summaryrefslogtreecommitdiffstats
path: root/kernel/kprobes.c
blob: c3340e836c37bbb8c59abe4c09e856ae05383669 (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
/*
 *  Kernel Probes (KProbes)
 *  kernel/kprobes.c
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * 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, 2002, 2004
 *
 * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
 *		Probes initial implementation (includes suggestions from
 *		Rusty Russell).
 * 2004-Aug	Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with
 *		hlists and exceptions notifier as suggested by Andi Kleen.
 * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
 *		interface to access function arguments.
 * 2004-Sep	Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes
 *		exceptions notifier to be first on the priority list.
 * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
 *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> added function-return probes.
 */
#include <linux/kprobes.h>
#include <linux/hash.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/module.h>
#include <linux/moduleloader.h>
#include <linux/kallsyms.h>
#include <linux/freezer.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/kdebug.h>
#include <linux/memory.h>
#include <linux/ftrace.h>

#include <asm-generic/sections.h>
#include <asm/cacheflush.h>
#include <asm/errno.h>
#include <asm/uaccess.h>

#define KPROBE_HASH_BITS 6
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)


/*
 * Some oddball architectures like 64bit powerpc have function descriptors
 * so this must be overridable.
 */
#ifndef kprobe_lookup_name
#define kprobe_lookup_name(name, addr) \
	addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
#endif

static int kprobes_initialized;
static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];

/* NOTE: change this value only with kprobe_mutex held */
static bool kprobes_all_disarmed;

static DEFINE_MUTEX(kprobe_mutex);	/* Protects kprobe_table */
static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
static struct {
	spinlock_t lock ____cacheline_aligned_in_smp;
} kretprobe_table_locks[KPROBE_TABLE_SIZE];

static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
{
	return &(kretprobe_table_locks[hash].lock);
}

/*
 * Normally, functions that we'd want to prohibit kprobes in, are marked
 * __kprobes. But, there are cases where such functions already belong to
 * a different section (__sched for preempt_schedule)
 *
 * For such cases, we now have a blacklist
 */
static struct kprobe_blackpoint kprobe_blacklist[] = {
	{"preempt_schedule",},
	{"native_get_debugreg",},
	{"irq_entries_start",},
	{"common_interrupt",},
	{NULL}    /* Terminator */
};

#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
/*
 * kprobe->ainsn.insn points to the copy of the instruction to be
 * single-stepped. x86_64, POWER4 and above have no-exec support and
 * stepping on the instruction on a vmalloced/kmalloced/data page
 * is a recipe for disaster
 */
#define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))

struct kprobe_insn_page {
	struct list_head list;
	kprobe_opcode_t *insns;		/* Page of instruction slots */
	char slot_used[INSNS_PER_PAGE];
	int nused;
	int ngarbage;
};

enum kprobe_slot_state {
	SLOT_CLEAN = 0,
	SLOT_DIRTY = 1,
	SLOT_USED = 2,
};

static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
static LIST_HEAD(kprobe_insn_pages);
static int kprobe_garbage_slots;
static int collect_garbage_slots(void);

/**
 * __get_insn_slot() - Find a slot on an executable page for an instruction.
 * We allocate an executable page if there's no room on existing ones.
 */
static kprobe_opcode_t __kprobes *__get_insn_slot(void)
{
	struct kprobe_insn_page *kip;

 retry:
	list_for_each_entry(kip, &kprobe_insn_pages, list) {
		if (kip->nused < INSNS_PER_PAGE) {
			int i;
			for (i = 0; i < INSNS_PER_PAGE; i++) {
				if (kip->slot_used[i] == SLOT_CLEAN) {
					kip->slot_used[i] = SLOT_USED;
					kip->nused++;
					return kip->insns + (i * MAX_INSN_SIZE);
				}
			}
			/* Surprise!  No unused slots.  Fix kip->nused. */
			kip->nused = INSNS_PER_PAGE;
		}
	}

	/* If there are any garbage slots, collect it and try again. */
	if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
		goto retry;
	}
	/* All out of space.  Need to allocate a new page. Use slot 0. */
	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
	if (!kip)
		return NULL;

	/*
	 * Use module_alloc so this page is within +/- 2GB of where the
	 * kernel image and loaded module images reside. This is required
	 * so x86_64 can correctly handle the %rip-relative fixups.
	 */
	kip->insns = module_alloc(PAGE_SIZE);
	if (!kip->insns) {
		kfree(kip);
		return NULL;
	}
	INIT_LIST_HEAD(&kip->list);
	list_add(&kip->list, &kprobe_insn_pages);
	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
	kip->slot_used[0] = SLOT_USED;
	kip->nused = 1;
	kip->ngarbage = 0;
	return kip->insns;
}

kprobe_opcode_t __kprobes *get_insn_slot(void)
{
	kprobe_opcode_t *ret;
	mutex_lock(&kprobe_insn_mutex);
	ret = __get_insn_slot();
	mutex_unlock(&kprobe_insn_mutex);
	return ret;
}

