summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_kprobe.c
blob: aa515d578c5b19638f4122795ab1ee73c930cdb1 (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
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
// SPDX-License-Identifier: GPL-2.0
/*
 * Kprobes-based tracing events
 *
 * Created by Masami Hiramatsu <mhiramat@redhat.com>
 *
 */
#define pr_fmt(fmt)	"trace_kprobe: " fmt

#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/rculist.h>
#include <linux/error-injection.h>

#include <asm/setup.h>  /* for COMMAND_LINE_SIZE */

#include "trace_dynevent.h"
#include "trace_kprobe_selftest.h"
#include "trace_probe.h"
#include "trace_probe_tmpl.h"

#define KPROBE_EVENT_SYSTEM "kprobes"
#define KRETPROBE_MAXACTIVE_MAX 4096
#define MAX_KPROBE_CMDLINE_SIZE 1024

/* Kprobe early definition from command line */
static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
static bool kprobe_boot_events_enabled __initdata;

static int __init set_kprobe_boot_events(char *str)
{
	strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
	return 0;
}
__setup("kprobe_event=", set_kprobe_boot_events);

static int trace_kprobe_create(int argc, const char **argv);
static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_kprobe_release(struct dyn_event *ev);
static bool trace_kprobe_is_busy(struct dyn_event *ev);
static bool trace_kprobe_match(const char *system, const char *event,
			int argc, const char **argv, struct dyn_event *ev);

static struct dyn_event_operations trace_kprobe_ops = {
	.create = trace_kprobe_create,
	.show = trace_kprobe_show,
	.is_busy = trace_kprobe_is_busy,
	.free = trace_kprobe_release,
	.match = trace_kprobe_match,
};

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

static bool is_trace_kprobe(struct dyn_event *ev)
{
	return ev->ops == &trace_kprobe_ops;
}

static struct trace_kprobe *to_trace_kprobe(struct dyn_event *ev)
{
	return container_of(ev, struct trace_kprobe, devent);
}

/**
 * for_each_trace_kprobe - iterate over the trace_kprobe list
 * @pos:	the struct trace_kprobe * for each entry
 * @dpos:	the struct dyn_event * to use as a loop cursor
 */
#define for_each_trace_kprobe(pos, dpos)	\
	for_each_dyn_event(dpos)		\
		if (is_trace_kprobe(dpos) && (pos = to_trace_kprobe(dpos)))

#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_module_exist(struct trace_kprobe *tk)
{
	char *p;
	bool ret;

	if (!tk->symbol)
		return false;
	p = strchr(tk->symbol, ':');
	if (!p)
		return true;
	*p = '\0';
	mutex_lock(&module_mutex);
	ret = !!find_module(tk->symbol);
	mutex_unlock(&module_mutex);
	*p = ':';

	return ret;
}

static bool trace_kprobe_is_busy(struct dyn_event *ev)
{
	struct trace_kprobe *tk = to_trace_kprobe(ev);

	return trace_probe_is_enabled(&tk->tp);
}

static bool trace_kprobe_match_command_head(struct trace_kprobe *tk,
					    int argc, const char **argv)
{
	char buf[MAX_ARGSTR_LEN + 1];

	if (!argc)
		return true;

	if (!tk->symbol)
		snprintf(buf, sizeof(buf), "0x%p", tk->rp.kp.addr);
	else if (tk->rp.kp.offset)
		snprintf(buf, sizeof(buf), "%s+%u",
			 trace_kprobe_symbol(tk), tk->rp.kp.offset);
	else
		snprintf(buf, sizeof(buf), "%s", trace_kprobe_symbol(tk));
	if (strcmp(buf, argv[0]))
		return false;
	argc--; argv++;

	return trace_probe_match_command_args(&tk->tp, argc, argv);
}

static bool trace_kprobe_match(const char *system, const char *event,
			int argc, const char **argv, struct dyn_event *ev)
{
	struct trace_kprobe *tk = to_trace_kprobe(ev);

	return strcmp(trace_probe_name(&tk->tp), event) == 0 &&
	    (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0) &&
	    trace_kprobe_match_command_head(tk, argc, argv);
}

static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
{
	unsigned long nhit = 0;
	int cpu;

	for_each_possible_cpu(cpu)
		nhit += *per_cpu_ptr(tk->nhit, cpu);

	return nhit;
}

static nokprobe_inline bool trace_kprobe_is_registered(struct trace_kprobe *tk)
{
	return !(list_empty(&tk->rp.kp.list) &&
		 hlist_unhashed(&tk->rp.kp.hlist));
}

