Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 3d920ff15c80dd26532c72c0c3dea77ef6557a9e (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
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
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
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
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
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
/*
 * POSIX message queues filesystem for Linux.
 *
 * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
 *                          Michal Wronski          (michal.wronski@gmail.com)
 *
 * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
 * Lockless receive & send, fd based notify:
 *			    Manfred Spraul	    (manfred@colorfullife.com)
 *
 * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
 *
 * This file is released under the GPL.
 */

#include <linux/capability.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/fs_context.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/vmalloc.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/signal.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/signal.h>
#include <linux/sched/user.h>

#include <net/sock.h>
#include "util.h"

struct mqueue_fs_context {
	struct ipc_namespace	*ipc_ns;
};

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

#define SEND		0
#define RECV		1

#define STATE_NONE	0
#define STATE_READY	1

struct posix_msg_tree_node {
	struct rb_node		rb_node;
	struct list_head	msg_list;
	int			priority;
};

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 rb_root msg_tree;
	struct rb_node *msg_tree_rightmost;
	struct posix_msg_tree_node *node_cache;
	struct mq_attr attr;

	struct sigevent notify;
	struct pid *notify_owner;
	struct user_namespace *notify_user_ns;
	struct user_struct *user;	/* user who created, for accounting */
	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) */
};

static struct file_system_type mqueue_fs_type;
static const struct inode_operations mqueue_dir_inode_operations;
static const struct file_operations mqueue_file_operations;
static const struct super_operations mqueue_super_ops;
static const struct fs_context_operations mqueue_fs_context_ops;
static void remove_notification(struct mqueue_inode_info *info);

static struct kmem_cache *mqueue_inode_cachep;

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);
}

/*
 * This routine should be called with the mq_lock held.
 */
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
{
	return get_ipc_ns(inode->i_sb->s_fs_info);
}

static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
{
	struct ipc_namespace *ns;

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

/* Auxiliary functions to manipulate messages' list */
static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
{
	struct rb_node **p, *parent = NULL;
	struct posix_msg_tree_node *leaf;
	bool rightmost = true;

	p = &info->msg_tree.rb_node;
	while (*p) {
		parent = *p;
		leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);

		if (likely(leaf->priority == msg->m_type))
			goto insert_msg;
		else if (msg->m_type < leaf->priority) {
			p = &(*p)->rb_left;
			rightmost = false;
		} else
			p = &(*p)->rb_right;
	}
	if (info->node_cache) {
		leaf = info->node_cache;
		info->node_cache = NULL;
	} else {
		leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC);
		if (!leaf)
			return -ENOMEM;
		INIT_LIST_HEAD(&leaf->msg_list);
	}
	leaf->priority = msg->m_type;

	if (rightmost)
		info->msg_tree_rightmost = &leaf->rb_node;

	rb_link_node(&leaf->rb_node, parent, p);
	rb_insert_color(&leaf->rb_node, &info->msg_tree);
insert_msg:
	info->attr.mq_curmsgs++;
	info->qsize += msg->m_ts;
	list_add_tail(&msg->m_list, &leaf->msg_list);
	return 0;
}

static inline void msg_tree_erase(struct posix_msg_tree_node *leaf,
				  struct mqueue_inode_info *info)
{
	struct rb_node *node = &leaf->rb_node;

	if (info->msg_tree_rightmost == node)
		info->msg_tree_rightmost = rb_prev(node);

	rb_erase(node, &info->msg_tree);
	if (info->node_cache) {
		kfree(leaf);
	} else {
		info->node_cache = leaf;
	}
}

static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
	struct rb_node *parent = NULL;
	struct posix_msg_tree_node *leaf;
	struct msg_msg *msg;

try_again:
	/*
	 * During insert, low priorities go to the left and high to the
	 * right.  On receive, we want the highest priorities first, so
	 * walk all the way to the right.
	 */
	parent = info->msg_tree_rightmost;
	if (!parent) {
		if (info->attr.mq_curmsgs) {
			pr_warn_once("Inconsistency in POSIX message queue, "
				     "no tree element, but supposedly messages "
				     "should exist!\n");
			info->attr.mq_curmsgs = 0;
		}
		return NULL;
	}
	leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);
	if (unlikely(list_empty(&leaf->msg_list))) {
		pr_warn_once("Inconsistency in POSIX message queue, "
			     "empty leaf node but we haven't implemented "
			     "lazy leaf delete!\n");
		msg_tree_erase(leaf, info);
		goto try_again;
	} else {
		msg = list_first_entry(&leaf->msg_list,
				       struct msg_msg, m_list);
		list_del(&msg->m_list);
		if (list_empty(&leaf->msg_list)) {
			msg_tree_erase(leaf, info);
		}
	}
	info->attr.mq_curmsgs--;
	info->qsize -= msg->m_ts;
	return msg;
}

