proc_sysctl.c 27.2 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 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
static struct ctl_table root_table[1];
static struct ctl_table_root sysctl_table_root;
static struct ctl_table_header root_table_header = {
	{{.count = 1,
	.ctl_table = root_table,
	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
	.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);

/* 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.
	 */
	list_del_init(&p->ctl_entry);
}

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;
}

static struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
						struct ctl_table_header *prev)
{
	struct ctl_table_root *root;
	struct list_head *header_list;
	struct ctl_table_header *head;
	struct list_head *tmp;

	spin_lock(&sysctl_lock);
	if (prev) {
		head = prev;
		tmp = &prev->ctl_entry;
		unuse_table(prev);
		goto next;
	}
	tmp = &root_table_header.ctl_entry;
	for (;;) {
		head = list_entry(tmp, struct ctl_table_header, ctl_entry);

		if (!use_table(head))
			goto next;
		spin_unlock(&sysctl_lock);
		return head;
	next:
		root = head->root;
		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:
	spin_unlock(&sysctl_lock);
	return NULL;
}

static struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
{
	return __sysctl_head_next(current->nsproxy, prev);
}

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);
}

static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
{
	for (; table->procname; table++) {
		table->parent = parent;
		if (table->child)
			sysctl_set_parent(table, table->child);
	}
}


A
Al Viro 已提交
231 232
static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
233 234
{
	struct inode *inode;
A
Al Viro 已提交
235
	struct proc_inode *ei;
236

A
Al Viro 已提交
237
	inode = new_inode(sb);
238 239 240
	if (!inode)
		goto out;

241 242
	inode->i_ino = get_next_ino();

A
Al Viro 已提交
243
	sysctl_head_get(head);
244
	ei = PROC_I(inode);
A
Al Viro 已提交
245 246 247
	ei->sysctl = head;
	ei->sysctl_entry = table;

248
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
A
Al Viro 已提交
249 250 251 252 253 254 255 256 257 258
	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;
	}
259 260 261 262
out:
	return inode;
}

A
Al Viro 已提交
263
static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
264
{
265
	for ( ; p->procname; p++) {
266
		if (strlen(p->procname) != name->len)
267 268
			continue;

269
		if (memcmp(p->procname, name->name, name->len) != 0)
270 271 272
			continue;

		/* I have a match */
A
Al Viro 已提交
273
		return p;
274 275 276 277
	}
	return NULL;
}

A
Adrian Bunk 已提交
278
static struct ctl_table_header *grab_header(struct inode *inode)
279
{
A
Al Viro 已提交
280 281 282 283 284
	if (PROC_I(inode)->sysctl)
		return sysctl_head_grab(PROC_I(inode)->sysctl);
	else
		return sysctl_head_next(NULL);
}
285

A
Al Viro 已提交
286 287 288 289 290 291 292 293 294 295
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);
296

A
Al Viro 已提交
297 298
	if (IS_ERR(head))
		return ERR_CAST(head);
299

A
Al Viro 已提交
300 301 302
	if (table && !table->child) {
		WARN_ON(1);
		goto out;
303 304
	}

A
Al Viro 已提交
305
	table = table ? table->child : head->ctl_table;
306

A
Al Viro 已提交
307 308 309 310 311 312 313 314 315
	p = find_in_table(table, name);
	if (!p) {
		for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
			if (h->attached_to != table)
				continue;
			p = find_in_table(h->attached_by, name);
			if (p)
				break;
		}
316 317
	}

A
Al Viro 已提交
318
	if (!p)
319 320 321
		goto out;

	err = ERR_PTR(-ENOMEM);
A
Al Viro 已提交
322 323 324 325
	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
	if (h)
		sysctl_head_finish(h);

326 327 328 329
	if (!inode)
		goto out;

	err = NULL;
330
	d_set_d_op(dentry, &proc_sys_dentry_operations);
331 332 333 334 335 336 337
	d_add(dentry, inode);

out:
	sysctl_head_finish(head);
	return err;
}

338 339
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
		size_t count, loff_t *ppos, int write)
340
{
A
Al Viro 已提交
341 342 343
	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;
344 345
	ssize_t error;
	size_t res;
346

A
Al Viro 已提交
347 348
	if (IS_ERR(head))
		return PTR_ERR(head);
349 350 351 352 353 354

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
355
	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
356 357
		goto out;

A
Al Viro 已提交
358 359 360 361 362
	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

363 364
	/* careful: calling conventions are nasty here */
	res = count;
365
	error = table->proc_handler(table, write, buf, &res, ppos);
366 367 368 369 370 371 372 373
	if (!error)
		error = res;
out:
	sysctl_head_finish(head);

	return error;
}

374
static ssize_t proc_sys_read(struct file *filp, char __user *buf,
375 376
				size_t count, loff_t *ppos)
{
377 378
	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
}
379

