summaryrefslogtreecommitdiffstats
path: root/kernel/seccomp.c
blob: efd384f3f852ea0d2611154752f646d411bbaf49 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
/*
 * linux/kernel/seccomp.c
 *
 * Copyright 2004-2005  Andrea Arcangeli <andrea@cpushare.com>
 *
 * Copyright (C) 2012 Google, Inc.
 * Will Drewry <wad@chromium.org>
 *
 * This defines a simple but solid secure-computing facility.
 *
 * Mode 1 uses a fixed list of allowed system calls.
 * Mode 2 allows user-defined system call filters in the form
 *        of Berkeley Packet Filters/Linux Socket Filters.
 */

#include <linux/atomic.h>
#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
#include <linux/slab.h>
#include <linux/syscalls.h>

#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
#include <asm/syscall.h>
#endif

#ifdef CONFIG_SECCOMP_FILTER
#include <linux/filter.h>
#include <linux/pid.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>

/**
 * struct seccomp_filter - container for seccomp BPF programs
 *
 * @usage: reference count to manage the object lifetime.
 *         get/put helpers should be used when accessing an instance
 *         outside of a lifetime-guarded section.  In general, this
 *         is only needed for handling filters shared across tasks.
 * @prev: points to a previously installed, or inherited, filter
 * @len: the number of instructions in the program
 * @insnsi: the BPF program instructions to evaluate
 *
 * seccomp_filter objects are organized in a tree linked via the @prev
 * pointer.  For any task, it appears to be a singly-linked list starting
 * with current->seccomp.filter, the most recently attached or inherited filter.
 * However, multiple filters may share a @prev node, by way of fork(), which
 * results in a unidirectional tree existing in memory.  This is similar to
 * how namespaces work.
 *
 * seccomp_filter objects should never be modified after being attached
 * to a task_struct (other than @usage).
 */
struct seccomp_filter {
	atomic_t usage;
	struct seccomp_filter *prev;
	struct bpf_prog *prog;
};

/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))

/*
 * Endianness is explicitly ignored and left for BPF program authors to manage
 * as per the specific architecture.
 */
static void populate_seccomp_data(struct seccomp_data *sd)
{
	struct task_struct *task = current;
	struct pt_regs *regs = task_pt_regs(task);
	unsigned long args[6];

	sd->nr = syscall_get_nr(task, regs);
	sd->arch = syscall_get_arch();
	syscall_get_arguments(task, regs, 0, 6, args);
	sd->args[0] = args[0];
	sd->args[1] = args[1];
	sd->args[2] = args[2];
	sd->args[3] = args[3];
	sd->args[4] = args[4];
	sd->args[5] = args[5];
	sd->instruction_pointer = KSTK_EIP(task);
}

/**
 *	seccomp_check_filter - verify seccomp filter code
 *	@filter: filter to verify
 *	@flen: length of filter
 *
 * Takes a previously checked filter (by bpf_check_classic) and
 * redirects all filter code that loads struct sk_buff data
 * and related data through seccomp_bpf_load.  It also
 * enforces length and alignment checking of those loads.
 *
 * Returns 0 if the rule set is legal or -EINVAL if not.
 */
static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
{
	int pc;
	for (pc = 0; pc < flen; pc++) {
		struct sock_filter *ftest = &filter[pc];
		u16 code = ftest->code;
		u32 k = ftest->k;

		switch (code) {
		case BPF_LD | BPF_W | BPF_ABS:
			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
			/* 32-bit aligned and not out of bounds. */
			if (k >= sizeof(struct seccomp_data) || k & 3)
				return -EINVAL;
			continue;
		case BPF_LD | BPF_W | BPF_LEN:
			ftest->code = BPF_LD | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		case BPF_LDX | BPF_W | BPF_LEN:
			ftest->code = BPF_LDX | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		/* Explicitly include allowed calls. */
		case BPF_RET | BPF_K:
		case BPF_RET | BPF_A:
		case BPF_ALU | BPF_ADD | BPF_K:
		case BPF_ALU | BPF_ADD | BPF_X:
		case BPF_ALU | BPF_SUB | BPF_K:
		case BPF_ALU | BPF_SUB | BPF_X:
		case BPF_ALU | BPF_MUL | BPF_K:
		case BPF_ALU | BPF_MUL | BPF_X:
		case BPF_ALU | BPF_DIV | BPF_K:
		case BPF_ALU | BPF_DIV | BPF_X:
		case BPF_ALU | BPF_AND | BPF_K:
		case BPF_ALU | BPF_AND | BPF_X:
		case BPF_ALU | BPF_OR | BPF_K:
		case BPF_ALU | BPF_OR | BPF_X:
		case BPF_ALU | BPF_XOR | BPF_K:
		case BPF_ALU | BPF_XOR | BPF_X:
		case BPF_ALU | BPF_LSH | BPF_K:
		case BPF_ALU | BPF_LSH | BPF_X:
		case BPF_ALU | BPF_RSH | BPF_K:
		case BPF_ALU | BPF_RSH | BPF_X:
		case BPF_ALU | BPF_NEG:
		case BPF_LD | BPF_IMM:
		case BPF_LDX | BPF_IMM:
		case BPF_MISC | BPF_TAX:
		case BPF_MISC | BPF_TXA:
		case BPF_LD | BPF_MEM:
		case BPF_LDX | BPF_MEM:
		case BPF_ST:
		case BPF_STX:
		case BPF_JMP | BPF_JA:
		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
			continue;
		default:
			return -EINVAL;
		}
	}
	return 0;
}

