Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 6f357f4fc85900db94f5a9dc45b098849e0e158d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
/*
 * linux/kernel/ptrace.c
 *
 * (C) Copyright 1999 Linus Torvalds
 *
 * Common interfaces for "ptrace()" which we do not want
 * to continually duplicate across every architecture.
 */

#include <linux/capability.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/signal.h>
#include <linux/uio.h>
#include <linux/audit.h>
#include <linux/pid_namespace.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/regset.h>
#include <linux/hw_breakpoint.h>
#include <linux/cn_proc.h>
#include <linux/compat.h>
#include <linux/sched/signal.h>

/*
 * Access another process' address space via ptrace.
 * Source/target buffer must be kernel space,
 * Do not walk the page table directly, use get_user_pages
 */
int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
		     void *buf, int len, unsigned int gup_flags)
{
	struct mm_struct *mm;
	int ret;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	if (!tsk->ptrace ||
	    (current != tsk->parent) ||
	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
	     !ptracer_capable(tsk, mm->user_ns))) {
		mmput(mm);
		return 0;
	}

	ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
	mmput(mm);

	return ret;
}


void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
		   const struct cred *ptracer_cred)
{
	BUG_ON(!list_empty(&child->ptrace_entry));
	list_add(&child->ptrace_entry, &new_parent->ptraced);
	child->parent = new_parent;
	child->ptracer_cred = get_cred(ptracer_cred);
}

/*
 * ptrace a task: make the debugger its new parent and
 * move it to the ptrace list.
 *
 * Must be called with the tasklist lock write-held.
 */
static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
{
	rcu_read_lock();
	__ptrace_link(child, new_parent, __task_cred(new_parent));
	rcu_read_unlock();
}

/**
 * __ptrace_unlink - unlink ptracee and restore its execution state
 * @child: ptracee to be unlinked
 *
 * Remove @child from the ptrace list, move it back to the original parent,
 * and restore the execution state so that it conforms to the group stop
 * state.
 *
 * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer
 * exiting.  For PTRACE_DETACH, unless the ptracee has been killed between
 * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED.
 * If the ptracer is exiting, the ptracee can be in any state.
 *
 * After detach, the ptracee should be in a state which conforms to the
 * group stop.  If the group is stopped or in the process of stopping, the
 * ptracee should be put into TASK_STOPPED; otherwise, it should be woken
 * up from TASK_TRACED.
 *
 * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED,
 * it goes through TRACED -> RUNNING -> STOPPED transition which is similar
 * to but in the opposite direction of what happens while attaching to a
 * stopped task.  However, in this direction, the intermediate RUNNING
 * state is not hidden even from the current ptracer and if it immediately
 * re-attaches and performs a WNOHANG wait(2), it may fail.
 *
 * CONTEXT:
 * write_lock_irq(tasklist_lock)
 */
void __ptrace_unlink(struct task_struct *child)
{
	const struct cred *old_cred;
	BUG_ON(!child->ptrace);

	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);

	child->parent = child->real_parent;
	list_del_init(&child->ptrace_entry);
	old_cred = child->ptracer_cred;
	child->ptracer_cred = NULL;
	put_cred(old_cred);

	spin_lock(&child->sighand->siglock);
	child->ptrace = 0;
	/*
	 * Clear all pending traps and TRAPPING.  TRAPPING should be
	 * cleared regardless of JOBCTL_STOP_PENDING.  Do it explicitly.
	 */
	task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK);
	task_clear_jobctl_trapping(child);

	/*
	 * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and
	 * @child isn't dead.
	 */
	if (!(child->flags & PF_EXITING) &&
	    (child->signal->flags & SIGNAL_STOP_STOPPED ||
	     child->signal->group_stop_count)) {
		child->jobctl |= JOBCTL_STOP_PENDING;

		/*
		 * This is only possible if this thread was cloned by the
		 * traced task running in the stopped group, set the signal
		 * for the future reports.
		 * FIXME: we should change ptrace_init_task() to handle this
		 * case.
		 */
		if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
			child->jobctl |= SIGSTOP;
	}

	/*
	 * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
	 * @child in the butt.  Note that @resume should be used iff @child
	 * is in TASK_TRACED; otherwise, we might unduly disrupt
	 * TASK_KILLABLE sleeps.
	 */
	if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
		ptrace_signal_wake_up(child, true);

	spin_unlock(&child->sighand->siglock);
}

/* Ensure that nothing can wake it up, even SIGKILL */
static bool ptrace_freeze_traced(struct task_struct *task)
{
	bool ret = false;

