forked from gcc-mirror/gcc
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathinterception_win.cc
1010 lines (892 loc) · 33.3 KB
/
interception_win.cc
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
//===-- interception_linux.cc -----------------------------------*- C++ -*-===//
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file is a part of AddressSanitizer, an address sanity checker.
//
// Windows-specific interception methods.
//
// This file is implementing several hooking techniques to intercept calls
// to functions. The hooks are dynamically installed by modifying the assembly
// code.
//
// The hooking techniques are making assumptions on the way the code is
// generated and are safe under these assumptions.
//
// On 64-bit architecture, there is no direct 64-bit jump instruction. To allow
// arbitrary branching on the whole memory space, the notion of trampoline
// region is used. A trampoline region is a memory space withing 2G boundary
// where it is safe to add custom assembly code to build 64-bit jumps.
//
// Hooking techniques
// ==================
//
// 1) Detour
//
// The Detour hooking technique is assuming the presence of an header with
// padding and an overridable 2-bytes nop instruction (mov edi, edi). The
// nop instruction can safely be replaced by a 2-bytes jump without any need
// to save the instruction. A jump to the target is encoded in the function
// header and the nop instruction is replaced by a short jump to the header.
//
// head: 5 x nop head: jmp <hook>
// func: mov edi, edi --> func: jmp short <head>
// [...] real: [...]
//
// This technique is only implemented on 32-bit architecture.
// Most of the time, Windows API are hookable with the detour technique.
//
// 2) Redirect Jump
//
// The redirect jump is applicable when the first instruction is a direct
// jump. The instruction is replaced by jump to the hook.
//
// func: jmp <label> --> func: jmp <hook>
//
// On an 64-bit architecture, a trampoline is inserted.
//
// func: jmp <label> --> func: jmp <tramp>
// [...]
//
// [trampoline]
// tramp: jmp QWORD [addr]
// addr: .bytes <hook>
//
// Note: <real> is equilavent to <label>.
//
// 3) HotPatch
//
// The HotPatch hooking is assuming the presence of an header with padding
// and a first instruction with at least 2-bytes.
//
// The reason to enforce the 2-bytes limitation is to provide the minimal
// space to encode a short jump. HotPatch technique is only rewriting one
// instruction to avoid breaking a sequence of instructions containing a
// branching target.
//
// Assumptions are enforced by MSVC compiler by using the /HOTPATCH flag.
// see: https://msdn.microsoft.com/en-us/library/ms173507.aspx
// Default padding length is 5 bytes in 32-bits and 6 bytes in 64-bits.
//
// head: 5 x nop head: jmp <hook>
// func: <instr> --> func: jmp short <head>
// [...] body: [...]
//
// [trampoline]
// real: <instr>
// jmp <body>
//
// On an 64-bit architecture:
//
// head: 6 x nop head: jmp QWORD [addr1]
// func: <instr> --> func: jmp short <head>
// [...] body: [...]
//
// [trampoline]
// addr1: .bytes <hook>
// real: <instr>
// jmp QWORD [addr2]
// addr2: .bytes <body>
//
// 4) Trampoline
//
// The Trampoline hooking technique is the most aggressive one. It is
// assuming that there is a sequence of instructions that can be safely
// replaced by a jump (enough room and no incoming branches).
//
// Unfortunately, these assumptions can't be safely presumed and code may
// be broken after hooking.
//
// func: <instr> --> func: jmp <hook>
// <instr>
// [...] body: [...]
//
// [trampoline]
// real: <instr>
// <instr>
// jmp <body>
//
// On an 64-bit architecture:
//
// func: <instr> --> func: jmp QWORD [addr1]
// <instr>
// [...] body: [...]
//
// [trampoline]
// addr1: .bytes <hook>
// real: <instr>
// <instr>
// jmp QWORD [addr2]
// addr2: .bytes <body>
//===----------------------------------------------------------------------===//
#ifdef _WIN32
#include "interception.h"
#include "sanitizer_common/sanitizer_platform.h"
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
namespace __interception {
static const int kAddressLength = FIRST_32_SECOND_64(4, 8);
static const int kJumpInstructionLength = 5;
static const int kShortJumpInstructionLength = 2;
static const int kIndirectJumpInstructionLength = 6;
static const int kBranchLength =
FIRST_32_SECOND_64(kJumpInstructionLength, kIndirectJumpInstructionLength);
static const int kDirectBranchLength = kBranchLength + kAddressLength;
static void InterceptionFailed() {
// Do we have a good way to abort with an error message here?
