forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
trace_kprobe.c
2091 lines (1742 loc) · 50.2 KB
/
trace_kprobe.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
// SPDX-License-Identifier: GPL-2.0
/*
* Kprobes-based tracing events
*
* Created by Masami Hiramatsu <[email protected]>
*
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
#include <linux/bpf-cgroup.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/rculist.h>
#include <linux/error-injection.h>
#include <asm/setup.h> /* for COMMAND_LINE_SIZE */
#include "trace_dynevent.h"
#include "trace_kprobe_selftest.h"
#include "trace_probe.h"
#include "trace_probe_tmpl.h"
#include "trace_probe_kernel.h"
#define KPROBE_EVENT_SYSTEM "kprobes"
#define KRETPROBE_MAXACTIVE_MAX 4096
/* Kprobe early definition from command line */
static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
static int __init set_kprobe_boot_events(char *str)
{
strscpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
disable_tracing_selftest("running kprobe events");
return 1;
}
__setup("kprobe_event=", set_kprobe_boot_events);
static int trace_kprobe_create(const char *raw_command);
static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_kprobe_release(struct dyn_event *ev);
static bool trace_kprobe_is_busy(struct dyn_event *ev);
static bool trace_kprobe_match(const char *system, const char *event,
int argc, const char **argv, struct dyn_event *ev);
static struct dyn_event_operations trace_kprobe_ops = {
.create = trace_kprobe_create,
.show = trace_kprobe_show,
.is_busy = trace_kprobe_is_busy,
.free = trace_kprobe_release,
.match = trace_kprobe_match,
};
/*
* Kprobe event core functions
*/
struct trace_kprobe {
struct dyn_event devent;
struct kretprobe rp; /* Use rp.kp for kprobe use */
unsigned long __percpu *nhit;
const char *symbol; /* symbol name */
struct trace_probe tp;
};
static bool is_trace_kprobe(struct dyn_event *ev)
{
return ev->ops == &trace_kprobe_ops;
}
static struct trace_kprobe *to_trace_kprobe(struct dyn_event *ev)
{
return container_of(ev, struct trace_kprobe, devent);
}
/**
* for_each_trace_kprobe - iterate over the trace_kprobe list
* @pos: the struct trace_kprobe * for each entry
* @dpos: the struct dyn_event * to use as a loop cursor
*/
#define for_each_trace_kprobe(pos, dpos) \
for_each_dyn_event(dpos) \
if (is_trace_kprobe(dpos) && (pos = to_trace_kprobe(dpos)))
static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
{
return tk->rp.handler != NULL;
}
static nokprobe_inline const char *trace_kprobe_symbol(struct trace_kprobe *tk)
{
return tk->symbol ? tk->symbol : "unknown";
}
static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
{
return tk->rp.kp.offset;
}
static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk)
{
return kprobe_gone(&tk->rp.kp);
}
static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
struct module *mod)
{
int len = strlen(module_name(mod));
const char *name = trace_kprobe_symbol(tk);
return strncmp(module_name(mod), name, len) == 0 && name[len] == ':';
}
static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
{
char *p;
bool ret;
if (!tk->symbol)
return false;
p = strchr(tk->symbol, ':');
if (!p)
return true;
*p = '\0';
rcu_read_lock_sched();
ret = !!find_module(tk->symbol);
rcu_read_unlock_sched();
*p = ':';
return ret;
}
static bool trace_kprobe_is_busy(struct dyn_event *ev)
{
struct trace_kprobe *tk = to_trace_kprobe(ev);
return trace_probe_is_enabled(&tk->tp);
}
static bool trace_kprobe_match_command_head(struct trace_kprobe *tk,
int argc, const char **argv)
{
char buf[MAX_ARGSTR_LEN + 1];
if (!argc)
return true;
if (!tk->symbol)
snprintf(buf, sizeof(buf), "0x%p", tk->rp.kp.addr);
else if (tk->rp.kp.offset)
snprintf(buf, sizeof(buf), "%s+%u",
trace_kprobe_symbol(tk), tk->rp.kp.offset);
else
snprintf(buf, sizeof(buf), "%s", trace_kprobe_symbol(tk));
if (strcmp(buf, argv[0]))
return false;
argc--; argv++;
return trace_probe_match_command_args(&tk->tp, argc, argv);
}
static bool trace_kprobe_match(const char *system, const char *event,