	/* Lockless, nobody but us can set this flag */
	if (task->jobctl & JOBCTL_LISTENING)
		return ret;

	spin_lock_irq(&task->sighand->siglock);
	if (task_is_traced(task) && !__fatal_signal_pending(task)) {
		task->state = __TASK_TRACED;
		ret = true;
	}
	spin_unlock_irq(&task->sighand->siglock);

	return ret;
}

static void ptrace_unfreeze_traced(struct task_struct *task)
{
	if (task->state != __TASK_TRACED)
		return;

	WARN_ON(!task->ptrace || task->parent != current);

	/*
	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
	 * Recheck state under the lock to close this race.
	 */
	spin_lock_irq(&task->sighand->siglock);
	if (task->state == __TASK_TRACED) {
		if (__fatal_signal_pending(task))
			wake_up_state(task, __TASK_TRACED);
		else
			task->state = TASK_TRACED;
	}
	spin_unlock_irq(&task->sighand->siglock);
}

/**
 * ptrace_check_attach - check whether ptracee is ready for ptrace operation
 * @child: ptracee to check for
 * @ignore_state: don't check whether @child is currently %TASK_TRACED
 *
 * Check whether @child is being ptraced by %current and ready for further
 * ptrace operations.  If @ignore_state is %false, @child also should be in
 * %TASK_TRACED state and on return the child is guaranteed to be traced
 * and not executing.  If @ignore_state is %true, @child can be in any
 * state.
 *
 * CONTEXT:
 * Grabs and releases tasklist_lock and @child->sighand->siglock.
 *
 * RETURNS:
 * 0 on success, -ESRCH if %child is not ready.
 */
static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
{
	int ret = -ESRCH;

	/*
	 * We take the read lock around doing both checks to close a
	 * possible race where someone else was tracing our child and
	 * detached between these two checks.  After this locked check,
	 * we are sure that this is our traced child and that can only
	 * be changed by us so it's not changing right after this.
	 */
	read_lock(&tasklist_lock);
	if (child->ptrace && child->parent == current) {
		WARN_ON(child->state == __TASK_TRACED);
		/*
		 * child->sighand can't be NULL, release_task()
		 * does ptrace_unlink() before __exit_signal().
		 */
		if (ignore_state || ptrace_freeze_traced(child))
			ret = 0;
	}
	read_unlock(&tasklist_lock);

	if (!ret && !ignore_state) {
		if (!wait_task_inactive(child, __TASK_TRACED)) {
			/*
			 * This can only happen if may_ptrace_stop() fails and
			 * ptrace_stop() changes ->state back to TASK_RUNNING,
			 * so we should not worry about leaking __TASK_TRACED.
			 */
			WARN_ON(child->state == __TASK_TRACED);
			ret = -ESRCH;
		}
	}

	return ret;
}

static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
{
	if (mode & PTRACE_MODE_NOAUDIT)
		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
	else
		return has_ns_capability(current, ns, CAP_SYS_PTRACE);
}

/* Returns 0 on success, -errno on denial. */
static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
	const struct cred *cred = current_cred(), *tcred;
	struct mm_struct *mm;
	kuid_t caller_uid;
	kgid_t caller_gid;

	if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
		WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
		return -EPERM;
	}

	/* May we inspect the given task?
	 * This check is used both for attaching with ptrace
	 * and for allowing access to sensitive information in /proc.
	 *
	 * ptrace_attach denies several cases that /proc allows
	 * because setting up the necessary parent/child relationship
	 * or halting the specified task is impossible.
	 */