__debugbreak();
}
static bool DistanceIsWithin2Gig(uptr from, uptr target) {
#if SANITIZER_WINDOWS64
if (from < target)
return target - from <= (uptr)0x7FFFFFFFU;
else
return from - target <= (uptr)0x80000000U;
#else
// In a 32-bit address space, the address calculation will wrap, so this check
// is unnecessary.
return true;
#endif
}
static uptr GetMmapGranularity() {
SYSTEM_INFO si;
GetSystemInfo(&si);
return si.dwAllocationGranularity;
}
static uptr RoundUpTo(uptr size, uptr boundary) {
return (size + boundary - 1) & ~(boundary - 1);
}
// FIXME: internal_str* and internal_mem* functions should be moved from the
// ASan sources into interception/.
static size_t _strlen(const char *str) {
const char* p = str;
while (*p != '\0') ++p;
return p - str;
}
static char* _strchr(char* str, char c) {
while (*str) {
if (*str == c)
return str;
++str;
}
return nullptr;
}
static void _memset(void *p, int value, size_t sz) {
for (size_t i = 0; i < sz; ++i)
((char*)p)[i] = (char)value;
}
static void _memcpy(void *dst, void *src, size_t sz) {
char *dst_c = (char*)dst,
*src_c = (char*)src;
for (size_t i = 0; i < sz; ++i)
dst_c[i] = src_c[i];
}
static bool ChangeMemoryProtection(
uptr address, uptr size, DWORD *old_protection) {
return ::VirtualProtect((void*)address, size,
PAGE_EXECUTE_READWRITE,
old_protection) != FALSE;
}
static bool RestoreMemoryProtection(
uptr address, uptr size, DWORD old_protection) {
DWORD unused;
return ::VirtualProtect((void*)address, size,
old_protection,
&unused) != FALSE;
}
static bool IsMemoryPadding(uptr address, uptr size) {
u8* function = (u8*)address;
for (size_t i = 0; i < size; ++i)
if (function[i] != 0x90 && function[i] != 0xCC)
return false;
return true;
}
static const u8 kHintNop9Bytes[] = {
0x66, 0x0F, 0x1F, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00
};
template<class T>
static bool FunctionHasPrefix(uptr address, const T &pattern) {
u8* function = (u8*)address - sizeof(pattern);
for (size_t i = 0; i < sizeof(pattern); ++i)
if (function[i] != pattern[i])
return false;
return true;
}
static bool FunctionHasPadding(uptr address, uptr size) {
if (IsMemoryPadding(address - size, size))
return true;
if (size <= sizeof(kHintNop9Bytes) &&
FunctionHasPrefix(address, kHintNop9Bytes))
return true;
return false;
}
static void WritePadding(uptr from, uptr size) {
_memset((void*)from, 0xCC, (size_t)size);
}
static void WriteJumpInstruction(uptr from, uptr target) {
if (!DistanceIsWithin2Gig(from + kJumpInstructionLength, target))
InterceptionFailed();
ptrdiff_t offset = target - from - kJumpInstructionLength;
*(u8*)from = 0xE9;
*(u32*)(from + 1) = offset;
}
static void WriteShortJumpInstruction(uptr from, uptr target) {
sptr offset = target - from - kShortJumpInstructionLength;
if (offset < -128 || offset > 127)
InterceptionFailed();
*(u8*)from = 0xEB;
*(u8*)(from + 1) = (u8)offset;
}
#if SANITIZER_WINDOWS64
static void WriteIndirectJumpInstruction(uptr from, uptr indirect_target) {
// jmp [rip + <offset>] = FF 25 <offset> where <offset> is a relative
// offset.
