/
syscall.c
1286 lines (1123 loc) · 30.9 KB
/
syscall.c
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
/*
* Copyright (c) 1991, 1992 Paul Kranenburg <pk@cs.few.eur.nl>
* Copyright (c) 1993 Branko Lankester <branko@hacktic.nl>
* Copyright (c) 1993, 1994, 1995, 1996 Rick Sladkey <jrs@world.std.com>
* Copyright (c) 1996-1999 Wichert Akkerman <wichert@cistron.nl>
* Copyright (c) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Linux for s390 port by D.J. Barrow
* <barrow_dj@mail.yahoo.com,djbarrow@de.ibm.com>
* Copyright (c) 1999-2018 The strace developers.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "defs.h"
#include "mmap_notify.h"
#include "native_defs.h"
#include "ptrace.h"
#include "nsig.h"
#include "number_set.h"
#include "delay.h"
#include "retval.h"
#include <limits.h>
/* for struct iovec */
#include <sys/uio.h>
/* for __X32_SYSCALL_BIT */
#include <asm/unistd.h>
#include "regs.h"
#if defined(SPARC64)
# undef PTRACE_GETREGS
# define PTRACE_GETREGS PTRACE_GETREGS64
# undef PTRACE_SETREGS
# define PTRACE_SETREGS PTRACE_SETREGS64
#endif
#include "syscall.h"
#include "xstring.h"
/* Define these shorthand notations to simplify the syscallent files. */
#include "sysent_shorthand_defs.h"
#define SEN(syscall_name) SEN_ ## syscall_name, SYS_FUNC_NAME(sys_ ## syscall_name)
const struct_sysent sysent0[] = {
#include "syscallent.h"
};
#if SUPPORTED_PERSONALITIES > 1
# include PERSONALITY1_INCLUDE_FUNCS
static const struct_sysent sysent1[] = {
# include "syscallent1.h"
};
#endif
#if SUPPORTED_PERSONALITIES > 2
# include PERSONALITY2_INCLUDE_FUNCS
static const struct_sysent sysent2[] = {
# include "syscallent2.h"
};
#endif
/* Now undef them since short defines cause wicked namespace pollution. */
#include "sysent_shorthand_undefs.h"
const char *const errnoent[] = {
#include "errnoent.h"
};
const char *const signalent[] = {
#include "signalent.h"
};
/*
* `ioctlent[012].h' files are automatically generated by the auxiliary
* program `ioctlsort', such that the list is sorted by the `code' field.
* This has the side-effect of resolving the _IO.. macros into
* plain integers, eliminating the need to include here everything
* in "/usr/include".
*/
const struct_ioctlent ioctlent0[] = {
#include "ioctlent0.h"
};
#if SUPPORTED_PERSONALITIES > 1
static const struct_ioctlent ioctlent1[] = {
# include "ioctlent1.h"
};
# include PERSONALITY0_INCLUDE_PRINTERS_DECLS
static const struct_printers printers0 = {
# include PERSONALITY0_INCLUDE_PRINTERS_DEFS
};
# include PERSONALITY1_INCLUDE_PRINTERS_DECLS
static const struct_printers printers1 = {
# include PERSONALITY1_INCLUDE_PRINTERS_DEFS
};
#endif
#if SUPPORTED_PERSONALITIES > 2
static const struct_ioctlent ioctlent2[] = {
# include "ioctlent2.h"
};
# include PERSONALITY2_INCLUDE_PRINTERS_DECLS
static const struct_printers printers2 = {
# include PERSONALITY2_INCLUDE_PRINTERS_DEFS
};
#endif
enum {
nsyscalls0 = ARRAY_SIZE(sysent0)
#if SUPPORTED_PERSONALITIES > 1
, nsyscalls1 = ARRAY_SIZE(sysent1)
# if SUPPORTED_PERSONALITIES > 2
, nsyscalls2 = ARRAY_SIZE(sysent2)
# endif
#endif
};
enum {
nioctlents0 = ARRAY_SIZE(ioctlent0)
#if SUPPORTED_PERSONALITIES > 1
, nioctlents1 = ARRAY_SIZE(ioctlent1)
# if SUPPORTED_PERSONALITIES > 2
, nioctlents2 = ARRAY_SIZE(ioctlent2)