	/* Don't let security modules deny introspection */
	if (same_thread_group(task, current))
		return 0;
	rcu_read_lock();
	if (mode & PTRACE_MODE_FSCREDS) {
		caller_uid = cred->fsuid;
		caller_gid = cred->fsgid;
	} else {
		/*
		 * Using the euid would make more sense here, but something
		 * in userland might rely on the old behavior, and this
		 * shouldn't be a security problem since
		 * PTRACE_MODE_REALCREDS implies that the caller explicitly
		 * used a syscall that requests access to another process
		 * (and not a filesystem syscall to procfs).
		 */
		caller_uid = cred->uid;
		caller_gid = cred->gid;
	}
	tcred = __task_cred(task);
	if (uid_eq(caller_uid, tcred->euid) &&
	    uid_eq(caller_uid, tcred->suid) &&
	    uid_eq(caller_uid, tcred->uid)  &&
	    gid_eq(caller_gid, tcred->egid) &&
	    gid_eq(caller_gid, tcred->sgid) &&
	    gid_eq(caller_gid, tcred->gid))
		goto ok;
	if (ptrace_has_cap(tcred->user_ns, mode))
		goto ok;
	rcu_read_unlock();
	return -EPERM;
ok:
	rcu_read_unlock();
	mm = task->mm;
	if (mm &&
	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
	     !ptrace_has_cap(mm->user_ns, mode)))
	    return -EPERM;

	return security_ptrace_access_check(task, mode);
}

bool ptrace_may_access(struct task_struct *task, unsigned int mode)
{
	int err;
	task_lock(task);
	err = __ptrace_may_access(task, mode);
	task_unlock(task);
	return !err;
}

static int ptrace_attach(struct task_struct *task, long request,
			 unsigned long addr,
			 unsigned long flags)
{
	bool seize = (request == PTRACE_SEIZE);
	int retval;

	retval = -EIO;
	if (seize) {
		if (addr != 0)
			goto out;
		if (flags & ~(unsigned long)PTRACE_O_MASK)
			goto out;
		flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
	} else {
		flags = PT_PTRACED;
	}

	audit_ptrace(task);

	retval = -EPERM;
	if (unlikely(task->flags & PF_KTHREAD))
		goto out;
	if (same_thread_group(task, current))
		goto out;

	/*
	 * Protect exec's credential calculations against our interference;
	 * SUID, SGID and LSM creds get determined differently
	 * under ptrace.
	 */
	retval = -ERESTARTNOINTR;
	if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
		goto out;

	task_lock(task);
	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
	task_unlock(task);
	if (retval)
		goto unlock_creds;

	write_lock_irq(&tasklist_lock);
	retval = -EPERM;
	if (unlikely(task->exit_state))
		goto unlock_tasklist;
	if (task->ptrace)
		goto unlock_tasklist;

	if (seize)
		flags |= PT_SEIZED;
	task->ptrace = flags;

	ptrace_link(task, current);

	/* SEIZE doesn't trap tracee on attach */
	if (!seize)
		send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);

	spin_lock(&task->sighand->siglock);

	/*
	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
	 * TRAPPING, and kick it so that it transits to TRACED.  TRAPPING
	 * will be cleared if the child completes the transition or any
	 * event which clears the group stop states happens.  We'll wait
	 * for the transition to complete before returning from this
	 * function.
	 *
	 * This hides STOPPED -> RUNNING -> TRACED transition from the
	 * attaching thread but a different thread in the same group can
	 * still observe the transient RUNNING state.  IOW, if another
	 * thread's WNOHANG wait(2) on the stopped tracee races against
	 * ATTACH, the wait(2) may fail due to the transient RUNNING.
	 *
	 * The following task_is_stopped() test is safe as both transitions
	 * in and out of STOPPED are protected by siglock.
	 */
	if (task_is_stopped(task) &&
	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
		signal_wake_up_state(task, __TASK_STOPPED);

	spin_unlock(&task->sighand->siglock);

	retval = 0;
unlock_tasklist:
	write_unlock_irq(&tasklist_lock);
unlock_creds:
	mutex_unlock(&task->signal->cred_guard_mutex);
out:
	if (!retval) {
		/*
		 * We do not bother to change retval or clear JOBCTL_TRAPPING
		 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
		 * not return to user-mode, it will exit and clear this bit in
		 * __ptrace_unlink() if it wasn't already cleared by the tracee;
		 * and until then nobody can ptrace this task.
		 */
		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
		proc_ptrace_connector(task, PTRACE_ATTACH);
	}

	return retval;
}

/**
 * ptrace_traceme  --  helper for PTRACE_TRACEME
 *
 * Performs checks and sets PT_PTRACED.
 * Should be used by all ptrace implementations for PTRACE_TRACEME.
 */
static int ptrace_traceme(void)
{
	int ret = -EPERM;

