forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtrace_uprobe.c
1470 lines (1194 loc) · 33.2 KB
/
trace_uprobe.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
/*
* uprobes-based tracing events
*
* Copyright (C) IBM Corporation, 2010-2012
* Author: Srikar Dronamraju <[email protected]>
*/
#define pr_fmt(fmt) "trace_uprobe: " fmt
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/uprobes.h>
#include <linux/namei.h>
#include <linux/string.h>
#include <linux/rculist.h>
#include "trace_dynevent.h"
#include "trace_probe.h"
#include "trace_probe_tmpl.h"
#define UPROBE_EVENT_SYSTEM "uprobes"
struct uprobe_trace_entry_head {
struct trace_entry ent;
unsigned long vaddr[];
};
#define SIZEOF_TRACE_ENTRY(is_return) \
(sizeof(struct uprobe_trace_entry_head) + \
sizeof(unsigned long) * (is_return ? 2 : 1))
#define DATAOF_TRACE_ENTRY(entry, is_return) \
((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))
struct trace_uprobe_filter {
rwlock_t rwlock;
int nr_systemwide;
struct list_head perf_events;
};
static int trace_uprobe_create(int argc, const char **argv);
static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_uprobe_release(struct dyn_event *ev);
static bool trace_uprobe_is_busy(struct dyn_event *ev);
static bool trace_uprobe_match(const char *system, const char *event,
struct dyn_event *ev);
static struct dyn_event_operations trace_uprobe_ops = {
.create = trace_uprobe_create,
.show = trace_uprobe_show,
.is_busy = trace_uprobe_is_busy,
.free = trace_uprobe_release,
.match = trace_uprobe_match,
};
/*
* uprobe event core functions
*/
struct trace_uprobe {
struct dyn_event devent;
struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
struct path path;
struct inode *inode;
char *filename;
unsigned long offset;
unsigned long ref_ctr_offset;
unsigned long nhit;
struct trace_probe tp;
};
static bool is_trace_uprobe(struct dyn_event *ev)
{
return ev->ops == &trace_uprobe_ops;
}
static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
{
return container_of(ev, struct trace_uprobe, devent);
}
/**
* for_each_trace_uprobe - iterate over the trace_uprobe list
* @pos: the struct trace_uprobe * for each entry
* @dpos: the struct dyn_event * to use as a loop cursor
*/
#define for_each_trace_uprobe(pos, dpos) \
for_each_dyn_event(dpos) \
if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos)))
#define SIZEOF_TRACE_UPROBE(n) \
(offsetof(struct trace_uprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
static int register_uprobe_event(struct trace_uprobe *tu);
static int unregister_uprobe_event(struct trace_uprobe *tu);
struct uprobe_dispatch_data {
struct trace_uprobe *tu;
unsigned long bp_addr;
};
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs);
#ifdef CONFIG_STACK_GROWSUP
static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
{
return addr - (n * sizeof(long));
}
#else
static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
{
return addr + (n * sizeof(long));
}
#endif
static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
{
unsigned long ret;
unsigned long addr = user_stack_pointer(regs);
addr = adjust_stack_addr(addr, n);
if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret)))
return 0;
return ret;
}
/*
* Uprobes-specific fetch functions
*/
static nokprobe_inline int
probe_mem_read(void *dest, void *src, size_t size)
{
void __user *vaddr = (void __force __user *)src;
return copy_from_user(dest, vaddr, size) ? -EFAULT : 0;
}
/*
* Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
* length and relative data location.
*/
static nokprobe_inline int
fetch_store_string(unsigned long addr, void *dest, void *base)
{
long ret;
u32 loc = *(u32 *)dest;
int maxlen = get_loc_len(loc);
u8 *dst = get_loc_data(dest, base);
void __user *src = (void __force __user *) addr;
if (unlikely(!maxlen))
return -ENOMEM;
if (addr == FETCH_TOKEN_COMM)
ret = strlcpy(dst, current->comm, maxlen);
else
ret = strncpy_from_user(dst, src, maxlen);
if (ret >= 0) {
if (ret == maxlen)
dst[ret - 1] = '\0';
else
/*
* Include the terminating null byte. In this case it
* was copied by strncpy_from_user but not accounted
* for in ret.