# endif
#endif
};
#if SUPPORTED_PERSONALITIES > 1
const struct_sysent *sysent = sysent0;
const struct_ioctlent *ioctlent = ioctlent0;
const struct_printers *printers = &printers0;
#endif
const unsigned int nerrnos = ARRAY_SIZE(errnoent);
const unsigned int nsignals = ARRAY_SIZE(signalent);
unsigned nsyscalls = nsyscalls0;
unsigned nioctlents = nioctlents0;
const unsigned int nsyscall_vec[SUPPORTED_PERSONALITIES] = {
nsyscalls0,
#if SUPPORTED_PERSONALITIES > 1
nsyscalls1,
#endif
#if SUPPORTED_PERSONALITIES > 2
nsyscalls2,
#endif
};
const struct_sysent *const sysent_vec[SUPPORTED_PERSONALITIES] = {
sysent0,
#if SUPPORTED_PERSONALITIES > 1
sysent1,
#endif
#if SUPPORTED_PERSONALITIES > 2
sysent2,
#endif
};
const char *const personality_names[] =
# if defined X86_64
{"64 bit", "32 bit", "x32"}
# elif defined X32
{"x32", "32 bit"}
# elif SUPPORTED_PERSONALITIES == 2
{"64 bit", "32 bit"}
# else
{STRINGIFY_VAL(__WORDSIZE) " bit"}
# endif
;
const char *const personality_designators[] =
# if defined X86_64
{ "64", "32", "x32" }
# elif defined X32
{ "x32", "32" }
# elif SUPPORTED_PERSONALITIES == 2
{ "64", "32" }
# else
{ STRINGIFY_VAL(__WORDSIZE) }
# endif
;
#if SUPPORTED_PERSONALITIES > 1
unsigned current_personality;
# ifndef current_wordsize
unsigned current_wordsize = PERSONALITY0_WORDSIZE;
static const int personality_wordsize[SUPPORTED_PERSONALITIES] = {
PERSONALITY0_WORDSIZE,
PERSONALITY1_WORDSIZE,
# if SUPPORTED_PERSONALITIES > 2
PERSONALITY2_WORDSIZE,
# endif
};
# endif
# ifndef current_klongsize
unsigned current_klongsize = PERSONALITY0_KLONGSIZE;
static const int personality_klongsize[SUPPORTED_PERSONALITIES] = {
PERSONALITY0_KLONGSIZE,
PERSONALITY1_KLONGSIZE,
# if SUPPORTED_PERSONALITIES > 2
PERSONALITY2_KLONGSIZE,
# endif
};
# endif
void
set_personality(unsigned int personality)
{
if (personality == current_personality)
return;
if (personality >= SUPPORTED_PERSONALITIES)
error_msg_and_die("Requested switch to unsupported personality "
"%u", personality);
nsyscalls = nsyscall_vec[personality];
sysent = sysent_vec[personality];
switch (personality) {
case 0:
ioctlent = ioctlent0;
nioctlents = nioctlents0;
printers = &printers0;
break;
case 1:
ioctlent = ioctlent1;
nioctlents = nioctlents1;
printers = &printers1;
break;
# if SUPPORTED_PERSONALITIES > 2
case 2:
ioctlent = ioctlent2;
nioctlents = nioctlents2;
printers = &printers2;
break;
# endif
}
current_personality = personality;
# ifndef current_wordsize
current_wordsize = personality_wordsize[personality];
# endif
# ifndef current_klongsize
current_klongsize = personality_klongsize[personality];
# endif
}
static void
update_personality(struct tcb *tcp, unsigned int personality)
{
static bool need_mpers_warning[] =
{ false, !HAVE_PERSONALITY_1_MPERS, !HAVE_PERSONALITY_2_MPERS };
set_personality(personality);
if (personality == tcp->currpers)
return;
tcp->currpers = personality;
if (!qflag) {
error_msg("[ Process PID=%d runs in %s mode. ]",
tcp->pid, personality_names[personality]);
}
if (need_mpers_warning[personality]) {
error_msg("WARNING: Proper structure decoding for this "
"personality is not supported, please consider "
"building strace with mpers support enabled.");
need_mpers_warning[personality] = false;
