mqueue.c 30.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4
/*
 * POSIX message queues filesystem for Linux.
 *
 * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
5
 *                          Michal Wronski          (michal.wronski@gmail.com)
L
Linus Torvalds 已提交
6 7 8 9 10
 *
 * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
 * Lockless receive & send, fd based notify:
 * 			    Manfred Spraul	    (manfred@colorfullife.com)
 *
11 12
 * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
 *
L
Linus Torvalds 已提交
13 14 15
 * This file is released under the GPL.
 */

16
#include <linux/capability.h>
L
Linus Torvalds 已提交
17 18 19 20 21 22 23 24 25 26 27 28
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/mqueue.h>
#include <linux/msg.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
29
#include <linux/audit.h>
30
#include <linux/signal.h>
I
Ingo Molnar 已提交
31 32
#include <linux/mutex.h>

L
Linus Torvalds 已提交
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
#include <net/sock.h>
#include "util.h"

#define MQUEUE_MAGIC	0x19800202
#define DIRENT_SIZE	20
#define FILENT_SIZE	80

#define SEND		0
#define RECV		1

#define STATE_NONE	0
#define STATE_PENDING	1
#define STATE_READY	2

/* used by sysctl */
#define FS_MQUEUE 	1
#define CTL_QUEUESMAX 	2
#define CTL_MSGMAX 	3
#define CTL_MSGSIZEMAX 	4

/* default values */
#define DFLT_QUEUESMAX	256	/* max number of message queues */
#define DFLT_MSGMAX 	10	/* max number of messages in each queue */
#define HARD_MSGMAX 	(131072/sizeof(void*))
#define DFLT_MSGSIZEMAX 8192	/* max message size */


struct ext_wait_queue {		/* queue of sleeping tasks */
	struct task_struct *task;
	struct list_head list;
	struct msg_msg *msg;	/* ptr of loaded message */
	int state;		/* one of STATE_* values */
};

struct mqueue_inode_info {
	spinlock_t lock;
	struct inode vfs_inode;
	wait_queue_head_t wait_q;

	struct msg_msg **messages;
	struct mq_attr attr;

	struct sigevent notify;
76
	struct pid* notify_owner;
77
	struct user_struct *user;	/* user who created, for accounting */
L
Linus Torvalds 已提交
78 79 80 81 82 83 84 85 86
	struct sock *notify_sock;
	struct sk_buff *notify_cookie;

	/* for tasks waiting for free space and messages, respectively */
	struct ext_wait_queue e_wait_q[2];

	unsigned long qsize; /* size of queue in memory (sum of all msgs) */
};

87
static const struct inode_operations mqueue_dir_inode_operations;
88
static const struct file_operations mqueue_file_operations;
L
Linus Torvalds 已提交
89 90 91 92
static struct super_operations mqueue_super_ops;
static void remove_notification(struct mqueue_inode_info *info);

static spinlock_t mq_lock;
93
static struct kmem_cache *mqueue_inode_cachep;
L
Linus Torvalds 已提交
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
static struct vfsmount *mqueue_mnt;

static unsigned int queues_count;
static unsigned int queues_max 	= DFLT_QUEUESMAX;
static unsigned int msg_max 	= DFLT_MSGMAX;
static unsigned int msgsize_max = DFLT_MSGSIZEMAX;

static struct ctl_table_header * mq_sysctl_table;

static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
{
	return container_of(inode, struct mqueue_inode_info, vfs_inode);
}

static struct inode *mqueue_get_inode(struct super_block *sb, int mode,
							struct mq_attr *attr)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		inode->i_mtime = inode->i_ctime = inode->i_atime =
				CURRENT_TIME;

		if (S_ISREG(mode)) {
			struct mqueue_inode_info *info;
			struct task_struct *p = current;
			struct user_struct *u = p->user;
			unsigned long mq_bytes, mq_msg_tblsz;

			inode->i_fop = &mqueue_file_operations;
			inode->i_size = FILENT_SIZE;
			/* mqueue specific info */
			info = MQUEUE_I(inode);
			spin_lock_init(&info->lock);
			init_waitqueue_head(&info->wait_q);
			INIT_LIST_HEAD(&info->e_wait_q[0].list);
			INIT_LIST_HEAD(&info->e_wait_q[1].list);
			info->messages = NULL;
137
			info->notify_owner = NULL;
L
Linus Torvalds 已提交
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
			info->qsize = 0;
			info->user = NULL;	/* set when all is ok */
			memset(&info->attr, 0, sizeof(info->attr));
			info->attr.mq_maxmsg = DFLT_MSGMAX;
			info->attr.mq_msgsize = DFLT_MSGSIZEMAX;
			if (attr) {
				info->attr.mq_maxmsg = attr->mq_maxmsg;
				info->attr.mq_msgsize = attr->mq_msgsize;
			}
			mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
			mq_bytes = (mq_msg_tblsz +
				(info->attr.mq_maxmsg * info->attr.mq_msgsize));