int argc, const char **argv, struct dyn_event *ev)
{
struct trace_kprobe *tk = to_trace_kprobe(ev);
return (event[0] == '\0' ||
strcmp(trace_probe_name(&tk->tp), event) == 0) &&
(!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0) &&
trace_kprobe_match_command_head(tk, argc, argv);
}
static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
{
unsigned long nhit = 0;
int cpu;
for_each_possible_cpu(cpu)
nhit += *per_cpu_ptr(tk->nhit, cpu);
return nhit;
}
static nokprobe_inline bool trace_kprobe_is_registered(struct trace_kprobe *tk)
{
return !(list_empty(&tk->rp.kp.list) &&
hlist_unhashed(&tk->rp.kp.hlist));
}
/* Return 0 if it fails to find the symbol address */
static nokprobe_inline
unsigned long trace_kprobe_address(struct trace_kprobe *tk)
{
unsigned long addr;
if (tk->symbol) {
addr = (unsigned long)
kallsyms_lookup_name(trace_kprobe_symbol(tk));
if (addr)
addr += tk->rp.kp.offset;
} else {
addr = (unsigned long)tk->rp.kp.addr;
}
return addr;
}
static nokprobe_inline struct trace_kprobe *
trace_kprobe_primary_from_call(struct trace_event_call *call)
{
struct trace_probe *tp;
tp = trace_probe_primary_from_call(call);
if (WARN_ON_ONCE(!tp))
return NULL;
return container_of(tp, struct trace_kprobe, tp);
}
bool trace_kprobe_on_func_entry(struct trace_event_call *call)
{
struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
return tk ? (kprobe_on_func_entry(tk->rp.kp.addr,
tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false;
}
bool trace_kprobe_error_injectable(struct trace_event_call *call)
{
struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
return tk ? within_error_injection_list(trace_kprobe_address(tk)) :
false;
}
static int register_kprobe_event(struct trace_kprobe *tk);
static int unregister_kprobe_event(struct trace_kprobe *tk);
static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
struct pt_regs *regs);
static void free_trace_kprobe(struct trace_kprobe *tk)
{
if (tk) {
trace_probe_cleanup(&tk->tp);
kfree(tk->symbol);
free_percpu(tk->nhit);
kfree(tk);
}
}
/*
* Allocate new trace_probe and initialize it (including kprobes).
*/
static struct trace_kprobe *alloc_trace_kprobe(const char *group,
const char *event,
void *addr,
const char *symbol,
unsigned long offs,
int maxactive,
int nargs, bool is_return)
{
struct trace_kprobe *tk;
int ret = -ENOMEM;
tk = kzalloc(struct_size(tk, tp.args, nargs), GFP_KERNEL);
if (!tk)
return ERR_PTR(ret);
tk->nhit = alloc_percpu(unsigned long);
if (!tk->nhit)
goto error;
if (symbol) {
tk->symbol = kstrdup(symbol, GFP_KERNEL);
if (!tk->symbol)
goto error;
tk->rp.kp.symbol_name = tk->symbol;
tk->rp.kp.offset = offs;
} else
tk->rp.kp.addr = addr;
if (is_return)
tk->rp.handler = kretprobe_dispatcher;
else
tk->rp.kp.pre_handler = kprobe_dispatcher;
tk->rp.maxactive = maxactive;
INIT_HLIST_NODE(&tk->rp.kp.hlist);
INIT_LIST_HEAD(&tk->rp.kp.list);
ret = trace_probe_init(&tk->tp, event, group, false);
if (ret < 0)
goto error;
dyn_event_init(&tk->devent, &trace_kprobe_ops);
return tk;
error:
free_trace_kprobe(tk);
return ERR_PTR(ret);
}
static struct trace_kprobe *find_trace_kprobe(const char *event,
const char *group)
{
struct dyn_event *pos;
struct trace_kprobe *tk;
for_each_trace_kprobe(tk, pos)
if (strcmp(trace_probe_name(&tk->tp), event) == 0 &&
strcmp(trace_probe_group_name(&tk->tp), group) == 0)
return tk;
return NULL;
}
static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
{
int ret = 0;
if (trace_kprobe_is_registered(tk) && !trace_kprobe_has_gone(tk)) {
if (trace_kprobe_is_return(tk))
ret = enable_kretprobe(&tk->rp);
else
ret = enable_kprobe(&tk->rp.kp);
}
return ret;
}
static void __disable_trace_kprobe(struct trace_probe *tp)
{
struct trace_kprobe *tk;
list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) {
if (!trace_kprobe_is_registered(tk))
continue;
if (trace_kprobe_is_return(tk))
disable_kretprobe(&tk->rp);
else
disable_kprobe(&tk->rp.kp);
}
}
/*
* Enable trace_probe
* if the file is NULL, enable "perf" handler, or enable "trace" handler.
