aboutsummaryrefslogtreecommitdiff
path: root/ipc/sem.c
blob: d56d3ab6bb8a7b62b6aa9141b1d22f34a3c3c002 (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
/*
 * linux/ipc/sem.c
 * Copyright (C) 1992 Krishna Balasubramanian
 * Copyright (C) 1995 Eric Schenk, Bruno Haible
 *
 * IMPLEMENTATION NOTES ON CODE REWRITE (Eric Schenk, January 1995):
 * This code underwent a massive rewrite in order to solve some problems
 * with the original code. In particular the original code failed to
 * wake up processes that were waiting for semval to go to 0 if the
 * value went to 0 and was then incremented rapidly enough. In solving
 * this problem I have also modified the implementation so that it
 * processes pending operations in a FIFO manner, thus give a guarantee
 * that processes waiting for a lock on the semaphore won't starve
 * unless another locking process fails to unlock.
 * In addition the following two changes in behavior have been introduced:
 * - The original implementation of semop returned the value
 *   last semaphore element examined on success. This does not
 *   match the manual page specifications, and effectively
 *   allows the user to read the semaphore even if they do not
 *   have read permissions. The implementation now returns 0
 *   on success as stated in the manual page.
 * - There is some confusion over whether the set of undo adjustments
 *   to be performed at exit should be done in an atomic manner.
 *   That is, if we are attempting to decrement the semval should we queue
 *   up and wait until we can do so legally?
 *   The original implementation attempted to do this.
 *   The current implementation does not do so. This is because I don't
 *   think it is the right thing (TM) to do, and because I couldn't
 *   see a clean way to get the old behavior with the new design.
 *   The POSIX standard and SVID should be consulted to determine
 *   what behavior is mandated.
 *
 * Further notes on refinement (Christoph Rohland, December 1998):
 * - The POSIX standard says, that the undo adjustments simply should
 *   redo. So the current implementation is o.K.
 * - The previous code had two flaws:
 *   1) It actively gave the semaphore to the next waiting process
 *      sleeping on the semaphore. Since this process did not have the
 *      cpu this led to many unnecessary context switches and bad
 *      performance. Now we only check which process should be able to
 *      get the semaphore and if this process wants to reduce some
 *      semaphore value we simply wake it up without doing the
 *      operation. So it has to try to get it later. Thus e.g. the
 *      running process may reacquire the semaphore during the current
 *      time slice. If it only waits for zero or increases the semaphore,
 *      we do the operation in advance and wake it up.
 *   2) It did not wake up all zero waiting processes. We try to do
 *      better but only get the semops right which only wait for zero or
 *      increase. If there are decrement operations in the operations
 *      array we do the same as before.
 *
 * With the incarnation of O(1) scheduler, it becomes unnecessary to perform
 * check/retry algorithm for waking up blocked processes as the new scheduler
 * is better at handling thread switch than the old one.
 *
 * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
 *
 * SMP-threaded, sysctl's added
 * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
 * Enforced range limit on SEM_UNDO
 * (c) 2001 Red Hat Inc <alan@redhat.com>
 * Lockless wakeup
 * (c) 2003 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/slab.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/time.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>

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

#define sem_ids(ns)	((ns)->ids[IPC_SEM_IDS])

#define sem_unlock(sma)		ipc_unlock(&(sma)->sem_perm)
#define sem_checkid(sma, semid)	ipc_checkid(&sma->sem_perm, semid)

static int newary(struct ipc_namespace *, struct ipc_params *);
static void freeary(struct ipc_namespace *, struct kern_ipc_perm *);
#ifdef CONFIG_PROC_FS
static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
#endif

#define SEMMSL_FAST	256 /* 512 bytes on stack */
#define SEMOPM_FAST	64  /* ~ 372 bytes on stack */

/*
 * linked list protection:
 *	sem_undo.id_next,
 *	sem_array.sem_pending{,last},
 *	sem_array.sem_undo: sem_lock() for read/write
 *	sem_undo.proc_next: only "current" is allowed to read/write that field.
 *	
 */

#define sc_semmsl	sem_ctls[0]
#define sc_semmns	sem_ctls[1]
#define sc_semopm	sem_ctls[2]
#define sc_semmni	sem_ctls[3]

void sem_init_ns(struct ipc_namespace *ns)
{
	ns->sc_semmsl = SEMMSL;
	ns->sc_semmns = SEMMNS;
	ns->sc_semopm = SEMOPM;
	ns->sc_semmni = SEMMNI;
	ns->used_sems = 0;
	ipc_init_ids(&ns->ids[IPC_SEM_IDS]);
}