380 381 382 383
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);
384 385
}

L
Lucas De Marchi 已提交
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
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;
}
419 420

static int proc_sys_fill_cache(struct file *filp, void *dirent,
A
Al Viro 已提交
421 422 423
				filldir_t filldir,
				struct ctl_table_header *head,
				struct ctl_table *table)
424 425 426 427 428 429 430 431 432 433 434 435 436
{
	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
437 438 439 440 441 442 443
		child = d_alloc(dir, &qname);
		if (child) {
			inode = proc_sys_make_inode(dir->d_sb, head, table);
			if (!inode) {
				dput(child);
				return -ENOMEM;
			} else {
444
				d_set_d_op(child, &proc_sys_dentry_operations);
A
Al Viro 已提交
445
				d_add(child, inode);
446
			}
A
Al Viro 已提交
447 448
		} else {
			return -ENOMEM;
449 450 451
		}
	}
	inode = child->d_inode;
A
Al Viro 已提交
452 453
	ino  = inode->i_ino;
	type = inode->i_mode >> 12;
454
	dput(child);
A
Al Viro 已提交
455 456 457 458 459 460 461 462
	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)
{

463
	for (; table->procname; table++, (*pos)++) {
A
Al Viro 已提交
464 465 466 467 468 469 470 471 472 473 474 475
		int res;

		if (*pos < file->f_pos)
			continue;

		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
		if (res)
			return res;

		file->f_pos = *pos + 1;
	}
	return 0;
476 477 478 479
}

static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
A
Al Viro 已提交
480
	struct dentry *dentry = filp->f_path.dentry;
481
	struct inode *inode = dentry->d_inode;
A
Al Viro 已提交
482 483 484
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	struct ctl_table_header *h = NULL;
485
	unsigned long pos;
A
Al Viro 已提交
486 487 488 489
	int ret = -EINVAL;

	if (IS_ERR(head))
		return PTR_ERR(head);
490

A
Al Viro 已提交
491 492
	if (table && !table->child) {
		WARN_ON(1);
493
		goto out;
A
Al Viro 已提交
494 495 496
	}

	table = table ? table->child : head->ctl_table;
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513

	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;

A
Al Viro 已提交
514 515 516
	ret = scan(head, table, &pos, filp, dirent, filldir);
	if (ret)
		goto out;
517

A
Al Viro 已提交
518 519
	for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
		if (h->attached_to != table)
520
			continue;
A
Al Viro 已提交
521 522 523 524
		ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
		if (ret) {
			sysctl_head_finish(h);
			break;
525 526 527 528 529 530 531 532
		}
	}
	ret = 1;
out:
	sysctl_head_finish(head);
	return ret;
}

533
static int proc_sys_permission(struct inode *inode, int mask)
534 535 536 537 538
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
539 540
	struct ctl_table_header *head;
	struct ctl_table *table;
541 542
	int error;

543 544 545 546 547
	/* 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
548 549
	if (IS_ERR(head))
		return PTR_ERR(head);
550

551
	table = PROC_I(inode)->sysctl_entry;
A
Al Viro 已提交
552 553 554
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
555
		error = sysctl_perm(head->root, table, mask & ~MAY_NOT_BLOCK);
556 557 558 559 560 561 562 563 564 565 566 567 568 569

	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
570 571 572 573 574 575 576 577 578
	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;
	}
579

C
Christoph Hellwig 已提交
580 581 582
	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
583 584
}

A
Al Viro 已提交
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601
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;
}

602
static const struct file_operations proc_sys_file_operations = {
L
Lucas De Marchi 已提交
603 604
	.open		= proc_sys_open,
	.poll		= proc_sys_poll,
605 606
	.read		= proc_sys_read,
	.write		= proc_sys_write,
607
	.llseek		= default_llseek,
A
Al Viro 已提交
608 609 610
};

static const struct file_operations proc_sys_dir_file_operations = {
611
	.read		= generic_read_dir,
612
	.readdir	= proc_sys_readdir,
613
	.llseek		= generic_file_llseek,
614 615
};

616
static const struct inode_operations proc_sys_inode_operations = {
A
Al Viro 已提交
617 618 619 620 621 622
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static const struct inode_operations proc_sys_dir_operations = {
623 624 625
	.lookup		= proc_sys_lookup,
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
A
Al Viro 已提交
626
	.getattr	= proc_sys_getattr,
627 628 629 630
};

static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
{
631 632
	if (nd->flags & LOOKUP_RCU)
		return -ECHILD;
A
Al Viro 已提交
633 634 635
	return !PROC_I(dentry->d_inode)->sysctl->unregistering;
}

