aboutsummaryrefslogtreecommitdiffstats
path: root/ipc/util.c
blob: 464a8abd779fb0bc54b861bc5f4bb29347686dbe (plain) (blame)
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
/*
 * linux/ipc/util.c
 * Copyright (C) 1992 Krishna Balasubramanian
 *
 * Sep 1997 - Call suser() last after "normal" permission checks so we
 *            get BSD style process accounting right.
 *            Occurs in several places in the IPC code.
 *            Chris Evans, <chris@ferret.lmh.ox.ac.uk>
 * Nov 1999 - ipc helper functions, unified SMP locking
 *	      Manfred Spraul <manfred@colorfullife.com>
 * Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary().
 *            Mingming Cao <cmm@us.ibm.com>
 * Mar 2006 - support for audit of ipc object properties
 *            Dustin Kirkland <dustin.kirkland@us.ibm.com>
 * Jun 2006 - namespaces ssupport
 *            OpenVZ, SWsoft Inc.
 *            Pavel Emelianov <xemul@openvz.org>
 */

#include <linux/mm.h>
#include <linux/shm.h>
#include <linux/init.h>
#include <linux/msg.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include <linux/highuid.h>
#include <linux/security.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/audit.h>
#include <linux/nsproxy.h>
#include <linux/rwsem.h>
#include <linux/memory.h>
#include <linux/ipc_namespace.h>

#include <asm/unistd.h>

#include "util.h"

struct ipc_proc_iface {
	const char *path;
	const char *header;
	int ids;
	int (*show)(struct seq_file *, void *);
};

#ifdef CONFIG_MEMORY_HOTPLUG

static void ipc_memory_notifier(struct work_struct *work)
{
	ipcns_notify(IPCNS_MEMCHANGED);
}

static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);


static int ipc_memory_callback(struct notifier_block *self,
				unsigned long action, void *arg)
{
	switch (action) {
	case MEM_ONLINE:    /* memory successfully brought online */
	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
		/*
		 * This is done by invoking the ipcns notifier chain with the
		 * IPC_MEMCHANGED event.
		 * In order not to keep the lock on the hotplug memory chain
		 * for too long, queue a work item that will, when waken up,
		 * activate the ipcns notification chain.
		 * No need to keep several ipc work items on the queue.
		 */
		if (!work_pending(&ipc_memory_wq))
			schedule_work(&ipc_memory_wq);
		break;
	case MEM_GOING_ONLINE:
	case MEM_GOING_OFFLINE:
	case MEM_CANCEL_ONLINE:
	case MEM_CANCEL_OFFLINE:
	default:
		break;
	}

	return NOTIFY_OK;
}

#endif /* CONFIG_MEMORY_HOTPLUG */

/**
 *	ipc_init	-	initialise IPC subsystem
 *
 *	The various system5 IPC resources (semaphores, messages and shared
 *	memory) are initialised
 *	A callback routine is registered into the memory hotplug notifier
 *	chain: since msgmni scales to lowmem this callback routine will be
 *	called upon successful memory add / remove to recompute msmgni.
 */
 
static int __init ipc_init(void)
{
	sem_init();
	msg_init();
	shm_init();
	hotplug_memory_notifier(ipc_memory_callback, IPC_CALLBACK_PRI);
	register_ipcns_notifier(&init_ipc_ns);
	return 0;
}
__initcall(ipc_init);

/**
 *	ipc_init_ids		-	initialise IPC identifiers
 *	@ids: Identifier set
 *
 *	Set up the sequence range to use for the ipc identifier range (limited
 *	below IPCMNI) then initialise the ids idr.
 */
 
void ipc_init_ids(struct ipc_ids *ids)
{
	init_rwsem(&ids->rw_mutex);

	ids->in_use = 0;
	ids->seq = 0;
	ids->next_id = -1;
	{
		int seq_limit = INT_MAX/SEQ_MULTIPLIER;
		if (seq_limit > USHRT_MAX)
			ids->seq_max = USHRT_MAX;
		 else
		 	ids->seq_max = seq_limit;
	}

