summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/kprobes/core.c
blob: 211bce445522d541cc1bcc05e44e401b376f8093 (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
/*
 *  Kernel Probes (KProbes)
 *
 * 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 contributions from
 *		Rusty Russell).
 * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
 *		interface to access function arguments.
 * 2004-Oct	Jim Keniston <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> adapted for x86_64 from i386.
 * 2005-Mar	Roland McGrath <roland@redhat.com>
 *		Fixed to handle %rip-relative addressing mode correctly.
 * 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.
 * 2005-May	Rusty Lynch <rusty.lynch@intel.com>
 *		Added function return probes functionality
 * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
 *		kprobe-booster and kretprobe-booster for i386.
 * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
 *		and kretprobe-booster for x86-64
 * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
 *		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
 *		unified x86 kprobes code.
 */
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/ftrace.h>

#include <asm/cacheflush.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>

#include "common.h"

void jprobe_return_end(void);

DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs))

#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
	  (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) |   \
	  (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf))    \
	 << (row % 32))
	/*
	 * Undefined/reserved opcodes, conditional jump, Opcode Extension
	 * Groups, and some special opcodes can not boost.
	 * This is non-const and volatile to keep gcc from statically
	 * optimizing it out, as variable_test_bit makes gcc think only
	 * *(unsigned long*) is used.
	 */
static volatile u32 twobyte_is_boostable[256 / 32] = {
	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
	/*      ----------------------------------------------          */
	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */
	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
	W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
	W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */
	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */
	W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
	W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */
	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
	W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */
	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */
	W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
	W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */
	W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */
	W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0)   /* f0 */
	/*      -----------------------------------------------         */
	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
};
#undef W

struct kretprobe_blackpoint kretprobe_blacklist[] = {
	{"__switch_to", }, /* This function switches only current task, but
			      doesn't switch kernel stack.*/
	{NULL, NULL}	/* Terminator */
};

const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);

static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
{
	struct __arch_relative_insn {
		u8 op;
		s32 raddr;
	} __packed *insn;

	insn = (struct __arch_relative_insn *)from;
	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
	insn->op = op;
}

/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
void __kprobes synthesize_reljump(void *from, void *to)
{
	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
}

/* Insert a call instruction at address 'from', which calls address 'to'.*/
void __kprobes synthesize_relcall(void *from, void *to)
{
	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
}

/*
 * Skip the prefixes of the instruction.
 */
static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
{
	insn_attr_t attr;

	attr = inat_get_opcode_attribute((insn_byte_t)*insn);
	while (inat_is_legacy_prefix(attr)) {
		insn++;
		attr = inat_get_opcode_attribute((insn_byte_t)*insn);
	}
#ifdef CONFIG_X86_64
	if (inat_is_rex_prefix(attr))
		insn++;
#endif
	return insn;
}

/*
 * Returns non-zero if opcode is boostable.
 * RIP relative instructions are adjusted at copying time in 64 bits mode
 */
int __kprobes can_boost(kprobe_opcode_t *opcodes)
{
	kprobe_opcode_t opcode;
	kprobe_opcode_t *orig_opcodes = opcodes;

	if (search_exception_tables((unsigned long)opcodes))
		return 0;	/* Page fault may occur on this address. */

retry:
	if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
		return 0;
	opcode = *(opcodes++);

	/* 2nd-byte opcode */
	if (opcode == 0x0f) {
		if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
			return 0;
		return test_bit(*opcodes,
				(unsigned long *)twobyte_is_boostable);
	}

	switch (opcode & 0xf0) {
#ifdef CONFIG_X86_64
	case 0x40:
		goto retry; /* REX prefix is boostable */
#endif
	case 0x60:
		if (0x63 < opcode && opcode < 0x67)
			goto retry; /* prefixes */
		/* can't boost Address-size override and bound */
		return (opcode != 0x62 && opcode != 0x67);
	case 0x70:
		return 0; /* can't boost conditional jump */
	case 0xc0:
		/* can't boost software-interruptions */
		return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
	case 0xd0:
		/* can boost AA* and XLAT */
		return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
	case 0xe0:
		/* can boost in/out and absolute jmps */
		return ((opcode & 0x04) || opcode == 0xea);
	case 0xf0:
		if ((opcode & 0x0c) == 0 && opcode != 0xf1)
			goto retry; /* lock/rep(ne) prefix */
		/* clear and set flags are boostable */
		return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
	default:
		/* segment override prefixes are boostable */
		if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e)
			goto retry; /* prefixes */
		/* CS override prefix and call are not boostable */
		return (opcode != 0x2e && opcode != 0x9a);
	}
}