	write_lock_irq(&tasklist_lock);
	/* Are we already being traced? */
	if (!current->ptrace) {
		ret = security_ptrace_traceme(current->parent);
		/*
		 * Check PF_EXITING to ensure ->real_parent has not passed
		 * exit_ptrace(). Otherwise we don't report the error but
		 * pretend ->real_parent untraces us right after return.
		 */
		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
			current->ptrace = PT_PTRACED;
			ptrace_link(current, current->real_parent);
		}
	}
	write_unlock_irq(&tasklist_lock);

	return ret;
}

/*
 * Called with irqs disabled, returns true if childs should reap themselves.
 */
static int ignoring_children(struct sighand_struct *sigh)
{
	int ret;
	spin_lock(&sigh->siglock);
	ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) ||
	      (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT);
	spin_unlock(&sigh->siglock);
	return ret;
}

/*
 * Called with tasklist_lock held for writing.
 * Unlink a traced task, and clean it up if it was a traced zombie.
 * Return true if it needs to be reaped with release_task().
 * (We can't call release_task() here because we already hold tasklist_lock.)
 *
 * If it's a zombie, our attachedness prevented normal parent notification
 * or self-reaping.  Do notification now if it would have happened earlier.
 * If it should reap itself, return true.
 *
 * If it's our own child, there is no notification to do. But if our normal
 * children self-reap, then this child was prevented by ptrace and we must
 * reap it now, in that case we must also wake up sub-threads sleeping in
 * do_wait().
 */
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
{
	bool dead;

	__ptrace_unlink(p);

	if (p->exit_state != EXIT_ZOMBIE)
		return false;

	dead = !thread_group_leader(p);

	if (!dead && thread_group_empty(p)) {
		if (!same_thread_group(p->real_parent, tracer))
			dead = do_notify_parent(p, p->exit_signal);
		else if (ignoring_children(tracer->sighand)) {
			__wake_up_parent(p, tracer);
			dead = true;
		}
	}
	/* Mark it as in the process of being reaped. */
	if (dead)
		p->exit_state = EXIT_DEAD;
	return dead;
}

static int ptrace_detach(struct task_struct *child, unsigned int data)
{
	if (!valid_signal(data))
		return -EIO;

	/* Architecture-specific hardware disable .. */
	ptrace_disable(child);

	write_lock_irq(&tasklist_lock);
	/*
	 * We rely on ptrace_freeze_traced(). It can't be killed and
	 * untraced by another thread, it can't be a zombie.
	 */
	WARN_ON(!child->ptrace || child->exit_state);
	/*
	 * tasklist_lock avoids the race with wait_task_stopped(), see
	 * the comment in ptrace_resume().
	 */
	child->exit_code = data;
	__ptrace_detach(current, child);
	write_unlock_irq(&tasklist_lock);

	proc_ptrace_connector(child, PTRACE_DETACH);

	return 0;
}

/*
 * Detach all tasks we were using ptrace on. Called with tasklist held
 * for writing.
 */
void exit_ptrace(struct task_struct *tracer, struct list_head *dead)
{
	struct task_struct *p, *n;

	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
		if (unlikely(p->ptrace & PT_EXITKILL))
			send_sig_info(SIGKILL, SEND_SIG_PRIV, p);

		if (__ptrace_detach(tracer, p))
			list_add(&p->ptrace_entry, dead);
	}
}

int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE);

		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		if (copy_to_user(dst, buf, retval))
			return -EFAULT;
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;
	}
	return copied;
}

int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		if (copy_from_user(buf, src, this_len))
			return -EFAULT;
		retval = ptrace_access_vm(tsk, dst, buf, this_len,
				FOLL_FORCE | FOLL_WRITE);
		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;
	}
	return copied;
}

static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
	unsigned flags;

	if (data & ~(unsigned long)PTRACE_O_MASK)
		return -EINVAL;

	if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
		if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
		    !IS_ENABLED(CONFIG_SECCOMP))
			return -EINVAL;

		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED ||
		    current->ptrace & PT_SUSPEND_SECCOMP)
			return -EPERM;
	}

