aboutsummaryrefslogtreecommitdiffstats
path: root/net/compat.c
blob: 67fb6a3834a3a538221b347c309842cda1816521 (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
/*
 * 32bit Socket syscall emulation. Based on arch/sparc64/kernel/sys_sparc32.c.
 *
 * Copyright (C) 2000		VA Linux Co
 * Copyright (C) 2000		Don Dugger <n0ano@valinux.com>
 * Copyright (C) 1999 		Arun Sharma <arun.sharma@intel.com>
 * Copyright (C) 1997,1998 	Jakub Jelinek (jj@sunsite.mff.cuni.cz)
 * Copyright (C) 1997 		David S. Miller (davem@caip.rutgers.edu)
 * Copyright (C) 2000		Hewlett-Packard Co.
 * Copyright (C) 2000		David Mosberger-Tang <davidm@hpl.hp.com>
 * Copyright (C) 2000,2001	Andi Kleen, SuSE Labs
 */

#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/file.h>
#include <linux/icmpv6.h>
#include <linux/socket.h>
#include <linux/syscalls.h>
#include <linux/filter.h>
#include <linux/compat.h>
#include <linux/security.h>

#include <net/scm.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <asm/uaccess.h>
#include <net/compat.h>

static inline int iov_from_user_compat_to_kern(struct iovec *kiov,
					  struct compat_iovec __user *uiov32,
					  int niov)
{
	int tot_len = 0;

	while (niov > 0) {
		compat_uptr_t buf;
		compat_size_t len;

		if (get_user(len, &uiov32->iov_len) ||
		   get_user(buf, &uiov32->iov_base)) {
			tot_len = -EFAULT;
			break;
		}
		tot_len += len;
		kiov->iov_base = compat_ptr(buf);
		kiov->iov_len = (__kernel_size_t) len;
		uiov32++;
		kiov++;
		niov--;
	}
	return tot_len;
}

int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
{
	compat_uptr_t tmp1, tmp2, tmp3;

	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
	    __get_user(tmp1, &umsg->msg_name) ||
	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
	    __get_user(tmp2, &umsg->msg_iov) ||
	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
	    __get_user(tmp3, &umsg->msg_control) ||
	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
		return -EFAULT;
	kmsg->msg_name = compat_ptr(tmp1);
	kmsg->msg_iov = compat_ptr(tmp2);
	kmsg->msg_control = compat_ptr(tmp3);
	return 0;
}

/* I've named the args so it is easy to tell whose space the pointers are in. */
int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
		   struct sockaddr *kern_address, int mode)
{
	int tot_len;

	if (kern_msg->msg_namelen) {
		if (mode==VERIFY_READ) {
			int err = move_addr_to_kernel(kern_msg->msg_name,
						      kern_msg->msg_namelen,
						      kern_address);
			if (err < 0)
				return err;
		}
		kern_msg->msg_name = kern_address;
	} else
		kern_msg->msg_name = NULL;

	tot_len = iov_from_user_compat_to_kern(kern_iov,
					  (struct compat_iovec __user *)kern_msg->msg_iov,
					  kern_msg->msg_iovlen);
	if (tot_len >= 0)
		kern_msg->msg_iov = kern_iov;

	return tot_len;
}

/* Bleech... */
#define CMSG_COMPAT_ALIGN(len)	ALIGN((len), sizeof(s32))

#define CMSG_COMPAT_DATA(cmsg)				\
	((void __user *)((char __user *)(cmsg) + CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr))))
#define CMSG_COMPAT_SPACE(len)				\
	(CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)) + CMSG_COMPAT_ALIGN(len))
#define CMSG_COMPAT_LEN(len)				\
	(CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)) + (len))

#define CMSG_COMPAT_FIRSTHDR(msg)			\
	(((msg)->msg_controllen) >= sizeof(struct compat_cmsghdr) ?	\
	 (struct compat_cmsghdr __user *)((msg)->msg_control) :		\
	 (struct compat_cmsghdr __user *)NULL)

#define CMSG_COMPAT_OK(ucmlen, ucmsg, mhdr) \
	((ucmlen) >= sizeof(struct compat_cmsghdr) && \
	 (ucmlen) <= (unsigned long) \
	 ((mhdr)->msg_controllen - \
	  ((char *)(ucmsg) - (char *)(mhdr)->msg_control)))

static inline struct compat_cmsghdr __user *cmsg_compat_nxthdr(struct msghdr *msg,
		struct compat_cmsghdr __user *cmsg, int cmsg_len)
{
	char __user *ptr = (char __user *)cmsg + CMSG_COMPAT_ALIGN(cmsg_len);
	if ((unsigned long)(ptr + 1 - (char __user *)msg->msg_control) >
			msg->msg_controllen)
		return NULL;
	return (struct compat_cmsghdr __user *)ptr;
}

/* There is a lot of hair here because the alignment rules (and
 * thus placement) of cmsg headers and length are different for
 * 32-bit apps.  -DaveM
 */
int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk,
			       unsigned char *stackbuf, int stackbuf_size)
{
	struct compat_cmsghdr __user *ucmsg;
	struct cmsghdr *kcmsg, *kcmsg_base;
	compat_size_t ucmlen;
	__kernel_size_t kcmlen, tmp;
	int err = -EFAULT;

	kcmlen = 0;
	kcmsg_base = kcmsg = (struct cmsghdr *)stackbuf;
	ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg);
	while (ucmsg != NULL) {
		if (get_user(ucmlen, &ucmsg->cmsg_len))
			return -EFAULT;

		/* Catch bogons. */
		if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg))
			return -EINVAL;

		tmp = ((ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg))) +
		       CMSG_ALIGN(sizeof(struct cmsghdr)));
		tmp = CMSG_ALIGN(tmp);
		kcmlen += tmp;
		ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
	}
	if (kcmlen == 0)
		return -EINVAL;

	/* The kcmlen holds the 64-bit version of the control length.
	 * It may not be modified as we do not stick it into the kmsg
	 * until we have successfully copied over all of the data
	 * from the user.
	 */
	if (kcmlen > stackbuf_size)
		kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL);
	if (kcmsg == NULL)
		return -ENOBUFS;

	/* Now copy them over neatly. */
	memset(kcmsg, 0, kcmlen);
	ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg);
	while (ucmsg != NULL) {
		if (__get_user(ucmlen, &ucmsg->cmsg_len))
			goto Efault;
		if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg))
			goto Einval;
		tmp = ((ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg))) +
		       CMSG_ALIGN(sizeof(struct cmsghdr)));
		if ((char *)kcmsg_base + kcmlen - (char *)kcmsg < CMSG_ALIGN(tmp))
			goto Einval;
		kcmsg->cmsg_len = tmp;
		tmp = CMSG_ALIGN(tmp);
		if (__get_user(kcmsg->cmsg_level, &ucmsg->cmsg_level) ||
		    __get_user(kcmsg->cmsg_type, &ucmsg->cmsg_type) ||
		    copy_from_user(CMSG_DATA(kcmsg),
				   CMSG_COMPAT_DATA(ucmsg),
				   (ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg)))))
			goto Efault;

		/* Advance. */
		kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp);
		ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
	}

	/* Ok, looks like we made it.  Hook it up and return success. */
	kmsg->msg_control = kcmsg_base;
	kmsg->msg_controllen = kcmlen;
	return 0;

Einval:
	err = -EINVAL;
Efault:
	if (kcmsg_base != (struct cmsghdr *)stackbuf)
		sock_kfree_s(sk, kcmsg_base, kcmlen);
	return err;
}

int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
{
	struct compat_timeval ctv;
	struct compat_timespec cts;
	struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
	struct compat_cmsghdr cmhdr;
	int cmlen;

	if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) {
		kmsg->msg_flags |= MSG_CTRUNC;
		return 0; /* XXX: return error? check spec. */
	}

	if (level == SOL_SOCKET && type == SO_TIMESTAMP) {
		struct timeval *tv = (struct timeval *)data;
		ctv.tv_sec = tv->tv_sec;
		ctv.tv_usec = tv->tv_usec;
		data = &ctv;
		len = sizeof(ctv);
	}
	if (level == SOL_SOCKET && type == SO_TIMESTAMPNS) {
		struct timespec *ts = (struct timespec *)data;
		cts.tv_sec = ts->tv_sec;
		cts.tv_nsec = ts->tv_nsec;
		data = &cts;
		len = sizeof(cts);
	}

	cmlen = CMSG_COMPAT_LEN(len);
	if (kmsg->msg_controllen < cmlen) {
		kmsg->msg_flags |= MSG_CTRUNC;
		cmlen = kmsg->msg_controllen;
	}
	cmhdr.cmsg_level = level;
	cmhdr.cmsg_type = type;
	cmhdr.cmsg_len = cmlen;

	if (copy_to_user(cm, &cmhdr, sizeof cmhdr))
		return -EFAULT;
	if (copy_to_user(CMSG_COMPAT_DATA(cm), data, cmlen - sizeof(struct compat_cmsghdr)))
		return -EFAULT;
	cmlen = CMSG_COMPAT_SPACE(len);
	if (kmsg->msg_controllen < cmlen)
		cmlen = kmsg->msg_controllen;
	kmsg->msg_control += cmlen;
	kmsg->msg_controllen -= cmlen;
	return 0;
}

void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
{
	struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
	int fdmax = (kmsg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int);
	int fdnum = scm->fp->count;
	struct file **fp = scm->fp->fp;
	int __user *cmfptr;
	int err = 0, i;

	if (fdnum < fdmax)
		fdmax = fdnum;

	for (i = 0, cmfptr = (int __user *) CMSG_COMPAT_DATA(cm); i < fdmax; i++, cmfptr++) {
		int new_fd;
		err = security_file_receive(fp[i]);
		if (err)
			break;
		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & kmsg->msg_flags
					  ? O_CLOEXEC : 0);
		if (err < 0)
			break;
		new_fd = err;
		err = put_user(new_fd, cmfptr);
		if (err) {
			put_unused_fd(new_fd);
			break;
		}
		/* Bump the usage count and install the file. */
		get_file(fp[i]);
		fd_install(new_fd, fp[i]);
	}

	if (i > 0) {
		int cmlen = CMSG_COMPAT_LEN(i * sizeof(int));
		err = put_user(SOL_SOCKET, &cm->cmsg_level);
		if (!err)
			err = put_user(SCM_RIGHTS, &cm->cmsg_type);
		if (!err)
			err = put_user(cmlen, &cm->cmsg_len);
		if (!err) {
			cmlen = CMSG_COMPAT_SPACE(i * sizeof(int));
			kmsg->msg_control += cmlen;
			kmsg->msg_controllen -= cmlen;
		}
	}
	if (i < fdnum)
		kmsg->msg_flags |= MSG_CTRUNC;

	/*
	 * All of the files that fit in the message have had their
	 * usage counts incremented, so we just free the list.
	 */
	__scm_destroy(scm);
}

/*
 * A struct sock_filter is architecture independent.
 */
struct compat_sock_fprog {
	u16		len;
	compat_uptr_t	filter;		/* struct sock_filter * */
};

static int do_set_attach_filter(struct socket *sock, int level, int optname,
				char __user *optval, int optlen)
{
	struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval;
	struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog));
	compat_uptr_t ptr;
	u16 len;

	if (!access_ok(VERIFY_READ, fprog32, sizeof(*fprog32)) ||
	    !access_ok(VERIFY_WRITE, kfprog, sizeof(struct sock_fprog)) ||
	    __get_user(len, &fprog32->len) ||
	    __get_user(ptr, &fprog32->filter) ||
	    __put_user(len, &kfprog->len) ||
	    __put_user(compat_ptr(ptr), &kfprog->filter))
		return -EFAULT;

	return sock_setsockopt(sock, level, optname, (char __user *)kfprog,
			      sizeof(struct sock_fprog));
}

static int do_set_sock_timeout(struct socket *sock, int level,
		int optname, char __user *optval, int optlen)
{
	struct compat_timeval __user *up = (struct compat_timeval __user *) optval;
	struct timeval ktime;
	mm_segment_t old_fs;
	int err;

	if (optlen < sizeof(*up))
		return -EINVAL;
	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
	    __get_user(ktime.tv_sec, &up->tv_sec) ||
	    __get_user(ktime.tv_usec, &up->tv_usec))
		return -EFAULT;
	old_fs = get_fs();
	set_fs(KERNEL_DS);
	err = sock_setsockopt(sock, level, optname, (char *) &ktime, sizeof(ktime));
	set_fs(old_fs);

	return err;
}

static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
				char __user *optval, int optlen)
{
	if (optname == SO_ATTACH_FILTER)
		return do_set_attach_filter(sock, level, optname,
					    optval, optlen);
	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
		return do_set_sock_timeout(sock, level, optname, optval, optlen);

	return sock_setsockopt(sock, level, optname, optval, optlen);
}

asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
				char __user *optval, int optlen)
{
	int err;
	struct socket *sock;

	if (optlen < 0)
		return -EINVAL;

	if ((sock = sockfd_lookup(fd, &err))!=NULL)
	{
		err = security_socket_setsockopt(sock,level,optname);
		if (err) {
			sockfd_put(sock);
			return err;
		}

		if (level == SOL_SOCKET)
			err = compat_sock_setsockopt(sock, level,
					optname, optval, optlen);
		else if (sock->ops->compat_setsockopt)
			err = sock->ops->compat_setsockopt(sock, level,
					optname, optval, optlen);
		else
			err = sock->ops->setsockopt(sock, level,
					optname, optval, optlen);
		sockfd_put(sock);
	}
	return err;
}

static int do_get_sock_timeout(struct socket *sock, int level, int optname,
		char __user *optval, int __user *optlen)
{
	struct compat_timeval __user *up;
	struct timeval ktime;
	mm_segment_t old_fs;
	int len, err;

	up = (struct compat_timeval __user *) optval;
	if (get_user(len, optlen))
		return -EFAULT;
	if (len < sizeof(*up))
		return -EINVAL;
	len = sizeof(ktime);
	old_fs = get_fs();
	set_fs(KERNEL_DS);
	err = sock_getsockopt(sock, level, optname, (char *) &ktime, &len);
	set_fs(old_fs);

	if (!err) {
		if (put_user(sizeof(*up), optlen) ||
		    !access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
		    __put_user(ktime.tv_sec, &up->tv_sec) ||
		    __put_user(ktime.tv_usec, &up->tv_usec))
			err = -EFAULT;
	}
	return err;
}

static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
				char __user *optval, int __user *optlen)
{
	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
		return do_get_sock_timeout(sock, level, optname, optval, optlen);
	return sock_getsockopt(sock, level, optname, optval, optlen);
}

int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
	struct compat_timeval __user *ctv =
			(struct compat_timeval __user*) userstamp;
	int err = -ENOENT;
	struct timeval tv;

	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk);
	tv = ktime_to_timeval(sk->sk_stamp);
	if (tv.tv_sec == -1)
		return err;
	if (tv.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		tv = ktime_to_timeval(sk->sk_stamp);
	}
	err = 0;
	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
			put_user(tv.tv_usec, &ctv->tv_usec))
		err = -EFAULT;
	return err;
}
EXPORT_SYMBOL(compat_sock_get_timestamp);

int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
	struct compat_timespec __user *ctv =
			(struct compat_timespec __user*) userstamp;
	int err = -ENOENT;
	struct timespec ts;