/* Return 0 if it fails to find the symbol address */
static nokprobe_inline
unsigned long trace_kprobe_address(struct trace_kprobe *tk)
{
	unsigned long addr;

	if (tk->symbol) {
		addr = (unsigned long)
			kallsyms_lookup_name(trace_kprobe_symbol(tk));
		if (addr)
			addr += tk->rp.kp.offset;
	} else {
		addr = (unsigned long)tk->rp.kp.addr;
	}
	return addr;
}

static nokprobe_inline struct trace_kprobe *
trace_kprobe_primary_from_call(struct trace_event_call *call)
{
	struct trace_probe *tp;

	tp = trace_probe_primary_from_call(call);
	if (WARN_ON_ONCE(!tp))
		return NULL;

	return container_of(tp, struct trace_kprobe, tp);
}

bool trace_kprobe_on_func_entry(struct trace_event_call *call)
{
	struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);

	return tk ? kprobe_on_func_entry(tk->rp.kp.addr,
			tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false;
}

bool trace_kprobe_error_injectable(struct trace_event_call *call)
{
	struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);

	return tk ? within_error_injection_list(trace_kprobe_address(tk)) :
	       false;
}

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

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

static void free_trace_kprobe(struct trace_kprobe *tk)
{
	if (tk) {
		trace_probe_cleanup(&tk->tp);
		kfree(tk->symbol);
		free_percpu(tk->nhit);
		kfree(tk);
	}
}

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

	tk = kzalloc(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;
	INIT_HLIST_NODE(&tk->rp.kp.hlist);
	INIT_LIST_HEAD(&tk->rp.kp.list);

	ret = trace_probe_init(&tk->tp, event, group, false);
	if (ret < 0)
		goto error;

	dyn_event_init(&tk->devent, &trace_kprobe_ops);
	return tk;
error:
	free_trace_kprobe(tk);
	return ERR_PTR(ret);
}

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

	for_each_trace_kprobe(tk, pos)
		if (strcmp(trace_probe_name(&tk->tp), event) == 0 &&
		    strcmp(trace_probe_group_name(&tk->tp), group) == 0)
			return tk;
	return NULL;
}

static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
{
	int ret = 0;

	if (trace_kprobe_is_registered(tk) && !trace_kprobe_has_gone(tk)) {
		if (trace_kprobe_is_return(tk))
			ret = enable_kretprobe(&tk->rp);
		else
			ret = enable_kprobe(&tk->rp.kp);
	}

	return ret;
}

static void __disable_trace_kprobe(struct trace_probe *tp)
{
	struct trace_probe *pos;
	struct trace_kprobe *tk;

	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
		tk = container_of(pos, struct trace_kprobe, tp);
		if (!trace_kprobe_is_registered(tk))
			continue;
		if (trace_kprobe_is_return(tk))
			disable_kretprobe(&tk->rp);
		else
			disable_kprobe(&tk->rp.kp);
	}
}

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

	tp = trace_probe_primary_from_call(call);
	if (WARN_ON_ONCE(!tp))
		return -ENODEV;
	enabled = trace_probe_is_enabled(tp);

	/* This also changes "enabled" state */
	if (file) {
		ret = trace_probe_add_file(tp, file);
		if (ret)
			return ret;
	} else
		trace_probe_set_flag(tp, TP_FLAG_PROFILE);

	if (enabled)
		return 0;

	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
		tk = container_of(pos, struct trace_kprobe, tp);
		if (trace_kprobe_has_gone(tk))
			continue;
		ret = __enable_trace_kprobe(tk);
		if (ret)
			break;
		enabled = true;
	}

	if (ret) {
		/* Failed to enable one of them. Roll back all */
		if (enabled)
			__disable_trace_kprobe(tp);
		if (file)
			trace_probe_remove_file(tp, file);
		else
			trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
	}

	return ret;
}

/*
 * Disable trace_probe
 * if the file is NULL, disable "perf" handler, or disable "trace" handler.
 */
static int disable_trace_kprobe(struct trace_event_call *call,
				struct trace_event_file *file)
{
	struct trace_probe *tp;

	tp = trace_probe_primary_from_call(call);
	if (WARN_ON_ONCE(!tp))
		return -ENODEV;