static unsigned long
__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
	struct kprobe *kp;

	kp = get_kprobe((void *)addr);
	/* There is no probe, return original address */
	if (!kp)
		return addr;

	/*
	 *  Basically, kp->ainsn.insn has an original instruction.
	 *  However, RIP-relative instruction can not do single-stepping
	 *  at different place, __copy_instruction() tweaks the displacement of
	 *  that instruction. In that case, we can't recover the instruction
	 *  from the kp->ainsn.insn.
	 *
	 *  On the other hand, kp->opcode has a copy of the first byte of
	 *  the probed instruction, which is overwritten by int3. And
	 *  the instruction at kp->addr is not modified by kprobes except
	 *  for the first byte, we can recover the original instruction
	 *  from it and kp->opcode.
	 */
	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
	buf[0] = kp->opcode;
	return (unsigned long)buf;
}

/*
 * Recover the probed instruction at addr for further analysis.
 * Caller must lock kprobes by kprobe_mutex, or disable preemption
 * for preventing to release referencing kprobes.
 */
unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
{
	unsigned long __addr;

	__addr = __recover_optprobed_insn(buf, addr);
	if (__addr != addr)
		return __addr;

	return __recover_probed_insn(buf, addr);
}

/* Check if paddr is at an instruction boundary */
static int __kprobes can_probe(unsigned long paddr)
{
	unsigned long addr, __addr, offset = 0;
	struct insn insn;
	kprobe_opcode_t buf[MAX_INSN_SIZE];

	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
		return 0;

	/* Decode instructions */
	addr = paddr - offset;
	while (addr < paddr) {
		/*
		 * Check if the instruction has been modified by another
		 * kprobe, in which case we replace the breakpoint by the
		 * original instruction in our buffer.
		 * Also, jump optimization will change the breakpoint to
		 * relative-jump. Since the relative-jump itself is
		 * normally used, we just go through if there is no kprobe.
		 */
		__addr = recover_probed_instruction(buf, addr);
		kernel_insn_init(&insn, (void *)__addr);
		insn_get_length(&insn);

		/*
		 * Another debugging subsystem might insert this breakpoint.
		 * In that case, we can't recover it.
		 */
		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
			return 0;
		addr += insn.length;
	}

	return (addr == paddr);
}

/*
 * Returns non-zero if opcode modifies the interrupt flag.
 */
static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
{
	/* Skip prefixes */
	insn = skip_prefixes(insn);

	switch (*insn) {
	case 0xfa:		/* cli */
	case 0xfb:		/* sti */
	case 0xcf:		/* iret/iretd */
	case 0x9d:		/* popf/popfd */
		return 1;
	}

	return 0;
}

/*
 * Copy an instruction and adjust the displacement if the instruction
 * uses the %rip-relative addressing mode.
 * If it does, Return the address of the 32-bit displacement word.
 * If not, return null.
 * Only applicable to 64-bit x86.
 */
int __kprobes __copy_instruction(u8 *dest, u8 *src)
{
	struct insn insn;
	kprobe_opcode_t buf[MAX_INSN_SIZE];

	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
	insn_get_length(&insn);
	/* Another subsystem puts a breakpoint, failed to recover */
	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
		return 0;
	memcpy(dest, insn.kaddr, insn.length);