*/
ret++;
*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
}
return ret;
}
/* Return the length of string -- including null terminal byte */
static nokprobe_inline int
fetch_store_strlen(unsigned long addr)
{
int len;
void __user *vaddr = (void __force __user *) addr;
if (addr == FETCH_TOKEN_COMM)
len = strlen(current->comm) + 1;
else
len = strnlen_user(vaddr, MAX_STRING_SIZE);
return (len > MAX_STRING_SIZE) ? 0 : len;
}
static unsigned long translate_user_vaddr(unsigned long file_offset)
{
unsigned long base_addr;
struct uprobe_dispatch_data *udd;
udd = (void *) current->utask->vaddr;
base_addr = udd->bp_addr - udd->tu->offset;
return base_addr + file_offset;
}
/* Note that we don't verify it, since the code does not come from user space */
static int
process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
void *base)
{
unsigned long val;
/* 1st stage: get value from context */
switch (code->op) {
case FETCH_OP_REG:
val = regs_get_register(regs, code->param);
break;
case FETCH_OP_STACK:
val = get_user_stack_nth(regs, code->param);
break;
case FETCH_OP_STACKP:
val = user_stack_pointer(regs);
break;
case FETCH_OP_RETVAL:
val = regs_return_value(regs);
break;
case FETCH_OP_IMM:
val = code->immediate;
break;
case FETCH_OP_COMM:
val = FETCH_TOKEN_COMM;
break;
case FETCH_OP_FOFFS:
val = translate_user_vaddr(code->immediate);
break;
default:
return -EILSEQ;
}
code++;
return process_fetch_insn_bottom(code, val, dest, base);
}
NOKPROBE_SYMBOL(process_fetch_insn)
static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
rwlock_init(&filter->rwlock);
filter->nr_systemwide = 0;
INIT_LIST_HEAD(&filter->perf_events);
}
static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
{
return !filter->nr_systemwide && list_empty(&filter->perf_events);
}
static inline bool is_ret_probe(struct trace_uprobe *tu)
{
return tu->consumer.ret_handler != NULL;
}
static bool trace_uprobe_is_busy(struct dyn_event *ev)
{
struct trace_uprobe *tu = to_trace_uprobe(ev);
return trace_probe_is_enabled(&tu->tp);
}
static bool trace_uprobe_match(const char *system, const char *event,
struct dyn_event *ev)
{
struct trace_uprobe *tu = to_trace_uprobe(ev);
return strcmp(trace_event_name(&tu->tp.call), event) == 0 &&
(!system || strcmp(tu->tp.call.class->system, system) == 0);
}
/*
* Allocate new trace_uprobe and initialize it (including uprobes).
*/
static struct trace_uprobe *
alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
{
struct trace_uprobe *tu;
if (!event || !group)
return ERR_PTR(-EINVAL);
tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
if (!tu)
return ERR_PTR(-ENOMEM);
tu->tp.call.class = &tu->tp.class;
tu->tp.call.name = kstrdup(event, GFP_KERNEL);
if (!tu->tp.call.name)
goto error;
tu->tp.class.system = kstrdup(group, GFP_KERNEL);
if (!tu->tp.class.system)
goto error;
dyn_event_init(&tu->devent, &trace_uprobe_ops);
INIT_LIST_HEAD(&tu->tp.files);
tu->consumer.handler = uprobe_dispatcher;
if (is_ret)
tu->consumer.ret_handler = uretprobe_dispatcher;
init_trace_uprobe_filter(&tu->filter);
return tu;
error:
kfree(tu->tp.call.name);
kfree(tu);
return ERR_PTR(-ENOMEM);
}
static void free_trace_uprobe(struct trace_uprobe *tu)
{
int i;
if (!tu)
return;
for (i = 0; i < tu->tp.nr_args; i++)
traceprobe_free_probe_arg(&tu->tp.args[i]);
path_put(&tu->path);
kfree(tu->tp.call.class->system);
kfree(tu->tp.call.name);
kfree(tu->filename);
kfree(tu);
}
static struct trace_uprobe *find_probe_event(const char *event, const char *group)
{
struct dyn_event *pos;
struct trace_uprobe *tu;
for_each_trace_uprobe(tu, pos)
if (strcmp(trace_event_name(&tu->tp.call), event) == 0 &&
strcmp(tu->tp.call.class->system, group) == 0)
return tu;
return NULL;
}
/* Unregister a trace_uprobe and probe_event */
static int unregister_trace_uprobe(struct trace_uprobe *tu)
{
int ret;
ret = unregister_uprobe_event(tu);
if (ret)
return ret;
dyn_event_remove(&tu->devent);
free_trace_uprobe(tu);
return 0;
}
/*
* Uprobe with multiple reference counter is not allowed. i.e.