}
}
#endif
#ifdef SYS_socket_subcall
static void
decode_socket_subcall(struct tcb *tcp)
{
const int call = tcp->u_arg[0];
if (call < 1 || call >= SYS_socket_nsubcalls)
return;
const kernel_ulong_t scno = SYS_socket_subcall + call;
const unsigned int nargs = sysent[scno].nargs;
uint64_t buf[nargs];
if (umoven(tcp, tcp->u_arg[1], nargs * current_wordsize, buf) < 0)
return;
tcp->scno = scno;
tcp->qual_flg = qual_flags(scno);
tcp->s_ent = &sysent[scno];
unsigned int i;
for (i = 0; i < nargs; ++i)
tcp->u_arg[i] = (sizeof(uint32_t) == current_wordsize)
? ((uint32_t *) (void *) buf)[i] : buf[i];
}
#endif /* SYS_socket_subcall */
#ifdef SYS_ipc_subcall
static void
decode_ipc_subcall(struct tcb *tcp)
{
unsigned int call = tcp->u_arg[0];
const unsigned int version = call >> 16;
if (version) {
# if defined S390 || defined S390X
return;
# else
# ifdef SPARC64
if (current_wordsize == 8)
return;
# endif
set_tcb_priv_ulong(tcp, version);
call &= 0xffff;
# endif
}
switch (call) {
case 1: case 2: case 3: case 4:
case 11: case 12: case 13: case 14:
case 21: case 22: case 23: case 24:
break;
default:
return;
}
tcp->scno = SYS_ipc_subcall + call;
tcp->qual_flg = qual_flags(tcp->scno);
tcp->s_ent = &sysent[tcp->scno];
const unsigned int n = tcp->s_ent->nargs;
unsigned int i;
for (i = 0; i < n; i++)
tcp->u_arg[i] = tcp->u_arg[i + 1];
}
#endif /* SYS_ipc_subcall */
#ifdef SYS_syscall_subcall
static void
decode_syscall_subcall(struct tcb *tcp)
{
if (!scno_is_valid(tcp->u_arg[0]))
return;
tcp->scno = tcp->u_arg[0];
tcp->qual_flg = qual_flags(tcp->scno);
tcp->s_ent = &sysent[tcp->scno];
memmove(&tcp->u_arg[0], &tcp->u_arg[1],
sizeof(tcp->u_arg) - sizeof(tcp->u_arg[0]));
# ifdef LINUX_MIPSO32
/*
* Fetching the last arg of 7-arg syscalls (fadvise64_64
* and sync_file_range) requires additional code,
* see linux/mips/get_syscall_args.c
*/
if (tcp->s_ent->nargs == MAX_ARGS) {
if (umoven(tcp,
mips_REG_SP + MAX_ARGS * sizeof(tcp->u_arg[0]),
sizeof(tcp->u_arg[0]),
&tcp->u_arg[MAX_ARGS - 1]) < 0)
tcp->u_arg[MAX_ARGS - 1] = 0;
}
# endif /* LINUX_MIPSO32 */
}
#endif /* SYS_syscall_subcall */
static void
dumpio(struct tcb *tcp)
{
int fd = tcp->u_arg[0];
if (fd < 0)
return;
if (is_number_in_set(fd, write_set)) {
switch (tcp->s_ent->sen) {
case SEN_write:
case SEN_pwrite:
case SEN_send:
case SEN_sendto:
case SEN_mq_timedsend:
dumpstr(tcp, tcp->u_arg[1], tcp->u_arg[2]);
break;
case SEN_writev:
case SEN_pwritev:
case SEN_pwritev2:
case SEN_vmsplice:
dumpiov_upto(tcp, tcp->u_arg[2], tcp->u_arg[1], -1);
break;
case SEN_sendmsg:
dumpiov_in_msghdr(tcp, tcp->u_arg[1], -1);
break;
case SEN_sendmmsg:
dumpiov_in_mmsghdr(tcp, tcp->u_arg[1]);
break;
}
}
if (syserror(tcp))
return;
if (is_number_in_set(fd, read_set)) {
switch (tcp->s_ent->sen) {
case SEN_read:
case SEN_pread:
case SEN_recv:
case SEN_recvfrom:
case SEN_mq_timedreceive:
dumpstr(tcp, tcp->u_arg[1], tcp->u_rval);
return;
case SEN_readv:
case SEN_preadv:
case SEN_preadv2:
dumpiov_upto(tcp, tcp->u_arg[2], tcp->u_arg[1],
tcp->u_rval);
return;
case SEN_recvmsg:
dumpiov_in_msghdr(tcp, tcp->u_arg[1], tcp->u_rval);
return;
case SEN_recvmmsg:
dumpiov_in_mmsghdr(tcp, tcp->u_arg[1]);
return;
}
}
}
const char *
err_name(unsigned long err)
{
if ((err < nerrnos) && errnoent[err])