// The offset is the distance from then end of the jump instruction to the
// memory location containing the targeted address. The displacement is still
// 32-bit in x64, so indirect_target must be located within +/- 2GB range.
int offset = indirect_target - from - kIndirectJumpInstructionLength;
if (!DistanceIsWithin2Gig(from + kIndirectJumpInstructionLength,
indirect_target)) {
InterceptionFailed();
}
*(u16*)from = 0x25FF;
*(u32*)(from + 2) = offset;
}
#endif
static void WriteBranch(
uptr from, uptr indirect_target, uptr target) {
#if SANITIZER_WINDOWS64
WriteIndirectJumpInstruction(from, indirect_target);
*(u64*)indirect_target = target;
#else
(void)indirect_target;
WriteJumpInstruction(from, target);
#endif
}
static void WriteDirectBranch(uptr from, uptr target) {
#if SANITIZER_WINDOWS64
// Emit an indirect jump through immediately following bytes:
// jmp [rip + kBranchLength]
// .quad <target>
WriteBranch(from, from + kBranchLength, target);
#else
WriteJumpInstruction(from, target);
#endif
}
struct TrampolineMemoryRegion {
uptr content;
uptr allocated_size;
uptr max_size;
};
static const uptr kTrampolineScanLimitRange = 1 << 31; // 2 gig
static const int kMaxTrampolineRegion = 1024;
static TrampolineMemoryRegion TrampolineRegions[kMaxTrampolineRegion];
static void *AllocateTrampolineRegion(uptr image_address, size_t granularity) {
#if SANITIZER_WINDOWS64
uptr address = image_address;
uptr scanned = 0;
while (scanned < kTrampolineScanLimitRange) {
MEMORY_BASIC_INFORMATION info;
if (!::VirtualQuery((void*)address, &info, sizeof(info)))
return nullptr;
// Check whether a region can be allocated at |address|.
if (info.State == MEM_FREE && info.RegionSize >= granularity) {
void *page = ::VirtualAlloc((void*)RoundUpTo(address, granularity),
granularity,
MEM_RESERVE | MEM_COMMIT,
PAGE_EXECUTE_READWRITE);
return page;
}
// Move to the next region.
address = (uptr)info.BaseAddress + info.RegionSize;
scanned += info.RegionSize;
}
return nullptr;
#else
return ::VirtualAlloc(nullptr,
granularity,
MEM_RESERVE | MEM_COMMIT,
PAGE_EXECUTE_READWRITE);
#endif
}
// Used by unittests to release mapped memory space.
void TestOnlyReleaseTrampolineRegions() {
for (size_t bucket = 0; bucket < kMaxTrampolineRegion; ++bucket) {
TrampolineMemoryRegion *current = &TrampolineRegions[bucket];
if (current->content == 0)
return;
::VirtualFree((void*)current->content, 0, MEM_RELEASE);
current->content = 0;
}
}
static uptr AllocateMemoryForTrampoline(uptr image_address, size_t size) {
// Find a region within 2G with enough space to allocate |size| bytes.
TrampolineMemoryRegion *region = nullptr;
for (size_t bucket = 0; bucket < kMaxTrampolineRegion; ++bucket) {
TrampolineMemoryRegion* current = &TrampolineRegions[bucket];
if (current->content == 0) {
// No valid region found, allocate a new region.
size_t bucket_size = GetMmapGranularity();
void *content = AllocateTrampolineRegion(image_address, bucket_size);
if (content == nullptr)
return 0U;
current->content = (uptr)content;
current->allocated_size = 0;
current->max_size = bucket_size;
region = current;
break;
} else if (current->max_size - current->allocated_size > size) {
#if SANITIZER_WINDOWS64
// In 64-bits, the memory space must be allocated within 2G boundary.
uptr next_address = current->content + current->allocated_size;
if (next_address < image_address ||
next_address - image_address >= 0x7FFF0000)
continue;
#endif
// The space can be allocated in the current region.
region = current;
break;
}
}
// Failed to find a region.
if (region == nullptr)
return 0U;
// Allocate the space in the current region.
uptr allocated_space = region->content + region->allocated_size;
region->allocated_size += size;
WritePadding(allocated_space, size);
return allocated_space;
}
// Returns 0 on error.
static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
switch (*(u64*)address) {
case 0x90909090909006EB: // stub: jmp over 6 x nop.
return 8;
}
switch (*(u8*)address) {
case 0x90: // 90 : nop
return 1;
case 0x50: // push eax / rax
case 0x51: // push ecx / rcx
case 0x52: // push edx / rdx
case 0x53: // push ebx / rbx
case 0x54: // push esp / rsp
case 0x55: // push ebp / rbp
case 0x56: // push esi / rsi
case 0x57: // push edi / rdi
case 0x5D: // pop ebp / rbp
return 1;
case 0x6A: // 6A XX = push XX
return 2;
case 0xb8: // b8 XX XX XX XX : mov eax, XX XX XX XX
case 0xB9: // b9 XX XX XX XX : mov ecx, XX XX XX XX
return 5;
// Cannot overwrite control-instruction. Return 0 to indicate failure.