#ifdef CONFIG_IPC_NS
void sem_exit_ns(struct ipc_namespace *ns)
{
	free_ipcs(ns, &sem_ids(ns), freeary);
}
#endif

void __init sem_init (void)
{
	sem_init_ns(&init_ipc_ns);
	ipc_init_proc_interface("sysvipc/sem",
				"       key      semid perms      nsems   uid   gid  cuid  cgid      otime      ctime\n",
				IPC_SEM_IDS, sysvipc_sem_proc_show);
}

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

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

	return container_of(ipcp, struct sem_array, sem_perm);
}

static inline struct sem_array *sem_lock_check(struct ipc_namespace *ns,
						int id)
{
	struct kern_ipc_perm *ipcp = ipc_lock_check(&sem_ids(ns), id);

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

	return container_of(ipcp, struct sem_array, sem_perm);
}

static inline void sem_lock_and_putref(struct sem_array *sma)
{
	ipc_lock_by_ptr(&sma->sem_perm);
	ipc_rcu_putref(sma);
}

static inline void sem_getref_and_unlock(struct sem_array *sma)
{
	ipc_rcu_getref(sma);
	ipc_unlock(&(sma)->sem_perm);
}

static inline void sem_putref(struct sem_array *sma)
{
	ipc_lock_by_ptr(&sma->sem_perm);
	ipc_rcu_putref(sma);
	ipc_unlock(&(sma)->sem_perm);
}

static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
{
	ipc_rmid(&sem_ids(ns), &s->sem_perm);
}

/*
 * Lockless wakeup algorithm:
 * Without the check/retry algorithm a lockless wakeup is possible:
 * - queue.status is initialized to -EINTR before blocking.
 * - wakeup is performed by
 *	* unlinking the queue entry from sma->sem_pending
 *	* setting queue.status to IN_WAKEUP
 *	  This is the notification for the blocked thread that a
 *	  result value is imminent.
 *	* call wake_up_process
 *	* set queue.status to the final value.
 * - the previously blocked thread checks queue.status:
 *   	* if it's IN_WAKEUP, then it must wait until the value changes
 *   	* if it's not -EINTR, then the operation was completed by
 *   	  update_queue. semtimedop can return queue.status without
 *   	  performing any operation on the sem array.
 *   	* otherwise it must acquire the spinlock and check what's up.
 *
 * The two-stage algorithm is necessary to protect against the following
 * races:
 * - if queue.status is set after wake_up_process, then the woken up idle
 *   thread could race forward and try (and fail) to acquire sma->lock
 *   before update_queue had a chance to set queue.status
 * - if queue.status is written before wake_up_process and if the
 *   blocked process is woken up by a signal between writing
 *   queue.status and the wake_up_process, then the woken up
 *   process could return from semtimedop and die by calling
 *   sys_exit before wake_up_process is called. Then wake_up_process
 *   will oops, because the task structure is already invalid.
 *   (yes, this happened on s390 with sysv msg).
 *
 */
#define IN_WAKEUP	1

/**
 * newary - Create a new semaphore set
 * @ns: namespace
 * @params: ptr to the structure that contains key, semflg and nsems
 *
 * Called with sem_ids.rw_mutex held (as a writer)
 */

static int newary(struct ipc_namespace *ns, struct ipc_params *params)
{
	int id;
	int retval;
	struct sem_array *sma;
	int size;
	key_t key = params->key;
	int nsems = params->u.nsems;
	int semflg = params->flg;

	if (!nsems)
		return -EINVAL;
	if (ns->used_sems + nsems > ns->sc_semmns)
		return -ENOSPC;

	size = sizeof (*sma) + nsems * sizeof (struct sem);
	sma = ipc_rcu_alloc(size);
	if (!sma) {
		return -ENOMEM;
	}
	memset (sma, 0, size);

	sma->sem_perm.mode = (semflg & S_IRWXUGO);
	sma->sem_perm.key = key;

	sma->sem_perm.security = NULL;
	retval = security_sem_alloc(sma);
	if (retval) {
		ipc_rcu_putref(sma);
		return retval;
	}

	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
	if (id < 0) {
		security_sem_free(sma);
		ipc_rcu_putref(sma);
		return id;
	}
	ns->used_sems += nsems;

	sma->sem_base = (struct sem *) &sma[1];
	/* sma->sem_pending = NULL; */
	sma->sem_pending_last = &sma->sem_pending;
	/* sma->undo = NULL; */
	sma->sem_nsems = nsems;
	sma->sem_ctime = get_seconds();
	sem_unlock(sma);

	return sma->sem_perm.id;
}


/*
 * Called with sem_ids.rw_mutex and ipcp locked.
 */
static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
{
	struct sem_array *sma;

	sma = container_of(ipcp, struct sem_array, sem_perm);
	return security_sem_associate(sma, semflg);
}