return errnoent[err];
return NULL;
}
static void
print_err_ret(kernel_ulong_t ret, unsigned long u_error)
{
const char *u_error_str = err_name(u_error);
if (u_error_str)
tprintf("= %" PRI_kld " %s (%s)",
ret, u_error_str, strerror(u_error));
else
tprintf("= %" PRI_kld " (errno %lu)", ret, u_error);
}
static long get_regs(struct tcb *);
static int get_syscall_args(struct tcb *);
static int get_syscall_result(struct tcb *);
static int arch_get_scno(struct tcb *tcp);
static int arch_set_scno(struct tcb *, kernel_ulong_t);
static void get_error(struct tcb *, const bool);
static int arch_set_error(struct tcb *);
static int arch_set_success(struct tcb *);
struct inject_opts *inject_vec[SUPPORTED_PERSONALITIES];
static struct inject_opts *
tcb_inject_opts(struct tcb *tcp)
{
return (scno_in_range(tcp->scno) && tcp->inject_vec[current_personality])
? &tcp->inject_vec[current_personality][tcp->scno] : NULL;
}
static long
tamper_with_syscall_entering(struct tcb *tcp, unsigned int *signo)
{
if (!tcp->inject_vec[current_personality]) {
tcp->inject_vec[current_personality] =
xcalloc(nsyscalls, sizeof(**inject_vec));
memcpy(tcp->inject_vec[current_personality],
inject_vec[current_personality],
nsyscalls * sizeof(**inject_vec));
}
struct inject_opts *opts = tcb_inject_opts(tcp);
if (!opts || opts->first == 0)
return 0;
--opts->first;
if (opts->first != 0)
return 0;
opts->first = opts->step;
if (!recovering(tcp)) {
if (opts->data.flags & INJECT_F_SIGNAL)
*signo = opts->data.signo;
if (opts->data.flags & (INJECT_F_ERROR | INJECT_F_RETVAL)) {
kernel_long_t scno =
(opts->data.flags & INJECT_F_SYSCALL)
? (kernel_long_t) shuffle_scno(opts->data.scno)
: -1;
if (!arch_set_scno(tcp, scno)) {
tcp->flags |= TCB_TAMPERED;
if (scno != -1)
tcp->flags |= TCB_TAMPERED_NO_FAIL;
}
}
if (opts->data.flags & INJECT_F_DELAY_ENTER)
delay_tcb(tcp, opts->data.delay_idx, true);
if (opts->data.flags & INJECT_F_DELAY_EXIT)
tcp->flags |= TCB_INJECT_DELAY_EXIT;
}
return 0;
}
static long
tamper_with_syscall_exiting(struct tcb *tcp)
{
struct inject_opts *opts = tcb_inject_opts(tcp);
if (!opts)
return 0;
if (inject_delay_exit(tcp))
delay_tcb(tcp, opts->data.delay_idx, false);
if (!syscall_tampered(tcp))
return 0;
if (!syserror(tcp) ^ !!syscall_tampered_nofail(tcp)) {
error_msg("Failed to tamper with process %d: unexpectedly got"
" %serror (return value %#" PRI_klx ", error %lu)",
tcp->pid, syscall_tampered_nofail(tcp) ? "" : "no ",
tcp->u_rval, tcp->u_error);
return 1;
}
bool update_tcb = false;
if (opts->data.flags & INJECT_F_RETVAL) {
kernel_long_t inject_rval =
retval_get(opts->data.rval_idx);
kernel_long_t u_rval = tcp->u_rval;
tcp->u_rval = inject_rval;
if (arch_set_success(tcp)) {
tcp->u_rval = u_rval;
} else {
update_tcb = true;
tcp->u_error = 0;
}
} else {
unsigned long new_error = retval_get(opts->data.rval_idx);
if (new_error != tcp->u_error && new_error <= MAX_ERRNO_VALUE) {
unsigned long u_error = tcp->u_error;
tcp->u_error = new_error;
if (arch_set_error(tcp)) {
tcp->u_error = u_error;
} else {
update_tcb = true;
}
}
}
if (update_tcb) {
tcp->u_error = 0;
get_error(tcp, !(tcp->s_ent->sys_flags & SYSCALL_NEVER_FAILS));
}
return 0;
}
/*
* Returns:
* 0: "ignore this ptrace stop", bail out silently.