N
Nick Piggin 已提交
636
static int proc_sys_delete(const struct dentry *dentry)
A
Al Viro 已提交
637 638 639 640
{
	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
}

641 642 643 644 645 646 647 648 649 650 651 652 653 654 655
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
656 657 658 659
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
660
{
A
Al Viro 已提交
661
	struct ctl_table_header *head;
N
Nick Piggin 已提交
662 663
	/* Although proc doesn't have negative dentries, rcu-walk means
	 * that inode here can be NULL */
A
Al Viro 已提交
664
	/* AV: can it, indeed? */
N
Nick Piggin 已提交
665
	if (!inode)
A
Al Viro 已提交
666
		return 1;
N
Nick Piggin 已提交
667
	if (name->len != len)
A
Al Viro 已提交
668
		return 1;
N
Nick Piggin 已提交
669
	if (memcmp(name->name, str, len))
A
Al Viro 已提交
670
		return 1;
A
Al Viro 已提交
671 672
	head = rcu_dereference(PROC_I(inode)->sysctl);
	return !head || !sysctl_is_seen(head);
673 674
}

A
Al Viro 已提交
675
static const struct dentry_operations proc_sys_dentry_operations = {
676
	.d_revalidate	= proc_sys_revalidate,
A
Al Viro 已提交
677 678
	.d_delete	= proc_sys_delete,
	.d_compare	= proc_sys_compare,
679 680
};

681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945
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;
	}
}

#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
static int sysctl_depth(struct ctl_table *table)
{
	struct ctl_table *tmp;
	int depth;

	depth = 0;
	for (tmp = table; tmp->parent; tmp = tmp->parent)
		depth++;

	return depth;
}

static struct ctl_table *sysctl_parent(struct ctl_table *table, int n)
{
	int i;

	for (i = 0; table && i < n; i++)
		table = table->parent;

	return table;
}


static void sysctl_print_path(struct ctl_table *table)
{
	struct ctl_table *tmp;
	int depth, i;
	depth = sysctl_depth(table);
	if (table->procname) {
		for (i = depth; i >= 0; i--) {
			tmp = sysctl_parent(table, i);
			printk("/%s", tmp->procname?tmp->procname:"");
		}
	}
	printk(" ");
}

static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
						struct ctl_table *table)
{
	struct ctl_table_header *head;
	struct ctl_table *ref, *test;
	int depth, cur_depth;

	depth = sysctl_depth(table);

	for (head = __sysctl_head_next(namespaces, NULL); head;
	     head = __sysctl_head_next(namespaces, head)) {
		cur_depth = depth;
		ref = head->ctl_table;
repeat:
		test = sysctl_parent(table, cur_depth);
		for (; ref->procname; ref++) {
			int match = 0;
			if (cur_depth && !ref->child)
				continue;

			if (test->procname && ref->procname &&
			    (strcmp(test->procname, ref->procname) == 0))
					match++;

			if (match) {
				if (cur_depth != 0) {
					cur_depth--;
					ref = ref->child;
					goto repeat;
				}
				goto out;
			}
		}
	}
	ref = NULL;
out:
	sysctl_head_finish(head);
	return ref;
}

static void set_fail(const char **fail, struct ctl_table *table, const char *str)
{
	if (*fail) {
		printk(KERN_ERR "sysctl table check failed: ");
		sysctl_print_path(table);
		printk(" %s\n", *fail);
		dump_stack();
	}
	*fail = str;
}

static void sysctl_check_leaf(struct nsproxy *namespaces,
				struct ctl_table *table, const char **fail)
{
	struct ctl_table *ref;

	ref = sysctl_check_lookup(namespaces, table);
	if (ref && (ref != table))
		set_fail(fail, table, "Sysctl already exists");
}

static int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
{
	int error = 0;
	for (; table->procname; table++) {
		const char *fail = NULL;

		if (table->parent) {
			if (!table->parent->procname)
				set_fail(&fail, table, "Parent without procname");
		}
		if (table->child) {
			if (table->data)
				set_fail(&fail, table, "Directory with data?");
			if (table->maxlen)
				set_fail(&fail, table, "Directory with maxlen?");
			if ((table->mode & (S_IRUGO|S_IXUGO)) != table->mode)
				set_fail(&fail, table, "Writable sysctl directory");
			if (table->proc_handler)
				set_fail(&fail, table, "Directory with proc_handler");
			if (table->extra1)
				set_fail(&fail, table, "Directory with extra1");
			if (table->extra2)
				set_fail(&fail, table, "Directory with extra2");
		} else {
			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)
					set_fail(&fail, table, "No data");
				if (!table->maxlen)
					set_fail(&fail, table, "No maxlen");
			}
#ifdef CONFIG_PROC_SYSCTL
			if (!table->proc_handler)
				set_fail(&fail, table, "No proc_handler");
#endif
			sysctl_check_leaf(namespaces, table, &fail);
		}
		if (table->mode > 0777)
			set_fail(&fail, table, "bogus .mode");
		if (fail) {
			set_fail(&fail, table, NULL);
			error = -EINVAL;
		}
		if (table->child)
			error |= sysctl_check_table(namespaces, table->child);
	}
	return error;
}
#endif /* CONFIG_SYSCTL_SYSCALL_CHECK */

