summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_kprobe.c
blob: c9b5aa10fbf9c582b38f21f76de5a83398f6bb4a (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
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
/*
 * Kprobes-based tracing events
 *
 * Created by Masami Hiramatsu <mhiramat@redhat.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
#define pr_fmt(fmt)	"trace_kprobe: " fmt

#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/rculist.h>

#include "trace_probe.h"

#define KPROBE_EVENT_SYSTEM "kprobes"
#define KRETPROBE_MAXACTIVE_MAX 4096

/**
 * Kprobe event core functions
 */
struct trace_kprobe {
	struct list_head	list;
	struct kretprobe	rp;	/* Use rp.kp for kprobe use */
	unsigned long __percpu *nhit;
	const char		*symbol;	/* symbol name */
	struct trace_probe	tp;
};

#define SIZEOF_TRACE_KPROBE(n)				\
	(offsetof(struct trace_kprobe, tp.args) +	\
	(sizeof(struct probe_arg) * (n)))


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(mod->name);
	const char *name = trace_kprobe_symbol(tk);
	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
}

static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
{
	return !!strchr(trace_kprobe_symbol(tk), ':');
}

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 int register_kprobe_event(struct trace_kprobe *tk);
static int unregister_kprobe_event(struct trace_kprobe *tk);

static DEFINE_MUTEX(probe_lock);
static LIST_HEAD(probe_list);

static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
				struct pt_regs *regs);

/* Memory fetching by symbol */
struct symbol_cache {
	char		*symbol;
	long		offset;
	unsigned long	addr;
};

unsigned long update_symbol_cache(struct symbol_cache *sc)
{
	sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);

	if (sc->addr)
		sc->addr += sc->offset;

	return sc->addr;
}

void free_symbol_cache(struct symbol_cache *sc)
{
	kfree(sc->symbol);
	kfree(sc);
}

struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
{
	struct symbol_cache *sc;

	if (!sym || strlen(sym) == 0)
		return NULL;

	sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
	if (!sc)
		return NULL;

	sc->symbol = kstrdup(sym, GFP_KERNEL);
	if (!sc->symbol) {
		kfree(sc);
		return NULL;
	}
	sc->offset = offset;
	update_symbol_cache(sc);

	return sc;
}

/*
 * Kprobes-specific fetch functions
 */
#define DEFINE_FETCH_stack(type)					\
static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,		\
					  void *offset, void *dest)	\
{									\
	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
				(unsigned int)((unsigned long)offset));	\
}									\
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type));

DEFINE_BASIC_FETCH_FUNCS(stack)
/* No string on the stack entry */
#define fetch_stack_string	NULL
#define fetch_stack_string_size	NULL

#define DEFINE_FETCH_memory(type)					\
static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,		\
					  void *addr, void *dest)	\
{									\
	type retval;							\
	if (probe_kernel_address(addr, retval))				\
		*(type *)dest = 0;					\
	else								\
		*(type *)dest = retval;					\
}									\
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type));

DEFINE_BASIC_FETCH_FUNCS(memory)
/*
 * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
 * length and relative data location.
 */
static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
					    void *addr, void *dest)
{
	int maxlen = get_rloc_len(*(u32 *)dest);
	u8 *dst = get_rloc_data(dest);
	long ret;

	if (!maxlen)
		return;

	/*
	 * Try to get string again, since the string can be changed while
	 * probing.
	 */
	ret = strncpy_from_unsafe(dst, addr, maxlen);

	if (ret < 0) {	/* Failed to fetch string */
		dst[0] = '\0';
		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
	} else {
		*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
	}
}
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string));

/* Return the length of string -- including null terminal byte */
static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
						 void *addr, void *dest)
{
	mm_segment_t old_fs;
	int ret, len = 0;
	u8 c;

	old_fs = get_fs();
	set_fs(KERNEL_DS);
	pagefault_disable();

	do {
		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
		len++;
	} while (c && ret == 0 && len < MAX_STRING_SIZE);

	pagefault_enable();
	set_fs(old_fs);

	if (ret < 0)	/* Failed to check the length */
		*(u32 *)dest = 0;
	else
		*(u32 *)dest = len;
}
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size));

#define DEFINE_FETCH_symbol(type)					\
void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\
{									\
	struct symbol_cache *sc = data;					\
	if (sc->addr)							\
		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
	else								\
		*(type *)dest = 0;					\
}									\
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type));

DEFINE_BASIC_FETCH_FUNCS(symbol)
DEFINE_FETCH_symbol(string)
DEFINE_FETCH_symbol(string_size)

