forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
kprobes.c
2039 lines (1755 loc) · 50.3 KB
/
kprobes.c
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
/*
* 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 <[email protected]> Kernel
* Probes initial implementation (includes suggestions from
* Rusty Russell).
* 2004-Aug Updated by Prasanna S Panchamukhi <[email protected]> with
* hlists and exceptions notifier as suggested by Andi Kleen.
* 2004-July Suparna Bhattacharya <[email protected]> added jumper probes
* interface to access function arguments.
* 2004-Sep Prasanna S Panchamukhi <[email protected]> Changed Kprobes
* exceptions notifier to be first on the priority list.
* 2005-May Hien Nguyen <[email protected]>, Jim Keniston
* <[email protected]> and Prasanna S Panchamukhi
* <[email protected]> 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/sysctl.h>
#include <linux/kdebug.h>
#include <linux/memory.h>
#include <linux/ftrace.h>
#include <linux/cpu.h>
#include <linux/jump_label.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;
/* This protects kprobe_table and optimizing_list */
static DEFINE_MUTEX(kprobe_mutex);
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",},
{"mcount",}, /* mcount can be called from everywhere */
{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
*/
struct kprobe_insn_page {
struct list_head list;
kprobe_opcode_t *insns; /* Page of instruction slots */
int nused;
int ngarbage;
char slot_used[];
};
#define KPROBE_INSN_PAGE_SIZE(slots) \
(offsetof(struct kprobe_insn_page, slot_used) + \
(sizeof(char) * (slots)))
struct kprobe_insn_cache {
struct list_head pages; /* list of kprobe_insn_page */
size_t insn_size; /* size of instruction slot */
int nr_garbage;
};
static int slots_per_page(struct kprobe_insn_cache *c)
{
return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t));
}
enum kprobe_slot_state {
SLOT_CLEAN = 0,
SLOT_DIRTY = 1,
SLOT_USED = 2,
};
static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */
static struct kprobe_insn_cache kprobe_insn_slots = {
.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
.insn_size = MAX_INSN_SIZE,
.nr_garbage = 0,
};
static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c);
/**
* __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(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip;
retry:
list_for_each_entry(kip, &c->pages, list) {
if (kip->nused < slots_per_page(c)) {
int i;
for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_CLEAN) {
kip->slot_used[i] = SLOT_USED;
kip->nused++;
return kip->insns + (i * c->insn_size);
}
}
/* kip->nused is broken. Fix it. */
kip->nused = slots_per_page(c);
WARN_ON(1);
}
}
/* If there are any garbage slots, collect it and try again. */
if (c->nr_garbage && collect_garbage_slots(c) == 0)
goto retry;
/* All out of space. Need to allocate a new page. */
kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), 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);
memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c));
kip->slot_used[0] = SLOT_USED;
kip->nused = 1;
kip->ngarbage = 0;
list_add(&kip->list, &c->pages);
return kip->insns;
}
kprobe_opcode_t __kprobes *get_insn_slot(void)
{
kprobe_opcode_t *ret = NULL;
mutex_lock(&kprobe_insn_mutex);
ret = __get_insn_slot(&kprobe_insn_slots);
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(&kip->list)) {
list_del(&kip->list);
module_free(NULL, kip->insns);
kfree(kip);
}
return 1;
}
return 0;
}
static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
synchronize_sched();
list_for_each_entry_safe(kip, next, &c->pages, list) {
int i;
if (kip->ngarbage == 0)
continue;
kip->ngarbage = 0; /* we will collect all garbages */
for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_DIRTY &&
collect_one_slot(kip, i))
break;
}
}
c->nr_garbage = 0;
return 0;
}
static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
list_for_each_entry(kip, &c->pages, list) {
long idx = ((long)slot - (long)kip->insns) /
(c->insn_size * sizeof(kprobe_opcode_t));
if (idx >= 0 && idx < slots_per_page(c)) {
WARN_ON(kip->slot_used[idx] != SLOT_USED);
if (dirty) {
kip->slot_used[idx] = SLOT_DIRTY;
kip->ngarbage++;
if (++c->nr_garbage > slots_per_page(c))
collect_garbage_slots(c);
} else
collect_one_slot(kip, idx);
return;
}
}
/* Could not free this slot. */
WARN_ON(1);
}
void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
{
mutex_lock(&kprobe_insn_mutex);
__free_insn_slot(&kprobe_insn_slots, slot, dirty);
mutex_unlock(&kprobe_insn_mutex);
}
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */
static struct kprobe_insn_cache kprobe_optinsn_slots = {
.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
/* .insn_size is initialized later */
.nr_garbage = 0,
};
/* Get a slot for optimized_kprobe buffer */
kprobe_opcode_t __kprobes *get_optinsn_slot(void)
{
kprobe_opcode_t *ret = NULL;
mutex_lock(&kprobe_optinsn_mutex);
ret = __get_insn_slot(&kprobe_optinsn_slots);
mutex_unlock(&kprobe_optinsn_mutex);
return ret;
}
void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty)
{
mutex_lock(&kprobe_optinsn_mutex);
__free_insn_slot(&kprobe_optinsn_slots, slot, dirty);
mutex_unlock(&kprobe_optinsn_mutex);
}
#endif
#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;
}
static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
/* Return true if the kprobe is an aggregator */
static inline int kprobe_aggrprobe(struct kprobe *p)
{
return p->pre_handler == aggr_pre_handler;
}
/*
* 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));
}
#ifdef CONFIG_OPTPROBES
/* NOTE: change this value only with kprobe_mutex held */
static bool kprobes_allow_optimization;
/*
* Call all pre_handler on the list, but ignores its return value.