	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk);
	ts = ktime_to_timespec(sk->sk_stamp);
	if (ts.tv_sec == -1)
		return err;
	if (ts.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		ts = ktime_to_timespec(sk->sk_stamp);
	}
	err = 0;
	if (put_user(ts.tv_sec, &ctv->tv_sec) ||
			put_user(ts.tv_nsec, &ctv->tv_nsec))
		err = -EFAULT;
	return err;
}
EXPORT_SYMBOL(compat_sock_get_timestampns);

asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
				char __user *optval, int __user *optlen)
{
	int err;
	struct socket *sock;

	if ((sock = sockfd_lookup(fd, &err))!=NULL)
	{
		err = security_socket_getsockopt(sock, level,
							   optname);
		if (err) {
			sockfd_put(sock);
			return err;
		}

		if (level == SOL_SOCKET)
			err = compat_sock_getsockopt(sock, level,
					optname, optval, optlen);
		else if (sock->ops->compat_getsockopt)
			err = sock->ops->compat_getsockopt(sock, level,
					optname, optval, optlen);
		else
			err = sock->ops->getsockopt(sock, level,
					optname, optval, optlen);
		sockfd_put(sock);
	}
	return err;
}

struct compat_group_req {
	__u32				 gr_interface;
	struct __kernel_sockaddr_storage gr_group
		__attribute__ ((aligned(4)));
} __attribute__ ((packed));

struct compat_group_source_req {
	__u32				 gsr_interface;
	struct __kernel_sockaddr_storage gsr_group
		__attribute__ ((aligned(4)));
	struct __kernel_sockaddr_storage gsr_source
		__attribute__ ((aligned(4)));
} __attribute__ ((packed));

struct compat_group_filter {
	__u32				 gf_interface;
	struct __kernel_sockaddr_storage gf_group
		__attribute__ ((aligned(4)));
	__u32				 gf_fmode;
	__u32				 gf_numsrc;
	struct __kernel_sockaddr_storage gf_slist[1]
		__attribute__ ((aligned(4)));
} __attribute__ ((packed));

#define __COMPAT_GF0_SIZE (sizeof(struct compat_group_filter) - \
			sizeof(struct __kernel_sockaddr_storage))


int compat_mc_setsockopt(struct sock *sock, int level, int optname,
	char __user *optval, int optlen,
	int (*setsockopt)(struct sock *,int,int,char __user *,int))
{
	char __user	*koptval = optval;
	int		koptlen = optlen;

	switch (optname) {
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct compat_group_req __user *gr32 = (void *)optval;
		struct group_req __user *kgr =
			compat_alloc_user_space(sizeof(struct group_req));
		u32 interface;

		if (!access_ok(VERIFY_READ, gr32, sizeof(*gr32)) ||
		    !access_ok(VERIFY_WRITE, kgr, sizeof(struct group_req)) ||
		    __get_user(interface, &gr32->gr_interface) ||
		    __put_user(interface, &kgr->gr_interface) ||
		    copy_in_user(&kgr->gr_group, &gr32->gr_group,
				sizeof(kgr->gr_group)))
			return -EFAULT;
		koptval = (char __user *)kgr;
		koptlen = sizeof(struct group_req);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct compat_group_source_req __user *gsr32 = (void *)optval;
		struct group_source_req __user *kgsr = compat_alloc_user_space(
			sizeof(struct group_source_req));
		u32 interface;

		if (!access_ok(VERIFY_READ, gsr32, sizeof(*gsr32)) ||
		    !access_ok(VERIFY_WRITE, kgsr,
			sizeof(struct group_source_req)) ||
		    __get_user(interface, &gsr32->gsr_interface) ||
		    __put_user(interface, &kgsr->gsr_interface) ||
		    copy_in_user(&kgsr->gsr_group, &gsr32->gsr_group,
				sizeof(kgsr->gsr_group)) ||
		    copy_in_user(&kgsr->gsr_source, &gsr32->gsr_source,
				sizeof(kgsr->gsr_source)))
			return -EFAULT;
		koptval = (char __user *)kgsr;
		koptlen = sizeof(struct group_source_req);
		break;
	}
	case MCAST_MSFILTER:
	{
		struct compat_group_filter __user *gf32 = (void *)optval;
		struct group_filter __user *kgf;
		u32 interface, fmode, numsrc;

		if (!access_ok(VERIFY_READ, gf32, __COMPAT_GF0_SIZE) ||
		    __get_user(interface, &gf32->gf_interface) ||
		    __get_user(fmode, &gf32->gf_fmode) ||
		    __get_user(numsrc, &gf32->gf_numsrc))
			return -EFAULT;
		koptlen = optlen + sizeof(struct group_filter) -
				sizeof(struct compat_group_filter);
		if (koptlen < GROUP_FILTER_SIZE(numsrc))
			return -EINVAL;
		kgf = compat_alloc_user_space(koptlen);
		if (!access_ok(VERIFY_WRITE, kgf, koptlen) ||
		    __put_user(interface, &kgf->gf_interface) ||
		    __put_user(fmode, &kgf->gf_fmode) ||
		    __put_user(numsrc, &kgf->gf_numsrc) ||
		    copy_in_user(&kgf->gf_group, &gf32->gf_group,
				sizeof(kgf->gf_group)) ||
		    (numsrc && copy_in_user(kgf->gf_slist, gf32->gf_slist,
				numsrc * sizeof(kgf->gf_slist[0]))))
			return -EFAULT;
		koptval = (char __user *)kgf;
		break;
	}

	default:
		break;
	}
	return setsockopt(sock, level, optname, koptval, koptlen);
}

EXPORT_SYMBOL(compat_mc_setsockopt);

int compat_mc_getsockopt(struct sock *sock, int level, int optname,
	char __user *optval, int __user *optlen,
	int (*getsockopt)(struct sock *,int,int,char __user *,int __user *))
{
	struct compat_group_filter __user *gf32 = (void *)optval;
	struct group_filter __user *kgf;
	int __user	*koptlen;
	u32 interface, fmode, numsrc;
	int klen, ulen, err;

	if (optname != MCAST_MSFILTER)
		return getsockopt(sock, level, optname, optval, optlen);

	koptlen = compat_alloc_user_space(sizeof(*koptlen));
	if (!access_ok(VERIFY_READ, optlen, sizeof(*optlen)) ||
	    __get_user(ulen, optlen))
		return -EFAULT;

	/* adjust len for pad */
	klen = ulen + sizeof(*kgf) - sizeof(*gf32);

	if (klen < GROUP_FILTER_SIZE(0))
		return -EINVAL;

	if (!access_ok(VERIFY_WRITE, koptlen, sizeof(*koptlen)) ||
	    __put_user(klen, koptlen))
		return -EFAULT;

	/* have to allow space for previous compat_alloc_user_space, too */
	kgf = compat_alloc_user_space(klen+sizeof(*optlen));

	if (!access_ok(VERIFY_READ, gf32, __COMPAT_GF0_SIZE) ||
	    __get_user(interface, &gf32->gf_interface) ||
	    __get_user(fmode, &gf32->gf_fmode) ||
	    __get_user(numsrc, &gf32->gf_numsrc) ||
	    __put_user(interface, &kgf->gf_interface) ||
	    __put_user(fmode, &kgf->gf_fmode) ||
	    __put_user(numsrc, &kgf->gf_numsrc) ||
	    copy_in_user(&kgf->gf_group,&gf32->gf_group,sizeof(kgf->gf_group)))
		return -EFAULT;

	err = getsockopt(sock, level, optname, (char __user *)kgf, koptlen);
	if (err)
		return err;

	if (!access_ok(VERIFY_READ, koptlen, sizeof(*koptlen)) ||
	    __get_user(klen, koptlen))
		return -EFAULT;

	ulen = klen - (sizeof(*kgf)-sizeof(*gf32));

	if (!access_ok(VERIFY_WRITE, optlen, sizeof(*optlen)) ||
	    __put_user(ulen, optlen))
		return -EFAULT;

	if (!access_ok(VERIFY_READ, kgf, klen) ||
	    !access_ok(VERIFY_WRITE, gf32, ulen) ||
	    __get_user(interface, &kgf->gf_interface) ||
	    __get_user(fmode, &kgf->gf_fmode) ||
	    __get_user(numsrc, &kgf->gf_numsrc) ||
	    __put_user(interface, &gf32->gf_interface) ||
	    __put_user(fmode, &gf32->gf_fmode) ||
	    __put_user(numsrc, &gf32->gf_numsrc))
		return -EFAULT;
	if (numsrc) {
		int copylen;

		klen -= GROUP_FILTER_SIZE(0);
		copylen = numsrc * sizeof(gf32->gf_slist[0]);
		if (copylen > klen)
			copylen = klen;
	        if (copy_in_user(gf32->gf_slist, kgf->gf_slist, copylen))
			return -EFAULT;
	}
	return err;
}

EXPORT_SYMBOL(compat_mc_getsockopt);


/* Argument list sizes for compat_sys_socketcall */
#define AL(x) ((x) * sizeof(u32))
static unsigned char nas[19]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
				AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
				AL(6),AL(2),AL(5),AL(5),AL(3),AL(3),
				AL(6)};
#undef AL

asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags)
{
	return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
}

asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
{
	return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
}

asmlinkage long compat_sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr,
				   int __user *upeer_addrlen,
				   const compat_sigset_t __user *sigmask,
				   compat_size_t sigsetsize, int flags)
{
	compat_sigset_t ss32;
	sigset_t ksigmask, sigsaved;
	int ret;

	if (sigmask) {
		if (sigsetsize != sizeof(compat_sigset_t))
			return -EINVAL;
		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
			return -EFAULT;
		sigset_from_compat(&ksigmask, &ss32);

		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
	}

	ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags);

	if (ret == -ERESTARTNOHAND) {
		/*
		 * Don't restore the signal mask yet. Let do_signal() deliver
		 * the signal on the way back to userspace, before the signal
		 * mask is restored.
		 */
		if (sigmask) {
			memcpy(&current->saved_sigmask, &sigsaved,
			       sizeof(sigsaved));
			set_restore_sigmask();
		}
	} else if (sigmask)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	return ret;
}

asmlinkage long compat_sys_socketcall(int call, u32 __user *args)
{
	int ret;
	u32 a[6];
	u32 a0, a1;

	if (call < SYS_SOCKET || call > SYS_PACCEPT)
		return -EINVAL;
	if (copy_from_user(a, args, nas[call]))
		return -EFAULT;
	a0 = a[0];
	a1 = a[1];

	switch (call) {
	case SYS_SOCKET:
		ret = sys_socket(a0, a1, a[2]);
		break;
	case SYS_BIND:
		ret = sys_bind(a0, compat_ptr(a1), a[2]);
		break;
	case SYS_CONNECT:
		ret = sys_connect(a0, compat_ptr(a1), a[2]);
		break;
	case SYS_LISTEN:
		ret = sys_listen(a0, a1);
		break;
	case SYS_ACCEPT:
		ret = do_accept(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
		break;
	case SYS_GETSOCKNAME:
		ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
		break;
	case SYS_GETPEERNAME:
		ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
		break;
	case SYS_SOCKETPAIR:
		ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
		break;
	case SYS_SEND:
		ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
		break;
	case SYS_SENDTO:
		ret = sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]);
		break;
	case SYS_RECV:
		ret = sys_recv(a0, compat_ptr(a1), a[2], a[3]);
		break;
	case SYS_RECVFROM:
		ret = sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), compat_ptr(a[5]));
		break;
	case SYS_SHUTDOWN:
		ret = sys_shutdown(a0,a1);
		break;
	case SYS_SETSOCKOPT:
		ret = compat_sys_setsockopt(a0, a1, a[2],
				compat_ptr(a[3]), a[4]);
		break;
	case SYS_GETSOCKOPT:
		ret = compat_sys_getsockopt(a0, a1, a[2],
				compat_ptr(a[3]), compat_ptr(a[4]));
		break;
	case SYS_SENDMSG:
		ret = compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
		break;
	case SYS_RECVMSG:
		ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]);
		break;
	case SYS_PACCEPT:
		ret = compat_sys_paccept(a0, compat_ptr(a1), compat_ptr(a[2]),
					 compat_ptr(a[3]), a[4], a[5]);
		break;
	default:
		ret = -EINVAL;
		break;
	}
	return ret;
}
#n3974'>3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700
/*
 *  NSA Security-Enhanced Linux (SELinux) security module
 *
 *  This file contains the SELinux hook function implementations.
 *
 *  Authors:  Stephen Smalley, <sds@epoch.ncsc.mil>
 *	      Chris Vance, <cvance@nai.com>
 *	      Wayne Salamon, <wsalamon@nai.com>
 *	      James Morris <jmorris@redhat.com>
 *
 *  Copyright (C) 2001,2002 Networks Associates Technology, Inc.
 *  Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com>
 *					   Eric Paris <eparis@redhat.com>
 *  Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
 *			    <dgoeddel@trustedcs.com>
 *  Copyright (C) 2006, 2007 Hewlett-Packard Development Company, L.P.
 *		Paul Moore <paul.moore@hp.com>
 *  Copyright (C) 2007 Hitachi Software Engineering Co., Ltd.
 *		       Yuichi Nakamura <ynakam@hitachisoft.jp>
 *
 *	This program is free software; you can redistribute it and/or modify
 *	it under the terms of the GNU General Public License version 2,
 *	as published by the Free Software Foundation.
 */

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/tracehook.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/security.h>
#include <linux/xattr.h>
#include <linux/capability.h>
#include <linux/unistd.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/tty.h>
#include <net/icmp.h>
#include <net/ip.h>		/* for local_port_range[] */
#include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
#include <net/net_namespace.h>
#include <net/netlabel.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>	/* for network interface checks */
#include <linux/netlink.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/dccp.h>
#include <linux/quota.h>
#include <linux/un.h>		/* for Unix socket types */
#include <net/af_unix.h>	/* for Unix socket types */
#include <linux/parser.h>
#include <linux/nfs_mount.h>
#include <net/ipv6.h>
#include <linux/hugetlb.h>
#include <linux/personality.h>
#include <linux/sysctl.h>
#include <linux/audit.h>
#include <linux/string.h>
#include <linux/selinux.h>
#include <linux/mutex.h>
#include <linux/posix-timers.h>

#include "avc.h"
#include "objsec.h"
#include "netif.h"
#include "netnode.h"
#include "netport.h"
#include "xfrm.h"
#include "netlabel.h"
#include "audit.h"

#define XATTR_SELINUX_SUFFIX "selinux"
#define XATTR_NAME_SELINUX XATTR_SECURITY_PREFIX XATTR_SELINUX_SUFFIX

#define NUM_SEL_MNT_OPTS 5

extern unsigned int policydb_loaded_version;
extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm);
extern struct security_operations *security_ops;