/* Return 1 if all garbages are collected, otherwise 0. */
static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
{
	kip->slot_used[idx] = SLOT_CLEAN;
	kip->nused--;
	if (kip->nused == 0) {
		/*
		 * Page is no longer in use.  Free it unless
		 * it's the last one.  We keep the last one
		 * so as not to have to set it up again the
		 * next time somebody inserts a probe.
		 */
		if (!list_is_singular(&kprobe_insn_pages)) {
			list_del(&kip->list);
			module_free(NULL, kip->insns);
			kfree(kip);
		}
		return 1;
	}
	return 0;
}

static int __kprobes collect_garbage_slots(void)
{
	struct kprobe_insn_page *kip, *next;

	/* Ensure no-one is interrupted on the garbages */
	synchronize_sched();

	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
		int i;
		if (kip->ngarbage == 0)
			continue;
		kip->ngarbage = 0;	/* we will collect all garbages */
		for (i = 0; i < INSNS_PER_PAGE; i++) {
			if (kip->slot_used[i] == SLOT_DIRTY &&
			    collect_one_slot(kip, i))
				break;
		}
	}
	kprobe_garbage_slots = 0;
	return 0;
}

void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
{
	struct kprobe_insn_page *kip;

	mutex_lock(&kprobe_insn_mutex);
	list_for_each_entry(kip, &kprobe_insn_pages, list) {
		if (kip->insns <= slot &&
		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
			int i = (slot - kip->insns) / MAX_INSN_SIZE;
			if (dirty) {
				kip->slot_used[i] = SLOT_DIRTY;
				kip->ngarbage++;
			} else
				collect_one_slot(kip, i);
			break;
		}
	}

	if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
		collect_garbage_slots();

	mutex_unlock(&kprobe_insn_mutex);
}
#endif

/* We have preemption disabled.. so it is safe to use __ versions */
static inline void set_kprobe_instance(struct kprobe *kp)
{
	__get_cpu_var(kprobe_instance) = kp;
}

static inline void reset_kprobe_instance(void)
{
	__get_cpu_var(kprobe_instance) = NULL;
}

/*
 * This routine is called either:
 * 	- under the kprobe_mutex - during kprobe_[un]register()
 * 				OR
 * 	- with preemption disabled - from arch/xxx/kernel/kprobes.c
 */
struct kprobe __kprobes *get_kprobe(void *addr)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;

	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
	hlist_for_each_entry_rcu(p, node, head, hlist) {
		if (p->addr == addr)
			return p;
	}
	return NULL;
}

/* Arm a kprobe with text_mutex */
static void __kprobes arm_kprobe(struct kprobe *kp)
{
	mutex_lock(&text_mutex);
	arch_arm_kprobe(kp);
	mutex_unlock(&text_mutex);
}

/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
	mutex_lock(&text_mutex);
	arch_disarm_kprobe(kp);
	mutex_unlock(&text_mutex);
}

/*
 * Aggregate handlers for multiple kprobes support - these handlers
 * take care of invoking the individual kprobe handlers on p->list
 */
static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct kprobe *kp;

	list_for_each_entry_rcu(kp, &p->list, list) {
		if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
			set_kprobe_instance(kp);
			if (kp->pre_handler(kp, regs))
				return 1;
		}
		reset_kprobe_instance();
	}
	return 0;
}

static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
					unsigned long flags)
{
	struct kprobe *kp;

	list_for_each_entry_rcu(kp, &p->list, list) {
		if (kp->post_handler && likely(!kprobe_disabled(kp))) {
			set_kprobe_instance(kp);
			kp->post_handler(kp, regs, flags);
			reset_kprobe_instance();
		}
	}
}

static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
					int trapnr)
{
	struct kprobe *cur = __get_cpu_var(kprobe_instance);

	/*
	 * if we faulted "during" the execution of a user specified
	 * probe handler, invoke just that probe's fault handler
	 */
	if (cur && cur->fault_handler) {
		if (cur->fault_handler(cur, regs, trapnr))
			return 1;
	}
	return 0;
}

static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct kprobe *cur = __get_cpu_var(kprobe_instance);
	int ret = 0;

	if (cur && cur->break_handler) {
		if (cur->break_handler(cur, regs))
			ret = 1;
	}
	reset_kprobe_instance();
	return ret;
}

/* Walks the list and increments nmissed count for multiprobe case */
void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
{
	struct kprobe *kp;
	if (p->pre_handler != aggr_pre_handler) {
		p->nmissed++;
	} else {
		list_for_each_entry_rcu(kp, &p->list, list)
			kp->nmissed++;
	}
	return;
}

void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
				struct hlist_head *head)
{
	struct kretprobe *rp = ri->rp;