#ifdef CONFIG_X86_64
	if (insn_rip_relative(&insn)) {
		s64 newdisp;
		u8 *disp;
		kernel_insn_init(&insn, dest);
		insn_get_displacement(&insn);
		/*
		 * The copied instruction uses the %rip-relative addressing
		 * mode.  Adjust the displacement for the difference between
		 * the original location of this instruction and the location
		 * of the copy that will actually be run.  The tricky bit here
		 * is making sure that the sign extension happens correctly in
		 * this calculation, since we need a signed 32-bit result to
		 * be sign-extended to 64 bits when it's added to the %rip
		 * value and yield the same 64-bit result that the sign-
		 * extension of the original signed 32-bit displacement would
		 * have given.
		 */
		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
		if ((s64) (s32) newdisp != newdisp) {
			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
			return 0;
		}
		disp = (u8 *) dest + insn_offset_displacement(&insn);
		*(s32 *) disp = (s32) newdisp;
	}
#endif
	return insn.length;
}

static int __kprobes arch_copy_kprobe(struct kprobe *p)
{
	int ret;

	/* Copy an instruction with recovering if other optprobe modifies it.*/
	ret = __copy_instruction(p->ainsn.insn, p->addr);
	if (!ret)
		return -EINVAL;

	/*
	 * __copy_instruction can modify the displacement of the instruction,
	 * but it doesn't affect boostable check.
	 */
	if (can_boost(p->ainsn.insn))
		p->ainsn.boostable = 0;
	else
		p->ainsn.boostable = -1;

	/* Check whether the instruction modifies Interrupt Flag or not */
	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);

	/* Also, displacement change doesn't affect the first byte */
	p->opcode = p->ainsn.insn[0];

	return 0;
}

int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
	if (alternatives_text_reserved(p->addr, p->addr))
		return -EINVAL;

	if (!can_probe((unsigned long)p->addr))
		return -EILSEQ;
	/* insn: must be on special executable page on x86. */
	p->ainsn.insn = get_insn_slot();
	if (!p->ainsn.insn)
		return -ENOMEM;

	return arch_copy_kprobe(p);
}

void __kprobes arch_arm_kprobe(struct kprobe *p)
{
	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
}

void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
	text_poke(p->addr, &p->opcode, 1);
}

void __kprobes arch_remove_kprobe(struct kprobe *p)
{
	if (p->ainsn.insn) {
		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
		p->ainsn.insn = NULL;
	}
}

static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	kcb->prev_kprobe.kp = kprobe_running();
	kcb->prev_kprobe.status = kcb->kprobe_status;
	kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags;
	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
}

static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
	kcb->kprobe_status = kcb->prev_kprobe.status;
	kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags;
	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
}

static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
				struct kprobe_ctlblk *kcb)
{
	__this_cpu_write(current_kprobe, p);
	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
	if (p->ainsn.if_modifier)
		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
}

static void __kprobes clear_btf(void)
{
	if (test_thread_flag(TIF_BLOCKSTEP)) {
		unsigned long debugctl = get_debugctlmsr();

		debugctl &= ~DEBUGCTLMSR_BTF;
		update_debugctlmsr(debugctl);
	}
}

static void __kprobes restore_btf(void)
{
	if (test_thread_flag(TIF_BLOCKSTEP)) {
		unsigned long debugctl = get_debugctlmsr();

		debugctl |= DEBUGCTLMSR_BTF;
		update_debugctlmsr(debugctl);
	}
}

void __kprobes
arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
	unsigned long *sara = stack_addr(regs);

	ri->ret_addr = (kprobe_opcode_t *) *sara;

	/* Replace the return addr with trampoline addr */
	*sara = (unsigned long) &kretprobe_trampoline;
}

static void __kprobes
setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
{
	if (setup_detour_execution(p, regs, reenter))
		return;

#if !defined(CONFIG_PREEMPT)
	if (p->ainsn.boostable == 1 && !p->post_handler) {
		/* Boost up -- we can execute copied instructions directly */
		if (!reenter)
			reset_current_kprobe();
		/*
		 * Reentering boosted probe doesn't reset current_kprobe,
		 * nor set current_kprobe, because it doesn't use single
		 * stepping.
		 */
		regs->ip = (unsigned long)p->ainsn.insn;
		preempt_enable_no_resched();
		return;
	}
#endif
	if (reenter) {
		save_previous_kprobe(kcb);
		set_current_kprobe(p, regs, kcb);
		kcb->kprobe_status = KPROBE_REENTER;
	} else
		kcb->kprobe_status = KPROBE_HIT_SS;
	/* Prepare real single stepping */
	clear_btf();
	regs->flags |= X86_EFLAGS_TF;
	regs->flags &= ~X86_EFLAGS_IF;
	/* single step inline if the instruction is an int3 */
	if (p->opcode == BREAKPOINT_INSTRUCTION)
		regs->ip = (unsigned long)p->addr;
	else
		regs->ip = (unsigned long)p->ainsn.insn;
}

