summaryrefslogtreecommitdiff
path: root/ipc/msg.c
blob: a3c0dc40a0cf31fe489af987ebcc1b6ee00de407 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
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
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
369
370
371
372
373
374
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
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
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
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
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
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
/*
 * 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
 * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
 *
 * support for audit of ipc object properties and permission changes
 * Dustin Kirkland <dustin.kirkland@us.ibm.com>
 *
 * namespaces support
 * OpenVZ, SWsoft Inc.
 * Pavel Emelianov <xemul@openvz.org>
 */

#include <linux/capability.h>
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/mm.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>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>

#include <asm/current.h>
#include <asm/uaccess.h>
#include "util.h"

/*
 * 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
#define SEARCH_NUMBER		5

#define msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])

#define msg_unlock(msq)		ipc_unlock(&(msq)->q_perm)

static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
static int newque(struct ipc_namespace *, struct ipc_params *);
#ifdef CONFIG_PROC_FS
static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
#endif

/*
 * Scale msgmni with the available lowmem size: the memory dedicated to msg
 * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
 * Also take into account the number of nsproxies created so far.
 * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
 */
void recompute_msgmni(struct ipc_namespace *ns)
{
	struct sysinfo i;
	unsigned long allowed;
	int nb_ns;

	si_meminfo(&i);
	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
		/ MSGMNB;
	nb_ns = atomic_read(&nr_ipc_ns);
	allowed /= nb_ns;

	if (allowed < MSGMNI) {
		ns->msg_ctlmni = MSGMNI;
		return;
	}

	if (allowed > IPCMNI / nb_ns) {
		ns->msg_ctlmni = IPCMNI / nb_ns;
		return;
	}

	ns->msg_ctlmni = allowed;
}

void msg_init_ns(struct ipc_namespace *ns)
{
	ns->msg_ctlmax = MSGMAX;
	ns->msg_ctlmnb = MSGMNB;

	recompute_msgmni(ns);

	atomic_set(&ns->msg_bytes, 0);
	atomic_set(&ns->msg_hdrs, 0);
	ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
}

#ifdef CONFIG_IPC_NS
void msg_exit_ns(struct ipc_namespace *ns)
{
	free_ipcs(ns, &msg_ids(ns), freeque);
	idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
}
#endif

void __init msg_init(void)
{
	msg_init_ns(&init_ipc_ns);

	printk(KERN_INFO "msgmni has been set to %d\n",
		init_ipc_ns.msg_ctlmni);

	ipc_init_proc_interface("sysvipc/msg",
				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
				IPC_MSG_IDS, sysvipc_msg_proc_show);
}

/*
 * msg_lock_(check_) routines are called in the paths where the rw_mutex
 * is not held.
 */
static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);

	if (IS_ERR(ipcp))
		return (struct msg_queue *)ipcp;

	return container_of(ipcp, struct msg_queue, q_perm);
}

static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
						int id)
{
	struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);

	if (IS_ERR(ipcp))
		return (struct msg_queue *)ipcp;

	return container_of(ipcp, struct msg_queue, q_perm);
}

static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct msg_queue, q_perm);
}

static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
							int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct msg_queue, q_perm);
}

static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
{
	ipc_rmid(&msg_ids(ns), &s->q_perm);
}

/**
 * newque - Create a new msg queue
 * @ns: namespace
 * @params: ptr to the structure that contains the key and msgflg
 *
 * Called with msg_ids.rw_mutex held (writer)
 */
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
	struct msg_queue *msq;
	int id, retval;
	key_t key = params->key;
	int msgflg = params->flg;

	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;
	}

	/* ipc_addid() locks msq upon success. */
	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
	if (id < 0) {
		security_msg_queue_free(msq);
		ipc_rcu_putref(msq);
		return id;
	}

	msq->q_stime = msq->q_rtime = 0;
	msq->q_ctime = get_seconds();
	msq->q_cbytes = msq->q_qnum = 0;
	msq->q_qbytes = ns->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);

	ipc_unlock_object(&msq->q_perm);
	rcu_read_unlock();

	return msq->q_perm.id;
}

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 msg_sender *mss, *t;

	list_for_each_entry_safe(mss, t, h, list) {
		if (kill)
			mss->list.next = NULL;
		wake_up_process(mss->tsk);
	}
}

static void expunge_all(struct msg_queue *msq, int res)
{
	struct msg_receiver *msr, *t;

	list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
		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 IDR, and cleans up all the
 * messages associated with this queue.
 *
 * msg_ids.rw_mutex (writer) and the spinlock for this message queue are held
 * before freeque() is called. msg_ids.rw_mutex remains locked on exit.
 */
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
	struct msg_msg *msg, *t;
	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);

	expunge_all(msq, -EIDRM);
	ss_wakeup(&msq->q_senders, 1);
	msg_rmid(ns, msq);
	msg_unlock(msq);

	list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
		atomic_dec(&ns->msg_hdrs);
		free_msg(msg);
	}
	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
	security_msg_queue_free(msq);
	ipc_rcu_putref(msq);
}