	/* remove rp inst off the rprobe_inst_table */
	hlist_del(&ri->hlist);
	INIT_HLIST_NODE(&ri->hlist);
	if (likely(rp)) {
		spin_lock(&rp->lock);
		hlist_add_head(&ri->hlist, &rp->free_instances);
		spin_unlock(&rp->lock);
	} else
		/* Unregistering */
		hlist_add_head(&ri->hlist, head);
}

void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
			 struct hlist_head **head, unsigned long *flags)
{
	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
	spinlock_t *hlist_lock;

	*head = &kretprobe_inst_table[hash];
	hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_lock_irqsave(hlist_lock, *flags);
}

static void __kprobes kretprobe_table_lock(unsigned long hash,
	unsigned long *flags)
{
	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_lock_irqsave(hlist_lock, *flags);
}

void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
	unsigned long *flags)
{
	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
	spinlock_t *hlist_lock;

	hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_unlock_irqrestore(hlist_lock, *flags);
}

void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
{
	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_unlock_irqrestore(hlist_lock, *flags);
}

/*
 * This function is called from finish_task_switch when task tk becomes dead,
 * so that we can recycle any function-return probe instances associated
 * with this task. These left over instances represent probed functions
 * that have been called but will never return.
 */
void __kprobes kprobe_flush_task(struct task_struct *tk)
{
	struct kretprobe_instance *ri;
	struct hlist_head *head, empty_rp;
	struct hlist_node *node, *tmp;
	unsigned long hash, flags = 0;

	if (unlikely(!kprobes_initialized))
		/* Early boot.  kretprobe_table_locks not yet initialized. */
		return;

	hash = hash_ptr(tk, KPROBE_HASH_BITS);
	head = &kretprobe_inst_table[hash];
	kretprobe_table_lock(hash, &flags);
	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
		if (ri->task == tk)
			recycle_rp_inst(ri, &empty_rp);
	}
	kretprobe_table_unlock(hash, &flags);
	INIT_HLIST_HEAD(&empty_rp);
	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
		hlist_del(&ri->hlist);
		kfree(ri);
	}
}

static inline void free_rp_inst(struct kretprobe *rp)
{
	struct kretprobe_instance *ri;
	struct hlist_node *pos, *next;

	hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) {
		hlist_del(&ri->hlist);
		kfree(ri);
	}
}

static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
{
	unsigned long flags, hash;
	struct kretprobe_instance *ri;
	struct hlist_node *pos, *next;
	struct hlist_head *head;

	/* No race here */
	for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
		kretprobe_table_lock(hash, &flags);
		head = &kretprobe_inst_table[hash];
		hlist_for_each_entry_safe(ri, pos, next, head, hlist) {
			if (ri->rp == rp)
				ri->rp = NULL;
		}
		kretprobe_table_unlock(hash, &flags);
	}
	free_rp_inst(rp);
}

/*
 * Keep all fields in the kprobe consistent
 */
static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
{
	memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
	memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
}

/*
* Add the new probe to ap->list. Fail if this is the
* second jprobe at the address - two jprobes can't coexist
*/
static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
	if (p->break_handler) {
		if (ap->break_handler)
			return -EEXIST;
		list_add_tail_rcu(&p->list, &ap->list);
		ap->break_handler = aggr_break_handler;
	} else
		list_add_rcu(&p->list, &ap->list);
	if (p->post_handler && !ap->post_handler)
		ap->post_handler = aggr_post_handler;

	if (kprobe_disabled(ap) && !kprobe_disabled(p)) {
		ap->flags &= ~KPROBE_FLAG_DISABLED;
		if (!kprobes_all_disarmed)
			/* Arm the breakpoint again. */
			arm_kprobe(ap);
	}
	return 0;
}

/*
 * Fill in the required fields of the "manager kprobe". Replace the
 * earlier kprobe in the hlist with the manager kprobe
 */
static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
{
	copy_kprobe(p, ap);
	flush_insn_slot(ap);
	ap->addr = p->addr;
	ap->flags = p->flags;
	ap->pre_handler = aggr_pre_handler;
	ap->fault_handler = aggr_fault_handler;
	/* We don't care the kprobe which has gone. */
	if (p->post_handler && !kprobe_gone(p))
		ap->post_handler = aggr_post_handler;
	if (p->break_handler && !kprobe_gone(p))
		ap->break_handler = aggr_break_handler;

	INIT_LIST_HEAD(&ap->list);
	list_add_rcu(&p->list, &ap->list);

	hlist_replace_rcu(&p->hlist, &ap->hlist);
}

/*
 * This is the second or subsequent kprobe at the address - handle
 * the intricacies
 */
static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
					  struct kprobe *p)
{
	int ret = 0;
	struct kprobe *ap = old_p;

	if (old_p->pre_handler != aggr_pre_handler) {
		/* If old_p is not an aggr_probe, create new aggr_kprobe. */
		ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
		if (!ap)
			return -ENOMEM;
		add_aggr_kprobe(ap, old_p);
	}

	if (kprobe_gone(ap)) {
		/*
		 * Attempting to insert new probe at the same location that
		 * had a probe in the module vaddr area which already
		 * freed. So, the instruction slot has already been
		 * released. We need a new slot for the new probe.
		 */
		ret = arch_prepare_kprobe(ap);
		if (ret)
			/*
			 * Even if fail to allocate new slot, don't need to
			 * free aggr_probe. It will be used next time, or
			 * freed by unregister_kprobe.
			 */
			return ret;