/**
 * seccomp_run_filters - evaluates all seccomp filters against @syscall
 * @syscall: number of the current system call
 *
 * Returns valid seccomp BPF response codes.
 */
static u32 seccomp_run_filters(struct seccomp_data *sd)
{
	struct seccomp_data sd_local;
	u32 ret = SECCOMP_RET_ALLOW;
	/* Make sure cross-thread synced filter points somewhere sane. */
	struct seccomp_filter *f =
			lockless_dereference(current->seccomp.filter);

	/* Ensure unexpected behavior doesn't result in failing open. */
	if (unlikely(WARN_ON(f == NULL)))
		return SECCOMP_RET_KILL;

	if (!sd) {
		populate_seccomp_data(&sd_local);
		sd = &sd_local;
	}

	/*
	 * All filters in the list are evaluated and the lowest BPF return
	 * value always takes priority (ignoring the DATA).
	 */
	for (; f; f = f->prev) {
		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd);

		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
			ret = cur_ret;
	}
	return ret;
}
#endif /* CONFIG_SECCOMP_FILTER */

static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
{
	assert_spin_locked(&current->sighand->siglock);

	if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
		return false;

	return true;
}

static inline void seccomp_assign_mode(struct task_struct *task,
				       unsigned long seccomp_mode)
{
	assert_spin_locked(&task->sighand->siglock);

	task->seccomp.mode = seccomp_mode;
	/*
	 * Make sure TIF_SECCOMP cannot be set before the mode (and
	 * filter) is set.
	 */
	smp_mb__before_atomic();
	set_tsk_thread_flag(task, TIF_SECCOMP);
}

#ifdef CONFIG_SECCOMP_FILTER
/* Returns 1 if the parent is an ancestor of the child. */
static int is_ancestor(struct seccomp_filter *parent,
		       struct seccomp_filter *child)
{
	/* NULL is the root ancestor. */
	if (parent == NULL)
		return 1;
	for (; child; child = child->prev)
		if (child == parent)
			return 1;
	return 0;
}

/**
 * seccomp_can_sync_threads: checks if all threads can be synchronized
 *
 * Expects sighand and cred_guard_mutex locks to be held.
 *
 * Returns 0 on success, -ve on error, or the pid of a thread which was
 * either not in the correct seccomp mode or it did not have an ancestral
 * seccomp filter.
 */
static inline pid_t seccomp_can_sync_threads(void)
{
	struct task_struct *thread, *caller;

	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
	assert_spin_locked(&current->sighand->siglock);

	/* Validate all threads being eligible for synchronization. */
	caller = current;
	for_each_thread(caller, thread) {
		pid_t failed;

		/* Skip current, since it is initiating the sync. */
		if (thread == caller)
			continue;

		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
		    (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
		     is_ancestor(thread->seccomp.filter,
				 caller->seccomp.filter)))
			continue;

		/* Return the first thread that cannot be synchronized. */
		failed = task_pid_vnr(thread);
		/* If the pid cannot be resolved, then return -ESRCH */
		if (unlikely(WARN_ON(failed == 0)))
			failed = -ESRCH;
		return failed;
	}

	return 0;
}

/**
 * seccomp_sync_threads: sets all threads to use current's filter
 *
 * Expects sighand and cred_guard_mutex locks to be held, and for
 * seccomp_can_sync_threads() to have returned success already
 * without dropping the locks.
 *
 */
static inline void seccomp_sync_threads(void)
{
	struct task_struct *thread, *caller;

