-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathkprobes.c
More file actions
3047 lines (2580 loc) · 74.3 KB
/
kprobes.c
File metadata and controls
3047 lines (2580 loc) · 74.3 KB
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Kernel Probes (KProbes)
*
* 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.
*/
#define pr_fmt(fmt) "kprobes: " fmt
#include <linux/kprobes.h>
#include <linux/hash.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/export.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 <linux/static_call.h>
#include <linux/perf_event.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#include <asm/errno.h>
#include <linux/uaccess.h>
#define KPROBE_HASH_BITS 6
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL)
#define kprobe_sysctls_init() do { } while (0)
#endif
static int kprobes_initialized;
/* kprobe_table can be accessed by
* - Normal hlist traversal and RCU add/del under 'kprobe_mutex' is held.
* Or
* - RCU hlist traversal under disabling preempt (breakpoint handlers)
*/
static struct hlist_head kprobe_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);
kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
unsigned int __unused)
{
return ((kprobe_opcode_t *)(kallsyms_lookup_name(name)));
}
/*
* Blacklist -- list of 'struct kprobe_blacklist_entry' to store info where
* kprobes can not probe.
*/
static LIST_HEAD(kprobe_blacklist);
#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 */
struct kprobe_insn_cache *cache;
int nused;
int ngarbage;
char slot_used[];
};
#define KPROBE_INSN_PAGE_SIZE(slots) \
(offsetof(struct kprobe_insn_page, slot_used) + \
(sizeof(char) * (slots)))
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,
};
void __weak *alloc_insn_page(void)
{
/*
* Use module_alloc() so this page is within +/- 2GB of where the
* kernel image and loaded module images reside. This is required
* for most of the architectures.
* (e.g. x86-64 needs this to handle the %rip-relative fixups.)
*/
return module_alloc(PAGE_SIZE);
}
static void free_insn_page(void *page)
{
module_memfree(page);
}
struct kprobe_insn_cache kprobe_insn_slots = {
.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
.alloc = alloc_insn_page,
.free = free_insn_page,
.sym = KPROBE_INSN_PAGE_SYM,
.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
.insn_size = MAX_INSN_SIZE,
.nr_garbage = 0,
};
static int 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.
*/
kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip;
kprobe_opcode_t *slot = NULL;
/* Since the slot array is not protected by rcu, we need a mutex */
mutex_lock(&c->mutex);
retry:
rcu_read_lock();
list_for_each_entry_rcu(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++;
slot = kip->insns + (i * c->insn_size);
rcu_read_unlock();
goto out;
}
}
/* kip->nused is broken. Fix it. */
kip->nused = slots_per_page(c);
WARN_ON(1);
}
}
rcu_read_unlock();
/* 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)
goto out;
kip->insns = c->alloc();
if (!kip->insns) {
kfree(kip);
goto out;
}
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;
kip->cache = c;
list_add_rcu(&kip->list, &c->pages);
slot = kip->insns;
/* Record the perf ksymbol register event after adding the page */
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns,
PAGE_SIZE, false, c->sym);
out:
mutex_unlock(&c->mutex);
return slot;
}
/* Return true if all garbages are collected, otherwise false. */
static bool 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)) {
/*
* Record perf ksymbol unregister event before removing
* the page.
*/
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
(unsigned long)kip->insns, PAGE_SIZE, true,
kip->cache->sym);
list_del_rcu(&kip->list);
synchronize_rcu();
kip->cache->free(kip->insns);
kfree(kip);
}
return true;
}
return false;
}
static int collect_garbage_slots(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
synchronize_rcu();
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;
}
void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
long idx;
mutex_lock(&c->mutex);
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
idx = ((long)slot - (long)kip->insns) /
(c->insn_size * sizeof(kprobe_opcode_t));
if (idx >= 0 && idx < slots_per_page(c))
goto out;
}
/* Could not find this slot. */
WARN_ON(1);
kip = NULL;
out:
rcu_read_unlock();
/* Mark and sweep: this may sleep */
if (kip) {
/* Check double free */
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);
}
}
mutex_unlock(&c->mutex);
}
/*
* Check given address is on the page of kprobe instruction slots.
