summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_uprobe.c
blob: 8520acc34b185f7cb05fcbc4a2a30685dce0ef13 (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
/*
 * uprobes-based tracing events
 *
 * 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
 *
 * Copyright (C) IBM Corporation, 2010-2012
 * Author:	Srikar Dronamraju <srikar@linux.vnet.ibm.com>
 */

#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/uprobes.h>
#include <linux/namei.h>
#include <linux/string.h>

#include "trace_probe.h"

#define UPROBE_EVENT_SYSTEM	"uprobes"

struct uprobe_trace_entry_head {
	struct trace_entry	ent;
	unsigned long		vaddr[];
};

#define SIZEOF_TRACE_ENTRY(is_return)			\
	(sizeof(struct uprobe_trace_entry_head) +	\
	 sizeof(unsigned long) * (is_return ? 2 : 1))

#define DATAOF_TRACE_ENTRY(entry, is_return)		\
	((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))

struct trace_uprobe_filter {
	rwlock_t		rwlock;
	int			nr_systemwide;
	struct list_head	perf_events;
};

/*
 * uprobe event core functions
 */
struct trace_uprobe {
	struct list_head		list;
	struct trace_uprobe_filter	filter;
	struct uprobe_consumer		consumer;
	struct inode			*inode;
	char				*filename;
	unsigned long			offset;
	unsigned long			nhit;
	struct trace_probe		tp;
};

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

static int register_uprobe_event(struct trace_uprobe *tu);
static int unregister_uprobe_event(struct trace_uprobe *tu);

static DEFINE_MUTEX(uprobe_lock);
static LIST_HEAD(uprobe_list);

struct uprobe_dispatch_data {
	struct trace_uprobe	*tu;
	unsigned long		bp_addr;
};

static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
				unsigned long func, struct pt_regs *regs);

#ifdef CONFIG_STACK_GROWSUP
static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
{
	return addr - (n * sizeof(long));
}
#else
static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
{
	return addr + (n * sizeof(long));
}
#endif

static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
{
	unsigned long ret;
	unsigned long addr = user_stack_pointer(regs);

	addr = adjust_stack_addr(addr, n);

	if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret)))
		return 0;

	return ret;
}

/*
 * Uprobes-specific fetch functions
 */
#define DEFINE_FETCH_stack(type)					\
static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,		\
					 void *offset, void *dest)	\
{									\
	*(type *)dest = (type)get_user_stack_nth(regs,			\
					      ((unsigned long)offset)); \
}
DEFINE_BASIC_FETCH_FUNCS(stack)
/* No string on the stack entry */
#define fetch_stack_string	NULL
#define fetch_stack_string_size	NULL

#define DEFINE_FETCH_memory(type)					\
static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,		\
					  void *addr, void *dest)	\
{									\
	type retval;							\
	void __user *vaddr = (void __force __user *) addr;		\
									\
	if (copy_from_user(&retval, vaddr, sizeof(type)))		\
		*(type *)dest = 0;					\
	else								\
		*(type *) dest = retval;				\
}
DEFINE_BASIC_FETCH_FUNCS(memory)
/*
 * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
 * length and relative data location.
 */
static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
					    void *addr, void *dest)
{
	long ret;
	u32 rloc = *(u32 *)dest;
	int maxlen  = get_rloc_len(rloc);
	u8 *dst = get_rloc_data(dest);
	void __user *src = (void __force __user *) addr;

	if (!maxlen)
		return;

	ret = strncpy_from_user(dst, src, maxlen);

	if (ret < 0) {	/* Failed to fetch string */
		((u8 *)get_rloc_data(dest))[0] = '\0';
		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc));
	} else {
		*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc));
	}
}

static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
						 void *addr, void *dest)
{
	int len;
	void __user *vaddr = (void __force __user *) addr;

	len = strnlen_user(vaddr, MAX_STRING_SIZE);

	if (len == 0 || len > MAX_STRING_SIZE)  /* Failed to check length */
		*(u32 *)dest = 0;
	else
		*(u32 *)dest = len;
}

static unsigned long translate_user_vaddr(void *file_offset)
{
	unsigned long base_addr;
	struct uprobe_dispatch_data *udd;

	udd = (void *) current->utask->vaddr;

	base_addr = udd->bp_addr - udd->tu->offset;
	return base_addr + (unsigned long)file_offset;
}