	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
	assert_spin_locked(&current->sighand->siglock);

	/* Synchronize all threads. */
	caller = current;
	for_each_thread(caller, thread) {
		/* Skip current, since it needs no changes. */
		if (thread == caller)
			continue;

		/* Get a task reference for the new leaf node. */
		get_seccomp_filter(caller);
		/*
		 * Drop the task reference to the shared ancestor since
		 * current's path will hold a reference.  (This also
		 * allows a put before the assignment.)
		 */
		put_seccomp_filter(thread);
		smp_store_release(&thread->seccomp.filter,
				  caller->seccomp.filter);

		/*
		 * Don't let an unprivileged task work around
		 * the no_new_privs restriction by creating
		 * a thread that sets it up, enters seccomp,
		 * then dies.
		 */
		if (task_no_new_privs(caller))
			task_set_no_new_privs(thread);

		/*
		 * Opt the other thread into seccomp if needed.
		 * As threads are considered to be trust-realm
		 * equivalent (see ptrace_may_access), it is safe to
		 * allow one thread to transition the other.
		 */
		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
	}
}

/**
 * seccomp_prepare_filter: Prepares a seccomp filter for use.
 * @fprog: BPF program to install
 *
 * Returns filter on success or an ERR_PTR on failure.
 */
static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
	struct seccomp_filter *sfilter;
	int ret;
	const bool save_orig = config_enabled(CONFIG_CHECKPOINT_RESTORE);

	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
		return ERR_PTR(-EINVAL);

	BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));

	/*
	 * Installing a seccomp filter requires that the task has
	 * CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
	 * This avoids scenarios where unprivileged tasks can affect the
	 * behavior of privileged children.
	 */
	if (!task_no_new_privs(current) &&
	    security_capable_noaudit(current_cred(), current_user_ns(),
				     CAP_SYS_ADMIN) != 0)
		return ERR_PTR(-EACCES);

	/* Allocate a new seccomp_filter */
	sfilter = kzalloc(sizeof(*sfilter), GFP_KERNEL | __GFP_NOWARN);
	if (!sfilter)
		return ERR_PTR(-ENOMEM);

	ret = bpf_prog_create_from_user(&sfilter->prog, fprog,
					seccomp_check_filter, save_orig);
	if (ret < 0) {
		kfree(sfilter);
		return ERR_PTR(ret);
	}

	atomic_set(&sfilter->usage, 1);

	return sfilter;
}

/**
 * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog
 * @user_filter: pointer to the user data containing a sock_fprog.
 *
 * Returns 0 on success and non-zero otherwise.
 */
static struct seccomp_filter *
seccomp_prepare_user_filter(const char __user *user_filter)
{
	struct sock_fprog fprog;
	struct seccomp_filter *filter = ERR_PTR(-EFAULT);

#ifdef CONFIG_COMPAT
	if (is_compat_task()) {
		struct compat_sock_fprog fprog32;
		if (copy_from_user(&fprog32, user_filter, sizeof(fprog32)))
			goto out;
		fprog.len = fprog32.len;
		fprog.filter = compat_ptr(fprog32.filter);
	} else /* falls through to the if below. */
#endif
	if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
		goto out;
	filter = seccomp_prepare_filter(&fprog);
out:
	return filter;
}

/**
 * seccomp_attach_filter: validate and attach filter
 * @flags:  flags to change filter behavior
 * @filter: seccomp filter to add to the current process
 *
 * Caller must be holding current->sighand->siglock lock.
 *
 * Returns 0 on success, -ve on error.
 */
static long seccomp_attach_filter(unsigned int flags,
				  struct seccomp_filter *filter)
{
	unsigned long total_insns;
	struct seccomp_filter *walker;

	assert_spin_locked(&current->sighand->siglock);

	/* Validate resulting filter length. */
	total_insns = filter->prog->len;
	for (walker = current->seccomp.filter; walker; walker = walker->prev)
		total_insns += walker->prog->len + 4;  /* 4 instr penalty */
	if (total_insns > MAX_INSNS_PER_PATH)
		return -ENOMEM;

	/* If thread sync has been requested, check that it is possible. */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
		int ret;

		ret = seccomp_can_sync_threads();
		if (ret)
			return ret;
	}

	/*
	 * If there is an existing filter, make it the prev and don't drop its
	 * task reference.
	 */
	filter->prev = current->seccomp.filter;
	current->seccomp.filter = filter;