* This must be called from arch-dep optimized caller.
*/
void __kprobes opt_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);
kp->pre_handler(kp, regs);
}
reset_kprobe_instance();
}
}
/* Return true(!0) if the kprobe is ready for optimization. */
static inline int kprobe_optready(struct kprobe *p)
{
struct optimized_kprobe *op;
if (kprobe_aggrprobe(p)) {
op = container_of(p, struct optimized_kprobe, kp);
return arch_prepared_optinsn(&op->optinsn);
}
return 0;
}
/*
* Return an optimized kprobe whose optimizing code replaces
* instructions including addr (exclude breakpoint).
*/
static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
{
int i;
struct kprobe *p = NULL;
struct optimized_kprobe *op;
/* Don't check i == 0, since that is a breakpoint case. */
for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++)
p = get_kprobe((void *)(addr - i));
if (p && kprobe_optready(p)) {
op = container_of(p, struct optimized_kprobe, kp);
if (arch_within_optimized_kprobe(op, addr))
return p;
}
return NULL;
}
/* Optimization staging list, protected by kprobe_mutex */
static LIST_HEAD(optimizing_list);
static void kprobe_optimizer(struct work_struct *work);
static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
#define OPTIMIZE_DELAY 5
/* Kprobe jump optimizer */
static __kprobes void kprobe_optimizer(struct work_struct *work)
{
struct optimized_kprobe *op, *tmp;
/* Lock modules while optimizing kprobes */
mutex_lock(&module_mutex);
mutex_lock(&kprobe_mutex);
if (kprobes_all_disarmed || !kprobes_allow_optimization)
goto end;
/*
* Wait for quiesence period to ensure all running interrupts
* are done. Because optprobe may modify multiple instructions
* there is a chance that Nth instruction is interrupted. In that
* case, running interrupt can return to 2nd-Nth byte of jump
* instruction. This wait is for avoiding it.
*/
synchronize_sched();
/*
* The optimization/unoptimization refers online_cpus via
* stop_machine() and cpu-hotplug modifies online_cpus.
* And same time, text_mutex will be held in cpu-hotplug and here.
* This combination can cause a deadlock (cpu-hotplug try to lock
* text_mutex but stop_machine can not be done because online_cpus
* has been changed)
* To avoid this deadlock, we need to call get_online_cpus()
* for preventing cpu-hotplug outside of text_mutex locking.
*/
get_online_cpus();
mutex_lock(&text_mutex);
list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
WARN_ON(kprobe_disabled(&op->kp));
if (arch_optimize_kprobe(op) < 0)
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
list_del_init(&op->list);
}
mutex_unlock(&text_mutex);
put_online_cpus();
end:
mutex_unlock(&kprobe_mutex);
mutex_unlock(&module_mutex);
}
/* Optimize kprobe if p is ready to be optimized */
static __kprobes void optimize_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
/* Check if the kprobe is disabled or not ready for optimization. */
if (!kprobe_optready(p) || !kprobes_allow_optimization ||
(kprobe_disabled(p) || kprobes_all_disarmed))
return;
/* Both of break_handler and post_handler are not supported. */
if (p->break_handler || p->post_handler)
return;
op = container_of(p, struct optimized_kprobe, kp);
/* Check there is no other kprobes at the optimized instructions */
if (arch_check_optimized_kprobe(op) < 0)
return;
/* Check if it is already optimized. */
if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
return;
op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
list_add(&op->list, &optimizing_list);
if (!delayed_work_pending(&optimizing_work))
schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
}
/* Unoptimize a kprobe if p is optimized */
static __kprobes void unoptimize_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
op = container_of(p, struct optimized_kprobe, kp);
if (!list_empty(&op->list))
/* Dequeue from the optimization queue */
list_del_init(&op->list);
else
/* Replace jump with break */
arch_unoptimize_kprobe(op);
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
}
}
/* Remove optimized instructions */
static void __kprobes kill_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
if (!list_empty(&op->list)) {
/* Dequeue from the optimization queue */
list_del_init(&op->list);
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
}
/* Don't unoptimize, because the target code will be freed. */
arch_remove_optimized_kprobe(op);
}
/* Try to prepare optimized instructions */
static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
arch_prepare_optimized_kprobe(op);
}
/* Free optimized instructions and optimized_kprobe */
static __kprobes void free_aggr_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
arch_remove_optimized_kprobe(op);
kfree(op);
}
/* Allocate new optimized_kprobe and try to prepare optimized instructions */
static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL);
if (!op)
return NULL;
INIT_LIST_HEAD(&op->list);