#define DEFINE_FETCH_file_offset(type)					\
static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,	\
					       void *offset, void *dest)\
{									\
	void *vaddr = (void *)translate_user_vaddr(offset);		\
									\
	FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest);		\
}
DEFINE_BASIC_FETCH_FUNCS(file_offset)
DEFINE_FETCH_file_offset(string)
DEFINE_FETCH_file_offset(string_size)

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

	ASSIGN_FETCH_TYPE_END
};

static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
	rwlock_init(&filter->rwlock);
	filter->nr_systemwide = 0;
	INIT_LIST_HEAD(&filter->perf_events);
}

static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
{
	return !filter->nr_systemwide && list_empty(&filter->perf_events);
}

static inline bool is_ret_probe(struct trace_uprobe *tu)
{
	return tu->consumer.ret_handler != NULL;
}

/*
 * Allocate new trace_uprobe and initialize it (including uprobes).
 */
static struct trace_uprobe *
alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
{
	struct trace_uprobe *tu;

	if (!event || !is_good_name(event))
		return ERR_PTR(-EINVAL);

	if (!group || !is_good_name(group))
		return ERR_PTR(-EINVAL);

	tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
	if (!tu)
		return ERR_PTR(-ENOMEM);

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

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

	INIT_LIST_HEAD(&tu->list);
	INIT_LIST_HEAD(&tu->tp.files);
	tu->consumer.handler = uprobe_dispatcher;
	if (is_ret)
		tu->consumer.ret_handler = uretprobe_dispatcher;
	init_trace_uprobe_filter(&tu->filter);
	return tu;

error:
	kfree(tu->tp.call.name);
	kfree(tu);

	return ERR_PTR(-ENOMEM);
}

static void free_trace_uprobe(struct trace_uprobe *tu)
{
	int i;

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

	iput(tu->inode);
	kfree(tu->tp.call.class->system);
	kfree(tu->tp.call.name);
	kfree(tu->filename);
	kfree(tu);
}

static struct trace_uprobe *find_probe_event(const char *event, const char *group)
{
	struct trace_uprobe *tu;

	list_for_each_entry(tu, &uprobe_list, list)
		if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 &&
		    strcmp(tu->tp.call.class->system, group) == 0)
			return tu;

	return NULL;
}

/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */
static int unregister_trace_uprobe(struct trace_uprobe *tu)
{
	int ret;

	ret = unregister_uprobe_event(tu);
	if (ret)
		return ret;

	list_del(&tu->list);
	free_trace_uprobe(tu);
	return 0;
}

/* Register a trace_uprobe and probe_event */
static int register_trace_uprobe(struct trace_uprobe *tu)
{
	struct trace_uprobe *old_tu;
	int ret;

	mutex_lock(&uprobe_lock);

	/* register as an event */
	old_tu = find_probe_event(ftrace_event_name(&tu->tp.call),
			tu->tp.call.class->system);
	if (old_tu) {
		/* delete old event */
		ret = unregister_trace_uprobe(old_tu);
		if (ret)
			goto end;
	}

	ret = register_uprobe_event(tu);
	if (ret) {
		pr_warning("Failed to register probe event(%d)\n", ret);
		goto end;
	}

	list_add_tail(&tu->list, &uprobe_list);

end:
	mutex_unlock(&uprobe_lock);

	return ret;
}

/*
 * Argument syntax:
 *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
 *
 *  - Remove uprobe: -:[GRP/]EVENT
 */
static int create_trace_uprobe(int argc, char **argv)
{
	struct trace_uprobe *tu;
	struct inode *inode;
	char *arg, *event, *group, *filename;
	char buf[MAX_EVENT_NAME_LEN];
	struct path path;
	unsigned long offset;
	bool is_delete, is_return;
	int i, ret;

	inode = NULL;
	ret = 0;
	is_delete = false;
	is_return = false;
	event = NULL;
	group = NULL;