	/* Now that the new filter is in place, synchronize to all threads. */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
		seccomp_sync_threads();

	return 0;
}

void __get_seccomp_filter(struct seccomp_filter *filter)
{
	/* Reference count is bounded by the number of total processes. */
	atomic_inc(&filter->usage);
}

/* get_seccomp_filter - increments the reference count of the filter on @tsk */
void get_seccomp_filter(struct task_struct *tsk)
{
	struct seccomp_filter *orig = tsk->seccomp.filter;
	if (!orig)
		return;
	__get_seccomp_filter(orig);
}

static inline void seccomp_filter_free(struct seccomp_filter *filter)
{
	if (filter) {
		bpf_prog_destroy(filter->prog);
		kfree(filter);
	}
}

static void __put_seccomp_filter(struct seccomp_filter *orig)
{
	/* Clean up single-reference branches iteratively. */
	while (orig && atomic_dec_and_test(&orig->usage)) {
		struct seccomp_filter *freeme = orig;
		orig = orig->prev;
		seccomp_filter_free(freeme);
	}
}

/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
void put_seccomp_filter(struct task_struct *tsk)
{
	__put_seccomp_filter(tsk->seccomp.filter);
}

/**
 * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
 * @syscall: syscall number to send to userland
 * @reason: filter-supplied reason code to send to userland (via si_errno)
 *
 * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
 */
static void seccomp_send_sigsys(int syscall, int reason)
{
	struct siginfo info;
	memset(&info, 0, sizeof(info));
	info.si_signo = SIGSYS;
	info.si_code = SYS_SECCOMP;
	info.si_call_addr = (void __user *)KSTK_EIP(current);
	info.si_errno = reason;
	info.si_arch = syscall_get_arch();
	info.si_syscall = syscall;
	force_sig_info(SIGSYS, &info, current);
}
#endif	/* CONFIG_SECCOMP_FILTER */

/*
 * Secure computing mode 1 allows only read/write/exit/sigreturn.
 * To be fully secure this must be combined with rlimit
 * to limit the stack allocations too.
 */
static int mode1_syscalls[] = {
	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
	0, /* null terminated */
};

#ifdef CONFIG_COMPAT
static int mode1_syscalls_32[] = {
	__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
	0, /* null terminated */
};
#endif

static void __secure_computing_strict(int this_syscall)
{
	int *syscall_whitelist = mode1_syscalls;
#ifdef CONFIG_COMPAT
	if (is_compat_task())
		syscall_whitelist = mode1_syscalls_32;
#endif
	do {
		if (*syscall_whitelist == this_syscall)
			return;
	} while (*++syscall_whitelist);

#ifdef SECCOMP_DEBUG
	dump_stack();
#endif
	audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
	do_exit(SIGKILL);
}

#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER
void secure_computing_strict(int this_syscall)
{
	int mode = current->seccomp.mode;

	if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
		return;

	if (mode == SECCOMP_MODE_DISABLED)
		return;
	else if (mode == SECCOMP_MODE_STRICT)
		__secure_computing_strict(this_syscall);
	else
		BUG();
}
#else
int __secure_computing(void)
{
	u32 phase1_result = seccomp_phase1(NULL);

	if (likely(phase1_result == SECCOMP_PHASE1_OK))
		return 0;
	else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
		return -1;
	else
		return seccomp_phase2(phase1_result);
}

#ifdef CONFIG_SECCOMP_FILTER
static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
{
	u32 filter_ret, action;
	int data;

	/*
	 * Make sure that any changes to mode from another thread have
	 * been seen after TIF_SECCOMP was seen.
	 */
	rmb();

	filter_ret = seccomp_run_filters(sd);
	data = filter_ret & SECCOMP_RET_DATA;
	action = filter_ret & SECCOMP_RET_ACTION;

	switch (action) {
	case SECCOMP_RET_ERRNO:
		/* Set low-order bits as an errno, capped at MAX_ERRNO. */
		if (data > MAX_ERRNO)
			data = MAX_ERRNO;
		syscall_set_return_value(current, task_pt_regs(current),
					 -data, 0);
		goto skip;

	case SECCOMP_RET_TRAP:
		/* Show the handler the original registers. */
		syscall_rollback(current, task_pt_regs(current));
		/* Let the filter pass back 16 bits of data. */
		seccomp_send_sigsys(this_syscall, data);
		goto skip;

	case SECCOMP_RET_TRACE:
		return filter_ret;  /* Save the rest for phase 2. */

	case SECCOMP_RET_ALLOW:
		return SECCOMP_PHASE1_OK;

	case SECCOMP_RET_KILL:
	default:
		audit_seccomp(this_syscall, SIGSYS, action);
		do_exit(SIGSYS);
	}

	unreachable();

skip:
	audit_seccomp(this_syscall, 0, action);
	return SECCOMP_PHASE1_SKIP;
}
#endif