/*
 * Called with sem_ids.rw_mutex and ipcp locked.
 */
static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
				struct ipc_params *params)
{
	struct sem_array *sma;

	sma = container_of(ipcp, struct sem_array, sem_perm);
	if (params->u.nsems > sma->sem_nsems)
		return -EINVAL;

	return 0;
}

asmlinkage long sys_semget(key_t key, int nsems, int semflg)
{
	struct ipc_namespace *ns;
	struct ipc_ops sem_ops;
	struct ipc_params sem_params;

	ns = current->nsproxy->ipc_ns;

	if (nsems < 0 || nsems > ns->sc_semmsl)
		return -EINVAL;

	sem_ops.getnew = newary;
	sem_ops.associate = sem_security;
	sem_ops.more_checks = sem_more_checks;

	sem_params.key = key;
	sem_params.flg = semflg;
	sem_params.u.nsems = nsems;

	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
}

/* Manage the doubly linked list sma->sem_pending as a FIFO:
 * insert new queue elements at the tail sma->sem_pending_last.
 */
static inline void append_to_queue (struct sem_array * sma,
				    struct sem_queue * q)
{
	*(q->prev = sma->sem_pending_last) = q;
	*(sma->sem_pending_last = &q->next) = NULL;
}

static inline void prepend_to_queue (struct sem_array * sma,
				     struct sem_queue * q)
{
	q->next = sma->sem_pending;
	*(q->prev = &sma->sem_pending) = q;
	if (q->next)
		q->next->prev = &q->next;
	else /* sma->sem_pending_last == &sma->sem_pending */
		sma->sem_pending_last = &q->next;
}

static inline void remove_from_queue (struct sem_array * sma,
				      struct sem_queue * q)
{
	*(q->prev) = q->next;
	if (q->next)
		q->next->prev = q->prev;
	else /* sma->sem_pending_last == &q->next */
		sma->sem_pending_last = q->prev;
	q->prev = NULL; /* mark as removed */
}

/*
 * Determine whether a sequence of semaphore operations would succeed
 * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
 */

static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
			     int nsops, struct sem_undo *un, int pid)
{
	int result, sem_op;
	struct sembuf *sop;
	struct sem * curr;

	for (sop = sops; sop < sops + nsops; sop++) {
		curr = sma->sem_base + sop->sem_num;
		sem_op = sop->sem_op;
		result = curr->semval;
  
		if (!sem_op && result)
			goto would_block;

		result += sem_op;
		if (result < 0)
			goto would_block;
		if (result > SEMVMX)
			goto out_of_range;
		if (sop->sem_flg & SEM_UNDO) {
			int undo = un->semadj[sop->sem_num] - sem_op;
			/*
	 		 *	Exceeding the undo range is an error.
			 */
			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
				goto out_of_range;
		}
		curr->semval = result;
	}

	sop--;
	while (sop >= sops) {
		sma->sem_base[sop->sem_num].sempid = pid;
		if (sop->sem_flg & SEM_UNDO)
			un->semadj[sop->sem_num] -= sop->sem_op;
		sop--;
	}
	
	sma->sem_otime = get_seconds();
	return 0;

out_of_range:
	result = -ERANGE;
	goto undo;

would_block:
	if (sop->sem_flg & IPC_NOWAIT)
		result = -EAGAIN;
	else
		result = 1;

undo:
	sop--;
	while (sop >= sops) {
		sma->sem_base[sop->sem_num].semval -= sop->sem_op;
		sop--;
	}

	return result;
}

/* Go through the pending queue for the indicated semaphore
 * looking for tasks that can be completed.
 */
static void update_queue (struct sem_array * sma)
{
	int error;
	struct sem_queue * q;

	q = sma->sem_pending;
	while(q) {
		error = try_atomic_semop(sma, q->sops, q->nsops,
					 q->undo, q->pid);

		/* Does q->sleeper still need to sleep? */
		if (error <= 0) {
			struct sem_queue *n;
			remove_from_queue(sma,q);
			q->status = IN_WAKEUP;
			/*
			 * Continue scanning. The next operation
			 * that must be checked depends on the type of the
			 * completed operation:
			 * - if the operation modified the array, then
			 *   restart from the head of the queue and
			 *   check for threads that might be waiting
			 *   for semaphore values to become 0.
			 * - if the operation didn't modify the array,
			 *   then just continue.
			 */
			if (q->alter)
				n = sma->sem_pending;
			else
				n = q->next;
			wake_up_process(q->sleeper);
			/* hands-off: q will disappear immediately after
			 * writing q->status.
			 */
			smp_wmb();
			q->status = error;
			q = n;
		} else {
			q = q->next;
		}
	}
}

