aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_kprobe.c
blob: 375f81a568dc267cfc847009418c056cfb24469f (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
/*
 * 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
 */

#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/debugfs.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/ptrace.h>
#include <linux/perf_event.h>

#include "trace.h"
#include "trace_output.h"

#define MAX_TRACE_ARGS 128
#define MAX_ARGSTR_LEN 63
#define MAX_EVENT_NAME_LEN 64
#define KPROBE_EVENT_SYSTEM "kprobes"

/* Reserved field names */
#define FIELD_STRING_IP "__probe_ip"
#define FIELD_STRING_NARGS "__probe_nargs"
#define FIELD_STRING_RETIP "__probe_ret_ip"
#define FIELD_STRING_FUNC "__probe_func"

const char *reserved_field_names[] = {
	"common_type",
	"common_flags",
	"common_preempt_count",
	"common_pid",
	"common_tgid",
	"common_lock_depth",
	FIELD_STRING_IP,
	FIELD_STRING_NARGS,
	FIELD_STRING_RETIP,
	FIELD_STRING_FUNC,
};

struct fetch_func {
	unsigned long (*func)(struct pt_regs *, void *);
	void *data;
};

static __kprobes unsigned long call_fetch(struct fetch_func *f,
					  struct pt_regs *regs)
{
	return f->func(regs, f->data);
}

/* fetch handlers */
static __kprobes unsigned long fetch_register(struct pt_regs *regs,
					      void *offset)
{
	return regs_get_register(regs, (unsigned int)((unsigned long)offset));
}

static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
					   void *num)
{
	return regs_get_kernel_stack_nth(regs,
					 (unsigned int)((unsigned long)num));
}

static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
{
	unsigned long retval;

	if (probe_kernel_address(addr, retval))
		return 0;
	return retval;
}

static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
{
	return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
}

static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
					      void *dummy)
{
	return regs_return_value(regs);
}

static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
						   void *dummy)
{
	return kernel_stack_pointer(regs);
}

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

static 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;
}

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

static 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;
}

static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
{
	struct symbol_cache *sc = data;

	if (sc->addr)
		return fetch_memory(regs, (void *)sc->addr);
	else
		return 0;
}

/* Special indirect memory access interface */
struct indirect_fetch_data {
	struct fetch_func orig;
	long offset;
};

static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
{
	struct indirect_fetch_data *ind = data;
	unsigned long addr;

	addr = call_fetch(&ind->orig, regs);
	if (addr) {
		addr += ind->offset;
		return fetch_memory(regs, (void *)addr);
	} else
		return 0;
}

static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
{
	if (data->orig.func == fetch_indirect)
		free_indirect_fetch_data(data->orig.data);
	else if (data->orig.func == fetch_symbol)
		free_symbol_cache(data->orig.data);
	kfree(data);
}

/**
 * Kprobe event core functions
 */

struct probe_arg {
	struct fetch_func	fetch;
	const char		*name;
};

/* Flags for trace_probe */
#define TP_FLAG_TRACE	1
#define TP_FLAG_PROFILE	2

struct trace_probe {
	struct list_head	list;
	struct kretprobe	rp;	/* Use rp.kp for kprobe use */
	unsigned long 		nhit;
	unsigned int		flags;	/* For TP_FLAG_* */
	const char		*symbol;	/* symbol name */
	struct ftrace_event_call	call;
	struct trace_event		event;
	unsigned int		nr_args;
	struct probe_arg	args[];
};

#define SIZEOF_TRACE_PROBE(n)			\
	(offsetof(struct trace_probe, args) +	\
	(sizeof(struct probe_arg) * (n)))

static __kprobes int probe_is_return(struct trace_probe *tp)
{
	return tp->rp.handler != NULL;
}

static __kprobes const char *probe_symbol(struct trace_probe *tp)
{
	return tp->symbol ? tp->symbol : "unknown";
}

static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
{
	int ret = -EINVAL;

