msg.c 18.6 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * linux/ipc/msg.c
 * Copyright (C) 1992 Krishna Balasubramanian 
 *
 * Removed all the remaining kerneld mess
 * Catch the -EFAULT stuff properly
 * Use GFP_KERNEL for messages as in 1.2
 * Fixed up the unchecked user space derefs
 * Copyright (C) 1998 Alan Cox & Andi Kleen
 *
 * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
 *
 * mostly rewritten, threaded and wake-one semantics added
 * MSGMAX limit removed, sysctl's added
15
 * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
S
Steve Grubb 已提交
16 17 18
 *
 * support for audit of ipc object properties and permission changes
 * Dustin Kirkland <dustin.kirkland@us.ibm.com>
L
Linus Torvalds 已提交
19 20
 */

21
#include <linux/capability.h>
L
Linus Torvalds 已提交
22 23 24 25 26 27 28 29 30 31 32
#include <linux/config.h>
#include <linux/slab.h>
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/list.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
33
#include <linux/seq_file.h>
I
Ingo Molnar 已提交
34 35
#include <linux/mutex.h>

L
Linus Torvalds 已提交
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
#include <asm/current.h>
#include <asm/uaccess.h>
#include "util.h"

/* sysctl: */
int msg_ctlmax = MSGMAX;
int msg_ctlmnb = MSGMNB;
int msg_ctlmni = MSGMNI;

/* one msg_receiver structure for each sleeping receiver */
struct msg_receiver {
	struct list_head r_list;
	struct task_struct* r_tsk;

	int r_mode;
	long r_msgtype;
	long r_maxsize;

	struct msg_msg* volatile r_msg;
};

/* one msg_sender for each sleeping sender */
struct msg_sender {
	struct list_head list;
	struct task_struct* tsk;
};

#define SEARCH_ANY		1
#define SEARCH_EQUAL		2
#define SEARCH_NOTEQUAL		3
#define SEARCH_LESSEQUAL	4

static atomic_t msg_bytes = ATOMIC_INIT(0);
static atomic_t msg_hdrs = ATOMIC_INIT(0);

static struct ipc_ids msg_ids;

#define msg_lock(id)	((struct msg_queue*)ipc_lock(&msg_ids,id))
#define msg_unlock(msq)	ipc_unlock(&(msq)->q_perm)
#define msg_rmid(id)	((struct msg_queue*)ipc_rmid(&msg_ids,id))
#define msg_checkid(msq, msgid)	\
	ipc_checkid(&msg_ids,&msq->q_perm,msgid)
#define msg_buildid(id, seq) \
	ipc_buildid(&msg_ids, id, seq)

static void freeque (struct msg_queue *msq, int id);
static int newque (key_t key, int msgflg);
#ifdef CONFIG_PROC_FS
84
static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
L
Linus Torvalds 已提交
85 86 87 88 89
#endif

void __init msg_init (void)
{
	ipc_init_ids(&msg_ids,msg_ctlmni);
90 91 92 93
	ipc_init_proc_interface("sysvipc/msg",
				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
				&msg_ids,
				sysvipc_msg_proc_show);
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
}

static int newque (key_t key, int msgflg)
{
	int id;
	int retval;
	struct msg_queue *msq;

	msq  = ipc_rcu_alloc(sizeof(*msq));
	if (!msq) 
		return -ENOMEM;

	msq->q_perm.mode = (msgflg & S_IRWXUGO);
	msq->q_perm.key = key;

	msq->q_perm.security = NULL;
	retval = security_msg_queue_alloc(msq);
	if (retval) {
		ipc_rcu_putref(msq);
		return retval;
	}

	id = ipc_addid(&msg_ids, &msq->q_perm, msg_ctlmni);
	if(id == -1) {
		security_msg_queue_free(msq);
		ipc_rcu_putref(msq);
		return -ENOSPC;
	}