	idr_init(&ids->ipcs_idr);
}

#ifdef CONFIG_PROC_FS
static const struct file_operations sysvipc_proc_fops;
/**
 *	ipc_init_proc_interface	-  Create a proc interface for sysipc types using a seq_file interface.
 *	@path: Path in procfs
 *	@header: Banner to be printed at the beginning of the file.
 *	@ids: ipc id table to iterate.
 *	@show: show routine.
 */
void __init ipc_init_proc_interface(const char *path, const char *header,
		int ids, int (*show)(struct seq_file *, void *))
{
	struct proc_dir_entry *pde;
	struct ipc_proc_iface *iface;

	iface = kmalloc(sizeof(*iface), GFP_KERNEL);
	if (!iface)
		return;
	iface->path	= path;
	iface->header	= header;
	iface->ids	= ids;
	iface->show	= show;

	pde = proc_create_data(path,
			       S_IRUGO,        /* world readable */
			       NULL,           /* parent dir */
			       &sysvipc_proc_fops,
			       iface);
	if (!pde) {
		kfree(iface);
	}
}
#endif

/**
 *	ipc_findkey	-	find a key in an ipc identifier set	
 *	@ids: Identifier set
 *	@key: The key to find
 *	
 *	Requires ipc_ids.rw_mutex locked.
 *	Returns the LOCKED pointer to the ipc structure if found or NULL
 *	if not.
 *	If key is found ipc points to the owning ipc structure
 */
 
static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
{
	struct kern_ipc_perm *ipc;
	int next_id;
	int total;

	for (total = 0, next_id = 0; total < ids->in_use; next_id++) {
		ipc = idr_find(&ids->ipcs_idr, next_id);

		if (ipc == NULL)
			continue;

		if (ipc->key != key) {
			total++;
			continue;
		}

		ipc_lock_by_ptr(ipc);
		return ipc;
	}

	return NULL;
}

/**
 *	ipc_get_maxid 	-	get the last assigned id
 *	@ids: IPC identifier set
 *
 *	Called with ipc_ids.rw_mutex held.
 */

int ipc_get_maxid(struct ipc_ids *ids)
{
	struct kern_ipc_perm *ipc;
	int max_id = -1;
	int total, id;

	if (ids->in_use == 0)
		return -1;

	if (ids->in_use == IPCMNI)
		return IPCMNI - 1;

	/* Look for the last assigned id */
	total = 0;
	for (id = 0; id < IPCMNI && total < ids->in_use; id++) {
		ipc = idr_find(&ids->ipcs_idr, id);
		if (ipc != NULL) {
			max_id = id;
			total++;
		}
	}
	return max_id;
}

/**
 *	ipc_addid 	-	add an IPC identifier
 *	@ids: IPC identifier set
 *	@new: new IPC permission set
 *	@size: limit for the number of used ids
 *
 *	Add an entry 'new' to the IPC ids idr. The permissions object is
 *	initialised and the first free entry is set up and the id assigned
 *	is returned. The 'new' entry is returned in a locked state on success.
 *	On failure the entry is not locked and a negative err-code is returned.
 *
 *	Called with ipc_ids.rw_mutex held as a writer.
 */
 
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
	kuid_t euid;
	kgid_t egid;
	int id;
	int next_id = ids->next_id;

	if (size > IPCMNI)
		size = IPCMNI;

	if (ids->in_use >= size)
		return -ENOSPC;

	idr_preload(GFP_KERNEL);

	spin_lock_init(&new->lock);
	new->deleted = 0;
	rcu_read_lock();
	spin_lock(&new->lock);

	id = idr_alloc(&ids->ipcs_idr, new,
		       (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
		       GFP_NOWAIT);
	idr_preload_end();
	if (id < 0) {
		spin_unlock(&new->lock);
		rcu_read_unlock();
		return id;
	}

	ids->in_use++;

	current_euid_egid(&euid, &egid);
	new->cuid = new->uid = euid;
	new->gid = new->cgid = egid;