* This will be used for checking whether the address on a stack
* is on a text area or not.
*/
bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
{
struct kprobe_insn_page *kip;
bool ret = false;
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
if (addr >= (unsigned long)kip->insns &&
addr < (unsigned long)kip->insns + PAGE_SIZE) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
unsigned long *value, char *type, char *sym)
{
struct kprobe_insn_page *kip;
int ret = -ERANGE;
rcu_read_lock();
list_for_each_entry_rcu(kip, &c->pages, list) {
if ((*symnum)--)
continue;
strscpy(sym, c->sym, KSYM_NAME_LEN);
*type = 't';
*value = (unsigned long)kip->insns;
ret = 0;
break;
}
rcu_read_unlock();
return ret;
}
#ifdef CONFIG_OPTPROBES
void __weak *alloc_optinsn_page(void)
{
return alloc_insn_page();
}
void __weak free_optinsn_page(void *page)
{
free_insn_page(page);
}
/* For optimized_kprobe buffer */
struct kprobe_insn_cache kprobe_optinsn_slots = {
.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
.alloc = alloc_optinsn_page,
.free = free_optinsn_page,
.sym = KPROBE_OPTINSN_PAGE_SYM,
.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
/* .insn_size is initialized later */
.nr_garbage = 0,
};
#endif
#endif
/* We have preemption disabled.. so it is safe to use __ versions */
static inline void set_kprobe_instance(struct kprobe *kp)
{
__this_cpu_write(kprobe_instance, kp);
}
static inline void reset_kprobe_instance(void)
{
__this_cpu_write(kprobe_instance, NULL);
}
/*
* This routine is called either:
* - under the 'kprobe_mutex' - during kprobe_[un]register().
* OR
* - with preemption disabled - from architecture specific code.
*/
struct kprobe *get_kprobe(void *addr)
{
struct hlist_head *head;
struct kprobe *p;
head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
hlist_for_each_entry_rcu(p, head, hlist,
lockdep_is_held(&kprobe_mutex)) {
if (p->addr == addr)
return p;
}
return NULL;
}
NOKPROBE_SYMBOL(get_kprobe);
static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
/* Return true if 'p' is an aggregator */
static inline bool kprobe_aggrprobe(struct kprobe *p)
{
return p->pre_handler == aggr_pre_handler;
}
/* Return true if 'p' is unused */
static inline bool kprobe_unused(struct kprobe *p)
{
return kprobe_aggrprobe(p) && kprobe_disabled(p) &&
list_empty(&p->list);
}
/* Keep all fields in the kprobe consistent. */
static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p)
{
memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t));
memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn));
}
#ifdef CONFIG_OPTPROBES
/* NOTE: This is protected by 'kprobe_mutex'. */
static bool kprobes_allow_optimization;
/*
* Call all 'kprobe::pre_handler' on the list, but ignores its return value.
* This must be called from arch-dep optimized caller.
*/
void 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();
}
}
NOKPROBE_SYMBOL(opt_pre_handler);
/* Free optimized instructions and optimized_kprobe */
static void free_aggr_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
arch_remove_optimized_kprobe(op);
arch_remove_kprobe(p);
kfree(op);
}
/* Return true 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 true if the kprobe is disarmed. Note: p must be on hash list */
bool kprobe_disarmed(struct kprobe *p)
{
struct optimized_kprobe *op;
/* If kprobe is not aggr/opt probe, just return kprobe is disabled */
if (!kprobe_aggrprobe(p))
return kprobe_disabled(p);
op = container_of(p, struct optimized_kprobe, kp);
return kprobe_disabled(p) && list_empty(&op->list);
}
/* Return true if the probe is queued on (un)optimizing lists */
static bool kprobe_queued(struct kprobe *p)
{
struct optimized_kprobe *op;
if (kprobe_aggrprobe(p)) {
op = container_of(p, struct optimized_kprobe, kp);
if (!list_empty(&op->list))
return true;
}
return false;
}
/*
* Return an optimized kprobe whose optimizing code replaces
* instructions including 'addr' (exclude breakpoint).
