mqueue.c 30.6 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
#include <linux/mutex.h>
32 33
#include <linux/nsproxy.h>
#include <linux/pid.h>
34
#include <linux/ipc_namespace.h>
35
#include <linux/ima.h>
I
Ingo Molnar 已提交
36

L
Linus Torvalds 已提交
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
#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

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;
67
	struct pid* notify_owner;
68
	struct user_struct *user;	/* user who created, for accounting */
L
Linus Torvalds 已提交
69 70 71 72 73 74 75 76 77
	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) */
};

78
static const struct inode_operations mqueue_dir_inode_operations;
79
static const struct file_operations mqueue_file_operations;
L
Linus Torvalds 已提交
80 81 82
static struct super_operations mqueue_super_ops;
static void remove_notification(struct mqueue_inode_info *info);

83
static struct kmem_cache *mqueue_inode_cachep;
L
Linus Torvalds 已提交
84 85 86 87 88 89 90 91

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);
}

92 93 94 95
/*
 * This routine should be called with the mq_lock held.
 */
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
96
{
97
	return get_ipc_ns(inode->i_sb->s_fs_info);
98 99
}

100
static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
101
{
102 103 104 105 106 107
	struct ipc_namespace *ns;

	spin_lock(&mq_lock);
	ns = __get_ns_from_inode(inode);
	spin_unlock(&mq_lock);
	return ns;
108 109
}

110 111 112
static struct inode *mqueue_get_inode(struct super_block *sb,
		struct ipc_namespace *ipc_ns, int mode,
		struct mq_attr *attr)
L
Linus Torvalds 已提交
113
{
114
	struct user_struct *u = current_user();
L
Linus Torvalds 已提交
115 116 117 118 119
	struct inode *inode;

	inode = new_inode(sb);
	if (inode) {
		inode->i_mode = mode;
120 121
		inode->i_uid = current_fsuid();
		inode->i_gid = current_fsgid();
L
Linus Torvalds 已提交
122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
		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;
			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;
139
			info->notify_owner = NULL;
L
Linus Torvalds 已提交
140 141 142
			info->qsize = 0;
			info->user = NULL;	/* set when all is ok */
			memset(&info->attr, 0, sizeof(info->attr));
143 144
			info->attr.mq_maxmsg = ipc_ns->mq_msg_max;
			info->attr.mq_msgsize = ipc_ns->mq_msgsize_max;
L
Linus Torvalds 已提交
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
			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)) {
173
			inc_nlink(inode);
L
Linus Torvalds 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
			/* 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;
190 191
	struct ipc_namespace *ns = data;
	int error = 0;
L
Linus Torvalds 已提交
192 193 194 195 196 197

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

198 199 200 201 202 203
	inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO,
				NULL);
	if (!inode) {
		error = -ENOMEM;
		goto out;
	}
L
Linus Torvalds 已提交
204 205 206 207

	sb->s_root = d_alloc_root(inode);
	if (!sb->s_root) {
		iput(inode);
208
		error = -ENOMEM;
L
Linus Torvalds 已提交
209 210
	}

211 212
out:
	return error;
L
Linus Torvalds 已提交
213 214
}

215 216 217
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
218
{
219 220 221
	if (!(flags & MS_KERNMOUNT))
		data = current->nsproxy->ipc_ns;
	return get_sb_ns(fs_type, flags, data, mqueue_fill_super, mnt);
L
Linus Torvalds 已提交
222 223
}

224
static void init_once(void *foo)
L
Linus Torvalds 已提交
225 226 227
{
	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;

C
Christoph Lameter 已提交
228
	inode_init_once(&p->vfs_inode);
L
Linus Torvalds 已提交
229 230 231 232 233 234
}

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

235
	ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
	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;
252
	struct ipc_namespace *ipc_ns;
L
Linus Torvalds 已提交
253 254 255 256 257

	if (S_ISDIR(inode->i_mode)) {
		clear_inode(inode);
		return;
	}
258
	ipc_ns = get_ns_from_inode(inode);
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273
	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;
274 275 276 277 278 279 280 281
		/*
		 * get_ns_from_inode() ensures that the
		 * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
		 * to which we now hold a reference, or it is NULL.
		 * We can't put it here under mq_lock, though.
		 */
		if (ipc_ns)
			ipc_ns->mq_queues_count--;
L
Linus Torvalds 已提交
282 283 284
		spin_unlock(&mq_lock);
		free_uid(user);
	}
285 286
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
L
Linus Torvalds 已提交
287 288 289 290 291 292 293 294
}