/* SECMARK reference count */
atomic_t selinux_secmark_refcount = ATOMIC_INIT(0);

#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
int selinux_enforcing;

static int __init enforcing_setup(char *str)
{
	unsigned long enforcing;
	if (!strict_strtoul(str, 0, &enforcing))
		selinux_enforcing = enforcing ? 1 : 0;
	return 1;
}
__setup("enforcing=", enforcing_setup);
#endif

#ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM
int selinux_enabled = CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE;

static int __init selinux_enabled_setup(char *str)
{
	unsigned long enabled;
	if (!strict_strtoul(str, 0, &enabled))
		selinux_enabled = enabled ? 1 : 0;
	return 1;
}
__setup("selinux=", selinux_enabled_setup);
#else
int selinux_enabled = 1;
#endif


/*
 * Minimal support for a secondary security module,
 * just to allow the use of the capability module.
 */
static struct security_operations *secondary_ops;

/* Lists of inode and superblock security structures initialized
   before the policy was loaded. */
static LIST_HEAD(superblock_security_head);
static DEFINE_SPINLOCK(sb_security_lock);

static struct kmem_cache *sel_inode_cache;

/**
 * selinux_secmark_enabled - Check to see if SECMARK is currently enabled
 *
 * Description:
 * This function checks the SECMARK reference counter to see if any SECMARK
 * targets are currently configured, if the reference counter is greater than
 * zero SECMARK is considered to be enabled.  Returns true (1) if SECMARK is
 * enabled, false (0) if SECMARK is disabled.
 *
 */
static int selinux_secmark_enabled(void)
{
	return (atomic_read(&selinux_secmark_refcount) > 0);
}

/*
 * initialise the security for the init task
 */
static void cred_init_security(void)
{
	struct cred *cred = (struct cred *) current->real_cred;
	struct task_security_struct *tsec;

	tsec = kzalloc(sizeof(struct task_security_struct), GFP_KERNEL);
	if (!tsec)
		panic("SELinux:  Failed to initialize initial task.\n");

	tsec->osid = tsec->sid = SECINITSID_KERNEL;
	cred->security = tsec;
}

/*
 * get the security ID of a set of credentials
 */
static inline u32 cred_sid(const struct cred *cred)
{
	const struct task_security_struct *tsec;

	tsec = cred->security;
	return tsec->sid;
}

/*
 * get the objective security ID of a task
 */
static inline u32 task_sid(const struct task_struct *task)
{
	u32 sid;

	rcu_read_lock();
	sid = cred_sid(__task_cred(task));
	rcu_read_unlock();
	return sid;
}

/*
 * get the subjective security ID of the current task
 */
static inline u32 current_sid(void)
{
	const struct task_security_struct *tsec = current_cred()->security;

	return tsec->sid;
}

/* Allocate and free functions for each kind of security blob. */

static int inode_alloc_security(struct inode *inode)
{
	struct inode_security_struct *isec;
	u32 sid = current_sid();

	isec = kmem_cache_zalloc(sel_inode_cache, GFP_NOFS);
	if (!isec)
		return -ENOMEM;

	mutex_init(&isec->lock);
	INIT_LIST_HEAD(&isec->list);
	isec->inode = inode;
	isec->sid = SECINITSID_UNLABELED;
	isec->sclass = SECCLASS_FILE;
	isec->task_sid = sid;
	inode->i_security = isec;

	return 0;
}

static void inode_free_security(struct inode *inode)
{
	struct inode_security_struct *isec = inode->i_security;
	struct superblock_security_struct *sbsec = inode->i_sb->s_security;

	spin_lock(&sbsec->isec_lock);
	if (!list_empty(&isec->list))
		list_del_init(&isec->list);
	spin_unlock(&sbsec->isec_lock);

	inode->i_security = NULL;
	kmem_cache_free(sel_inode_cache, isec);
}

static int file_alloc_security(struct file *file)
{
	struct file_security_struct *fsec;
	u32 sid = current_sid();

	fsec = kzalloc(sizeof(struct file_security_struct), GFP_KERNEL);
	if (!fsec)
		return -ENOMEM;

	fsec->sid = sid;
	fsec->fown_sid = sid;
	file->f_security = fsec;

	return 0;
}

static void file_free_security(struct file *file)
{
	struct file_security_struct *fsec = file->f_security;
	file->f_security = NULL;
	kfree(fsec);
}

static int superblock_alloc_security(struct super_block *sb)
{
	struct superblock_security_struct *sbsec;

	sbsec = kzalloc(sizeof(struct superblock_security_struct), GFP_KERNEL);
	if (!sbsec)
		return -ENOMEM;

	mutex_init(&sbsec->lock);
	INIT_LIST_HEAD(&sbsec->list);
	INIT_LIST_HEAD(&sbsec->isec_head);
	spin_lock_init(&sbsec->isec_lock);
	sbsec->sb = sb;
	sbsec->sid = SECINITSID_UNLABELED;
	sbsec->def_sid = SECINITSID_FILE;
	sbsec->mntpoint_sid = SECINITSID_UNLABELED;
	sb->s_security = sbsec;

	return 0;
}

static void superblock_free_security(struct super_block *sb)
{
	struct superblock_security_struct *sbsec = sb->s_security;

	spin_lock(&sb_security_lock);
	if (!list_empty(&sbsec->list))
		list_del_init(&sbsec->list);
	spin_unlock(&sb_security_lock);

	sb->s_security = NULL;
	kfree(sbsec);
}

static int sk_alloc_security(struct sock *sk, int family, gfp_t priority)
{
	struct sk_security_struct *ssec;

	ssec = kzalloc(sizeof(*ssec), priority);
	if (!ssec)
		return -ENOMEM;

	ssec->peer_sid = SECINITSID_UNLABELED;
	ssec->sid = SECINITSID_UNLABELED;
	sk->sk_security = ssec;

	selinux_netlbl_sk_security_reset(ssec);

	return 0;
}

static void sk_free_security(struct sock *sk)
{
	struct sk_security_struct *ssec = sk->sk_security;

	sk->sk_security = NULL;
	selinux_netlbl_sk_security_free(ssec);
	kfree(ssec);
}

/* The security server must be initialized before
   any labeling or access decisions can be provided. */
extern int ss_initialized;

/* The file system's label must be initialized prior to use. */

static char *labeling_behaviors[6] = {
	"uses xattr",
	"uses transition SIDs",
	"uses task SIDs",
	"uses genfs_contexts",
	"not configured for labeling",
	"uses mountpoint labeling",
};

static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry);

static inline int inode_doinit(struct inode *inode)
{
	return inode_doinit_with_dentry(inode, NULL);
}

enum {
	Opt_error = -1,
	Opt_context = 1,
	Opt_fscontext = 2,
	Opt_defcontext = 3,
	Opt_rootcontext = 4,
	Opt_labelsupport = 5,
};

static const match_table_t tokens = {
	{Opt_context, CONTEXT_STR "%s"},
	{Opt_fscontext, FSCONTEXT_STR "%s"},
	{Opt_defcontext, DEFCONTEXT_STR "%s"},
	{Opt_rootcontext, ROOTCONTEXT_STR "%s"},
	{Opt_labelsupport, LABELSUPP_STR},
	{Opt_error, NULL},
};

#define SEL_MOUNT_FAIL_MSG "SELinux:  duplicate or incompatible mount options\n"

static int may_context_mount_sb_relabel(u32 sid,
			struct superblock_security_struct *sbsec,
			const struct cred *cred)
{
	const struct task_security_struct *tsec = cred->security;
	int rc;

	rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELFROM, NULL);
	if (rc)
		return rc;

	rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELTO, NULL);
	return rc;
}

static int may_context_mount_inode_relabel(u32 sid,
			struct superblock_security_struct *sbsec,
			const struct cred *cred)
{
	const struct task_security_struct *tsec = cred->security;
	int rc;
	rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__RELABELFROM, NULL);
	if (rc)
		return rc;

	rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM,
			  FILESYSTEM__ASSOCIATE, NULL);
	return rc;
}

static int sb_finish_set_opts(struct super_block *sb)
{
	struct superblock_security_struct *sbsec = sb->s_security;
	struct dentry *root = sb->s_root;
	struct inode *root_inode = root->d_inode;
	int rc = 0;

	if (sbsec->behavior == SECURITY_FS_USE_XATTR) {
		/* Make sure that the xattr handler exists and that no
		   error other than -ENODATA is returned by getxattr on
		   the root directory.  -ENODATA is ok, as this may be
		   the first boot of the SELinux kernel before we have
		   assigned xattr values to the filesystem. */
		if (!root_inode->i_op->getxattr) {
			printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
			       "xattr support\n", sb->s_id, sb->s_type->name);
			rc = -EOPNOTSUPP;
			goto out;
		}
		rc = root_inode->i_op->getxattr(root, XATTR_NAME_SELINUX, NULL, 0);
		if (rc < 0 && rc != -ENODATA) {
			if (rc == -EOPNOTSUPP)
				printk(KERN_WARNING "SELinux: (dev %s, type "
				       "%s) has no security xattr handler\n",
				       sb->s_id, sb->s_type->name);
			else
				printk(KERN_WARNING "SELinux: (dev %s, type "
				       "%s) getxattr errno %d\n", sb->s_id,
				       sb->s_type->name, -rc);
			goto out;
		}
	}

	sbsec->flags |= (SE_SBINITIALIZED | SE_SBLABELSUPP);

	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
		       sb->s_id, sb->s_type->name);
	else
		printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n",
		       sb->s_id, sb->s_type->name,
		       labeling_behaviors[sbsec->behavior-1]);

	if (sbsec->behavior == SECURITY_FS_USE_GENFS ||
	    sbsec->behavior == SECURITY_FS_USE_MNTPOINT ||
	    sbsec->behavior == SECURITY_FS_USE_NONE ||
	    sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
		sbsec->flags &= ~SE_SBLABELSUPP;

	/* Initialize the root inode. */
	rc = inode_doinit_with_dentry(root_inode, root);

	/* Initialize any other inodes associated with the superblock, e.g.
	   inodes created prior to initial policy load or inodes created
	   during get_sb by a pseudo filesystem that directly
	   populates itself. */
	spin_lock(&sbsec->isec_lock);
next_inode:
	if (!list_empty(&sbsec->isec_head)) {
		struct inode_security_struct *isec =
				list_entry(sbsec->isec_head.next,
					   struct inode_security_struct, list);
		struct inode *inode = isec->inode;
		spin_unlock(&sbsec->isec_lock);
		inode = igrab(inode);
		if (inode) {
			if (!IS_PRIVATE(inode))
				inode_doinit(inode);
			iput(inode);
		}
		spin_lock(&sbsec->isec_lock);
		list_del_init(&isec->list);
		goto next_inode;
	}
	spin_unlock(&sbsec->isec_lock);
out:
	return rc;
}

/*
 * This function should allow an FS to ask what it's mount security
 * options were so it can use those later for submounts, displaying
 * mount options, or whatever.
 */
static int selinux_get_mnt_opts(const struct super_block *sb,
				struct security_mnt_opts *opts)
{
	int rc = 0, i;
	struct superblock_security_struct *sbsec = sb->s_security;
	char *context = NULL;
	u32 len;
	char tmp;

	security_init_mnt_opts(opts);

	if (!(sbsec->flags & SE_SBINITIALIZED))
		return -EINVAL;

	if (!ss_initialized)
		return -EINVAL;

	tmp = sbsec->flags & SE_MNTMASK;
	/* count the number of mount options for this sb */
	for (i = 0; i < 8; i++) {
		if (tmp & 0x01)
			opts->num_mnt_opts++;
		tmp >>= 1;
	}
	/* Check if the Label support flag is set */
	if (sbsec->flags & SE_SBLABELSUPP)
		opts->num_mnt_opts++;

	opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
	if (!opts->mnt_opts) {
		rc = -ENOMEM;
		goto out_free;
	}

	opts->mnt_opts_flags = kcalloc(opts->num_mnt_opts, sizeof(int), GFP_ATOMIC);
	if (!opts->mnt_opts_flags) {
		rc = -ENOMEM;
		goto out_free;
	}

	i = 0;
	if (sbsec->flags & FSCONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = FSCONTEXT_MNT;
	}
	if (sbsec->flags & CONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->mntpoint_sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = CONTEXT_MNT;
	}
	if (sbsec->flags & DEFCONTEXT_MNT) {
		rc = security_sid_to_context(sbsec->def_sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = DEFCONTEXT_MNT;
	}
	if (sbsec->flags & ROOTCONTEXT_MNT) {
		struct inode *root = sbsec->sb->s_root->d_inode;
		struct inode_security_struct *isec = root->i_security;

		rc = security_sid_to_context(isec->sid, &context, &len);
		if (rc)
			goto out_free;
		opts->mnt_opts[i] = context;
		opts->mnt_opts_flags[i++] = ROOTCONTEXT_MNT;
	}
	if (sbsec->flags & SE_SBLABELSUPP) {
		opts->mnt_opts[i] = NULL;
		opts->mnt_opts_flags[i++] = SE_SBLABELSUPP;
	}

	BUG_ON(i != opts->num_mnt_opts);

	return 0;

out_free:
	security_free_mnt_opts(opts);
	return rc;
}

static int bad_option(struct superblock_security_struct *sbsec, char flag,
		      u32 old_sid, u32 new_sid)
{
	char mnt_flags = sbsec->flags & SE_MNTMASK;

	/* check if the old mount command had the same options */
	if (sbsec->flags & SE_SBINITIALIZED)
		if (!(sbsec->flags & flag) ||
		    (old_sid != new_sid))
			return 1;

	/* check if we were passed the same options twice,
	 * aka someone passed context=a,context=b
	 */
	if (!(sbsec->flags & SE_SBINITIALIZED))
		if (mnt_flags & flag)
			return 1;
	return 0;
}

/*
 * Allow filesystems with binary mount data to explicitly set mount point
 * labeling information.
 */
static int selinux_set_mnt_opts(struct super_block *sb,
				struct security_mnt_opts *opts)
{
	const struct cred *cred = current_cred();
	int rc = 0, i;
	struct superblock_security_struct *sbsec = sb->s_security;
	const char *name = sb->s_type->name;
	struct inode *inode = sbsec->sb->s_root->d_inode;
	struct inode_security_struct *root_isec = inode->i_security;
	u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
	u32 defcontext_sid = 0;
	char **mount_options = opts->mnt_opts;
	int *flags = opts->mnt_opts_flags;
	int num_opts = opts->num_mnt_opts;

	mutex_lock(&sbsec->lock);

	if (!ss_initialized) {
		if (!num_opts) {
			/* Defer initialization until selinux_complete_init,
			   after the initial policy is loaded and the security
			   server is ready to handle calls. */
			spin_lock(&sb_security_lock);
			if (list_empty(&sbsec->list))
				list_add(&sbsec->list, &superblock_security_head);
			spin_unlock(&sb_security_lock);
			goto out;
		}
		rc = -EINVAL;
		printk(KERN_WARNING "SELinux: Unable to set superblock options "
			"before the security server is initialized\n");
		goto out;
	}