/**
 * seccomp_phase1() - run fast path seccomp checks on the current syscall
 * @arg sd: The seccomp_data or NULL
 *
 * This only reads pt_regs via the syscall_xyz helpers.  The only change
 * it will make to pt_regs is via syscall_set_return_value, and it will
 * only do that if it returns SECCOMP_PHASE1_SKIP.
 *
 * If sd is provided, it will not read pt_regs at all.
 *
 * It may also call do_exit or force a signal; these actions must be
 * safe.
 *
 * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
 * be processed normally.
 *
 * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
 * invoked.  In this case, seccomp_phase1 will have set the return value
 * using syscall_set_return_value.
 *
 * If it returns anything else, then the return value should be passed
 * to seccomp_phase2 from a context in which ptrace hooks are safe.
 */
u32 seccomp_phase1(struct seccomp_data *sd)
{
	int mode = current->seccomp.mode;
	int this_syscall = sd ? sd->nr :
		syscall_get_nr(current, task_pt_regs(current));

	if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
		return SECCOMP_PHASE1_OK;

	switch (mode) {
	case SECCOMP_MODE_STRICT:
		__secure_computing_strict(this_syscall);  /* may call do_exit */
		return SECCOMP_PHASE1_OK;
#ifdef CONFIG_SECCOMP_FILTER
	case SECCOMP_MODE_FILTER:
		return __seccomp_phase1_filter(this_syscall, sd);
#endif
	default:
		BUG();
	}
}

/**
 * seccomp_phase2() - finish slow path seccomp work for the current syscall
 * @phase1_result: The return value from seccomp_phase1()
 *
 * This must be called from a context in which ptrace hooks can be used.
 *
 * Returns 0 if the syscall should be processed or -1 to skip the syscall.
 */
int seccomp_phase2(u32 phase1_result)
{
	struct pt_regs *regs = task_pt_regs(current);
	u32 action = phase1_result & SECCOMP_RET_ACTION;
	int data = phase1_result & SECCOMP_RET_DATA;

	BUG_ON(action != SECCOMP_RET_TRACE);

	audit_seccomp(syscall_get_nr(current, regs), 0, action);

	/* Skip these calls if there is no tracer. */
	if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
		syscall_set_return_value(current, regs,
					 -ENOSYS, 0);
		return -1;
	}

	/* Allow the BPF to provide the event message */
	ptrace_event(PTRACE_EVENT_SECCOMP, data);
	/*
	 * The delivery of a fatal signal during event
	 * notification may silently skip tracer notification.
	 * Terminating the task now avoids executing a system
	 * call that may not be intended.
	 */
	if (fatal_signal_pending(current))
		do_exit(SIGSYS);
	if (syscall_get_nr(current, regs) < 0)
		return -1;  /* Explicit request to skip. */

	return 0;
}
#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */

long prctl_get_seccomp(void)
{
	return current->seccomp.mode;
}

/**
 * seccomp_set_mode_strict: internal function for setting strict seccomp
 *
 * Once current->seccomp.mode is non-zero, it may not be changed.
 *
 * Returns 0 on success or -EINVAL on failure.
 */
static long seccomp_set_mode_strict(void)
{
	const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
	long ret = -EINVAL;

	spin_lock_irq(&current->sighand->siglock);

	if (!seccomp_may_assign_mode(seccomp_mode))
		goto out;

#ifdef TIF_NOTSC
	disable_TSC();
#endif
	seccomp_assign_mode(current, seccomp_mode);
	ret = 0;

out:
	spin_unlock_irq(&current->sighand->siglock);

	return ret;
}

#ifdef CONFIG_SECCOMP_FILTER
/**
 * seccomp_set_mode_filter: internal function for setting seccomp filter
 * @flags:  flags to change filter behavior
 * @filter: struct sock_fprog containing filter
 *
 * This function may be called repeatedly to install additional filters.
 * Every filter successfully installed will be evaluated (in reverse order)
 * for each system call the task makes.
 *
 * Once current->seccomp.mode is non-zero, it may not be changed.
 *
 * Returns 0 on success or -EINVAL on failure.
 */
static long seccomp_set_mode_filter(unsigned int flags,
				    const char __user *filter)
{
	const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
	struct seccomp_filter *prepared = NULL;
	long ret = -EINVAL;