	if (file) {
		if (!trace_probe_get_file_link(tp, file))
			return -ENOENT;
		if (!trace_probe_has_single_file(tp))
			goto out;
		trace_probe_clear_flag(tp, TP_FLAG_TRACE);
	} else
		trace_probe_clear_flag(tp, TP_FLAG_PROFILE);

	if (!trace_probe_is_enabled(tp))
		__disable_trace_kprobe(tp);

 out:
	if (file)
		/*
		 * Synchronization is done in below function. For perf event,
		 * file == NULL and perf_trace_event_unreg() calls
		 * tracepoint_synchronize_unregister() to ensure synchronize
		 * event. We don't need to care about it.
		 */
		trace_probe_remove_file(tp, file);

	return 0;
}

#if defined(CONFIG_KPROBES_ON_FTRACE) && \
	!defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
static bool __within_notrace_func(unsigned long addr)
{
	unsigned long offset, size;

	if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset))
		return false;

	/* Get the entry address of the target function */
	addr -= offset;

	/*
	 * Since ftrace_location_range() does inclusive range check, we need
	 * to subtract 1 byte from the end address.
	 */
	return !ftrace_location_range(addr, addr + size - 1);
}

static bool within_notrace_func(struct trace_kprobe *tk)
{
	unsigned long addr = addr = trace_kprobe_address(tk);
	char symname[KSYM_NAME_LEN], *p;

	if (!__within_notrace_func(addr))
		return false;

	/* Check if the address is on a suffixed-symbol */
	if (!lookup_symbol_name(addr, symname)) {
		p = strchr(symname, '.');
		if (!p)
			return true;
		*p = '\0';
		addr = (unsigned long)kprobe_lookup_name(symname, 0);
		if (addr)
			return __within_notrace_func(addr);
	}

	return true;
}
#else
#define within_notrace_func(tk)	(false)
#endif

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

	ret = security_locked_down(LOCKDOWN_KPROBES);
	if (ret)
		return ret;

	if (trace_kprobe_is_registered(tk))
		return -EINVAL;

	if (within_notrace_func(tk)) {
		pr_warn("Could not probe notrace function %s\n",
			trace_kprobe_symbol(tk));
		return -EINVAL;
	}

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

	/* Set/clear disabled flag according to tp->flag */
	if (trace_probe_is_enabled(&tk->tp))
		tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
	else
		tk->rp.kp.flags |= KPROBE_FLAG_DISABLED;

	if (trace_kprobe_is_return(tk))
		ret = register_kretprobe(&tk->rp);
	else
		ret = register_kprobe(&tk->rp.kp);

	return ret;
}

/* Internal unregister function - just handle k*probes and flags */
static void __unregister_trace_kprobe(struct trace_kprobe *tk)
{
	if (trace_kprobe_is_registered(tk)) {
		if (trace_kprobe_is_return(tk))
			unregister_kretprobe(&tk->rp);
		else
			unregister_kprobe(&tk->rp.kp);
		/* Cleanup kprobe for reuse and mark it unregistered */
		INIT_HLIST_NODE(&tk->rp.kp.hlist);
		INIT_LIST_HEAD(&tk->rp.kp.list);
		if (tk->rp.kp.symbol_name)
			tk->rp.kp.addr = NULL;
	}
}

/* Unregister a trace_probe and probe_event */
static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
	/* If other probes are on the event, just unregister kprobe */
	if (trace_probe_has_sibling(&tk->tp))
		goto unreg;

	/* Enabled event can not be unregistered */
	if (trace_probe_is_enabled(&tk->tp))
		return -EBUSY;

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

unreg:
	__unregister_trace_kprobe(tk);
	dyn_event_remove(&tk->devent);
	trace_probe_unlink(&tk->tp);

	return 0;
}

static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig,
					 struct trace_kprobe *comp)
{
	struct trace_probe_event *tpe = orig->tp.event;
	struct trace_probe *pos;
	int i;

	list_for_each_entry(pos, &tpe->probes, list) {
		orig = container_of(pos, struct trace_kprobe, tp);
		if (strcmp(trace_kprobe_symbol(orig),
			   trace_kprobe_symbol(comp)) ||
		    trace_kprobe_offset(orig) != trace_kprobe_offset(comp))
			continue;