*/
static struct kprobe *get_optimized_kprobe(kprobe_opcode_t *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 / sizeof(kprobe_opcode_t); i++)
p = get_kprobe(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 LIST_HEAD(unoptimizing_list);
static LIST_HEAD(freeing_list);
static void kprobe_optimizer(struct work_struct *work);
static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
#define OPTIMIZE_DELAY 5
/*
* Optimize (replace a breakpoint with a jump) kprobes listed on
* 'optimizing_list'.
*/
static void do_optimize_kprobes(void)
{
lockdep_assert_held(&text_mutex);
/*
* The optimization/unoptimization refers 'online_cpus' via
* stop_machine() and cpu-hotplug modifies the 'online_cpus'.
* And same time, 'text_mutex' will be held in cpu-hotplug and here.
* This combination can cause a deadlock (cpu-hotplug tries to lock
* 'text_mutex' but stop_machine() can not be done because
* the 'online_cpus' has been changed)
* To avoid this deadlock, caller must have locked cpu-hotplug
* for preventing cpu-hotplug outside of 'text_mutex' locking.
*/
lockdep_assert_cpus_held();
/* Optimization never be done when disarmed */
if (kprobes_all_disarmed || !kprobes_allow_optimization ||
list_empty(&optimizing_list))
return;
arch_optimize_kprobes(&optimizing_list);
}
/*
* Unoptimize (replace a jump with a breakpoint and remove the breakpoint
* if need) kprobes listed on 'unoptimizing_list'.
*/
static void do_unoptimize_kprobes(void)
{
struct optimized_kprobe *op, *tmp;
lockdep_assert_held(&text_mutex);
/* See comment in do_optimize_kprobes() */
lockdep_assert_cpus_held();
if (!list_empty(&unoptimizing_list))
arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
/* Loop on 'freeing_list' for disarming and removing from kprobe hash list */
list_for_each_entry_safe(op, tmp, &freeing_list, list) {
/* Switching from detour code to origin */
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
/* Disarm probes if marked disabled and not gone */
if (kprobe_disabled(&op->kp) && !kprobe_gone(&op->kp))
arch_disarm_kprobe(&op->kp);
if (kprobe_unused(&op->kp)) {
/*
* Remove unused probes from hash list. After waiting
* for synchronization, these probes are reclaimed.
* (reclaiming is done by do_free_cleaned_kprobes().)
*/
hlist_del_rcu(&op->kp.hlist);
} else
list_del_init(&op->list);
}
}
/* Reclaim all kprobes on the 'freeing_list' */
static void do_free_cleaned_kprobes(void)
{
struct optimized_kprobe *op, *tmp;
list_for_each_entry_safe(op, tmp, &freeing_list, list) {
list_del_init(&op->list);
if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) {
/*
* This must not happen, but if there is a kprobe
* still in use, keep it on kprobes hash list.
*/
continue;
}
free_aggr_kprobe(&op->kp);
}
}
/* Start optimizer after OPTIMIZE_DELAY passed */
static void kick_kprobe_optimizer(void)
{
schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
}
/* Kprobe jump optimizer */
static void kprobe_optimizer(struct work_struct *work)
{
mutex_lock(&kprobe_mutex);
cpus_read_lock();
mutex_lock(&text_mutex);
/*
* Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
* kprobes before waiting for quiesence period.
*/
do_unoptimize_kprobes();
/*
* Step 2: Wait for quiesence period to ensure all potentially
* preempted tasks to have normally scheduled. Because optprobe
* may modify multiple instructions, there is a chance that Nth
* instruction is preempted. In that case, such tasks can return
* to 2nd-Nth byte of jump instruction. This wait is for avoiding it.
* Note that on non-preemptive kernel, this is transparently converted
* to synchronoze_sched() to wait for all interrupts to have completed.