/* The following counts are associated to each semaphore:
 *   semncnt        number of tasks waiting on semval being nonzero
 *   semzcnt        number of tasks waiting on semval being zero
 * This model assumes that a task waits on exactly one semaphore.
 * Since semaphore operations are to be performed atomically, tasks actually
 * wait on a whole sequence of semaphores simultaneously.
 * The counts we return here are a rough approximation, but still
 * warrant that semncnt+semzcnt>0 if the task is on the pending queue.
 */
static int count_semncnt (struct sem_array * sma, ushort semnum)
{
	int semncnt;
	struct sem_queue * q;

	semncnt = 0;
	for (q = sma->sem_pending; q; q = q->next) {
		struct sembuf * sops = q->sops;
		int nsops = q->nsops;
		int i;
		for (i = 0; i < nsops; i++)
			if (sops[i].sem_num == semnum
			    && (sops[i].sem_op < 0)
			    && !(sops[i].sem_flg & IPC_NOWAIT))
				semncnt++;
	}
	return semncnt;
}
static int count_semzcnt (struct sem_array * sma, ushort semnum)
{
	int semzcnt;
	struct sem_queue * q;

	semzcnt = 0;
	for (q = sma->sem_pending; q; q = q->next) {
		struct sembuf * sops = q->sops;
		int nsops = q->nsops;
		int i;
		for (i = 0; i < nsops; i++)
			if (sops[i].sem_num == semnum
			    && (sops[i].sem_op == 0)
			    && !(sops[i].sem_flg & IPC_NOWAIT))
				semzcnt++;
	}
	return semzcnt;
}

/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
 * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
 * remains locked on exit.
 */
static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
	struct sem_undo *un;
	struct sem_queue *q;
	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);

	/* Invalidate the existing undo structures for this semaphore set.
	 * (They will be freed without any further action in exit_sem()
	 * or during the next semop.)
	 */
	for (un = sma->undo; un; un = un->id_next)
		un->semid = -1;

	/* Wake up all pending processes and let them fail with EIDRM. */
	q = sma->sem_pending;
	while(q) {
		struct sem_queue *n;
		/* lazy remove_from_queue: we are killing the whole queue */
		q->prev = NULL;
		n = q->next;
		q->status = IN_WAKEUP;
		wake_up_process(q->sleeper); /* doesn't sleep */
		smp_wmb();
		q->status = -EIDRM;	/* hands-off q */
		q = n;
	}

	/* Remove the semaphore set from the IDR */
	sem_rmid(ns, sma);
	sem_unlock(sma);

	ns->used_sems -= sma->sem_nsems;
	security_sem_free(sma);
	ipc_rcu_putref(sma);
}

static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
{
	switch(version) {
	case IPC_64:
		return copy_to_user(buf, in, sizeof(*in));
	case IPC_OLD:
	    {
		struct semid_ds out;

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

		out.sem_otime	= in->sem_otime;
		out.sem_ctime	= in->sem_ctime;
		out.sem_nsems	= in->sem_nsems;

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

static int semctl_nolock(struct ipc_namespace *ns, int semid,
			 int cmd, int version, union semun arg)
{
	int err = -EINVAL;
	struct sem_array *sma;

	switch(cmd) {
	case IPC_INFO:
	case SEM_INFO:
	{
		struct seminfo seminfo;
		int max_id;

		err = security_sem_semctl(NULL, cmd);
		if (err)
			return err;
		
		memset(&seminfo,0,sizeof(seminfo));
		seminfo.semmni = ns->sc_semmni;
		seminfo.semmns = ns->sc_semmns;
		seminfo.semmsl = ns->sc_semmsl;
		seminfo.semopm = ns->sc_semopm;
		seminfo.semvmx = SEMVMX;
		seminfo.semmnu = SEMMNU;
		seminfo.semmap = SEMMAP;
		seminfo.semume = SEMUME;
		down_read(&sem_ids(ns).rw_mutex);
		if (cmd == SEM_INFO) {
			seminfo.semusz = sem_ids(ns).in_use;
			seminfo.semaem = ns->used_sems;
		} else {
			seminfo.semusz = SEMUSZ;
			seminfo.semaem = SEMAEM;
		}
		max_id = ipc_get_maxid(&sem_ids(ns));
		up_read(&sem_ids(ns).rw_mutex);
		if (copy_to_user (arg.__buf, &seminfo, sizeof(struct seminfo))) 
			return -EFAULT;
		return (max_id < 0) ? 0: max_id;
	}
	case IPC_STAT:
	case SEM_STAT:
	{
		struct semid64_ds tbuf;
		int id;

		if (cmd == SEM_STAT) {
			sma = sem_lock(ns, semid);
			if (IS_ERR(sma))
				return PTR_ERR(sma);
			id = sma->sem_perm.id;
		} else {
			sma = sem_lock_check(ns, semid);
			if (IS_ERR(sma))
				return PTR_ERR(sma);
			id = 0;
		}

		err = -EACCES;
		if (ipcperms (&sma->sem_perm, S_IRUGO))
			goto out_unlock;

		err = security_sem_semctl(sma, cmd);
		if (err)
			goto out_unlock;