/*
 * We have reentered the kprobe_handler(), since another probe was hit while
 * within the handler. We save the original kprobes variables and just single
 * step on the instruction of the new probe without calling any user handlers.
 */
static int __kprobes
reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
	switch (kcb->kprobe_status) {
	case KPROBE_HIT_SSDONE:
	case KPROBE_HIT_ACTIVE:
		kprobes_inc_nmissed_count(p);
		setup_singlestep(p, regs, kcb, 1);
		break;
	case KPROBE_HIT_SS:
		/* A probe has been hit in the codepath leading up to, or just
		 * after, single-stepping of a probed instruction. This entire
		 * codepath should strictly reside in .kprobes.text section.
		 * Raise a BUG or we'll continue in an endless reentering loop
		 * and eventually a stack overflow.
		 */
		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
		       p->addr);
		dump_kprobe(p);
		BUG();
	default:
		/* impossible cases */
		WARN_ON(1);
		return 0;
	}

	return 1;
}

/*
 * Interrupts are disabled on entry as trap3 is an interrupt gate and they
 * remain disabled throughout this function.
 */
static int __kprobes kprobe_handler(struct pt_regs *regs)
{
	kprobe_opcode_t *addr;
	struct kprobe *p;
	struct kprobe_ctlblk *kcb;

	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
	/*
	 * We don't want to be preempted for the entire
	 * duration of kprobe processing. We conditionally
	 * re-enable preemption at the end of this function,
	 * and also in reenter_kprobe() and setup_singlestep().
	 */
	preempt_disable();

	kcb = get_kprobe_ctlblk();
	p = get_kprobe(addr);

	if (p) {
		if (kprobe_running()) {
			if (reenter_kprobe(p, regs, kcb))
				return 1;
		} else {
			set_current_kprobe(p, regs, kcb);
			kcb->kprobe_status = KPROBE_HIT_ACTIVE;

			/*
			 * If we have no pre-handler or it returned 0, we
			 * continue with normal processing.  If we have a
			 * pre-handler and it returned non-zero, it prepped
			 * for calling the break_handler below on re-entry
			 * for jprobe processing, so get out doing nothing
			 * more here.
			 */
			if (!p->pre_handler || !p->pre_handler(p, regs))
				setup_singlestep(p, regs, kcb, 0);
			return 1;
		}
	} else if (*addr != BREAKPOINT_INSTRUCTION) {
		/*
		 * The breakpoint instruction was removed right
		 * after we hit it.  Another cpu has removed
		 * either a probepoint or a debugger breakpoint
		 * at this address.  In either case, no further
		 * handling of this interrupt is appropriate.
		 * Back up over the (now missing) int3 and run
		 * the original instruction.
		 */
		regs->ip = (unsigned long)addr;
		preempt_enable_no_resched();
		return 1;
	} else if (kprobe_running()) {
		p = __this_cpu_read(current_kprobe);
		if (p->break_handler && p->break_handler(p, regs)) {
			if (!skip_singlestep(p, regs, kcb))
				setup_singlestep(p, regs, kcb, 0);
			return 1;
		}
	} /* else: not a kprobe fault; let the kernel handle it */