	/*
	 * Binary mount data FS will come through this function twice.  Once
	 * from an explicit call and once from the generic calls from the vfs.
	 * Since the generic VFS calls will not contain any security mount data
	 * we need to skip the double mount verification.
	 *
	 * This does open a hole in which we will not notice if the first
	 * mount using this sb set explict options and a second mount using
	 * this sb does not set any security options.  (The first options
	 * will be used for both mounts)
	 */
	if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)
	    && (num_opts == 0))
		goto out;

	/*
	 * parse the mount options, check if they are valid sids.
	 * also check if someone is trying to mount the same sb more
	 * than once with different security options.
	 */
	for (i = 0; i < num_opts; i++) {
		u32 sid;

		if (flags[i] == SE_SBLABELSUPP)
			continue;
		rc = security_context_to_sid(mount_options[i],
					     strlen(mount_options[i]), &sid);
		if (rc) {
			printk(KERN_WARNING "SELinux: security_context_to_sid"
			       "(%s) failed for (dev %s, type %s) errno=%d\n",
			       mount_options[i], sb->s_id, name, rc);
			goto out;
		}
		switch (flags[i]) {
		case FSCONTEXT_MNT:
			fscontext_sid = sid;

			if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
					fscontext_sid))
				goto out_double_mount;

			sbsec->flags |= FSCONTEXT_MNT;
			break;
		case CONTEXT_MNT:
			context_sid = sid;

			if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
					context_sid))
				goto out_double_mount;

			sbsec->flags |= CONTEXT_MNT;
			break;
		case ROOTCONTEXT_MNT:
			rootcontext_sid = sid;

			if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
					rootcontext_sid))
				goto out_double_mount;

			sbsec->flags |= ROOTCONTEXT_MNT;

			break;
		case DEFCONTEXT_MNT:
			defcontext_sid = sid;

			if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
					defcontext_sid))
				goto out_double_mount;

			sbsec->flags |= DEFCONTEXT_MNT;

			break;
		default:
			rc = -EINVAL;
			goto out;
		}
	}

	if (sbsec->flags & SE_SBINITIALIZED) {
		/* previously mounted with options, but not on this attempt? */
		if ((sbsec->flags & SE_MNTMASK) && !num_opts)
			goto out_double_mount;
		rc = 0;
		goto out;
	}

	if (strcmp(sb->s_type->name, "proc") == 0)
		sbsec->flags |= SE_SBPROC;

	/* Determine the labeling behavior to use for this filesystem type. */
	rc = security_fs_use((sbsec->flags & SE_SBPROC) ? "proc" : sb->s_type->name, &sbsec->behavior, &sbsec->sid);
	if (rc) {
		printk(KERN_WARNING "%s: security_fs_use(%s) returned %d\n",
		       __func__, sb->s_type->name, rc);
		goto out;
	}

	/* sets the context of the superblock for the fs being mounted. */
	if (fscontext_sid) {
		rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred);
		if (rc)
			goto out;

		sbsec->sid = fscontext_sid;
	}

	/*
	 * Switch to using mount point labeling behavior.
	 * sets the label used on all file below the mountpoint, and will set
	 * the superblock context if not already set.
	 */
	if (context_sid) {
		if (!fscontext_sid) {
			rc = may_context_mount_sb_relabel(context_sid, sbsec,
							  cred);
			if (rc)
				goto out;
			sbsec->sid = context_sid;
		} else {
			rc = may_context_mount_inode_relabel(context_sid, sbsec,
							     cred);
			if (rc)
				goto out;
		}
		if (!rootcontext_sid)
			rootcontext_sid = context_sid;

		sbsec->mntpoint_sid = context_sid;
		sbsec->behavior = SECURITY_FS_USE_MNTPOINT;
	}

	if (rootcontext_sid) {
		rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec,
						     cred);
		if (rc)
			goto out;

		root_isec->sid = rootcontext_sid;
		root_isec->initialized = 1;
	}

	if (defcontext_sid) {
		if (sbsec->behavior != SECURITY_FS_USE_XATTR) {
			rc = -EINVAL;
			printk(KERN_WARNING "SELinux: defcontext option is "
			       "invalid for this filesystem type\n");
			goto out;
		}

		if (defcontext_sid != sbsec->def_sid) {
			rc = may_context_mount_inode_relabel(defcontext_sid,
							     sbsec, cred);
			if (rc)
				goto out;
		}

		sbsec->def_sid = defcontext_sid;
	}

	rc = sb_finish_set_opts(sb);
out:
	mutex_unlock(&sbsec->lock);
	return rc;
out_double_mount:
	rc = -EINVAL;
	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, different "
	       "security settings for (dev %s, type %s)\n", sb->s_id, name);
	goto out;
}

static void selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
					struct super_block *newsb)
{
	const struct superblock_security_struct *oldsbsec = oldsb->s_security;
	struct superblock_security_struct *newsbsec = newsb->s_security;

	int set_fscontext =	(oldsbsec->flags & FSCONTEXT_MNT);
	int set_context =	(oldsbsec->flags & CONTEXT_MNT);
	int set_rootcontext =	(oldsbsec->flags & ROOTCONTEXT_MNT);

	/*
	 * if the parent was able to be mounted it clearly had no special lsm
	 * mount options.  thus we can safely put this sb on the list and deal
	 * with it later
	 */
	if (!ss_initialized) {
		spin_lock(&sb_security_lock);
		if (list_empty(&newsbsec->list))
			list_add(&newsbsec->list, &superblock_security_head);
		spin_unlock(&sb_security_lock);
		return;
	}

	/* how can we clone if the old one wasn't set up?? */
	BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED));

	/* if fs is reusing a sb, just let its options stand... */
	if (newsbsec->flags & SE_SBINITIALIZED)
		return;

	mutex_lock(&newsbsec->lock);

	newsbsec->flags = oldsbsec->flags;

	newsbsec->sid = oldsbsec->sid;
	newsbsec->def_sid = oldsbsec->def_sid;
	newsbsec->behavior = oldsbsec->behavior;

	if (set_context) {
		u32 sid = oldsbsec->mntpoint_sid;

		if (!set_fscontext)
			newsbsec->sid = sid;
		if (!set_rootcontext) {
			struct inode *newinode = newsb->s_root->d_inode;
			struct inode_security_struct *newisec = newinode->i_security;
			newisec->sid = sid;
		}
		newsbsec->mntpoint_sid = sid;
	}
	if (set_rootcontext) {
		const struct inode *oldinode = oldsb->s_root->d_inode;
		const struct inode_security_struct *oldisec = oldinode->i_security;
		struct inode *newinode = newsb->s_root->d_inode;
		struct inode_security_struct *newisec = newinode->i_security;

		newisec->sid = oldisec->sid;
	}

	sb_finish_set_opts(newsb);
	mutex_unlock(&newsbsec->lock);
}

static int selinux_parse_opts_str(char *options,
				  struct security_mnt_opts *opts)
{
	char *p;
	char *context = NULL, *defcontext = NULL;
	char *fscontext = NULL, *rootcontext = NULL;
	int rc, num_mnt_opts = 0;

	opts->num_mnt_opts = 0;

	/* Standard string-based options. */
	while ((p = strsep(&options, "|")) != NULL) {
		int token;
		substring_t args[MAX_OPT_ARGS];

		if (!*p)
			continue;

		token = match_token(p, tokens, args);

		switch (token) {
		case Opt_context:
			if (context || defcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			context = match_strdup(&args[0]);
			if (!context) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_fscontext:
			if (fscontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			fscontext = match_strdup(&args[0]);
			if (!fscontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_rootcontext:
			if (rootcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			rootcontext = match_strdup(&args[0]);
			if (!rootcontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;

		case Opt_defcontext:
			if (context || defcontext) {
				rc = -EINVAL;
				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
				goto out_err;
			}
			defcontext = match_strdup(&args[0]);
			if (!defcontext) {
				rc = -ENOMEM;
				goto out_err;
			}
			break;
		case Opt_labelsupport:
			break;
		default:
			rc = -EINVAL;
			printk(KERN_WARNING "SELinux:  unknown mount option\n");
			goto out_err;

		}
	}

	rc = -ENOMEM;
	opts->mnt_opts = kcalloc(NUM_SEL_MNT_OPTS, sizeof(char *), GFP_ATOMIC);
	if (!opts->mnt_opts)
		goto out_err;

	opts->mnt_opts_flags = kcalloc(NUM_SEL_MNT_OPTS, sizeof(int), GFP_ATOMIC);
	if (!opts->mnt_opts_flags) {
		kfree(opts->mnt_opts);
		goto out_err;
	}

	if (fscontext) {
		opts->mnt_opts[num_mnt_opts] = fscontext;
		opts->mnt_opts_flags[num_mnt_opts++] = FSCONTEXT_MNT;
	}
	if (context) {
		opts->mnt_opts[num_mnt_opts] = context;
		opts->mnt_opts_flags[num_mnt_opts++] = CONTEXT_MNT;
	}
	if (rootcontext) {
		opts->mnt_opts[num_mnt_opts] = rootcontext;
		opts->mnt_opts_flags[num_mnt_opts++] = ROOTCONTEXT_MNT;
	}
	if (defcontext) {
		opts->mnt_opts[num_mnt_opts] = defcontext;
		opts->mnt_opts_flags[num_mnt_opts++] = DEFCONTEXT_MNT;
	}

	opts->num_mnt_opts = num_mnt_opts;
	return 0;

out_err:
	kfree(context);
	kfree(defcontext);
	kfree(fscontext);
	kfree(rootcontext);
	return rc;
}
/*
 * string mount options parsing and call set the sbsec
 */
static int superblock_doinit(struct super_block *sb, void *data)
{
	int rc = 0;
	char *options = data;
	struct security_mnt_opts opts;

	security_init_mnt_opts(&opts);

	if (!data)
		goto out;

	BUG_ON(sb->s_type->fs_flags & FS_BINARY_MOUNTDATA);

	rc = selinux_parse_opts_str(options, &opts);
	if (rc)
		goto out_err;

out:
	rc = selinux_set_mnt_opts(sb, &opts);

out_err:
	security_free_mnt_opts(&opts);
	return rc;
}

static void selinux_write_opts(struct seq_file *m,
			       struct security_mnt_opts *opts)
{
	int i;
	char *prefix;

	for (i = 0; i < opts->num_mnt_opts; i++) {
		char *has_comma;

		if (opts->mnt_opts[i])
			has_comma = strchr(opts->mnt_opts[i], ',');
		else
			has_comma = NULL;

		switch (opts->mnt_opts_flags[i]) {
		case CONTEXT_MNT:
			prefix = CONTEXT_STR;
			break;
		case FSCONTEXT_MNT:
			prefix = FSCONTEXT_STR;
			break;
		case ROOTCONTEXT_MNT:
			prefix = ROOTCONTEXT_STR;
			break;
		case DEFCONTEXT_MNT:
			prefix = DEFCONTEXT_STR;
			break;
		case SE_SBLABELSUPP:
			seq_putc(m, ',');
			seq_puts(m, LABELSUPP_STR);
			continue;
		default:
			BUG();
		};
		/* we need a comma before each option */
		seq_putc(m, ',');
		seq_puts(m, prefix);
		if (has_comma)
			seq_putc(m, '\"');
		seq_puts(m, opts->mnt_opts[i]);
		if (has_comma)
			seq_putc(m, '\"');
	}
}

static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb)
{
	struct security_mnt_opts opts;
	int rc;

	rc = selinux_get_mnt_opts(sb, &opts);
	if (rc) {
		/* before policy load we may get EINVAL, don't show anything */
		if (rc == -EINVAL)
			rc = 0;
		return rc;
	}

	selinux_write_opts(m, &opts);

	security_free_mnt_opts(&opts);

	return rc;
}

static inline u16 inode_mode_to_security_class(umode_t mode)
{
	switch (mode & S_IFMT) {
	case S_IFSOCK:
		return SECCLASS_SOCK_FILE;
	case S_IFLNK:
		return SECCLASS_LNK_FILE;
	case S_IFREG:
		return SECCLASS_FILE;
	case S_IFBLK:
		return SECCLASS_BLK_FILE;
	case S_IFDIR:
		return SECCLASS_DIR;
	case S_IFCHR:
		return SECCLASS_CHR_FILE;
	case S_IFIFO:
		return SECCLASS_FIFO_FILE;

	}

	return SECCLASS_FILE;
}

static inline int default_protocol_stream(int protocol)
{
	return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP);
}

static inline int default_protocol_dgram(int protocol)
{
	return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP);
}

static inline u16 socket_type_to_security_class(int family, int type, int protocol)
{
	switch (family) {
	case PF_UNIX:
		switch (type) {
		case SOCK_STREAM:
		case SOCK_SEQPACKET:
			return SECCLASS_UNIX_STREAM_SOCKET;
		case SOCK_DGRAM:
			return SECCLASS_UNIX_DGRAM_SOCKET;
		}
		break;
	case PF_INET:
	case PF_INET6:
		switch (type) {
		case SOCK_STREAM:
			if (default_protocol_stream(protocol))
				return SECCLASS_TCP_SOCKET;
			else
				return SECCLASS_RAWIP_SOCKET;
		case SOCK_DGRAM:
			if (default_protocol_dgram(protocol))
				return SECCLASS_UDP_SOCKET;
			else
				return SECCLASS_RAWIP_SOCKET;
		case SOCK_DCCP:
			return SECCLASS_DCCP_SOCKET;
		default:
			return SECCLASS_RAWIP_SOCKET;
		}
		break;
	case PF_NETLINK:
		switch (protocol) {
		case NETLINK_ROUTE:
			return SECCLASS_NETLINK_ROUTE_SOCKET;
		case NETLINK_FIREWALL:
			return SECCLASS_NETLINK_FIREWALL_SOCKET;
		case NETLINK_INET_DIAG:
			return SECCLASS_NETLINK_TCPDIAG_SOCKET;
		case NETLINK_NFLOG:
			return SECCLASS_NETLINK_NFLOG_SOCKET;
		case NETLINK_XFRM:
			return SECCLASS_NETLINK_XFRM_SOCKET;
		case NETLINK_SELINUX:
			return SECCLASS_NETLINK_SELINUX_SOCKET;
		case NETLINK_AUDIT:
			return SECCLASS_NETLINK_AUDIT_SOCKET;
		case NETLINK_IP6_FW:
			return SECCLASS_NETLINK_IP6FW_SOCKET;
		case NETLINK_DNRTMSG:
			return SECCLASS_NETLINK_DNRT_SOCKET;
		case NETLINK_KOBJECT_UEVENT:
			return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET;
		default:
			return SECCLASS_NETLINK_SOCKET;
		}
	case PF_PACKET:
		return SECCLASS_PACKET_SOCKET;
	case PF_KEY:
		return SECCLASS_KEY_SOCKET;
	case PF_APPLETALK:
		return SECCLASS_APPLETALK_SOCKET;
	}

	return SECCLASS_SOCKET;
}

#ifdef CONFIG_PROC_FS
static int selinux_proc_get_sid(struct proc_dir_entry *de,
				u16 tclass,
				u32 *sid)
{
	int buflen, rc;
	char *buffer, *path, *end;

	buffer = (char *)__get_free_page(GFP_KERNEL);
	if (!buffer)
		return -ENOMEM;

	buflen = PAGE_SIZE;
	end = buffer+buflen;
	*--end = '\0';
	buflen--;
	path = end-1;
	*path = '/';
	while (de && de != de->parent) {
		buflen -= de->namelen + 1;
		if (buflen < 0)
			break;
		end -= de->namelen;
		memcpy(end, de->name, de->namelen);
		*--end = '/';
		path = end;
		de = de->parent;
	}
	rc = security_genfs_sid("proc", path, tclass, sid);
	free_page((unsigned long)buffer);
	return rc;
}
#else
static int selinux_proc_get_sid(struct proc_dir_entry *de,
				u16 tclass,
				u32 *sid)
{
	return -EINVAL;
}
#endif

