 849
static int sysctl_check_dups(struct nsproxy *namespaces,
	struct ctl_table_header *header,
	const char *path, struct ctl_table *table)
850
{
851 852 853 854 855
	struct ctl_table_root *root;
	struct ctl_table_set *set;
	struct ctl_table_header *dir_head, *head;
	struct ctl_table *dir_table;
	int error = 0;
856

857 858 859
	/* No dups if we are the only member of our directory */
	if (header->attached_by != table)
		return 0;
860

861 862
	dir_head = header->parent;
	dir_table = header->attached_to;
863

864
	error = sysctl_check_table_dups(path, dir_table, table);
865

866 867 868
	root = &sysctl_table_root;
	do {
		set = lookup_header_set(root, namespaces);
869

870 871
		list_for_each_entry(head, &set->list, ctl_entry) {
			if (head->unregistering)
872
				continue;
873 874 875 876
			if (head->attached_to != dir_table)
				continue;
			error = sysctl_check_table_dups(path, head->attached_by,
							table);
877
		}
878 879 880 881
		root = list_entry(root->root_list.next,
				  struct ctl_table_root, root_list);
	} while (root != &sysctl_table_root);
	return error;
882 883
}

884
static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
885
{
886 887
	struct va_format vaf;
	va_list args;
888

889 890 891 892 893 894
	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);
895

896 897
	va_end(args);
	return -EINVAL;
898 899
}

900
static int sysctl_check_table(const char *path, struct ctl_table *table)
901
{
902
	int err = 0;
903 904
	for (; table->procname; table++) {
		if (table->child)
905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925
			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);
926
	}
927
	return err;
928 929 930
}

/**
931
 * __register_sysctl_table - register a leaf sysctl table
932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
 * @root: List of sysctl headers to register on
 * @namespaces: Data to compute which lists of sysctl entries are visible
 * @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
 *
949
 * mode - the file permissions for the /proc/sys file
950
 *
951
 * child - must be %NULL.
952 953 954 955 956 957 958 959
 *
 * 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.
 *
960 961
 * There must be a proc_handler routine for any terminal nodes.
 * Several default handlers are available to cover common cases -
962 963 964 965 966 967 968 969 970 971 972
 *
 * 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.
 */
973
struct ctl_table_header *__register_sysctl_table(
974 975
	struct ctl_table_root *root,
	struct nsproxy *namespaces,
976
	const char *path, struct ctl_table *table)
977 978 979
{
	struct ctl_table_header *header;
	struct ctl_table *new, **prevp;
980 981
	const char *name, *nextname;
	unsigned int npath = 0;
982
	struct ctl_table_set *set;
983 984
	size_t path_bytes = 0;
	char *new_name;
985 986

	/* Count the path components */
987 988 989 990 991 992 993 994 995 996 997 998 999 1000
	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;
		path_bytes += namelen + 1;
		npath++;
	}
1001 1002 1003 1004 1005 1006 1007 1008 1009

	/*
	 * For each path component, allocate a 2-element ctl_table array.
	 * The first array element will be filled with the sysctl entry
	 * for this, the second will be the sentinel (procname == 0).
	 *
	 * We allocate everything in one go so that we don't have to
	 * worry about freeing additional memory in unregister_sysctl_table.
	 */
1010
	header = kzalloc(sizeof(struct ctl_table_header) + path_bytes +
1011 1012 1013 1014 1015
			 (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL);
	if (!header)
		return NULL;

	new = (struct ctl_table *) (header + 1);
1016
	new_name = (char *)(new + (2 * npath));
1017 1018 1019

	/* Now connect the dots */
	prevp = &header->ctl_table;
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
	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;
		memcpy(new_name, name, namelen);
		new_name[namelen] = '\0';

1034
		new->procname = new_name;
1035 1036 1037 1038 1039 1040
		new->mode     = 0555;

		*prevp = new;
		prevp = &new->child;

		new += 2;
1041
		new_name += namelen + 1;
1042 1043
	}
	*prevp = table;
1044 1045

	init_header(header, root, NULL, table);
1046 1047
	if (sysctl_check_table(path, table))
		goto fail;
1048