123
	msq->q_id = msg_buildid(id,msq->q_perm.seq);
L
Linus Torvalds 已提交
124 125 126 127 128 129 130 131 132 133
	msq->q_stime = msq->q_rtime = 0;
	msq->q_ctime = get_seconds();
	msq->q_cbytes = msq->q_qnum = 0;
	msq->q_qbytes = msg_ctlmnb;
	msq->q_lspid = msq->q_lrpid = 0;
	INIT_LIST_HEAD(&msq->q_messages);
	INIT_LIST_HEAD(&msq->q_receivers);
	INIT_LIST_HEAD(&msq->q_senders);
	msg_unlock(msq);

134
	return msq->q_id;
L
Linus Torvalds 已提交
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
}

static inline void ss_add(struct msg_queue* msq, struct msg_sender* mss)
{
	mss->tsk=current;
	current->state=TASK_INTERRUPTIBLE;
	list_add_tail(&mss->list,&msq->q_senders);
}

static inline void ss_del(struct msg_sender* mss)
{
	if(mss->list.next != NULL)
		list_del(&mss->list);
}

static void ss_wakeup(struct list_head* h, int kill)
{
	struct list_head *tmp;

	tmp = h->next;
	while (tmp != h) {
		struct msg_sender* mss;
		
		mss = list_entry(tmp,struct msg_sender,list);
		tmp = tmp->next;
		if(kill)
			mss->list.next=NULL;
		wake_up_process(mss->tsk);
	}
}

static void expunge_all(struct msg_queue* msq, int res)
{
	struct list_head *tmp;

	tmp = msq->q_receivers.next;
	while (tmp != &msq->q_receivers) {
		struct msg_receiver* msr;
		
		msr = list_entry(tmp,struct msg_receiver,r_list);
		tmp = tmp->next;
		msr->r_msg = NULL;
		wake_up_process(msr->r_tsk);
		smp_mb();
		msr->r_msg = ERR_PTR(res);
	}
}
/* 
 * freeque() wakes up waiters on the sender and receiver waiting queue, 
 * removes the message queue from message queue ID 
 * array, and cleans up all the messages associated with this queue.
 *
I
Ingo Molnar 已提交
187 188
 * msg_ids.mutex and the spinlock for this message queue is hold
 * before freeque() is called. msg_ids.mutex remains locked on exit.
L
Linus Torvalds 已提交
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
 */
static void freeque (struct msg_queue *msq, int id)
{
	struct list_head *tmp;

	expunge_all(msq,-EIDRM);
	ss_wakeup(&msq->q_senders,1);
	msq = msg_rmid(id);
	msg_unlock(msq);
		
	tmp = msq->q_messages.next;
	while(tmp != &msq->q_messages) {
		struct msg_msg* msg = list_entry(tmp,struct msg_msg,m_list);
		tmp = tmp->next;
		atomic_dec(&msg_hdrs);
		free_msg(msg);
	}
	atomic_sub(msq->q_cbytes, &msg_bytes);
	security_msg_queue_free(msq);
	ipc_rcu_putref(msq);
}

asmlinkage long sys_msgget (key_t key, int msgflg)
{
	int id, ret = -EPERM;
	struct msg_queue *msq;
	
I
Ingo Molnar 已提交
216
	mutex_lock(&msg_ids.mutex);
L
Linus Torvalds 已提交
217 218 219 220 221 222 223 224 225 226 227
	if (key == IPC_PRIVATE) 
		ret = newque(key, msgflg);
	else if ((id = ipc_findkey(&msg_ids, key)) == -1) { /* key not used */
		if (!(msgflg & IPC_CREAT))
			ret = -ENOENT;
		else
			ret = newque(key, msgflg);
	} else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) {
		ret = -EEXIST;
	} else {
		msq = msg_lock(id);
228
		BUG_ON(msq==NULL);
L
Linus Torvalds 已提交
229 230 231 232 233 234 235 236 237 238
		if (ipcperms(&msq->q_perm, msgflg))
			ret = -EACCES;
		else {
			int qid = msg_buildid(id, msq->q_perm.seq);
		    	ret = security_msg_queue_associate(msq, msgflg);
			if (!ret)
				ret = qid;
		}
		msg_unlock(msq);
	}
I
Ingo Molnar 已提交
239
	mutex_unlock(&msg_ids.mutex);
L
Linus Torvalds 已提交
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
	return ret;
}

