[win/asan] GetInstructionSize: Support some more 3 byte instructions. #120474
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This patch adds several instructions seen when trying to run a executable built with ASan with llvm-mingw. (x86 and x86_64, using the git tip in llvm-project). Also includes instructions collected by Roman Pišl and Eric Pouech in the Wine bug reports below. Related: llvm#96270 Co-authored-by: Roman Pišl <[email protected]> https://bugs.winehq.org/show_bug.cgi?id=50993 https://bugs.winehq.org/attachment.cgi?id=70233 Co-authored-by: Eric Pouech <[email protected]> https://bugs.winehq.org/show_bug.cgi?id=52386 https://bugs.winehq.org/attachment.cgi?id=71626
|
@llvm/pr-subscribers-compiler-rt-sanitizer Author: None (bernhardu) ChangesThis patch adds several instructions seen when trying to run a Also includes instructions collected by Full diff: https://github.com/llvm/llvm-project/pull/120474.diff 2 Files Affected:
diff --git a/compiler-rt/lib/interception/interception_win.cpp b/compiler-rt/lib/interception/interception_win.cpp
index a5897274521e92..282e6399683e8d 100644
--- a/compiler-rt/lib/interception/interception_win.cpp
+++ b/compiler-rt/lib/interception/interception_win.cpp
@@ -634,6 +634,10 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
case 0xD284: // 84 D2 : test dl,dl
return 2;
+ case 0x3980: // 80 39 XX : cmp BYTE PTR [rcx], XX
+ case 0x4D8B: // 8B 4D XX : mov XX(%ebp), ecx
+ case 0x558B: // 8B 55 XX : mov XX(%ebp), edx
+ case 0x758B: // 8B 75 XX : mov XX(%ebp), esp
case 0xE483: // 83 E4 XX : and esp, XX
case 0xEC83: // 83 EC XX : sub esp, XX
case 0xC1F6: // F6 C1 XX : test cl, XX
@@ -740,6 +744,9 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
case 0xc1ff48: // 48 ff c1 : inc rcx
case 0xc1ff49: // 49 ff c1 : inc r9
case 0xc28b41: // 41 8b c2 : mov eax, r10d
+ case 0x01b60f: // 0f b6 01 : movzx eax, BYTE PTR [rcx]
+ case 0x09b60f: // 0f b6 09 : movzx ecx, BYTE PTR [rcx]
+ case 0x11b60f: // 0f b6 11 : movzx edx, BYTE PTR [rcx]
case 0xc2b60f: // 0f b6 c2 : movzx eax, dl
case 0xc2ff48: // 48 ff c2 : inc rdx
case 0xc2ff49: // 49 ff c2 : inc r10
@@ -758,6 +765,7 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
case 0xc98548: // 48 85 c9 : test rcx, rcx
case 0xc9854d: // 4d 85 c9 : test r9, r9
case 0xc98b4c: // 4c 8b c9 : mov r9, rcx
+ case 0xd12948: // 48 29 d1 : sub rcx, rdx
case 0xca2b48: // 48 2b ca : sub rcx, rdx
case 0xca3b48: // 48 3b ca : cmp rcx, rdx
case 0xd12b48: // 48 2b d1 : sub rdx, rcx
@@ -767,16 +775,33 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
case 0xd2854d: // 4d 85 d2 : test r10, r10
case 0xd28b4c: // 4c 8b d2 : mov r10, rdx
case 0xd2b60f: // 0f b6 d2 : movzx edx, dl
+ case 0xd2be0f: // 0f be d2 : movsx edx, dl
case 0xd98b4c: // 4c 8b d9 : mov r11, rcx
case 0xd9f748: // 48 f7 d9 : neg rcx
+ case 0xc03145: // 45 31 c0 : xor r8d,r8d
+ case 0xc93145: // 45 31 c9 : xor r9d,r9d
case 0xdb3345: // 45 33 db : xor r11d, r11d
+ case 0xc08445: // 45 84 c0 : test r8b,r8b
+ case 0xd28445: // 45 84 d2 : test r10b,r10b
case 0xdb8548: // 48 85 db : test rbx, rbx
case 0xdb854d: // 4d 85 db : test r11, r11
case 0xdc8b4c: // 4c 8b dc : mov r11, rsp
case 0xe48548: // 48 85 e4 : test rsp, rsp
case 0xe4854d: // 4d 85 e4 : test r12, r12