*/
synchronize_rcu_tasks();
/* Step 3: Optimize kprobes after quiesence period */
do_optimize_kprobes();
/* Step 4: Free cleaned kprobes after quiesence period */
do_free_cleaned_kprobes();
mutex_unlock(&text_mutex);
cpus_read_unlock();
/* Step 5: Kick optimizer again if needed */
if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
kick_kprobe_optimizer();
mutex_unlock(&kprobe_mutex);
}
/* Wait for completing optimization and unoptimization */
void wait_for_kprobe_optimizer(void)
{
mutex_lock(&kprobe_mutex);
while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) {
mutex_unlock(&kprobe_mutex);
/* This will also make 'optimizing_work' execute immmediately */
flush_delayed_work(&optimizing_work);
/* 'optimizing_work' might not have been queued yet, relax */
cpu_relax();
mutex_lock(&kprobe_mutex);
}
mutex_unlock(&kprobe_mutex);
}
bool optprobe_queued_unopt(struct optimized_kprobe *op)
{
struct optimized_kprobe *_op;
list_for_each_entry(_op, &unoptimizing_list, list) {
if (op == _op)
return true;
}
return false;
}
/* Optimize kprobe if p is ready to be optimized */
static 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;
/* kprobes with 'post_handler' can not be optimized */
if (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) {
if (optprobe_queued_unopt(op)) {
/* This is under unoptimizing. Just dequeue the probe */
list_del_init(&op->list);
}
return;
}
op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
/*
* On the 'unoptimizing_list' and 'optimizing_list',
* 'op' must have OPTIMIZED flag
*/
if (WARN_ON_ONCE(!list_empty(&op->list)))
return;
list_add(&op->list, &optimizing_list);
kick_kprobe_optimizer();
}
/* Short cut to direct unoptimizing */
static void force_unoptimize_kprobe(struct optimized_kprobe *op)
{
lockdep_assert_cpus_held();
arch_unoptimize_kprobe(op);
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
}
/* Unoptimize a kprobe if p is optimized */
static void unoptimize_kprobe(struct kprobe *p, bool force)
{
struct optimized_kprobe *op;
if (!kprobe_aggrprobe(p) || kprobe_disarmed(p))
return; /* This is not an optprobe nor optimized */
op = container_of(p, struct optimized_kprobe, kp);
if (!kprobe_optimized(p))
return;
if (!list_empty(&op->list)) {
if (optprobe_queued_unopt(op)) {
/* Queued in unoptimizing queue */
if (force) {
/*
* Forcibly unoptimize the kprobe here, and queue it
* in the freeing list for release afterwards.
*/
force_unoptimize_kprobe(op);
list_move(&op->list, &freeing_list);
}
} else {
/* Dequeue from the optimizing queue */
list_del_init(&op->list);
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
}
return;
}
/* Optimized kprobe case */
if (force) {
/* Forcibly update the code: this is a special case */
force_unoptimize_kprobe(op);
} else {
list_add(&op->list, &unoptimizing_list);
kick_kprobe_optimizer();
}
}
/* Cancel unoptimizing for reusing */
static int reuse_unused_kprobe(struct kprobe *ap)
{
struct optimized_kprobe *op;
/*
* Unused kprobe MUST be on the way of delayed unoptimizing (means
* there is still a relative jump) and disabled.
*/
op = container_of(ap, struct optimized_kprobe, kp);
WARN_ON_ONCE(list_empty(&op->list));
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again. (remove from 'op->list') */
if (!kprobe_optready(ap))
return -EINVAL;
optimize_kprobe(ap);
return 0;
}
/* Remove optimized instructions */
static void 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 (un)optimization queue */
list_del_init(&op->list);
op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
if (kprobe_unused(p)) {
/*
* Unused kprobe is on unoptimizing or freeing list. We move it
* to freeing_list and let the kprobe_optimizer() remove it from
* the kprobe hash list and free it.