	if (ff->func == fetch_argument)
		ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
	else if (ff->func == fetch_register) {
		const char *name;
		name = regs_query_register_name((unsigned int)((long)ff->data));
		ret = snprintf(buf, n, "%%%s", name);
	} else if (ff->func == fetch_stack)
		ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
	else if (ff->func == fetch_memory)
		ret = snprintf(buf, n, "@0x%p", ff->data);
	else if (ff->func == fetch_symbol) {
		struct symbol_cache *sc = ff->data;
		if (sc->offset)
			ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
					sc->offset);
		else
			ret = snprintf(buf, n, "@%s", sc->symbol);
	} else if (ff->func == fetch_retvalue)
		ret = snprintf(buf, n, "$retval");
	else if (ff->func == fetch_stack_address)
		ret = snprintf(buf, n, "$stack");
	else if (ff->func == fetch_indirect) {
		struct indirect_fetch_data *id = ff->data;
		size_t l = 0;
		ret = snprintf(buf, n, "%+ld(", id->offset);
		if (ret >= n)
			goto end;
		l += ret;
		ret = probe_arg_string(buf + l, n - l, &id->orig);
		if (ret < 0)
			goto end;
		l += ret;
		ret = snprintf(buf + l, n - l, ")");
		ret += l;
	}
end:
	if (ret >= n)
		return -ENOSPC;
	return ret;
}

static int register_probe_event(struct trace_probe *tp);
static void unregister_probe_event(struct trace_probe *tp);

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);

/* Check the name is good for event/group */
static int check_event_name(const char *name)
{
	if (!isalpha(*name) && *name != '_')
		return 0;
	while (*++name != '\0') {
		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
			return 0;
	}
	return 1;
}

/*
 * Allocate new trace_probe and initialize it (including kprobes).
 */
static struct trace_probe *alloc_trace_probe(const char *group,
					     const char *event,
					     void *addr,
					     const char *symbol,
					     unsigned long offs,
					     int nargs, int is_return)
{
	struct trace_probe *tp;
	int ret = -ENOMEM;

	tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
	if (!tp)
		return ERR_PTR(ret);

	if (symbol) {
		tp->symbol = kstrdup(symbol, GFP_KERNEL);
		if (!tp->symbol)
			goto error;
		tp->rp.kp.symbol_name = tp->symbol;
		tp->rp.kp.offset = offs;
	} else
		tp->rp.kp.addr = addr;

	if (is_return)
		tp->rp.handler = kretprobe_dispatcher;
	else
		tp->rp.kp.pre_handler = kprobe_dispatcher;

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

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

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

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

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

static void free_probe_arg(struct probe_arg *arg)
{
	if (arg->fetch.func == fetch_symbol)
		free_symbol_cache(arg->fetch.data);
	else if (arg->fetch.func == fetch_indirect)
		free_indirect_fetch_data(arg->fetch.data);
	kfree(arg->name);
}

static void free_trace_probe(struct trace_probe *tp)
{
	int i;

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

	kfree(tp->call.system);
	kfree(tp->call.name);
	kfree(tp->symbol);
	kfree(tp);
}

static struct trace_probe *find_probe_event(const char *event,
					    const char *group)
{
	struct trace_probe *tp;

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

/* Unregister a trace_probe and probe_event: call with locking probe_lock */
static void unregister_trace_probe(struct trace_probe *tp)
{
	if (probe_is_return(tp))
		unregister_kretprobe(&tp->rp);
	else
		unregister_kprobe(&tp->rp.kp);
	list_del(&tp->list);
	unregister_probe_event(tp);
}

/* Register a trace_probe and probe_event */
static int register_trace_probe(struct trace_probe *tp)
{
	struct trace_probe *old_tp;
	int ret;

	mutex_lock(&probe_lock);

	/* register as an event */
	old_tp = find_probe_event(tp->call.name, tp->call.system);
	if (old_tp) {
		/* delete old event */
		unregister_trace_probe(old_tp);
		free_trace_probe(old_tp);
	}
	ret = register_probe_event(tp);
	if (ret) {
		pr_warning("Faild to register probe event(%d)\n", ret);
		goto end;
	}

	tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
	if (probe_is_return(tp))
		ret = register_kretprobe(&tp->rp);
	else
		ret = register_kprobe(&tp->rp.kp);

	if (ret) {
		pr_warning("Could not insert probe(%d)\n", ret);
		if (ret == -EILSEQ) {
			pr_warning("Probing address(0x%p) is not an "
				   "instruction boundary.\n",
				   tp->rp.kp.addr);
			ret = -EINVAL;
		}
		unregister_probe_event(tp);
	} else
		list_add_tail(&tp->list, &probe_list);
end:
	mutex_unlock(&probe_lock);
	return ret;
}