/* kprobes don't support file_offset fetch methods */
#define fetch_file_offset_u8		NULL
#define fetch_file_offset_u16		NULL
#define fetch_file_offset_u32		NULL
#define fetch_file_offset_u64		NULL
#define fetch_file_offset_string	NULL
#define fetch_file_offset_string_size	NULL

/* Fetch type information table */
static const struct fetch_type kprobes_fetch_type_table[] = {
	/* Special types */
	[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
					sizeof(u32), 1, "__data_loc char[]"),
	[FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
					string_size, sizeof(u32), 0, "u32"),
	/* Basic types */
	ASSIGN_FETCH_TYPE(u8,  u8,  0),
	ASSIGN_FETCH_TYPE(u16, u16, 0),
	ASSIGN_FETCH_TYPE(u32, u32, 0),
	ASSIGN_FETCH_TYPE(u64, u64, 0),
	ASSIGN_FETCH_TYPE(s8,  u8,  1),
	ASSIGN_FETCH_TYPE(s16, u16, 1),
	ASSIGN_FETCH_TYPE(s32, u32, 1),
	ASSIGN_FETCH_TYPE(s64, u64, 1),
	ASSIGN_FETCH_TYPE_ALIAS(x8,  u8,  u8,  0),
	ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
	ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
	ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),

	ASSIGN_FETCH_TYPE_END
};

/*
 * 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(SIZEOF_TRACE_KPROBE(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;

	if (!event || !is_good_name(event)) {
		ret = -EINVAL;
		goto error;
	}

	tk->tp.call.class = &tk->tp.class;
	tk->tp.call.name = kstrdup(event, GFP_KERNEL);
	if (!tk->tp.call.name)
		goto error;

	if (!group || !is_good_name(group)) {
		ret = -EINVAL;
		goto error;
	}

	tk->tp.class.system = kstrdup(group, GFP_KERNEL);
	if (!tk->tp.class.system)
		goto error;

	INIT_LIST_HEAD(&tk->list);
	INIT_LIST_HEAD(&tk->tp.files);
	return tk;
error:
	kfree(tk->tp.call.name);
	kfree(tk->symbol);
	free_percpu(tk->nhit);
	kfree(tk);
	return ERR_PTR(ret);
}

static void free_trace_kprobe(struct trace_kprobe *tk)
{
	int i;

	for (i = 0; i < tk->tp.nr_args; i++)
		traceprobe_free_probe_arg(&tk->tp.args[i]);

	kfree(tk->tp.call.class->system);
	kfree(tk->tp.call.name);
	kfree(tk->symbol);
	free_percpu(tk->nhit);
	kfree(tk);
}

static struct trace_kprobe *find_trace_kprobe(const char *event,
					      const char *group)
{
	struct trace_kprobe *tk;

	list_for_each_entry(tk, &probe_list, list)
		if (strcmp(trace_event_name(&tk->tp.call), event) == 0 &&
		    strcmp(tk->tp.call.class->system, group) == 0)
			return tk;
	return NULL;
}

/*
 * Enable trace_probe
 * if the file is NULL, enable "perf" handler, or enable "trace" handler.
 */
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
	int ret = 0;

	if (file) {
		struct event_file_link *link;

		link = kmalloc(sizeof(*link), GFP_KERNEL);
		if (!link) {
			ret = -ENOMEM;
			goto out;
		}

		link->file = file;
		list_add_tail_rcu(&link->list, &tk->tp.files);

		tk->tp.flags |= TP_FLAG_TRACE;
	} else
		tk->tp.flags |= TP_FLAG_PROFILE;

	if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
		if (trace_kprobe_is_return(tk))
			ret = enable_kretprobe(&tk->rp);
		else
			ret = enable_kprobe(&tk->rp.kp);
	}
 out:
	return ret;
}

/*
 * Disable trace_probe
 * if the file is NULL, disable "perf" handler, or disable "trace" handler.
 */
static int
disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
	struct event_file_link *link = NULL;
	int wait = 0;
	int ret = 0;

	if (file) {
		link = find_event_file_link(&tk->tp, file);
		if (!link) {
			ret = -EINVAL;
			goto out;
		}

		list_del_rcu(&link->list);
		wait = 1;
		if (!list_empty(&tk->tp.files))
			goto out;

		tk->tp.flags &= ~TP_FLAG_TRACE;
	} else
		tk->tp.flags &= ~TP_FLAG_PROFILE;