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;
295
	struct ipc_namespace *ipc_ns;
L
Linus Torvalds 已提交
296 297

	spin_lock(&mq_lock);
298 299 300 301 302
	ipc_ns = __get_ns_from_inode(dir);
	if (!ipc_ns) {
		error = -EACCES;
		goto out_unlock;
	}
303 304
	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
			!capable(CAP_SYS_RESOURCE)) {
L
Linus Torvalds 已提交
305
		error = -ENOSPC;
306
		goto out_unlock;
L
Linus Torvalds 已提交
307
	}
308
	ipc_ns->mq_queues_count++;
L
Linus Torvalds 已提交
309 310
	spin_unlock(&mq_lock);

311
	inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
L
Linus Torvalds 已提交
312 313 314
	if (!inode) {
		error = -ENOMEM;
		spin_lock(&mq_lock);
315 316
		ipc_ns->mq_queues_count--;
		goto out_unlock;
L
Linus Torvalds 已提交
317 318
	}

319
	put_ipc_ns(ipc_ns);
L
Linus Torvalds 已提交
320 321 322 323 324 325
	dir->i_size += DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;

	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
326
out_unlock:
L
Linus Torvalds 已提交
327
	spin_unlock(&mq_lock);
328 329
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
L
Linus Torvalds 已提交
330 331 332 333 334 335 336 337 338
	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;
339
  	drop_nlink(inode);
L
Linus Torvalds 已提交
340 341 342 343 344 345 346 347 348 349 350 351
  	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,
352
				size_t count, loff_t *off)
L
Linus Torvalds 已提交
353
{
J
Josef Sipek 已提交
354
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
355
	char buffer[FILENT_SIZE];
356
	ssize_t ret;
L
Linus Torvalds 已提交
357 358 359 360 361 362 363 364 365

	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,
366
			pid_vnr(info->notify_owner));
L
Linus Torvalds 已提交
367 368 369
	spin_unlock(&info->lock);
	buffer[sizeof(buffer)-1] = '\0';

370 371 372 373
	ret = simple_read_from_buffer(u_data, count, off, buffer,
				strlen(buffer));
	if (ret <= 0)
		return ret;
L
Linus Torvalds 已提交
374

J
Josef Sipek 已提交
375
	filp->f_path.dentry->d_inode->i_atime = filp->f_path.dentry->d_inode->i_ctime = CURRENT_TIME;
376
	return ret;
L
Linus Torvalds 已提交
377 378
}

379
static int mqueue_flush_file(struct file *filp, fl_owner_t id)
L
Linus Torvalds 已提交
380
{
J
Josef Sipek 已提交
381
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
382 383

	spin_lock(&info->lock);
384
	if (task_tgid(current) == info->notify_owner)
L
Linus Torvalds 已提交
385 386 387 388 389 390 391 392
		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
393
	struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
	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;
536 537
			sig_i.si_pid = task_tgid_nr_ns(current,
						ns_of_pid(info->notify_owner));
538
			sig_i.si_uid = current_uid();
L
Linus Torvalds 已提交
539

540 541
			kill_pid_info(info->notify.sigev_signo,
				      &sig_i, info->notify_owner);
L
Linus Torvalds 已提交
542 543 544
			break;
		case SIGEV_THREAD:
			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
545
			netlink_sendskb(info->notify_sock, info->notify_cookie);
L
Linus Torvalds 已提交
546 547 548
			break;
		}
		/* after notification unregisters process */
549 550
		put_pid(info->notify_owner);
		info->notify_owner = NULL;
L
Linus Torvalds 已提交
551 552 553 554
	}
	wake_up(&info->wait_q);
}