		/*
		 * trace_probe_compare_arg_type() ensured that nr_args and
		 * each argument name and type are same. Let's compare comm.
		 */
		for (i = 0; i < orig->tp.nr_args; i++) {
			if (strcmp(orig->tp.args[i].comm,
				   comp->tp.args[i].comm))
				break;
		}

		if (i == orig->tp.nr_args)
			return true;
	}

	return false;
}

static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
{
	int ret;

	ret = trace_probe_compare_arg_type(&tk->tp, &to->tp);
	if (ret) {
		/* Note that argument starts index = 2 */
		trace_probe_log_set_index(ret + 1);
		trace_probe_log_err(0, DIFF_ARG_TYPE);
		return -EEXIST;
	}
	if (trace_kprobe_has_same_kprobe(to, tk)) {
		trace_probe_log_set_index(0);
		trace_probe_log_err(0, SAME_PROBE);
		return -EEXIST;
	}

	/* Append to existing event */
	ret = trace_probe_append(&tk->tp, &to->tp);
	if (ret)
		return ret;

	/* Register k*probe */
	ret = __register_trace_kprobe(tk);
	if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
		pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
		ret = 0;
	}

	if (ret)
		trace_probe_unlink(&tk->tp);
	else
		dyn_event_add(&tk->devent);

	return ret;
}

/* Register a trace_probe and probe_event */
static int register_trace_kprobe(struct trace_kprobe *tk)
{
	struct trace_kprobe *old_tk;
	int ret;

	mutex_lock(&event_mutex);

	old_tk = find_trace_kprobe(trace_probe_name(&tk->tp),
				   trace_probe_group_name(&tk->tp));
	if (old_tk) {
		if (trace_kprobe_is_return(tk) != trace_kprobe_is_return(old_tk)) {
			trace_probe_log_set_index(0);
			trace_probe_log_err(0, DIFF_PROBE_TYPE);
			ret = -EEXIST;
		} else {
			ret = append_trace_kprobe(tk, old_tk);
		}
		goto end;
	}

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

	/* Register k*probe */
	ret = __register_trace_kprobe(tk);
	if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
		pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
		ret = 0;
	}

	if (ret < 0)
		unregister_kprobe_event(tk);
	else
		dyn_event_add(&tk->devent);

end:
	mutex_unlock(&event_mutex);
	return ret;
}

/* Module notifier call back, checking event on the module */
static int trace_kprobe_module_callback(struct notifier_block *nb,
				       unsigned long val, void *data)
{
	struct module *mod = data;
	struct dyn_event *pos;
	struct trace_kprobe *tk;
	int ret;

	if (val != MODULE_STATE_COMING)
		return NOTIFY_DONE;

	/* Update probes on coming module */
	mutex_lock(&event_mutex);
	for_each_trace_kprobe(tk, pos) {
		if (trace_kprobe_within_module(tk, mod)) {
			/* Don't need to check busy - this should have gone. */
			__unregister_trace_kprobe(tk);
			ret = __register_trace_kprobe(tk);
			if (ret)
				pr_warn("Failed to re-register probe %s on %s: %d\n",
					trace_probe_name(&tk->tp),
					mod->name, ret);
		}
	}
	mutex_unlock(&event_mutex);

	return NOTIFY_DONE;
}

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

/* 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 trace_kprobe_create(int argc, const char *argv[])
{
	/*
	 * Argument syntax:
	 *  - Add kprobe:
	 *      p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
	 *  - Add kretprobe:
	 *      r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
	 * Fetch args:
	 *  $retval	: fetch return value
	 *  $stack	: fetch stack address
	 *  $stackN	: fetch Nth of stack (N:0-)
	 *  $comm       : fetch current task comm
	 *  @ADDR	: fetch memory at ADDR (ADDR should be in kernel)
	 *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
	 *  %REG	: fetch register REG
	 * Dereferencing memory fetch:
	 *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
	 * Alias name of args:
	 *  NAME=FETCHARG : set NAME as alias of FETCHARG.
	 * Type of args:
	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
	 */
	struct trace_kprobe *tk = NULL;
	int i, len, ret = 0;
	bool is_return = false;
	char *symbol = NULL, *tmp = NULL;
	const char *event = NULL, *group = KPROBE_EVENT_SYSTEM;
	int maxactive = 0;
	long offset = 0;
	void *addr = NULL;
	char buf[MAX_EVENT_NAME_LEN];
	unsigned int flags = TPARG_FL_KERNEL;

	switch (argv[0][0]) {
	case 'r':
		is_return = true;
		flags |= TPARG_FL_RETURN;
		break;
	case 'p':
		break;
	default:
		return -ECANCELED;
	}
	if (argc < 2)
		return -ECANCELED;