	if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) {
		if (trace_kprobe_is_return(tk))
			disable_kretprobe(&tk->rp);
		else
			disable_kprobe(&tk->rp.kp);
		wait = 1;
	}
 out:
	if (wait) {
		/*
		 * Synchronize with kprobe_trace_func/kretprobe_trace_func
		 * to ensure disabled (all running handlers are finished).
		 * This is not only for kfree(), but also the caller,
		 * trace_remove_event_call() supposes it for releasing
		 * event_call related objects, which will be accessed in
		 * the kprobe_trace_func/kretprobe_trace_func.
		 */
		synchronize_sched();
		kfree(link);	/* Ignored if link == NULL */
	}

	return ret;
}

/* Internal register function - just handle k*probes and flags */
static int __register_trace_kprobe(struct trace_kprobe *tk)
{
	int i, ret;

	if (trace_probe_is_registered(&tk->tp))
		return -EINVAL;

	for (i = 0; i < tk->tp.nr_args; i++)
		traceprobe_update_arg(&tk->tp.args[i]);

	/* 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);

	if (ret == 0)
		tk->tp.flags |= TP_FLAG_REGISTERED;
	else {
		pr_warn("Could not insert probe at %s+%lu: %d\n",
			trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
		if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
			pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
			ret = 0;
		} else if (ret == -EILSEQ) {
			pr_warn("Probing address(0x%p) is not an instruction boundary.\n",
				tk->rp.kp.addr);
			ret = -EINVAL;
		}
	}

	return ret;
}

/* Internal unregister function - just handle k*probes and flags */
static void __unregister_trace_kprobe(struct trace_kprobe *tk)
{
	if (trace_probe_is_registered(&tk->tp)) {
		if (trace_kprobe_is_return(tk))
			unregister_kretprobe(&tk->rp);
		else
			unregister_kprobe(&tk->rp.kp);
		tk->tp.flags &= ~TP_FLAG_REGISTERED;
		/* Cleanup kprobe for reuse */
		if (tk->rp.kp.symbol_name)
			tk->rp.kp.addr = NULL;
	}
}

/* Unregister a trace_probe and probe_event: call with locking probe_lock */
static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
	/* Enabled event can not be unregistered */
	if (trace_probe_is_enabled(&tk->tp))
		return -EBUSY;

	/* Will fail if probe is being used by ftrace or perf */
	if (unregister_kprobe_event(tk))
		return -EBUSY;

	__unregister_trace_kprobe(tk);
	list_del(&tk->list);

	return 0;
}

/* 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(&probe_lock);

	/* Delete old (same name) event if exist */
	old_tk = find_trace_kprobe(trace_event_name(&tk->tp.call),
			tk->tp.call.class->system);
	if (old_tk) {
		ret = unregister_trace_kprobe(old_tk);
		if (ret < 0)
			goto end;
		free_trace_kprobe(old_tk);
	}

	/* Register new event */
	ret = register_kprobe_event(tk);
	if (ret) {
		pr_warn("Failed to register probe event(%d)\n", ret);
		goto end;
	}

	/* Register k*probe */
	ret = __register_trace_kprobe(tk);
	if (ret < 0)
		unregister_kprobe_event(tk);
	else
		list_add_tail(&tk->list, &probe_list);

end:
	mutex_unlock(&probe_lock);
	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 trace_kprobe *tk;
	int ret;

	if (val != MODULE_STATE_COMING)
		return NOTIFY_DONE;

	/* Update probes on coming module */
	mutex_lock(&probe_lock);
	list_for_each_entry(tk, &probe_list, list) {
		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_event_name(&tk->tp.call),
					mod->name, ret);
		}
	}
	mutex_unlock(&probe_lock);

	return NOTIFY_DONE;
}

static struct notifier_block trace_kprobe_module_nb = {
	.notifier_call = trace_kprobe_module_callback,
	.priority = 1	/* Invoked after kprobe module callback */
};

/* Convert certain expected symbols into '_' when generating event names */
static inline void sanitize_event_name(char *name)
{
	while (*name++ != '\0')
		if (*name == ':' || *name == '.')
			*name = '_';
}

static int create_trace_kprobe(int argc, char **argv)
{
	/*
	 * Argument syntax:
	 *  - Add kprobe:
	 *      p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
	 *  - Add kretprobe:
	 *      r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [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;
	int i, ret = 0;
	bool is_return = false, is_delete = false;
	char *symbol = NULL, *event = NULL, *group = NULL;
	int maxactive = 0;
	char *arg;
	unsigned long offset = 0;
	void *addr = NULL;
	char buf[MAX_EVENT_NAME_LEN];