A
Al Viro 已提交
555
static long prepare_timeout(struct timespec *p)
L
Linus Torvalds 已提交
556
{
A
Al Viro 已提交
557
	struct timespec nowts;
L
Linus Torvalds 已提交
558 559
	long timeout;

A
Al Viro 已提交
560 561 562
	if (p) {
		if (unlikely(p->tv_nsec < 0 || p->tv_sec < 0
			|| p->tv_nsec >= NSEC_PER_SEC))
L
Linus Torvalds 已提交
563 564 565
			return -EINVAL;
		nowts = CURRENT_TIME;
		/* first subtract as jiffies can't be too big */
A
Al Viro 已提交
566 567 568 569
		p->tv_sec -= nowts.tv_sec;
		if (p->tv_nsec < nowts.tv_nsec) {
			p->tv_nsec += NSEC_PER_SEC;
			p->tv_sec--;
L
Linus Torvalds 已提交
570
		}
A
Al Viro 已提交
571 572
		p->tv_nsec -= nowts.tv_nsec;
		if (p->tv_sec < 0)
L
Linus Torvalds 已提交
573 574
			return 0;

A
Al Viro 已提交
575
		timeout = timespec_to_jiffies(p) + 1;
L
Linus Torvalds 已提交
576 577 578 579 580 581 582 583
	} else
		return MAX_SCHEDULE_TIMEOUT;

	return timeout;
}

static void remove_notification(struct mqueue_inode_info *info)
{
584
	if (info->notify_owner != NULL &&
L
Linus Torvalds 已提交
585 586
	    info->notify.sigev_notify == SIGEV_THREAD) {
		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
587
		netlink_sendskb(info->notify_sock, info->notify_cookie);
L
Linus Torvalds 已提交
588
	}
589 590
	put_pid(info->notify_owner);
	info->notify_owner = NULL;
L
Linus Torvalds 已提交
591 592
}

593
static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
L
Linus Torvalds 已提交
594 595 596 597 598 599 600
{
	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 {
601 602
		if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
				attr->mq_msgsize > ipc_ns->mq_msgsize_max)
L
Linus Torvalds 已提交
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
			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
 */
618 619 620
static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir,
			struct dentry *dentry, int oflag, mode_t mode,
			struct mq_attr *attr)
L
Linus Torvalds 已提交
621
{
622
	const struct cred *cred = current_cred();
623
	struct file *result;
L
Linus Torvalds 已提交
624 625
	int ret;

A
Al Viro 已提交
626
	if (attr) {
627
		ret = -EINVAL;
628
		if (!mq_attr_ok(ipc_ns, attr))
629
			goto out;
L
Linus Torvalds 已提交
630
		/* store for use during create */
A
Al Viro 已提交
631
		dentry->d_fsdata = attr;
L
Linus Torvalds 已提交
632 633
	}

A
Al Viro 已提交
634
	mode &= ~current_umask();
635
	ret = mnt_want_write(ipc_ns->mq_mnt);
636 637
	if (ret)
		goto out;
L
Linus Torvalds 已提交
638 639 640
	ret = vfs_create(dir->d_inode, dentry, mode, NULL);
	dentry->d_fsdata = NULL;
	if (ret)
641 642
		goto out_drop_write;

643
	result = dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
644 645 646 647
	/*
	 * dentry_open() took a persistent mnt_want_write(),
	 * so we can now drop this one.
	 */
648
	mnt_drop_write(ipc_ns->mq_mnt);
649 650 651
	return result;

out_drop_write:
652
	mnt_drop_write(ipc_ns->mq_mnt);
653 654
out:
	dput(dentry);
655
	mntput(ipc_ns->mq_mnt);
656
	return ERR_PTR(ret);
L
Linus Torvalds 已提交
657 658 659
}

/* Opens existing queue */
660 661
static struct file *do_open(struct ipc_namespace *ipc_ns,
				struct dentry *dentry, int oflag)
L
Linus Torvalds 已提交
662
{
663 664 665 666
	const struct cred *cred = current_cred();

	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
						  MAY_READ | MAY_WRITE };
L
Linus Torvalds 已提交
667