			spin_lock(&mq_lock);
			if (u->mq_bytes + mq_bytes < u->mq_bytes ||
		 	    u->mq_bytes + mq_bytes >
			    p->signal->rlim[RLIMIT_MSGQUEUE].rlim_cur) {
				spin_unlock(&mq_lock);
				goto out_inode;
			}
			u->mq_bytes += mq_bytes;
			spin_unlock(&mq_lock);

			info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
			if (!info->messages) {
				spin_lock(&mq_lock);
				u->mq_bytes -= mq_bytes;
				spin_unlock(&mq_lock);
				goto out_inode;
			}
			/* all is ok */
			info->user = get_uid(u);
		} else if (S_ISDIR(mode)) {
171
			inc_nlink(inode);
L
Linus Torvalds 已提交
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
			/* Some things misbehave if size == 0 on a directory */
			inode->i_size = 2 * DIRENT_SIZE;
			inode->i_op = &mqueue_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;
		}
	}
	return inode;
out_inode:
	make_bad_inode(inode);
	iput(inode);
	return NULL;
}

static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *inode;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = MQUEUE_MAGIC;
	sb->s_op = &mqueue_super_ops;

	inode = mqueue_get_inode(sb, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
	if (!inode)
		return -ENOMEM;

	sb->s_root = d_alloc_root(inode);
	if (!sb->s_root) {
		iput(inode);
		return -ENOMEM;
	}

	return 0;
}

207 208 209
static int mqueue_get_sb(struct file_system_type *fs_type,
			 int flags, const char *dev_name,
			 void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
210
{
211
	return get_sb_single(fs_type, flags, data, mqueue_fill_super, mnt);
L
Linus Torvalds 已提交
212 213
}

214
static void init_once(void *foo, struct kmem_cache * cachep, unsigned long flags)
L
Linus Torvalds 已提交
215 216 217
{
	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;

218
	if (flags & SLAB_CTOR_CONSTRUCTOR)
L
Linus Torvalds 已提交
219 220 221 222 223 224 225
		inode_init_once(&p->vfs_inode);
}

static struct inode *mqueue_alloc_inode(struct super_block *sb)
{
	struct mqueue_inode_info *ei;

226
	ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void mqueue_destroy_inode(struct inode *inode)
{
	kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
}

static void mqueue_delete_inode(struct inode *inode)
{
	struct mqueue_inode_info *info;
	struct user_struct *user;
	unsigned long mq_bytes;
	int i;

	if (S_ISDIR(inode->i_mode)) {
		clear_inode(inode);
		return;
	}
	info = MQUEUE_I(inode);
	spin_lock(&info->lock);
	for (i = 0; i < info->attr.mq_curmsgs; i++)
		free_msg(info->messages[i]);
	kfree(info->messages);
	spin_unlock(&info->lock);

	clear_inode(inode);

	mq_bytes = (info->attr.mq_maxmsg * sizeof(struct msg_msg *) +
		   (info->attr.mq_maxmsg * info->attr.mq_msgsize));
	user = info->user;
	if (user) {
		spin_lock(&mq_lock);
		user->mq_bytes -= mq_bytes;
		queues_count--;
		spin_unlock(&mq_lock);
		free_uid(user);
	}
}

static int mqueue_create(struct inode *dir, struct dentry *dentry,
				int mode, struct nameidata *nd)
{
	struct inode *inode;
	struct mq_attr *attr = dentry->d_fsdata;
	int error;

	spin_lock(&mq_lock);
	if (queues_count >= queues_max && !capable(CAP_SYS_RESOURCE)) {
		error = -ENOSPC;
		goto out_lock;
	}
	queues_count++;
	spin_unlock(&mq_lock);

	inode = mqueue_get_inode(dir->i_sb, mode, attr);
	if (!inode) {
		error = -ENOMEM;
		spin_lock(&mq_lock);
		queues_count--;
		goto out_lock;
	}

	dir->i_size += DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;

	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
out_lock:
	spin_unlock(&mq_lock);
	return error;
}

static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
{
  	struct inode *inode = dentry->d_inode;

	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
	dir->i_size -= DIRENT_SIZE;
309
  	drop_nlink(inode);
L
Linus Torvalds 已提交
310 311 312 313 314 315 316 317 318 319 320 321 322 323
  	dput(dentry);
  	return 0;
}