	/* argc must be >= 1 */
	if (argv[0][0] == 'p')
		is_return = false;
	else if (argv[0][0] == 'r')
		is_return = true;
	else if (argv[0][0] == '-')
		is_delete = true;
	else {
		pr_info("Probe definition must be started with 'p', 'r' or"
			" '-'.\n");
		return -EINVAL;
	}

	event = strchr(&argv[0][1], ':');
	if (event) {
		event[0] = '\0';
		event++;
	}
	if (is_return && isdigit(argv[0][1])) {
		ret = kstrtouint(&argv[0][1], 0, &maxactive);
		if (ret) {
			pr_info("Failed to parse maxactive.\n");
			return ret;
		}
		/* kretprobes instances are iterated over via a list. The
		 * maximum should stay reasonable.
		 */
		if (maxactive > KRETPROBE_MAXACTIVE_MAX) {
			pr_info("Maxactive is too big (%d > %d).\n",
				maxactive, KRETPROBE_MAXACTIVE_MAX);
			return -E2BIG;
		}
	}

	if (event) {
		if (strchr(event, '/')) {
			group = event;
			event = strchr(group, '/') + 1;
			event[-1] = '\0';
			if (strlen(group) == 0) {
				pr_info("Group name is not specified\n");
				return -EINVAL;
			}
		}
		if (strlen(event) == 0) {
			pr_info("Event name is not specified\n");
			return -EINVAL;
		}
	}
	if (!group)
		group = KPROBE_EVENT_SYSTEM;

	if (is_delete) {
		if (!event) {
			pr_info("Delete command needs an event name.\n");
			return -EINVAL;
		}
		mutex_lock(&probe_lock);
		tk = find_trace_kprobe(event, group);
		if (!tk) {
			mutex_unlock(&probe_lock);
			pr_info("Event %s/%s doesn't exist.\n", group, event);
			return -ENOENT;
		}
		/* delete an event */
		ret = unregister_trace_kprobe(tk);
		if (ret == 0)
			free_trace_kprobe(tk);
		mutex_unlock(&probe_lock);
		return ret;
	}

	if (argc < 2) {
		pr_info("Probe point is not specified.\n");
		return -EINVAL;
	}

	/* try to parse an address. if that fails, try to read the
	 * input as a symbol. */
	if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
		/* a symbol specified */
		symbol = argv[1];
		/* TODO: support .init module functions */
		ret = traceprobe_split_symbol_offset(symbol, &offset);
		if (ret) {
			pr_info("Failed to parse either an address or a symbol.\n");
			return ret;
		}
		if (offset && is_return &&
		    !kprobe_on_func_entry(NULL, symbol, offset)) {
			pr_info("Given offset is not valid for return probe.\n");
			return -EINVAL;
		}
	}
	argc -= 2; argv += 2;

	/* setup a probe */
	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;
	}
	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
			       argc, is_return);
	if (IS_ERR(tk)) {
		pr_info("Failed to allocate trace_probe.(%d)\n",
			(int)PTR_ERR(tk));
		return PTR_ERR(tk);
	}

	/* parse arguments */
	ret = 0;
	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
		struct probe_arg *parg = &tk->tp.args[i];

		/* Increment count for freeing args in error case */
		tk->tp.nr_args++;

		/* Parse argument name */
		arg = strchr(argv[i], '=');
		if (arg) {
			*arg++ = '\0';
			parg->name = kstrdup(argv[i], GFP_KERNEL);
		} else {
			arg = argv[i];
			/* If argument name is omitted, set "argN" */
			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
			parg->name = kstrdup(buf, GFP_KERNEL);
		}

		if (!parg->name) {
			pr_info("Failed to allocate argument[%d] name.\n", i);
			ret = -ENOMEM;
			goto error;
		}

		if (!is_good_name(parg->name)) {
			pr_info("Invalid argument[%d] name: %s\n",
				i, parg->name);
			ret = -EINVAL;
			goto error;
		}

		if (traceprobe_conflict_field_name(parg->name,
							tk->tp.args, i)) {
			pr_info("Argument[%d] name '%s' conflicts with "
				"another field.\n", i, argv[i]);
			ret = -EINVAL;
			goto error;
		}