	trace_probe_log_init("trace_kprobe", argc, argv);

	event = strchr(&argv[0][1], ':');
	if (event)
		event++;

	if (isdigit(argv[0][1])) {
		if (!is_return) {
			trace_probe_log_err(1, MAXACT_NO_KPROBE);
			goto parse_error;
		}
		if (event)
			len = event - &argv[0][1] - 1;
		else
			len = strlen(&argv[0][1]);
		if (len > MAX_EVENT_NAME_LEN - 1) {
			trace_probe_log_err(1, BAD_MAXACT);
			goto parse_error;
		}
		memcpy(buf, &argv[0][1], len);
		buf[len] = '\0';
		ret = kstrtouint(buf, 0, &maxactive);
		if (ret || !maxactive) {
			trace_probe_log_err(1, BAD_MAXACT);
			goto parse_error;
		}
		/* kretprobes instances are iterated over via a list. The
		 * maximum should stay reasonable.
		 */
		if (maxactive > KRETPROBE_MAXACTIVE_MAX) {
			trace_probe_log_err(1, MAXACT_TOO_BIG);
			goto parse_error;
		}
	}

	/* try to parse an address. if that fails, try to read the
	 * input as a symbol. */
	if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
		trace_probe_log_set_index(1);
		/* Check whether uprobe event specified */
		if (strchr(argv[1], '/') && strchr(argv[1], ':')) {
			ret = -ECANCELED;
			goto error;
		}
		/* a symbol specified */
		symbol = kstrdup(argv[1], GFP_KERNEL);
		if (!symbol)
			return -ENOMEM;
		/* TODO: support .init module functions */
		ret = traceprobe_split_symbol_offset(symbol, &offset);
		if (ret || offset < 0 || offset > UINT_MAX) {
			trace_probe_log_err(0, BAD_PROBE_ADDR);
			goto parse_error;
		}
		if (kprobe_on_func_entry(NULL, symbol, offset))
			flags |= TPARG_FL_FENTRY;
		if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
			trace_probe_log_err(0, BAD_RETPROBE);
			goto parse_error;
		}
	}

	trace_probe_log_set_index(0);
	if (event) {
		ret = traceprobe_parse_event_name(&event, &group, buf,
						  event - argv[0]);
		if (ret)
			goto parse_error;
	} else {
		/* 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;
	}

	/* setup a probe */
	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
			       argc - 2, is_return);
	if (IS_ERR(tk)) {
		ret = PTR_ERR(tk);
		/* This must return -ENOMEM, else there is a bug */
		WARN_ON_ONCE(ret != -ENOMEM);
		goto out;	/* We know tk is not allocated */
	}
	argc -= 2; argv += 2;

	/* 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(&tk->tp, i, tmp, flags);
		kfree(tmp);
		if (ret)
			goto error;	/* This can be -ENOMEM */
	}

	ret = traceprobe_set_print_fmt(&tk->tp, is_return);
	if (ret < 0)
		goto error;

	ret = register_trace_kprobe(tk);
	if (ret) {
		trace_probe_log_set_index(1);
		if (ret == -EILSEQ)
			trace_probe_log_err(0, BAD_INSN_BNDRY);
		else if (ret == -ENOENT)
			trace_probe_log_err(0, BAD_PROBE_ADDR);
		else if (ret != -ENOMEM && ret != -EEXIST)
			trace_probe_log_err(0, FAIL_REG_PROBE);
		goto error;
	}

out:
	trace_probe_log_clear();
	kfree(symbol);
	return ret;

parse_error:
	ret = -EINVAL;
error:
	free_trace_kprobe(tk);
	goto out;
}

static int create_or_delete_trace_kprobe(int argc, char **argv)
{
	int ret;

	if (argv[0][0] == '-')
		return dyn_event_release(argc, argv, &trace_kprobe_ops);

	ret = trace_kprobe_create(argc, (const char **)argv);
	return ret == -ECANCELED ? -EINVAL : ret;
}

static int trace_kprobe_release(struct dyn_event *ev)
{
	struct trace_kprobe *tk = to_trace_kprobe(ev);
	int ret = unregister_trace_kprobe(tk);

	if (!ret)
		free_trace_kprobe(tk);
	return ret;
}

static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev)
{
	struct trace_kprobe *tk = to_trace_kprobe(ev);
	int i;

	seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p');
	seq_printf(m, ":%s/%s", trace_probe_group_name(&tk->tp),
				trace_probe_name(&tk->tp));