*/
static int enable_trace_kprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
struct trace_probe *tp;
struct trace_kprobe *tk;
bool enabled;
int ret = 0;
tp = trace_probe_primary_from_call(call);
if (WARN_ON_ONCE(!tp))
return -ENODEV;
enabled = trace_probe_is_enabled(tp);
/* This also changes "enabled" state */
if (file) {
ret = trace_probe_add_file(tp, file);
if (ret)
return ret;
} else
trace_probe_set_flag(tp, TP_FLAG_PROFILE);
if (enabled)
return 0;
list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) {
if (trace_kprobe_has_gone(tk))
continue;
ret = __enable_trace_kprobe(tk);
if (ret)
break;
enabled = true;
}
if (ret) {
/* Failed to enable one of them. Roll back all */
if (enabled)
__disable_trace_kprobe(tp);
if (file)
trace_probe_remove_file(tp, file);
else
trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
}
return ret;
}
/*
* Disable trace_probe
* if the file is NULL, disable "perf" handler, or disable "trace" handler.
*/
static int disable_trace_kprobe(struct trace_event_call *call,
struct trace_event_file *file)
{
struct trace_probe *tp;
tp = trace_probe_primary_from_call(call);
if (WARN_ON_ONCE(!tp))
return -ENODEV;
if (file) {
if (!trace_probe_get_file_link(tp, file))
return -ENOENT;
if (!trace_probe_has_single_file(tp))
goto out;
trace_probe_clear_flag(tp, TP_FLAG_TRACE);
} else
trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
if (!trace_probe_is_enabled(tp))
__disable_trace_kprobe(tp);
out:
if (file)
/*
* Synchronization is done in below function. For perf event,
* file == NULL and perf_trace_event_unreg() calls
* tracepoint_synchronize_unregister() to ensure synchronize
* event. We don't need to care about it.
*/
trace_probe_remove_file(tp, file);
return 0;
}
#if defined(CONFIG_DYNAMIC_FTRACE) && \
!defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
static bool __within_notrace_func(unsigned long addr)
{
unsigned long offset, size;
if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset))
return false;
/* Get the entry address of the target function */
addr -= offset;
/*
* Since ftrace_location_range() does inclusive range check, we need
* to subtract 1 byte from the end address.
*/
return !ftrace_location_range(addr, addr + size - 1);
}
static bool within_notrace_func(struct trace_kprobe *tk)
{
unsigned long addr = trace_kprobe_address(tk);
char symname[KSYM_NAME_LEN], *p;
if (!__within_notrace_func(addr))
return false;
/* Check if the address is on a suffixed-symbol */
if (!lookup_symbol_name(addr, symname)) {
p = strchr(symname, '.');
if (!p)
return true;
*p = '\0';
addr = (unsigned long)kprobe_lookup_name(symname, 0);
if (addr)
return __within_notrace_func(addr);
}
return true;
}
#else
#define within_notrace_func(tk) (false)
#endif
/* Internal register function - just handle k*probes and flags */
static int __register_trace_kprobe(struct trace_kprobe *tk)
{
int i, ret;
ret = security_locked_down(LOCKDOWN_KPROBES);
if (ret)
return ret;
if (trace_kprobe_is_registered(tk))
return -EINVAL;
if (within_notrace_func(tk)) {
pr_warn("Could not probe notrace function %s\n",
trace_kprobe_symbol(tk));
return -EINVAL;
}
for (i = 0; i < tk->tp.nr_args; i++) {
ret = traceprobe_update_arg(&tk->tp.args[i]);
if (ret)
return ret;
}
/* Set/clear disabled flag according to tp->flag */
if (trace_probe_is_enabled(&tk->tp))
tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
else
tk->rp.kp.flags |= KPROBE_FLAG_DISABLED;
if (trace_kprobe_is_return(tk))
ret = register_kretprobe(&tk->rp);
else
ret = register_kprobe(&tk->rp.kp);