* 1: ok, decoded; call
* syscall_entering_finish(tcp, syscall_entering_trace(tcp, ...)).
* other: error; call syscall_entering_finish(tcp, res), where res is the value
* returned.
*/
int
syscall_entering_decode(struct tcb *tcp)
{
int res = get_scno(tcp);
if (res == 0)
return res;
int scno_good = res;
if (res != 1 || (res = get_syscall_args(tcp)) != 1) {
printleader(tcp);
tprintf("%s(", scno_good == 1 ? tcp->s_ent->sys_name : "????");
/*
* " <unavailable>" will be added later by the code which
* detects ptrace errors.
*/
return res;
}
#if defined SYS_ipc_subcall \
|| defined SYS_socket_subcall \
|| defined SYS_syscall_subcall
for (;;) {
switch (tcp->s_ent->sen) {
# ifdef SYS_ipc_subcall
case SEN_ipc:
decode_ipc_subcall(tcp);
break;
# endif
# ifdef SYS_socket_subcall
case SEN_socketcall:
decode_socket_subcall(tcp);
break;
# endif
# ifdef SYS_syscall_subcall
case SEN_syscall:
decode_syscall_subcall(tcp);
if (tcp->s_ent->sen != SEN_syscall)
continue;
break;
# endif
}
break;
}
#endif
return 1;
}
int
syscall_entering_trace(struct tcb *tcp, unsigned int *sig)
{
/* Restrain from fault injection while the trace executes strace code. */
if (hide_log(tcp)) {
tcp->qual_flg &= ~QUAL_INJECT;
}
switch (tcp->s_ent->sen) {
case SEN_execve:
case SEN_execveat:
#if defined SPARC || defined SPARC64
case SEN_execv:
#endif
tcp->flags &= ~TCB_HIDE_LOG;
break;
}
if (!traced(tcp) || (tracing_paths && !pathtrace_match(tcp))) {
tcp->flags |= TCB_FILTERED;
return 0;
}
tcp->flags &= ~TCB_FILTERED;
if (hide_log(tcp)) {
return 0;
}
if (inject(tcp))
tamper_with_syscall_entering(tcp, sig);
if (cflag == CFLAG_ONLY_STATS) {
return 0;
}
#ifdef ENABLE_STACKTRACE
if (stack_trace_enabled) {
if (tcp->s_ent->sys_flags & STACKTRACE_CAPTURE_ON_ENTER)
unwind_tcb_capture(tcp);
}
#endif
printleader(tcp);
tprintf("%s(", tcp->s_ent->sys_name);
int res = raw(tcp) ? printargs(tcp) : tcp->s_ent->sys_func(tcp);
fflush(tcp->outf);
return res;
}
void
syscall_entering_finish(struct tcb *tcp, int res)
{
tcp->flags |= TCB_INSYSCALL;
tcp->sys_func_rval = res;
/* Measure the entrance time as late as possible to avoid errors. */
if ((Tflag || cflag) && !filtered(tcp))
clock_gettime(CLOCK_MONOTONIC, &tcp->etime);
}
/* Returns:
* 0: "bail out".
* 1: ok.
* -1: error in one of ptrace ops.
*
* If not 0, call syscall_exiting_trace(tcp, res), where res is the return
* value. Anyway, call syscall_exiting_finish(tcp) then.