	if (next_id < 0) {
		new->seq = ids->seq++;
		if (ids->seq > ids->seq_max)
			ids->seq = 0;
	} else {
		new->seq = ipcid_to_seqx(next_id);
		ids->next_id = -1;
	}

	new->id = ipc_buildid(id, new->seq);
	return id;
}

/**
 *	ipcget_new	-	create a new ipc object
 *	@ns: namespace
 *	@ids: IPC identifer set
 *	@ops: the actual creation routine to call
 *	@params: its parameters
 *
 *	This routine is called by sys_msgget, sys_semget() and sys_shmget()
 *	when the key is IPC_PRIVATE.
 */
static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
		struct ipc_ops *ops, struct ipc_params *params)
{
	int err;

	down_write(&ids->rw_mutex);
	err = ops->getnew(ns, params);
	up_write(&ids->rw_mutex);
	return err;
}

/**
 *	ipc_check_perms	-	check security and permissions for an IPC
 *	@ns: IPC namespace
 *	@ipcp: ipc permission set
 *	@ops: the actual security routine to call
 *	@params: its parameters
 *
 *	This routine is called by sys_msgget(), sys_semget() and sys_shmget()
 *      when the key is not IPC_PRIVATE and that key already exists in the
 *      ids IDR.
 *
 *	On success, the IPC id is returned.
 *
 *	It is called with ipc_ids.rw_mutex and ipcp->lock held.
 */
static int ipc_check_perms(struct ipc_namespace *ns,
			   struct kern_ipc_perm *ipcp,
			   struct ipc_ops *ops,
			   struct ipc_params *params)
{
	int err;

	if (ipcperms(ns, ipcp, params->flg))
		err = -EACCES;
	else {
		err = ops->associate(ipcp, params->flg);
		if (!err)
			err = ipcp->id;
	}

	return err;
}

/**
 *	ipcget_public	-	get an ipc object or create a new one
 *	@ns: namespace
 *	@ids: IPC identifer set
 *	@ops: the actual creation routine to call
 *	@params: its parameters
 *
 *	This routine is called by sys_msgget, sys_semget() and sys_shmget()
 *	when the key is not IPC_PRIVATE.
 *	It adds a new entry if the key is not found and does some permission
 *      / security checkings if the key is found.
 *
 *	On success, the ipc id is returned.
 */
static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
		struct ipc_ops *ops, struct ipc_params *params)
{
	struct kern_ipc_perm *ipcp;
	int flg = params->flg;
	int err;

	/*
	 * Take the lock as a writer since we are potentially going to add
	 * a new entry + read locks are not "upgradable"
	 */
	down_write(&ids->rw_mutex);
	ipcp = ipc_findkey(ids, params->key);
	if (ipcp == NULL) {
		/* key not used */
		if (!(flg & IPC_CREAT))
			err = -ENOENT;
		else
			err = ops->getnew(ns, params);
	} else {
		/* ipc object has been locked by ipc_findkey() */

		if (flg & IPC_CREAT && flg & IPC_EXCL)
			err = -EEXIST;
		else {
			err = 0;
			if (ops->more_checks)
				err = ops->more_checks(ipcp, params);
			if (!err)
				/*
				 * ipc_check_perms returns the IPC id on
				 * success
				 */
				err = ipc_check_perms(ns, ipcp, ops, params);
		}
		ipc_unlock(ipcp);
	}
	up_write(&ids->rw_mutex);

	return err;
}


/**
 *	ipc_rmid	-	remove an IPC identifier
 *	@ids: IPC identifier set
 *	@ipcp: ipc perm structure containing the identifier to remove
 *
 *	ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
 *	before this function is called, and remain locked on the exit.
 */
 
void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
	int lid = ipcid_to_idx(ipcp->id);

	idr_remove(&ids->ipcs_idr, lid);

	ids->in_use--;

	ipcp->deleted = 1;

	return;
}

/**
 *	ipc_alloc	-	allocate ipc space
 *	@size: size desired
 *
 *	Allocate memory from the appropriate pools and return a pointer to it.
 *	NULL is returned if the allocation fails
 */
 
void* ipc_alloc(int size)
{
	void* out;
	if(size > PAGE_SIZE)
		out = vmalloc(size);
	else
		out = kmalloc(size, GFP_KERNEL);
	return out;
}