static struct inode *mqueue_get_inode(struct super_block *sb,
		struct ipc_namespace *ipc_ns, umode_t mode,
		struct mq_attr *attr)
{
	struct user_struct *u = current_user();
	struct inode *inode;
	int ret = -ENOMEM;

	inode = new_inode(sb);
	if (!inode)
		goto err;

	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_mtime = inode->i_ctime = inode->i_atime = current_time(inode);

	if (S_ISREG(mode)) {
		struct mqueue_inode_info *info;
		unsigned long mq_bytes, mq_treesize;

		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->notify_owner = NULL;
		info->notify_user_ns = NULL;
		info->qsize = 0;
		info->user = NULL;	/* set when all is ok */
		info->msg_tree = RB_ROOT;
		info->msg_tree_rightmost = NULL;
		info->node_cache = NULL;
		memset(&info->attr, 0, sizeof(info->attr));
		info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
					   ipc_ns->mq_msg_default);
		info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
					    ipc_ns->mq_msgsize_default);
		if (attr) {
			info->attr.mq_maxmsg = attr->mq_maxmsg;
			info->attr.mq_msgsize = attr->mq_msgsize;
		}
		/*
		 * We used to allocate a static array of pointers and account
		 * the size of that array as well as one msg_msg struct per
		 * possible message into the queue size. That's no longer
		 * accurate as the queue is now an rbtree and will grow and
		 * shrink depending on usage patterns.  We can, however, still
		 * account one msg_msg struct per message, but the nodes are
		 * allocated depending on priority usage, and most programs
		 * only use one, or a handful, of priorities.  However, since
		 * this is pinned memory, we need to assume worst case, so
		 * that means the min(mq_maxmsg, max_priorities) * struct
		 * posix_msg_tree_node.
		 */

		ret = -EINVAL;
		if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0)
			goto out_inode;
		if (capable(CAP_SYS_RESOURCE)) {
			if (info->attr.mq_maxmsg > HARD_MSGMAX ||
			    info->attr.mq_msgsize > HARD_MSGSIZEMAX)
				goto out_inode;
		} else {
			if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max ||
					info->attr.mq_msgsize > ipc_ns->mq_msgsize_max)
				goto out_inode;
		}
		ret = -EOVERFLOW;
		/* check for overflow */
		if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg)
			goto out_inode;
		mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
			min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
			sizeof(struct posix_msg_tree_node);
		mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize;
		if (mq_bytes + mq_treesize < mq_bytes)
			goto out_inode;
		mq_bytes += mq_treesize;
		spin_lock(&mq_lock);
		if (u->mq_bytes + mq_bytes < u->mq_bytes ||
		    u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
			spin_unlock(&mq_lock);
			/* mqueue_evict_inode() releases info->messages */
			ret = -EMFILE;
			goto out_inode;
		}
		u->mq_bytes += mq_bytes;
		spin_unlock(&mq_lock);

		/* all is ok */
		info->user = get_uid(u);
	} else if (S_ISDIR(mode)) {
		inc_nlink(inode);
		/* 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:
	iput(inode);
err:
	return ERR_PTR(ret);
}

static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct inode *inode;
	struct ipc_namespace *ns = sb->s_fs_info;