	/* Validate flags. */
	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
		return -EINVAL;

	/* Prepare the new filter before holding any locks. */
	prepared = seccomp_prepare_user_filter(filter);
	if (IS_ERR(prepared))
		return PTR_ERR(prepared);

	/*
	 * Make sure we cannot change seccomp or nnp state via TSYNC
	 * while another thread is in the middle of calling exec.
	 */
	if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
	    mutex_lock_killable(&current->signal->cred_guard_mutex))
		goto out_free;

	spin_lock_irq(&current->sighand->siglock);

	if (!seccomp_may_assign_mode(seccomp_mode))
		goto out;

	ret = seccomp_attach_filter(flags, prepared);
	if (ret)
		goto out;
	/* Do not free the successfully attached filter. */
	prepared = NULL;

	seccomp_assign_mode(current, seccomp_mode);
out:
	spin_unlock_irq(&current->sighand->siglock);
	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
		mutex_unlock(&current->signal->cred_guard_mutex);
out_free:
	seccomp_filter_free(prepared);
	return ret;
}
#else
static inline long seccomp_set_mode_filter(unsigned int flags,
					   const char __user *filter)
{
	return -EINVAL;
}
#endif

/* Common entry point for both prctl and syscall. */
static long do_seccomp(unsigned int op, unsigned int flags,
		       const char __user *uargs)
{
	switch (op) {
	case SECCOMP_SET_MODE_STRICT:
		if (flags != 0 || uargs != NULL)
			return -EINVAL;
		return seccomp_set_mode_strict();
	case SECCOMP_SET_MODE_FILTER:
		return seccomp_set_mode_filter(flags, uargs);
	default:
		return -EINVAL;
	}
}

SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
			 const char __user *, uargs)
{
	return do_seccomp(op, flags, uargs);
}

/**
 * prctl_set_seccomp: configures current->seccomp.mode
 * @seccomp_mode: requested mode to use
 * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
 *
 * Returns 0 on success or -EINVAL on failure.
 */
long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
	unsigned int op;
	char __user *uargs;

	switch (seccomp_mode) {
	case SECCOMP_MODE_STRICT:
		op = SECCOMP_SET_MODE_STRICT;
		/*
		 * Setting strict mode through prctl always ignored filter,
		 * so make sure it is always NULL here to pass the internal
		 * check in do_seccomp().
		 */
		uargs = NULL;
		break;
	case SECCOMP_MODE_FILTER:
		op = SECCOMP_SET_MODE_FILTER;
		uargs = filter;
		break;
	default:
		return -EINVAL;
	}

	/* prctl interface doesn't have flags, so they are always zero. */
	return do_seccomp(op, 0, uargs);
}

#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
			void __user *data)
{
	struct seccomp_filter *filter;
	struct sock_fprog_kern *fprog;
	long ret;
	unsigned long count = 0;

	if (!capable(CAP_SYS_ADMIN) ||
	    current->seccomp.mode != SECCOMP_MODE_DISABLED) {
		return -EACCES;
	}

	spin_lock_irq(&task->sighand->siglock);
	if (task->seccomp.mode != SECCOMP_MODE_FILTER) {
		ret = -EINVAL;
		goto out;
	}

	filter = task->seccomp.filter;
	while (filter) {
		filter = filter->prev;
		count++;
	}

	if (filter_off >= count) {
		ret = -ENOENT;
		goto out;
	}
	count -= filter_off;

	filter = task->seccomp.filter;
	while (filter && count > 1) {
		filter = filter->prev;
		count--;
	}

	if (WARN_ON(count != 1 || !filter)) {
		/* The filter tree shouldn't shrink while we're using it. */
		ret = -ENOENT;
		goto out;
	}

	fprog = filter->prog->orig_prog;
	if (!fprog) {
		/* This must be a new non-cBPF filter, since we save every
		 * every cBPF filter's orig_prog above when
		 * CONFIG_CHECKPOINT_RESTORE is enabled.
		 */
		ret = -EMEDIUMTYPE;
		goto out;
	}

	ret = fprog->len;
	if (!data)
		goto out;

	__get_seccomp_filter(filter);
	spin_unlock_irq(&task->sighand->siglock);

	if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
		ret = -EFAULT;

	__put_seccomp_filter(filter);
	return ret;

out:
	spin_unlock_irq(&task->sighand->siglock);
	return ret;
}
#endif