/**
 *	ipc_free        -       free ipc space
 *	@ptr: pointer returned by ipc_alloc
 *	@size: size of block
 *
 *	Free a block created with ipc_alloc(). The caller must know the size
 *	used in the allocation call.
 */

void ipc_free(void* ptr, int size)
{
	if(size > PAGE_SIZE)
		vfree(ptr);
	else
		kfree(ptr);
}

/*
 * rcu allocations:
 * There are three headers that are prepended to the actual allocation:
 * - during use: ipc_rcu_hdr.
 * - during the rcu grace period: ipc_rcu_grace.
 * - [only if vmalloc]: ipc_rcu_sched.
 * Their lifetime doesn't overlap, thus the headers share the same memory.
 * Unlike a normal union, they are right-aligned, thus some container_of
 * forward/backward casting is necessary:
 */
struct ipc_rcu_hdr
{
	int refcount;
	int is_vmalloc;
	void *data[0];
};


struct ipc_rcu_grace
{
	struct rcu_head rcu;
	/* "void *" makes sure alignment of following data is sane. */
	void *data[0];
};

struct ipc_rcu_sched
{
	struct work_struct work;
	/* "void *" makes sure alignment of following data is sane. */
	void *data[0];
};

#define HDRLEN_KMALLOC		(sizeof(struct ipc_rcu_grace) > sizeof(struct ipc_rcu_hdr) ? \
					sizeof(struct ipc_rcu_grace) : sizeof(struct ipc_rcu_hdr))
#define HDRLEN_VMALLOC		(sizeof(struct ipc_rcu_sched) > HDRLEN_KMALLOC ? \
					sizeof(struct ipc_rcu_sched) : HDRLEN_KMALLOC)

static inline int rcu_use_vmalloc(int size)
{
	/* Too big for a single page? */
	if (HDRLEN_KMALLOC + size > PAGE_SIZE)
		return 1;
	return 0;
}

/**
 *	ipc_rcu_alloc	-	allocate ipc and rcu space 
 *	@size: size desired
 *
 *	Allocate memory for the rcu header structure +  the object.
 *	Returns the pointer to the object.
 *	NULL is returned if the allocation fails. 
 */
 
void* ipc_rcu_alloc(int size)
{
	void* out;
	/* 
	 * We prepend the allocation with the rcu struct, and
	 * workqueue if necessary (for vmalloc). 
	 */
	if (rcu_use_vmalloc(size)) {
		out = vmalloc(HDRLEN_VMALLOC + size);
		if (out) {
			out += HDRLEN_VMALLOC;
			container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 1;
			container_of(out, struct ipc_rcu_hdr, data)->refcount = 1;
		}
	} else {
		out = kmalloc(HDRLEN_KMALLOC + size, GFP_KERNEL);
		if (out) {
			out += HDRLEN_KMALLOC;
			container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 0;
			container_of(out, struct ipc_rcu_hdr, data)->refcount = 1;
		}
	}

	return out;
}

void ipc_rcu_getref(void *ptr)
{
	container_of(ptr, struct ipc_rcu_hdr, data)->refcount++;
}

static void ipc_do_vfree(struct work_struct *work)
{
	vfree(container_of(work, struct ipc_rcu_sched, work));
}

/**
 * ipc_schedule_free - free ipc + rcu space
 * @head: RCU callback structure for queued work
 * 
 * Since RCU callback function is called in bh,
 * we need to defer the vfree to schedule_work().
 */
static void ipc_schedule_free(struct rcu_head *head)
{
	struct ipc_rcu_grace *grace;
	struct ipc_rcu_sched *sched;

	grace = container_of(head, struct ipc_rcu_grace, rcu);
	sched = container_of(&(grace->data[0]), struct ipc_rcu_sched,
				data[0]);