*/
int
syscall_exiting_decode(struct tcb *tcp, struct timespec *pts)
{
/* Measure the exit time as early as possible to avoid errors. */
if ((Tflag || cflag) && !(filtered(tcp) || hide_log(tcp)))
clock_gettime(CLOCK_MONOTONIC, pts);
if (tcp->s_ent->sys_flags & MEMORY_MAPPING_CHANGE)
mmap_notify_report(tcp);
if (filtered(tcp) || hide_log(tcp))
return 0;
#if SUPPORTED_PERSONALITIES > 1
update_personality(tcp, tcp->currpers);
#endif
return get_syscall_result(tcp);
}
int
syscall_exiting_trace(struct tcb *tcp, struct timespec *ts, int res)
{
if (syscall_tampered(tcp) || inject_delay_exit(tcp))
tamper_with_syscall_exiting(tcp);
if (cflag) {
count_syscall(tcp, ts);
if (cflag == CFLAG_ONLY_STATS) {
return 0;
}
}
/* If not in -ff mode, and printing_tcp != tcp,
* then the log currently does not end with output
* of _our syscall entry_, but with something else.
* We need to say which syscall's return is this.
*
* Forced reprinting via TCB_REPRINT is used only by
* "strace -ff -oLOG test/threaded_execve" corner case.
* It's the only case when -ff mode needs reprinting.
*/
if ((followfork < 2 && printing_tcp != tcp) || (tcp->flags & TCB_REPRINT)) {
tcp->flags &= ~TCB_REPRINT;
printleader(tcp);
tprintf("<... %s resumed> ", tcp->s_ent->sys_name);
}
printing_tcp = tcp;
tcp->s_prev_ent = NULL;
if (res != 1) {
/* There was error in one of prior ptrace ops */
tprints(") ");
tabto();
tprints("= ? <unavailable>\n");
line_ended();
return res;
}
tcp->s_prev_ent = tcp->s_ent;
int sys_res = 0;
if (raw(tcp)) {
/* sys_res = printargs(tcp); - but it's nop on sysexit */
} else {
/* FIXME: not_failing_only (IOW, option -z) is broken:
* failure of syscall is known only after syscall return.
* Thus we end up with something like this on, say, ENOENT:
* open("does_not_exist", O_RDONLY <unfinished ...>
* {next syscall decode}
* whereas the intended result is that open(...) line
* is not shown at all.
*/
if (not_failing_only && tcp->u_error)
return 0; /* ignore failed syscalls */
if (tcp->sys_func_rval & RVAL_DECODED)
sys_res = tcp->sys_func_rval;
else
sys_res = tcp->s_ent->sys_func(tcp);
}
tprints(") ");
tabto();
if (raw(tcp)) {
if (tcp->u_error)
print_err_ret(tcp->u_rval, tcp->u_error);
else
tprintf("= %#" PRI_klx, tcp->u_rval);
if (syscall_tampered(tcp))
tprints(" (INJECTED)");
} else if (!(sys_res & RVAL_NONE) && tcp->u_error) {
switch (tcp->u_error) {
/* Blocked signals do not interrupt any syscalls.
* In this case syscalls don't return ERESTARTfoo codes.
*
* Deadly signals set to SIG_DFL interrupt syscalls
* and kill the process regardless of which of the codes below
* is returned by the interrupted syscall.
* In some cases, kernel forces a kernel-generated deadly
* signal to be unblocked and set to SIG_DFL (and thus cause
* death) if it is blocked or SIG_IGNed: for example, SIGSEGV
* or SIGILL. (The alternative is to leave process spinning
* forever on the faulty instruction - not useful).
*
* SIG_IGNed signals and non-deadly signals set to SIG_DFL
* (for example, SIGCHLD, SIGWINCH) interrupt syscalls,
* but kernel will always restart them.
*/
case ERESTARTSYS:
/* Most common type of signal-interrupted syscall exit code.
* The system call will be restarted with the same arguments
* if SA_RESTART is set; otherwise, it will fail with EINTR.
*/
tprints("= ? ERESTARTSYS (To be restarted if SA_RESTART is set)");
break;
case ERESTARTNOINTR:
/* Rare. For example, fork() returns this if interrupted.
* SA_RESTART is ignored (assumed set): the restart is unconditional.
*/
tprints("= ? ERESTARTNOINTR (To be restarted)");
break;
case ERESTARTNOHAND:
/* pause(), rt_sigsuspend() etc use this code.
* SA_RESTART is ignored (assumed not set):
* syscall won't restart (will return EINTR instead)
* even after signal with SA_RESTART set. However,
* after SIG_IGN or SIG_DFL signal it will restart
* (thus the name "restart only if has no handler").