static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
{
	switch(version) {
	case IPC_64:
		return copy_to_user (buf, in, sizeof(*in));
	case IPC_OLD:
	    {
		struct msqid_ds out;

		memset(&out,0,sizeof(out));

		ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm);

		out.msg_stime		= in->msg_stime;
		out.msg_rtime		= in->msg_rtime;
		out.msg_ctime		= in->msg_ctime;

		if(in->msg_cbytes > USHRT_MAX)
			out.msg_cbytes	= USHRT_MAX;
		else
			out.msg_cbytes	= in->msg_cbytes;
		out.msg_lcbytes		= in->msg_cbytes;

		if(in->msg_qnum > USHRT_MAX)
			out.msg_qnum	= USHRT_MAX;
		else
			out.msg_qnum	= in->msg_qnum;

		if(in->msg_qbytes > USHRT_MAX)
			out.msg_qbytes	= USHRT_MAX;
		else
			out.msg_qbytes	= in->msg_qbytes;
		out.msg_lqbytes		= in->msg_qbytes;

		out.msg_lspid		= in->msg_lspid;
		out.msg_lrpid		= in->msg_lrpid;

		return copy_to_user (buf, &out, sizeof(out));
	    }
	default:
		return -EINVAL;
	}
}

struct msq_setbuf {
	unsigned long	qbytes;
	uid_t		uid;
	gid_t		gid;
	mode_t		mode;
};

static inline unsigned long copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version)
{
	switch(version) {
	case IPC_64:
	    {
		struct msqid64_ds tbuf;

		if (copy_from_user (&tbuf, buf, sizeof (tbuf)))
			return -EFAULT;

		out->qbytes		= tbuf.msg_qbytes;
		out->uid		= tbuf.msg_perm.uid;
		out->gid		= tbuf.msg_perm.gid;
		out->mode		= tbuf.msg_perm.mode;

		return 0;
	    }
	case IPC_OLD:
	    {
		struct msqid_ds tbuf_old;

		if (copy_from_user (&tbuf_old, buf, sizeof (tbuf_old)))
			return -EFAULT;

		out->uid		= tbuf_old.msg_perm.uid;
		out->gid		= tbuf_old.msg_perm.gid;
		out->mode		= tbuf_old.msg_perm.mode;

		if(tbuf_old.msg_qbytes == 0)
			out->qbytes	= tbuf_old.msg_lqbytes;
		else
			out->qbytes	= tbuf_old.msg_qbytes;

		return 0;
	    }
	default:
		return -EINVAL;
	}
}

asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf)
{
	int err, version;
	struct msg_queue *msq;
	struct msq_setbuf setbuf;
	struct kern_ipc_perm *ipcp;
	
	if (msqid < 0 || cmd < 0)
		return -EINVAL;

	version = ipc_parse_version(&cmd);

	switch (cmd) {
	case IPC_INFO: 
	case MSG_INFO: 
	{ 
		struct msginfo msginfo;
		int max_id;
		if (!buf)
			return -EFAULT;
		/* We must not return kernel stack data.
		 * due to padding, it's not enough
		 * to set all member fields.
		 */

		err = security_msg_queue_msgctl(NULL, cmd);
		if (err)
			return err;