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

		kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
		tbuf.sem_otime  = sma->sem_otime;
		tbuf.sem_ctime  = sma->sem_ctime;
		tbuf.sem_nsems  = sma->sem_nsems;
		sem_unlock(sma);
		if (copy_semid_to_user (arg.buf, &tbuf, version))
			return -EFAULT;
		return id;
	}
	default:
		return -EINVAL;
	}
	return err;
out_unlock:
	sem_unlock(sma);
	return err;
}

static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
		int cmd, int version, union semun arg)
{
	struct sem_array *sma;
	struct sem* curr;
	int err;
	ushort fast_sem_io[SEMMSL_FAST];
	ushort* sem_io = fast_sem_io;
	int nsems;

	sma = sem_lock_check(ns, semid);
	if (IS_ERR(sma))
		return PTR_ERR(sma);

	nsems = sma->sem_nsems;

	err = -EACCES;
	if (ipcperms (&sma->sem_perm, (cmd==SETVAL||cmd==SETALL)?S_IWUGO:S_IRUGO))
		goto out_unlock;

	err = security_sem_semctl(sma, cmd);
	if (err)
		goto out_unlock;

	err = -EACCES;
	switch (cmd) {
	case GETALL:
	{
		ushort __user *array = arg.array;
		int i;

		if(nsems > SEMMSL_FAST) {
			sem_getref_and_unlock(sma);

			sem_io = ipc_alloc(sizeof(ushort)*nsems);
			if(sem_io == NULL) {
				sem_putref(sma);
				return -ENOMEM;
			}

			sem_lock_and_putref(sma);
			if (sma->sem_perm.deleted) {
				sem_unlock(sma);
				err = -EIDRM;
				goto out_free;
			}
		}

		for (i = 0; i < sma->sem_nsems; i++)
			sem_io[i] = sma->sem_base[i].semval;
		sem_unlock(sma);
		err = 0;
		if(copy_to_user(array, sem_io, nsems*sizeof(ushort)))
			err = -EFAULT;
		goto out_free;
	}
	case SETALL:
	{
		int i;
		struct sem_undo *un;

		sem_getref_and_unlock(sma);

		if(nsems > SEMMSL_FAST) {
			sem_io = ipc_alloc(sizeof(ushort)*nsems);
			if(sem_io == NULL) {
				sem_putref(sma);
				return -ENOMEM;
			}
		}

		if (copy_from_user (sem_io, arg.array, nsems*sizeof(ushort))) {
			sem_putref(sma);
			err = -EFAULT;
			goto out_free;
		}

		for (i = 0; i < nsems; i++) {
			if (sem_io[i] > SEMVMX) {
				sem_putref(sma);
				err = -ERANGE;
				goto out_free;
			}
		}
		sem_lock_and_putref(sma);
		if (sma->sem_perm.deleted) {
			sem_unlock(sma);
			err = -EIDRM;
			goto out_free;
		}

		for (i = 0; i < nsems; i++)
			sma->sem_base[i].semval = sem_io[i];
		for (un = sma->undo; un; un = un->id_next)
			for (i = 0; i < nsems; i++)
				un->semadj[i] = 0;
		sma->sem_ctime = get_seconds();
		/* maybe some queued-up processes were waiting for this */
		update_queue(sma);
		err = 0;
		goto out_unlock;
	}
	/* GETVAL, GETPID, GETNCTN, GETZCNT, SETVAL: fall-through */
	}
	err = -EINVAL;
	if(semnum < 0 || semnum >= nsems)
		goto out_unlock;

	curr = &sma->sem_base[semnum];

	switch (cmd) {
	case GETVAL:
		err = curr->semval;
		goto out_unlock;
	case GETPID:
		err = curr->sempid;
		goto out_unlock;
	case GETNCNT:
		err = count_semncnt(sma,semnum);
		goto out_unlock;
	case GETZCNT:
		err = count_semzcnt(sma,semnum);
		goto out_unlock;
	case SETVAL:
	{
		int val = arg.val;
		struct sem_undo *un;
		err = -ERANGE;
		if (val > SEMVMX || val < 0)
			goto out_unlock;

		for (un = sma->undo; un; un = un->id_next)
			un->semadj[semnum] = 0;
		curr->semval = val;
		curr->sempid = task_tgid_vnr(current);
		sma->sem_ctime = get_seconds();
		/* maybe some queued-up processes were waiting for this */
		update_queue(sma);
		err = 0;
		goto out_unlock;
	}
	}
out_unlock:
	sem_unlock(sma);
out_free:
	if(sem_io != fast_sem_io)
		ipc_free(sem_io, sizeof(ushort)*nsems);
	return err;
}

static inline unsigned long
copy_semid_from_user(struct semid64_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 semid_ds tbuf_old;