	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
	sb->s_blocksize = PAGE_SIZE;
	sb->s_blocksize_bits = PAGE_SHIFT;
	sb->s_magic = MQUEUE_MAGIC;
	sb->s_op = &mqueue_super_ops;

	inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		return -ENOMEM;
	return 0;
}

static int mqueue_get_tree(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx = fc->fs_private;

	return get_tree_keyed(fc, mqueue_fill_super, ctx->ipc_ns);
}

static void mqueue_fs_context_free(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx = fc->fs_private;

	put_ipc_ns(ctx->ipc_ns);
	kfree(ctx);
}

static int mqueue_init_fs_context(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx;

	ctx = kzalloc(sizeof(struct mqueue_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	ctx->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
	fc->fs_private = ctx;
	fc->ops = &mqueue_fs_context_ops;
	return 0;
}

static struct vfsmount *mq_create_mount(struct ipc_namespace *ns)
{
	struct mqueue_fs_context *ctx;
	struct fs_context *fc;
	struct vfsmount *mnt;

	fc = fs_context_for_mount(&mqueue_fs_type, SB_KERNMOUNT);
	if (IS_ERR(fc))
		return ERR_CAST(fc);

	ctx = fc->fs_private;
	put_ipc_ns(ctx->ipc_ns);
	ctx->ipc_ns = get_ipc_ns(ns);
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);

	mnt = fc_mount(fc);
	put_fs_context(fc);
	return mnt;
}

static void init_once(void *foo)
{
	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;

	inode_init_once(&p->vfs_inode);
}

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

	ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

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

static void mqueue_evict_inode(struct inode *inode)
{
	struct mqueue_inode_info *info;
	struct user_struct *user;
	struct ipc_namespace *ipc_ns;
	struct msg_msg *msg, *nmsg;
	LIST_HEAD(tmp_msg);

	clear_inode(inode);

	if (S_ISDIR(inode->i_mode))
		return;

	ipc_ns = get_ns_from_inode(inode);
	info = MQUEUE_I(inode);
	spin_lock(&info->lock);
	while ((msg = msg_get(info)) != NULL)
		list_add_tail(&msg->m_list, &tmp_msg);
	kfree(info->node_cache);
	spin_unlock(&info->lock);

	list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) {
		list_del(&msg->m_list);
		free_msg(msg);
	}

	user = info->user;
	if (user) {
		unsigned long mq_bytes, mq_treesize;

		/* Total amount of bytes accounted for the mqueue */
		mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
			min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
			sizeof(struct posix_msg_tree_node);

		mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
					  info->attr.mq_msgsize);

		spin_lock(&mq_lock);
		user->mq_bytes -= mq_bytes;
		/*
		 * 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--;
		spin_unlock(&mq_lock);
		free_uid(user);
	}
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
}

static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
{
	struct inode *dir = dentry->d_parent->d_inode;
	struct inode *inode;
	struct mq_attr *attr = arg;
	int error;
	struct ipc_namespace *ipc_ns;

	spin_lock(&mq_lock);
	ipc_ns = __get_ns_from_inode(dir);
	if (!ipc_ns) {
		error = -EACCES;
		goto out_unlock;
	}

	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
	    !capable(CAP_SYS_RESOURCE)) {
		error = -ENOSPC;
		goto out_unlock;
	}
	ipc_ns->mq_queues_count++;
	spin_unlock(&mq_lock);

	inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
	if (IS_ERR(inode)) {
		error = PTR_ERR(inode);
		spin_lock(&mq_lock);
		ipc_ns->mq_queues_count--;
		goto out_unlock;
	}

	put_ipc_ns(ipc_ns);
	dir->i_size += DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);

	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
out_unlock:
	spin_unlock(&mq_lock);
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
	return error;
}

static int mqueue_create(struct inode *dir, struct dentry *dentry,
				umode_t mode, bool excl)
{
	return mqueue_create_attr(dentry, mode, NULL);
}

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

	dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);
	dir->i_size -= DIRENT_SIZE;
	drop_nlink(inode);
	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)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	char buffer[FILENT_SIZE];
	ssize_t ret;

	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,
			pid_vnr(info->notify_owner));
	spin_unlock(&info->lock);
	buffer[sizeof(buffer)-1] = '\0';

	ret = simple_read_from_buffer(u_data, count, off, buffer,
				strlen(buffer));
	if (ret <= 0)
		return ret;

	file_inode(filp)->i_atime = file_inode(filp)->i_ctime = current_time(file_inode(filp));
	return ret;
}

static int mqueue_flush_file(struct file *filp, fl_owner_t id)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));

	spin_lock(&info->lock);
	if (task_tgid(current) == info->notify_owner)
		remove_notification(info);

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

static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	__poll_t retval = 0;