/*
*	This is routine for system read from queue file.
*	To avoid mess with doing here some sort of mq_receive we allow
*	to read only queue size & notification info (the only values
*	that are interesting from user point of view and aren't accessible
*	through std routines)
*/
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
				size_t count, loff_t * off)
{
J
Josef Sipek 已提交
324
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
	char buffer[FILENT_SIZE];
	size_t slen;
	loff_t o;

	if (!count)
		return 0;

	spin_lock(&info->lock);
	snprintf(buffer, sizeof(buffer),
			"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
			info->qsize,
			info->notify_owner ? info->notify.sigev_notify : 0,
			(info->notify_owner &&
			 info->notify.sigev_notify == SIGEV_SIGNAL) ?
				info->notify.sigev_signo : 0,
340
			pid_nr(info->notify_owner));
L
Linus Torvalds 已提交
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
	spin_unlock(&info->lock);
	buffer[sizeof(buffer)-1] = '\0';
	slen = strlen(buffer)+1;

	o = *off;
	if (o > slen)
		return 0;

	if (o + count > slen)
		count = slen - o;

	if (copy_to_user(u_data, buffer + o, count))
		return -EFAULT;

	*off = o + count;
J
Josef Sipek 已提交
356
	filp->f_path.dentry->d_inode->i_atime = filp->f_path.dentry->d_inode->i_ctime = CURRENT_TIME;
L
Linus Torvalds 已提交
357 358 359
	return count;
}

360
static int mqueue_flush_file(struct file *filp, fl_owner_t id)
L
Linus Torvalds 已提交
361
{
J
Josef Sipek 已提交
362
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
363 364

	spin_lock(&info->lock);
365
	if (task_tgid(current) == info->notify_owner)
L
Linus Torvalds 已提交
366 367 368 369 370 371 372 373
		remove_notification(info);

	spin_unlock(&info->lock);
	return 0;
}

static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
J
Josef Sipek 已提交
374
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519
	int retval = 0;

	poll_wait(filp, &info->wait_q, poll_tab);

	spin_lock(&info->lock);
	if (info->attr.mq_curmsgs)
		retval = POLLIN | POLLRDNORM;

	if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
		retval |= POLLOUT | POLLWRNORM;
	spin_unlock(&info->lock);

	return retval;
}

/* Adds current to info->e_wait_q[sr] before element with smaller prio */
static void wq_add(struct mqueue_inode_info *info, int sr,
			struct ext_wait_queue *ewp)
{
	struct ext_wait_queue *walk;

	ewp->task = current;

	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
		if (walk->task->static_prio <= current->static_prio) {
			list_add_tail(&ewp->list, &walk->list);
			return;
		}
	}
	list_add_tail(&ewp->list, &info->e_wait_q[sr].list);
}

/*
 * Puts current task to sleep. Caller must hold queue lock. After return
 * lock isn't held.
 * sr: SEND or RECV
 */
static int wq_sleep(struct mqueue_inode_info *info, int sr,
			long timeout, struct ext_wait_queue *ewp)
{
	int retval;
	signed long time;

	wq_add(info, sr, ewp);

	for (;;) {
		set_current_state(TASK_INTERRUPTIBLE);

		spin_unlock(&info->lock);
		time = schedule_timeout(timeout);

		while (ewp->state == STATE_PENDING)
			cpu_relax();

		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out;
		}
		spin_lock(&info->lock);
		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out_unlock;
		}
		if (signal_pending(current)) {
			retval = -ERESTARTSYS;
			break;
		}
		if (time == 0) {
			retval = -ETIMEDOUT;
			break;
		}
	}
	list_del(&ewp->list);
out_unlock:
	spin_unlock(&info->lock);
out:
	return retval;
}

/*
 * Returns waiting task that should be serviced first or NULL if none exists
 */
static struct ext_wait_queue *wq_get_first_waiter(
		struct mqueue_inode_info *info, int sr)
{
	struct list_head *ptr;

	ptr = info->e_wait_q[sr].list.prev;
	if (ptr == &info->e_wait_q[sr].list)
		return NULL;
	return list_entry(ptr, struct ext_wait_queue, list);
}

/* Auxiliary functions to manipulate messages' list */
static void msg_insert(struct msg_msg *ptr, struct mqueue_inode_info *info)
{
	int k;

	k = info->attr.mq_curmsgs - 1;
	while (k >= 0 && info->messages[k]->m_type >= ptr->m_type) {
		info->messages[k + 1] = info->messages[k];
		k--;
	}
	info->attr.mq_curmsgs++;
	info->qsize += ptr->m_ts;
	info->messages[k + 1] = ptr;
}

static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
	info->qsize -= info->messages[--info->attr.mq_curmsgs]->m_ts;
	return info->messages[info->attr.mq_curmsgs];
}

static inline void set_cookie(struct sk_buff *skb, char code)
{
	((char*)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
}