/*
 * Called with msg_ids.rw_mutex and ipcp locked.
 */
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);

	return security_msg_queue_associate(msq, msgflg);
}

SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
{
	struct ipc_namespace *ns;
	struct ipc_ops msg_ops;
	struct ipc_params msg_params;

	ns = current->nsproxy->ipc_ns;

	msg_ops.getnew = newque;
	msg_ops.associate = msg_security;
	msg_ops.more_checks = NULL;

	msg_params.key = key;
	msg_params.flg = msgflg;

	return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params);
}

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;
	}
}

static inline unsigned long
copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
{
	switch(version) {
	case IPC_64:
		if (copy_from_user(out, buf, sizeof(*out)))
			return -EFAULT;
		return 0;
	case IPC_OLD:
	{
		struct msqid_ds tbuf_old;

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

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

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

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

/*
 * This function handles some msgctl commands which require the rw_mutex
 * to be held in write mode.
 * NOTE: no locks must be held, the rw_mutex is taken inside this function.
 */
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
		       struct msqid_ds __user *buf, int version)
{
	struct kern_ipc_perm *ipcp;
	struct msqid64_ds uninitialized_var(msqid64);
	struct msg_queue *msq;
	int err;

	if (cmd == IPC_SET) {
		if (copy_msqid_from_user(&msqid64, buf, version))
			return -EFAULT;
	}

	down_write(&msg_ids(ns).rw_mutex);
	rcu_read_lock();

	ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
				      &msqid64.msg_perm, msqid64.msg_qbytes);
	if (IS_ERR(ipcp)) {
		err = PTR_ERR(ipcp);
		goto out_unlock1;
	}

	msq = container_of(ipcp, struct msg_queue, q_perm);

	err = security_msg_queue_msgctl(msq, cmd);
	if (err)
		goto out_unlock1;

	switch (cmd) {
	case IPC_RMID:
		ipc_lock_object(&msq->q_perm);
		/* freeque unlocks the ipc object and rcu */
		freeque(ns, ipcp);
		goto out_up;
	case IPC_SET:
		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
		    !capable(CAP_SYS_RESOURCE)) {
			err = -EPERM;
			goto out_unlock1;
		}

		ipc_lock_object(&msq->q_perm);
		err = ipc_update_perm(&msqid64.msg_perm, ipcp);
		if (err)
			goto out_unlock0;

		msq->q_qbytes = msqid64.msg_qbytes;

		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);
		break;
	default:
		err = -EINVAL;
		goto out_unlock1;
	}

out_unlock0:
	ipc_unlock_object(&msq->q_perm);
out_unlock1:
	rcu_read_unlock();
out_up:
	up_write(&msg_ids(ns).rw_mutex);
	return err;
}

static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
			 int cmd, int version, void __user *buf)
{
	int err;
	struct msg_queue *msq;

	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 = ns->msg_ctlmni;
		msginfo.msgmax = ns->msg_ctlmax;
		msginfo.msgmnb = ns->msg_ctlmnb;
		msginfo.msgssz = MSGSSZ;
		msginfo.msgseg = MSGSEG;
		down_read(&msg_ids(ns).rw_mutex);
		if (cmd == MSG_INFO) {
			msginfo.msgpool = msg_ids(ns).in_use;
			msginfo.msgmap = atomic_read(&ns->msg_hdrs);
			msginfo.msgtql = atomic_read(&ns->msg_bytes);
		} else {
			msginfo.msgmap = MSGMAP;
			msginfo.msgpool = MSGPOOL;
			msginfo.msgtql = MSGTQL;
		}
		max_id = ipc_get_maxid(&msg_ids(ns));
		up_read(&msg_ids(ns).rw_mutex);
		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;