	/* Avoid intermediate state when all opts are cleared */
	flags = child->ptrace;
	flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);
	flags |= (data << PT_OPT_FLAG_SHIFT);
	child->ptrace = flags;

	return 0;
}

static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info)
{
	unsigned long flags;
	int error = -ESRCH;

	if (lock_task_sighand(child, &flags)) {
		error = -EINVAL;
		if (likely(child->last_siginfo != NULL)) {
			copy_siginfo(info, child->last_siginfo);
			error = 0;
		}
		unlock_task_sighand(child, &flags);
	}
	return error;
}

static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info)
{
	unsigned long flags;
	int error = -ESRCH;

	if (lock_task_sighand(child, &flags)) {
		error = -EINVAL;
		if (likely(child->last_siginfo != NULL)) {
			copy_siginfo(child->last_siginfo, info);
			error = 0;
		}
		unlock_task_sighand(child, &flags);
	}
	return error;
}

static int ptrace_peek_siginfo(struct task_struct *child,
				unsigned long addr,
				unsigned long data)
{
	struct ptrace_peeksiginfo_args arg;
	struct sigpending *pending;
	struct sigqueue *q;
	int ret, i;

	ret = copy_from_user(&arg, (void __user *) addr,
				sizeof(struct ptrace_peeksiginfo_args));
	if (ret)
		return -EFAULT;

	if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED)
		return -EINVAL; /* unknown flags */

	if (arg.nr < 0)
		return -EINVAL;

	if (arg.flags & PTRACE_PEEKSIGINFO_SHARED)
		pending = &child->signal->shared_pending;
	else
		pending = &child->pending;

	for (i = 0; i < arg.nr; ) {
		kernel_siginfo_t info;
		s32 off = arg.off + i;

		spin_lock_irq(&child->sighand->siglock);
		list_for_each_entry(q, &pending->list, list) {
			if (!off--) {
				copy_siginfo(&info, &q->info);
				break;
			}
		}
		spin_unlock_irq(&child->sighand->siglock);

		if (off >= 0) /* beyond the end of the list */
			break;

#ifdef CONFIG_COMPAT
		if (unlikely(in_compat_syscall())) {
			compat_siginfo_t __user *uinfo = compat_ptr(data);

			if (copy_siginfo_to_user32(uinfo, &info)) {
				ret = -EFAULT;
				break;
			}

		} else
#endif
		{
			siginfo_t __user *uinfo = (siginfo_t __user *) data;

			if (copy_siginfo_to_user(uinfo, &info)) {
				ret = -EFAULT;
				break;
			}
		}

		data += sizeof(siginfo_t);
		i++;

		if (signal_pending(current))
			break;

		cond_resched();
	}

	if (i > 0)
		return i;

	return ret;
}

#ifdef PTRACE_SINGLESTEP
#define is_singlestep(request)		((request) == PTRACE_SINGLESTEP)
#else
#define is_singlestep(request)		0
#endif

#ifdef PTRACE_SINGLEBLOCK
#define is_singleblock(request)		((request) == PTRACE_SINGLEBLOCK)
#else
#define is_singleblock(request)		0
#endif

#ifdef PTRACE_SYSEMU
#define is_sysemu_singlestep(request)	((request) == PTRACE_SYSEMU_SINGLESTEP)
#else
#define is_sysemu_singlestep(request)	0
#endif

static int ptrace_resume(struct task_struct *child, long request,
			 unsigned long data)
{
	bool need_siglock;

	if (!valid_signal(data))
		return -EIO;

	if (request == PTRACE_SYSCALL)
		set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
	else
		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);

#ifdef TIF_SYSCALL_EMU
	if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
		set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
	else
		clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif

	if (is_singleblock(request)) {
		if (unlikely(!arch_has_block_step()))
			return -EIO;
		user_enable_block_step(child);
	} else if (is_singlestep(request) || is_sysemu_singlestep(request)) {
		if (unlikely(!arch_has_single_step()))
			return -EIO;
		user_enable_single_step(child);
	} else {
		user_disable_single_step(child);
	}

	/*
	 * Change ->exit_code and ->state under siglock to avoid the race
	 * with wait_task_stopped() in between; a non-zero ->exit_code will
	 * wrongly look like another report from tracee.
	 *
	 * Note that we need siglock even if ->exit_code == data and/or this
	 * status was not reported yet, the new status must not be cleared by
	 * wait_task_stopped() after resume.
	 *
	 * If data == 0 we do not care if wait_task_stopped() reports the old
	 * status and clears the code too; this can't race with the tracee, it
	 * takes siglock after resume.
	 */
	need_siglock = data && !thread_group_empty(current);
	if (need_siglock)
		spin_lock_irq(&child->sighand->siglock);
	child->exit_code = data;
	wake_up_state(child, __TASK_TRACED);
	if (need_siglock)
		spin_unlock_irq(&child->sighand->siglock);