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

	if (argv[0][1] == ':') {
		event = &argv[0][2];
		arg = strchr(event, '/');

		if (arg) {
			group = event;
			event = arg + 1;
			event[-1] = '\0';

			if (strlen(group) == 0) {
				pr_info("Group name is not specified\n");
				return -EINVAL;
			}
		}
		if (strlen(event) == 0) {
			pr_info("Event name is not specified\n");
			return -EINVAL;
		}
	}
	if (!group)
		group = UPROBE_EVENT_SYSTEM;

	if (is_delete) {
		int ret;

		if (!event) {
			pr_info("Delete command needs an event name.\n");
			return -EINVAL;
		}
		mutex_lock(&uprobe_lock);
		tu = find_probe_event(event, group);

		if (!tu) {
			mutex_unlock(&uprobe_lock);
			pr_info("Event %s/%s doesn't exist.\n", group, event);
			return -ENOENT;
		}
		/* delete an event */
		ret = unregister_trace_uprobe(tu);
		mutex_unlock(&uprobe_lock);
		return ret;
	}

	if (argc < 2) {
		pr_info("Probe point is not specified.\n");
		return -EINVAL;
	}
	if (isdigit(argv[1][0])) {
		pr_info("probe point must be have a filename.\n");
		return -EINVAL;
	}
	arg = strchr(argv[1], ':');
	if (!arg) {
		ret = -EINVAL;
		goto fail_address_parse;
	}

	*arg++ = '\0';
	filename = argv[1];
	ret = kern_path(filename, LOOKUP_FOLLOW, &path);
	if (ret)
		goto fail_address_parse;

	inode = igrab(path.dentry->d_inode);
	path_put(&path);

	if (!inode || !S_ISREG(inode->i_mode)) {
		ret = -EINVAL;
		goto fail_address_parse;
	}

	ret = kstrtoul(arg, 0, &offset);
	if (ret)
		goto fail_address_parse;

	argc -= 2;
	argv += 2;

	/* setup a probe */
	if (!event) {
		char *tail;
		char *ptr;

		tail = kstrdup(kbasename(filename), GFP_KERNEL);
		if (!tail) {
			ret = -ENOMEM;
			goto fail_address_parse;
		}

		ptr = strpbrk(tail, ".-_");
		if (ptr)
			*ptr = '\0';

		snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset);
		event = buf;
		kfree(tail);
	}

	tu = alloc_trace_uprobe(group, event, argc, is_return);
	if (IS_ERR(tu)) {
		pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu));
		ret = PTR_ERR(tu);
		goto fail_address_parse;
	}
	tu->offset = offset;
	tu->inode = inode;
	tu->filename = kstrdup(filename, GFP_KERNEL);

	if (!tu->filename) {
		pr_info("Failed to allocate filename.\n");
		ret = -ENOMEM;
		goto error;
	}

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

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

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

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

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

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

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

	ret = register_trace_uprobe(tu);
	if (ret)
		goto error;
	return 0;

error:
	free_trace_uprobe(tu);
	return ret;

fail_address_parse:
	iput(inode);

	pr_info("Failed to parse address or file.\n");

	return ret;
}

static int cleanup_all_probes(void)
{
	struct trace_uprobe *tu;
	int ret = 0;

	mutex_lock(&uprobe_lock);
	while (!list_empty(&uprobe_list)) {
		tu = list_entry(uprobe_list.next, struct trace_uprobe, list);
		ret = unregister_trace_uprobe(tu);
		if (ret)
			break;
	}
	mutex_unlock(&uprobe_lock);
	return ret;
}

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

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

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

static int probes_seq_show(struct seq_file *m, void *v)
{
	struct trace_uprobe *tu = v;
	char c = is_ret_probe(tu) ? 'r' : 'p';
	int i;

	seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system,
			ftrace_event_name(&tu->tp.call));
	seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);

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

	seq_putc(m, '\n');
	return 0;
}

static const struct seq_operations probes_seq_op = {
	.start	= probes_seq_start,
	.next	= probes_seq_next,
	.stop	= probes_seq_stop,
	.show	= probes_seq_show
};

static int probes_open(struct inode *inode, struct file *file)
{
	int ret;