		memset(&msginfo,0,sizeof(msginfo));	
		msginfo.msgmni = msg_ctlmni;
		msginfo.msgmax = msg_ctlmax;
		msginfo.msgmnb = msg_ctlmnb;
		msginfo.msgssz = MSGSSZ;
		msginfo.msgseg = MSGSEG;
I
Ingo Molnar 已提交
369
		mutex_lock(&msg_ids.mutex);
L
Linus Torvalds 已提交
370 371 372 373 374 375 376 377 378 379
		if (cmd == MSG_INFO) {
			msginfo.msgpool = msg_ids.in_use;
			msginfo.msgmap = atomic_read(&msg_hdrs);
			msginfo.msgtql = atomic_read(&msg_bytes);
		} else {
			msginfo.msgmap = MSGMAP;
			msginfo.msgpool = MSGPOOL;
			msginfo.msgtql = MSGTQL;
		}
		max_id = msg_ids.max_id;
I
Ingo Molnar 已提交
380
		mutex_unlock(&msg_ids.mutex);
L
Linus Torvalds 已提交
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
		if (copy_to_user (buf, &msginfo, sizeof(struct msginfo)))
			return -EFAULT;
		return (max_id < 0) ? 0: max_id;
	}
	case MSG_STAT:
	case IPC_STAT:
	{
		struct msqid64_ds tbuf;
		int success_return;
		if (!buf)
			return -EFAULT;
		if(cmd == MSG_STAT && msqid >= msg_ids.entries->size)
			return -EINVAL;

		memset(&tbuf,0,sizeof(tbuf));

		msq = msg_lock(msqid);
		if (msq == NULL)
			return -EINVAL;

		if(cmd == MSG_STAT) {
			success_return = msg_buildid(msqid, msq->q_perm.seq);
		} else {
			err = -EIDRM;
			if (msg_checkid(msq,msqid))
				goto out_unlock;
			success_return = 0;
		}
		err = -EACCES;
		if (ipcperms (&msq->q_perm, S_IRUGO))
			goto out_unlock;

		err = security_msg_queue_msgctl(msq, cmd);
		if (err)
			goto out_unlock;

		kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
		tbuf.msg_stime  = msq->q_stime;
		tbuf.msg_rtime  = msq->q_rtime;
		tbuf.msg_ctime  = msq->q_ctime;
		tbuf.msg_cbytes = msq->q_cbytes;
		tbuf.msg_qnum   = msq->q_qnum;
		tbuf.msg_qbytes = msq->q_qbytes;
		tbuf.msg_lspid  = msq->q_lspid;
		tbuf.msg_lrpid  = msq->q_lrpid;
		msg_unlock(msq);
		if (copy_msqid_to_user(buf, &tbuf, version))
			return -EFAULT;
		return success_return;
	}
	case IPC_SET:
		if (!buf)
			return -EFAULT;
		if (copy_msqid_from_user (&setbuf, buf, version))
			return -EFAULT;
		break;
	case IPC_RMID:
		break;
	default:
		return  -EINVAL;
	}

I
Ingo Molnar 已提交
443
	mutex_lock(&msg_ids.mutex);
L
Linus Torvalds 已提交
444 445 446 447 448 449 450 451 452
	msq = msg_lock(msqid);
	err=-EINVAL;
	if (msq == NULL)
		goto out_up;

	err = -EIDRM;
	if (msg_checkid(msq,msqid))
		goto out_unlock_up;
	ipcp = &msq->q_perm;
S
Steve Grubb 已提交
453 454 455 456 457

	err = audit_ipc_obj(ipcp);
	if (err)
		goto out_unlock_up;

L
Linus Torvalds 已提交
458 459 460 461 462 463 464 465 466 467 468 469 470
	err = -EPERM;
	if (current->euid != ipcp->cuid && 
	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN))
	    /* We _could_ check for CAP_CHOWN above, but we don't */
		goto out_unlock_up;

	err = security_msg_queue_msgctl(msq, cmd);
	if (err)
		goto out_unlock_up;

	switch (cmd) {
	case IPC_SET:
	{
S
Steve Grubb 已提交
471 472
		err = audit_ipc_set_perm(setbuf.qbytes, setbuf.uid, setbuf.gid, setbuf.mode, ipcp);
		if (err)
473 474
			goto out_unlock_up;