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

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

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

/*
 * This function handles some semctl 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 semctl_down(struct ipc_namespace *ns, int semid,
		       int cmd, int version, union semun arg)
{
	struct sem_array *sma;
	int err;
	struct semid64_ds semid64;
	struct kern_ipc_perm *ipcp;

	if(cmd == IPC_SET) {
		if (copy_semid_from_user(&semid64, arg.buf, version))
			return -EFAULT;
	}

	ipcp = ipcctl_pre_down(&sem_ids(ns), semid, cmd, &semid64.sem_perm, 0);
	if (IS_ERR(ipcp))
		return PTR_ERR(ipcp);

	sma = container_of(ipcp, struct sem_array, sem_perm);

	err = security_sem_semctl(sma, cmd);
	if (err)
		goto out_unlock;

	switch(cmd){
	case IPC_RMID:
		freeary(ns, ipcp);
		goto out_up;
	case IPC_SET:
		ipc_update_perm(&semid64.sem_perm, ipcp);
		sma->sem_ctime = get_seconds();
		break;
	default:
		err = -EINVAL;
	}

out_unlock:
	sem_unlock(sma);
out_up:
	up_write(&sem_ids(ns).rw_mutex);
	return err;
}

asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg)
{
	int err = -EINVAL;
	int version;
	struct ipc_namespace *ns;

	if (semid < 0)
		return -EINVAL;

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

	switch(cmd) {
	case IPC_INFO:
	case SEM_INFO:
	case IPC_STAT:
	case SEM_STAT:
		err = semctl_nolock(ns, semid, cmd, version, arg);
		return err;
	case GETALL:
	case GETVAL:
	case GETPID:
	case GETNCNT:
	case GETZCNT:
	case SETVAL:
	case SETALL:
		err = semctl_main(ns,semid,semnum,cmd,version,arg);
		return err;
	case IPC_RMID:
	case IPC_SET:
		err = semctl_down(ns, semid, cmd, version, arg);
		return err;
	default:
		return -EINVAL;
	}
}

/* If the task doesn't already have a undo_list, then allocate one
 * here.  We guarantee there is only one thread using this undo list,
 * and current is THE ONE
 *
 * If this allocation and assignment succeeds, but later
 * portions of this code fail, there is no need to free the sem_undo_list.
 * Just let it stay associated with the task, and it'll be freed later
 * at exit time.
 *
 * This can block, so callers must hold no locks.
 */
static inline int get_undo_list(struct sem_undo_list **undo_listp)
{
	struct sem_undo_list *undo_list;

	undo_list = current->sysvsem.undo_list;
	if (!undo_list) {
		undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL);
		if (undo_list == NULL)
			return -ENOMEM;
		spin_lock_init(&undo_list->lock);
		atomic_set(&undo_list->refcnt, 1);
		current->sysvsem.undo_list = undo_list;
	}
	*undo_listp = undo_list;
	return 0;
}

static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid)
{
	struct sem_undo **last, *un;

	last = &ulp->proc_list;
	un = *last;
	while(un != NULL) {
		if(un->semid==semid)
			break;
		if(un->semid==-1) {
			*last=un->proc_next;
			kfree(un);
		} else {
			last=&un->proc_next;
		}
		un=*last;
	}
	return un;
}

static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
{
	struct sem_array *sma;
	struct sem_undo_list *ulp;
	struct sem_undo *un, *new;
	int nsems;
	int error;

	error = get_undo_list(&ulp);
	if (error)
		return ERR_PTR(error);

	spin_lock(&ulp->lock);
	un = lookup_undo(ulp, semid);
	spin_unlock(&ulp->lock);
	if (likely(un!=NULL))
		goto out;

	/* no undo structure around - allocate one. */
	sma = sem_lock_check(ns, semid);
	if (IS_ERR(sma))
		return ERR_PTR(PTR_ERR(sma));

	nsems = sma->sem_nsems;
	sem_getref_and_unlock(sma);