	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
		ret = cleanup_all_probes();
		if (ret)
			return ret;
	}

	return seq_open(file, &probes_seq_op);
}

static ssize_t probes_write(struct file *file, const char __user *buffer,
			    size_t count, loff_t *ppos)
{
	return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe);
}

static const struct file_operations uprobe_events_ops = {
	.owner		= THIS_MODULE,
	.open		= probes_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
	.write		= probes_write,
};

/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
	struct trace_uprobe *tu = v;

	seq_printf(m, "  %s %-44s %15lu\n", tu->filename,
			ftrace_event_name(&tu->tp.call), tu->nhit);
	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 uprobe_profile_ops = {
	.owner		= THIS_MODULE,
	.open		= profile_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

struct uprobe_cpu_buffer {
	struct mutex mutex;
	void *buf;
};
static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
static int uprobe_buffer_refcnt;

static int uprobe_buffer_init(void)
{
	int cpu, err_cpu;

	uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer);
	if (uprobe_cpu_buffer == NULL)
		return -ENOMEM;

	for_each_possible_cpu(cpu) {
		struct page *p = alloc_pages_node(cpu_to_node(cpu),
						  GFP_KERNEL, 0);
		if (p == NULL) {
			err_cpu = cpu;
			goto err;
		}
		per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p);
		mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex);
	}

	return 0;

err:
	for_each_possible_cpu(cpu) {
		if (cpu == err_cpu)
			break;
		free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf);
	}

	free_percpu(uprobe_cpu_buffer);
	return -ENOMEM;
}

static int uprobe_buffer_enable(void)
{
	int ret = 0;

	BUG_ON(!mutex_is_locked(&event_mutex));

	if (uprobe_buffer_refcnt++ == 0) {
		ret = uprobe_buffer_init();
		if (ret < 0)
			uprobe_buffer_refcnt--;
	}

	return ret;
}

static void uprobe_buffer_disable(void)
{
	int cpu;

	BUG_ON(!mutex_is_locked(&event_mutex));

	if (--uprobe_buffer_refcnt == 0) {
		for_each_possible_cpu(cpu)
			free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer,
							     cpu)->buf);

		free_percpu(uprobe_cpu_buffer);
		uprobe_cpu_buffer = NULL;
	}
}

static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
{
	struct uprobe_cpu_buffer *ucb;
	int cpu;

	cpu = raw_smp_processor_id();
	ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu);

	/*
	 * Use per-cpu buffers for fastest access, but we might migrate
	 * so the mutex makes sure we have sole access to it.
	 */
	mutex_lock(&ucb->mutex);

	return ucb;
}

static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
{
	mutex_unlock(&ucb->mutex);
}

static void __uprobe_trace_func(struct trace_uprobe *tu,
				unsigned long func, struct pt_regs *regs,
				struct uprobe_cpu_buffer *ucb, int dsize,
				struct ftrace_event_file *ftrace_file)
{
	struct uprobe_trace_entry_head *entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	void *data;
	int size, esize;
	struct ftrace_event_call *call = &tu->tp.call;

	WARN_ON(call != ftrace_file->event_call);

	if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE))
		return;

	if (ftrace_trigger_soft_disabled(ftrace_file))
		return;

	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
	size = esize + tu->tp.size + dsize;
	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
						call->event.type, size, 0, 0);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	if (is_ret_probe(tu)) {
		entry->vaddr[0] = func;
		entry->vaddr[1] = instruction_pointer(regs);
		data = DATAOF_TRACE_ENTRY(entry, true);
	} else {
		entry->vaddr[0] = instruction_pointer(regs);
		data = DATAOF_TRACE_ENTRY(entry, false);
	}

	memcpy(data, ucb->buf, tu->tp.size + dsize);

	event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0);
}

/* uprobe handler */
static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
			     struct uprobe_cpu_buffer *ucb, int dsize)
{
	struct event_file_link *link;

	if (is_ret_probe(tu))
		return 0;

	rcu_read_lock();
	list_for_each_entry_rcu(link, &tu->tp.files, list)
		__uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file);
	rcu_read_unlock();

	return 0;
}

static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
				 struct pt_regs *regs,
				 struct uprobe_cpu_buffer *ucb, int dsize)
{
	struct event_file_link *link;

	rcu_read_lock();
	list_for_each_entry_rcu(link, &tu->tp.files, list)
		__uprobe_trace_func(tu, func, regs, ucb, dsize, link->file);
	rcu_read_unlock();
}