	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 int probes_seq_show(struct seq_file *m, void *v)
{
	struct dyn_event *ev = v;

	if (!is_trace_kprobe(ev))
		return 0;

	return trace_kprobe_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;

	ret = security_locked_down(LOCKDOWN_TRACEFS);
	if (ret)
		return ret;

	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
		ret = dyn_events_release_all(&trace_kprobe_ops);
		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 trace_parse_run_command(file, buffer, count, ppos,
				       create_or_delete_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 dyn_event *ev = v;
	struct trace_kprobe *tk;

	if (!is_trace_kprobe(ev))
		return 0;

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

	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)
{
	int ret;

	ret = security_locked_down(LOCKDOWN_TRACEFS);
	if (ret)
		return ret;

	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 specific fetch functions */

/* Return the length of string -- including null terminal byte */
static nokprobe_inline int
fetch_store_strlen(unsigned long addr)
{
	int ret, len = 0;
	u8 c;

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

	return (ret < 0) ? ret : len;
}

/* Return the length of string -- including null terminal byte */
static nokprobe_inline int
fetch_store_strlen_user(unsigned long addr)
{
	const void __user *uaddr =  (__force const void __user *)addr;

	return strnlen_unsafe_user(uaddr, MAX_STRING_SIZE);
}

/*
 * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
 * length and relative data location.
 */
static nokprobe_inline int
fetch_store_string(unsigned long addr, void *dest, void *base)
{
	int maxlen = get_loc_len(*(u32 *)dest);
	void *__dest;
	long ret;

	if (unlikely(!maxlen))
		return -ENOMEM;

	__dest = get_loc_data(dest, base);

	/*
	 * Try to get string again, since the string can be changed while
	 * probing.
	 */
	ret = strncpy_from_unsafe(__dest, (void *)addr, maxlen);
	if (ret >= 0)
		*(u32 *)dest = make_data_loc(ret, __dest - base);

	return ret;
}

/*
 * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
 * with max length and relative data location.
 */
static nokprobe_inline int
fetch_store_string_user(unsigned long addr, void *dest, void *base)
{
	const void __user *uaddr =  (__force const void __user *)addr;
	int maxlen = get_loc_len(*(u32 *)dest);
	void *__dest;
	long ret;

	if (unlikely(!maxlen))
		return -ENOMEM;

	__dest = get_loc_data(dest, base);

	ret = strncpy_from_unsafe_user(__dest, uaddr, maxlen);
	if (ret >= 0)
		*(u32 *)dest = make_data_loc(ret, __dest - base);

	return ret;
}

static nokprobe_inline int
probe_mem_read(void *dest, void *src, size_t size)
{
	return probe_kernel_read(dest, src, size);
}

static nokprobe_inline int
probe_mem_read_user(void *dest, void *src, size_t size)
{
	const void __user *uaddr =  (__force const void __user *)src;

	return probe_user_read(dest, uaddr, size);
}

/* 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;

retry:
	/* 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 = regs_get_kernel_stack_nth(regs, code->param);
		break;
	case FETCH_OP_STACKP:
		val = kernel_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 = (unsigned long)current->comm;
		break;
	case FETCH_OP_DATA:
		val = (unsigned long)code->data;
		break;
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
	case FETCH_OP_ARG:
		val = regs_get_kernel_argument(regs, code->param);
		break;
#endif
	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
		code++;
		goto retry;
	default:
		return -EILSEQ;
	}
	code++;

	return process_fetch_insn_bottom(code, val, dest, base);
}
NOKPROBE_SYMBOL(process_fetch_insn)

/* 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 = trace_probe_event_call(&tk->tp);

	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(&entry[1], &tk->tp, regs, sizeof(*entry), 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;

	trace_probe_for_each_link_rcu(link, &tk->tp)
		__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 = trace_probe_event_call(&tk->tp);

	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(&entry[1], &tk->tp, regs, sizeof(*entry), 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;

	trace_probe_for_each_link_rcu(link, &tk->tp)
		__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;

	field = (struct kprobe_trace_entry_head *)iter->ent;
	tp = trace_probe_primary_from_call(
		container_of(event, struct trace_event_call, event));
	if (WARN_ON_ONCE(!tp))
		goto out;

	trace_seq_printf(s, "%s: (", trace_probe_name(tp));