/*
 * The next function is only to split too long sys_mq_timedsend
 */
static void __do_notify(struct mqueue_inode_info *info)
{
	/* notification
	 * invoked when there is registered process and there isn't process
	 * waiting synchronously for message AND state of queue changed from
	 * empty to not empty. Here we are sure that no one is waiting
	 * synchronously. */
	if (info->notify_owner &&
	    info->attr.mq_curmsgs == 1) {
		struct siginfo sig_i;
		switch (info->notify.sigev_notify) {
		case SIGEV_NONE:
			break;
		case SIGEV_SIGNAL:
			/* sends signal */

			sig_i.si_signo = info->notify.sigev_signo;
			sig_i.si_errno = 0;
			sig_i.si_code = SI_MESGQ;
			sig_i.si_value = info->notify.sigev_value;
			sig_i.si_pid = current->tgid;
			sig_i.si_uid = current->uid;

520 521
			kill_pid_info(info->notify.sigev_signo,
				      &sig_i, info->notify_owner);
L
Linus Torvalds 已提交
522 523 524 525 526 527 528 529
			break;
		case SIGEV_THREAD:
			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
			netlink_sendskb(info->notify_sock,
					info->notify_cookie, 0);
			break;
		}
		/* after notification unregisters process */
530 531
		put_pid(info->notify_owner);
		info->notify_owner = NULL;
L
Linus Torvalds 已提交
532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568
	}
	wake_up(&info->wait_q);
}

static long prepare_timeout(const struct timespec __user *u_arg)
{
	struct timespec ts, nowts;
	long timeout;

	if (u_arg) {
		if (unlikely(copy_from_user(&ts, u_arg,
					sizeof(struct timespec))))
			return -EFAULT;

		if (unlikely(ts.tv_nsec < 0 || ts.tv_sec < 0
			|| ts.tv_nsec >= NSEC_PER_SEC))
			return -EINVAL;
		nowts = CURRENT_TIME;
		/* first subtract as jiffies can't be too big */
		ts.tv_sec -= nowts.tv_sec;
		if (ts.tv_nsec < nowts.tv_nsec) {
			ts.tv_nsec += NSEC_PER_SEC;
			ts.tv_sec--;
		}
		ts.tv_nsec -= nowts.tv_nsec;
		if (ts.tv_sec < 0)
			return 0;

		timeout = timespec_to_jiffies(&ts) + 1;
	} else
		return MAX_SCHEDULE_TIMEOUT;

	return timeout;
}

static void remove_notification(struct mqueue_inode_info *info)
{
569
	if (info->notify_owner != NULL &&
L
Linus Torvalds 已提交
570 571 572 573
	    info->notify.sigev_notify == SIGEV_THREAD) {
		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
		netlink_sendskb(info->notify_sock, info->notify_cookie, 0);
	}
574 575
	put_pid(info->notify_owner);
	info->notify_owner = NULL;
L
Linus Torvalds 已提交
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
}

static int mq_attr_ok(struct mq_attr *attr)
{
	if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
		return 0;
	if (capable(CAP_SYS_RESOURCE)) {
		if (attr->mq_maxmsg > HARD_MSGMAX)
			return 0;
	} else {
		if (attr->mq_maxmsg > msg_max ||
				attr->mq_msgsize > msgsize_max)
			return 0;
	}
	/* check for overflow */
	if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
		return 0;
	if ((unsigned long)(attr->mq_maxmsg * attr->mq_msgsize) +
	    (attr->mq_maxmsg * sizeof (struct msg_msg *)) <
	    (unsigned long)(attr->mq_maxmsg * attr->mq_msgsize))
		return 0;
	return 1;
}

/*
 * Invoked when creating a new queue via sys_mq_open
 */
static struct file *do_create(struct dentry *dir, struct dentry *dentry,
			int oflag, mode_t mode, struct mq_attr __user *u_attr)
{
	struct mq_attr attr;
	int ret;

609 610
	if (u_attr) {
		ret = -EFAULT;
L
Linus Torvalds 已提交
611
		if (copy_from_user(&attr, u_attr, sizeof(attr)))
612 613
			goto out;
		ret = -EINVAL;
L
Linus Torvalds 已提交
614
		if (!mq_attr_ok(&attr))
615
			goto out;
L
Linus Torvalds 已提交
616 617 618 619
		/* store for use during create */
		dentry->d_fsdata = &attr;
	}

620
	mode &= ~current->fs->umask;
L
Linus Torvalds 已提交
621 622 623
	ret = vfs_create(dir->d_inode, dentry, mode, NULL);
	dentry->d_fsdata = NULL;
	if (ret)
624
		goto out;
L
Linus Torvalds 已提交
625

626
	return dentry_open(dentry, mqueue_mnt, oflag);
L
Linus Torvalds 已提交
627

628 629 630 631
out:
	dput(dentry);
	mntput(mqueue_mnt);
	return ERR_PTR(ret);
L
Linus Torvalds 已提交
632 633 634 635 636 637 638 639
}

/* Opens existing queue */
static struct file *do_open(struct dentry *dentry, int oflag)
{
static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
					MAY_READ | MAY_WRITE };

640 641 642
	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) {
		dput(dentry);
		mntput(mqueue_mnt);
L
Linus Torvalds 已提交
643
		return ERR_PTR(-EINVAL);
644
	}
L
Linus Torvalds 已提交
645