		/*
		 * Clear gone flag to prevent allocating new slot again, and
		 * set disabled flag because it is not armed yet.
		 */
		ap->flags = (ap->flags & ~KPROBE_FLAG_GONE)
			    | KPROBE_FLAG_DISABLED;
	}

	copy_kprobe(ap, p);
	return add_new_kprobe(ap, p);
}

/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
{
	struct kprobe *kp;

	list_for_each_entry_rcu(kp, &p->list, list) {
		if (!kprobe_disabled(kp))
			/*
			 * There is an active probe on the list.
			 * We can't disable aggr_kprobe.
			 */
			return 0;
	}
	p->flags |= KPROBE_FLAG_DISABLED;
	return 1;
}

static int __kprobes in_kprobes_functions(unsigned long addr)
{
	struct kprobe_blackpoint *kb;

	if (addr >= (unsigned long)__kprobes_text_start &&
	    addr < (unsigned long)__kprobes_text_end)
		return -EINVAL;
	/*
	 * If there exists a kprobe_blacklist, verify and
	 * fail any probe registration in the prohibited area
	 */
	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
		if (kb->start_addr) {
			if (addr >= kb->start_addr &&
			    addr < (kb->start_addr + kb->range))
				return -EINVAL;
		}
	}
	return 0;
}

/*
 * If we have a symbol_name argument, look it up and add the offset field
 * to it. This way, we can specify a relative address to a symbol.
 */
static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
{
	kprobe_opcode_t *addr = p->addr;
	if (p->symbol_name) {
		if (addr)
			return NULL;
		kprobe_lookup_name(p->symbol_name, addr);
	}

	if (!addr)
		return NULL;
	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
}

/* Check passed kprobe is valid and return kprobe in kprobe_table. */
static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
{
	struct kprobe *old_p, *list_p;

	old_p = get_kprobe(p->addr);
	if (unlikely(!old_p))
		return NULL;

	if (p != old_p) {
		list_for_each_entry_rcu(list_p, &old_p->list, list)
			if (list_p == p)
			/* kprobe p is a valid probe */
				goto valid;
		return NULL;
	}
valid:
	return old_p;
}

/* Return error if the kprobe is being re-registered */
static inline int check_kprobe_rereg(struct kprobe *p)
{
	int ret = 0;
	struct kprobe *old_p;

	mutex_lock(&kprobe_mutex);
	old_p = __get_valid_kprobe(p);
	if (old_p)
		ret = -EINVAL;
	mutex_unlock(&kprobe_mutex);
	return ret;
}

int __kprobes register_kprobe(struct kprobe *p)
{
	int ret = 0;
	struct kprobe *old_p;
	struct module *probed_mod;
	kprobe_opcode_t *addr;

	addr = kprobe_addr(p);
	if (!addr)
		return -EINVAL;
	p->addr = addr;

	ret = check_kprobe_rereg(p);
	if (ret)
		return ret;

	preempt_disable();
	if (!kernel_text_address((unsigned long) p->addr) ||
	    in_kprobes_functions((unsigned long) p->addr) ||
	    ftrace_text_reserved(p->addr, p->addr)) {
		preempt_enable();
		return -EINVAL;
	}

	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
	p->flags &= KPROBE_FLAG_DISABLED;

	/*
	 * Check if are we probing a module.
	 */
	probed_mod = __module_text_address((unsigned long) p->addr);
	if (probed_mod) {
		/*
		 * We must hold a refcount of the probed module while updating
		 * its code to prohibit unexpected unloading.
		 */
		if (unlikely(!try_module_get(probed_mod))) {
			preempt_enable();
			return -EINVAL;
		}
		/*
		 * If the module freed .init.text, we couldn't insert
		 * kprobes in there.
		 */
		if (within_module_init((unsigned long)p->addr, probed_mod) &&
		    probed_mod->state != MODULE_STATE_COMING) {
			module_put(probed_mod);
			preempt_enable();
			return -EINVAL;
		}
	}
	preempt_enable();

	p->nmissed = 0;
	INIT_LIST_HEAD(&p->list);
	mutex_lock(&kprobe_mutex);
	old_p = get_kprobe(p->addr);
	if (old_p) {
		ret = register_aggr_kprobe(old_p, p);
		goto out;
	}

	mutex_lock(&text_mutex);
	ret = arch_prepare_kprobe(p);
	if (ret)
		goto out_unlock_text;