L
Linus Torvalds 已提交
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
		err = -EPERM;
		if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE))
			goto out_unlock_up;

		msq->q_qbytes = setbuf.qbytes;

		ipcp->uid = setbuf.uid;
		ipcp->gid = setbuf.gid;
		ipcp->mode = (ipcp->mode & ~S_IRWXUGO) | 
			(S_IRWXUGO & setbuf.mode);
		msq->q_ctime = get_seconds();
		/* sleeping receivers might be excluded by
		 * stricter permissions.
		 */
		expunge_all(msq,-EAGAIN);
		/* sleeping senders might be able to send
		 * due to a larger queue size.
		 */
		ss_wakeup(&msq->q_senders,0);
		msg_unlock(msq);
		break;
	}
	case IPC_RMID:
		freeque (msq, msqid); 
		break;
	}
	err = 0;
out_up:
I
Ingo Molnar 已提交
503
	mutex_unlock(&msg_ids.mutex);
L
Linus Torvalds 已提交
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824
	return err;
out_unlock_up:
	msg_unlock(msq);
	goto out_up;
out_unlock:
	msg_unlock(msq);
	return err;
}

static int testmsg(struct msg_msg* msg,long type,int mode)
{
	switch(mode)
	{
		case SEARCH_ANY:
			return 1;
		case SEARCH_LESSEQUAL:
			if(msg->m_type <=type)
				return 1;
			break;
		case SEARCH_EQUAL:
			if(msg->m_type == type)
				return 1;
			break;
		case SEARCH_NOTEQUAL:
			if(msg->m_type != type)
				return 1;
			break;
	}
	return 0;
}

static inline int pipelined_send(struct msg_queue* msq, struct msg_msg* msg)
{
	struct list_head* tmp;

	tmp = msq->q_receivers.next;
	while (tmp != &msq->q_receivers) {
		struct msg_receiver* msr;
		msr = list_entry(tmp,struct msg_receiver,r_list);
		tmp = tmp->next;
		if(testmsg(msg,msr->r_msgtype,msr->r_mode) &&
		   !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) {
			list_del(&msr->r_list);
			if(msr->r_maxsize < msg->m_ts) {
				msr->r_msg = NULL;
				wake_up_process(msr->r_tsk);
				smp_mb();
				msr->r_msg = ERR_PTR(-E2BIG);
			} else {
				msr->r_msg = NULL;
				msq->q_lrpid = msr->r_tsk->pid;
				msq->q_rtime = get_seconds();
				wake_up_process(msr->r_tsk);
				smp_mb();
				msr->r_msg = msg;
				return 1;
			}
		}
	}
	return 0;
}

asmlinkage long sys_msgsnd (int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg)
{
	struct msg_queue *msq;
	struct msg_msg *msg;
	long mtype;
	int err;
	
	if (msgsz > msg_ctlmax || (long) msgsz < 0 || msqid < 0)
		return -EINVAL;
	if (get_user(mtype, &msgp->mtype))
		return -EFAULT; 
	if (mtype < 1)
		return -EINVAL;

	msg = load_msg(msgp->mtext, msgsz);
	if(IS_ERR(msg))
		return PTR_ERR(msg);

	msg->m_type = mtype;
	msg->m_ts = msgsz;

	msq = msg_lock(msqid);
	err=-EINVAL;
	if(msq==NULL)
		goto out_free;

	err= -EIDRM;
	if (msg_checkid(msq,msqid))
		goto out_unlock_free;

	for (;;) {
		struct msg_sender s;

		err=-EACCES;
		if (ipcperms(&msq->q_perm, S_IWUGO))
			goto out_unlock_free;

		err = security_msg_queue_msgsnd(msq, msg, msgflg);
		if (err)
			goto out_unlock_free;

		if(msgsz + msq->q_cbytes <= msq->q_qbytes &&
				1 + msq->q_qnum <= msq->q_qbytes) {
			break;
		}