/* The inode's security attributes must be initialized before first use. */
static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry)
{
	struct superblock_security_struct *sbsec = NULL;
	struct inode_security_struct *isec = inode->i_security;
	u32 sid;
	struct dentry *dentry;
#define INITCONTEXTLEN 255
	char *context = NULL;
	unsigned len = 0;
	int rc = 0;

	if (isec->initialized)
		goto out;

	mutex_lock(&isec->lock);
	if (isec->initialized)
		goto out_unlock;

	sbsec = inode->i_sb->s_security;
	if (!(sbsec->flags & SE_SBINITIALIZED)) {
		/* Defer initialization until selinux_complete_init,
		   after the initial policy is loaded and the security
		   server is ready to handle calls. */
		spin_lock(&sbsec->isec_lock);
		if (list_empty(&isec->list))
			list_add(&isec->list, &sbsec->isec_head);
		spin_unlock(&sbsec->isec_lock);
		goto out_unlock;
	}

	switch (sbsec->behavior) {
	case SECURITY_FS_USE_XATTR:
		if (!inode->i_op->getxattr) {
			isec->sid = sbsec->def_sid;
			break;
		}

		/* Need a dentry, since the xattr API requires one.
		   Life would be simpler if we could just pass the inode. */
		if (opt_dentry) {
			/* Called from d_instantiate or d_splice_alias. */
			dentry = dget(opt_dentry);
		} else {
			/* Called from selinux_complete_init, try to find a dentry. */
			dentry = d_find_alias(inode);
		}
		if (!dentry) {
			/*
			 * this is can be hit on boot when a file is accessed
			 * before the policy is loaded.  When we load policy we
			 * may find inodes that have no dentry on the
			 * sbsec->isec_head list.  No reason to complain as these
			 * will get fixed up the next time we go through
			 * inode_doinit with a dentry, before these inodes could
			 * be used again by userspace.
			 */
			goto out_unlock;
		}

		len = INITCONTEXTLEN;
		context = kmalloc(len+1, GFP_NOFS);
		if (!context) {
			rc = -ENOMEM;
			dput(dentry);
			goto out_unlock;
		}
		context[len] = '\0';
		rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX,
					   context, len);
		if (rc == -ERANGE) {
			/* Need a larger buffer.  Query for the right size. */
			rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX,
						   NULL, 0);
			if (rc < 0) {
				dput(dentry);
				goto out_unlock;
			}
			kfree(context);
			len = rc;
			context = kmalloc(len+1, GFP_NOFS);
			if (!context) {
				rc = -ENOMEM;
				dput(dentry);
				goto out_unlock;
			}
			context[len] = '\0';
			rc = inode->i_op->getxattr(dentry,
						   XATTR_NAME_SELINUX,
						   context, len);
		}
		dput(dentry);
		if (rc < 0) {
			if (rc != -ENODATA) {
				printk(KERN_WARNING "SELinux: %s:  getxattr returned "
				       "%d for dev=%s ino=%ld\n", __func__,
				       -rc, inode->i_sb->s_id, inode->i_ino);
				kfree(context);
				goto out_unlock;
			}
			/* Map ENODATA to the default file SID */
			sid = sbsec->def_sid;
			rc = 0;
		} else {
			rc = security_context_to_sid_default(context, rc, &sid,
							     sbsec->def_sid,
							     GFP_NOFS);
			if (rc) {
				char *dev = inode->i_sb->s_id;
				unsigned long ino = inode->i_ino;

				if (rc == -EINVAL) {
					if (printk_ratelimit())
						printk(KERN_NOTICE "SELinux: inode=%lu on dev=%s was found to have an invalid "
							"context=%s.  This indicates you may need to relabel the inode or the "
							"filesystem in question.\n", ino, dev, context);
				} else {
					printk(KERN_WARNING "SELinux: %s:  context_to_sid(%s) "
					       "returned %d for dev=%s ino=%ld\n",
					       __func__, context, -rc, dev, ino);
				}
				kfree(context);
				/* Leave with the unlabeled SID */
				rc = 0;
				break;
			}
		}
		kfree(context);
		isec->sid = sid;
		break;
	case SECURITY_FS_USE_TASK:
		isec->sid = isec->task_sid;
		break;
	case SECURITY_FS_USE_TRANS:
		/* Default to the fs SID. */
		isec->sid = sbsec->sid;

		/* Try to obtain a transition SID. */
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
		rc = security_transition_sid(isec->task_sid,
					     sbsec->sid,
					     isec->sclass,
					     &sid);
		if (rc)
			goto out_unlock;
		isec->sid = sid;
		break;
	case SECURITY_FS_USE_MNTPOINT:
		isec->sid = sbsec->mntpoint_sid;
		break;
	default:
		/* Default to the fs superblock SID. */
		isec->sid = sbsec->sid;

		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
			struct proc_inode *proci = PROC_I(inode);
			if (proci->pde) {
				isec->sclass = inode_mode_to_security_class(inode->i_mode);
				rc = selinux_proc_get_sid(proci->pde,
							  isec->sclass,
							  &sid);
				if (rc)
					goto out_unlock;
				isec->sid = sid;
			}
		}
		break;
	}

	isec->initialized = 1;

out_unlock:
	mutex_unlock(&isec->lock);
out:
	if (isec->sclass == SECCLASS_FILE)
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
	return rc;
}

/* Convert a Linux signal to an access vector. */
static inline u32 signal_to_av(int sig)
{
	u32 perm = 0;

	switch (sig) {
	case SIGCHLD:
		/* Commonly granted from child to parent. */
		perm = PROCESS__SIGCHLD;
		break;
	case SIGKILL:
		/* Cannot be caught or ignored */
		perm = PROCESS__SIGKILL;
		break;
	case SIGSTOP:
		/* Cannot be caught or ignored */
		perm = PROCESS__SIGSTOP;
		break;
	default:
		/* All other signals. */
		perm = PROCESS__SIGNAL;
		break;
	}

	return perm;
}

/*
 * Check permission between a pair of credentials
 * fork check, ptrace check, etc.
 */
static int cred_has_perm(const struct cred *actor,
			 const struct cred *target,
			 u32 perms)
{
	u32 asid = cred_sid(actor), tsid = cred_sid(target);

	return avc_has_perm(asid, tsid, SECCLASS_PROCESS, perms, NULL);
}

/*
 * Check permission between a pair of tasks, e.g. signal checks,
 * fork check, ptrace check, etc.
 * tsk1 is the actor and tsk2 is the target
 * - this uses the default subjective creds of tsk1
 */
static int task_has_perm(const struct task_struct *tsk1,
			 const struct task_struct *tsk2,
			 u32 perms)
{
	const struct task_security_struct *__tsec1, *__tsec2;
	u32 sid1, sid2;

	rcu_read_lock();
	__tsec1 = __task_cred(tsk1)->security;	sid1 = __tsec1->sid;
	__tsec2 = __task_cred(tsk2)->security;	sid2 = __tsec2->sid;
	rcu_read_unlock();
	return avc_has_perm(sid1, sid2, SECCLASS_PROCESS, perms, NULL);
}

/*
 * Check permission between current and another task, e.g. signal checks,
 * fork check, ptrace check, etc.
 * current is the actor and tsk2 is the target
 * - this uses current's subjective creds
 */
static int current_has_perm(const struct task_struct *tsk,
			    u32 perms)
{
	u32 sid, tsid;

	sid = current_sid();
	tsid = task_sid(tsk);
	return avc_has_perm(sid, tsid, SECCLASS_PROCESS, perms, NULL);
}

#if CAP_LAST_CAP > 63
#error Fix SELinux to handle capabilities > 63.
#endif

/* Check whether a task is allowed to use a capability. */
static int task_has_capability(struct task_struct *tsk,
			       const struct cred *cred,
			       int cap, int audit)
{
	struct avc_audit_data ad;
	struct av_decision avd;
	u16 sclass;
	u32 sid = cred_sid(cred);
	u32 av = CAP_TO_MASK(cap);
	int rc;

	AVC_AUDIT_DATA_INIT(&ad, CAP);
	ad.tsk = tsk;
	ad.u.cap = cap;

	switch (CAP_TO_INDEX(cap)) {
	case 0:
		sclass = SECCLASS_CAPABILITY;
		break;
	case 1:
		sclass = SECCLASS_CAPABILITY2;
		break;
	default:
		printk(KERN_ERR
		       "SELinux:  out of range capability %d\n", cap);
		BUG();
	}

	rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
	if (audit == SECURITY_CAP_AUDIT)
		avc_audit(sid, sid, sclass, av, &avd, rc, &ad);
	return rc;
}

/* Check whether a task is allowed to use a system operation. */
static int task_has_system(struct task_struct *tsk,
			   u32 perms)
{
	u32 sid = task_sid(tsk);

	return avc_has_perm(sid, SECINITSID_KERNEL,
			    SECCLASS_SYSTEM, perms, NULL);
}

/* Check whether a task has a particular permission to an inode.
   The 'adp' parameter is optional and allows other audit
   data to be passed (e.g. the dentry). */
static int inode_has_perm(const struct cred *cred,
			  struct inode *inode,
			  u32 perms,
			  struct avc_audit_data *adp)
{
	struct inode_security_struct *isec;
	struct avc_audit_data ad;
	u32 sid;

	if (unlikely(IS_PRIVATE(inode)))
		return 0;

	sid = cred_sid(cred);
	isec = inode->i_security;

	if (!adp) {
		adp = &ad;
		AVC_AUDIT_DATA_INIT(&ad, FS);
		ad.u.fs.inode = inode;
	}

	return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp);
}

/* Same as inode_has_perm, but pass explicit audit data containing
   the dentry to help the auditing code to more easily generate the
   pathname if needed. */
static inline int dentry_has_perm(const struct cred *cred,
				  struct vfsmount *mnt,
				  struct dentry *dentry,
				  u32 av)
{
	struct inode *inode = dentry->d_inode;
	struct avc_audit_data ad;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.mnt = mnt;
	ad.u.fs.path.dentry = dentry;
	return inode_has_perm(cred, inode, av, &ad);
}

/* Check whether a task can use an open file descriptor to
   access an inode in a given way.  Check access to the
   descriptor itself, and then use dentry_has_perm to
   check a particular permission to the file.
   Access to the descriptor is implicitly granted if it
   has the same SID as the process.  If av is zero, then
   access to the file is not checked, e.g. for cases
   where only the descriptor is affected like seek. */
static int file_has_perm(const struct cred *cred,
			 struct file *file,
			 u32 av)
{
	struct file_security_struct *fsec = file->f_security;
	struct inode *inode = file->f_path.dentry->d_inode;
	struct avc_audit_data ad;
	u32 sid = cred_sid(cred);
	int rc;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path = file->f_path;

	if (sid != fsec->sid) {
		rc = avc_has_perm(sid, fsec->sid,
				  SECCLASS_FD,
				  FD__USE,
				  &ad);
		if (rc)
			goto out;
	}

	/* av is zero if only checking access to the descriptor. */
	rc = 0;
	if (av)
		rc = inode_has_perm(cred, inode, av, &ad);

out:
	return rc;
}

/* Check whether a task can create a file. */
static int may_create(struct inode *dir,
		      struct dentry *dentry,
		      u16 tclass)
{
	const struct cred *cred = current_cred();
	const struct task_security_struct *tsec = cred->security;
	struct inode_security_struct *dsec;
	struct superblock_security_struct *sbsec;
	u32 sid, newsid;
	struct avc_audit_data ad;
	int rc;

	dsec = dir->i_security;
	sbsec = dir->i_sb->s_security;

	sid = tsec->sid;
	newsid = tsec->create_sid;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.dentry = dentry;

	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR,
			  DIR__ADD_NAME | DIR__SEARCH,
			  &ad);
	if (rc)
		return rc;

	if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
		rc = security_transition_sid(sid, dsec->sid, tclass, &newsid);
		if (rc)
			return rc;
	}

	rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad);
	if (rc)
		return rc;

	return avc_has_perm(newsid, sbsec->sid,
			    SECCLASS_FILESYSTEM,
			    FILESYSTEM__ASSOCIATE, &ad);
}

/* Check whether a task can create a key. */
static int may_create_key(u32 ksid,
			  struct task_struct *ctx)
{
	u32 sid = task_sid(ctx);

	return avc_has_perm(sid, ksid, SECCLASS_KEY, KEY__CREATE, NULL);
}

#define MAY_LINK	0
#define MAY_UNLINK	1
#define MAY_RMDIR	2

/* Check whether a task can link, unlink, or rmdir a file/directory. */
static int may_link(struct inode *dir,
		    struct dentry *dentry,
		    int kind)

{
	struct inode_security_struct *dsec, *isec;
	struct avc_audit_data ad;
	u32 sid = current_sid();
	u32 av;
	int rc;

	dsec = dir->i_security;
	isec = dentry->d_inode->i_security;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.dentry = dentry;

	av = DIR__SEARCH;
	av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME);
	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad);
	if (rc)
		return rc;

	switch (kind) {
	case MAY_LINK:
		av = FILE__LINK;
		break;
	case MAY_UNLINK:
		av = FILE__UNLINK;
		break;
	case MAY_RMDIR:
		av = DIR__RMDIR;
		break;
	default:
		printk(KERN_WARNING "SELinux: %s:  unrecognized kind %d\n",
			__func__, kind);
		return 0;
	}

	rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad);
	return rc;
}

static inline int may_rename(struct inode *old_dir,
			     struct dentry *old_dentry,
			     struct inode *new_dir,
			     struct dentry *new_dentry)
{
	struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec;
	struct avc_audit_data ad;
	u32 sid = current_sid();
	u32 av;
	int old_is_dir, new_is_dir;
	int rc;

	old_dsec = old_dir->i_security;
	old_isec = old_dentry->d_inode->i_security;
	old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
	new_dsec = new_dir->i_security;