668 669
	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) {
		dput(dentry);
670
		mntput(ipc_ns->mq_mnt);
L
Linus Torvalds 已提交
671
		return ERR_PTR(-EINVAL);
672
	}
L
Linus Torvalds 已提交
673

674
	if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) {
675
		dput(dentry);
676
		mntput(ipc_ns->mq_mnt);
L
Linus Torvalds 已提交
677
		return ERR_PTR(-EACCES);
678
	}
L
Linus Torvalds 已提交
679

680
	return dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
L
Linus Torvalds 已提交
681 682
}

683 684
SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, mode_t, mode,
		struct mq_attr __user *, u_attr)
L
Linus Torvalds 已提交
685 686 687 688
{
	struct dentry *dentry;
	struct file *filp;
	char *name;
A
Al Viro 已提交
689
	struct mq_attr attr;
L
Linus Torvalds 已提交
690
	int fd, error;
691
	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
L
Linus Torvalds 已提交
692

A
Al Viro 已提交
693 694 695 696
	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
		return -EFAULT;

	audit_mq_open(oflag, mode, u_attr ? &attr : NULL);
697

L
Linus Torvalds 已提交
698 699 700
	if (IS_ERR(name = getname(u_name)))
		return PTR_ERR(name);

U
Ulrich Drepper 已提交
701
	fd = get_unused_fd_flags(O_CLOEXEC);
L
Linus Torvalds 已提交
702 703 704
	if (fd < 0)
		goto out_putname;

705 706
	mutex_lock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
	dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name));
L
Linus Torvalds 已提交
707 708 709 710
	if (IS_ERR(dentry)) {
		error = PTR_ERR(dentry);
		goto out_err;
	}
711
	mntget(ipc_ns->mq_mnt);
L
Linus Torvalds 已提交
712 713 714

	if (oflag & O_CREAT) {
		if (dentry->d_inode) {	/* entry already exists */
715
			audit_inode(name, dentry);
716 717 718
			error = -EEXIST;
			if (oflag & O_EXCL)
				goto out;
719
			filp = do_open(ipc_ns, dentry, oflag);
L
Linus Torvalds 已提交
720
		} else {
721 722
			filp = do_create(ipc_ns, ipc_ns->mq_mnt->mnt_root,
						dentry, oflag, mode,
A
Al Viro 已提交
723
						u_attr ? &attr : NULL);
L
Linus Torvalds 已提交
724
		}
725 726 727 728
	} else {
		error = -ENOENT;
		if (!dentry->d_inode)
			goto out;
729
		audit_inode(name, dentry);
730
		filp = do_open(ipc_ns, dentry, oflag);
731
	}
L
Linus Torvalds 已提交
732 733 734 735 736

	if (IS_ERR(filp)) {
		error = PTR_ERR(filp);
		goto out_putfd;
	}
737
	ima_counts_get(filp);
L
Linus Torvalds 已提交
738 739 740 741

	fd_install(fd, filp);
	goto out_upsem;

742 743
out:
	dput(dentry);
744
	mntput(ipc_ns->mq_mnt);
745
out_putfd:
L
Linus Torvalds 已提交
746 747 748 749
	put_unused_fd(fd);
out_err:
	fd = error;
out_upsem:
750
	mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
L
Linus Torvalds 已提交
751 752 753 754 755
out_putname:
	putname(name);
	return fd;
}

756
SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
L
Linus Torvalds 已提交
757 758 759 760 761
{
	int err;
	char *name;
	struct dentry *dentry;
	struct inode *inode = NULL;
762
	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
L
Linus Torvalds 已提交
763 764 765 766 767

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

768
	mutex_lock_nested(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex,
769
			I_MUTEX_PARENT);
770
	dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name));
L
Linus Torvalds 已提交
771 772 773 774 775 776 777 778 779 780 781 782 783
	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);
784
	err = mnt_want_write(ipc_ns->mq_mnt);
785 786
	if (err)
		goto out_err;
L
Linus Torvalds 已提交
787
	err = vfs_unlink(dentry->d_parent->d_inode, dentry);
788
	mnt_drop_write(ipc_ns->mq_mnt);
L
Linus Torvalds 已提交
789 790 791 792
out_err:
	dput(dentry);

out_unlock:
793
	mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
L
Linus Torvalds 已提交
794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810
	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
811
 * ipc/sem.c for more details.
L
Linus Torvalds 已提交
812 813 814 815 816 817 818 819 820 821 822 823 824 825 826
 *
 * 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);
827
	smp_wmb();
L
Linus Torvalds 已提交
828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845
	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);
846
	smp_wmb();
L
Linus Torvalds 已提交
847 848 849
	sender->state = STATE_READY;
}