	preempt_enable_no_resched();
	return 0;
}

/*
 * When a retprobed function returns, this code saves registers and
 * calls trampoline_handler() runs, which calls the kretprobe's handler.
 */
static void __used __kprobes kretprobe_trampoline_holder(void)
{
	asm volatile (
			".global kretprobe_trampoline\n"
			"kretprobe_trampoline: \n"
#ifdef CONFIG_X86_64
			/* We don't bother saving the ss register */
			"	pushq %rsp\n"
			"	pushfq\n"
			SAVE_REGS_STRING
			"	movq %rsp, %rdi\n"
			"	call trampoline_handler\n"
			/* Replace saved sp with true return address. */
			"	movq %rax, 152(%rsp)\n"
			RESTORE_REGS_STRING
			"	popfq\n"
#else
			"	pushf\n"
			SAVE_REGS_STRING
			"	movl %esp, %eax\n"
			"	call trampoline_handler\n"
			/* Move flags to cs */
			"	movl 56(%esp), %edx\n"
			"	movl %edx, 52(%esp)\n"
			/* Replace saved flags with true return address. */
			"	movl %eax, 56(%esp)\n"
			RESTORE_REGS_STRING
			"	popf\n"
#endif
			"	ret\n");
}

/*
 * Called from kretprobe_trampoline
 */
static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
{
	struct kretprobe_instance *ri = NULL;
	struct hlist_head *head, empty_rp;
	struct hlist_node *tmp;
	unsigned long flags, orig_ret_address = 0;
	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
	kprobe_opcode_t *correct_ret_addr = NULL;

	INIT_HLIST_HEAD(&empty_rp);
	kretprobe_hash_lock(current, &head, &flags);
	/* fixup registers */
#ifdef CONFIG_X86_64
	regs->cs = __KERNEL_CS;
#else
	regs->cs = __KERNEL_CS | get_kernel_rpl();
	regs->gs = 0;
#endif
	regs->ip = trampoline_address;
	regs->orig_ax = ~0UL;

	/*
	 * It is possible to have multiple instances associated with a given
	 * task either because multiple functions in the call path have
	 * return probes installed on them, and/or more than one
	 * return probe was registered for a target function.
	 *
	 * We can handle this because:
	 *     - instances are always pushed into the head of the list
	 *     - when multiple return probes are registered for the same
	 *	 function, the (chronologically) first instance's ret_addr
	 *	 will be the real return address, and all the rest will
	 *	 point to kretprobe_trampoline.
	 */
	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
		if (ri->task != current)
			/* another task is sharing our hash bucket */
			continue;

		orig_ret_address = (unsigned long)ri->ret_addr;

		if (orig_ret_address != trampoline_address)
			/*
			 * This is the real return address. Any other
			 * instances associated with this task are for
			 * other calls deeper on the call stack
			 */
			break;
	}

	kretprobe_assert(ri, orig_ret_address, trampoline_address);

	correct_ret_addr = ri->ret_addr;
	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
		if (ri->task != current)
			/* another task is sharing our hash bucket */
			continue;

		orig_ret_address = (unsigned long)ri->ret_addr;
		if (ri->rp && ri->rp->handler) {
			__this_cpu_write(current_kprobe, &ri->rp->kp);
			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
			ri->ret_addr = correct_ret_addr;
			ri->rp->handler(ri, regs);
			__this_cpu_write(current_kprobe, NULL);
		}

		recycle_rp_inst(ri, &empty_rp);

		if (orig_ret_address != trampoline_address)
			/*
			 * This is the real return address. Any other
			 * instances associated with this task are for
			 * other calls deeper on the call stack
			 */
			break;
	}

	kretprobe_hash_unlock(current, &flags);

	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
		hlist_del(&ri->hlist);
		kfree(ri);
	}
	return (void *)orig_ret_address;
}

/*
 * Called after single-stepping.  p->addr is the address of the
 * instruction whose first byte has been replaced by the "int 3"
 * instruction.  To avoid the SMP problems that can occur when we
 * temporarily put back the original opcode to single-step, we
 * single-stepped a copy of the instruction.  The address of this
 * copy is p->ainsn.insn.
 *
 * This function prepares to return from the post-single-step
 * interrupt.  We have to fix up the stack as follows:
 *
 * 0) Except in the case of absolute or indirect jump or call instructions,
 * the new ip is relative to the copied instruction.  We need to make
 * it relative to the original instruction.
 *
 * 1) If the single-stepped instruction was pushfl, then the TF and IF
 * flags are set in the just-pushed flags, and may need to be cleared.
 *
 * 2) If the single-stepped instruction was a call, the return address
 * that is atop the stack is the address following the copied instruction.
 * We need to make it the address following the original instruction.
 *
 * If this is the first time we've single-stepped the instruction at
 * this probepoint, and the instruction is boostable, boost it: add a
 * jump instruction after the copied instruction, that jumps to the next
 * instruction after the probepoint.
 */
static void __kprobes
resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
	unsigned long *tos = stack_addr(regs);
	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
	unsigned long orig_ip = (unsigned long)p->addr;
	kprobe_opcode_t *insn = p->ainsn.insn;