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

		rcu_read_lock();
		if (cmd == MSG_STAT) {
			msq = msq_obtain_object(ns, msqid);
			if (IS_ERR(msq)) {
				err = PTR_ERR(msq);
				goto out_unlock;
			}
			success_return = msq->q_perm.id;
		} else {
			msq = msq_obtain_object_check(ns, msqid);
			if (IS_ERR(msq)) {
				err = PTR_ERR(msq);
				goto out_unlock;
			}
			success_return = 0;
		}

		err = -EACCES;
		if (ipcperms(ns, &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;
		rcu_read_unlock();

		if (copy_msqid_to_user(buf, &tbuf, version))
			return -EFAULT;
		return success_return;
	}

	default:
		return -EINVAL;
	}

	return err;
out_unlock:
	rcu_read_unlock();
	return err;
}

SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
{
	int version;
	struct ipc_namespace *ns;

	if (msqid < 0 || cmd < 0)
		return -EINVAL;

	version = ipc_parse_version(&cmd);
	ns = current->nsproxy->ipc_ns;

	switch (cmd) {
	case IPC_INFO:
	case MSG_INFO:
	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
	case IPC_STAT:
		return msgctl_nolock(ns, msqid, cmd, version, buf);
	case IPC_SET:
	case IPC_RMID:
		return msgctl_down(ns, msqid, cmd, buf, version);
	default:
		return  -EINVAL;
	}
}

static int testmsg(struct msg_msg *msg, long type, int mode)
{
	switch(mode)
	{
		case SEARCH_ANY:
		case SEARCH_NUMBER:
			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 msg_receiver *msr, *t;

	list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
		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 = task_pid_vnr(msr->r_tsk);
				msq->q_rtime = get_seconds();
				wake_up_process(msr->r_tsk);
				smp_mb();
				msr->r_msg = msg;

				return 1;
			}
		}
	}
	return 0;
}

long do_msgsnd(int msqid, long mtype, void __user *mtext,
		size_t msgsz, int msgflg)
{
	struct msg_queue *msq;
	struct msg_msg *msg;
	int err;
	struct ipc_namespace *ns;

	ns = current->nsproxy->ipc_ns;

	if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0)
		return -EINVAL;
	if (mtype < 1)
		return -EINVAL;

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

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

	rcu_read_lock();
	msq = msq_obtain_object_check(ns, msqid);
	if (IS_ERR(msq)) {
		err = PTR_ERR(msq);
		goto out_unlock1;
	}

	for (;;) {
		struct msg_sender s;

		err = -EACCES;
		if (ipcperms(ns, &msq->q_perm, S_IWUGO))
			goto out_unlock1;

		err = security_msg_queue_msgsnd(msq, msg, msgflg);
		if (err)
			goto out_unlock1;

		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_unlock1;
		}

		ipc_lock_object(&msq->q_perm);
		ss_add(msq, &s);

		if (!ipc_rcu_getref(msq)) {
			err = -EIDRM;
			goto out_unlock0;
		}

		ipc_unlock_object(&msq->q_perm);
		rcu_read_unlock();
		schedule();

		rcu_read_lock();
		ipc_lock_object(&msq->q_perm);

		ipc_rcu_putref(msq);
		if (msq->q_perm.deleted) {
			err = -EIDRM;
			goto out_unlock0;
		}

		ss_del(&s);

		if (signal_pending(current)) {
			err = -ERESTARTNOHAND;
			goto out_unlock0;
		}

		ipc_unlock_object(&msq->q_perm);
	}

	ipc_lock_object(&msq->q_perm);
	msq->q_lspid = task_tgid_vnr(current);
	msq->q_stime = get_seconds();

	if (!pipelined_send(msq, msg)) {
		/* no one 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, &ns->msg_bytes);
		atomic_inc(&ns->msg_hdrs);
	}

	err = 0;
	msg = NULL;

out_unlock0:
	ipc_unlock_object(&msq->q_perm);
out_unlock1:
	rcu_read_unlock();
	if (msg != NULL)
		free_msg(msg);
	return err;
}

SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
		int, msgflg)
{
	long mtype;

	if (get_user(mtype, &msgp->mtype))
		return -EFAULT;
	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
}

static inline int convert_mode(long *msgtyp, int msgflg)
{
	if (msgflg & MSG_COPY)
		return SEARCH_NUMBER;
	/*
	 *  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;
}

static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
{
	struct msgbuf __user *msgp = dest;
	size_t msgsz;

	if (put_user(msg->m_type, &msgp->mtype))
		return -EFAULT;

	msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
	if (store_msg(msgp->mtext, msg, msgsz))
		return -EFAULT;
	return msgsz;
}

#ifdef CONFIG_CHECKPOINT_RESTORE
/*
 * This function creates new kernel message structure, large enough to store
 * bufsz message bytes.
 */
static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
	struct msg_msg *copy;