/* Event entry printers */
static enum print_line_t
print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event)
{
	struct uprobe_trace_entry_head *entry;
	struct trace_seq *s = &iter->seq;
	struct trace_uprobe *tu;
	u8 *data;
	int i;

	entry = (struct uprobe_trace_entry_head *)iter->ent;
	tu = container_of(event, struct trace_uprobe, tp.call.event);

	if (is_ret_probe(tu)) {
		trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)",
				 ftrace_event_name(&tu->tp.call),
				 entry->vaddr[1], entry->vaddr[0]);
		data = DATAOF_TRACE_ENTRY(entry, true);
	} else {
		trace_seq_printf(s, "%s: (0x%lx)",
				 ftrace_event_name(&tu->tp.call),
				 entry->vaddr[0]);
		data = DATAOF_TRACE_ENTRY(entry, false);
	}

	for (i = 0; i < tu->tp.nr_args; i++) {
		struct probe_arg *parg = &tu->tp.args[i];

		if (!parg->type->print(s, parg->name, data + parg->offset, entry))
			goto out;
	}

	trace_seq_putc(s, '\n');

 out:
	return trace_handle_return(s);
}

typedef bool (*filter_func_t)(struct uprobe_consumer *self,
				enum uprobe_filter_ctx ctx,
				struct mm_struct *mm);

static int
probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
		   filter_func_t filter)
{
	bool enabled = trace_probe_is_enabled(&tu->tp);
	struct event_file_link *link = NULL;
	int ret;

	if (file) {
		if (tu->tp.flags & TP_FLAG_PROFILE)
			return -EINTR;

		link = kmalloc(sizeof(*link), GFP_KERNEL);
		if (!link)
			return -ENOMEM;

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

		tu->tp.flags |= TP_FLAG_TRACE;
	} else {
		if (tu->tp.flags & TP_FLAG_TRACE)
			return -EINTR;

		tu->tp.flags |= TP_FLAG_PROFILE;
	}

	WARN_ON(!uprobe_filter_is_empty(&tu->filter));

	if (enabled)
		return 0;

	ret = uprobe_buffer_enable();
	if (ret)
		goto err_flags;

	tu->consumer.filter = filter;
	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
	if (ret)
		goto err_buffer;

	return 0;

 err_buffer:
	uprobe_buffer_disable();

 err_flags:
	if (file) {
		list_del(&link->list);
		kfree(link);
		tu->tp.flags &= ~TP_FLAG_TRACE;
	} else {
		tu->tp.flags &= ~TP_FLAG_PROFILE;
	}
	return ret;
}

static void
probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file)
{
	if (!trace_probe_is_enabled(&tu->tp))
		return;

	if (file) {
		struct event_file_link *link;

		link = find_event_file_link(&tu->tp, file);
		if (!link)
			return;

		list_del_rcu(&link->list);
		/* synchronize with u{,ret}probe_trace_func */
		synchronize_sched();
		kfree(link);

		if (!list_empty(&tu->tp.files))
			return;
	}

	WARN_ON(!uprobe_filter_is_empty(&tu->filter));

	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
	tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;

	uprobe_buffer_disable();
}

static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
{
	int ret, i, size;
	struct uprobe_trace_entry_head field;
	struct trace_uprobe *tu = event_call->data;

	if (is_ret_probe(tu)) {
		DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0);
		DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0);
		size = SIZEOF_TRACE_ENTRY(true);
	} else {
		DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0);
		size = SIZEOF_TRACE_ENTRY(false);
	}
	/* Set argument names as fields */
	for (i = 0; i < tu->tp.nr_args; i++) {
		struct probe_arg *parg = &tu->tp.args[i];

		ret = trace_define_field(event_call, parg->type->fmttype,
					 parg->name, size + parg->offset,
					 parg->type->size, parg->type->is_signed,
					 FILTER_OTHER);

		if (ret)
			return ret;
	}
	return 0;
}

#ifdef CONFIG_PERF_EVENTS
static bool
__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
{
	struct perf_event *event;