	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
	if (!new) {
		sem_putref(sma);
		return ERR_PTR(-ENOMEM);
	}
	new->semadj = (short *) &new[1];
	new->semid = semid;

	spin_lock(&ulp->lock);
	un = lookup_undo(ulp, semid);
	if (un) {
		spin_unlock(&ulp->lock);
		kfree(new);
		sem_putref(sma);
		goto out;
	}
	sem_lock_and_putref(sma);
	if (sma->sem_perm.deleted) {
		sem_unlock(sma);
		spin_unlock(&ulp->lock);
		kfree(new);
		un = ERR_PTR(-EIDRM);
		goto out;
	}
	new->proc_next = ulp->proc_list;
	ulp->proc_list = new;
	new->id_next = sma->undo;
	sma->undo = new;
	sem_unlock(sma);
	un = new;
	spin_unlock(&ulp->lock);
out:
	return un;
}

asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops,
			unsigned nsops, const struct timespec __user *timeout)
{
	int error = -EINVAL;
	struct sem_array *sma;
	struct sembuf fast_sops[SEMOPM_FAST];
	struct sembuf* sops = fast_sops, *sop;
	struct sem_undo *un;
	int undos = 0, alter = 0, max;
	struct sem_queue queue;
	unsigned long jiffies_left = 0;
	struct ipc_namespace *ns;

	ns = current->nsproxy->ipc_ns;

	if (nsops < 1 || semid < 0)
		return -EINVAL;
	if (nsops > ns->sc_semopm)
		return -E2BIG;
	if(nsops > SEMOPM_FAST) {
		sops = kmalloc(sizeof(*sops)*nsops,GFP_KERNEL);
		if(sops==NULL)
			return -ENOMEM;
	}
	if (copy_from_user (sops, tsops, nsops * sizeof(*tsops))) {
		error=-EFAULT;
		goto out_free;
	}
	if (timeout) {
		struct timespec _timeout;
		if (copy_from_user(&_timeout, timeout, sizeof(*timeout))) {
			error = -EFAULT;
			goto out_free;
		}
		if (_timeout.tv_sec < 0 || _timeout.tv_nsec < 0 ||
			_timeout.tv_nsec >= 1000000000L) {
			error = -EINVAL;
			goto out_free;
		}
		jiffies_left = timespec_to_jiffies(&_timeout);
	}
	max = 0;
	for (sop = sops; sop < sops + nsops; sop++) {
		if (sop->sem_num >= max)
			max = sop->sem_num;
		if (sop->sem_flg & SEM_UNDO)
			undos = 1;
		if (sop->sem_op != 0)
			alter = 1;
	}

retry_undos:
	if (undos) {
		un = find_undo(ns, semid);
		if (IS_ERR(un)) {
			error = PTR_ERR(un);
			goto out_free;
		}
	} else
		un = NULL;

	sma = sem_lock_check(ns, semid);
	if (IS_ERR(sma)) {
		error = PTR_ERR(sma);
		goto out_free;
	}

	/*
	 * semid identifiers are not unique - find_undo may have
	 * allocated an undo structure, it was invalidated by an RMID
	 * and now a new array with received the same id. Check and retry.
	 */
	if (un && un->semid == -1) {
		sem_unlock(sma);
		goto retry_undos;
	}
	error = -EFBIG;
	if (max >= sma->sem_nsems)
		goto out_unlock_free;

	error = -EACCES;
	if (ipcperms(&sma->sem_perm, alter ? S_IWUGO : S_IRUGO))
		goto out_unlock_free;

	error = security_sem_semop(sma, sops, nsops, alter);
	if (error)
		goto out_unlock_free;

	error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
	if (error <= 0) {
		if (alter && error == 0)
			update_queue (sma);
		goto out_unlock_free;
	}

	/* We need to sleep on this operation, so we put the current
	 * task into the pending queue and go to sleep.
	 */
		
	queue.sma = sma;
	queue.sops = sops;
	queue.nsops = nsops;
	queue.undo = un;
	queue.pid = task_tgid_vnr(current);
	queue.id = semid;
	queue.alter = alter;
	if (alter)
		append_to_queue(sma ,&queue);
	else
		prepend_to_queue(sma ,&queue);

	queue.status = -EINTR;
	queue.sleeper = current;
	current->state = TASK_INTERRUPTIBLE;
	sem_unlock(sma);

	if (timeout)
		jiffies_left = schedule_timeout(jiffies_left);
	else
		schedule();

	error = queue.status;
	while(unlikely(error == IN_WAKEUP)) {
		cpu_relax();
		error = queue.status;
	}

	if (error != -EINTR) {
		/* fast path: update_queue already obtained all requested
		 * resources */
		goto out_free;
	}

	sma = sem_lock(ns, semid);
	if (IS_ERR(sma)) {
		BUG_ON(queue.prev != NULL);
		error = -EIDRM;
		goto out_free;
	}