op->kp.addr = p->addr;
arch_prepare_optimized_kprobe(op);
return &op->kp;
}
static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
/*
* Prepare an optimized_kprobe and optimize it
* NOTE: p must be a normal registered kprobe
*/
static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
{
struct kprobe *ap;
struct optimized_kprobe *op;
ap = alloc_aggr_kprobe(p);
if (!ap)
return;
op = container_of(ap, struct optimized_kprobe, kp);
if (!arch_prepared_optinsn(&op->optinsn)) {
/* If failed to setup optimizing, fallback to kprobe */
free_aggr_kprobe(ap);
return;
}
init_aggr_kprobe(ap, p);
optimize_kprobe(ap);
}
#ifdef CONFIG_SYSCTL
/* This should be called with kprobe_mutex locked */
static void __kprobes optimize_all_kprobes(void)
{
struct hlist_head *head;
struct hlist_node *node;
struct kprobe *p;
unsigned int i;
/* If optimization is already allowed, just return */
if (kprobes_allow_optimization)
return;
kprobes_allow_optimization = true;
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))
optimize_kprobe(p);
}
printk(KERN_INFO "Kprobes globally optimized\n");
}
/* This should be called with kprobe_mutex locked */
static void __kprobes unoptimize_all_kprobes(void)
{
struct hlist_head *head;
struct hlist_node *node;
struct kprobe *p;
unsigned int i;
/* If optimization is already prohibited, just return */
if (!kprobes_allow_optimization)
return;
kprobes_allow_optimization = false;
printk(KERN_INFO "Kprobes globally unoptimized\n");
get_online_cpus(); /* For avoiding text_mutex deadlock */
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))
unoptimize_kprobe(p);
}
}
mutex_unlock(&text_mutex);
put_online_cpus();
/* Allow all currently running kprobes to complete */
synchronize_sched();
}
int sysctl_kprobes_optimization;
int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos)
{
int ret;
mutex_lock(&kprobe_mutex);
sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (sysctl_kprobes_optimization)
optimize_all_kprobes();
else
unoptimize_all_kprobes();
mutex_unlock(&kprobe_mutex);
return ret;
}
#endif /* CONFIG_SYSCTL */
static void __kprobes __arm_kprobe(struct kprobe *p)
{
struct kprobe *old_p;
/* Check collision with other optimized kprobes */
old_p = get_optimized_kprobe((unsigned long)p->addr);
if (unlikely(old_p))
unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
arch_arm_kprobe(p);
optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
}
static void __kprobes __disarm_kprobe(struct kprobe *p)
{
struct kprobe *old_p;
unoptimize_kprobe(p); /* Try to unoptimize */
arch_disarm_kprobe(p);
/* If another kprobe was blocked, optimize it. */
old_p = get_optimized_kprobe((unsigned long)p->addr);
if (unlikely(old_p))
optimize_kprobe(old_p);
}
#else /* !CONFIG_OPTPROBES */
#define optimize_kprobe(p) do {} while (0)
#define unoptimize_kprobe(p) do {} while (0)
#define kill_optimized_kprobe(p) do {} while (0)
#define prepare_optimized_kprobe(p) do {} while (0)
#define try_to_optimize_kprobe(p) do {} while (0)
#define __arm_kprobe(p) arch_arm_kprobe(p)
#define __disarm_kprobe(p) arch_disarm_kprobe(p)
static __kprobes void free_aggr_kprobe(struct kprobe *p)
{
kfree(p);
}
static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
{
return kzalloc(sizeof(struct kprobe), GFP_KERNEL);
}
#endif /* CONFIG_OPTPROBES */
/* Arm a kprobe with text_mutex */
static void __kprobes arm_kprobe(struct kprobe *kp)
{
/*
* Here, since __arm_kprobe() doesn't use stop_machine(),
* this doesn't cause deadlock on text_mutex. So, we don't
* need get_online_cpus().
*/
mutex_lock(&text_mutex);
__arm_kprobe(kp);
mutex_unlock(&text_mutex);
}
/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
get_online_cpus(); /* For avoiding text_mutex deadlock */
mutex_lock(&text_mutex);
__disarm_kprobe(kp);
mutex_unlock(&text_mutex);
put_online_cpus();
}
/*
* 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 (!kprobe_aggrprobe(p)) {
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)
__acquires(hlist_lock)
{
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)
__acquires(hlist_lock)
{
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)
__releases(hlist_lock)
{
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);
}
static void __kprobes kretprobe_table_unlock(unsigned long hash,
unsigned long *flags)
__releases(hlist_lock)
{
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);
}
/*
* 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 || p->post_handler)
unoptimize_kprobe(ap); /* Fall back to normal kprobe */
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 void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
{
/* Copy p's insn slot to ap */
copy_kprobe(p, ap);
flush_insn_slot(ap);
ap->addr = p->addr;
ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED;
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);
INIT_HLIST_NODE(&ap->hlist);
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;