850 851 852
SYSCALL_DEFINE5(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)
L
Linus Torvalds 已提交
853 854 855 856 857 858 859
{
	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;
A
Al Viro 已提交
860
	struct timespec ts, *p = NULL;
L
Linus Torvalds 已提交
861 862 863
	long timeout;
	int ret;

A
Al Viro 已提交
864 865 866 867 868 869
	if (u_abs_timeout) {
		if (copy_from_user(&ts, u_abs_timeout, 
					sizeof(struct timespec)))
			return -EFAULT;
		p = &ts;
	}
870

L
Linus Torvalds 已提交
871 872 873
	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
		return -EINVAL;

A
Al Viro 已提交
874 875
	audit_mq_sendrecv(mqdes, msg_len, msg_prio, p);
	timeout = prepare_timeout(p);
L
Linus Torvalds 已提交
876 877 878 879 880 881

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

J
Josef Sipek 已提交
882
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
883 884 885
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);
886
	audit_inode(NULL, filp->f_path.dentry);
L
Linus Torvalds 已提交
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

	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;
}

943 944 945
SYSCALL_DEFINE5(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)
L
Linus Torvalds 已提交
946 947 948 949 950 951 952 953
{
	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;
A
Al Viro 已提交
954
	struct timespec ts, *p = NULL;
L
Linus Torvalds 已提交
955

A
Al Viro 已提交
956 957 958 959 960 961
	if (u_abs_timeout) {
		if (copy_from_user(&ts, u_abs_timeout, 
					sizeof(struct timespec)))
			return -EFAULT;
		p = &ts;
	}
962

A
Al Viro 已提交
963 964
	audit_mq_sendrecv(mqdes, msg_len, 0, p);
	timeout = prepare_timeout(p);
L
Linus Torvalds 已提交
965 966 967 968 969 970

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

J
Josef Sipek 已提交
971
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
972 973 974
	if (unlikely(filp->f_op != &mqueue_file_operations))
		goto out_fput;
	info = MQUEUE_I(inode);
975
	audit_inode(NULL, filp->f_path.dentry);
L
Linus Torvalds 已提交
976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032

	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.
 */
1033 1034
SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
		const struct sigevent __user *, u_notification)
L
Linus Torvalds 已提交
1035 1036 1037 1038 1039 1040 1041 1042 1043
{
	int ret;
	struct file *filp;
	struct sock *sock;
	struct inode *inode;
	struct sigevent notification;
	struct mqueue_inode_info *info;
	struct sk_buff *nc;

A
Al Viro 已提交
1044
	if (u_notification) {
L
Linus Torvalds 已提交
1045 1046 1047
		if (copy_from_user(&notification, u_notification,
					sizeof(struct sigevent)))
			return -EFAULT;
A
Al Viro 已提交
1048 1049 1050
	}

	audit_mq_notify(mqdes, u_notification ? &notification : NULL);
L
Linus Torvalds 已提交
1051

A
Al Viro 已提交
1052 1053 1054
	nc = NULL;
	sock = NULL;
	if (u_notification != NULL) {
L
Linus Torvalds 已提交
1055 1056 1057 1058 1059
		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 &&
1060
			!valid_signal(notification.sigev_signo)) {
L
Linus Torvalds 已提交
1061 1062 1063
			return -EINVAL;
		}
		if (notification.sigev_notify == SIGEV_THREAD) {
P
Patrick McHardy 已提交
1064 1065
			long timeo;

L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093
			/* 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;
			}