1049 1050 1051
	spin_lock(&sysctl_lock);
	header->set = lookup_header_set(root, namespaces);
	header->attached_by = header->ctl_table;
1052
	header->attached_to = &root_table[1];
1053
	header->parent = &root_table_header;
1054 1055 1056
	set = header->set;
	root = header->root;
	for (;;) {
1057 1058 1059 1060 1061 1062
		struct ctl_table_header *p;
		list_for_each_entry(p, &set->list, ctl_entry) {
			if (p->unregistering)
				continue;
			try_attach(p, header);
		}
1063 1064 1065 1066 1067
		if (root == &sysctl_table_root)
			break;
		root = list_entry(root->root_list.prev,
				  struct ctl_table_root, root_list);
		set = lookup_header_set(root, namespaces);
1068
	}
1069 1070
	if (sysctl_check_dups(namespaces, header, path, table))
		goto fail_locked;
1071
	insert_header(header);
1072 1073 1074
	spin_unlock(&sysctl_lock);

	return header;
1075 1076 1077 1078 1079 1080
fail_locked:
	spin_unlock(&sysctl_lock);
fail:
	kfree(header);
	dump_stack();
	return NULL;
1081 1082
}

1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095
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;
}

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 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
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,
	struct ctl_table_header ***subheader,
	struct ctl_table_root *root, struct nsproxy *namespaces,
	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;
		header = __register_sysctl_table(root, namespaces, path, files);
		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,
						  root, namespaces, entry->child);
		pos[0] = '\0';
		if (err)
			goto out;
	}
	err = 0;
out:
	/* On failure our caller will unregister all registered subheaders */
	return err;
}

1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206
/**
 * __register_sysctl_paths - register a sysctl table hierarchy
 * @root: List of sysctl headers to register on
 * @namespaces: Data to compute which lists of sysctl entries are visible
 * @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(
	struct ctl_table_root *root,
	struct nsproxy *namespaces,
	const struct ctl_path *path, struct ctl_table *table)
{
1207
	struct ctl_table *ctl_table_arg = table;
1208 1209
	int nr_subheaders = count_subheaders(table);
	struct ctl_table_header *header = NULL, **subheaders, **subheader;
1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222
	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;
	}
1223 1224 1225 1226 1227 1228
	while (table->procname && table->child && !table[1].procname) {
		pos = append_path(new_path, pos, table->procname);
		if (!pos)
			goto out;
		table = table->child;
	}
1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
	if (nr_subheaders == 1) {
		header = __register_sysctl_table(root, namespaces, new_path, table);
		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;
1241
		header->ctl_table_arg = ctl_table_arg;
1242 1243 1244 1245 1246 1247

		if (register_leaf_sysctl_tables(new_path, pos, &subheader,
						root, namespaces, table))
			goto err_register_leaves;
	}

1248 1249 1250
out:
	kfree(new_path);
	return header;
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261

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;
1262 1263
}

1264 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
/**
 * 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)
{
	return __register_sysctl_paths(&sysctl_table_root, current->nsproxy,
					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);

1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312
static void drop_sysctl_table(struct ctl_table_header *header)
{
	if (--header->nreg)
		return;

	start_unregistering(header);
	if (!--header->parent->count) {
		WARN_ON(1);
		kfree_rcu(header->parent, rcu);
	}
	if (!--header->count)
		kfree_rcu(header, rcu);
}

1313 1314 1315 1316 1317 1318 1319 1320 1321
/**
 * 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)
{
1322
	int nr_subheaders;
1323 1324 1325 1326 1327
	might_sleep();

	if (header == NULL)
		return;

1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
	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;
	}

1344
	spin_lock(&sysctl_lock);
1345
	drop_sysctl_table(header);
1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356
	spin_unlock(&sysctl_lock);
}
EXPORT_SYMBOL(unregister_sysctl_table);

void setup_sysctl_set(struct ctl_table_set *p,
	int (*is_seen)(struct ctl_table_set *))
{
	INIT_LIST_HEAD(&p->list);
	p->is_seen = is_seen;
}

1357 1358 1359 1360
void retire_sysctl_set(struct ctl_table_set *set)
{
	WARN_ON(!list_empty(&set->list));
}
1361

A
Alexey Dobriyan 已提交
1362
int __init proc_sys_init(void)
1363
{
A
Alexey Dobriyan 已提交
1364 1365
	struct proc_dir_entry *proc_sys_root;

1366
	proc_sys_root = proc_mkdir("sys", NULL);
A
Al Viro 已提交
1367 1368
	proc_sys_root->proc_iops = &proc_sys_dir_operations;
	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
1369
	proc_sys_root->nlink = 0;
1370 1371

	return sysctl_init();
1372
}