case 0xE9: // E9 XX XX XX XX : jmp <label>
case 0xE8: // E8 XX XX XX XX : call <func>
case 0xC3: // C3 : ret
case 0xEB: // EB XX : jmp XX (short jump)
case 0x70: // 7Y YY : jy XX (short conditional jump)
case 0x71:
case 0x72:
case 0x73:
case 0x74:
case 0x75:
case 0x76:
case 0x77:
case 0x78:
case 0x79:
case 0x7A:
case 0x7B:
case 0x7C:
case 0x7D:
case 0x7E:
case 0x7F:
return 0;
}
switch (*(u16*)(address)) {
case 0xFF8B: // 8B FF : mov edi, edi
case 0xEC8B: // 8B EC : mov ebp, esp
case 0xc889: // 89 C8 : mov eax, ecx
case 0xC18B: // 8B C1 : mov eax, ecx
case 0xC033: // 33 C0 : xor eax, eax
case 0xC933: // 33 C9 : xor ecx, ecx
case 0xD233: // 33 D2 : xor edx, edx
return 2;
// Cannot overwrite control-instruction. Return 0 to indicate failure.
case 0x25FF: // FF 25 XX XX XX XX : jmp [XXXXXXXX]
return 0;
}
switch (0x00FFFFFF & *(u32*)address) {
case 0x24A48D: // 8D A4 24 XX XX XX XX : lea esp, [esp + XX XX XX XX]
return 7;
}
#if SANITIZER_WINDOWS64
switch (*(u8*)address) {
case 0xA1: // A1 XX XX XX XX XX XX XX XX :
// movabs eax, dword ptr ds:[XXXXXXXX]
return 9;
}
switch (*(u16*)address) {
case 0x5040: // push rax
case 0x5140: // push rcx
case 0x5240: // push rdx
case 0x5340: // push rbx
case 0x5440: // push rsp
case 0x5540: // push rbp
case 0x5640: // push rsi
case 0x5740: // push rdi
case 0x5441: // push r12
case 0x5541: // push r13
case 0x5641: // push r14
case 0x5741: // push r15
case 0x9066: // Two-byte NOP
return 2;
case 0x058B: // 8B 05 XX XX XX XX : mov eax, dword ptr [XX XX XX XX]
if (rel_offset)
*rel_offset = 2;
return 6;
}
switch (0x00FFFFFF & *(u32*)address) {
case 0xe58948: // 48 8b c4 : mov rbp, rsp
case 0xc18b48: // 48 8b c1 : mov rax, rcx
case 0xc48b48: // 48 8b c4 : mov rax, rsp
case 0xd9f748: // 48 f7 d9 : neg rcx
case 0xd12b48: // 48 2b d1 : sub rdx, rcx
case 0x07c1f6: // f6 c1 07 : test cl, 0x7
case 0xc98548: // 48 85 C9 : test rcx, rcx
case 0xc0854d: // 4d 85 c0 : test r8, r8
case 0xc2b60f: // 0f b6 c2 : movzx eax, dl
case 0xc03345: // 45 33 c0 : xor r8d, r8d
case 0xdb3345: // 45 33 DB : xor r11d, r11d
case 0xd98b4c: // 4c 8b d9 : mov r11, rcx
case 0xd28b4c: // 4c 8b d2 : mov r10, rdx
case 0xc98b4c: // 4C 8B C9 : mov r9, rcx
case 0xd2b60f: // 0f b6 d2 : movzx edx, dl
case 0xca2b48: // 48 2b ca : sub rcx, rdx
case 0x10b70f: // 0f b7 10 : movzx edx, WORD PTR [rax]
case 0xc00b4d: // 3d 0b c0 : or r8, r8
case 0xd18b48: // 48 8b d1 : mov rdx, rcx
case 0xdc8b4c: // 4c 8b dc : mov r11, rsp
case 0xd18b4c: // 4c 8b d1 : mov r10, rcx
return 3;
case 0xec8348: // 48 83 ec XX : sub rsp, XX
case 0xf88349: // 49 83 f8 XX : cmp r8, XX
case 0x588948: // 48 89 58 XX : mov QWORD PTR[rax + XX], rbx
return 4;
case 0xec8148: // 48 81 EC XX XX XX XX : sub rsp, XXXXXXXX
return 7;
case 0x058b48: // 48 8b 05 XX XX XX XX :
// mov rax, QWORD PTR [rip + XXXXXXXX]
case 0x25ff48: // 48 ff 25 XX XX XX XX :
// rex.W jmp QWORD PTR [rip + XXXXXXXX]
// Instructions having offset relative to 'rip' need offset adjustment.