* If inode and offset matches, reference counter offset *must*
* match as well. Though, there is one exception: If user is
* replacing old trace_uprobe with new one(same group/event),
* then we allow same uprobe with new reference counter as far
* as the new one does not conflict with any other existing
* ones.
*/
static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new)
{
struct dyn_event *pos;
struct trace_uprobe *tmp, *old = NULL;
struct inode *new_inode = d_real_inode(new->path.dentry);
old = find_probe_event(trace_event_name(&new->tp.call),
new->tp.call.class->system);
for_each_trace_uprobe(tmp, pos) {
if ((old ? old != tmp : true) &&
new_inode == d_real_inode(tmp->path.dentry) &&
new->offset == tmp->offset &&
new->ref_ctr_offset != tmp->ref_ctr_offset) {
pr_warn("Reference counter offset mismatch.");
return ERR_PTR(-EINVAL);
}
}
return old;
}
/* Register a trace_uprobe and probe_event */
static int register_trace_uprobe(struct trace_uprobe *tu)
{
struct trace_uprobe *old_tu;
int ret;
mutex_lock(&event_mutex);
/* register as an event */
old_tu = find_old_trace_uprobe(tu);
if (IS_ERR(old_tu)) {
ret = PTR_ERR(old_tu);
goto end;
}
if (old_tu) {
/* delete old event */
ret = unregister_trace_uprobe(old_tu);
if (ret)
goto end;
}
ret = register_uprobe_event(tu);
if (ret) {
pr_warn("Failed to register probe event(%d)\n", ret);
goto end;
}
dyn_event_add(&tu->devent);
end:
mutex_unlock(&event_mutex);
return ret;
}
/*
* Argument syntax:
* - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
*/
static int trace_uprobe_create(int argc, const char **argv)
{
struct trace_uprobe *tu;
const char *event = NULL, *group = UPROBE_EVENT_SYSTEM;
char *arg, *filename, *rctr, *rctr_end, *tmp;
char buf[MAX_EVENT_NAME_LEN];
struct path path;
unsigned long offset, ref_ctr_offset;
bool is_return = false;
int i, ret;
ret = 0;
ref_ctr_offset = 0;
switch (argv[0][0]) {
case 'r':
is_return = true;
break;
case 'p':
break;
default:
return -ECANCELED;
}
if (argc < 2)
return -ECANCELED;
if (argv[0][1] == ':')
event = &argv[0][2];
if (!strchr(argv[1], '/'))
return -ECANCELED;
filename = kstrdup(argv[1], GFP_KERNEL);
if (!filename)
return -ENOMEM;
/* Find the last occurrence, in case the path contains ':' too. */
arg = strrchr(filename, ':');
if (!arg || !isdigit(arg[1])) {
kfree(filename);
return -ECANCELED;
}
trace_probe_log_init("trace_uprobe", argc, argv);
trace_probe_log_set_index(1); /* filename is the 2nd argument */
*arg++ = '\0';
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret) {
trace_probe_log_err(0, FILE_NOT_FOUND);
kfree(filename);
trace_probe_log_clear();
return ret;
}
if (!d_is_reg(path.dentry)) {
trace_probe_log_err(0, NO_REGULAR_FILE);
ret = -EINVAL;
goto fail_address_parse;
}
/* Parse reference counter offset if specified. */
rctr = strchr(arg, '(');
if (rctr) {
rctr_end = strchr(rctr, ')');
if (!rctr_end) {
ret = -EINVAL;
rctr_end = rctr + strlen(rctr);
trace_probe_log_err(rctr_end - filename,