		/* queue full, wait: */
		if(msgflg&IPC_NOWAIT) {
			err=-EAGAIN;
			goto out_unlock_free;
		}
		ss_add(msq, &s);
		ipc_rcu_getref(msq);
		msg_unlock(msq);
		schedule();

		ipc_lock_by_ptr(&msq->q_perm);
		ipc_rcu_putref(msq);
		if (msq->q_perm.deleted) {
			err = -EIDRM;
			goto out_unlock_free;
		}
		ss_del(&s);
		
		if (signal_pending(current)) {
			err=-ERESTARTNOHAND;
			goto out_unlock_free;
		}
	}

	msq->q_lspid = current->tgid;
	msq->q_stime = get_seconds();

	if(!pipelined_send(msq,msg)) {
		/* noone is waiting for this message, enqueue it */
		list_add_tail(&msg->m_list,&msq->q_messages);
		msq->q_cbytes += msgsz;
		msq->q_qnum++;
		atomic_add(msgsz,&msg_bytes);
		atomic_inc(&msg_hdrs);
	}
	
	err = 0;
	msg = NULL;

out_unlock_free:
	msg_unlock(msq);
out_free:
	if(msg!=NULL)
		free_msg(msg);
	return err;
}

static inline int convert_mode(long* msgtyp, int msgflg)
{
	/* 
	 *  find message of correct type.
	 *  msgtyp = 0 => get first.
	 *  msgtyp > 0 => get first message of matching type.
	 *  msgtyp < 0 => get message with least type must be < abs(msgtype).  
	 */
	if(*msgtyp==0)
		return SEARCH_ANY;
	if(*msgtyp<0) {
		*msgtyp=-(*msgtyp);
		return SEARCH_LESSEQUAL;
	}
	if(msgflg & MSG_EXCEPT)
		return SEARCH_NOTEQUAL;
	return SEARCH_EQUAL;
}

asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz,
			    long msgtyp, int msgflg)
{
	struct msg_queue *msq;
	struct msg_msg *msg;
	int mode;

	if (msqid < 0 || (long) msgsz < 0)
		return -EINVAL;
	mode = convert_mode(&msgtyp,msgflg);

	msq = msg_lock(msqid);
	if(msq==NULL)
		return -EINVAL;

	msg = ERR_PTR(-EIDRM);
	if (msg_checkid(msq,msqid))
		goto out_unlock;

	for (;;) {
		struct msg_receiver msr_d;
		struct list_head* tmp;

		msg = ERR_PTR(-EACCES);
		if (ipcperms (&msq->q_perm, S_IRUGO))
			goto out_unlock;