		/* Parse fetch argument */
		ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
						is_return, true,
						kprobes_fetch_type_table);
		if (ret) {
			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
			goto error;
		}
	}

	ret = register_trace_kprobe(tk);
	if (ret)
		goto error;
	return 0;

error:
	free_trace_kprobe(tk);
	return ret;
}

static int release_all_trace_kprobes(void)
{
	struct trace_kprobe *tk;
	int ret = 0;

	mutex_lock(&probe_lock);
	/* Ensure no probe is in use. */
	list_for_each_entry(tk, &probe_list, list)
		if (trace_probe_is_enabled(&tk->tp)) {
			ret = -EBUSY;
			goto end;
		}
	/* TODO: Use batch unregistration */
	while (!list_empty(&probe_list)) {
		tk = list_entry(probe_list.next, struct trace_kprobe, list);
		ret = unregister_trace_kprobe(tk);
		if (ret)
			goto end;
		free_trace_kprobe(tk);
	}

end:
	mutex_unlock(&probe_lock);

	return ret;
}

/* Probes listing interfaces */
static void *probes_seq_start(struct seq_file *m, loff_t *pos)
{
	mutex_lock(&probe_lock);
	return seq_list_start(&probe_list, *pos);
}

static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
	return seq_list_next(v, &probe_list, pos);
}

static void probes_seq_stop(struct seq_file *m, void *v)
{
	mutex_unlock(&probe_lock);
}

static int probes_seq_show(struct seq_file *m, void *v)
{
	struct trace_kprobe *tk = v;
	int i;

	seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p');
	seq_printf(m, ":%s/%s", tk->tp.call.class->system,
			trace_event_name(&tk->tp.call));

	if (!tk->symbol)
		seq_printf(m, " 0x%p", tk->rp.kp.addr);
	else if (tk->rp.kp.offset)
		seq_printf(m, " %s+%u", trace_kprobe_symbol(tk),
			   tk->rp.kp.offset);
	else
		seq_printf(m, " %s", trace_kprobe_symbol(tk));

	for (i = 0; i < tk->tp.nr_args; i++)
		seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm);
	seq_putc(m, '\n');

	return 0;
}

static const struct seq_operations probes_seq_op = {
	.start  = probes_seq_start,
	.next   = probes_seq_next,
	.stop   = probes_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 = release_all_trace_kprobes();
		if (ret < 0)
			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 traceprobe_probes_write(file, buffer, count, ppos,
			create_trace_kprobe);
}

static const struct file_operations kprobe_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 trace_kprobe *tk = v;

	seq_printf(m, "  %-44s %15lu %15lu\n",
		   trace_event_name(&tk->tp.call),
		   trace_kprobe_nhit(tk),
		   tk->rp.kp.nmissed);

	return 0;
}

static const struct seq_operations profile_seq_op = {
	.start  = probes_seq_start,
	.next   = probes_seq_next,
	.stop   = probes_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 kprobe_profile_ops = {
	.owner          = THIS_MODULE,
	.open           = profile_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = seq_release,
};

/* Kprobe handler */
static nokprobe_inline void
__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
		    struct trace_event_file *trace_file)
{
	struct kprobe_trace_entry_head *entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	int size, dsize, pc;
	unsigned long irq_flags;
	struct trace_event_call *call = &tk->tp.call;

	WARN_ON(call != trace_file->event_call);

	if (trace_trigger_soft_disabled(trace_file))
		return;

	local_save_flags(irq_flags);
	pc = preempt_count();

	dsize = __get_data_size(&tk->tp, regs);
	size = sizeof(*entry) + tk->tp.size + dsize;

	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
						call->event.type,
						size, irq_flags, pc);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->ip = (unsigned long)tk->rp.kp.addr;
	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);

	event_trigger_unlock_commit_regs(trace_file, buffer, event,
					 entry, irq_flags, pc, regs);
}

static void
kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
	struct event_file_link *link;

	list_for_each_entry_rcu(link, &tk->tp.files, list)
		__kprobe_trace_func(tk, regs, link->file);
}
NOKPROBE_SYMBOL(kprobe_trace_func);

/* Kretprobe handler */
static nokprobe_inline void
__kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
		       struct pt_regs *regs,
		       struct trace_event_file *trace_file)
{
	struct kretprobe_trace_entry_head *entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	int size, pc, dsize;
	unsigned long irq_flags;
	struct trace_event_call *call = &tk->tp.call;

	WARN_ON(call != trace_file->event_call);

	if (trace_trigger_soft_disabled(trace_file))
		return;

	local_save_flags(irq_flags);
	pc = preempt_count();

	dsize = __get_data_size(&tk->tp, regs);
	size = sizeof(*entry) + tk->tp.size + dsize;

	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
						call->event.type,
						size, irq_flags, pc);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->func = (unsigned long)tk->rp.kp.addr;
	entry->ret_ip = (unsigned long)ri->ret_addr;
	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);

	event_trigger_unlock_commit_regs(trace_file, buffer, event,
					 entry, irq_flags, pc, regs);
}

static void
kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
		     struct pt_regs *regs)
{
	struct event_file_link *link;

	list_for_each_entry_rcu(link, &tk->tp.files, list)
		__kretprobe_trace_func(tk, ri, regs, link->file);
}
NOKPROBE_SYMBOL(kretprobe_trace_func);