REFCNT_OPEN_BRACE);
goto fail_address_parse;
} else if (rctr_end[1] != '\0') {
ret = -EINVAL;
trace_probe_log_err(rctr_end + 1 - filename,
BAD_REFCNT_SUFFIX);
goto fail_address_parse;
}
*rctr++ = '\0';
*rctr_end = '\0';
ret = kstrtoul(rctr, 0, &ref_ctr_offset);
if (ret) {
trace_probe_log_err(rctr - filename, BAD_REFCNT);
goto fail_address_parse;
}
}
/* Parse uprobe offset. */
ret = kstrtoul(arg, 0, &offset);
if (ret) {
trace_probe_log_err(arg - filename, BAD_UPROBE_OFFS);
goto fail_address_parse;
}
/* setup a probe */
trace_probe_log_set_index(0);
if (event) {
ret = traceprobe_parse_event_name(&event, &group, buf,
event - argv[0]);
if (ret)
goto fail_address_parse;
} else {
char *tail;
char *ptr;
tail = kstrdup(kbasename(filename), GFP_KERNEL);
if (!tail) {
ret = -ENOMEM;
goto fail_address_parse;
}
ptr = strpbrk(tail, ".-_");
if (ptr)
*ptr = '\0';
snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset);
event = buf;
kfree(tail);
}
argc -= 2;
argv += 2;
tu = alloc_trace_uprobe(group, event, argc, is_return);
if (IS_ERR(tu)) {
ret = PTR_ERR(tu);
/* This must return -ENOMEM otherwise there is a bug */
WARN_ON_ONCE(ret != -ENOMEM);
goto fail_address_parse;
}
tu->offset = offset;
tu->ref_ctr_offset = ref_ctr_offset;
tu->path = path;
tu->filename = filename;
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
tmp = kstrdup(argv[i], GFP_KERNEL);
if (!tmp) {
ret = -ENOMEM;
goto error;
}
trace_probe_log_set_index(i + 2);
ret = traceprobe_parse_probe_arg(&tu->tp, i, tmp,
is_return ? TPARG_FL_RETURN : 0);
kfree(tmp);
if (ret)
goto error;
}
ret = register_trace_uprobe(tu);
if (!ret)
goto out;
error:
free_trace_uprobe(tu);
out:
trace_probe_log_clear();
return ret;
fail_address_parse:
trace_probe_log_clear();
path_put(&path);
kfree(filename);
return ret;
}
static int create_or_delete_trace_uprobe(int argc, char **argv)
{
int ret;
if (argv[0][0] == '-')
return dyn_event_release(argc, argv, &trace_uprobe_ops);
ret = trace_uprobe_create(argc, (const char **)argv);
return ret == -ECANCELED ? -EINVAL : ret;
}
static int trace_uprobe_release(struct dyn_event *ev)
{
struct trace_uprobe *tu = to_trace_uprobe(ev);
return unregister_trace_uprobe(tu);
}
/* Probes listing interfaces */
static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev)
{
struct trace_uprobe *tu = to_trace_uprobe(ev);
char c = is_ret_probe(tu) ? 'r' : 'p';
int i;
seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, tu->tp.call.class->system,
trace_event_name(&tu->tp.call), tu->filename,
(int)(sizeof(void *) * 2), tu->offset);
if (tu->ref_ctr_offset)
seq_printf(m, "(0x%lx)", tu->ref_ctr_offset);
for (i = 0; i < tu->tp.nr_args; i++)
seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
seq_putc(m, '\n');
return 0;
}
static int probes_seq_show(struct seq_file *m, void *v)
{
struct dyn_event *ev = v;
if (!is_trace_uprobe(ev))
return 0;
return trace_uprobe_show(m, ev);
}
static const struct seq_operations probes_seq_op = {