if (rel_offset)
*rel_offset = 3;
return 7;
case 0x2444c7: // C7 44 24 XX YY YY YY YY
// mov dword ptr [rsp + XX], YYYYYYYY
return 8;
}
switch (*(u32*)(address)) {
case 0x24448b48: // 48 8b 44 24 XX : mov rax, QWORD ptr [rsp + XX]
case 0x246c8948: // 48 89 6C 24 XX : mov QWORD ptr [rsp + XX], rbp
case 0x245c8948: // 48 89 5c 24 XX : mov QWORD PTR [rsp + XX], rbx
case 0x24748948: // 48 89 74 24 XX : mov QWORD PTR [rsp + XX], rsi
return 5;
}
#else
switch (*(u8*)address) {
case 0xA1: // A1 XX XX XX XX : mov eax, dword ptr ds:[XXXXXXXX]
return 5;
}
switch (*(u16*)address) {
case 0x458B: // 8B 45 XX : mov eax, dword ptr [ebp + XX]
case 0x5D8B: // 8B 5D XX : mov ebx, dword ptr [ebp + XX]
case 0x7D8B: // 8B 7D XX : mov edi, dword ptr [ebp + XX]
case 0xEC83: // 83 EC XX : sub esp, XX
case 0x75FF: // FF 75 XX : push dword ptr [ebp + XX]
return 3;
case 0xC1F7: // F7 C1 XX YY ZZ WW : test ecx, WWZZYYXX
case 0x25FF: // FF 25 XX YY ZZ WW : jmp dword ptr ds:[WWZZYYXX]
return 6;
case 0x3D83: // 83 3D XX YY ZZ WW TT : cmp TT, WWZZYYXX
return 7;
case 0x7D83: // 83 7D XX YY : cmp dword ptr [ebp + XX], YY
return 4;
}
switch (0x00FFFFFF & *(u32*)address) {
case 0x24448A: // 8A 44 24 XX : mov eal, dword ptr [esp + XX]
case 0x24448B: // 8B 44 24 XX : mov eax, dword ptr [esp + XX]
case 0x244C8B: // 8B 4C 24 XX : mov ecx, dword ptr [esp + XX]
case 0x24548B: // 8B 54 24 XX : mov edx, dword ptr [esp + XX]
case 0x24748B: // 8B 74 24 XX : mov esi, dword ptr [esp + XX]
case 0x247C8B: // 8B 7C 24 XX : mov edi, dword ptr [esp + XX]
return 4;
}
switch (*(u32*)address) {
case 0x2444B60F: // 0F B6 44 24 XX : movzx eax, byte ptr [esp + XX]
return 5;
}
#endif
// Unknown instruction!
// FIXME: Unknown instruction failures might happen when we add a new
// interceptor or a new compiler version. In either case, they should result
// in visible and readable error messages. However, merely calling abort()
// leads to an infinite recursion in CheckFailed.
InterceptionFailed();
return 0;
}
// Returns 0 on error.
static size_t RoundUpToInstrBoundary(size_t size, uptr address) {
size_t cursor = 0;
while (cursor < size) {
size_t instruction_size = GetInstructionSize(address + cursor);
if (!instruction_size)
return 0;
cursor += instruction_size;
}
return cursor;
}
static bool CopyInstructions(uptr to, uptr from, size_t size) {
size_t cursor = 0;
while (cursor != size) {
size_t rel_offset = 0;
size_t instruction_size = GetInstructionSize(from + cursor, &rel_offset);
_memcpy((void*)(to + cursor), (void*)(from + cursor),
(size_t)instruction_size);
if (rel_offset) {
uptr delta = to - from;
uptr relocated_offset = *(u32*)(to + cursor + rel_offset) - delta;
#if SANITIZER_WINDOWS64
if (relocated_offset + 0x80000000U >= 0xFFFFFFFFU)
return false;
#endif
*(u32*)(to + cursor + rel_offset) = relocated_offset;
}
cursor += instruction_size;
}
return true;
}
#if !SANITIZER_WINDOWS64
bool OverrideFunctionWithDetour(
uptr old_func, uptr new_func, uptr *orig_old_func) {
const int kDetourHeaderLen = 5;
const u16 kDetourInstruction = 0xFF8B;
uptr header = (uptr)old_func - kDetourHeaderLen;
uptr patch_length = kDetourHeaderLen + kShortJumpInstructionLength;
// Validate that the function is hookable.
if (*(u16*)old_func != kDetourInstruction ||
!IsMemoryPadding(header, kDetourHeaderLen))
return false;
// Change memory protection to writable.