return ret;
}
/* Internal unregister function - just handle k*probes and flags */
static void __unregister_trace_kprobe(struct trace_kprobe *tk)
{
if (trace_kprobe_is_registered(tk)) {
if (trace_kprobe_is_return(tk))
unregister_kretprobe(&tk->rp);
else
unregister_kprobe(&tk->rp.kp);
/* Cleanup kprobe for reuse and mark it unregistered */
INIT_HLIST_NODE(&tk->rp.kp.hlist);
INIT_LIST_HEAD(&tk->rp.kp.list);
if (tk->rp.kp.symbol_name)
tk->rp.kp.addr = NULL;
}
}
/* Unregister a trace_probe and probe_event */
static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
/* If other probes are on the event, just unregister kprobe */
if (trace_probe_has_sibling(&tk->tp))
goto unreg;
/* Enabled event can not be unregistered */
if (trace_probe_is_enabled(&tk->tp))
return -EBUSY;
/* If there's a reference to the dynamic event */
if (trace_event_dyn_busy(trace_probe_event_call(&tk->tp)))
return -EBUSY;
/* Will fail if probe is being used by ftrace or perf */
if (unregister_kprobe_event(tk))
return -EBUSY;
unreg:
__unregister_trace_kprobe(tk);
dyn_event_remove(&tk->devent);
trace_probe_unlink(&tk->tp);
return 0;
}
static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig,
struct trace_kprobe *comp)
{
struct trace_probe_event *tpe = orig->tp.event;
int i;
list_for_each_entry(orig, &tpe->probes, tp.list) {
if (strcmp(trace_kprobe_symbol(orig),
trace_kprobe_symbol(comp)) ||
trace_kprobe_offset(orig) != trace_kprobe_offset(comp))
continue;
/*
* trace_probe_compare_arg_type() ensured that nr_args and
* each argument name and type are same. Let's compare comm.
*/
for (i = 0; i < orig->tp.nr_args; i++) {
if (strcmp(orig->tp.args[i].comm,
comp->tp.args[i].comm))
break;
}
if (i == orig->tp.nr_args)
return true;
}
return false;
}
static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
{
int ret;
ret = trace_probe_compare_arg_type(&tk->tp, &to->tp);
if (ret) {
/* Note that argument starts index = 2 */
trace_probe_log_set_index(ret + 1);
trace_probe_log_err(0, DIFF_ARG_TYPE);
return -EEXIST;
}
if (trace_kprobe_has_same_kprobe(to, tk)) {
trace_probe_log_set_index(0);
trace_probe_log_err(0, SAME_PROBE);
return -EEXIST;
}
/* Append to existing event */
ret = trace_probe_append(&tk->tp, &to->tp);
if (ret)
return ret;
/* Register k*probe */
ret = __register_trace_kprobe(tk);
if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
}
if (ret)
trace_probe_unlink(&tk->tp);
else
dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
return ret;
}
/* Register a trace_probe and probe_event */
static int register_trace_kprobe(struct trace_kprobe *tk)
{
struct trace_kprobe *old_tk;
int ret;
mutex_lock(&event_mutex);
old_tk = find_trace_kprobe(trace_probe_name(&tk->tp),
trace_probe_group_name(&tk->tp));
if (old_tk) {
if (trace_kprobe_is_return(tk) != trace_kprobe_is_return(old_tk)) {
trace_probe_log_set_index(0);
trace_probe_log_err(0, DIFF_PROBE_TYPE);
ret = -EEXIST;
} else {
ret = append_trace_kprobe(tk, old_tk);
}
goto end;
}
/* Register new event */
ret = register_kprobe_event(tk);
if (ret) {
if (ret == -EEXIST) {
trace_probe_log_set_index(0);
trace_probe_log_err(0, EVENT_EXIST);
} else
pr_warn("Failed to register probe event(%d)\n", ret);
goto end;
}
/* Register k*probe */
ret = __register_trace_kprobe(tk);
if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
}
if (ret < 0)
unregister_kprobe_event(tk);
else
dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
end:
mutex_unlock(&event_mutex);
return ret;
}
/* Module notifier call back, checking event on the module */