	if (filter->nr_systemwide)
		return true;

	list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
		if (event->hw.tp_target->mm == mm)
			return true;
	}

	return false;
}

static inline bool
uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
{
	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
}

static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
{
	bool done;

	write_lock(&tu->filter.rwlock);
	if (event->hw.tp_target) {
		list_del(&event->hw.tp_list);
		done = tu->filter.nr_systemwide ||
			(event->hw.tp_target->flags & PF_EXITING) ||
			uprobe_filter_event(tu, event);
	} else {
		tu->filter.nr_systemwide--;
		done = tu->filter.nr_systemwide;
	}
	write_unlock(&tu->filter.rwlock);

	if (!done)
		return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);

	return 0;
}

static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
{
	bool done;
	int err;

	write_lock(&tu->filter.rwlock);
	if (event->hw.tp_target) {
		/*
		 * event->parent != NULL means copy_process(), we can avoid
		 * uprobe_apply(). current->mm must be probed and we can rely
		 * on dup_mmap() which preserves the already installed bp's.
		 *
		 * attr.enable_on_exec means that exec/mmap will install the
		 * breakpoints we need.
		 */
		done = tu->filter.nr_systemwide ||
			event->parent || event->attr.enable_on_exec ||
			uprobe_filter_event(tu, event);
		list_add(&event->hw.tp_list, &tu->filter.perf_events);
	} else {
		done = tu->filter.nr_systemwide;
		tu->filter.nr_systemwide++;
	}
	write_unlock(&tu->filter.rwlock);

	err = 0;
	if (!done) {
		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
		if (err)
			uprobe_perf_close(tu, event);
	}
	return err;
}

static bool uprobe_perf_filter(struct uprobe_consumer *uc,
				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
	struct trace_uprobe *tu;
	int ret;

	tu = container_of(uc, struct trace_uprobe, consumer);
	read_lock(&tu->filter.rwlock);
	ret = __uprobe_perf_filter(&tu->filter, mm);
	read_unlock(&tu->filter.rwlock);

	return ret;
}

static void __uprobe_perf_func(struct trace_uprobe *tu,
			       unsigned long func, struct pt_regs *regs,
			       struct uprobe_cpu_buffer *ucb, int dsize)
{
	struct ftrace_event_call *call = &tu->tp.call;
	struct uprobe_trace_entry_head *entry;
	struct hlist_head *head;
	void *data;
	int size, esize;
	int rctx;

	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));

	size = esize + tu->tp.size + dsize;
	size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
		return;

	preempt_disable();
	head = this_cpu_ptr(call->perf_events);
	if (hlist_empty(head))
		goto out;

	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
	if (!entry)
		goto out;

	if (is_ret_probe(tu)) {
		entry->vaddr[0] = func;
		entry->vaddr[1] = instruction_pointer(regs);
		data = DATAOF_TRACE_ENTRY(entry, true);
	} else {
		entry->vaddr[0] = instruction_pointer(regs);
		data = DATAOF_TRACE_ENTRY(entry, false);
	}

	memcpy(data, ucb->buf, tu->tp.size + dsize);

	if (size - esize > tu->tp.size + dsize) {
		int len = tu->tp.size + dsize;

		memset(data + len, 0, size - esize - len);
	}

	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 out:
	preempt_enable();
}

/* uprobe profile handler */
static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
			    struct uprobe_cpu_buffer *ucb, int dsize)
{
	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
		return UPROBE_HANDLER_REMOVE;

	if (!is_ret_probe(tu))
		__uprobe_perf_func(tu, 0, regs, ucb, dsize);
	return 0;
}

static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
				struct pt_regs *regs,
				struct uprobe_cpu_buffer *ucb, int dsize)
{
	__uprobe_perf_func(tu, func, regs, ucb, dsize);
}
#endif	/* CONFIG_PERF_EVENTS */

static int
trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
		      void *data)
{
	struct trace_uprobe *tu = event->data;
	struct ftrace_event_file *file = data;

	switch (type) {
	case TRACE_REG_REGISTER:
		return probe_event_enable(tu, file, NULL);

	case TRACE_REG_UNREGISTER:
		probe_event_disable(tu, file);
		return 0;