	INIT_WORK(&sched->work, ipc_do_vfree);
	schedule_work(&sched->work);
}

void ipc_rcu_putref(void *ptr)
{
	if (--container_of(ptr, struct ipc_rcu_hdr, data)->refcount > 0)
		return;

	if (container_of(ptr, struct ipc_rcu_hdr, data)->is_vmalloc) {
		call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu,
				ipc_schedule_free);
	} else {
		kfree_rcu(container_of(ptr, struct ipc_rcu_grace, data), rcu);
	}
}

/**
 *	ipcperms	-	check IPC permissions
 *	@ns: IPC namespace
 *	@ipcp: IPC permission set
 *	@flag: desired permission set.
 *
 *	Check user, group, other permissions for access
 *	to ipc resources. return 0 if allowed
 *
 * 	@flag will most probably be 0 or S_...UGO from <linux/stat.h>
 */
 
int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag)
{
	kuid_t euid = current_euid();
	int requested_mode, granted_mode;

	audit_ipc_obj(ipcp);
	requested_mode = (flag >> 6) | (flag >> 3) | flag;
	granted_mode = ipcp->mode;
	if (uid_eq(euid, ipcp->cuid) ||
	    uid_eq(euid, ipcp->uid))
		granted_mode >>= 6;
	else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid))
		granted_mode >>= 3;
	/* is there some bit set in requested_mode but not in granted_mode? */
	if ((requested_mode & ~granted_mode & 0007) && 
	    !ns_capable(ns->user_ns, CAP_IPC_OWNER))
		return -1;

	return security_ipc_permission(ipcp, flag);
}

/*
 * Functions to convert between the kern_ipc_perm structure and the
 * old/new ipc_perm structures
 */

/**
 *	kernel_to_ipc64_perm	-	convert kernel ipc permissions to user
 *	@in: kernel permissions
 *	@out: new style IPC permissions
 *
 *	Turn the kernel object @in into a set of permissions descriptions
 *	for returning to userspace (@out).
 */
 

void kernel_to_ipc64_perm (struct kern_ipc_perm *in, struct ipc64_perm *out)
{
	out->key	= in->key;
	out->uid	= from_kuid_munged(current_user_ns(), in->uid);
	out->gid	= from_kgid_munged(current_user_ns(), in->gid);
	out->cuid	= from_kuid_munged(current_user_ns(), in->cuid);
	out->cgid	= from_kgid_munged(current_user_ns(), in->cgid);
	out->mode	= in->mode;
	out->seq	= in->seq;
}

/**
 *	ipc64_perm_to_ipc_perm	-	convert new ipc permissions to old
 *	@in: new style IPC permissions
 *	@out: old style IPC permissions
 *
 *	Turn the new style permissions object @in into a compatibility
 *	object and store it into the @out pointer.
 */
 
void ipc64_perm_to_ipc_perm (struct ipc64_perm *in, struct ipc_perm *out)
{
	out->key	= in->key;
	SET_UID(out->uid, in->uid);
	SET_GID(out->gid, in->gid);
	SET_UID(out->cuid, in->cuid);
	SET_GID(out->cgid, in->cgid);
	out->mode	= in->mode;
	out->seq	= in->seq;
}

/**
 * ipc_lock - Lock an ipc structure without rw_mutex held
 * @ids: IPC identifier set
 * @id: ipc id to look for
 *
 * Look for an id in the ipc ids idr and lock the associated ipc object.
 *
 * The ipc object is locked on exit.
 */

struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
{
	struct kern_ipc_perm *out;
	int lid = ipcid_to_idx(id);

	rcu_read_lock();
	out = idr_find(&ids->ipcs_idr, lid);
	if (out == NULL) {
		rcu_read_unlock();
		return ERR_PTR(-EINVAL);
	}

	spin_lock(&out->lock);
	