	AVC_AUDIT_DATA_INIT(&ad, FS);

	ad.u.fs.path.dentry = old_dentry;
	rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR,
			  DIR__REMOVE_NAME | DIR__SEARCH, &ad);
	if (rc)
		return rc;
	rc = avc_has_perm(sid, old_isec->sid,
			  old_isec->sclass, FILE__RENAME, &ad);
	if (rc)
		return rc;
	if (old_is_dir && new_dir != old_dir) {
		rc = avc_has_perm(sid, old_isec->sid,
				  old_isec->sclass, DIR__REPARENT, &ad);
		if (rc)
			return rc;
	}

	ad.u.fs.path.dentry = new_dentry;
	av = DIR__ADD_NAME | DIR__SEARCH;
	if (new_dentry->d_inode)
		av |= DIR__REMOVE_NAME;
	rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad);
	if (rc)
		return rc;
	if (new_dentry->d_inode) {
		new_isec = new_dentry->d_inode->i_security;
		new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode);
		rc = avc_has_perm(sid, new_isec->sid,
				  new_isec->sclass,
				  (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad);
		if (rc)
			return rc;
	}

	return 0;
}

/* Check whether a task can perform a filesystem operation. */
static int superblock_has_perm(const struct cred *cred,
			       struct super_block *sb,
			       u32 perms,
			       struct avc_audit_data *ad)
{
	struct superblock_security_struct *sbsec;
	u32 sid = cred_sid(cred);

	sbsec = sb->s_security;
	return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad);
}

/* Convert a Linux mode and permission mask to an access vector. */
static inline u32 file_mask_to_av(int mode, int mask)
{
	u32 av = 0;

	if ((mode & S_IFMT) != S_IFDIR) {
		if (mask & MAY_EXEC)
			av |= FILE__EXECUTE;
		if (mask & MAY_READ)
			av |= FILE__READ;

		if (mask & MAY_APPEND)
			av |= FILE__APPEND;
		else if (mask & MAY_WRITE)
			av |= FILE__WRITE;

	} else {
		if (mask & MAY_EXEC)
			av |= DIR__SEARCH;
		if (mask & MAY_WRITE)
			av |= DIR__WRITE;
		if (mask & MAY_READ)
			av |= DIR__READ;
	}

	return av;
}

/* Convert a Linux file to an access vector. */
static inline u32 file_to_av(struct file *file)
{
	u32 av = 0;

	if (file->f_mode & FMODE_READ)
		av |= FILE__READ;
	if (file->f_mode & FMODE_WRITE) {
		if (file->f_flags & O_APPEND)
			av |= FILE__APPEND;
		else
			av |= FILE__WRITE;
	}
	if (!av) {
		/*
		 * Special file opened with flags 3 for ioctl-only use.
		 */
		av = FILE__IOCTL;
	}

	return av;
}

/*
 * Convert a file to an access vector and include the correct open
 * open permission.
 */
static inline u32 open_file_to_av(struct file *file)
{
	u32 av = file_to_av(file);

	if (selinux_policycap_openperm) {
		mode_t mode = file->f_path.dentry->d_inode->i_mode;
		/*
		 * lnk files and socks do not really have an 'open'
		 */
		if (S_ISREG(mode))
			av |= FILE__OPEN;
		else if (S_ISCHR(mode))
			av |= CHR_FILE__OPEN;
		else if (S_ISBLK(mode))
			av |= BLK_FILE__OPEN;
		else if (S_ISFIFO(mode))
			av |= FIFO_FILE__OPEN;
		else if (S_ISDIR(mode))
			av |= DIR__OPEN;
		else if (S_ISSOCK(mode))
			av |= SOCK_FILE__OPEN;
		else
			printk(KERN_ERR "SELinux: WARNING: inside %s with "
				"unknown mode:%o\n", __func__, mode);
	}
	return av;
}

/* Hook functions begin here. */

static int selinux_ptrace_access_check(struct task_struct *child,
				     unsigned int mode)
{
	int rc;

	rc = cap_ptrace_access_check(child, mode);
	if (rc)
		return rc;

	if (mode == PTRACE_MODE_READ) {
		u32 sid = current_sid();
		u32 csid = task_sid(child);
		return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL);
	}

	return current_has_perm(child, PROCESS__PTRACE);
}

static int selinux_ptrace_traceme(struct task_struct *parent)
{
	int rc;

	rc = cap_ptrace_traceme(parent);
	if (rc)
		return rc;

	return task_has_perm(parent, current, PROCESS__PTRACE);
}

static int selinux_capget(struct task_struct *target, kernel_cap_t *effective,
			  kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
	int error;

	error = current_has_perm(target, PROCESS__GETCAP);
	if (error)
		return error;

	return cap_capget(target, effective, inheritable, permitted);
}

static int selinux_capset(struct cred *new, const struct cred *old,
			  const kernel_cap_t *effective,
			  const kernel_cap_t *inheritable,
			  const kernel_cap_t *permitted)
{
	int error;

	error = cap_capset(new, old,
				      effective, inheritable, permitted);
	if (error)
		return error;

	return cred_has_perm(old, new, PROCESS__SETCAP);
}

/*
 * (This comment used to live with the selinux_task_setuid hook,
 * which was removed).
 *
 * Since setuid only affects the current process, and since the SELinux
 * controls are not based on the Linux identity attributes, SELinux does not
 * need to control this operation.  However, SELinux does control the use of
 * the CAP_SETUID and CAP_SETGID capabilities using the capable hook.
 */

static int selinux_capable(struct task_struct *tsk, const struct cred *cred,
			   int cap, int audit)
{
	int rc;

	rc = cap_capable(tsk, cred, cap, audit);
	if (rc)
		return rc;

	return task_has_capability(tsk, cred, cap, audit);
}

static int selinux_sysctl_get_sid(ctl_table *table, u16 tclass, u32 *sid)
{
	int buflen, rc;
	char *buffer, *path, *end;

	rc = -ENOMEM;
	buffer = (char *)__get_free_page(GFP_KERNEL);
	if (!buffer)
		goto out;

	buflen = PAGE_SIZE;
	end = buffer+buflen;
	*--end = '\0';
	buflen--;
	path = end-1;
	*path = '/';
	while (table) {
		const char *name = table->procname;
		size_t namelen = strlen(name);
		buflen -= namelen + 1;
		if (buflen < 0)
			goto out_free;
		end -= namelen;
		memcpy(end, name, namelen);
		*--end = '/';
		path = end;
		table = table->parent;
	}
	buflen -= 4;
	if (buflen < 0)
		goto out_free;
	end -= 4;
	memcpy(end, "/sys", 4);
	path = end;
	rc = security_genfs_sid("proc", path, tclass, sid);
out_free:
	free_page((unsigned long)buffer);
out:
	return rc;
}

static int selinux_sysctl(ctl_table *table, int op)
{
	int error = 0;
	u32 av;
	u32 tsid, sid;
	int rc;

	sid = current_sid();

	rc = selinux_sysctl_get_sid(table, (op == 0001) ?
				    SECCLASS_DIR : SECCLASS_FILE, &tsid);
	if (rc) {
		/* Default to the well-defined sysctl SID. */
		tsid = SECINITSID_SYSCTL;
	}

	/* The op values are "defined" in sysctl.c, thereby creating
	 * a bad coupling between this module and sysctl.c */
	if (op == 001) {
		error = avc_has_perm(sid, tsid,
				     SECCLASS_DIR, DIR__SEARCH, NULL);
	} else {
		av = 0;
		if (op & 004)
			av |= FILE__READ;
		if (op & 002)
			av |= FILE__WRITE;
		if (av)
			error = avc_has_perm(sid, tsid,
					     SECCLASS_FILE, av, NULL);
	}

	return error;
}

static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb)
{
	const struct cred *cred = current_cred();
	int rc = 0;

	if (!sb)
		return 0;

	switch (cmds) {
	case Q_SYNC:
	case Q_QUOTAON:
	case Q_QUOTAOFF:
	case Q_SETINFO:
	case Q_SETQUOTA:
		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL);
		break;
	case Q_GETFMT:
	case Q_GETINFO:
	case Q_GETQUOTA:
		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL);
		break;
	default:
		rc = 0;  /* let the kernel handle invalid cmds */
		break;
	}
	return rc;
}

static int selinux_quota_on(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, NULL, dentry, FILE__QUOTAON);
}

static int selinux_syslog(int type)
{
	int rc;

	rc = cap_syslog(type);
	if (rc)
		return rc;

	switch (type) {
	case 3:		/* Read last kernel messages */
	case 10:	/* Return size of the log buffer */
		rc = task_has_system(current, SYSTEM__SYSLOG_READ);
		break;
	case 6:		/* Disable logging to console */
	case 7:		/* Enable logging to console */
	case 8:		/* Set level of messages printed to console */
		rc = task_has_system(current, SYSTEM__SYSLOG_CONSOLE);
		break;
	case 0:		/* Close log */
	case 1:		/* Open log */
	case 2:		/* Read from log */
	case 4:		/* Read/clear last kernel messages */
	case 5:		/* Clear ring buffer */
	default:
		rc = task_has_system(current, SYSTEM__SYSLOG_MOD);
		break;
	}
	return rc;
}

/*
 * Check that a process has enough memory to allocate a new virtual
 * mapping. 0 means there is enough memory for the allocation to
 * succeed and -ENOMEM implies there is not.
 *
 * Do not audit the selinux permission check, as this is applied to all
 * processes that allocate mappings.
 */
static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
{
	int rc, cap_sys_admin = 0;

	rc = selinux_capable(current, current_cred(), CAP_SYS_ADMIN,
			     SECURITY_CAP_NOAUDIT);
	if (rc == 0)
		cap_sys_admin = 1;

	return __vm_enough_memory(mm, pages, cap_sys_admin);
}

/* binprm security operations */

static int selinux_bprm_set_creds(struct linux_binprm *bprm)
{
	const struct task_security_struct *old_tsec;
	struct task_security_struct *new_tsec;
	struct inode_security_struct *isec;
	struct avc_audit_data ad;
	struct inode *inode = bprm->file->f_path.dentry->d_inode;
	int rc;

	rc = cap_bprm_set_creds(bprm);
	if (rc)
		return rc;

	/* SELinux context only depends on initial program or script and not
	 * the script interpreter */
	if (bprm->cred_prepared)
		return 0;

	old_tsec = current_security();
	new_tsec = bprm->cred->security;
	isec = inode->i_security;

	/* Default to the current task SID. */
	new_tsec->sid = old_tsec->sid;
	new_tsec->osid = old_tsec->sid;

	/* Reset fs, key, and sock SIDs on execve. */
	new_tsec->create_sid = 0;
	new_tsec->keycreate_sid = 0;
	new_tsec->sockcreate_sid = 0;

	if (old_tsec->exec_sid) {
		new_tsec->sid = old_tsec->exec_sid;
		/* Reset exec SID on execve. */
		new_tsec->exec_sid = 0;
	} else {
		/* Check for a default transition on this program. */
		rc = security_transition_sid(old_tsec->sid, isec->sid,
					     SECCLASS_PROCESS, &new_tsec->sid);
		if (rc)
			return rc;
	}

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path = bprm->file->f_path;

	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
		new_tsec->sid = old_tsec->sid;

	if (new_tsec->sid == old_tsec->sid) {
		rc = avc_has_perm(old_tsec->sid, isec->sid,
				  SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad);
		if (rc)
			return rc;
	} else {
		/* Check permissions for the transition. */
		rc = avc_has_perm(old_tsec->sid, new_tsec->sid,
				  SECCLASS_PROCESS, PROCESS__TRANSITION, &ad);
		if (rc)
			return rc;

		rc = avc_has_perm(new_tsec->sid, isec->sid,
				  SECCLASS_FILE, FILE__ENTRYPOINT, &ad);
		if (rc)
			return rc;

		/* Check for shared state */
		if (bprm->unsafe & LSM_UNSAFE_SHARE) {
			rc = avc_has_perm(old_tsec->sid, new_tsec->sid,
					  SECCLASS_PROCESS, PROCESS__SHARE,
					  NULL);
			if (rc)
				return -EPERM;
		}

		/* Make sure that anyone attempting to ptrace over a task that
		 * changes its SID has the appropriate permit */
		if (bprm->unsafe &
		    (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
			struct task_struct *tracer;
			struct task_security_struct *sec;
			u32 ptsid = 0;

			rcu_read_lock();
			tracer = tracehook_tracer_task(current);
			if (likely(tracer != NULL)) {
				sec = __task_cred(tracer)->security;
				ptsid = sec->sid;
			}
			rcu_read_unlock();

			if (ptsid != 0) {
				rc = avc_has_perm(ptsid, new_tsec->sid,
						  SECCLASS_PROCESS,
						  PROCESS__PTRACE, NULL);
				if (rc)
					return -EPERM;
			}
		}

		/* Clear any possibly unsafe personality bits on exec: */
		bprm->per_clear |= PER_CLEAR_ON_SETID;
	}

	return 0;
}

static int selinux_bprm_secureexec(struct linux_binprm *bprm)
{
	const struct cred *cred = current_cred();
	const struct task_security_struct *tsec = cred->security;
	u32 sid, osid;
	int atsecure = 0;

	sid = tsec->sid;
	osid = tsec->osid;

	if (osid != sid) {
		/* Enable secure mode for SIDs transitions unless
		   the noatsecure permission is granted between
		   the two SIDs, i.e. ahp returns 0. */
		atsecure = avc_has_perm(osid, sid,
					SECCLASS_PROCESS,
					PROCESS__NOATSECURE, NULL);
	}

	return (atsecure || cap_bprm_secureexec(bprm));
}

extern struct vfsmount *selinuxfs_mount;
extern struct dentry *selinux_null;

/* Derived from fs/exec.c:flush_old_files. */
static inline void flush_unauthorized_files(const struct cred *cred,
					    struct files_struct *files)
{
	struct avc_audit_data ad;
	struct file *file, *devnull = NULL;
	struct tty_struct *tty;
	struct fdtable *fdt;
	long j = -1;
	int drop_tty = 0;

	tty = get_current_tty();
	if (tty) {
		file_list_lock();
		if (!list_empty(&tty->tty_files)) {
			struct inode *inode;

			/* Revalidate access to controlling tty.
			   Use inode_has_perm on the tty inode directly rather
			   than using file_has_perm, as this particular open
			   file may belong to another process and we are only
			   interested in the inode-based check here. */
			file = list_first_entry(&tty->tty_files, struct file, f_u.fu_list);
			inode = file->f_path.dentry->d_inode;
			if (inode_has_perm(cred, inode,
					   FILE__READ | FILE__WRITE, NULL)) {
				drop_tty = 1;
			}
		}
		file_list_unlock();
		tty_kref_put(tty);
	}
	/* Reset controlling tty. */
	if (drop_tty)
		no_tty();