/* Split symbol and offset. */
static int split_symbol_offset(char *symbol, unsigned long *offset)
{
	char *tmp;
	int ret;

	if (!offset)
		return -EINVAL;

	tmp = strchr(symbol, '+');
	if (tmp) {
		/* skip sign because strict_strtol doesn't accept '+' */
		ret = strict_strtoul(tmp + 1, 0, offset);
		if (ret)
			return ret;
		*tmp = '\0';
	} else
		*offset = 0;
	return 0;
}

#define PARAM_MAX_ARGS 16
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))

static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
{
	int ret = 0;
	unsigned long param;

	if (strcmp(arg, "retval") == 0) {
		if (is_return) {
			ff->func = fetch_retvalue;
			ff->data = NULL;
		} else
			ret = -EINVAL;
	} else if (strncmp(arg, "stack", 5) == 0) {
		if (arg[5] == '\0') {
			ff->func = fetch_stack_address;
			ff->data = NULL;
		} else if (isdigit(arg[5])) {
			ret = strict_strtoul(arg + 5, 10, &param);
			if (ret || param > PARAM_MAX_STACK)
				ret = -EINVAL;
			else {
				ff->func = fetch_stack;
				ff->data = (void *)param;
			}
		} else
			ret = -EINVAL;
	} else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
		ret = strict_strtoul(arg + 3, 10, &param);
		if (ret || param > PARAM_MAX_ARGS)
			ret = -EINVAL;
		else {
			ff->func = fetch_argument;
			ff->data = (void *)param;
		}
	} else
		ret = -EINVAL;
	return ret;
}

/* Recursive argument parser */
static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
{
	int ret = 0;
	unsigned long param;
	long offset;
	char *tmp;

	switch (arg[0]) {
	case '$':
		ret = parse_probe_vars(arg + 1, ff, is_return);
		break;
	case '%':	/* named register */
		ret = regs_query_register_offset(arg + 1);
		if (ret >= 0) {
			ff->func = fetch_register;
			ff->data = (void *)(unsigned long)ret;
			ret = 0;
		}
		break;
	case '@':	/* memory or symbol */
		if (isdigit(arg[1])) {
			ret = strict_strtoul(arg + 1, 0, &param);
			if (ret)
				break;
			ff->func = fetch_memory;
			ff->data = (void *)param;
		} else {
			ret = split_symbol_offset(arg + 1, &offset);
			if (ret)
				break;
			ff->data = alloc_symbol_cache(arg + 1, offset);
			if (ff->data)
				ff->func = fetch_symbol;
			else
				ret = -EINVAL;
		}
		break;
	case '+':	/* indirect memory */
	case '-':
		tmp = strchr(arg, '(');
		if (!tmp) {
			ret = -EINVAL;
			break;
		}
		*tmp = '\0';
		ret = strict_strtol(arg + 1, 0, &offset);
		if (ret)
			break;
		if (arg[0] == '-')
			offset = -offset;
		arg = tmp + 1;
		tmp = strrchr(arg, ')');
		if (tmp) {
			struct indirect_fetch_data *id;
			*tmp = '\0';
			id = kzalloc(sizeof(struct indirect_fetch_data),
				     GFP_KERNEL);
			if (!id)
				return -ENOMEM;
			id->offset = offset;
			ret = __parse_probe_arg(arg, &id->orig, is_return);
			if (ret)
				kfree(id);
			else {
				ff->func = fetch_indirect;
				ff->data = (void *)id;
			}
		} else
			ret = -EINVAL;
		break;
	default:
		/* TODO: support custom handler */
		ret = -EINVAL;
	}
	return ret;
}