	/* ipc_rmid() may have already freed the ID while ipc_lock
	 * was spinning: here verify that the structure is still valid
	 */
	if (out->deleted) {
		spin_unlock(&out->lock);
		rcu_read_unlock();
		return ERR_PTR(-EINVAL);
	}

	return out;
}

struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
{
	struct kern_ipc_perm *out;

	out = ipc_lock(ids, id);
	if (IS_ERR(out))
		return out;

	if (ipc_checkid(out, id)) {
		ipc_unlock(out);
		return ERR_PTR(-EIDRM);
	}

	return out;
}

/**
 * ipcget - Common sys_*get() code
 * @ns : namsepace
 * @ids : IPC identifier set
 * @ops : operations to be called on ipc object creation, permission checks
 *        and further checks
 * @params : the parameters needed by the previous operations.
 *
 * Common routine called by sys_msgget(), sys_semget() and sys_shmget().
 */
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
			struct ipc_ops *ops, struct ipc_params *params)
{
	if (params->key == IPC_PRIVATE)
		return ipcget_new(ns, ids, ops, params);
	else
		return ipcget_public(ns, ids, ops, params);
}

/**
 * ipc_update_perm - update the permissions of an IPC.
 * @in:  the permission given as input.
 * @out: the permission of the ipc to set.
 */
int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
{
	kuid_t uid = make_kuid(current_user_ns(), in->uid);
	kgid_t gid = make_kgid(current_user_ns(), in->gid);
	if (!uid_valid(uid) || !gid_valid(gid))
		return -EINVAL;

	out->uid = uid;
	out->gid = gid;
	out->mode = (out->mode & ~S_IRWXUGO)
		| (in->mode & S_IRWXUGO);

	return 0;
}

/**
 * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
 * @ns:  the ipc namespace
 * @ids:  the table of ids where to look for the ipc
 * @id:   the id of the ipc to retrieve
 * @cmd:  the cmd to check
 * @perm: the permission to set
 * @extra_perm: one extra permission parameter used by msq
 *
 * This function does some common audit and permissions check for some IPC_XXX
 * cmd and is called from semctl_down, shmctl_down and msgctl_down.
 * It must be called without any lock held and
 *  - retrieves the ipc with the given id in the given table.
 *  - performs some audit and permission check, depending on the given cmd
 *  - returns the ipc with both ipc and rw_mutex locks held in case of success
 *    or an err-code without any lock held otherwise.
 */
struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
				      struct ipc_ids *ids, int id, int cmd,
				      struct ipc64_perm *perm, int extra_perm)
{
	struct kern_ipc_perm *ipcp;
	kuid_t euid;
	int err;

	down_write(&ids->rw_mutex);
	ipcp = ipc_lock_check(ids, id);
	if (IS_ERR(ipcp)) {
		err = PTR_ERR(ipcp);
		goto out_up;
	}

	audit_ipc_obj(ipcp);
	if (cmd == IPC_SET)
		audit_ipc_set_perm(extra_perm, perm->uid,
					 perm->gid, perm->mode);

	euid = current_euid();
	if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)  ||
	    ns_capable(ns->user_ns, CAP_SYS_ADMIN))
		return ipcp;

	err = -EPERM;
	ipc_unlock(ipcp);
out_up:
	up_write(&ids->rw_mutex);
	return ERR_PTR(err);
}

#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION


/**
 *	ipc_parse_version	-	IPC call version
 *	@cmd: pointer to command
 *
 *	Return IPC_64 for new style IPC and IPC_OLD for old style IPC. 
 *	The @cmd value is turned from an encoding command and version into
 *	just the command code.
 */
 
int ipc_parse_version (int *cmd)
{
	if (*cmd & IPC_64) {
		*cmd ^= IPC_64;
		return IPC_64;
	} else {
		return IPC_OLD;
	}
}

#endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */

#ifdef CONFIG_PROC_FS
struct ipc_proc_iter {
	struct ipc_namespace *ns;
	struct ipc_proc_iface *iface;
};