	/* Skip prefixes */
	insn = skip_prefixes(insn);

	regs->flags &= ~X86_EFLAGS_TF;
	switch (*insn) {
	case 0x9c:	/* pushfl */
		*tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF);
		*tos |= kcb->kprobe_old_flags;
		break;
	case 0xc2:	/* iret/ret/lret */
	case 0xc3:
	case 0xca:
	case 0xcb:
	case 0xcf:
	case 0xea:	/* jmp absolute -- ip is correct */
		/* ip is already adjusted, no more changes required */
		p->ainsn.boostable = 1;
		goto no_change;
	case 0xe8:	/* call relative - Fix return addr */
		*tos = orig_ip + (*tos - copy_ip);
		break;
#ifdef CONFIG_X86_32
	case 0x9a:	/* call absolute -- same as call absolute, indirect */
		*tos = orig_ip + (*tos - copy_ip);
		goto no_change;
#endif
	case 0xff:
		if ((insn[1] & 0x30) == 0x10) {
			/*
			 * call absolute, indirect
			 * Fix return addr; ip is correct.
			 * But this is not boostable
			 */
			*tos = orig_ip + (*tos - copy_ip);
			goto no_change;
		} else if (((insn[1] & 0x31) == 0x20) ||
			   ((insn[1] & 0x31) == 0x21)) {
			/*
			 * jmp near and far, absolute indirect
			 * ip is correct. And this is boostable
			 */
			p->ainsn.boostable = 1;
			goto no_change;
		}
	default:
		break;
	}

	if (p->ainsn.boostable == 0) {
		if ((regs->ip > copy_ip) &&
		    (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) {
			/*
			 * These instructions can be executed directly if it
			 * jumps back to correct address.
			 */
			synthesize_reljump((void *)regs->ip,
				(void *)orig_ip + (regs->ip - copy_ip));
			p->ainsn.boostable = 1;
		} else {
			p->ainsn.boostable = -1;
		}
	}

	regs->ip += orig_ip - copy_ip;

no_change:
	restore_btf();
}

/*
 * Interrupts are disabled on entry as trap1 is an interrupt gate and they
 * remain disabled throughout this function.
 */
static int __kprobes post_kprobe_handler(struct pt_regs *regs)
{
	struct kprobe *cur = kprobe_running();
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

	if (!cur)
		return 0;

	resume_execution(cur, regs, kcb);
	regs->flags |= kcb->kprobe_saved_flags;

	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
		kcb->kprobe_status = KPROBE_HIT_SSDONE;
		cur->post_handler(cur, regs, 0);
	}

	/* Restore back the original saved kprobes variables and continue. */
	if (kcb->kprobe_status == KPROBE_REENTER) {
		restore_previous_kprobe(kcb);
		goto out;
	}
	reset_current_kprobe();
out:
	preempt_enable_no_resched();

	/*
	 * if somebody else is singlestepping across a probe point, flags
	 * will have TF set, in which case, continue the remaining processing
	 * of do_debug, as if this is not a probe hit.
	 */
	if (regs->flags & X86_EFLAGS_TF)
		return 0;

	return 1;
}

int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
	struct kprobe *cur = kprobe_running();
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

	switch (kcb->kprobe_status) {
	case KPROBE_HIT_SS:
	case KPROBE_REENTER:
		/*
		 * We are here because the instruction being single
		 * stepped caused a page fault. We reset the current
		 * kprobe and the ip points back to the probe address
		 * and allow the page fault handler to continue as a
		 * normal page fault.
		 */
		regs->ip = (unsigned long)cur->addr;
		regs->flags |= kcb->kprobe_old_flags;
		if (kcb->kprobe_status == KPROBE_REENTER)
			restore_previous_kprobe(kcb);
		else
			reset_current_kprobe();
		preempt_enable_no_resched();
		break;
	case KPROBE_HIT_ACTIVE:
	case KPROBE_HIT_SSDONE:
		/*
		 * We increment the nmissed count for accounting,
		 * we can also use npre/npostfault count for accounting
		 * these specific fault cases.
		 */
		kprobes_inc_nmissed_count(cur);