.start = dyn_event_seq_start,
.next = dyn_event_seq_next,
.stop = dyn_event_seq_stop,
.show = probes_seq_show
};
static int probes_open(struct inode *inode, struct file *file)
{
int ret;
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&trace_uprobe_ops);
if (ret)
return ret;
}
return seq_open(file, &probes_seq_op);
}
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
return trace_parse_run_command(file, buffer, count, ppos,
create_or_delete_trace_uprobe);
}
static const struct file_operations uprobe_events_ops = {
.owner = THIS_MODULE,
.open = probes_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
.write = probes_write,
};
/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
struct dyn_event *ev = v;
struct trace_uprobe *tu;
if (!is_trace_uprobe(ev))
return 0;
tu = to_trace_uprobe(ev);
seq_printf(m, " %s %-44s %15lu\n", tu->filename,
trace_event_name(&tu->tp.call), tu->nhit);
return 0;
}
static const struct seq_operations profile_seq_op = {
.start = dyn_event_seq_start,
.next = dyn_event_seq_next,
.stop = dyn_event_seq_stop,
.show = probes_profile_seq_show
};
static int profile_open(struct inode *inode, struct file *file)
{
return seq_open(file, &profile_seq_op);
}
static const struct file_operations uprobe_profile_ops = {
.owner = THIS_MODULE,
.open = profile_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
struct uprobe_cpu_buffer {
struct mutex mutex;
void *buf;
};
static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
static int uprobe_buffer_refcnt;
static int uprobe_buffer_init(void)
{
int cpu, err_cpu;
uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer);
if (uprobe_cpu_buffer == NULL)
return -ENOMEM;
for_each_possible_cpu(cpu) {
struct page *p = alloc_pages_node(cpu_to_node(cpu),
GFP_KERNEL, 0);
if (p == NULL) {
err_cpu = cpu;
goto err;
}
per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p);
mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex);
}
return 0;
err:
for_each_possible_cpu(cpu) {
if (cpu == err_cpu)
break;
free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf);
}
free_percpu(uprobe_cpu_buffer);
return -ENOMEM;
}
static int uprobe_buffer_enable(void)
{
int ret = 0;
BUG_ON(!mutex_is_locked(&event_mutex));
if (uprobe_buffer_refcnt++ == 0) {
ret = uprobe_buffer_init();
if (ret < 0)
uprobe_buffer_refcnt--;
}
return ret;
}
static void uprobe_buffer_disable(void)
{
int cpu;
BUG_ON(!mutex_is_locked(&event_mutex));
if (--uprobe_buffer_refcnt == 0) {
for_each_possible_cpu(cpu)
free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer,
cpu)->buf);
free_percpu(uprobe_cpu_buffer);
uprobe_cpu_buffer = NULL;
}
}
static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
{
struct uprobe_cpu_buffer *ucb;
int cpu;
cpu = raw_smp_processor_id();
ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu);
/*
* Use per-cpu buffers for fastest access, but we might migrate
* so the mutex makes sure we have sole access to it.