	return 0;
}

#ifdef CONFIG_HAVE_ARCH_TRACEHOOK

static const struct user_regset *
find_regset(const struct user_regset_view *view, unsigned int type)
{
	const struct user_regset *regset;
	int n;

	for (n = 0; n < view->n; ++n) {
		regset = view->regsets + n;
		if (regset->core_note_type == type)
			return regset;
	}

	return NULL;
}

static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
			 struct iovec *kiov)
{
	const struct user_regset_view *view = task_user_regset_view(task);
	const struct user_regset *regset = find_regset(view, type);
	int regset_no;

	if (!regset || (kiov->iov_len % regset->size) != 0)
		return -EINVAL;

	regset_no = regset - view->regsets;
	kiov->iov_len = min(kiov->iov_len,
			    (__kernel_size_t) (regset->n * regset->size));

	if (req == PTRACE_GETREGSET)
		return copy_regset_to_user(task, view, regset_no, 0,
					   kiov->iov_len, kiov->iov_base);
	else
		return copy_regset_from_user(task, view, regset_no, 0,
					     kiov->iov_len, kiov->iov_base);
}

/*
 * This is declared in linux/regset.h and defined in machine-dependent
 * code.  We put the export here, near the primary machine-neutral use,
 * to ensure no machine forgets it.
 */
EXPORT_SYMBOL_GPL(task_user_regset_view);
#endif

int ptrace_request(struct task_struct *child, long request,
		   unsigned long addr, unsigned long data)
{
	bool seized = child->ptrace & PT_SEIZED;
	int ret = -EIO;
	kernel_siginfo_t siginfo, *si;
	void __user *datavp = (void __user *) data;
	unsigned long __user *datalp = datavp;
	unsigned long flags;

	switch (request) {
	case PTRACE_PEEKTEXT:
	case PTRACE_PEEKDATA:
		return generic_ptrace_peekdata(child, addr, data);
	case PTRACE_POKETEXT:
	case PTRACE_POKEDATA:
		return generic_ptrace_pokedata(child, addr, data);

#ifdef PTRACE_OLDSETOPTIONS
	case PTRACE_OLDSETOPTIONS:
#endif
	case PTRACE_SETOPTIONS:
		ret = ptrace_setoptions(child, data);
		break;
	case PTRACE_GETEVENTMSG:
		ret = put_user(child->ptrace_message, datalp);
		break;

	case PTRACE_PEEKSIGINFO:
		ret = ptrace_peek_siginfo(child, addr, data);
		break;

	case PTRACE_GETSIGINFO:
		ret = ptrace_getsiginfo(child, &siginfo);
		if (!ret)
			ret = copy_siginfo_to_user(datavp, &siginfo);
		break;

	case PTRACE_SETSIGINFO:
		ret = copy_siginfo_from_user(&siginfo, datavp);
		if (!ret)
			ret = ptrace_setsiginfo(child, &siginfo);
		break;

	case PTRACE_GETSIGMASK: {
		sigset_t *mask;

		if (addr != sizeof(sigset_t)) {
			ret = -EINVAL;
			break;
		}

		if (test_tsk_restore_sigmask(child))
			mask = &child->saved_sigmask;
		else
			mask = &child->blocked;

		if (copy_to_user(datavp, mask, sizeof(sigset_t)))
			ret = -EFAULT;
		else
			ret = 0;

		break;
	}

	case PTRACE_SETSIGMASK: {
		sigset_t new_set;

		if (addr != sizeof(sigset_t)) {
			ret = -EINVAL;
			break;
		}

		if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) {
			ret = -EFAULT;
			break;
		}

		sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));

		/*
		 * Every thread does recalc_sigpending() after resume, so
		 * retarget_shared_pending() and recalc_sigpending() are not
		 * called here.
		 */
		spin_lock_irq(&child->sighand->siglock);
		child->blocked = new_set;
		spin_unlock_irq(&child->sighand->siglock);

		clear_tsk_restore_sigmask(child);

		ret = 0;
		break;
	}

	case PTRACE_INTERRUPT:
		/*
		 * Stop tracee without any side-effect on signal or job
		 * control.  At least one trap is guaranteed to happen
		 * after this request.  If @child is already trapped, the
		 * current trap is not disturbed and another trap will
		 * happen after the current trap is ended with PTRACE_CONT.
		 *
		 * The actual trap might not be PTRACE_EVENT_STOP trap but
		 * the pending condition is cleared regardless.
		 */
		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
			break;