	/*
	 * Create dummy message to copy real message to.
	 */
	copy = load_msg(buf, bufsz);
	if (!IS_ERR(copy))
		copy->m_ts = bufsz;
	return copy;
}

static inline void free_copy(struct msg_msg *copy)
{
	if (copy)
		free_msg(copy);
}
#else
static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
	return ERR_PTR(-ENOSYS);
}

static inline void free_copy(struct msg_msg *copy)
{
}
#endif

static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
{
	struct msg_msg *msg;
	long count = 0;

	list_for_each_entry(msg, &msq->q_messages, m_list) {
		if (testmsg(msg, *msgtyp, mode) &&
		    !security_msg_queue_msgrcv(msq, msg, current,
					       *msgtyp, mode)) {
			if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
				*msgtyp = msg->m_type - 1;
			} else if (mode == SEARCH_NUMBER) {
				if (*msgtyp == count)
					return msg;
			} else
				return msg;
			count++;
		}
	}

	return ERR_PTR(-EAGAIN);
}

long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
{
	int mode;
	struct msg_queue *msq;
	struct ipc_namespace *ns;
	struct msg_msg *msg, *copy = NULL;

	ns = current->nsproxy->ipc_ns;

	if (msqid < 0 || (long) bufsz < 0)
		return -EINVAL;

	if (msgflg & MSG_COPY) {
		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
		if (IS_ERR(copy))
			return PTR_ERR(copy);
	}
	mode = convert_mode(&msgtyp, msgflg);

	rcu_read_lock();
	msq = msq_obtain_object_check(ns, msqid);
	if (IS_ERR(msq)) {
		rcu_read_unlock();
		free_copy(copy);
		return PTR_ERR(msq);
	}

	for (;;) {
		struct msg_receiver msr_d;

		msg = ERR_PTR(-EACCES);
		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
			goto out_unlock1;

		ipc_lock_object(&msq->q_perm);
		msg = find_msg(msq, &msgtyp, mode);
		if (!IS_ERR(msg)) {
			/*
			 * Found a suitable message.
			 * Unlink it from the queue.
			 */
			if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
				msg = ERR_PTR(-E2BIG);
				goto out_unlock0;
			}
			/*
			 * If we are copying, then do not unlink message and do
			 * not update queue parameters.
			 */
			if (msgflg & MSG_COPY) {
				msg = copy_msg(msg, copy);
				goto out_unlock0;
			}

			list_del(&msg->m_list);
			msq->q_qnum--;
			msq->q_rtime = get_seconds();
			msq->q_lrpid = task_tgid_vnr(current);
			msq->q_cbytes -= msg->m_ts;
			atomic_sub(msg->m_ts, &ns->msg_bytes);
			atomic_dec(&ns->msg_hdrs);
			ss_wakeup(&msq->q_senders, 0);

			goto out_unlock0;
		}

		/* No message waiting. Wait for a message */
		if (msgflg & IPC_NOWAIT) {
			msg = ERR_PTR(-ENOMSG);
			goto out_unlock0;
		}

		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 = bufsz;
		msr_d.r_msg = ERR_PTR(-EAGAIN);
		current->state = TASK_INTERRUPTIBLE;

		ipc_unlock_object(&msq->q_perm);
		rcu_read_unlock();
		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
		 * existence 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 acquiring the q_perm.lock in ipc_lock_object().
		 */
		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))
			goto out_unlock1;

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

		/* 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_unlock0;

		list_del(&msr_d.r_list);
		if (signal_pending(current)) {
			msg = ERR_PTR(-ERESTARTNOHAND);
			goto out_unlock0;
		}

		ipc_unlock_object(&msq->q_perm);
	}

out_unlock0:
	ipc_unlock_object(&msq->q_perm);
out_unlock1:
	rcu_read_unlock();
	if (IS_ERR(msg)) {
		free_copy(copy);
		return PTR_ERR(msg);
	}

	bufsz = msg_handler(buf, msg, bufsz);
	free_msg(msg);

	return bufsz;
}

SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
		long, msgtyp, int, msgflg)
{
	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
}

#ifdef CONFIG_PROC_FS
static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
{
	struct user_namespace *user_ns = seq_user_ns(s);
	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_perm.id,
			msq->q_perm.mode,
			msq->q_cbytes,
			msq->q_qnum,
			msq->q_lspid,
			msq->q_lrpid,
			from_kuid_munged(user_ns, msq->q_perm.uid),
			from_kgid_munged(user_ns, msq->q_perm.gid),
			from_kuid_munged(user_ns, msq->q_perm.cuid),
			from_kgid_munged(user_ns, msq->q_perm.cgid),
			msq->q_stime,
			msq->q_rtime,
			msq->q_ctime);
}
#endif