		msg = ERR_PTR(-EAGAIN);
		tmp = msq->q_messages.next;
		while (tmp != &msq->q_messages) {
			struct msg_msg *walk_msg;
			walk_msg = list_entry(tmp,struct msg_msg,m_list);
			if(testmsg(walk_msg,msgtyp,mode) &&
			   !security_msg_queue_msgrcv(msq, walk_msg, current, msgtyp, mode)) {
				msg = walk_msg;
				if(mode == SEARCH_LESSEQUAL && walk_msg->m_type != 1) {
					msg=walk_msg;
					msgtyp=walk_msg->m_type-1;
				} else {
					msg=walk_msg;
					break;
				}
			}
			tmp = tmp->next;
		}
		if(!IS_ERR(msg)) {
			/* Found a suitable message. Unlink it from the queue. */
			if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
				msg = ERR_PTR(-E2BIG);
				goto out_unlock;
			}
			list_del(&msg->m_list);
			msq->q_qnum--;
			msq->q_rtime = get_seconds();
			msq->q_lrpid = current->tgid;
			msq->q_cbytes -= msg->m_ts;
			atomic_sub(msg->m_ts,&msg_bytes);
			atomic_dec(&msg_hdrs);
			ss_wakeup(&msq->q_senders,0);
			msg_unlock(msq);
			break;
		}
		/* No message waiting. Wait for a message */
		if (msgflg & IPC_NOWAIT) {
			msg = ERR_PTR(-ENOMSG);
			goto out_unlock;
		}
		list_add_tail(&msr_d.r_list,&msq->q_receivers);
		msr_d.r_tsk = current;
		msr_d.r_msgtype = msgtyp;
		msr_d.r_mode = mode;
		if(msgflg & MSG_NOERROR)
			msr_d.r_maxsize = INT_MAX;
		 else
			msr_d.r_maxsize = msgsz;
		msr_d.r_msg = ERR_PTR(-EAGAIN);
		current->state = TASK_INTERRUPTIBLE;
		msg_unlock(msq);

		schedule();

		/* Lockless receive, part 1:
		 * Disable preemption.  We don't hold a reference to the queue
		 * and getting a reference would defeat the idea of a lockless
		 * operation, thus the code relies on rcu to guarantee the
		 * existance of msq:
		 * Prior to destruction, expunge_all(-EIRDM) changes r_msg.
		 * Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
		 * rcu_read_lock() prevents preemption between reading r_msg
		 * and the spin_lock() inside ipc_lock_by_ptr().
		 */
		rcu_read_lock();

		/* Lockless receive, part 2:
		 * Wait until pipelined_send or expunge_all are outside of
		 * wake_up_process(). There is a race with exit(), see
		 * ipc/mqueue.c for the details.
		 */
		msg = (struct msg_msg*) msr_d.r_msg;
		while (msg == NULL) {
			cpu_relax();
			msg = (struct msg_msg*) msr_d.r_msg;
		}

		/* Lockless receive, part 3:
		 * If there is a message or an error then accept it without
		 * locking.
		 */
		if(msg != ERR_PTR(-EAGAIN)) {
			rcu_read_unlock();
			break;
		}

		/* Lockless receive, part 3:
		 * Acquire the queue spinlock.
		 */
		ipc_lock_by_ptr(&msq->q_perm);
		rcu_read_unlock();

		/* Lockless receive, part 4:
		 * Repeat test after acquiring the spinlock.
		 */
		msg = (struct msg_msg*)msr_d.r_msg;
		if(msg != ERR_PTR(-EAGAIN))
			goto out_unlock;

		list_del(&msr_d.r_list);
		if (signal_pending(current)) {
			msg = ERR_PTR(-ERESTARTNOHAND);
out_unlock:
			msg_unlock(msq);
			break;
		}
	}
	if (IS_ERR(msg))
       		return PTR_ERR(msg);

	msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
	if (put_user (msg->m_type, &msgp->mtype) ||
	    store_msg(msgp->mtext, msg, msgsz)) {
		    msgsz = -EFAULT;
	}
	free_msg(msg);
	return msgsz;
}

#ifdef CONFIG_PROC_FS
825
static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
L
Linus Torvalds 已提交
826
{
827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844
	struct msg_queue *msq = it;

	return seq_printf(s,
			  "%10d %10d  %4o  %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n",
			  msq->q_perm.key,
			  msq->q_id,
			  msq->q_perm.mode,
			  msq->q_cbytes,
			  msq->q_qnum,
			  msq->q_lspid,
			  msq->q_lrpid,
			  msq->q_perm.uid,
			  msq->q_perm.gid,
			  msq->q_perm.cuid,
			  msq->q_perm.cgid,
			  msq->q_stime,
			  msq->q_rtime,
			  msq->q_ctime);
L
Linus Torvalds 已提交
845 846
}
#endif