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

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

	if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
		retval |= EPOLLOUT | EPOLLWRNORM;
	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;

	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
		if (walk->task->prio <= current->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,
		    ktime_t *timeout, struct ext_wait_queue *ewp)
	__releases(&info->lock)
{
	int retval;
	signed long time;

	wq_add(info, sr, ewp);

	for (;;) {
		__set_current_state(TASK_INTERRUPTIBLE);

		spin_unlock(&info->lock);
		time = schedule_hrtimeout_range_clock(timeout, 0,
			HRTIMER_MODE_ABS, CLOCK_REALTIME);

		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);
}


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 kernel_siginfo sig_i;
		switch (info->notify.sigev_notify) {
		case SIGEV_NONE:
			break;
		case SIGEV_SIGNAL:
			/* sends signal */

			clear_siginfo(&sig_i);
			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;
			/* map current pid/uid into info->owner's namespaces */
			rcu_read_lock();
			sig_i.si_pid = task_tgid_nr_ns(current,
						ns_of_pid(info->notify_owner));
			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
			rcu_read_unlock();

			kill_pid_info(info->notify.sigev_signo,
				      &sig_i, info->notify_owner);
			break;
		case SIGEV_THREAD:
			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
			netlink_sendskb(info->notify_sock, info->notify_cookie);
			break;
		}
		/* after notification unregisters process */
		put_pid(info->notify_owner);
		put_user_ns(info->notify_user_ns);
		info->notify_owner = NULL;
		info->notify_user_ns = NULL;
	}
	wake_up(&info->wait_q);
}

static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
			   struct timespec64 *ts)
{
	if (get_timespec64(ts, u_abs_timeout))
		return -EFAULT;
	if (!timespec64_valid(ts))
		return -EINVAL;
	return 0;
}

static void remove_notification(struct mqueue_inode_info *info)
{
	if (info->notify_owner != NULL &&
	    info->notify.sigev_notify == SIGEV_THREAD) {
		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
		netlink_sendskb(info->notify_sock, info->notify_cookie);
	}
	put_pid(info->notify_owner);
	put_user_ns(info->notify_user_ns);
	info->notify_owner = NULL;
	info->notify_user_ns = NULL;
}

static int prepare_open(struct dentry *dentry, int oflag, int ro,
			umode_t mode, struct filename *name,
			struct mq_attr *attr)
{
	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
						  MAY_READ | MAY_WRITE };
	int acc;

	if (d_really_is_negative(dentry)) {
		if (!(oflag & O_CREAT))
			return -ENOENT;
		if (ro)
			return ro;
		audit_inode_parent_hidden(name, dentry->d_parent);
		return vfs_mkobj(dentry, mode & ~current_umask(),
				  mqueue_create_attr, attr);
	}
	/* it already existed */
	audit_inode(name, dentry, 0);
	if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
		return -EEXIST;
	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
		return -EINVAL;
	acc = oflag2acc[oflag & O_ACCMODE];
	return inode_permission(d_inode(dentry), acc);
}

static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
		      struct mq_attr *attr)
{
	struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt;
	struct dentry *root = mnt->mnt_root;
	struct filename *name;
	struct path path;
	int fd, error;
	int ro;

	audit_mq_open(oflag, mode, attr);

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

	fd = get_unused_fd_flags(O_CLOEXEC);
	if (fd < 0)
		goto out_putname;

	ro = mnt_want_write(mnt);	/* we'll drop it in any case */
	inode_lock(d_inode(root));
	path.dentry = lookup_one_len(name->name, root, strlen(name->name));
	if (IS_ERR(path.dentry)) {
		error = PTR_ERR(path.dentry);
		goto out_putfd;
	}
	path.mnt = mntget(mnt);
	error = prepare_open(path.dentry, oflag, ro, mode, name, attr);
	if (!error) {
		struct file *file = dentry_open(&path, oflag, current_cred());
		if (!IS_ERR(file))
			fd_install(fd, file);
		else
			error = PTR_ERR(file);
	}
	path_put(&path);
out_putfd:
	if (error) {
		put_unused_fd(fd);
		fd = error;
	}
	inode_unlock(d_inode(root));
	if (!ro)
		mnt_drop_write(mnt);
out_putname:
	putname(name);
	return fd;
}

SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
		struct mq_attr __user *, u_attr)
{
	struct mq_attr attr;
	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
		return -EFAULT;

	return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL);
}

SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
{
	int err;
	struct filename *name;
	struct dentry *dentry;
	struct inode *inode = NULL;
	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
	struct vfsmount *mnt = ipc_ns->mq_mnt;

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

	audit_inode_parent_hidden(name, mnt->mnt_root);
	err = mnt_want_write(mnt);
	if (err)
		goto out_name;
	inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT);
	dentry = lookup_one_len(name->name, mnt->mnt_root,
				strlen(name->name));
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out_unlock;
	}

	inode = d_inode(dentry);
	if (!inode) {
		err = -ENOENT;
	} else {
		ihold(inode);
		err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL);
	}
	dput(dentry);

out_unlock:
	inode_unlock(d_inode(mnt->mnt_root));
	if (inode)
		iput(inode);
	mnt_drop_write(mnt);
out_name:
	putname(name);

	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:
 *
 * - Set pointer to message.
 * - Queue the receiver task for later wakeup (without the info->lock).
 * - Update its state to STATE_READY. Now the receiver can continue.
 * - Wake up the process after the lock is dropped. Should the process wake up
 *   before this wakeup (due to a timeout or a signal) it will either see
 *   STATE_READY and continue or acquire the lock to check the state again.
 *
 * 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 wake_q_head *wake_q,
				  struct mqueue_inode_info *info,
				  struct msg_msg *message,
				  struct ext_wait_queue *receiver)
{
	receiver->msg = message;
	list_del(&receiver->list);
	wake_q_add(wake_q, receiver->task);
	/*
	 * Rely on the implicit cmpxchg barrier from wake_q_add such
	 * that we can ensure that updating receiver->state is the last
	 * write operation: As once set, the receiver can continue,
	 * and if we don't have the reference count from the wake_q,
	 * yet, at that point we can later have a use-after-free
	 * condition and bogus wakeup.
	 */
	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 wake_q_head *wake_q,
				     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;
	}
	if (msg_insert(sender->msg, info))
		return;

	list_del(&sender->list);
	wake_q_add(wake_q, sender->task);
	sender->state = STATE_READY;
}

static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
		size_t msg_len, unsigned int msg_prio,
		struct timespec64 *ts)
{
	struct fd f;
	struct inode *inode;
	struct ext_wait_queue wait;
	struct ext_wait_queue *receiver;
	struct msg_msg *msg_ptr;
	struct mqueue_inode_info *info;
	ktime_t expires, *timeout = NULL;
	struct posix_msg_tree_node *new_leaf = NULL;
	int ret = 0;
	DEFINE_WAKE_Q(wake_q);

	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
		return -EINVAL;

	if (ts) {
		expires = timespec64_to_ktime(*ts);
		timeout = &expires;
	}

	audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts);

	f = fdget(mqdes);
	if (unlikely(!f.file)) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);
	audit_file(f.file);

	if (unlikely(!(f.file->f_mode & FMODE_WRITE))) {
		ret = -EBADF;
		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;

	/*
	 * msg_insert really wants us to have a valid, spare node struct so
	 * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will
	 * fall back to that if necessary.
	 */
	if (!info->node_cache)
		new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL);

	spin_lock(&info->lock);

	if (!info->node_cache && new_leaf) {
		/* Save our speculative allocation into the cache */
		INIT_LIST_HEAD(&new_leaf->msg_list);
		info->node_cache = new_leaf;
		new_leaf = NULL;
	} else {
		kfree(new_leaf);
	}

	if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
		if (f.file->f_flags & O_NONBLOCK) {
			ret = -EAGAIN;
		} else {
			wait.task = current;
			wait.msg = (void *) msg_ptr;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, SEND, timeout, &wait);
			/*
			 * wq_sleep must be called with info->lock held, and
			 * returns with the lock released
			 */
			goto out_free;
		}
	} else {
		receiver = wq_get_first_waiter(info, RECV);
		if (receiver) {
			pipelined_send(&wake_q, info, msg_ptr, receiver);
		} else {
			/* adds message to the queue */
			ret = msg_insert(msg_ptr, info);
			if (ret)
				goto out_unlock;
			__do_notify(info);
		}
		inode->i_atime = inode->i_mtime = inode->i_ctime =
				current_time(inode);
	}
out_unlock:
	spin_unlock(&info->lock);
	wake_up_q(&wake_q);
out_free:
	if (ret)
		free_msg(msg_ptr);
out_fput:
	fdput(f);
out:
	return ret;
}