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

	trace_seq_putc(s, ')');

	if (print_probe_args(s, tp->args, tp->nr_args,
			     (u8 *)&field[1], field) < 0)
		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;

	field = (struct kretprobe_trace_entry_head *)iter->ent;
	tp = trace_probe_primary_from_call(
		container_of(event, struct trace_event_call, event));
	if (WARN_ON_ONCE(!tp))
		goto out;

	trace_seq_printf(s, "%s: (", trace_probe_name(tp));

	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, ')');

	if (print_probe_args(s, tp->args, tp->nr_args,
			     (u8 *)&field[1], field) < 0)
		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;
	struct kprobe_trace_entry_head field;
	struct trace_probe *tp;

	tp = trace_probe_primary_from_call(event_call);
	if (WARN_ON_ONCE(!tp))
		return -ENOENT;

	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);

	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
}

static int kretprobe_event_define_fields(struct trace_event_call *event_call)
{
	int ret;
	struct kretprobe_trace_entry_head field;
	struct trace_probe *tp;

	tp = trace_probe_primary_from_call(event_call);
	if (WARN_ON_ONCE(!tp))
		return -ENOENT;

	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);

	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
}

#ifdef CONFIG_PERF_EVENTS

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

	if (bpf_prog_array_valid(call)) {
		unsigned long orig_ip = instruction_pointer(regs);
		int ret;

		ret = trace_call_bpf(call, regs);

		/*
		 * We need to check and see if we modified the pc of the
		 * pt_regs, and if so return 1 so that we don't do the
		 * single stepping.
		 */
		if (orig_ip != instruction_pointer(regs))
			return 1;
		if (!ret)
			return 0;
	}

	head = this_cpu_ptr(call->perf_events);
	if (hlist_empty(head))
		return 0;

	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 0;

	entry->ip = (unsigned long)tk->rp.kp.addr;
	memset(&entry[1], 0, dsize);
	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
			      head, NULL);
	return 0;
}
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 = trace_probe_event_call(&tk->tp);
	struct kretprobe_trace_entry_head *entry;
	struct hlist_head *head;
	int size, __size, dsize;
	int rctx;

	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, 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(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
			      head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);

int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
			const char **symbol, u64 *probe_offset,
			u64 *probe_addr, bool perf_type_tracepoint)
{
	const char *pevent = trace_event_name(event->tp_event);
	const char *group = event->tp_event->class->system;
	struct trace_kprobe *tk;

	if (perf_type_tracepoint)
		tk = find_trace_kprobe(pevent, group);
	else
		tk = event->tp_event->data;
	if (!tk)
		return -EINVAL;

	*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
					      : BPF_FD_TYPE_KPROBE;
	if (tk->symbol) {
		*symbol = tk->symbol;
		*probe_offset = tk->rp.kp.offset;
		*probe_addr = 0;
	} else {
		*symbol = NULL;
		*probe_offset = 0;
		*probe_addr = (unsigned long)tk->rp.kp.addr;
	}
	return 0;
}
#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_event_file *file = data;

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

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return enable_trace_kprobe(event, NULL);
	case TRACE_REG_PERF_UNREGISTER:
		return disable_trace_kprobe(event, 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);
	int ret = 0;

	raw_cpu_inc(*tk->nhit);

	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
		kprobe_trace_func(tk, regs);
#ifdef CONFIG_PERF_EVENTS
	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
		ret = kprobe_perf_func(tk, regs);
#endif
	return ret;
}
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 (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
		kretprobe_trace_func(tk, ri, regs);
#ifdef CONFIG_PERF_EVENTS
	if (trace_probe_test_flag(&tk->tp, 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 struct trace_event_fields kretprobe_fields_array[] = {
	{ .type = TRACE_FUNCTION_TYPE,
	  .define_fields = kretprobe_event_define_fields },
	{}
};

static struct trace_event_fields kprobe_fields_array[] = {
	{ .type = TRACE_FUNCTION_TYPE,
	  .define_fields = kprobe_event_define_fields },
	{}
};

static inline void init_trace_event_call(struct trace_kprobe *tk)
{
	struct trace_event_call *call = trace_probe_event_call(&tk->tp);

	if (trace_kprobe_is_return(tk)) {
		call->event.funcs = &kretprobe_funcs;
		call->class->fields_array = kretprobe_fields_array;
	} else {
		call->event.funcs = &kprobe_funcs;
		call->class->fields_array = kprobe_fields_array;
	}

	call->flags = TRACE_EVENT_FL_KPROBE;
	call->class->reg = kprobe_register;
}

static int register_kprobe_event(struct trace_kprobe *tk)
{
	init_trace_event_call(tk);

	return trace_probe_register_event_call(&tk->tp);
}

static int unregister_kprobe_event(struct trace_kprobe *tk)
{
	return trace_probe_unregister_event_call(&tk->tp);
}