*/
tprints("= ? ERESTARTNOHAND (To be restarted if no handler)");
break;
case ERESTART_RESTARTBLOCK:
/* Syscalls like nanosleep(), poll() which can't be
* restarted with their original arguments use this
* code. Kernel will execute restart_syscall() instead,
* which changes arguments before restarting syscall.
* SA_RESTART is ignored (assumed not set) similarly
* to ERESTARTNOHAND. (Kernel can't honor SA_RESTART
* since restart data is saved in "restart block"
* in task struct, and if signal handler uses a syscall
* which in turn saves another such restart block,
* old data is lost and restart becomes impossible)
*/
tprints("= ? ERESTART_RESTARTBLOCK (Interrupted by signal)");
break;
default:
print_err_ret(tcp->u_rval, tcp->u_error);
break;
}
if (syscall_tampered(tcp))
tprints(" (INJECTED)");
if ((sys_res & RVAL_STR) && tcp->auxstr)
tprintf(" (%s)", tcp->auxstr);
} else {
if (sys_res & RVAL_NONE)
tprints("= ?");
else {
switch (sys_res & RVAL_MASK) {
case RVAL_HEX:
#if ANY_WORDSIZE_LESS_THAN_KERNEL_LONG
if (current_klongsize < sizeof(tcp->u_rval)) {
tprintf("= %#x",
(unsigned int) tcp->u_rval);
} else
#endif
{
tprintf("= %#" PRI_klx, tcp->u_rval);
}
break;
case RVAL_OCTAL:
tprints("= ");
print_numeric_long_umask(tcp->u_rval);
break;
case RVAL_UDECIMAL:
#if ANY_WORDSIZE_LESS_THAN_KERNEL_LONG
if (current_klongsize < sizeof(tcp->u_rval)) {
tprintf("= %u",
(unsigned int) tcp->u_rval);
} else
#endif
{
tprintf("= %" PRI_klu, tcp->u_rval);
}
break;
case RVAL_FD:
if (show_fd_path) {
tprints("= ");
printfd(tcp, tcp->u_rval);
} else
tprintf("= %" PRI_kld, tcp->u_rval);
break;
default:
error_msg("invalid rval format");
break;
}
}
if ((sys_res & RVAL_STR) && tcp->auxstr)
tprintf(" (%s)", tcp->auxstr);
if (syscall_tampered(tcp))
tprints(" (INJECTED)");
}
if (Tflag) {
ts_sub(ts, ts, &tcp->etime);
tprintf(" <%ld.%06ld>",
(long) ts->tv_sec, (long) ts->tv_nsec / 1000);
}
tprints("\n");
dumpio(tcp);
line_ended();
#ifdef ENABLE_STACKTRACE
if (stack_trace_enabled)
unwind_tcb_print(tcp);
#endif
return 0;
}
void
syscall_exiting_finish(struct tcb *tcp)
{
tcp->flags &= ~(TCB_INSYSCALL | TCB_TAMPERED | TCB_INJECT_DELAY_EXIT);
tcp->sys_func_rval = 0;
free_tcb_priv_data(tcp);
}
bool
is_erestart(struct tcb *tcp)
{
switch (tcp->u_error) {
case ERESTARTSYS:
case ERESTARTNOINTR:
case ERESTARTNOHAND:
case ERESTART_RESTARTBLOCK:
return true;
default:
return false;
}
}
static unsigned long saved_u_error;
void
temporarily_clear_syserror(struct tcb *tcp)
{
saved_u_error = tcp->u_error;
tcp->u_error = 0;
}
void
restore_cleared_syserror(struct tcb *tcp)
{
tcp->u_error = saved_u_error;
}
#define XLAT_MACROS_ONLY
# include "xlat/nt_descriptor_types.h"
#undef XLAT_MACROS_ONLY
#include "arch_regs.c"
#if HAVE_ARCH_GETRVAL2
# include "arch_getrval2.c"
#endif
void
print_pc(struct tcb *tcp)
{
#if defined ARCH_PC_REG
# define ARCH_GET_PC 0
#elif defined ARCH_PC_PEEK_ADDR
kernel_ulong_t pc;
# define ARCH_PC_REG pc
# define ARCH_GET_PC upeek(tcp, ARCH_PC_PEEK_ADDR, &pc)
#else
# error Neither ARCH_PC_REG nor ARCH_PC_PEEK_ADDR is defined