DWORD protection = 0;
if (!ChangeMemoryProtection(header, patch_length, &protection))
return false;
// Write a relative jump to the redirected function.
WriteJumpInstruction(header, new_func);
// Write the short jump to the function prefix.
WriteShortJumpInstruction(old_func, header);
// Restore previous memory protection.
if (!RestoreMemoryProtection(header, patch_length, protection))
return false;
if (orig_old_func)
*orig_old_func = old_func + kShortJumpInstructionLength;
return true;
}
#endif
bool OverrideFunctionWithRedirectJump(
uptr old_func, uptr new_func, uptr *orig_old_func) {
// Check whether the first instruction is a relative jump.
if (*(u8*)old_func != 0xE9)
return false;
if (orig_old_func) {
uptr relative_offset = *(u32*)(old_func + 1);
uptr absolute_target = old_func + relative_offset + kJumpInstructionLength;
*orig_old_func = absolute_target;
}
#if SANITIZER_WINDOWS64
// If needed, get memory space for a trampoline jump.
uptr trampoline = AllocateMemoryForTrampoline(old_func, kDirectBranchLength);
if (!trampoline)
return false;
WriteDirectBranch(trampoline, new_func);
#endif
// Change memory protection to writable.
DWORD protection = 0;
if (!ChangeMemoryProtection(old_func, kJumpInstructionLength, &protection))
return false;
// Write a relative jump to the redirected function.
WriteJumpInstruction(old_func, FIRST_32_SECOND_64(new_func, trampoline));
// Restore previous memory protection.
if (!RestoreMemoryProtection(old_func, kJumpInstructionLength, protection))
return false;
return true;
}
bool OverrideFunctionWithHotPatch(
uptr old_func, uptr new_func, uptr *orig_old_func) {
const int kHotPatchHeaderLen = kBranchLength;
uptr header = (uptr)old_func - kHotPatchHeaderLen;
uptr patch_length = kHotPatchHeaderLen + kShortJumpInstructionLength;
// Validate that the function is hot patchable.
size_t instruction_size = GetInstructionSize(old_func);
if (instruction_size < kShortJumpInstructionLength ||
!FunctionHasPadding(old_func, kHotPatchHeaderLen))
return false;
if (orig_old_func) {
// Put the needed instructions into the trampoline bytes.
uptr trampoline_length = instruction_size + kDirectBranchLength;
uptr trampoline = AllocateMemoryForTrampoline(old_func, trampoline_length);
if (!trampoline)
return false;
if (!CopyInstructions(trampoline, old_func, instruction_size))
return false;
WriteDirectBranch(trampoline + instruction_size,
old_func + instruction_size);
*orig_old_func = trampoline;
}
// If needed, get memory space for indirect address.
uptr indirect_address = 0;
#if SANITIZER_WINDOWS64
indirect_address = AllocateMemoryForTrampoline(old_func, kAddressLength);
if (!indirect_address)
return false;
#endif
// Change memory protection to writable.
DWORD protection = 0;
if (!ChangeMemoryProtection(header, patch_length, &protection))
return false;
// Write jumps to the redirected function.
WriteBranch(header, indirect_address, new_func);
WriteShortJumpInstruction(old_func, header);
// Restore previous memory protection.
if (!RestoreMemoryProtection(header, patch_length, protection))
return false;
return true;
}
bool OverrideFunctionWithTrampoline(
uptr old_func, uptr new_func, uptr *orig_old_func) {
size_t instructions_length = kBranchLength;
size_t padding_length = 0;
uptr indirect_address = 0;
if (orig_old_func) {
// Find out the number of bytes of the instructions we need to copy
// to the trampoline.
instructions_length = RoundUpToInstrBoundary(kBranchLength, old_func);
if (!instructions_length)
return false;
// Put the needed instructions into the trampoline bytes.
uptr trampoline_length = instructions_length + kDirectBranchLength;
uptr trampoline = AllocateMemoryForTrampoline(old_func, trampoline_length);
if (!trampoline)
return false;
if (!CopyInstructions(trampoline, old_func, instructions_length))
return false;
WriteDirectBranch(trampoline + instructions_length,
old_func + instructions_length);
*orig_old_func = trampoline;
}
#if SANITIZER_WINDOWS64
// Check if the targeted address can be encoded in the function padding.