/**
 * __register_sysctl_paths - register a sysctl 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.
 *
 * 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
 *
 * mode - the file permissions for the /proc/sys file, and for sysctl(2)
 *
 * child - a pointer to the child sysctl table if this entry is a directory, or
 *         %NULL.
 *
 * proc_handler - the text handler routine (described below)
 *
 * de - for internal use by the sysctl routines
 *
 * 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.
 *
 * sysctl(2) can automatically manage read and write requests through
 * the sysctl table.  The data and maxlen fields of the ctl_table
 * struct enable minimal validation of the values being written to be
 * performed, and the mode field allows minimal authentication.
 *
 * There must be a proc_handler routine for any terminal nodes
 * mirrored under /proc/sys (non-terminals are handled by a built-in
 * directory handler).  Several default handlers are available to
 * cover common cases -
 *
 * 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.
 */
struct ctl_table_header *__register_sysctl_paths(
	struct ctl_table_root *root,
	struct nsproxy *namespaces,
	const struct ctl_path *path, struct ctl_table *table)
{
	struct ctl_table_header *header;
	struct ctl_table *new, **prevp;
	unsigned int n, npath;
	struct ctl_table_set *set;
946 947
	size_t path_bytes = 0;
	char *new_name;
948 949 950

	/* Count the path components */
	for (npath = 0; path[npath].procname; ++npath)
951
		path_bytes += strlen(path[npath].procname) + 1;
952 953 954 955 956 957 958 959 960

	/*
	 * 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.
	 */
961
	header = kzalloc(sizeof(struct ctl_table_header) + path_bytes +
962 963 964 965 966
			 (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL);
	if (!header)
		return NULL;

	new = (struct ctl_table *) (header + 1);
967
	new_name = (char *)(new + (2 * npath));
968 969 970 971 972

	/* Now connect the dots */
	prevp = &header->ctl_table;
	for (n = 0; n < npath; ++n, ++path) {
		/* Copy the procname */
973 974
		strcpy(new_name, path->procname);
		new->procname = new_name;
975 976 977 978 979 980
		new->mode     = 0555;

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

		new += 2;
981
		new_name += strlen(new_name) + 1;
982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
	}
	*prevp = table;
	header->ctl_table_arg = table;

	INIT_LIST_HEAD(&header->ctl_entry);
	header->used = 0;
	header->unregistering = NULL;
	header->root = root;
	sysctl_set_parent(NULL, header->ctl_table);
	header->count = 1;
#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
	if (sysctl_check_table(namespaces, header->ctl_table)) {
		kfree(header);
		return NULL;
	}
#endif
	spin_lock(&sysctl_lock);
	header->set = lookup_header_set(root, namespaces);
	header->attached_by = header->ctl_table;
	header->attached_to = root_table;
	header->parent = &root_table_header;
1003 1004 1005
	set = header->set;
	root = header->root;
	for (;;) {
1006 1007 1008 1009 1010 1011
		struct ctl_table_header *p;
		list_for_each_entry(p, &set->list, ctl_entry) {
			if (p->unregistering)
				continue;
			try_attach(p, header);
		}
1012 1013 1014 1015 1016
		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);
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 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
	}
	header->parent->count++;
	list_add_tail(&header->ctl_entry, &header->set->list);
	spin_unlock(&sysctl_lock);

	return header;
}

/**
 * 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);

/**
 * 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)
{
	might_sleep();

	if (header == NULL)
		return;

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

1093 1094 1095 1096
void retire_sysctl_set(struct ctl_table_set *set)
{
	WARN_ON(!list_empty(&set->list));
}
1097

A
Alexey Dobriyan 已提交
1098
int __init proc_sys_init(void)
1099
{
A
Alexey Dobriyan 已提交
1100 1101
	struct proc_dir_entry *proc_sys_root;

1102
	proc_sys_root = proc_mkdir("sys", NULL);
A
Al Viro 已提交
1103 1104
	proc_sys_root->proc_iops = &proc_sys_dir_operations;
	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
1105
	proc_sys_root->nlink = 0;
1106 1107

	return sysctl_init();
1108
}