static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
		size_t msg_len, unsigned int __user *u_msg_prio,
		struct timespec64 *ts)
{
	ssize_t ret;
	struct msg_msg *msg_ptr;
	struct fd f;
	struct inode *inode;
	struct mqueue_inode_info *info;
	struct ext_wait_queue wait;
	ktime_t expires, *timeout = NULL;
	struct posix_msg_tree_node *new_leaf = NULL;

	if (ts) {
		expires = timespec64_to_ktime(*ts);
		timeout = &expires;
	}

	audit_mq_sendrecv(mqdes, msg_len, 0, ts);

	f = fdget(mqdes);
	if (unlikely(!f.file)) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);
	audit_file(f.file);

	if (unlikely(!(f.file->f_mode & FMODE_READ))) {
		ret = -EBADF;
		goto out_fput;
	}

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

	/*
	 * msg_insert really wants us to have a valid, spare node struct so
	 * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will
	 * fall back to that if necessary.
	 */
	if (!info->node_cache)
		new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL);

	spin_lock(&info->lock);

	if (!info->node_cache && new_leaf) {
		/* Save our speculative allocation into the cache */
		INIT_LIST_HEAD(&new_leaf->msg_list);
		info->node_cache = new_leaf;
	} else {
		kfree(new_leaf);
	}

	if (info->attr.mq_curmsgs == 0) {
		if (f.file->f_flags & O_NONBLOCK) {
			spin_unlock(&info->lock);
			ret = -EAGAIN;
		} else {
			wait.task = current;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, RECV, timeout, &wait);
			msg_ptr = wait.msg;
		}
	} else {
		DEFINE_WAKE_Q(wake_q);

		msg_ptr = msg_get(info);

		inode->i_atime = inode->i_mtime = inode->i_ctime =
				current_time(inode);

		/* There is now free space in queue. */
		pipelined_receive(&wake_q, info);
		spin_unlock(&info->lock);
		wake_up_q(&wake_q);
		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:
	fdput(f);
out:
	return ret;
}

SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
		size_t, msg_len, unsigned int, msg_prio,
		const struct __kernel_timespec __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
}

SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
		size_t, msg_len, unsigned int __user *, u_msg_prio,
		const struct __kernel_timespec __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
}

/*
 * 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.
 */
static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
	int ret;
	struct fd f;
	struct sock *sock;
	struct inode *inode;
	struct mqueue_inode_info *info;
	struct sk_buff *nc;

	audit_mq_notify(mqdes, notification);

	nc = NULL;
	sock = NULL;
	if (notification != NULL) {
		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 &&
			!valid_signal(notification->sigev_signo)) {
			return -EINVAL;
		}
		if (notification->sigev_notify == SIGEV_THREAD) {
			long timeo;

			/* create the notify skb */
			nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
			if (!nc)
				return -ENOMEM;

			if (copy_from_user(nc->data,
					notification->sigev_value.sival_ptr,
					NOTIFY_COOKIE_LEN)) {
				ret = -EFAULT;
				goto free_skb;
			}

			/* TODO: add a header? */
			skb_put(nc, NOTIFY_COOKIE_LEN);
			/* and attach it to the socket */
retry:
			f = fdget(notification->sigev_signo);
			if (!f.file) {
				ret = -EBADF;
				goto out;
			}
			sock = netlink_getsockbyfilp(f.file);
			fdput(f);
			if (IS_ERR(sock)) {
				ret = PTR_ERR(sock);
				goto free_skb;
			}

			timeo = MAX_SCHEDULE_TIMEOUT;
			ret = netlink_attachskb(sock, nc, &timeo, NULL);
			if (ret == 1) {
				sock = NULL;
				goto retry;
			}
			if (ret)
				return ret;
		}
	}

	f = fdget(mqdes);
	if (!f.file) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);