/* Event entry printers */
static enum print_line_t
print_kprobe_event(struct trace_iterator *iter, int flags,
		   struct trace_event *event)
{
	struct kprobe_trace_entry_head *field;
	struct trace_seq *s = &iter->seq;
	struct trace_probe *tp;
	u8 *data;
	int i;

	field = (struct kprobe_trace_entry_head *)iter->ent;
	tp = container_of(event, struct trace_probe, call.event);

	trace_seq_printf(s, "%s: (", trace_event_name(&tp->call));

	if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
		goto out;

	trace_seq_putc(s, ')');

	data = (u8 *)&field[1];
	for (i = 0; i < tp->nr_args; i++)
		if (!tp->args[i].type->print(s, tp->args[i].name,
					     data + tp->args[i].offset, field))
			goto out;

	trace_seq_putc(s, '\n');
 out:
	return trace_handle_return(s);
}

static enum print_line_t
print_kretprobe_event(struct trace_iterator *iter, int flags,
		      struct trace_event *event)
{
	struct kretprobe_trace_entry_head *field;
	struct trace_seq *s = &iter->seq;
	struct trace_probe *tp;
	u8 *data;
	int i;

	field = (struct kretprobe_trace_entry_head *)iter->ent;
	tp = container_of(event, struct trace_probe, call.event);

	trace_seq_printf(s, "%s: (", trace_event_name(&tp->call));

	if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
		goto out;

	trace_seq_puts(s, " <- ");

	if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
		goto out;

	trace_seq_putc(s, ')');

	data = (u8 *)&field[1];
	for (i = 0; i < tp->nr_args; i++)
		if (!tp->args[i].type->print(s, tp->args[i].name,
					     data + tp->args[i].offset, field))
			goto out;

	trace_seq_putc(s, '\n');

 out:
	return trace_handle_return(s);
}


static int kprobe_event_define_fields(struct trace_event_call *event_call)
{
	int ret, i;
	struct kprobe_trace_entry_head field;
	struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;

	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
	/* Set argument names as fields */
	for (i = 0; i < tk->tp.nr_args; i++) {
		struct probe_arg *parg = &tk->tp.args[i];

		ret = trace_define_field(event_call, parg->type->fmttype,
					 parg->name,
					 sizeof(field) + parg->offset,
					 parg->type->size,
					 parg->type->is_signed,
					 FILTER_OTHER);
		if (ret)
			return ret;
	}
	return 0;
}

static int kretprobe_event_define_fields(struct trace_event_call *event_call)
{
	int ret, i;
	struct kretprobe_trace_entry_head field;
	struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;

	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
	/* Set argument names as fields */
	for (i = 0; i < tk->tp.nr_args; i++) {
		struct probe_arg *parg = &tk->tp.args[i];

		ret = trace_define_field(event_call, parg->type->fmttype,
					 parg->name,
					 sizeof(field) + parg->offset,
					 parg->type->size,
					 parg->type->is_signed,
					 FILTER_OTHER);
		if (ret)
			return ret;
	}
	return 0;
}

#ifdef CONFIG_PERF_EVENTS

/* Kprobe profile handler */
static void
kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
	struct trace_event_call *call = &tk->tp.call;
	struct bpf_prog *prog = call->prog;
	struct kprobe_trace_entry_head *entry;
	struct hlist_head *head;
	int size, __size, dsize;
	int rctx;

	if (prog && !trace_call_bpf(prog, regs))
		return;

	head = this_cpu_ptr(call->perf_events);
	if (hlist_empty(head))
		return;

	dsize = __get_data_size(&tk->tp, regs);
	__size = sizeof(*entry) + tk->tp.size + dsize;
	size = ALIGN(__size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);

	entry = perf_trace_buf_alloc(size, NULL, &rctx);
	if (!entry)
		return;

	entry->ip = (unsigned long)tk->rp.kp.addr;
	memset(&entry[1], 0, dsize);
	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
			      head, NULL);
}
NOKPROBE_SYMBOL(kprobe_perf_func);