*/
if (optprobe_queued_unopt(op))
list_move(&op->list, &freeing_list);
}
/* Don't touch the code, because it is already freed. */
arch_remove_optimized_kprobe(op);
}
static inline
void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
{
if (!kprobe_ftrace(p))
arch_prepare_optimized_kprobe(op, p);
}
/* Try to prepare optimized instructions */
static void prepare_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
__prepare_optimized_kprobe(op, p);
}
/* Allocate new optimized_kprobe and try to prepare optimized instructions. */
static 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;
__prepare_optimized_kprobe(op, p);
return &op->kp;
}
static void 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 void try_to_optimize_kprobe(struct kprobe *p)
{
struct kprobe *ap;
struct optimized_kprobe *op;
/* Impossible to optimize ftrace-based kprobe. */
if (kprobe_ftrace(p))
return;
/* For preparing optimization, jump_label_text_reserved() is called. */
cpus_read_lock();
jump_label_lock();
mutex_lock(&text_mutex);
ap = alloc_aggr_kprobe(p);
if (!ap)
goto out;
op = container_of(ap, struct optimized_kprobe, kp);
if (!arch_prepared_optinsn(&op->optinsn)) {
/* If failed to setup optimizing, fallback to kprobe. */
arch_remove_optimized_kprobe(op);
kfree(op);
goto out;
}
init_aggr_kprobe(ap, p);
optimize_kprobe(ap); /* This just kicks optimizer thread. */
out:
mutex_unlock(&text_mutex);
jump_label_unlock();
cpus_read_unlock();
}
static void optimize_all_kprobes(void)
{
struct hlist_head *head;
struct kprobe *p;
unsigned int i;
mutex_lock(&kprobe_mutex);
/* If optimization is already allowed, just return. */
if (kprobes_allow_optimization)
goto out;
cpus_read_lock();
kprobes_allow_optimization = true;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry(p, head, hlist)
if (!kprobe_disabled(p))
optimize_kprobe(p);
}
cpus_read_unlock();
pr_info("kprobe jump-optimization is enabled. All kprobes are optimized if possible.\n");
out:
mutex_unlock(&kprobe_mutex);
}
#ifdef CONFIG_SYSCTL
static void unoptimize_all_kprobes(void)
{
struct hlist_head *head;
struct kprobe *p;
unsigned int i;
mutex_lock(&kprobe_mutex);
/* If optimization is already prohibited, just return. */
if (!kprobes_allow_optimization) {
mutex_unlock(&kprobe_mutex);
return;
}
cpus_read_lock();
kprobes_allow_optimization = false;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry(p, head, hlist) {
if (!kprobe_disabled(p))
unoptimize_kprobe(p, false);
}
}
cpus_read_unlock();
mutex_unlock(&kprobe_mutex);
/* Wait for unoptimizing completion. */
wait_for_kprobe_optimizer();
pr_info("kprobe jump-optimization is disabled. All kprobes are based on software breakpoint.\n");
}
static DEFINE_MUTEX(kprobe_sysctl_mutex);
static int sysctl_kprobes_optimization;
static int proc_kprobes_optimization_handler(struct ctl_table *table,
int write, void *buffer,
size_t *length, loff_t *ppos)
{
int ret;
mutex_lock(&kprobe_sysctl_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_sysctl_mutex);
return ret;
}
static struct ctl_table kprobe_sysctls[] = {
{
.procname = "kprobes-optimization",
.data = &sysctl_kprobes_optimization,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_kprobes_optimization_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{}
};
static void __init kprobe_sysctls_init(void)
{
register_sysctl_init("debug", kprobe_sysctls);
}
#endif /* CONFIG_SYSCTL */
/* Put a breakpoint for a probe. */
static void __arm_kprobe(struct kprobe *p)
{
struct kprobe *_p;
lockdep_assert_held(&text_mutex);
/* Find the overlapping optimized kprobes. */
_p = get_optimized_kprobe(p->addr);
if (unlikely(_p))
/* Fallback to unoptimized kprobe */
unoptimize_kprobe(_p, true);
arch_arm_kprobe(p);
optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
}
/* Remove the breakpoint of a probe. */
static void __disarm_kprobe(struct kprobe *p, bool reopt)
{
struct kprobe *_p;