	ret = 0;
	spin_lock(&info->lock);
	if (notification == NULL) {
		if (info->notify_owner == task_tgid(current)) {
			remove_notification(info);
			inode->i_atime = inode->i_ctime = current_time(inode);
		}
	} else if (info->notify_owner != NULL) {
		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;
		}

		info->notify_owner = get_pid(task_tgid(current));
		info->notify_user_ns = get_user_ns(current_user_ns());
		inode->i_atime = inode->i_ctime = current_time(inode);
	}
	spin_unlock(&info->lock);
out_fput:
	fdput(f);
out:
	if (sock)
		netlink_detachskb(sock, nc);
	else
free_skb:
		dev_kfree_skb(nc);

	return ret;
}

SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
		const struct sigevent __user *, u_notification)
{
	struct sigevent n, *p = NULL;
	if (u_notification) {
		if (copy_from_user(&n, u_notification, sizeof(struct sigevent)))
			return -EFAULT;
		p = &n;
	}
	return do_mq_notify(mqdes, p);
}

static int do_mq_getsetattr(int mqdes, struct mq_attr *new, struct mq_attr *old)
{
	struct fd f;
	struct inode *inode;
	struct mqueue_inode_info *info;

	if (new && (new->mq_flags & (~O_NONBLOCK)))
		return -EINVAL;

	f = fdget(mqdes);
	if (!f.file)
		return -EBADF;

	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		fdput(f);
		return -EBADF;
	}

	inode = file_inode(f.file);
	info = MQUEUE_I(inode);

	spin_lock(&info->lock);

	if (old) {
		*old = info->attr;
		old->mq_flags = f.file->f_flags & O_NONBLOCK;
	}
	if (new) {
		audit_mq_getsetattr(mqdes, new);
		spin_lock(&f.file->f_lock);
		if (new->mq_flags & O_NONBLOCK)
			f.file->f_flags |= O_NONBLOCK;
		else
			f.file->f_flags &= ~O_NONBLOCK;
		spin_unlock(&f.file->f_lock);

		inode->i_atime = inode->i_ctime = current_time(inode);
	}

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

SYSCALL_DEFINE3(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 mq_attr *new = NULL, *old = NULL;

	if (u_mqstat) {
		new = &mqstat;
		if (copy_from_user(new, u_mqstat, sizeof(struct mq_attr)))
			return -EFAULT;
	}
	if (u_omqstat)
		old = &omqstat;

	ret = do_mq_getsetattr(mqdes, new, old);
	if (ret || !old)
		return ret;

	if (copy_to_user(u_omqstat, old, sizeof(struct mq_attr)))
		return -EFAULT;
	return 0;
}

#ifdef CONFIG_COMPAT

struct compat_mq_attr {
	compat_long_t mq_flags;      /* message queue flags		     */
	compat_long_t mq_maxmsg;     /* maximum number of messages	     */
	compat_long_t mq_msgsize;    /* maximum message size		     */
	compat_long_t mq_curmsgs;    /* number of messages currently queued  */
	compat_long_t __reserved[4]; /* ignored for input, zeroed for output */
};

static inline int get_compat_mq_attr(struct mq_attr *attr,
			const struct compat_mq_attr __user *uattr)
{
	struct compat_mq_attr v;

	if (copy_from_user(&v, uattr, sizeof(*uattr)))
		return -EFAULT;

	memset(attr, 0, sizeof(*attr));
	attr->mq_flags = v.mq_flags;
	attr->mq_maxmsg = v.mq_maxmsg;
	attr->mq_msgsize = v.mq_msgsize;
	attr->mq_curmsgs = v.mq_curmsgs;
	return 0;
}

static inline int put_compat_mq_attr(const struct mq_attr *attr,
			struct compat_mq_attr __user *uattr)
{
	struct compat_mq_attr v;

	memset(&v, 0, sizeof(v));
	v.mq_flags = attr->mq_flags;
	v.mq_maxmsg = attr->mq_maxmsg;
	v.mq_msgsize = attr->mq_msgsize;
	v.mq_curmsgs = attr->mq_curmsgs;
	if (copy_to_user(uattr, &v, sizeof(*uattr)))
		return -EFAULT;
	return 0;
}

COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
		       int, oflag, compat_mode_t, mode,
		       struct compat_mq_attr __user *, u_attr)
{
	struct mq_attr attr, *p = NULL;
	if (u_attr && oflag & O_CREAT) {
		p = &attr;
		if (get_compat_mq_attr(&attr, u_attr))
			return -EFAULT;
	}
	return do_mq_open(u_name, oflag, mode, p);
}

COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
		       const struct compat_sigevent __user *, u_notification)
{
	struct sigevent n, *p = NULL;
	if (u_notification) {
		if (get_compat_sigevent(&n, u_notification))
			return -EFAULT;
		if (n.sigev_notify == SIGEV_THREAD)
			n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
		p = &n;
	}
	return do_mq_notify(mqdes, p);
}

COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
		       const struct compat_mq_attr __user *, u_mqstat,
		       struct compat_mq_attr __user *, u_omqstat)
{
	int ret;
	struct mq_attr mqstat, omqstat;
	struct mq_attr *new = NULL, *old = NULL;

	if (u_mqstat) {
		new = &mqstat;
		if (get_compat_mq_attr(new, u_mqstat))
			return -EFAULT;
	}
	if (u_omqstat)
		old = &omqstat;

	ret = do_mq_getsetattr(mqdes, new, old);
	if (ret || !old)
		return ret;

	if (put_compat_mq_attr(old, u_omqstat))
		return -EFAULT;
	return 0;
}
#endif

#ifdef CONFIG_COMPAT_32BIT_TIME
static int compat_prepare_timeout(const struct old_timespec32 __user *p,
				   struct timespec64 *ts)
{
	if (get_old_timespec32(ts, p))
		return -EFAULT;
	if (!timespec64_valid(ts))
		return -EINVAL;
	return 0;
}

SYSCALL_DEFINE5(mq_timedsend_time32, mqd_t, mqdes,
		const char __user *, u_msg_ptr,
		unsigned int, msg_len, unsigned int, msg_prio,
		const struct old_timespec32 __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = compat_prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
}

SYSCALL_DEFINE5(mq_timedreceive_time32, mqd_t, mqdes,
		char __user *, u_msg_ptr,
		unsigned int, msg_len, unsigned int __user *, u_msg_prio,
		const struct old_timespec32 __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = compat_prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
}
#endif

static const struct inode_operations mqueue_dir_inode_operations = {
	.lookup = simple_lookup,
	.create = mqueue_create,
	.unlink = mqueue_unlink,
};

static const struct file_operations mqueue_file_operations = {
	.flush = mqueue_flush_file,
	.poll = mqueue_poll_file,
	.read = mqueue_read_file,
	.llseek = default_llseek,
};

static const struct super_operations mqueue_super_ops = {
	.alloc_inode = mqueue_alloc_inode,
	.free_inode = mqueue_free_inode,
	.evict_inode = mqueue_evict_inode,
	.statfs = simple_statfs,
};

static const struct fs_context_operations mqueue_fs_context_ops = {
	.free		= mqueue_fs_context_free,
	.get_tree	= mqueue_get_tree,
};

static struct file_system_type mqueue_fs_type = {
	.name			= "mqueue",
	.init_fs_context	= mqueue_init_fs_context,
	.kill_sb		= kill_litter_super,
	.fs_flags		= FS_USERNS_MOUNT,
};

int mq_init_ns(struct ipc_namespace *ns)
{
	struct vfsmount *m;

	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_msg_default   = DFLT_MSG;
	ns->mq_msgsize_default  = DFLT_MSGSIZE;

	m = mq_create_mount(ns);
	if (IS_ERR(m))
		return PTR_ERR(m);
	ns->mq_mnt = m;
	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)
{
	kern_unmount(ns->mq_mnt);
}

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|SLAB_ACCOUNT, init_once);
	if (mqueue_inode_cachep == NULL)
		return -ENOMEM;

	/* ignore failures - they are not fatal */
	mq_sysctl_table = mq_register_sysctl_table();

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

	spin_lock_init(&mq_lock);

	error = mq_init_ns(&init_ipc_ns);
	if (error)
		goto out_filesystem;

	return 0;

out_filesystem:
	unregister_filesystem(&mqueue_fs_type);
out_sysctl:
	if (mq_sysctl_table)
		unregister_sysctl_table(mq_sysctl_table);
	kmem_cache_destroy(mqueue_inode_cachep);
	return error;
}

device_initcall(init_mqueue_fs);