	/* Revalidate access to inherited open files. */

	AVC_AUDIT_DATA_INIT(&ad, FS);

	spin_lock(&files->file_lock);
	for (;;) {
		unsigned long set, i;
		int fd;

		j++;
		i = j * __NFDBITS;
		fdt = files_fdtable(files);
		if (i >= fdt->max_fds)
			break;
		set = fdt->open_fds->fds_bits[j];
		if (!set)
			continue;
		spin_unlock(&files->file_lock);
		for ( ; set ; i++, set >>= 1) {
			if (set & 1) {
				file = fget(i);
				if (!file)
					continue;
				if (file_has_perm(cred,
						  file,
						  file_to_av(file))) {
					sys_close(i);
					fd = get_unused_fd();
					if (fd != i) {
						if (fd >= 0)
							put_unused_fd(fd);
						fput(file);
						continue;
					}
					if (devnull) {
						get_file(devnull);
					} else {
						devnull = dentry_open(
							dget(selinux_null),
							mntget(selinuxfs_mount),
							O_RDWR, cred);
						if (IS_ERR(devnull)) {
							devnull = NULL;
							put_unused_fd(fd);
							fput(file);
							continue;
						}
					}
					fd_install(fd, devnull);
				}
				fput(file);
			}
		}
		spin_lock(&files->file_lock);

	}
	spin_unlock(&files->file_lock);
}

/*
 * Prepare a process for imminent new credential changes due to exec
 */
static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
{
	struct task_security_struct *new_tsec;
	struct rlimit *rlim, *initrlim;
	int rc, i;

	new_tsec = bprm->cred->security;
	if (new_tsec->sid == new_tsec->osid)
		return;

	/* Close files for which the new task SID is not authorized. */
	flush_unauthorized_files(bprm->cred, current->files);

	/* Always clear parent death signal on SID transitions. */
	current->pdeath_signal = 0;

	/* Check whether the new SID can inherit resource limits from the old
	 * SID.  If not, reset all soft limits to the lower of the current
	 * task's hard limit and the init task's soft limit.
	 *
	 * Note that the setting of hard limits (even to lower them) can be
	 * controlled by the setrlimit check.  The inclusion of the init task's
	 * soft limit into the computation is to avoid resetting soft limits
	 * higher than the default soft limit for cases where the default is
	 * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK.
	 */
	rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS,
			  PROCESS__RLIMITINH, NULL);
	if (rc) {
		for (i = 0; i < RLIM_NLIMITS; i++) {
			rlim = current->signal->rlim + i;
			initrlim = init_task.signal->rlim + i;
			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
		}
		update_rlimit_cpu(rlim->rlim_cur);
	}
}

/*
 * Clean up the process immediately after the installation of new credentials
 * due to exec
 */
static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
{
	const struct task_security_struct *tsec = current_security();
	struct itimerval itimer;
	u32 osid, sid;
	int rc, i;

	osid = tsec->osid;
	sid = tsec->sid;

	if (sid == osid)
		return;

	/* Check whether the new SID can inherit signal state from the old SID.
	 * If not, clear itimers to avoid subsequent signal generation and
	 * flush and unblock signals.
	 *
	 * This must occur _after_ the task SID has been updated so that any
	 * kill done after the flush will be checked against the new SID.
	 */
	rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL);
	if (rc) {
		memset(&itimer, 0, sizeof itimer);
		for (i = 0; i < 3; i++)
			do_setitimer(i, &itimer, NULL);
		spin_lock_irq(&current->sighand->siglock);
		if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
			__flush_signals(current);
			flush_signal_handlers(current, 1);
			sigemptyset(&current->blocked);
		}
		spin_unlock_irq(&current->sighand->siglock);
	}

	/* Wake up the parent if it is waiting so that it can recheck
	 * wait permission to the new task SID. */
	read_lock(&tasklist_lock);
	wake_up_interruptible(&current->real_parent->signal->wait_chldexit);
	read_unlock(&tasklist_lock);
}

/* superblock security operations */

static int selinux_sb_alloc_security(struct super_block *sb)
{
	return superblock_alloc_security(sb);
}

static void selinux_sb_free_security(struct super_block *sb)
{
	superblock_free_security(sb);
}

static inline int match_prefix(char *prefix, int plen, char *option, int olen)
{
	if (plen > olen)
		return 0;

	return !memcmp(prefix, option, plen);
}

static inline int selinux_option(char *option, int len)
{
	return (match_prefix(CONTEXT_STR, sizeof(CONTEXT_STR)-1, option, len) ||
		match_prefix(FSCONTEXT_STR, sizeof(FSCONTEXT_STR)-1, option, len) ||
		match_prefix(DEFCONTEXT_STR, sizeof(DEFCONTEXT_STR)-1, option, len) ||
		match_prefix(ROOTCONTEXT_STR, sizeof(ROOTCONTEXT_STR)-1, option, len) ||
		match_prefix(LABELSUPP_STR, sizeof(LABELSUPP_STR)-1, option, len));
}

static inline void take_option(char **to, char *from, int *first, int len)
{
	if (!*first) {
		**to = ',';
		*to += 1;
	} else
		*first = 0;
	memcpy(*to, from, len);
	*to += len;
}

static inline void take_selinux_option(char **to, char *from, int *first,
				       int len)
{
	int current_size = 0;

	if (!*first) {
		**to = '|';
		*to += 1;
	} else
		*first = 0;

	while (current_size < len) {
		if (*from != '"') {
			**to = *from;
			*to += 1;
		}
		from += 1;
		current_size += 1;
	}
}

static int selinux_sb_copy_data(char *orig, char *copy)
{
	int fnosec, fsec, rc = 0;
	char *in_save, *in_curr, *in_end;
	char *sec_curr, *nosec_save, *nosec;
	int open_quote = 0;

	in_curr = orig;
	sec_curr = copy;

	nosec = (char *)get_zeroed_page(GFP_KERNEL);
	if (!nosec) {
		rc = -ENOMEM;
		goto out;
	}

	nosec_save = nosec;
	fnosec = fsec = 1;
	in_save = in_end = orig;

	do {
		if (*in_end == '"')
			open_quote = !open_quote;
		if ((*in_end == ',' && open_quote == 0) ||
				*in_end == '\0') {
			int len = in_end - in_curr;

			if (selinux_option(in_curr, len))
				take_selinux_option(&sec_curr, in_curr, &fsec, len);
			else
				take_option(&nosec, in_curr, &fnosec, len);

			in_curr = in_end + 1;
		}
	} while (*in_end++);

	strcpy(in_save, nosec_save);
	free_page((unsigned long)nosec_save);
out:
	return rc;
}

static int selinux_sb_kern_mount(struct super_block *sb, int flags, void *data)
{
	const struct cred *cred = current_cred();
	struct avc_audit_data ad;
	int rc;

	rc = superblock_doinit(sb, data);
	if (rc)
		return rc;

	/* Allow all mounts performed by the kernel */
	if (flags & MS_KERNMOUNT)
		return 0;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.dentry = sb->s_root;
	return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
}

static int selinux_sb_statfs(struct dentry *dentry)
{
	const struct cred *cred = current_cred();
	struct avc_audit_data ad;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.dentry = dentry->d_sb->s_root;
	return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad);
}

static int selinux_mount(char *dev_name,
			 struct path *path,
			 char *type,
			 unsigned long flags,
			 void *data)
{
	const struct cred *cred = current_cred();

	if (flags & MS_REMOUNT)
		return superblock_has_perm(cred, path->mnt->mnt_sb,
					   FILESYSTEM__REMOUNT, NULL);
	else
		return dentry_has_perm(cred, path->mnt, path->dentry,
				       FILE__MOUNTON);
}

static int selinux_umount(struct vfsmount *mnt, int flags)
{
	const struct cred *cred = current_cred();

	return superblock_has_perm(cred, mnt->mnt_sb,
				   FILESYSTEM__UNMOUNT, NULL);
}

/* inode security operations */

static int selinux_inode_alloc_security(struct inode *inode)
{
	return inode_alloc_security(inode);
}

static void selinux_inode_free_security(struct inode *inode)
{
	inode_free_security(inode);
}

static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
				       char **name, void **value,
				       size_t *len)
{
	const struct cred *cred = current_cred();
	const struct task_security_struct *tsec = cred->security;
	struct inode_security_struct *dsec;
	struct superblock_security_struct *sbsec;
	u32 sid, newsid, clen;
	int rc;
	char *namep = NULL, *context;

	dsec = dir->i_security;
	sbsec = dir->i_sb->s_security;

	sid = tsec->sid;
	newsid = tsec->create_sid;

	if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
		rc = security_transition_sid(sid, dsec->sid,
					     inode_mode_to_security_class(inode->i_mode),
					     &newsid);
		if (rc) {
			printk(KERN_WARNING "%s:  "
			       "security_transition_sid failed, rc=%d (dev=%s "
			       "ino=%ld)\n",
			       __func__,
			       -rc, inode->i_sb->s_id, inode->i_ino);
			return rc;
		}
	}

	/* Possibly defer initialization to selinux_complete_init. */
	if (sbsec->flags & SE_SBINITIALIZED) {
		struct inode_security_struct *isec = inode->i_security;
		isec->sclass = inode_mode_to_security_class(inode->i_mode);
		isec->sid = newsid;
		isec->initialized = 1;
	}

	if (!ss_initialized || !(sbsec->flags & SE_SBLABELSUPP))
		return -EOPNOTSUPP;

	if (name) {
		namep = kstrdup(XATTR_SELINUX_SUFFIX, GFP_NOFS);
		if (!namep)
			return -ENOMEM;
		*name = namep;
	}

	if (value && len) {
		rc = security_sid_to_context_force(newsid, &context, &clen);
		if (rc) {
			kfree(namep);
			return rc;
		}
		*value = context;
		*len = clen;
	}

	return 0;
}

static int selinux_inode_create(struct inode *dir, struct dentry *dentry, int mask)
{
	return may_create(dir, dentry, SECCLASS_FILE);
}

static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
{
	return may_link(dir, old_dentry, MAY_LINK);
}

static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry)
{
	return may_link(dir, dentry, MAY_UNLINK);
}

static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name)
{
	return may_create(dir, dentry, SECCLASS_LNK_FILE);
}

static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, int mask)
{
	return may_create(dir, dentry, SECCLASS_DIR);
}

static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry)
{
	return may_link(dir, dentry, MAY_RMDIR);
}

static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
	return may_create(dir, dentry, inode_mode_to_security_class(mode));
}

static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry,
				struct inode *new_inode, struct dentry *new_dentry)
{
	return may_rename(old_inode, old_dentry, new_inode, new_dentry);
}

static int selinux_inode_readlink(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, NULL, dentry, FILE__READ);
}

static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *nameidata)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, NULL, dentry, FILE__READ);
}

static int selinux_inode_permission(struct inode *inode, int mask)
{
	const struct cred *cred = current_cred();

	if (!mask) {
		/* No permission to check.  Existence test. */
		return 0;
	}

	return inode_has_perm(cred, inode,
			      file_mask_to_av(inode->i_mode, mask), NULL);
}

static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr)
{
	const struct cred *cred = current_cred();

	if (iattr->ia_valid & ATTR_FORCE)
		return 0;

	if (iattr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID |
			       ATTR_ATIME_SET | ATTR_MTIME_SET))
		return dentry_has_perm(cred, NULL, dentry, FILE__SETATTR);

	return dentry_has_perm(cred, NULL, dentry, FILE__WRITE);
}

static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, mnt, dentry, FILE__GETATTR);
}

static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name)
{
	const struct cred *cred = current_cred();

	if (!strncmp(name, XATTR_SECURITY_PREFIX,
		     sizeof XATTR_SECURITY_PREFIX - 1)) {
		if (!strcmp(name, XATTR_NAME_CAPS)) {
			if (!capable(CAP_SETFCAP))
				return -EPERM;
		} else if (!capable(CAP_SYS_ADMIN)) {
			/* A different attribute in the security namespace.
			   Restrict to administrator. */
			return -EPERM;
		}
	}

	/* Not an attribute we recognize, so just check the
	   ordinary setattr permission. */
	return dentry_has_perm(cred, NULL, dentry, FILE__SETATTR);
}

static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
				  const void *value, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	struct inode_security_struct *isec = inode->i_security;
	struct superblock_security_struct *sbsec;
	struct avc_audit_data ad;
	u32 newsid, sid = current_sid();
	int rc = 0;

	if (strcmp(name, XATTR_NAME_SELINUX))
		return selinux_inode_setotherxattr(dentry, name);

	sbsec = inode->i_sb->s_security;
	if (!(sbsec->flags & SE_SBLABELSUPP))
		return -EOPNOTSUPP;

	if (!is_owner_or_cap(inode))
		return -EPERM;

	AVC_AUDIT_DATA_INIT(&ad, FS);
	ad.u.fs.path.dentry = dentry;

	rc = avc_has_perm(sid, isec->sid, isec->sclass,
			  FILE__RELABELFROM, &ad);
	if (rc)
		return rc;

	rc = security_context_to_sid(value, size, &newsid);
	if (rc == -EINVAL) {
		if (!capable(CAP_MAC_ADMIN))
			return rc;
		rc = security_context_to_sid_force(value, size, &newsid);
	}
	if (rc)
		return rc;

	rc = avc_has_perm(sid, newsid, isec->sclass,
			  FILE__RELABELTO, &ad);
	if (rc)
		return rc;

	rc = security_validate_transition(isec->sid, newsid, sid,
					  isec->sclass);
	if (rc)
		return rc;

	return avc_has_perm(newsid,
			    sbsec->sid,
			    SECCLASS_FILESYSTEM,
			    FILESYSTEM__ASSOCIATE,
			    &ad);
}

static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
					const void *value, size_t size,
					int flags)
{
	struct inode *inode = dentry->d_inode;
	struct inode_security_struct *isec = inode->i_security;
	u32 newsid;
	int rc;

	if (strcmp(name, XATTR_NAME_SELINUX)) {
		/* Not an attribute we recognize, so nothing to do. */
		return;
	}

	rc = security_context_to_sid_force(value, size, &newsid);
	if (rc) {
		printk(KERN_ERR "SELinux:  unable to map context to SID"
		       "for (%s, %lu), rc=%d\n",
		       inode->i_sb->s_id, inode->i_ino, -rc);
		return;
	}

	isec->sid = newsid;
	return;
}

static int selinux_inode_getxattr(struct dentry *dentry, const char *name)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, NULL, dentry, FILE__GETATTR);
}

static int selinux_inode_listxattr(struct dentry *dentry)
{
	const struct cred *cred = current_cred();

	return dentry_has_perm(cred, NULL, dentry, FILE__GETATTR);
}

static int selinux_inode_removexattr(struct dentry *dentry, const char *name)
{
	if (strcmp(name, XATTR_NAME_SELINUX))
		return selinux_inode_setotherxattr(dentry, name);

	/* No one is allowed to remove a SELinux security label.
	   You can change the label, but all data must be labeled. */
	return -EACCES;
}

/*
 * Copy the inode security context value to the user.
 *
 * Permission check is handled by selinux_inode_getxattr hook.
 */
static int selinux_inode_getsecurity(const struct inode *inode, const char *name, void **buffer, bool alloc)
{
	u32 size;
	int error;
	char *context = NULL;
	struct inode_security_struct *isec = inode->i_security;

	if (strcmp(name, XATTR_SELINUX_SUFFIX))
		return -EOPNOTSUPP;