P
Patrick McHardy 已提交
1094
			timeo = MAX_SCHEDULE_TIMEOUT;
1095
			ret = netlink_attachskb(sock, nc, &timeo, NULL);
L
Linus Torvalds 已提交
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110
			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
1111
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1112 1113 1114 1115 1116 1117 1118
	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) {
1119
		if (info->notify_owner == task_tgid(current)) {
L
Linus Torvalds 已提交
1120 1121 1122
			remove_notification(info);
			inode->i_atime = inode->i_ctime = CURRENT_TIME;
		}
1123
	} else if (info->notify_owner != NULL) {
L
Linus Torvalds 已提交
1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142
		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;
		}
1143 1144

		info->notify_owner = get_pid(task_tgid(current));
L
Linus Torvalds 已提交
1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158
		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;
}

1159 1160 1161
SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
		const struct mq_attr __user *, u_mqstat,
		struct mq_attr __user *, u_omqstat)
L
Linus Torvalds 已提交
1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180
{
	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
1181
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1182 1183 1184 1185 1186 1187 1188 1189 1190
	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) {
A
Al Viro 已提交
1191
		audit_mq_getsetattr(mqdes, &mqstat);
J
Jonathan Corbet 已提交
1192
		spin_lock(&filp->f_lock);
L
Linus Torvalds 已提交
1193 1194 1195 1196
		if (mqstat.mq_flags & O_NONBLOCK)
			filp->f_flags |= O_NONBLOCK;
		else
			filp->f_flags &= ~O_NONBLOCK;
J
Jonathan Corbet 已提交
1197
		spin_unlock(&filp->f_lock);
L
Linus Torvalds 已提交
1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214

		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;
}

1215
static const struct inode_operations mqueue_dir_inode_operations = {
L
Linus Torvalds 已提交
1216 1217 1218 1219 1220
	.lookup = simple_lookup,
	.create = mqueue_create,
	.unlink = mqueue_unlink,
};

1221
static const struct file_operations mqueue_file_operations = {
L
Linus Torvalds 已提交
1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
	.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,
};

1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
int mq_init_ns(struct ipc_namespace *ns)
{
	ns->mq_queues_count  = 0;
	ns->mq_queues_max    = DFLT_QUEUESMAX;
	ns->mq_msg_max       = DFLT_MSGMAX;
	ns->mq_msgsize_max   = DFLT_MSGSIZEMAX;

	ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns);
	if (IS_ERR(ns->mq_mnt)) {
		int err = PTR_ERR(ns->mq_mnt);
		ns->mq_mnt = NULL;
		return err;
	}
	return 0;
}

void mq_clear_sbinfo(struct ipc_namespace *ns)
{
	ns->mq_mnt->mnt_sb->s_fs_info = NULL;
}

void mq_put_mnt(struct ipc_namespace *ns)
{
	mntput(ns->mq_mnt);
}

L
Linus Torvalds 已提交
1267 1268 1269 1270 1271 1272
static int __init init_mqueue_fs(void)
{
	int error;

	mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
				sizeof(struct mqueue_inode_info), 0,
1273
				SLAB_HWCACHE_ALIGN, init_once);
L
Linus Torvalds 已提交
1274 1275 1276 1277
	if (mqueue_inode_cachep == NULL)
		return -ENOMEM;

	/* ignore failues - they are not fatal */
1278
	mq_sysctl_table = mq_register_sysctl_table();
L
Linus Torvalds 已提交
1279 1280 1281 1282 1283

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

1284 1285 1286
	spin_lock_init(&mq_lock);

	init_ipc_ns.mq_mnt = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
1287 1288
	if (IS_ERR(init_ipc_ns.mq_mnt)) {
		error = PTR_ERR(init_ipc_ns.mq_mnt);
L
Linus Torvalds 已提交
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
		goto out_filesystem;
	}

	return 0;

out_filesystem:
	unregister_filesystem(&mqueue_fs_type);
out_sysctl:
	if (mq_sysctl_table)
		unregister_sysctl_table(mq_sysctl_table);
1299
	kmem_cache_destroy(mqueue_inode_cachep);
L
Linus Torvalds 已提交
1300 1301 1302 1303
	return error;
}

__initcall(init_mqueue_fs);