	/*
	 * If queue.status != -EINTR we are woken up by another process
	 */
	error = queue.status;
	if (error != -EINTR) {
		goto out_unlock_free;
	}

	/*
	 * If an interrupt occurred we have to clean up the queue
	 */
	if (timeout && jiffies_left == 0)
		error = -EAGAIN;
	remove_from_queue(sma,&queue);
	goto out_unlock_free;

out_unlock_free:
	sem_unlock(sma);
out_free:
	if(sops != fast_sops)
		kfree(sops);
	return error;
}

asmlinkage long sys_semop (int semid, struct sembuf __user *tsops, unsigned nsops)
{
	return sys_semtimedop(semid, tsops, nsops, NULL);
}

/* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between
 * parent and child tasks.
 */

int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
{
	struct sem_undo_list *undo_list;
	int error;

	if (clone_flags & CLONE_SYSVSEM) {
		error = get_undo_list(&undo_list);
		if (error)
			return error;
		atomic_inc(&undo_list->refcnt);
		tsk->sysvsem.undo_list = undo_list;
	} else 
		tsk->sysvsem.undo_list = NULL;

	return 0;
}

/*
 * add semadj values to semaphores, free undo structures.
 * undo structures are not freed when semaphore arrays are destroyed
 * so some of them may be out of date.
 * IMPLEMENTATION NOTE: There is some confusion over whether the
 * set of adjustments that needs to be done should be done in an atomic
 * manner or not. That is, if we are attempting to decrement the semval
 * should we queue up and wait until we can do so legally?
 * The original implementation attempted to do this (queue and wait).
 * The current implementation does not do so. The POSIX standard
 * and SVID should be consulted to determine what behavior is mandated.
 */
void exit_sem(struct task_struct *tsk)
{
	struct sem_undo_list *undo_list;
	struct sem_undo *u, **up;
	struct ipc_namespace *ns;

	undo_list = tsk->sysvsem.undo_list;
	if (!undo_list)
		return;

	if (!atomic_dec_and_test(&undo_list->refcnt))
		return;

	ns = tsk->nsproxy->ipc_ns;
	/* There's no need to hold the semundo list lock, as current
         * is the last task exiting for this undo list.
	 */
	for (up = &undo_list->proc_list; (u = *up); *up = u->proc_next, kfree(u)) {
		struct sem_array *sma;
		int nsems, i;
		struct sem_undo *un, **unp;
		int semid;
	       
		semid = u->semid;

		if(semid == -1)
			continue;
		sma = sem_lock(ns, semid);
		if (IS_ERR(sma))
			continue;

		if (u->semid == -1)
			goto next_entry;

		BUG_ON(sem_checkid(sma, u->semid));

		/* remove u from the sma->undo list */
		for (unp = &sma->undo; (un = *unp); unp = &un->id_next) {
			if (u == un)
				goto found;
		}
		printk ("exit_sem undo list error id=%d\n", u->semid);
		goto next_entry;
found:
		*unp = un->id_next;
		/* perform adjustments registered in u */
		nsems = sma->sem_nsems;
		for (i = 0; i < nsems; i++) {
			struct sem * semaphore = &sma->sem_base[i];
			if (u->semadj[i]) {
				semaphore->semval += u->semadj[i];
				/*
				 * Range checks of the new semaphore value,
				 * not defined by sus:
				 * - Some unices ignore the undo entirely
				 *   (e.g. HP UX 11i 11.22, Tru64 V5.1)
				 * - some cap the value (e.g. FreeBSD caps
				 *   at 0, but doesn't enforce SEMVMX)
				 *
				 * Linux caps the semaphore value, both at 0
				 * and at SEMVMX.
				 *
				 * 	Manfred <manfred@colorfullife.com>
				 */
				if (semaphore->semval < 0)
					semaphore->semval = 0;
				if (semaphore->semval > SEMVMX)
					semaphore->semval = SEMVMX;
				semaphore->sempid = task_tgid_vnr(current);
			}
		}
		sma->sem_otime = get_seconds();
		/* maybe some queued-up processes were waiting for this */
		update_queue(sma);
next_entry:
		sem_unlock(sma);
	}
	kfree(undo_list);
}

#ifdef CONFIG_PROC_FS
static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
{
	struct sem_array *sma = it;

	return seq_printf(s,
			  "%10d %10d  %4o %10lu %5u %5u %5u %5u %10lu %10lu\n",
			  sma->sem_perm.key,
			  sma->sem_perm.id,
			  sma->sem_perm.mode,
			  sma->sem_nsems,
			  sma->sem_perm.uid,
			  sma->sem_perm.gid,
			  sma->sem_perm.cuid,
			  sma->sem_perm.cgid,
			  sma->sem_otime,
			  sma->sem_ctime);
}
#endif