/* Kretprobe profile handler */
static void
kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
		    struct pt_regs *regs)
{
	struct trace_event_call *call = &tk->tp.call;
	struct bpf_prog *prog = call->prog;
	struct kretprobe_trace_entry_head *entry;
	struct hlist_head *head;
	int size, __size, dsize;
	int rctx;

	if (prog && !trace_call_bpf(prog, regs))
		return;

	head = this_cpu_ptr(call->perf_events);
	if (hlist_empty(head))
		return;

	dsize = __get_data_size(&tk->tp, regs);
	__size = sizeof(*entry) + tk->tp.size + dsize;
	size = ALIGN(__size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);

	entry = perf_trace_buf_alloc(size, NULL, &rctx);
	if (!entry)
		return;

	entry->func = (unsigned long)tk->rp.kp.addr;
	entry->ret_ip = (unsigned long)ri->ret_addr;
	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
			      head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);
#endif	/* CONFIG_PERF_EVENTS */

/*
 * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex.
 *
 * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe
 * lockless, but we can't race with this __init function.
 */
static int kprobe_register(struct trace_event_call *event,
			   enum trace_reg type, void *data)
{
	struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
	struct trace_event_file *file = data;

	switch (type) {
	case TRACE_REG_REGISTER:
		return enable_trace_kprobe(tk, file);
	case TRACE_REG_UNREGISTER:
		return disable_trace_kprobe(tk, file);

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return enable_trace_kprobe(tk, NULL);
	case TRACE_REG_PERF_UNREGISTER:
		return disable_trace_kprobe(tk, NULL);
	case TRACE_REG_PERF_OPEN:
	case TRACE_REG_PERF_CLOSE:
	case TRACE_REG_PERF_ADD:
	case TRACE_REG_PERF_DEL:
		return 0;
#endif
	}
	return 0;
}

static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);

	raw_cpu_inc(*tk->nhit);

	if (tk->tp.flags & TP_FLAG_TRACE)
		kprobe_trace_func(tk, regs);
#ifdef CONFIG_PERF_EVENTS
	if (tk->tp.flags & TP_FLAG_PROFILE)
		kprobe_perf_func(tk, regs);
#endif
	return 0;	/* We don't tweek kernel, so just return 0 */
}
NOKPROBE_SYMBOL(kprobe_dispatcher);

static int
kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
	struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);

	raw_cpu_inc(*tk->nhit);

	if (tk->tp.flags & TP_FLAG_TRACE)
		kretprobe_trace_func(tk, ri, regs);
#ifdef CONFIG_PERF_EVENTS
	if (tk->tp.flags & TP_FLAG_PROFILE)
		kretprobe_perf_func(tk, ri, regs);
#endif
	return 0;	/* We don't tweek kernel, so just return 0 */
}
NOKPROBE_SYMBOL(kretprobe_dispatcher);

static struct trace_event_functions kretprobe_funcs = {
	.trace		= print_kretprobe_event
};

static struct trace_event_functions kprobe_funcs = {
	.trace		= print_kprobe_event
};

static int register_kprobe_event(struct trace_kprobe *tk)
{
	struct trace_event_call *call = &tk->tp.call;
	int ret;

	/* Initialize trace_event_call */
	INIT_LIST_HEAD(&call->class->fields);
	if (trace_kprobe_is_return(tk)) {
		call->event.funcs = &kretprobe_funcs;
		call->class->define_fields = kretprobe_event_define_fields;
	} else {
		call->event.funcs = &kprobe_funcs;
		call->class->define_fields = kprobe_event_define_fields;
	}
	if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
		return -ENOMEM;
	ret = register_trace_event(&call->event);
	if (!ret) {
		kfree(call->print_fmt);
		return -ENODEV;
	}
	call->flags = TRACE_EVENT_FL_KPROBE;
	call->class->reg = kprobe_register;
	call->data = tk;
	ret = trace_add_event_call(call);
	if (ret) {
		pr_info("Failed to register kprobe event: %s\n",
			trace_event_name(call));
		kfree(call->print_fmt);
		unregister_trace_event(&call->event);
	}
	return ret;
}

static int unregister_kprobe_event(struct trace_kprobe *tk)
{
	int ret;

	/* tp->event is unregistered in trace_remove_event_call() */
	ret = trace_remove_event_call(&tk->tp.call);
	if (!ret)
		kfree(tk->tp.call.print_fmt);
	return ret;
}

/* Make a tracefs interface for controlling probe points */
static __init int init_kprobe_trace(void)
{
	struct dentry *d_tracer;
	struct dentry *entry;

	if (register_module_notifier(&trace_kprobe_module_nb))
		return -EINVAL;

	d_tracer = tracing_init_dentry();
	if (IS_ERR(d_tracer))
		return 0;

	entry = tracefs_create_file("kprobe_events", 0644, d_tracer,
				    NULL, &kprobe_events_ops);