// Otherwise, allocate it in the trampoline region.
if (IsMemoryPadding(old_func - kAddressLength, kAddressLength)) {
indirect_address = old_func - kAddressLength;
padding_length = kAddressLength;
} else {
indirect_address = AllocateMemoryForTrampoline(old_func, kAddressLength);
if (!indirect_address)
return false;
}
#endif
// Change memory protection to writable.
uptr patch_address = old_func - padding_length;
uptr patch_length = instructions_length + padding_length;
DWORD protection = 0;
if (!ChangeMemoryProtection(patch_address, patch_length, &protection))
return false;
// Patch the original function.
WriteBranch(old_func, indirect_address, new_func);
// Restore previous memory protection.
if (!RestoreMemoryProtection(patch_address, patch_length, protection))
return false;
return true;
}
bool OverrideFunction(
uptr old_func, uptr new_func, uptr *orig_old_func) {
#if !SANITIZER_WINDOWS64
if (OverrideFunctionWithDetour(old_func, new_func, orig_old_func))
return true;
#endif
if (OverrideFunctionWithRedirectJump(old_func, new_func, orig_old_func))
return true;
if (OverrideFunctionWithHotPatch(old_func, new_func, orig_old_func))
return true;
if (OverrideFunctionWithTrampoline(old_func, new_func, orig_old_func))
return true;
return false;
}
static void **InterestingDLLsAvailable() {
static const char *InterestingDLLs[] = {
"kernel32.dll",
"msvcr110.dll", // VS2012
"msvcr120.dll", // VS2013
"vcruntime140.dll", // VS2015
"ucrtbase.dll", // Universal CRT
// NTDLL should go last as it exports some functions that we should
// override in the CRT [presumably only used internally].
"ntdll.dll", NULL};
static void *result[ARRAY_SIZE(InterestingDLLs)] = { 0 };
if (!result[0]) {
for (size_t i = 0, j = 0; InterestingDLLs[i]; ++i) {
if (HMODULE h = GetModuleHandleA(InterestingDLLs[i]))
result[j++] = (void *)h;
}
}
return &result[0];
}
namespace {
// Utility for reading loaded PE images.
template <typename T> class RVAPtr {
public:
RVAPtr(void *module, uptr rva)
: ptr_(reinterpret_cast<T *>(reinterpret_cast<char *>(module) + rva)) {}
operator T *() { return ptr_; }
T *operator->() { return ptr_; }
T *operator++() { return ++ptr_; }
private:
T *ptr_;
};
} // namespace
// Internal implementation of GetProcAddress. At least since Windows 8,
// GetProcAddress appears to initialize DLLs before returning function pointers
// into them. This is problematic for the sanitizers, because they typically
// want to intercept malloc *before* MSVCRT initializes. Our internal
// implementation walks the export list manually without doing initialization.
uptr InternalGetProcAddress(void *module, const char *func_name) {
// Check that the module header is full and present.
RVAPtr<IMAGE_DOS_HEADER> dos_stub(module, 0);
RVAPtr<IMAGE_NT_HEADERS> headers(module, dos_stub->e_lfanew);
if (!module || dos_stub->e_magic != IMAGE_DOS_SIGNATURE || // "MZ"
headers->Signature != IMAGE_NT_SIGNATURE || // "PE\0\0"
headers->FileHeader.SizeOfOptionalHeader <
sizeof(IMAGE_OPTIONAL_HEADER)) {
return 0;
}
IMAGE_DATA_DIRECTORY *export_directory =
&headers->OptionalHeader.DataDirectory[IMAGE_DIRECTORY_ENTRY_EXPORT];
if (export_directory->Size == 0)
return 0;
RVAPtr<IMAGE_EXPORT_DIRECTORY> exports(module,
export_directory->VirtualAddress);
RVAPtr<DWORD> functions(module, exports->AddressOfFunctions);
RVAPtr<DWORD> names(module, exports->AddressOfNames);
RVAPtr<WORD> ordinals(module, exports->AddressOfNameOrdinals);
for (DWORD i = 0; i < exports->NumberOfNames; i++) {
RVAPtr<char> name(module, names[i]);
if (!strcmp(func_name, name)) {
DWORD index = ordinals[i];
RVAPtr<char> func(module, functions[index]);
// Handle forwarded functions.