		/*
		 * INTERRUPT doesn't disturb existing trap sans one
		 * exception.  If ptracer issued LISTEN for the current
		 * STOP, this INTERRUPT should clear LISTEN and re-trap
		 * tracee into STOP.
		 */
		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
			ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);

		unlock_task_sighand(child, &flags);
		ret = 0;
		break;

	case PTRACE_LISTEN:
		/*
		 * Listen for events.  Tracee must be in STOP.  It's not
		 * resumed per-se but is not considered to be in TRACED by
		 * wait(2) or ptrace(2).  If an async event (e.g. group
		 * stop state change) happens, tracee will enter STOP trap
		 * again.  Alternatively, ptracer can issue INTERRUPT to
		 * finish listening and re-trap tracee into STOP.
		 */
		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
			break;

		si = child->last_siginfo;
		if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) {
			child->jobctl |= JOBCTL_LISTENING;
			/*
			 * If NOTIFY is set, it means event happened between
			 * start of this trap and now.  Trigger re-trap.
			 */
			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
				ptrace_signal_wake_up(child, true);
			ret = 0;
		}
		unlock_task_sighand(child, &flags);
		break;

	case PTRACE_DETACH:	 /* detach a process that was attached. */
		ret = ptrace_detach(child, data);
		break;

#ifdef CONFIG_BINFMT_ELF_FDPIC
	case PTRACE_GETFDPIC: {
		struct mm_struct *mm = get_task_mm(child);
		unsigned long tmp = 0;

		ret = -ESRCH;
		if (!mm)
			break;

		switch (addr) {
		case PTRACE_GETFDPIC_EXEC:
			tmp = mm->context.exec_fdpic_loadmap;
			break;
		case PTRACE_GETFDPIC_INTERP:
			tmp = mm->context.interp_fdpic_loadmap;
			break;
		default:
			break;
		}
		mmput(mm);

		ret = put_user(tmp, datalp);
		break;
	}
#endif

#ifdef PTRACE_SINGLESTEP
	case PTRACE_SINGLESTEP:
#endif
#ifdef PTRACE_SINGLEBLOCK
	case PTRACE_SINGLEBLOCK:
#endif
#ifdef PTRACE_SYSEMU
	case PTRACE_SYSEMU:
	case PTRACE_SYSEMU_SINGLESTEP:
#endif
	case PTRACE_SYSCALL:
	case PTRACE_CONT:
		return ptrace_resume(child, request, data);

	case PTRACE_KILL:
		if (child->exit_state)	/* already dead */
			return 0;
		return ptrace_resume(child, request, SIGKILL);

#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
	case PTRACE_GETREGSET:
	case PTRACE_SETREGSET: {
		struct iovec kiov;
		struct iovec __user *uiov = datavp;

		if (!access_ok(uiov, sizeof(*uiov)))
			return -EFAULT;

		if (__get_user(kiov.iov_base, &uiov->iov_base) ||
		    __get_user(kiov.iov_len, &uiov->iov_len))
			return -EFAULT;

		ret = ptrace_regset(child, request, addr, &kiov);
		if (!ret)
			ret = __put_user(kiov.iov_len, &uiov->iov_len);
		break;
	}
#endif

	case PTRACE_SECCOMP_GET_FILTER:
		ret = seccomp_get_filter(child, addr, datavp);
		break;

	case PTRACE_SECCOMP_GET_METADATA:
		ret = seccomp_get_metadata(child, addr, datavp);
		break;

	default:
		break;
	}

	return ret;
}

#ifndef arch_ptrace_attach
#define arch_ptrace_attach(child)	do { } while (0)
#endif

SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
		unsigned long, data)
{
	struct task_struct *child;
	long ret;

	if (request == PTRACE_TRACEME) {
		ret = ptrace_traceme();
		if (!ret)
			arch_ptrace_attach(current);
		goto out;
	}

	child = find_get_task_by_vpid(pid);
	if (!child) {
		ret = -ESRCH;
		goto out;
	}

	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
		ret = ptrace_attach(child, request, addr, data);
		/*
		 * Some architectures need to do book-keeping after
		 * a ptrace attach.
		 */
		if (!ret)
			arch_ptrace_attach(child);
		goto out_put_task_struct;
	}