646 647 648
	if (permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE], NULL)) {
		dput(dentry);
		mntput(mqueue_mnt);
L
Linus Torvalds 已提交
649
		return ERR_PTR(-EACCES);
650
	}
L
Linus Torvalds 已提交
651

652
	return dentry_open(dentry, mqueue_mnt, oflag);
L
Linus Torvalds 已提交
653 654 655 656 657 658 659 660 661 662
}

asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode,
				struct mq_attr __user *u_attr)
{
	struct dentry *dentry;
	struct file *filp;
	char *name;
	int fd, error;

663 664 665 666
	error = audit_mq_open(oflag, mode, u_attr);
	if (error != 0)
		return error;

L
Linus Torvalds 已提交
667 668 669 670 671 672 673
	if (IS_ERR(name = getname(u_name)))
		return PTR_ERR(name);

	fd = get_unused_fd();
	if (fd < 0)
		goto out_putname;

674
	mutex_lock(&mqueue_mnt->mnt_root->d_inode->i_mutex);
L
Linus Torvalds 已提交
675 676 677 678 679 680 681 682 683
	dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name));
	if (IS_ERR(dentry)) {
		error = PTR_ERR(dentry);
		goto out_err;
	}
	mntget(mqueue_mnt);

	if (oflag & O_CREAT) {
		if (dentry->d_inode) {	/* entry already exists */
684
			audit_inode(name, dentry->d_inode);
685 686 687 688
			error = -EEXIST;
			if (oflag & O_EXCL)
				goto out;
			filp = do_open(dentry, oflag);
L
Linus Torvalds 已提交
689 690 691 692
		} else {
			filp = do_create(mqueue_mnt->mnt_root, dentry,
						oflag, mode, u_attr);
		}
693 694 695 696
	} else {
		error = -ENOENT;
		if (!dentry->d_inode)
			goto out;
697
		audit_inode(name, dentry->d_inode);
698 699
		filp = do_open(dentry, oflag);
	}
L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709

	if (IS_ERR(filp)) {
		error = PTR_ERR(filp);
		goto out_putfd;
	}

	set_close_on_exec(fd, 1);
	fd_install(fd, filp);
	goto out_upsem;

710 711
out:
	dput(dentry);
L
Linus Torvalds 已提交
712
	mntput(mqueue_mnt);
713
out_putfd:
L
Linus Torvalds 已提交
714 715 716 717
	put_unused_fd(fd);
out_err:
	fd = error;
out_upsem:
718
	mutex_unlock(&mqueue_mnt->mnt_root->d_inode->i_mutex);
L
Linus Torvalds 已提交
719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734
out_putname:
	putname(name);
	return fd;
}

asmlinkage long sys_mq_unlink(const char __user *u_name)
{
	int err;
	char *name;
	struct dentry *dentry;
	struct inode *inode = NULL;

	name = getname(u_name);
	if (IS_ERR(name))
		return PTR_ERR(name);

735 736
	mutex_lock_nested(&mqueue_mnt->mnt_root->d_inode->i_mutex,
			I_MUTEX_PARENT);
L
Linus Torvalds 已提交
737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
	dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name));
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out_unlock;
	}

	if (!dentry->d_inode) {
		err = -ENOENT;
		goto out_err;
	}

	inode = dentry->d_inode;
	if (inode)
		atomic_inc(&inode->i_count);

	err = vfs_unlink(dentry->d_parent->d_inode, dentry);
out_err:
	dput(dentry);

out_unlock:
757
	mutex_unlock(&mqueue_mnt->mnt_root->d_inode->i_mutex);
L
Linus Torvalds 已提交
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774
	putname(name);
	if (inode)
		iput(inode);

	return err;
}

/* Pipelined send and receive functions.
 *
 * If a receiver finds no waiting message, then it registers itself in the
 * list of waiting receivers. A sender checks that list before adding the new
 * message into the message array. If there is a waiting receiver, then it
 * bypasses the message array and directly hands the message over to the
 * receiver.
 * The receiver accepts the message and returns without grabbing the queue
 * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers
 * are necessary. The same algorithm is used for sysv semaphores, see
775
 * ipc/sem.c for more details.
L
Linus Torvalds 已提交
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
 *
 * The same algorithm is used for senders.
 */

/* pipelined_send() - send a message directly to the task waiting in
 * sys_mq_timedreceive() (without inserting message into a queue).
 */
static inline void pipelined_send(struct mqueue_inode_info *info,
				  struct msg_msg *message,
				  struct ext_wait_queue *receiver)
{
	receiver->msg = message;
	list_del(&receiver->list);
	receiver->state = STATE_PENDING;
	wake_up_process(receiver->task);
791
	smp_wmb();
L
Linus Torvalds 已提交
792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
	receiver->state = STATE_READY;
}