	/* Event list interface */
	if (!entry)
		pr_warn("Could not create tracefs 'kprobe_events' entry\n");

	/* Profile interface */
	entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
				    NULL, &kprobe_profile_ops);

	if (!entry)
		pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
	return 0;
}
fs_initcall(init_kprobe_trace);


#ifdef CONFIG_FTRACE_STARTUP_TEST
/*
 * The "__used" keeps gcc from removing the function symbol
 * from the kallsyms table. 'noinline' makes sure that there
 * isn't an inlined version used by the test method below
 */
static __used __init noinline int
kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
{
	return a1 + a2 + a3 + a4 + a5 + a6;
}

static __init struct trace_event_file *
find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
	struct trace_event_file *file;

	list_for_each_entry(file, &tr->events, list)
		if (file->event_call == &tk->tp.call)
			return file;

	return NULL;
}

/*
 * Nobody but us can call enable_trace_kprobe/disable_trace_kprobe at this
 * stage, we can do this lockless.
 */
static __init int kprobe_trace_self_tests_init(void)
{
	int ret, warn = 0;
	int (*target)(int, int, int, int, int, int);
	struct trace_kprobe *tk;
	struct trace_event_file *file;

	if (tracing_is_disabled())
		return -ENODEV;

	target = kprobe_trace_selftest_target;

	pr_info("Testing kprobe tracing: ");

	ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
				  "$stack $stack0 +0($stack)",
				  create_trace_kprobe);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error on probing function entry.\n");
		warn++;
	} else {
		/* Enable trace point */
		tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
		if (WARN_ON_ONCE(tk == NULL)) {
			pr_warn("error on getting new probe.\n");
			warn++;
		} else {
			file = find_trace_probe_file(tk, top_trace_array());
			if (WARN_ON_ONCE(file == NULL)) {
				pr_warn("error on getting probe file.\n");
				warn++;
			} else
				enable_trace_kprobe(tk, file);
		}
	}

	ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
				  "$retval", create_trace_kprobe);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error on probing function return.\n");
		warn++;
	} else {
		/* Enable trace point */
		tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
		if (WARN_ON_ONCE(tk == NULL)) {
			pr_warn("error on getting 2nd new probe.\n");
			warn++;
		} else {
			file = find_trace_probe_file(tk, top_trace_array());
			if (WARN_ON_ONCE(file == NULL)) {
				pr_warn("error on getting probe file.\n");
				warn++;
			} else
				enable_trace_kprobe(tk, file);
		}
	}

	if (warn)
		goto end;

	ret = target(1, 2, 3, 4, 5, 6);

	/*
	 * Not expecting an error here, the check is only to prevent the
	 * optimizer from removing the call to target() as otherwise there
	 * are no side-effects and the call is never performed.
	 */
	if (ret != 21)
		warn++;

	/* Disable trace points before removing it */
	tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
	if (WARN_ON_ONCE(tk == NULL)) {
		pr_warn("error on getting test probe.\n");
		warn++;
	} else {
		if (trace_kprobe_nhit(tk) != 1) {
			pr_warn("incorrect number of testprobe hits\n");
			warn++;
		}

		file = find_trace_probe_file(tk, top_trace_array());
		if (WARN_ON_ONCE(file == NULL)) {
			pr_warn("error on getting probe file.\n");
			warn++;
		} else
			disable_trace_kprobe(tk, file);
	}

	tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
	if (WARN_ON_ONCE(tk == NULL)) {
		pr_warn("error on getting 2nd test probe.\n");
		warn++;
	} else {
		if (trace_kprobe_nhit(tk) != 1) {
			pr_warn("incorrect number of testprobe2 hits\n");
			warn++;
		}

		file = find_trace_probe_file(tk, top_trace_array());
		if (WARN_ON_ONCE(file == NULL)) {
			pr_warn("error on getting probe file.\n");
			warn++;
		} else
			disable_trace_kprobe(tk, file);
	}

	ret = traceprobe_command("-:testprobe", create_trace_kprobe);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error on deleting a probe.\n");
		warn++;
	}

	ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error on deleting a probe.\n");
		warn++;
	}

end:
	release_all_trace_kprobes();
	/*
	 * Wait for the optimizer work to finish. Otherwise it might fiddle
	 * with probes in already freed __init text.
	 */
	wait_for_kprobe_optimizer();
	if (warn)
		pr_cont("NG: Some tests are failed. Please check them.\n");
	else
		pr_cont("OK\n");
	return 0;
}

late_initcall(kprobe_trace_self_tests_init);

#endif
OpenPOWER on IntegriCloud