/* String length checking wrapper */
static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
{
	if (strlen(arg) > MAX_ARGSTR_LEN) {
		pr_info("Argument is too long.: %s\n",  arg);
		return -ENOSPC;
	}
	return __parse_probe_arg(arg, ff, is_return);
}

/* Return 1 if name is reserved or already used by another argument */
static int conflict_field_name(const char *name,
			       struct probe_arg *args, int narg)
{
	int i;
	for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
		if (strcmp(reserved_field_names[i], name) == 0)
			return 1;
	for (i = 0; i < narg; i++)
		if (strcmp(args[i].name, name) == 0)
			return 1;
	return 0;
}

static int create_trace_probe(int argc, char **argv)
{
	/*
	 * Argument syntax:
	 *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
	 *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
	 * Fetch args:
	 *  $argN	: fetch Nth of function argument. (N:0-)
	 *  $retval	: fetch return value
	 *  $stack	: fetch stack address
	 *  $stackN	: fetch Nth of stack (N:0-)
	 *  @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
	 * Indirect memory fetch:
	 *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
	 * Alias name of args:
	 *  NAME=FETCHARG : set NAME as alias of FETCHARG.
	 */
	struct trace_probe *tp;
	int i, ret = 0;
	int is_return = 0, is_delete = 0;
	char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
	unsigned long offset = 0;
	void *addr = NULL;
	char buf[MAX_EVENT_NAME_LEN];

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

	if (argv[0][1] == ':') {
		event = &argv[0][2];
		if (strchr(event, '/')) {
			group = event;
			event = strchr(group, '/') + 1;
			event[-1] = '\0';
			if (strlen(group) == 0) {
				pr_info("Group name is not specifiled\n");
				return -EINVAL;
			}
		}
		if (strlen(event) == 0) {
			pr_info("Event name is not specifiled\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;
		}
		tp = find_probe_event(event, group);
		if (!tp) {
			pr_info("Event %s/%s doesn't exist.\n", group, event);
			return -ENOENT;
		}
		/* delete an event */
		unregister_trace_probe(tp);
		free_trace_probe(tp);
		return 0;
	}

	if (argc < 2) {
		pr_info("Probe point is not specified.\n");
		return -EINVAL;
	}
	if (isdigit(argv[1][0])) {
		if (is_return) {
			pr_info("Return probe point must be a symbol.\n");
			return -EINVAL;
		}
		/* an address specified */
		ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
		if (ret) {
			pr_info("Failed to parse address.\n");
			return ret;
		}
	} else {
		/* a symbol specified */
		symbol = argv[1];
		/* TODO: support .init module functions */
		ret = split_symbol_offset(symbol, &offset);
		if (ret) {
			pr_info("Failed to parse symbol.\n");
			return ret;
		}
		if (offset && is_return) {
			pr_info("Return probe must be used without offset.\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);
		event = buf;
	}
	tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
			       is_return);
	if (IS_ERR(tp)) {
		pr_info("Failed to allocate trace_probe.(%d)\n",
			(int)PTR_ERR(tp));
		return PTR_ERR(tp);
	}

	/* parse arguments */
	ret = 0;
	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
		/* Parse argument name */
		arg = strchr(argv[i], '=');
		if (arg)
			*arg++ = '\0';
		else
			arg = argv[i];

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

		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
		if (!tp->args[i].name) {
			pr_info("Failed to allocate argument%d name '%s'.\n",
				i, argv[i]);
			ret = -ENOMEM;
			goto error;
		}

		/* Parse fetch argument */
		ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
		if (ret) {
			pr_info("Parse error at argument%d. (%d)\n", i, ret);
			kfree(tp->args[i].name);
			goto error;
		}

		tp->nr_args++;
	}

	ret = register_trace_probe(tp);
	if (ret)
		goto error;
	return 0;

error:
	free_trace_probe(tp);
	return ret;
}

static void cleanup_all_probes(void)
{
	struct trace_probe *tp;

	mutex_lock(&probe_lock);
	/* TODO: Use batch unregistration */
	while (!list_empty(&probe_list)) {
		tp = list_entry(probe_list.next, struct trace_probe, list);
		unregister_trace_probe(tp);
		free_trace_probe(tp);
	}
	mutex_unlock(&probe_lock);
}