	INIT_HLIST_NODE(&p->hlist);
	hlist_add_head_rcu(&p->hlist,
		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);

	if (!kprobes_all_disarmed && !kprobe_disabled(p))
		arch_arm_kprobe(p);

out_unlock_text:
	mutex_unlock(&text_mutex);
out:
	mutex_unlock(&kprobe_mutex);

	if (probed_mod)
		module_put(probed_mod);

	return ret;
}
EXPORT_SYMBOL_GPL(register_kprobe);

/*
 * Unregister a kprobe without a scheduler synchronization.
 */
static int __kprobes __unregister_kprobe_top(struct kprobe *p)
{
	struct kprobe *old_p, *list_p;

	old_p = __get_valid_kprobe(p);
	if (old_p == NULL)
		return -EINVAL;

	if (old_p == p ||
	    (old_p->pre_handler == aggr_pre_handler &&
	     list_is_singular(&old_p->list))) {
		/*
		 * Only probe on the hash list. Disarm only if kprobes are
		 * enabled and not gone - otherwise, the breakpoint would
		 * already have been removed. We save on flushing icache.
		 */
		if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
			disarm_kprobe(p);
		hlist_del_rcu(&old_p->hlist);
	} else {
		if (p->break_handler && !kprobe_gone(p))
			old_p->break_handler = NULL;
		if (p->post_handler && !kprobe_gone(p)) {
			list_for_each_entry_rcu(list_p, &old_p->list, list) {
				if ((list_p != p) && (list_p->post_handler))
					goto noclean;
			}
			old_p->post_handler = NULL;
		}
noclean:
		list_del_rcu(&p->list);
		if (!kprobe_disabled(old_p)) {
			try_to_disable_aggr_kprobe(old_p);
			if (!kprobes_all_disarmed && kprobe_disabled(old_p))
				disarm_kprobe(old_p);
		}
	}
	return 0;
}

static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
{
	struct kprobe *old_p;

	if (list_empty(&p->list))
		arch_remove_kprobe(p);
	else if (list_is_singular(&p->list)) {
		/* "p" is the last child of an aggr_kprobe */
		old_p = list_entry(p->list.next, struct kprobe, list);
		list_del(&p->list);
		arch_remove_kprobe(old_p);
		kfree(old_p);
	}
}

int __kprobes register_kprobes(struct kprobe **kps, int num)
{
	int i, ret = 0;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		ret = register_kprobe(kps[i]);
		if (ret < 0) {
			if (i > 0)
				unregister_kprobes(kps, i);
			break;
		}
	}
	return ret;
}
EXPORT_SYMBOL_GPL(register_kprobes);

void __kprobes unregister_kprobe(struct kprobe *p)
{
	unregister_kprobes(&p, 1);
}
EXPORT_SYMBOL_GPL(unregister_kprobe);

void __kprobes unregister_kprobes(struct kprobe **kps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(kps[i]) < 0)
			kps[i]->addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++)
		if (kps[i]->addr)
			__unregister_kprobe_bottom(kps[i]);
}
EXPORT_SYMBOL_GPL(unregister_kprobes);

static struct notifier_block kprobe_exceptions_nb = {
	.notifier_call = kprobe_exceptions_notify,
	.priority = 0x7fffffff /* we need to be notified first */
};

unsigned long __weak arch_deref_entry_point(void *entry)
{
	return (unsigned long)entry;
}

int __kprobes register_jprobes(struct jprobe **jps, int num)
{
	struct jprobe *jp;
	int ret = 0, i;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		unsigned long addr;
		jp = jps[i];
		addr = arch_deref_entry_point(jp->entry);

		if (!kernel_text_address(addr))
			ret = -EINVAL;
		else {
			/* Todo: Verify probepoint is a function entry point */
			jp->kp.pre_handler = setjmp_pre_handler;
			jp->kp.break_handler = longjmp_break_handler;
			ret = register_kprobe(&jp->kp);
		}
		if (ret < 0) {
			if (i > 0)
				unregister_jprobes(jps, i);
			break;
		}
	}
	return ret;
}
EXPORT_SYMBOL_GPL(register_jprobes);

int __kprobes register_jprobe(struct jprobe *jp)
{
	return register_jprobes(&jp, 1);
}
EXPORT_SYMBOL_GPL(register_jprobe);

void __kprobes unregister_jprobe(struct jprobe *jp)
{
	unregister_jprobes(&jp, 1);
}
EXPORT_SYMBOL_GPL(unregister_jprobe);

void __kprobes unregister_jprobes(struct jprobe **jps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
			jps[i]->kp.addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++) {
		if (jps[i]->kp.addr)
			__unregister_kprobe_bottom(&jps[i]->kp);
	}
}
EXPORT_SYMBOL_GPL(unregister_jprobes);

#ifdef CONFIG_KRETPROBES
/*
 * This kprobe pre_handler is registered with every kretprobe. When probe
 * hits it will set up the return probe.
 */
static int __kprobes pre_handler_kretprobe(struct kprobe *p,
					   struct pt_regs *regs)
{
	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
	unsigned long hash, flags = 0;
	struct kretprobe_instance *ri;