	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
				  request == PTRACE_INTERRUPT);
	if (ret < 0)
		goto out_put_task_struct;

	ret = arch_ptrace(child, request, addr, data);
	if (ret || request != PTRACE_DETACH)
		ptrace_unfreeze_traced(child);

 out_put_task_struct:
	put_task_struct(child);
 out:
	return ret;
}

int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
			    unsigned long data)
{
	unsigned long tmp;
	int copied;

	copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE);
	if (copied != sizeof(tmp))
		return -EIO;
	return put_user(tmp, (unsigned long __user *)data);
}

int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
			    unsigned long data)
{
	int copied;

	copied = ptrace_access_vm(tsk, addr, &data, sizeof(data),
			FOLL_FORCE | FOLL_WRITE);
	return (copied == sizeof(data)) ? 0 : -EIO;
}

#if defined CONFIG_COMPAT

int compat_ptrace_request(struct task_struct *child, compat_long_t request,
			  compat_ulong_t addr, compat_ulong_t data)
{
	compat_ulong_t __user *datap = compat_ptr(data);
	compat_ulong_t word;
	kernel_siginfo_t siginfo;
	int ret;

	switch (request) {
	case PTRACE_PEEKTEXT:
	case PTRACE_PEEKDATA:
		ret = ptrace_access_vm(child, addr, &word, sizeof(word),
				FOLL_FORCE);
		if (ret != sizeof(word))
			ret = -EIO;
		else
			ret = put_user(word, datap);
		break;

	case PTRACE_POKETEXT:
	case PTRACE_POKEDATA:
		ret = ptrace_access_vm(child, addr, &data, sizeof(data),
				FOLL_FORCE | FOLL_WRITE);
		ret = (ret != sizeof(data) ? -EIO : 0);
		break;

	case PTRACE_GETEVENTMSG:
		ret = put_user((compat_ulong_t) child->ptrace_message, datap);
		break;

	case PTRACE_GETSIGINFO:
		ret = ptrace_getsiginfo(child, &siginfo);
		if (!ret)
			ret = copy_siginfo_to_user32(
				(struct compat_siginfo __user *) datap,
				&siginfo);
		break;

	case PTRACE_SETSIGINFO:
		ret = copy_siginfo_from_user32(
			&siginfo, (struct compat_siginfo __user *) datap);
		if (!ret)
			ret = ptrace_setsiginfo(child, &siginfo);
		break;
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
	case PTRACE_GETREGSET:
	case PTRACE_SETREGSET:
	{
		struct iovec kiov;
		struct compat_iovec __user *uiov =
			(struct compat_iovec __user *) datap;
		compat_uptr_t ptr;
		compat_size_t len;

		if (!access_ok(uiov, sizeof(*uiov)))
			return -EFAULT;

		if (__get_user(ptr, &uiov->iov_base) ||
		    __get_user(len, &uiov->iov_len))
			return -EFAULT;

		kiov.iov_base = compat_ptr(ptr);
		kiov.iov_len = len;

		ret = ptrace_regset(child, request, addr, &kiov);
		if (!ret)
			ret = __put_user(kiov.iov_len, &uiov->iov_len);
		break;
	}
#endif

	default:
		ret = ptrace_request(child, request, addr, data);
	}

	return ret;
}

COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
		       compat_long_t, addr, compat_long_t, data)
{
	struct task_struct *child;
	long ret;

	if (request == PTRACE_TRACEME) {
		ret = ptrace_traceme();
		goto out;
	}

	child = find_get_task_by_vpid(pid);
	if (!child) {
		ret = -ESRCH;
		goto out;
	}

	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
		ret = ptrace_attach(child, request, addr, data);
		/*
		 * Some architectures need to do book-keeping after
		 * a ptrace attach.
		 */
		if (!ret)
			arch_ptrace_attach(child);
		goto out_put_task_struct;
	}

	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
				  request == PTRACE_INTERRUPT);
	if (!ret) {
		ret = compat_arch_ptrace(child, request, addr, data);
		if (ret || request != PTRACE_DETACH)
			ptrace_unfreeze_traced(child);
	}

 out_put_task_struct:
	put_task_struct(child);
 out:
	return ret;
}
#endif	/* CONFIG_COMPAT */