#ifdef CONFIG_PERF_EVENTS
/* create a trace_kprobe, but don't add it to global lists */
struct trace_event_call *
create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
			  bool is_return)
{
	struct trace_kprobe *tk;
	int ret;
	char *event;

	/*
	 * local trace_kprobes are not added to dyn_event, so they are never
	 * searched in find_trace_kprobe(). Therefore, there is no concern of
	 * duplicated name here.
	 */
	event = func ? func : "DUMMY_EVENT";

	tk = alloc_trace_kprobe(KPROBE_EVENT_SYSTEM, event, (void *)addr, func,
				offs, 0 /* maxactive */, 0 /* nargs */,
				is_return);

	if (IS_ERR(tk)) {
		pr_info("Failed to allocate trace_probe.(%d)\n",
			(int)PTR_ERR(tk));
		return ERR_CAST(tk);
	}

	init_trace_event_call(tk);

	if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
		ret = -ENOMEM;
		goto error;
	}

	ret = __register_trace_kprobe(tk);
	if (ret < 0)
		goto error;

	return trace_probe_event_call(&tk->tp);
error:
	free_trace_kprobe(tk);
	return ERR_PTR(ret);
}

void destroy_local_trace_kprobe(struct trace_event_call *event_call)
{
	struct trace_kprobe *tk;

	tk = trace_kprobe_primary_from_call(event_call);
	if (unlikely(!tk))
		return;

	if (trace_probe_is_enabled(&tk->tp)) {
		WARN_ON(1);
		return;
	}

	__unregister_trace_kprobe(tk);

	free_trace_kprobe(tk);
}
#endif /* CONFIG_PERF_EVENTS */

static __init void enable_boot_kprobe_events(void)
{
	struct trace_array *tr = top_trace_array();
	struct trace_event_file *file;
	struct trace_kprobe *tk;
	struct dyn_event *pos;

	mutex_lock(&event_mutex);
	for_each_trace_kprobe(tk, pos) {
		list_for_each_entry(file, &tr->events, list)
			if (file->event_call == trace_probe_event_call(&tk->tp))
				trace_event_enable_disable(file, 1, 0);
	}
	mutex_unlock(&event_mutex);
}

static __init void setup_boot_kprobe_events(void)
{
	char *p, *cmd = kprobe_boot_events_buf;
	int ret;

	strreplace(kprobe_boot_events_buf, ',', ' ');

	while (cmd && *cmd != '\0') {
		p = strchr(cmd, ';');
		if (p)
			*p++ = '\0';

		ret = trace_run_command(cmd, create_or_delete_trace_kprobe);
		if (ret)
			pr_warn("Failed to add event(%d): %s\n", ret, cmd);
		else
			kprobe_boot_events_enabled = true;

		cmd = p;
	}

	enable_boot_kprobe_events();
}

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

	ret = dyn_event_register(&trace_kprobe_ops);
	if (ret)
		return ret;

	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");

	setup_boot_kprobe_events();

	return 0;
}
fs_initcall(init_kprobe_trace);


#ifdef CONFIG_FTRACE_STARTUP_TEST
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 == trace_probe_event_call(&tk->tp))
			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;

	if (kprobe_boot_events_enabled) {
		pr_info("Skipping kprobe tests due to kprobe_event on cmdline\n");
		return 0;
	}

	target = kprobe_trace_selftest_target;

	pr_info("Testing kprobe tracing: ");

	ret = trace_run_command("p:testprobe kprobe_trace_selftest_target $stack $stack0 +0($stack)",
				create_or_delete_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(
					trace_probe_event_call(&tk->tp), file);
		}
	}

	ret = trace_run_command("r:testprobe2 kprobe_trace_selftest_target $retval",
				create_or_delete_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(
					trace_probe_event_call(&tk->tp), 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(
				trace_probe_event_call(&tk->tp), 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(
				trace_probe_event_call(&tk->tp), file);
	}

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

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

end:
	ret = dyn_events_release_all(&trace_kprobe_ops);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error on cleaning up probes.\n");
		warn++;
	}
	/*
	 * 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