static int trace_kprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
{
struct module *mod = data;
struct dyn_event *pos;
struct trace_kprobe *tk;
int ret;
if (val != MODULE_STATE_COMING)
return NOTIFY_DONE;
/* Update probes on coming module */
mutex_lock(&event_mutex);
for_each_trace_kprobe(tk, pos) {
if (trace_kprobe_within_module(tk, mod)) {
/* Don't need to check busy - this should have gone. */
__unregister_trace_kprobe(tk);
ret = __register_trace_kprobe(tk);
if (ret)
pr_warn("Failed to re-register probe %s on %s: %d\n",
trace_probe_name(&tk->tp),
module_name(mod), ret);
}
}
mutex_unlock(&event_mutex);
return NOTIFY_DONE;
}
static struct notifier_block trace_kprobe_module_nb = {
.notifier_call = trace_kprobe_module_callback,
.priority = 1 /* Invoked after kprobe module callback */
};
static int count_symbols(void *data, unsigned long unused)
{
unsigned int *count = data;
(*count)++;
return 0;
}
struct sym_count_ctx {
unsigned int count;
const char *name;
};
static int count_mod_symbols(void *data, const char *name, unsigned long unused)
{
struct sym_count_ctx *ctx = data;
if (strcmp(name, ctx->name) == 0)
ctx->count++;
return 0;
}
static unsigned int number_of_same_symbols(char *func_name)
{
struct sym_count_ctx ctx = { .count = 0, .name = func_name };
kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
module_kallsyms_on_each_symbol(NULL, count_mod_symbols, &ctx);
return ctx.count;
}
static int __trace_kprobe_create(int argc, const char *argv[])
{
/*
* Argument syntax:
* - Add kprobe:
* p[:[GRP/][EVENT]] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
* - Add kretprobe:
* r[MAXACTIVE][:[GRP/][EVENT]] [MOD:]KSYM[+0] [FETCHARGS]
* Or
* p[:[GRP/][EVENT]] [MOD:]KSYM[+0]%return [FETCHARGS]
*
* Fetch args:
* $retval : fetch return value
* $stack : fetch stack address
* $stackN : fetch Nth of stack (N:0-)
* $comm : fetch current task comm
* @ADDR : fetch memory at ADDR (ADDR should be in kernel)
* @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
* %REG : fetch register REG
* Dereferencing memory fetch:
* +|-offs(ARG) : fetch memory at ARG +|- offs address.
* Alias name of args:
* NAME=FETCHARG : set NAME as alias of FETCHARG.
* Type of args:
* FETCHARG:TYPE : use TYPE instead of unsigned long.
*/
struct trace_kprobe *tk = NULL;
int i, len, new_argc = 0, ret = 0;
bool is_return = false;
char *symbol = NULL, *tmp = NULL;
const char **new_argv = NULL;
const char *event = NULL, *group = KPROBE_EVENT_SYSTEM;
enum probe_print_type ptype;
int maxactive = 0;
long offset = 0;
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
char gbuf[MAX_EVENT_NAME_LEN];
char abuf[MAX_BTF_ARGS_LEN];
struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL };
switch (argv[0][0]) {
case 'r':
is_return = true;
break;
case 'p':
break;
default:
return -ECANCELED;
}
if (argc < 2)
return -ECANCELED;
trace_probe_log_init("trace_kprobe", argc, argv);
event = strchr(&argv[0][1], ':');
if (event)
event++;
if (isdigit(argv[0][1])) {
if (!is_return) {
trace_probe_log_err(1, BAD_MAXACT_TYPE);
goto parse_error;
}
if (event)
len = event - &argv[0][1] - 1;
else
len = strlen(&argv[0][1]);
if (len > MAX_EVENT_NAME_LEN - 1) {
trace_probe_log_err(1, BAD_MAXACT);
goto parse_error;
}
memcpy(buf, &argv[0][1], len);
buf[len] = '\0';
ret = kstrtouint(buf, 0, &maxactive);
if (ret || !maxactive) {
trace_probe_log_err(1, BAD_MAXACT);
goto parse_error;
}
/* kretprobes instances are iterated over via a list. The
* maximum should stay reasonable.