*/
mutex_lock(&ucb->mutex);
return ucb;
}
static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
{
mutex_unlock(&ucb->mutex);
}
static void __uprobe_trace_func(struct trace_uprobe *tu,
unsigned long func, struct pt_regs *regs,
struct uprobe_cpu_buffer *ucb, int dsize,
struct trace_event_file *trace_file)
{
struct uprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
void *data;
int size, esize;
struct trace_event_call *call = &tu->tp.call;
WARN_ON(call != trace_file->event_call);
if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE))
return;
if (trace_trigger_soft_disabled(trace_file))
return;
esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
size = esize + tu->tp.size + dsize;
event = trace_event_buffer_lock_reserve(&buffer, trace_file,
call->event.type, size, 0, 0);
if (!event)
return;
entry = ring_buffer_event_data(event);
if (is_ret_probe(tu)) {
entry->vaddr[0] = func;
entry->vaddr[1] = instruction_pointer(regs);
data = DATAOF_TRACE_ENTRY(entry, true);
} else {
entry->vaddr[0] = instruction_pointer(regs);
data = DATAOF_TRACE_ENTRY(entry, false);
}
memcpy(data, ucb->buf, tu->tp.size + dsize);
event_trigger_unlock_commit(trace_file, buffer, event, entry, 0, 0);
}
/* uprobe handler */
static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
struct uprobe_cpu_buffer *ucb, int dsize)
{
struct event_file_link *link;
if (is_ret_probe(tu))
return 0;
rcu_read_lock();
list_for_each_entry_rcu(link, &tu->tp.files, list)
__uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file);
rcu_read_unlock();
return 0;
}
static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
struct pt_regs *regs,
struct uprobe_cpu_buffer *ucb, int dsize)
{
struct event_file_link *link;
rcu_read_lock();
list_for_each_entry_rcu(link, &tu->tp.files, list)
__uprobe_trace_func(tu, func, regs, ucb, dsize, link->file);
rcu_read_unlock();
}
/* Event entry printers */
static enum print_line_t
print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event)
{
struct uprobe_trace_entry_head *entry;
struct trace_seq *s = &iter->seq;
struct trace_uprobe *tu;
u8 *data;
entry = (struct uprobe_trace_entry_head *)iter->ent;
tu = container_of(event, struct trace_uprobe, tp.call.event);
if (is_ret_probe(tu)) {
trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)",
trace_event_name(&tu->tp.call),
entry->vaddr[1], entry->vaddr[0]);
data = DATAOF_TRACE_ENTRY(entry, true);
} else {
trace_seq_printf(s, "%s: (0x%lx)",
trace_event_name(&tu->tp.call),
entry->vaddr[0]);
data = DATAOF_TRACE_ENTRY(entry, false);
}
if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0)
goto out;
trace_seq_putc(s, '\n');
out:
return trace_handle_return(s);
}
typedef bool (*filter_func_t)(struct uprobe_consumer *self,
enum uprobe_filter_ctx ctx,
struct mm_struct *mm);
static int
probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
filter_func_t filter)
{
bool enabled = trace_probe_is_enabled(&tu->tp);
struct event_file_link *link = NULL;
int ret;
if (file) {
if (tu->tp.flags & TP_FLAG_PROFILE)
return -EINTR;
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link)
return -ENOMEM;
link->file = file;
list_add_tail_rcu(&link->list, &tu->tp.files);
tu->tp.flags |= TP_FLAG_TRACE;
} else {
if (tu->tp.flags & TP_FLAG_TRACE)
return -EINTR;
tu->tp.flags |= TP_FLAG_PROFILE;
}
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
if (enabled)
return 0;
ret = uprobe_buffer_enable();
if (ret)
goto err_flags;
tu->consumer.filter = filter;
tu->inode = d_real_inode(tu->path.dentry);
if (tu->ref_ctr_offset) {
ret = uprobe_register_refctr(tu->inode, tu->offset,
tu->ref_ctr_offset, &tu->consumer);
} else {
ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
}
if (ret)
goto err_buffer;
return 0;
err_buffer:
uprobe_buffer_disable();
err_flags:
if (file) {
list_del(&link->list);
kfree(link);
tu->tp.flags &= ~TP_FLAG_TRACE;
} else {
tu->tp.flags &= ~TP_FLAG_PROFILE;
}
return ret;
}
static void
probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
{
if (!trace_probe_is_enabled(&tu->tp))
return;
if (file) {
struct event_file_link *link;
link = find_event_file_link(&tu->tp, file);
if (!link)
return;
list_del_rcu(&link->list);
/* synchronize with u{,ret}probe_trace_func */
synchronize_rcu();
kfree(link);