	/*TODO: consider to only swap the RA after the last pre_handler fired */
	hash = hash_ptr(current, KPROBE_HASH_BITS);
	spin_lock_irqsave(&rp->lock, flags);
	if (!hlist_empty(&rp->free_instances)) {
		ri = hlist_entry(rp->free_instances.first,
				struct kretprobe_instance, hlist);
		hlist_del(&ri->hlist);
		spin_unlock_irqrestore(&rp->lock, flags);

		ri->rp = rp;
		ri->task = current;

		if (rp->entry_handler && rp->entry_handler(ri, regs))
			return 0;

		arch_prepare_kretprobe(ri, regs);

		/* XXX(hch): why is there no hlist_move_head? */
		INIT_HLIST_NODE(&ri->hlist);
		kretprobe_table_lock(hash, &flags);
		hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
		kretprobe_table_unlock(hash, &flags);
	} else {
		rp->nmissed++;
		spin_unlock_irqrestore(&rp->lock, flags);
	}
	return 0;
}

int __kprobes register_kretprobe(struct kretprobe *rp)
{
	int ret = 0;
	struct kretprobe_instance *inst;
	int i;
	void *addr;

	if (kretprobe_blacklist_size) {
		addr = kprobe_addr(&rp->kp);
		if (!addr)
			return -EINVAL;

		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			if (kretprobe_blacklist[i].addr == addr)
				return -EINVAL;
		}
	}

	rp->kp.pre_handler = pre_handler_kretprobe;
	rp->kp.post_handler = NULL;
	rp->kp.fault_handler = NULL;
	rp->kp.break_handler = NULL;

	/* Pre-allocate memory for max kretprobe instances */
	if (rp->maxactive <= 0) {
#ifdef CONFIG_PREEMPT
		rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus());
#else
		rp->maxactive = num_possible_cpus();
#endif
	}
	spin_lock_init(&rp->lock);
	INIT_HLIST_HEAD(&rp->free_instances);
	for (i = 0; i < rp->maxactive; i++) {
		inst = kmalloc(sizeof(struct kretprobe_instance) +
			       rp->data_size, GFP_KERNEL);
		if (inst == NULL) {
			free_rp_inst(rp);
			return -ENOMEM;
		}
		INIT_HLIST_NODE(&inst->hlist);
		hlist_add_head(&inst->hlist, &rp->free_instances);
	}

	rp->nmissed = 0;
	/* Establish function entry probe point */
	ret = register_kprobe(&rp->kp);
	if (ret != 0)
		free_rp_inst(rp);
	return ret;
}
EXPORT_SYMBOL_GPL(register_kretprobe);

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	int ret = 0, i;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		ret = register_kretprobe(rps[i]);
		if (ret < 0) {
			if (i > 0)
				unregister_kretprobes(rps, i);
			break;
		}
	}
	return ret;
}
EXPORT_SYMBOL_GPL(register_kretprobes);

void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
	unregister_kretprobes(&rp, 1);
}
EXPORT_SYMBOL_GPL(unregister_kretprobe);

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
			rps[i]->kp.addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++) {
		if (rps[i]->kp.addr) {
			__unregister_kprobe_bottom(&rps[i]->kp);
			cleanup_rp_inst(rps[i]);
		}
	}
}
EXPORT_SYMBOL_GPL(unregister_kretprobes);

#else /* CONFIG_KRETPROBES */
int __kprobes register_kretprobe(struct kretprobe *rp)
{
	return -ENOSYS;
}
EXPORT_SYMBOL_GPL(register_kretprobe);

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	return -ENOSYS;
}
EXPORT_SYMBOL_GPL(register_kretprobes);

void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
}
EXPORT_SYMBOL_GPL(unregister_kretprobe);

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
}
EXPORT_SYMBOL_GPL(unregister_kretprobes);

static int __kprobes pre_handler_kretprobe(struct kprobe *p,
					   struct pt_regs *regs)
{
	return 0;
}

#endif /* CONFIG_KRETPROBES */

/* Set the kprobe gone and remove its instruction buffer. */
static void __kprobes kill_kprobe(struct kprobe *p)
{
	struct kprobe *kp;

	p->flags |= KPROBE_FLAG_GONE;
	if (p->pre_handler == aggr_pre_handler) {
		/*
		 * If this is an aggr_kprobe, we have to list all the
		 * chained probes and mark them GONE.
		 */
		list_for_each_entry_rcu(kp, &p->list, list)
			kp->flags |= KPROBE_FLAG_GONE;
		p->post_handler = NULL;
		p->break_handler = NULL;
	}
	/*
	 * Here, we can remove insn_slot safely, because no thread calls
	 * the original probed function (which will be freed soon) any more.
	 */
	arch_remove_kprobe(p);
}

void __kprobes dump_kprobe(struct kprobe *kp)
{
	printk(KERN_WARNING "Dumping kprobe:\n");
	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
	       kp->symbol_name, kp->addr, kp->offset);
}