*/
if (maxactive > KRETPROBE_MAXACTIVE_MAX) {
trace_probe_log_err(1, MAXACT_TOO_BIG);
goto parse_error;
}
}
/* try to parse an address. if that fails, try to read the
* input as a symbol. */
if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
trace_probe_log_set_index(1);
/* Check whether uprobe event specified */
if (strchr(argv[1], '/') && strchr(argv[1], ':')) {
ret = -ECANCELED;
goto error;
}
/* a symbol specified */
symbol = kstrdup(argv[1], GFP_KERNEL);
if (!symbol)
return -ENOMEM;
tmp = strchr(symbol, '%');
if (tmp) {
if (!strcmp(tmp, "%return")) {
*tmp = '\0';
is_return = true;
} else {
trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX);
goto parse_error;
}
}
/* TODO: support .init module functions */
ret = traceprobe_split_symbol_offset(symbol, &offset);
if (ret || offset < 0 || offset > UINT_MAX) {
trace_probe_log_err(0, BAD_PROBE_ADDR);
goto parse_error;
}
if (is_return)
ctx.flags |= TPARG_FL_RETURN;
ret = kprobe_on_func_entry(NULL, symbol, offset);
if (ret == 0 && !is_return)
ctx.flags |= TPARG_FL_FENTRY;
/* Defer the ENOENT case until register kprobe */
if (ret == -EINVAL && is_return) {
trace_probe_log_err(0, BAD_RETPROBE);
goto parse_error;
}
}
if (symbol && !strchr(symbol, ':')) {
unsigned int count;
count = number_of_same_symbols(symbol);
if (count > 1) {
/*
* Users should use ADDR to remove the ambiguity of
* using KSYM only.
*/
trace_probe_log_err(0, NON_UNIQ_SYMBOL);
ret = -EADDRNOTAVAIL;
goto error;
} else if (count == 0) {
/*
* We can return ENOENT earlier than when register the
* kprobe.
*/
trace_probe_log_err(0, BAD_PROBE_ADDR);
ret = -ENOENT;
goto error;
}
}
trace_probe_log_set_index(0);
if (event) {
ret = traceprobe_parse_event_name(&event, &group, gbuf,
event - argv[0]);
if (ret)
goto parse_error;
}
if (!event) {
/* Make a new event name */
if (symbol)
snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
is_return ? 'r' : 'p', symbol, offset);
else
snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p",
is_return ? 'r' : 'p', addr);
sanitize_event_name(buf);
event = buf;
}
argc -= 2; argv += 2;
ctx.funcname = symbol;
new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc,
abuf, MAX_BTF_ARGS_LEN, &ctx);
if (IS_ERR(new_argv)) {
ret = PTR_ERR(new_argv);
new_argv = NULL;
goto out;
}
if (new_argv) {
argc = new_argc;
argv = new_argv;
}
/* setup a probe */
tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
argc, is_return);
if (IS_ERR(tk)) {
ret = PTR_ERR(tk);
/* This must return -ENOMEM, else there is a bug */
WARN_ON_ONCE(ret != -ENOMEM);
goto out; /* We know tk is not allocated */
}
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
trace_probe_log_set_index(i + 2);
ctx.offset = 0;
ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx);
if (ret)
goto error; /* This can be -ENOMEM */
}
ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
ret = traceprobe_set_print_fmt(&tk->tp, ptype);
if (ret < 0)
goto error;
ret = register_trace_kprobe(tk);
if (ret) {
trace_probe_log_set_index(1);
if (ret == -EILSEQ)
trace_probe_log_err(0, BAD_INSN_BNDRY);
else if (ret == -ENOENT)
trace_probe_log_err(0, BAD_PROBE_ADDR);
else if (ret != -ENOMEM && ret != -EEXIST)
trace_probe_log_err(0, FAIL_REG_PROBE);
goto error;
}
out:
traceprobe_finish_parse(&ctx);
trace_probe_log_clear();
kfree(new_argv);
kfree(symbol);
return ret;
parse_error:
ret = -EINVAL;
error:
free_trace_kprobe(tk);
goto out;
}
static int trace_kprobe_create(const char *raw_command)
{
return trace_probe_create(raw_command, __trace_kprobe_create);
}
static int create_or_delete_trace_kprobe(const char *raw_command)
{
int ret;
if (raw_command[0] == '-')
return dyn_event_release(raw_command, &trace_kprobe_ops);
ret = trace_kprobe_create(raw_command);
return ret == -ECANCELED ? -EINVAL : ret;
}
static int trace_kprobe_run_command(struct dynevent_cmd *cmd)
{