/* 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_probe *tp = v;
	int i, ret;
	char buf[MAX_ARGSTR_LEN + 1];

	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
	seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);

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

	for (i = 0; i < tp->nr_args; i++) {
		ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
		if (ret < 0) {
			pr_warning("Argument%d decoding error(%d).\n", i, ret);
			return ret;
		}
		seq_printf(m, " %s=%s", tp->args[i].name, buf);
	}
	seq_printf(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)
{
	if ((file->f_mode & FMODE_WRITE) &&
	    (file->f_flags & O_TRUNC))
		cleanup_all_probes();

	return seq_open(file, &probes_seq_op);
}

static int command_trace_probe(const char *buf)
{
	char **argv;
	int argc = 0, ret = 0;

	argv = argv_split(GFP_KERNEL, buf, &argc);
	if (!argv)
		return -ENOMEM;

	if (argc)
		ret = create_trace_probe(argc, argv);

	argv_free(argv);
	return ret;
}

#define WRITE_BUFSIZE 128

static ssize_t probes_write(struct file *file, const char __user *buffer,
			    size_t count, loff_t *ppos)
{
	char *kbuf, *tmp;
	int ret;
	size_t done;
	size_t size;

	kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
	if (!kbuf)
		return -ENOMEM;

	ret = done = 0;
	while (done < count) {
		size = count - done;
		if (size >= WRITE_BUFSIZE)
			size = WRITE_BUFSIZE - 1;
		if (copy_from_user(kbuf, buffer + done, size)) {
			ret = -EFAULT;
			goto out;
		}
		kbuf[size] = '\0';
		tmp = strchr(kbuf, '\n');
		if (tmp) {
			*tmp = '\0';
			size = tmp - kbuf + 1;
		} else if (done + size < count) {
			pr_warning("Line length is too long: "
				   "Should be less than %d.", WRITE_BUFSIZE);
			ret = -EINVAL;
			goto out;
		}
		done += size;
		/* Remove comments */
		tmp = strchr(kbuf, '#');
		if (tmp)
			*tmp = '\0';

		ret = command_trace_probe(kbuf);
		if (ret)
			goto out;
	}
	ret = done;
out:
	kfree(kbuf);
	return ret;
}

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_probe *tp = v;

	seq_printf(m, "  %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
		   tp->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 __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
	struct kprobe_trace_entry *entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	int size, i, pc;
	unsigned long irq_flags;
	struct ftrace_event_call *call = &tp->call;

	tp->nhit++;

	local_save_flags(irq_flags);
	pc = preempt_count();

	size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);

	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
						  irq_flags, pc);
	if (!event)
		return 0;

	entry = ring_buffer_event_data(event);
	entry->nargs = tp->nr_args;
	entry->ip = (unsigned long)kp->addr;
	for (i = 0; i < tp->nr_args; i++)
		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);

	if (!filter_current_check_discard(buffer, call, entry, event))
		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
	return 0;
}

/* Kretprobe handler */
static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
					  struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
	struct kretprobe_trace_entry *entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	int size, i, pc;
	unsigned long irq_flags;
	struct ftrace_event_call *call = &tp->call;

	local_save_flags(irq_flags);
	pc = preempt_count();

	size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);

	event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
						  irq_flags, pc);
	if (!event)
		return 0;

	entry = ring_buffer_event_data(event);
	entry->nargs = tp->nr_args;
	entry->func = (unsigned long)tp->rp.kp.addr;
	entry->ret_ip = (unsigned long)ri->ret_addr;
	for (i = 0; i < tp->nr_args; i++)
		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);

	if (!filter_current_check_discard(buffer, call, entry, event))
		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);

	return 0;
}

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

	field = (struct kprobe_trace_entry *)iter->ent;
	event = ftrace_find_event(field->ent.type);
	tp = container_of(event, struct trace_probe, event);

	if (!trace_seq_printf(s, "%s: (", tp->call.name))
		goto partial;