/* Module notifier call back, checking kprobes on the module */
static int __kprobes kprobes_module_callback(struct notifier_block *nb,
					     unsigned long val, void *data)
{
	struct module *mod = data;
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;
	int checkcore = (val == MODULE_STATE_GOING);

	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
		return NOTIFY_DONE;

	/*
	 * When MODULE_STATE_GOING was notified, both of module .text and
	 * .init.text sections would be freed. When MODULE_STATE_LIVE was
	 * notified, only .init.text section would be freed. We need to
	 * disable kprobes which have been inserted in the sections.
	 */
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist)
			if (within_module_init((unsigned long)p->addr, mod) ||
			    (checkcore &&
			     within_module_core((unsigned long)p->addr, mod))) {
				/*
				 * The vaddr this probe is installed will soon
				 * be vfreed buy not synced to disk. Hence,
				 * disarming the breakpoint isn't needed.
				 */
				kill_kprobe(p);
			}
	}
	mutex_unlock(&kprobe_mutex);
	return NOTIFY_DONE;
}

static struct notifier_block kprobe_module_nb = {
	.notifier_call = kprobes_module_callback,
	.priority = 0
};

static int __init init_kprobes(void)
{
	int i, err = 0;
	unsigned long offset = 0, size = 0;
	char *modname, namebuf[128];
	const char *symbol_name;
	void *addr;
	struct kprobe_blackpoint *kb;

	/* FIXME allocate the probe table, currently defined statically */
	/* initialize all list heads */
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		INIT_HLIST_HEAD(&kprobe_table[i]);
		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
		spin_lock_init(&(kretprobe_table_locks[i].lock));
	}

	/*
	 * Lookup and populate the kprobe_blacklist.
	 *
	 * Unlike the kretprobe blacklist, we'll need to determine
	 * the range of addresses that belong to the said functions,
	 * since a kprobe need not necessarily be at the beginning
	 * of a function.
	 */
	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
		kprobe_lookup_name(kb->name, addr);
		if (!addr)
			continue;

		kb->start_addr = (unsigned long)addr;
		symbol_name = kallsyms_lookup(kb->start_addr,
				&size, &offset, &modname, namebuf);
		if (!symbol_name)
			kb->range = 0;
		else
			kb->range = size;
	}

	if (kretprobe_blacklist_size) {
		/* lookup the function address from its name */
		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			kprobe_lookup_name(kretprobe_blacklist[i].name,
					   kretprobe_blacklist[i].addr);
			if (!kretprobe_blacklist[i].addr)
				printk("kretprobe: lookup failed: %s\n",
				       kretprobe_blacklist[i].name);
		}
	}

	/* By default, kprobes are armed */
	kprobes_all_disarmed = false;

	err = arch_init_kprobes();
	if (!err)
		err = register_die_notifier(&kprobe_exceptions_nb);
	if (!err)
		err = register_module_notifier(&kprobe_module_nb);

	kprobes_initialized = (err == 0);

	if (!err)
		init_test_probes();
	return err;
}

#ifdef CONFIG_DEBUG_FS
static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
		const char *sym, int offset,char *modname)
{
	char *kprobe_type;

	if (p->pre_handler == pre_handler_kretprobe)
		kprobe_type = "r";
	else if (p->pre_handler == setjmp_pre_handler)
		kprobe_type = "j";
	else
		kprobe_type = "k";
	if (sym)
		seq_printf(pi, "%p  %s  %s+0x%x  %s %s%s\n",
			p->addr, kprobe_type, sym, offset,
			(modname ? modname : " "),
			(kprobe_gone(p) ? "[GONE]" : ""),
			((kprobe_disabled(p) && !kprobe_gone(p)) ?
			 "[DISABLED]" : ""));
	else
		seq_printf(pi, "%p  %s  %p %s%s\n",
			p->addr, kprobe_type, p->addr,
			(kprobe_gone(p) ? "[GONE]" : ""),
			((kprobe_disabled(p) && !kprobe_gone(p)) ?
			 "[DISABLED]" : ""));
}

static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
{
	return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL;
}

static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
{
	(*pos)++;
	if (*pos >= KPROBE_TABLE_SIZE)
		return NULL;
	return pos;
}

static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v)
{
	/* Nothing to do */
}

static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p, *kp;
	const char *sym = NULL;
	unsigned int i = *(loff_t *) v;
	unsigned long offset = 0;
	char *modname, namebuf[128];

	head = &kprobe_table[i];
	preempt_disable();
	hlist_for_each_entry_rcu(p, node, head, hlist) {
		sym = kallsyms_lookup((unsigned long)p->addr, NULL,
					&offset, &modname, namebuf);
		if (p->pre_handler == aggr_pre_handler) {
			list_for_each_entry_rcu(kp, &p->list, list)
				report_probe(pi, kp, sym, offset, modname);
		} else
			report_probe(pi, p, sym, offset, modname);
	}
	preempt_enable();
	return 0;
}

static const struct seq_operations kprobes_seq_ops = {
	.start = kprobe_seq_start,
	.next  = kprobe_seq_next,
	.stop  = kprobe_seq_stop,
	.show  = show_kprobe_addr
};

static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
{
	return seq_open(filp, &kprobes_seq_ops);
}

static const struct file_operations debugfs_kprobes_operations = {
	.open           = kprobes_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = seq_release,
};