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return probe_event_enable(tu, NULL, uprobe_perf_filter);

	case TRACE_REG_PERF_UNREGISTER:
		probe_event_disable(tu, NULL);
		return 0;

	case TRACE_REG_PERF_OPEN:
		return uprobe_perf_open(tu, data);

	case TRACE_REG_PERF_CLOSE:
		return uprobe_perf_close(tu, data);

#endif
	default:
		return 0;
	}
	return 0;
}

static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
{
	struct trace_uprobe *tu;
	struct uprobe_dispatch_data udd;
	struct uprobe_cpu_buffer *ucb;
	int dsize, esize;
	int ret = 0;


	tu = container_of(con, struct trace_uprobe, consumer);
	tu->nhit++;

	udd.tu = tu;
	udd.bp_addr = instruction_pointer(regs);

	current->utask->vaddr = (unsigned long) &udd;

	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
		return 0;

	dsize = __get_data_size(&tu->tp, regs);
	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));

	ucb = uprobe_buffer_get();
	store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);

	if (tu->tp.flags & TP_FLAG_TRACE)
		ret |= uprobe_trace_func(tu, regs, ucb, dsize);

#ifdef CONFIG_PERF_EVENTS
	if (tu->tp.flags & TP_FLAG_PROFILE)
		ret |= uprobe_perf_func(tu, regs, ucb, dsize);
#endif
	uprobe_buffer_put(ucb);
	return ret;
}

static int uretprobe_dispatcher(struct uprobe_consumer *con,
				unsigned long func, struct pt_regs *regs)
{
	struct trace_uprobe *tu;
	struct uprobe_dispatch_data udd;
	struct uprobe_cpu_buffer *ucb;
	int dsize, esize;

	tu = container_of(con, struct trace_uprobe, consumer);

	udd.tu = tu;
	udd.bp_addr = func;

	current->utask->vaddr = (unsigned long) &udd;

	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
		return 0;

	dsize = __get_data_size(&tu->tp, regs);
	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));

	ucb = uprobe_buffer_get();
	store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);

	if (tu->tp.flags & TP_FLAG_TRACE)
		uretprobe_trace_func(tu, func, regs, ucb, dsize);

#ifdef CONFIG_PERF_EVENTS
	if (tu->tp.flags & TP_FLAG_PROFILE)
		uretprobe_perf_func(tu, func, regs, ucb, dsize);
#endif
	uprobe_buffer_put(ucb);
	return 0;
}

static struct trace_event_functions uprobe_funcs = {
	.trace		= print_uprobe_event
};

static int register_uprobe_event(struct trace_uprobe *tu)
{
	struct ftrace_event_call *call = &tu->tp.call;
	int ret;

	/* Initialize ftrace_event_call */
	INIT_LIST_HEAD(&call->class->fields);
	call->event.funcs = &uprobe_funcs;
	call->class->define_fields = uprobe_event_define_fields;

	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
		return -ENOMEM;

	ret = register_ftrace_event(&call->event);
	if (!ret) {
		kfree(call->print_fmt);
		return -ENODEV;
	}

	call->class->reg = trace_uprobe_register;
	call->data = tu;
	ret = trace_add_event_call(call);

	if (ret) {
		pr_info("Failed to register uprobe event: %s\n",
			ftrace_event_name(call));
		kfree(call->print_fmt);
		unregister_ftrace_event(&call->event);
	}

	return ret;
}

static int unregister_uprobe_event(struct trace_uprobe *tu)
{
	int ret;

	/* tu->event is unregistered in trace_remove_event_call() */
	ret = trace_remove_event_call(&tu->tp.call);
	if (ret)
		return ret;
	kfree(tu->tp.call.print_fmt);
	tu->tp.call.print_fmt = NULL;
	return 0;
}

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

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

	trace_create_file("uprobe_events", 0644, d_tracer,
				    NULL, &uprobe_events_ops);
	/* Profile interface */
	trace_create_file("uprobe_profile", 0444, d_tracer,
				    NULL, &uprobe_profile_ops);
	return 0;
}

fs_initcall(init_uprobe_trace);