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

	if (!trace_seq_puts(s, ")"))
		goto partial;

	for (i = 0; i < field->nargs; i++)
		if (!trace_seq_printf(s, " %s=%lx",
				      tp->args[i].name, field->args[i]))
			goto partial;

	if (!trace_seq_puts(s, "\n"))
		goto partial;

	return TRACE_TYPE_HANDLED;
partial:
	return TRACE_TYPE_PARTIAL_LINE;
}

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

	field = (struct kretprobe_trace_entry *)iter->ent;
	event = ftrace_find_event(field->ent.type);
	tp = container_of(event, struct trace_probe, event);

	if (!trace_seq_printf(s, "%s: (", tp->call.name))
		goto partial;

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

	if (!trace_seq_puts(s, " <- "))
		goto partial;

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

	if (!trace_seq_puts(s, ")"))
		goto partial;

	for (i = 0; i < field->nargs; i++)
		if (!trace_seq_printf(s, " %s=%lx",
				      tp->args[i].name, field->args[i]))
			goto partial;

	if (!trace_seq_puts(s, "\n"))
		goto partial;

	return TRACE_TYPE_HANDLED;
partial:
	return TRACE_TYPE_PARTIAL_LINE;
}

static int probe_event_enable(struct ftrace_event_call *call)
{
	struct trace_probe *tp = (struct trace_probe *)call->data;

	tp->flags |= TP_FLAG_TRACE;
	if (probe_is_return(tp))
		return enable_kretprobe(&tp->rp);
	else
		return enable_kprobe(&tp->rp.kp);
}

static void probe_event_disable(struct ftrace_event_call *call)
{
	struct trace_probe *tp = (struct trace_probe *)call->data;

	tp->flags &= ~TP_FLAG_TRACE;
	if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
		if (probe_is_return(tp))
			disable_kretprobe(&tp->rp);
		else
			disable_kprobe(&tp->rp.kp);
	}
}

static int probe_event_raw_init(struct ftrace_event_call *event_call)
{
	INIT_LIST_HEAD(&event_call->fields);

	return 0;
}

#undef DEFINE_FIELD
#define DEFINE_FIELD(type, item, name, is_signed)			\
	do {								\
		ret = trace_define_field(event_call, #type, name,	\
					 offsetof(typeof(field), item),	\
					 sizeof(field.item), is_signed, \
					 FILTER_OTHER);			\
		if (ret)						\
			return ret;					\
	} while (0)

static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
{
	int ret, i;
	struct kprobe_trace_entry field;
	struct trace_probe *tp = (struct trace_probe *)event_call->data;

	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
	/* Set argument names as fields */
	for (i = 0; i < tp->nr_args; i++)
		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
	return 0;
}

static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
{
	int ret, i;
	struct kretprobe_trace_entry field;
	struct trace_probe *tp = (struct trace_probe *)event_call->data;

	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
	DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
	/* Set argument names as fields */
	for (i = 0; i < tp->nr_args; i++)
		DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
	return 0;
}

static int __probe_event_show_format(struct trace_seq *s,
				     struct trace_probe *tp, const char *fmt,
				     const char *arg)
{
	int i;

	/* Show format */
	if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
		return 0;

	for (i = 0; i < tp->nr_args; i++)
		if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
			return 0;

	if (!trace_seq_printf(s, "\", %s", arg))
		return 0;

	for (i = 0; i < tp->nr_args; i++)
		if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
			return 0;

	return trace_seq_puts(s, "\n");
}

#undef SHOW_FIELD
#define SHOW_FIELD(type, item, name)					\
	do {								\
		ret = trace_seq_printf(s, "\tfield: " #type " %s;\t"	\
				"offset:%u;\tsize:%u;\n", name,		\
				(unsigned int)offsetof(typeof(field), item),\
				(unsigned int)sizeof(type));		\
		if (!ret)						\
			return 0;					\
	} while (0)

static int kprobe_event_show_format(struct ftrace_event_call *call,
				    struct trace_seq *s)
{
	struct kprobe_trace_entry field __attribute__((unused));
	int ret, i;
	struct trace_probe *tp = (struct trace_probe *)call->data;

	SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);

	/* Show fields */
	for (i = 0; i < tp->nr_args; i++)
		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
	trace_seq_puts(s, "\n");

	return __probe_event_show_format(s, tp, "(%lx)",
					 "REC->" FIELD_STRING_IP);
}

static int kretprobe_event_show_format(struct ftrace_event_call *call,
				       struct trace_seq *s)
{
	struct kretprobe_trace_entry field __attribute__((unused));
	int ret, i;
	struct trace_probe *tp = (struct trace_probe *)call->data;

	SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
	SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);

	/* Show fields */
	for (i = 0; i < tp->nr_args; i++)
		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
	trace_seq_puts(s, "\n");

	return __probe_event_show_format(s, tp, "(%lx <- %lx)",
					 "REC->" FIELD_STRING_FUNC
					 ", REC->" FIELD_STRING_RETIP);
}

#ifdef CONFIG_EVENT_PROFILE

/* Kprobe profile handler */
static __kprobes int kprobe_profile_func(struct kprobe *kp,
					 struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
	struct ftrace_event_call *call = &tp->call;
	struct kprobe_trace_entry *entry;
	struct trace_entry *ent;
	int size, __size, i, pc, __cpu;
	unsigned long irq_flags;
	char *trace_buf;
	char *raw_data;
	int rctx;

	pc = preempt_count();
	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
	size = ALIGN(__size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);
	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
		     "profile buffer not large enough"))
		return 0;

	/*
	 * Protect the non nmi buffer
	 * This also protects the rcu read side
	 */
	local_irq_save(irq_flags);

	rctx = perf_swevent_get_recursion_context();
	if (rctx < 0)
		goto end_recursion;

	__cpu = smp_processor_id();

	if (in_nmi())
		trace_buf = rcu_dereference(perf_trace_buf_nmi);
	else
		trace_buf = rcu_dereference(perf_trace_buf);

	if (!trace_buf)
		goto end;

	raw_data = per_cpu_ptr(trace_buf, __cpu);

	/* Zero dead bytes from alignment to avoid buffer leak to userspace */
	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
	entry = (struct kprobe_trace_entry *)raw_data;
	ent = &entry->ent;

	tracing_generic_entry_update(ent, irq_flags, pc);
	ent->type = call->id;
	entry->nargs = tp->nr_args;
	entry->ip = (unsigned long)kp->addr;
	for (i = 0; i < tp->nr_args; i++)
		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
	perf_tp_event(call->id, entry->ip, 1, entry, size);

end:
	perf_swevent_put_recursion_context(rctx);
end_recursion:
	local_irq_restore(irq_flags);

	return 0;
}

/* Kretprobe profile handler */
static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
					    struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
	struct ftrace_event_call *call = &tp->call;
	struct kretprobe_trace_entry *entry;
	struct trace_entry *ent;
	int size, __size, i, pc, __cpu;
	unsigned long irq_flags;
	char *trace_buf;
	char *raw_data;
	int rctx;

	pc = preempt_count();
	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
	size = ALIGN(__size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);
	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
		     "profile buffer not large enough"))
		return 0;

	/*
	 * Protect the non nmi buffer
	 * This also protects the rcu read side
	 */
	local_irq_save(irq_flags);

	rctx = perf_swevent_get_recursion_context();
	if (rctx < 0)
		goto end_recursion;

	__cpu = smp_processor_id();

	if (in_nmi())
		trace_buf = rcu_dereference(perf_trace_buf_nmi);
	else
		trace_buf = rcu_dereference(perf_trace_buf);

	if (!trace_buf)
		goto end;

	raw_data = per_cpu_ptr(trace_buf, __cpu);