	/*
	 * If the caller has CAP_MAC_ADMIN, then get the raw context
	 * value even if it is not defined by current policy; otherwise,
	 * use the in-core value under current policy.
	 * Use the non-auditing forms of the permission checks since
	 * getxattr may be called by unprivileged processes commonly
	 * and lack of permission just means that we fall back to the
	 * in-core context value, not a denial.
	 */
	error = selinux_capable(current, current_cred(), CAP_MAC_ADMIN,
				SECURITY_CAP_NOAUDIT);
	if (!error)
		error = security_sid_to_context_force(isec->sid, &context,
						      &size);
	else
		error = security_sid_to_context(isec->sid, &context, &size);
	if (error)
		return error;
	error = size;
	if (alloc) {
		*buffer = context;
		goto out_nofree;
	}
	kfree(context);
out_nofree:
	return error;
}

static int selinux_inode_setsecurity(struct inode *inode, const char *name,
				     const void *value, size_t size, int flags)
{
	struct inode_security_struct *isec = inode->i_security;
	u32 newsid;
	int rc;

	if (strcmp(name, XATTR_SELINUX_SUFFIX))
		return -EOPNOTSUPP;

	if (!value || !size)
		return -EACCES;

	rc = security_context_to_sid((void *)value, size, &newsid);
	if (rc)
		return rc;

	isec->sid = newsid;
	return 0;
}

static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size)
{
	const int len = sizeof(XATTR_NAME_SELINUX);
	if (buffer && len <= buffer_size)
		memcpy(buffer, XATTR_NAME_SELINUX, len);
	return len;
}

static void selinux_inode_getsecid(const struct inode *inode, u32 *secid)
{
	struct inode_security_struct *isec = inode->i_security;
	*secid = isec->sid;
}

/* file security operations */

static int selinux_revalidate_file_permission(struct file *file, int mask)
{
	const struct cred *cred = current_cred();
	struct inode *inode = file->f_path.dentry->d_inode;

	/* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */
	if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE))
		mask |= MAY_APPEND;

	return file_has_perm(cred, file,
			     file_mask_to_av(inode->i_mode, mask));
}

static int selinux_file_permission(struct file *file, int mask)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct file_security_struct *fsec = file->f_security;
	struct inode_security_struct *isec = inode->i_security;
	u32 sid = current_sid();

	if (!mask)
		/* No permission to check.  Existence test. */
		return 0;

	if (sid == fsec->sid && fsec->isid == isec->sid &&
	    fsec->pseqno == avc_policy_seqno())
		/* No change since dentry_open check. */
		return 0;

	return selinux_revalidate_file_permission(file, mask);
}

static int selinux_file_alloc_security(struct file *file)
{
	return file_alloc_security(file);
}

static void selinux_file_free_security(struct file *file)
{
	file_free_security(file);
}

static int selinux_file_ioctl(struct file *file, unsigned int cmd,
			      unsigned long arg)
{
	const struct cred *cred = current_cred();
	u32 av = 0;

	if (_IOC_DIR(cmd) & _IOC_WRITE)
		av |= FILE__WRITE;
	if (_IOC_DIR(cmd) & _IOC_READ)
		av |= FILE__READ;
	if (!av)
		av = FILE__IOCTL;

	return file_has_perm(cred, file, av);
}

static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
{
	const struct cred *cred = current_cred();
	int rc = 0;

#ifndef CONFIG_PPC32
	if ((prot & PROT_EXEC) && (!file || (!shared && (prot & PROT_WRITE)))) {
		/*
		 * We are making executable an anonymous mapping or a
		 * private file mapping that will also be writable.
		 * This has an additional check.
		 */
		rc = cred_has_perm(cred, cred, PROCESS__EXECMEM);
		if (rc)
			goto error;
	}
#endif

	if (file) {
		/* read access is always possible with a mapping */
		u32 av = FILE__READ;

		/* write access only matters if the mapping is shared */
		if (shared && (prot & PROT_WRITE))
			av |= FILE__WRITE;

		if (prot & PROT_EXEC)
			av |= FILE__EXECUTE;

		return file_has_perm(cred, file, av);
	}

error:
	return rc;
}

static int selinux_file_mmap(struct file *file, unsigned long reqprot,
			     unsigned long prot, unsigned long flags,
			     unsigned long addr, unsigned long addr_only)
{
	int rc = 0;
	u32 sid = current_sid();

	if (addr < mmap_min_addr)
		rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT,
				  MEMPROTECT__MMAP_ZERO, NULL);
	if (rc || addr_only)
		return rc;

	if (selinux_checkreqprot)
		prot = reqprot;

	return file_map_prot_check(file, prot,
				   (flags & MAP_TYPE) == MAP_SHARED);
}

static int selinux_file_mprotect(struct vm_area_struct *vma,
				 unsigned long reqprot,
				 unsigned long prot)
{
	const struct cred *cred = current_cred();

	if (selinux_checkreqprot)
		prot = reqprot;

#ifndef CONFIG_PPC32
	if ((prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
		int rc = 0;
		if (vma->vm_start >= vma->vm_mm->start_brk &&
		    vma->vm_end <= vma->vm_mm->brk) {
			rc = cred_has_perm(cred, cred, PROCESS__EXECHEAP);
		} else if (!vma->vm_file &&
			   vma->vm_start <= vma->vm_mm->start_stack &&
			   vma->vm_end >= vma->vm_mm->start_stack) {
			rc = current_has_perm(current, PROCESS__EXECSTACK);
		} else if (vma->vm_file && vma->anon_vma) {
			/*
			 * We are making executable a file mapping that has
			 * had some COW done. Since pages might have been
			 * written, check ability to execute the possibly
			 * modified content.  This typically should only
			 * occur for text relocations.
			 */
			rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD);
		}
		if (rc)
			return rc;
	}
#endif

	return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED);
}

static int selinux_file_lock(struct file *file, unsigned int cmd)
{
	const struct cred *cred = current_cred();

	return file_has_perm(cred, file, FILE__LOCK);
}

static int selinux_file_fcntl(struct file *file, unsigned int cmd,
			      unsigned long arg)
{
	const struct cred *cred = current_cred();
	int err = 0;

	switch (cmd) {
	case F_SETFL:
		if (!file->f_path.dentry || !file->f_path.dentry->d_inode) {
			err = -EINVAL;
			break;
		}

		if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) {
			err = file_has_perm(cred, file, FILE__WRITE);
			break;
		}
		/* fall through */
	case F_SETOWN:
	case F_SETSIG:
	case F_GETFL:
	case F_GETOWN:
	case F_GETSIG:
		/* Just check FD__USE permission */
		err = file_has_perm(cred, file, 0);
		break;
	case F_GETLK:
	case F_SETLK:
	case F_SETLKW:
#if BITS_PER_LONG == 32
	case F_GETLK64:
	case F_SETLK64:
	case F_SETLKW64:
#endif
		if (!file->f_path.dentry || !file->f_path.dentry->d_inode) {
			err = -EINVAL;
			break;
		}
		err = file_has_perm(cred, file, FILE__LOCK);
		break;
	}

	return err;
}

static int selinux_file_set_fowner(struct file *file)
{
	struct file_security_struct *fsec;

	fsec = file->f_security;
	fsec->fown_sid = current_sid();

	return 0;
}

static int selinux_file_send_sigiotask(struct task_struct *tsk,
				       struct fown_struct *fown, int signum)
{
	struct file *file;
	u32 sid = task_sid(tsk);
	u32 perm;
	struct file_security_struct *fsec;

	/* struct fown_struct is never outside the context of a struct file */
	file = container_of(fown, struct file, f_owner);

	fsec = file->f_security;

	if (!signum)
		perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */
	else
		perm = signal_to_av(signum);

	return avc_has_perm(fsec->fown_sid, sid,
			    SECCLASS_PROCESS, perm, NULL);
}

static int selinux_file_receive(struct file *file)
{
	const struct cred *cred = current_cred();

	return file_has_perm(cred, file, file_to_av(file));
}

static int selinux_dentry_open(struct file *file, const struct cred *cred)
{
	struct file_security_struct *fsec;
	struct inode *inode;
	struct inode_security_struct *isec;

	inode = file->f_path.dentry->d_inode;
	fsec = file->f_security;
	isec = inode->i_security;
	/*
	 * Save inode label and policy sequence number
	 * at open-time so that selinux_file_permission
	 * can determine whether revalidation is necessary.
	 * Task label is already saved in the file security
	 * struct as its SID.
	 */
	fsec->isid = isec->sid;
	fsec->pseqno = avc_policy_seqno();
	/*
	 * Since the inode label or policy seqno may have changed
	 * between the selinux_inode_permission check and the saving
	 * of state above, recheck that access is still permitted.
	 * Otherwise, access might never be revalidated against the
	 * new inode label or new policy.
	 * This check is not redundant - do not remove.
	 */
	return inode_has_perm(cred, inode, open_file_to_av(file), NULL);
}

/* task security operations */

static int selinux_task_create(unsigned long clone_flags)
{
	return current_has_perm(current, PROCESS__FORK);
}

/*
 * detach and free the LSM part of a set of credentials
 */
static void selinux_cred_free(struct cred *cred)
{
	struct task_security_struct *tsec = cred->security;
	cred->security = NULL;
	kfree(tsec);
}

/*
 * prepare a new set of credentials for modification
 */
static int selinux_cred_prepare(struct cred *new, const struct cred *old,
				gfp_t gfp)
{
	const struct task_security_struct *old_tsec;
	struct task_security_struct *tsec;

	old_tsec = old->security;

	tsec = kmemdup(old_tsec, sizeof(struct task_security_struct), gfp);
	if (!tsec)
		return -ENOMEM;

	new->security = tsec;
	return 0;
}

/*
 * set the security data for a kernel service
 * - all the creation contexts are set to unlabelled
 */
static int selinux_kernel_act_as(struct cred *new, u32 secid)
{
	struct task_security_struct *tsec = new->security;
	u32 sid = current_sid();
	int ret;

	ret = avc_has_perm(sid, secid,
			   SECCLASS_KERNEL_SERVICE,
			   KERNEL_SERVICE__USE_AS_OVERRIDE,
			   NULL);
	if (ret == 0) {
		tsec->sid = secid;
		tsec->create_sid = 0;
		tsec->keycreate_sid = 0;
		tsec->sockcreate_sid = 0;
	}
	return ret;
}

/*
 * set the file creation context in a security record to the same as the
 * objective context of the specified inode
 */
static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode)
{
	struct inode_security_struct *isec = inode->i_security;
	struct task_security_struct *tsec = new->security;
	u32 sid = current_sid();
	int ret;

	ret = avc_has_perm(sid, isec->sid,
			   SECCLASS_KERNEL_SERVICE,
			   KERNEL_SERVICE__CREATE_FILES_AS,
			   NULL);

	if (ret == 0)
		tsec->create_sid = isec->sid;
	return 0;
}

static int selinux_task_setpgid(struct task_struct *p, pid_t pgid)
{
	return current_has_perm(p, PROCESS__SETPGID);
}

static int selinux_task_getpgid(struct task_struct *p)
{
	return current_has_perm(p, PROCESS__GETPGID);
}

static int selinux_task_getsid(struct task_struct *p)
{
	return current_has_perm(p, PROCESS__GETSESSION);
}

static void selinux_task_getsecid(struct task_struct *p, u32 *secid)
{
	*secid = task_sid(p);
}

static int selinux_task_setnice(struct task_struct *p, int nice)
{
	int rc;

	rc = cap_task_setnice(p, nice);
	if (rc)
		return rc;

	return current_has_perm(p, PROCESS__SETSCHED);
}

static int selinux_task_setioprio(struct task_struct *p, int ioprio)
{
	int rc;

	rc = cap_task_setioprio(p, ioprio);
	if (rc)
		return rc;

	return current_has_perm(p, PROCESS__SETSCHED);
}

static int selinux_task_getioprio(struct task_struct *p)
{
	return current_has_perm(p, PROCESS__GETSCHED);
}

static int selinux_task_setrlimit(unsigned int resource, struct rlimit *new_rlim)
{
	struct rlimit *old_rlim = current->signal->rlim + resource;

	/* Control the ability to change the hard limit (whether
	   lowering or raising it), so that the hard limit can
	   later be used as a safe reset point for the soft limit
	   upon context transitions.  See selinux_bprm_committing_creds. */
	if (old_rlim->rlim_max != new_rlim->rlim_max)
		return current_has_perm(current, PROCESS__SETRLIMIT);

	return 0;
}

static int selinux_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp)
{
	int rc;

	rc = cap_task_setscheduler(p, policy, lp);
	if (rc)
		return rc;

	return current_has_perm(p, PROCESS__SETSCHED);
}

static int selinux_task_getscheduler(struct task_struct *p)
{
	return current_has_perm(p, PROCESS__GETSCHED);
}

static int selinux_task_movememory(struct task_struct *p)
{
	return current_has_perm(p, PROCESS__SETSCHED);
}

static int selinux_task_kill(struct task_struct *p, struct siginfo *info,
				int sig, u32 secid)
{
	u32 perm;
	int rc;

	if (!sig)
		perm = PROCESS__SIGNULL; /* null signal; existence test */
	else
		perm = signal_to_av(sig);
	if (secid)
		rc = avc_has_perm(secid, task_sid(p),
				  SECCLASS_PROCESS, perm, NULL);
	else
		rc = current_has_perm(p, perm);
	return rc;
}

static int selinux_task_wait(struct task_struct *p)
{
	return task_has_perm(p, current, PROCESS__SIGCHLD);
}

static void selinux_task_to_inode(struct task_struct *p,
				  struct inode *inode)
{
	struct inode_security_struct *isec = inode->i_security;
	u32 sid = task_sid(p);

	isec->sid = sid;
	isec->initialized = 1;
}

/* Returns error only if unable to parse addresses */
static int selinux_parse_skb_ipv4(struct sk_buff *skb,
			struct avc_audit_data *ad, u8 *proto)
{
	int offset, ihlen, ret = -EINVAL;
	struct iphdr _iph, *ih;

	offset = skb_network_offset(skb);
	ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
	if (ih == NULL)
		goto out;

	ihlen = ih->ihl * 4;
	if (ihlen < sizeof(_iph))
		goto out;

	ad->u.net.v4info.saddr = ih->saddr;
	ad->u.net.v4info.daddr = ih->daddr;
	ret = 0;

	if (proto)
		*proto = ih->protocol;

	switch (ih->protocol) {
	case IPPROTO_TCP: {
		struct tcphdr _tcph, *th;

		if (ntohs(ih->frag_off) & IP_OFFSET)
			break;

		offset += ihlen;
		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
		if (th == NULL)
			break;

		ad->u.net.sport = th->source;
		ad->u.net.dport = th->dest;
		break;
	}

	case IPPROTO_UDP: {
		struct udphdr _udph, *uh;

		if (ntohs(ih->frag_off) & IP_OFFSET)
			break;

		offset += ihlen;
		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
		if (uh == NULL)
			break;

		ad->u.net.sport = uh->source;
		ad->u.net.dport = uh->dest;
		break;
	}

	case IPPROTO_DCCP: {
		struct dccp_hdr _dccph, *dh;

		if (ntohs(ih->frag_off) & IP_OFFSET)
			break;

		offset += ihlen;