/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
 * gets its message and put to the queue (we have one free place for sure). */
static inline void pipelined_receive(struct mqueue_inode_info *info)
{
	struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);

	if (!sender) {
		/* for poll */
		wake_up_interruptible(&info->wait_q);
		return;
	}
	msg_insert(sender->msg, info);
	list_del(&sender->list);
	sender->state = STATE_PENDING;
	wake_up_process(sender->task);
810
	smp_wmb();
L
Linus Torvalds 已提交
811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826
	sender->state = STATE_READY;
}

asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
	size_t msg_len, unsigned int msg_prio,
	const struct timespec __user *u_abs_timeout)
{
	struct file *filp;
	struct inode *inode;
	struct ext_wait_queue wait;
	struct ext_wait_queue *receiver;
	struct msg_msg *msg_ptr;
	struct mqueue_inode_info *info;
	long timeout;
	int ret;

827 828 829 830
	ret = audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout);
	if (ret != 0)
		return ret;

L
Linus Torvalds 已提交
831 832 833 834 835 836 837 838 839 840
	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
		return -EINVAL;

	timeout = prepare_timeout(u_abs_timeout);

	ret = -EBADF;
	filp = fget(mqdes);
	if (unlikely(!filp))
		goto out;

J
Josef Sipek 已提交
841
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
842 843 844
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);
845
	audit_inode(NULL, inode);
L
Linus Torvalds 已提交
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

	if (unlikely(!(filp->f_mode & FMODE_WRITE)))
		goto out_fput;

	if (unlikely(msg_len > info->attr.mq_msgsize)) {
		ret = -EMSGSIZE;
		goto out_fput;
	}

	/* First try to allocate memory, before doing anything with
	 * existing queues. */
	msg_ptr = load_msg(u_msg_ptr, msg_len);
	if (IS_ERR(msg_ptr)) {
		ret = PTR_ERR(msg_ptr);
		goto out_fput;
	}
	msg_ptr->m_ts = msg_len;
	msg_ptr->m_type = msg_prio;

	spin_lock(&info->lock);

	if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
		if (filp->f_flags & O_NONBLOCK) {
			spin_unlock(&info->lock);
			ret = -EAGAIN;
		} else if (unlikely(timeout < 0)) {
			spin_unlock(&info->lock);
			ret = timeout;
		} else {
			wait.task = current;
			wait.msg = (void *) msg_ptr;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, SEND, timeout, &wait);
		}
		if (ret < 0)
			free_msg(msg_ptr);
	} else {
		receiver = wq_get_first_waiter(info, RECV);
		if (receiver) {
			pipelined_send(info, msg_ptr, receiver);
		} else {
			/* adds message to the queue */
			msg_insert(msg_ptr, info);
			__do_notify(info);
		}
		inode->i_atime = inode->i_mtime = inode->i_ctime =
				CURRENT_TIME;
		spin_unlock(&info->lock);
		ret = 0;
	}
out_fput:
	fput(filp);
out:
	return ret;
}

asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
	size_t msg_len, unsigned int __user *u_msg_prio,
	const struct timespec __user *u_abs_timeout)
{
	long timeout;
	ssize_t ret;
	struct msg_msg *msg_ptr;
	struct file *filp;
	struct inode *inode;
	struct mqueue_inode_info *info;
	struct ext_wait_queue wait;

914 915 916 917
	ret = audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
	if (ret != 0)
		return ret;

L
Linus Torvalds 已提交
918 919 920 921 922 923 924
	timeout = prepare_timeout(u_abs_timeout);

	ret = -EBADF;
	filp = fget(mqdes);
	if (unlikely(!filp))
		goto out;

J
Josef Sipek 已提交
925
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
926 927 928
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);
929
	audit_inode(NULL, inode);
L
Linus Torvalds 已提交
930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997

	if (unlikely(!(filp->f_mode & FMODE_READ)))
		goto out_fput;

	/* checks if buffer is big enough */
	if (unlikely(msg_len < info->attr.mq_msgsize)) {
		ret = -EMSGSIZE;
		goto out_fput;
	}

	spin_lock(&info->lock);
	if (info->attr.mq_curmsgs == 0) {
		if (filp->f_flags & O_NONBLOCK) {
			spin_unlock(&info->lock);
			ret = -EAGAIN;
			msg_ptr = NULL;
		} else if (unlikely(timeout < 0)) {
			spin_unlock(&info->lock);
			ret = timeout;
			msg_ptr = NULL;
		} else {
			wait.task = current;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, RECV, timeout, &wait);
			msg_ptr = wait.msg;
		}
	} else {
		msg_ptr = msg_get(info);

		inode->i_atime = inode->i_mtime = inode->i_ctime =
				CURRENT_TIME;