/* Disable one kprobe */
int __kprobes disable_kprobe(struct kprobe *kp)
{
	int ret = 0;
	struct kprobe *p;

	mutex_lock(&kprobe_mutex);

	/* Check whether specified probe is valid. */
	p = __get_valid_kprobe(kp);
	if (unlikely(p == NULL)) {
		ret = -EINVAL;
		goto out;
	}

	/* If the probe is already disabled (or gone), just return */
	if (kprobe_disabled(kp))
		goto out;

	kp->flags |= KPROBE_FLAG_DISABLED;
	if (p != kp)
		/* When kp != p, p is always enabled. */
		try_to_disable_aggr_kprobe(p);

	if (!kprobes_all_disarmed && kprobe_disabled(p))
		disarm_kprobe(p);
out:
	mutex_unlock(&kprobe_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(disable_kprobe);

/* Enable one kprobe */
int __kprobes enable_kprobe(struct kprobe *kp)
{
	int ret = 0;
	struct kprobe *p;

	mutex_lock(&kprobe_mutex);

	/* Check whether specified probe is valid. */
	p = __get_valid_kprobe(kp);
	if (unlikely(p == NULL)) {
		ret = -EINVAL;
		goto out;
	}

	if (kprobe_gone(kp)) {
		/* This kprobe has gone, we couldn't enable it. */
		ret = -EINVAL;
		goto out;
	}

	if (!kprobes_all_disarmed && kprobe_disabled(p))
		arm_kprobe(p);

	p->flags &= ~KPROBE_FLAG_DISABLED;
	if (p != kp)
		kp->flags &= ~KPROBE_FLAG_DISABLED;
out:
	mutex_unlock(&kprobe_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(enable_kprobe);

static void __kprobes arm_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are armed, just return */
	if (!kprobes_all_disarmed)
		goto already_enabled;

	mutex_lock(&text_mutex);
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist)
			if (!kprobe_disabled(p))
				arch_arm_kprobe(p);
	}
	mutex_unlock(&text_mutex);

	kprobes_all_disarmed = false;
	printk(KERN_INFO "Kprobes globally enabled\n");

already_enabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

static void __kprobes disarm_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are already disarmed, just return */
	if (kprobes_all_disarmed)
		goto already_disabled;

	kprobes_all_disarmed = true;
	printk(KERN_INFO "Kprobes globally disabled\n");
	mutex_lock(&text_mutex);
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist) {
			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
				arch_disarm_kprobe(p);
		}
	}

	mutex_unlock(&text_mutex);
	mutex_unlock(&kprobe_mutex);
	/* Allow all currently running kprobes to complete */
	synchronize_sched();
	return;

already_disabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

/*
 * XXX: The debugfs bool file interface doesn't allow for callbacks
 * when the bool state is switched. We can reuse that facility when
 * available
 */
static ssize_t read_enabled_file_bool(struct file *file,
	       char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[3];

	if (!kprobes_all_disarmed)
		buf[0] = '1';
	else
		buf[0] = '0';
	buf[1] = '\n';
	buf[2] = 0x00;
	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
}

static ssize_t write_enabled_file_bool(struct file *file,
	       const char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[32];
	int buf_size;

	buf_size = min(count, (sizeof(buf)-1));
	if (copy_from_user(buf, user_buf, buf_size))
		return -EFAULT;

	switch (buf[0]) {
	case 'y':
	case 'Y':
	case '1':
		arm_all_kprobes();
		break;
	case 'n':
	case 'N':
	case '0':
		disarm_all_kprobes();
		break;
	}

	return count;
}

static const struct file_operations fops_kp = {
	.read =         read_enabled_file_bool,
	.write =        write_enabled_file_bool,
};

static int __kprobes debugfs_kprobe_init(void)
{
	struct dentry *dir, *file;
	unsigned int value = 1;

	dir = debugfs_create_dir("kprobes", NULL);
	if (!dir)
		return -ENOMEM;

	file = debugfs_create_file("list", 0444, dir, NULL,
				&debugfs_kprobes_operations);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	file = debugfs_create_file("enabled", 0600, dir,
					&value, &fops_kp);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	return 0;
}

late_initcall(debugfs_kprobe_init);
#endif /* CONFIG_DEBUG_FS */

module_init(init_kprobes);

/* defined in arch/.../kernel/kprobes.c */
EXPORT_SYMBOL_GPL(jprobe_return);
OpenPOWER on IntegriCloud