	/* Zero dead bytes from alignment to avoid buffer leak to userspace */
	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
	entry = (struct kretprobe_trace_entry *)raw_data;
	ent = &entry->ent;

	tracing_generic_entry_update(ent, irq_flags, pc);
	ent->type = call->id;
	entry->nargs = tp->nr_args;
	entry->func = (unsigned long)tp->rp.kp.addr;
	entry->ret_ip = (unsigned long)ri->ret_addr;
	for (i = 0; i < tp->nr_args; i++)
		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
	perf_tp_event(call->id, entry->ret_ip, 1, entry, size);

end:
	perf_swevent_put_recursion_context(rctx);
end_recursion:
	local_irq_restore(irq_flags);

	return 0;
}

static int probe_profile_enable(struct ftrace_event_call *call)
{
	struct trace_probe *tp = (struct trace_probe *)call->data;

	tp->flags |= TP_FLAG_PROFILE;

	if (probe_is_return(tp))
		return enable_kretprobe(&tp->rp);
	else
		return enable_kprobe(&tp->rp.kp);
}

static void probe_profile_disable(struct ftrace_event_call *call)
{
	struct trace_probe *tp = (struct trace_probe *)call->data;

	tp->flags &= ~TP_FLAG_PROFILE;

	if (!(tp->flags & TP_FLAG_TRACE)) {
		if (probe_is_return(tp))
			disable_kretprobe(&tp->rp);
		else
			disable_kprobe(&tp->rp.kp);
	}
}
#endif	/* CONFIG_EVENT_PROFILE */


static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);

	if (tp->flags & TP_FLAG_TRACE)
		kprobe_trace_func(kp, regs);
#ifdef CONFIG_EVENT_PROFILE
	if (tp->flags & TP_FLAG_PROFILE)
		kprobe_profile_func(kp, regs);
#endif	/* CONFIG_EVENT_PROFILE */
	return 0;	/* We don't tweek kernel, so just return 0 */
}

static __kprobes
int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);

	if (tp->flags & TP_FLAG_TRACE)
		kretprobe_trace_func(ri, regs);
#ifdef CONFIG_EVENT_PROFILE
	if (tp->flags & TP_FLAG_PROFILE)
		kretprobe_profile_func(ri, regs);
#endif	/* CONFIG_EVENT_PROFILE */
	return 0;	/* We don't tweek kernel, so just return 0 */
}

static int register_probe_event(struct trace_probe *tp)
{
	struct ftrace_event_call *call = &tp->call;
	int ret;

	/* Initialize ftrace_event_call */
	if (probe_is_return(tp)) {
		tp->event.trace = print_kretprobe_event;
		call->raw_init = probe_event_raw_init;
		call->show_format = kretprobe_event_show_format;
		call->define_fields = kretprobe_event_define_fields;
	} else {
		tp->event.trace = print_kprobe_event;
		call->raw_init = probe_event_raw_init;
		call->show_format = kprobe_event_show_format;
		call->define_fields = kprobe_event_define_fields;
	}
	call->event = &tp->event;
	call->id = register_ftrace_event(&tp->event);
	if (!call->id)
		return -ENODEV;
	call->enabled = 0;
	call->regfunc = probe_event_enable;
	call->unregfunc = probe_event_disable;

#ifdef CONFIG_EVENT_PROFILE
	call->profile_enable = probe_profile_enable;
	call->profile_disable = probe_profile_disable;
#endif
	call->data = tp;
	ret = trace_add_event_call(call);
	if (ret) {
		pr_info("Failed to register kprobe event: %s\n", call->name);
		unregister_ftrace_event(&tp->event);
	}
	return ret;
}

static void unregister_probe_event(struct trace_probe *tp)
{
	/* tp->event is unregistered in trace_remove_event_call() */
	trace_remove_event_call(&tp->call);
}

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

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

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

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

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

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


#ifdef CONFIG_FTRACE_STARTUP_TEST

static 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 int kprobe_trace_self_tests_init(void)
{
	int ret;
	int (*target)(int, int, int, int, int, int);

	target = kprobe_trace_selftest_target;

	pr_info("Testing kprobe tracing: ");

	ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
				  "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
	if (WARN_ON_ONCE(ret))
		pr_warning("error enabling function entry\n");

	ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
				  "$retval");
	if (WARN_ON_ONCE(ret))
		pr_warning("error enabling function return\n");

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

	cleanup_all_probes();

	pr_cont("OK\n");
	return 0;
}

late_initcall(kprobe_trace_self_tests_init);

#endif