DWORD offset = functions[index];
if (offset >= export_directory->VirtualAddress &&
offset < export_directory->VirtualAddress + export_directory->Size) {
// An entry for a forwarded function is a string with the following
// format: "<module> . <function_name>" that is stored into the
// exported directory.
char function_name[256];
size_t funtion_name_length = _strlen(func);
if (funtion_name_length >= sizeof(function_name) - 1)
InterceptionFailed();
_memcpy(function_name, func, funtion_name_length);
function_name[funtion_name_length] = '\0';
char* separator = _strchr(function_name, '.');
if (!separator)
InterceptionFailed();
*separator = '\0';
void* redirected_module = GetModuleHandleA(function_name);
if (!redirected_module)
InterceptionFailed();
return InternalGetProcAddress(redirected_module, separator + 1);
}
return (uptr)(char *)func;
}
}
return 0;
}
bool OverrideFunction(
const char *func_name, uptr new_func, uptr *orig_old_func) {
bool hooked = false;
void **DLLs = InterestingDLLsAvailable();
for (size_t i = 0; DLLs[i]; ++i) {
uptr func_addr = InternalGetProcAddress(DLLs[i], func_name);
if (func_addr &&
OverrideFunction(func_addr, new_func, orig_old_func)) {
hooked = true;
}
}
return hooked;
}
bool OverrideImportedFunction(const char *module_to_patch,
const char *imported_module,
const char *function_name, uptr new_function,
uptr *orig_old_func) {
HMODULE module = GetModuleHandleA(module_to_patch);
if (!module)
return false;
// Check that the module header is full and present.
RVAPtr<IMAGE_DOS_HEADER> dos_stub(module, 0);
RVAPtr<IMAGE_NT_HEADERS> headers(module, dos_stub->e_lfanew);
if (!module || dos_stub->e_magic != IMAGE_DOS_SIGNATURE || // "MZ"
headers->Signature != IMAGE_NT_SIGNATURE || // "PE\0\0"
headers->FileHeader.SizeOfOptionalHeader <
sizeof(IMAGE_OPTIONAL_HEADER)) {
return false;
}
IMAGE_DATA_DIRECTORY *import_directory =
&headers->OptionalHeader.DataDirectory[IMAGE_DIRECTORY_ENTRY_IMPORT];
// Iterate the list of imported DLLs. FirstThunk will be null for the last
// entry.
RVAPtr<IMAGE_IMPORT_DESCRIPTOR> imports(module,
import_directory->VirtualAddress);
for (; imports->FirstThunk != 0; ++imports) {
RVAPtr<const char> modname(module, imports->Name);
if (_stricmp(&*modname, imported_module) == 0)
break;
}
if (imports->FirstThunk == 0)
return false;
// We have two parallel arrays: the import address table (IAT) and the table
// of names. They start out containing the same data, but the loader rewrites
// the IAT to hold imported addresses and leaves the name table in
// OriginalFirstThunk alone.
RVAPtr<IMAGE_THUNK_DATA> name_table(module, imports->OriginalFirstThunk);
RVAPtr<IMAGE_THUNK_DATA> iat(module, imports->FirstThunk);
for (; name_table->u1.Ordinal != 0; ++name_table, ++iat) {
if (!IMAGE_SNAP_BY_ORDINAL(name_table->u1.Ordinal)) {
RVAPtr<IMAGE_IMPORT_BY_NAME> import_by_name(
module, name_table->u1.ForwarderString);
const char *funcname = &import_by_name->Name[0];
if (strcmp(funcname, function_name) == 0)
break;
}
}
if (name_table->u1.Ordinal == 0)
return false;
// Now we have the correct IAT entry. Do the swap. We have to make the page
// read/write first.
if (orig_old_func)
*orig_old_func = iat->u1.AddressOfData;
DWORD old_prot, unused_prot;
if (!VirtualProtect(&iat->u1.AddressOfData, 4, PAGE_EXECUTE_READWRITE,
&old_prot))