		/*
		 * We come here because instructions in the pre/post
		 * handler caused the page_fault, this could happen
		 * if handler tries to access user space by
		 * copy_from_user(), get_user() etc. Let the
		 * user-specified handler try to fix it first.
		 */
		if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
			return 1;

		/*
		 * In case the user-specified fault handler returned
		 * zero, try to fix up.
		 */
		if (fixup_exception(regs))
			return 1;

		/*
		 * fixup routine could not handle it,
		 * Let do_page_fault() fix it.
		 */
		break;
	default:
		break;
	}
	return 0;
}

/*
 * Wrapper routine for handling exceptions.
 */
int __kprobes
kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
{
	struct die_args *args = data;
	int ret = NOTIFY_DONE;

	if (args->regs && user_mode_vm(args->regs))
		return ret;

	switch (val) {
	case DIE_INT3:
		if (kprobe_handler(args->regs))
			ret = NOTIFY_STOP;
		break;
	case DIE_DEBUG:
		if (post_kprobe_handler(args->regs)) {
			/*
			 * Reset the BS bit in dr6 (pointed by args->err) to
			 * denote completion of processing
			 */
			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
			ret = NOTIFY_STOP;
		}
		break;
	case DIE_GPF:
		/*
		 * To be potentially processing a kprobe fault and to
		 * trust the result from kprobe_running(), we have
		 * be non-preemptible.
		 */
		if (!preemptible() && kprobe_running() &&
		    kprobe_fault_handler(args->regs, args->trapnr))
			ret = NOTIFY_STOP;
		break;
	default:
		break;
	}
	return ret;
}

int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct jprobe *jp = container_of(p, struct jprobe, kp);
	unsigned long addr;
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

	kcb->jprobe_saved_regs = *regs;
	kcb->jprobe_saved_sp = stack_addr(regs);
	addr = (unsigned long)(kcb->jprobe_saved_sp);

	/*
	 * As Linus pointed out, gcc assumes that the callee
	 * owns the argument space and could overwrite it, e.g.
	 * tailcall optimization. So, to be absolutely safe
	 * we also save and restore enough stack bytes to cover
	 * the argument area.
	 */
	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr,
	       MIN_STACK_SIZE(addr));
	regs->flags &= ~X86_EFLAGS_IF;
	trace_hardirqs_off();
	regs->ip = (unsigned long)(jp->entry);
	return 1;
}

void __kprobes jprobe_return(void)
{
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

	asm volatile (
#ifdef CONFIG_X86_64
			"       xchg   %%rbx,%%rsp	\n"
#else
			"       xchgl   %%ebx,%%esp	\n"
#endif
			"       int3			\n"
			"       .globl jprobe_return_end\n"
			"       jprobe_return_end:	\n"
			"       nop			\n"::"b"
			(kcb->jprobe_saved_sp):"memory");
}

int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
	u8 *addr = (u8 *) (regs->ip - 1);
	struct jprobe *jp = container_of(p, struct jprobe, kp);

	if ((addr > (u8 *) jprobe_return) &&
	    (addr < (u8 *) jprobe_return_end)) {
		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
			printk(KERN_ERR
			       "current sp %p does not match saved sp %p\n",
			       stack_addr(regs), kcb->jprobe_saved_sp);
			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
			show_regs(saved_regs);
			printk(KERN_ERR "Current registers\n");
			show_regs(regs);
			BUG();
		}
		*regs = kcb->jprobe_saved_regs;
		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
		       kcb->jprobes_stack,
		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
		preempt_enable_no_resched();
		return 1;
	}
	return 0;
}

int __init arch_init_kprobes(void)
{
	return arch_init_optprobes();
}

int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
	return 0;
}