		/* There is now free space in queue. */
		pipelined_receive(info);
		spin_unlock(&info->lock);
		ret = 0;
	}
	if (ret == 0) {
		ret = msg_ptr->m_ts;

		if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) ||
			store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) {
			ret = -EFAULT;
		}
		free_msg(msg_ptr);
	}
out_fput:
	fput(filp);
out:
	return ret;
}

/*
 * Notes: the case when user wants us to deregister (with NULL as pointer)
 * and he isn't currently owner of notification, will be silently discarded.
 * It isn't explicitly defined in the POSIX.
 */
asmlinkage long sys_mq_notify(mqd_t mqdes,
				const struct sigevent __user *u_notification)
{
	int ret;
	struct file *filp;
	struct sock *sock;
	struct inode *inode;
	struct sigevent notification;
	struct mqueue_inode_info *info;
	struct sk_buff *nc;

998 999 1000 1001
	ret = audit_mq_notify(mqdes, u_notification);
	if (ret != 0)
		return ret;

L
Linus Torvalds 已提交
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
	nc = NULL;
	sock = NULL;
	if (u_notification != NULL) {
		if (copy_from_user(&notification, u_notification,
					sizeof(struct sigevent)))
			return -EFAULT;

		if (unlikely(notification.sigev_notify != SIGEV_NONE &&
			     notification.sigev_notify != SIGEV_SIGNAL &&
			     notification.sigev_notify != SIGEV_THREAD))
			return -EINVAL;
		if (notification.sigev_notify == SIGEV_SIGNAL &&
1014
			!valid_signal(notification.sigev_signo)) {
L
Linus Torvalds 已提交
1015 1016 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
			return -EINVAL;
		}
		if (notification.sigev_notify == SIGEV_THREAD) {
			/* create the notify skb */
			nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
			ret = -ENOMEM;
			if (!nc)
				goto out;
			ret = -EFAULT;
			if (copy_from_user(nc->data,
					notification.sigev_value.sival_ptr,
					NOTIFY_COOKIE_LEN)) {
				goto out;
			}

			/* TODO: add a header? */
			skb_put(nc, NOTIFY_COOKIE_LEN);
			/* and attach it to the socket */
retry:
			filp = fget(notification.sigev_signo);
			ret = -EBADF;
			if (!filp)
				goto out;
			sock = netlink_getsockbyfilp(filp);
			fput(filp);
			if (IS_ERR(sock)) {
				ret = PTR_ERR(sock);
				sock = NULL;
				goto out;
			}

A
Alexey Kuznetsov 已提交
1046 1047
			ret = netlink_attachskb(sock, nc, 0,
					MAX_SCHEDULE_TIMEOUT, NULL);
L
Linus Torvalds 已提交
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
			if (ret == 1)
		       		goto retry;
			if (ret) {
				sock = NULL;
				nc = NULL;
				goto out;
			}
		}
	}

	ret = -EBADF;
	filp = fget(mqdes);
	if (!filp)
		goto out;

J
Josef Sipek 已提交
1063
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1064 1065 1066 1067 1068 1069 1070
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);

	ret = 0;
	spin_lock(&info->lock);
	if (u_notification == NULL) {
1071
		if (info->notify_owner == task_tgid(current)) {
L
Linus Torvalds 已提交
1072 1073 1074
			remove_notification(info);
			inode->i_atime = inode->i_ctime = CURRENT_TIME;
		}
1075
	} else if (info->notify_owner != NULL) {
L
Linus Torvalds 已提交
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
		ret = -EBUSY;
	} else {
		switch (notification.sigev_notify) {
		case SIGEV_NONE:
			info->notify.sigev_notify = SIGEV_NONE;
			break;
		case SIGEV_THREAD:
			info->notify_sock = sock;
			info->notify_cookie = nc;
			sock = NULL;
			nc = NULL;
			info->notify.sigev_notify = SIGEV_THREAD;
			break;
		case SIGEV_SIGNAL:
			info->notify.sigev_signo = notification.sigev_signo;
			info->notify.sigev_value = notification.sigev_value;
			info->notify.sigev_notify = SIGEV_SIGNAL;
			break;
		}
1095 1096

		info->notify_owner = get_pid(task_tgid(current));
L
Linus Torvalds 已提交
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
		inode->i_atime = inode->i_ctime = CURRENT_TIME;
	}
	spin_unlock(&info->lock);
out_fput:
	fput(filp);
out:
	if (sock) {
		netlink_detachskb(sock, nc);
	} else if (nc) {
		dev_kfree_skb(nc);
	}
	return ret;
}

asmlinkage long sys_mq_getsetattr(mqd_t mqdes,
			const struct mq_attr __user *u_mqstat,
			struct mq_attr __user *u_omqstat)
{
	int ret;
	struct mq_attr mqstat, omqstat;
	struct file *filp;
	struct inode *inode;
	struct mqueue_inode_info *info;

	if (u_mqstat != NULL) {
		if (copy_from_user(&mqstat, u_mqstat, sizeof(struct mq_attr)))
			return -EFAULT;
		if (mqstat.mq_flags & (~O_NONBLOCK))
			return -EINVAL;
	}

	ret = -EBADF;
	filp = fget(mqdes);
	if (!filp)
		goto out;