/*
 * This routine locks the ipc structure found at least at position pos.
 */
static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
					      loff_t *new_pos)
{
	struct kern_ipc_perm *ipc;
	int total, id;

	total = 0;
	for (id = 0; id < pos && total < ids->in_use; id++) {
		ipc = idr_find(&ids->ipcs_idr, id);
		if (ipc != NULL)
			total++;
	}

	if (total >= ids->in_use)
		return NULL;

	for ( ; pos < IPCMNI; pos++) {
		ipc = idr_find(&ids->ipcs_idr, pos);
		if (ipc != NULL) {
			*new_pos = pos + 1;
			ipc_lock_by_ptr(ipc);
			return ipc;
		}
	}

	/* Out of range - return NULL to terminate iteration */
	return NULL;
}

static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos)
{
	struct ipc_proc_iter *iter = s->private;
	struct ipc_proc_iface *iface = iter->iface;
	struct kern_ipc_perm *ipc = it;

	/* If we had an ipc id locked before, unlock it */
	if (ipc && ipc != SEQ_START_TOKEN)
		ipc_unlock(ipc);

	return sysvipc_find_ipc(&iter->ns->ids[iface->ids], *pos, pos);
}

/*
 * File positions: pos 0 -> header, pos n -> ipc id = n - 1.
 * SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START.
 */
static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
{
	struct ipc_proc_iter *iter = s->private;
	struct ipc_proc_iface *iface = iter->iface;
	struct ipc_ids *ids;

	ids = &iter->ns->ids[iface->ids];

	/*
	 * Take the lock - this will be released by the corresponding
	 * call to stop().
	 */
	down_read(&ids->rw_mutex);

	/* pos < 0 is invalid */
	if (*pos < 0)
		return NULL;

	/* pos == 0 means header */
	if (*pos == 0)
		return SEQ_START_TOKEN;

	/* Find the (pos-1)th ipc */
	return sysvipc_find_ipc(ids, *pos - 1, pos);
}

static void sysvipc_proc_stop(struct seq_file *s, void *it)
{
	struct kern_ipc_perm *ipc = it;
	struct ipc_proc_iter *iter = s->private;
	struct ipc_proc_iface *iface = iter->iface;
	struct ipc_ids *ids;

	/* If we had a locked structure, release it */
	if (ipc && ipc != SEQ_START_TOKEN)
		ipc_unlock(ipc);

	ids = &iter->ns->ids[iface->ids];
	/* Release the lock we took in start() */
	up_read(&ids->rw_mutex);
}

static int sysvipc_proc_show(struct seq_file *s, void *it)
{
	struct ipc_proc_iter *iter = s->private;
	struct ipc_proc_iface *iface = iter->iface;

	if (it == SEQ_START_TOKEN)
		return seq_puts(s, iface->header);

	return iface->show(s, it);
}

static const struct seq_operations sysvipc_proc_seqops = {
	.start = sysvipc_proc_start,
	.stop  = sysvipc_proc_stop,
	.next  = sysvipc_proc_next,
	.show  = sysvipc_proc_show,
};

static int sysvipc_proc_open(struct inode *inode, struct file *file)
{
	int ret;
	struct seq_file *seq;
	struct ipc_proc_iter *iter;

	ret = -ENOMEM;
	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		goto out;

	ret = seq_open(file, &sysvipc_proc_seqops);
	if (ret)
		goto out_kfree;

	seq = file->private_data;
	seq->private = iter;

	iter->iface = PDE(inode)->data;
	iter->ns    = get_ipc_ns(current->nsproxy->ipc_ns);
out:
	return ret;
out_kfree:
	kfree(iter);
	goto out;
}

static int sysvipc_proc_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct ipc_proc_iter *iter = seq->private;
	put_ipc_ns(iter->ns);
	return seq_release_private(inode, file);
}

static const struct file_operations sysvipc_proc_fops = {
	.open    = sysvipc_proc_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = sysvipc_proc_release,
};
#endif /* CONFIG_PROC_FS */