J
Josef Sipek 已提交
1133
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1134 1135 1136 1137 1138 1139 1140 1141 1142
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);

	spin_lock(&info->lock);

	omqstat = info->attr;
	omqstat.mq_flags = filp->f_flags & O_NONBLOCK;
	if (u_mqstat) {
1143 1144 1145
		ret = audit_mq_getsetattr(mqdes, &mqstat);
		if (ret != 0)
			goto out;
L
Linus Torvalds 已提交
1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166
		if (mqstat.mq_flags & O_NONBLOCK)
			filp->f_flags |= O_NONBLOCK;
		else
			filp->f_flags &= ~O_NONBLOCK;

		inode->i_atime = inode->i_ctime = CURRENT_TIME;
	}

	spin_unlock(&info->lock);

	ret = 0;
	if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat,
						sizeof(struct mq_attr)))
		ret = -EFAULT;

out_fput:
	fput(filp);
out:
	return ret;
}

1167
static const struct inode_operations mqueue_dir_inode_operations = {
L
Linus Torvalds 已提交
1168 1169 1170 1171 1172
	.lookup = simple_lookup,
	.create = mqueue_create,
	.unlink = mqueue_unlink,
};

1173
static const struct file_operations mqueue_file_operations = {
L
Linus Torvalds 已提交
1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261
	.flush = mqueue_flush_file,
	.poll = mqueue_poll_file,
	.read = mqueue_read_file,
};

static struct super_operations mqueue_super_ops = {
	.alloc_inode = mqueue_alloc_inode,
	.destroy_inode = mqueue_destroy_inode,
	.statfs = simple_statfs,
	.delete_inode = mqueue_delete_inode,
	.drop_inode = generic_delete_inode,
};

static struct file_system_type mqueue_fs_type = {
	.name = "mqueue",
	.get_sb = mqueue_get_sb,
	.kill_sb = kill_litter_super,
};

static int msg_max_limit_min = DFLT_MSGMAX;
static int msg_max_limit_max = HARD_MSGMAX;

static int msg_maxsize_limit_min = DFLT_MSGSIZEMAX;
static int msg_maxsize_limit_max = INT_MAX;

static ctl_table mq_sysctls[] = {
	{
		.ctl_name	= CTL_QUEUESMAX,
		.procname	= "queues_max",
		.data		= &queues_max,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_MSGMAX,
		.procname	= "msg_max",
		.data		= &msg_max,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.extra1		= &msg_max_limit_min,
		.extra2		= &msg_max_limit_max,
	},
	{
		.ctl_name	= CTL_MSGSIZEMAX,
		.procname	= "msgsize_max",
		.data		= &msgsize_max,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.extra1		= &msg_maxsize_limit_min,
		.extra2		= &msg_maxsize_limit_max,
	},
	{ .ctl_name = 0 }
};

static ctl_table mq_sysctl_dir[] = {
	{
		.ctl_name	= FS_MQUEUE,
		.procname	= "mqueue",
		.mode		= 0555,
		.child		= mq_sysctls,
	},
	{ .ctl_name = 0 }
};

static ctl_table mq_sysctl_root[] = {
	{
		.ctl_name	= CTL_FS,
		.procname	= "fs",
		.mode		= 0555,
		.child		= mq_sysctl_dir,
	},
	{ .ctl_name = 0 }
};

static int __init init_mqueue_fs(void)
{
	int error;

	mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
				sizeof(struct mqueue_inode_info), 0,
				SLAB_HWCACHE_ALIGN, init_once, NULL);
	if (mqueue_inode_cachep == NULL)
		return -ENOMEM;

	/* ignore failues - they are not fatal */
1262
	mq_sysctl_table = register_sysctl_table(mq_sysctl_root);
L
Linus Torvalds 已提交
1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283

	error = register_filesystem(&mqueue_fs_type);
	if (error)
		goto out_sysctl;

	if (IS_ERR(mqueue_mnt = kern_mount(&mqueue_fs_type))) {
		error = PTR_ERR(mqueue_mnt);
		goto out_filesystem;
	}

	/* internal initialization - not common for vfs */
	queues_count = 0;
	spin_lock_init(&mq_lock);

	return 0;

out_filesystem:
	unregister_filesystem(&mqueue_fs_type);
out_sysctl:
	if (mq_sysctl_table)
		unregister_sysctl_table(mq_sysctl_table);
1284
	kmem_cache_destroy(mqueue_inode_cachep);
L
Linus Torvalds 已提交
1285 1286 1287 1288
	return error;
}

__initcall(init_mqueue_fs);