+ case 0xc88948: // 48 89 c8 : mov rax,rcx
+ case 0xcb8948: // 48 89 cb : mov rbx,rcx
+ case 0xd08948: // 48 89 d0 : mov rax,rdx
+ case 0xd18948: // 48 89 d1 : mov rcx,rdx
+ case 0xd38948: // 48 89 d3 : mov rbx,rdx
case 0xe58948: // 48 89 e5 : mov rbp, rsp
case 0xed8548: // 48 85 ed : test rbp, rbp
+ case 0xc88949: // 49 89 c8 : mov r8, rcx
+ case 0xc98949: // 49 89 c9 : mov r9, rcx
+ case 0xca8949: // 49 89 ca : mov r10,rcx
+ case 0xd08949: // 49 89 d0 : mov r8, rdx
+ case 0xd18949: // 49 89 d1 : mov r9, rdx
+ case 0xd28949: // 49 89 d2 : mov r10, rdx
+ case 0xd38949: // 49 89 d3 : mov r11, rdx
case 0xed854d: // 4d 85 ed : test r13, r13
case 0xf6854d: // 4d 85 f6 : test r14, r14
case 0xff854d: // 4d 85 ff : test r15, r15
diff --git a/compiler-rt/lib/interception/tests/interception_win_test.cpp b/compiler-rt/lib/interception/tests/interception_win_test.cpp
index 04d9a6766f65ad..c8bfcfad573771 100644
--- a/compiler-rt/lib/interception/tests/interception_win_test.cpp
+++ b/compiler-rt/lib/interception/tests/interception_win_test.cpp
@@ -852,8 +852,12 @@ const struct InstructionSizeData {
{ 2, {0x8B, 0xC1}, 0, "8B C1 : mov eax, ecx"},
{ 2, {0x8B, 0xEC}, 0, "8B EC : mov ebp, esp"},
{ 2, {0x8B, 0xFF}, 0, "8B FF : mov edi, edi"},
+ { 3, {0x80, 0x39, 0x72}, 0, "80 39 XX : cmp BYTE PTR [rcx], XX"},
{ 3, {0x83, 0xE4, 0x72}, 0, "83 E4 XX : and esp, XX"},
{ 3, {0x83, 0xEC, 0x72}, 0, "83 EC XX : sub esp, XX"},
+ { 3, {0x8B, 0x4D, 0x72}, 0, "8B 4D XX : mov XX(%ebp), ecx"},
+ { 3, {0x8B, 0x55, 0x72}, 0, "8B 55 XX : mov XX(%ebp), edx"},
+ { 3, {0x8B, 0x75, 0x72}, 0, "8B 75 XX : mov XX(%ebp), esp"},
{ 3, {0xc2, 0x71, 0x72}, 0, "C2 XX XX : ret XX (needed for registering weak functions)"},
{ 5, {0x68, 0x71, 0x72, 0x73, 0x74}, 0, "68 XX XX XX XX : push imm32"},
{ 5, {0xb8, 0x71, 0x72, 0x73, 0x74}, 0, "b8 XX XX XX XX : mov eax, XX XX XX XX"},
@@ -875,17 +879,26 @@ const struct InstructionSizeData {
{ 2, {0x66, 0x90}, 0, "66 90 : Two-byte NOP"},
{ 2, {0x84, 0xc0}, 0, "84 c0 : test al, al"},
{ 2, {0x8a, 0x01}, 0, "8a 01 : mov al, byte ptr [rcx]"},
+ { 3, {0x0f, 0xb6, 0x01}, 0, "0f b6 01 : movzx eax, BYTE PTR [rcx]"},
+ { 3, {0x0f, 0xb6, 0x09}, 0, "0f b6 09 : movzx ecx, BYTE PTR [rcx]"},
+ { 3, {0x0f, 0xb6, 0x11}, 0, "0f b6 11 : movzx edx, BYTE PTR [rcx]"},
{ 3, {0x0f, 0xb6, 0xc2}, 0, "0f b6 c2 : movzx eax, dl"},
{ 3, {0x0f, 0xb6, 0xd2}, 0, "0f b6 d2 : movzx edx, dl"},
{ 3, {0x0f, 0xb7, 0x10}, 0, "0f b7 10 : movzx edx, WORD PTR [rax]"},
+ { 3, {0x0f, 0xbe, 0xd2}, 0, "0f be d2 : movsx edx, dl"},
{ 3, {0x41, 0x8b, 0xc0}, 0, "41 8b c0 : mov eax, r8d"},
{ 3, {0x41, 0x8b, 0xc1}, 0, "41 8b c1 : mov eax, r9d"},
{ 3, {0x41, 0x8b, 0xc2}, 0, "41 8b c2 : mov eax, r10d"},
{ 3, {0x41, 0x8b, 0xc3}, 0, "41 8b c3 : mov eax, r11d"},
{ 3, {0x41, 0x8b, 0xc4}, 0, "41 8b c4 : mov eax, r12d"},
+ { 3, {0x45, 0x31, 0xc0}, 0, "45 31 c0 : xor r8d,r8d"},
+ { 3, {0x45, 0x31, 0xc9}, 0, "45 31 c9 : xor r9d,r9d"},
{ 3, {0x45, 0x33, 0xc0}, 0, "45 33 c0 : xor r8d, r8d"},
{ 3, {0x45, 0x33, 0xc9}, 0, "45 33 c9 : xor r9d, r9d"},
{ 3, {0x45, 0x33, 0xdb}, 0, "45 33 db : xor r11d, r11d"},
+ { 3, {0x45, 0x84, 0xc0}, 0, "45 84 c0 : test r8b,r8b"},
+ { 3, {0x45, 0x84, 0xd2}, 0, "45 84 d2 : test r10b,r10b"},
+ { 3, {0x48, 0x29, 0xd1}, 0, "48 29 d1 : sub rcx, rdx"},
{ 3, {0x48, 0x2b, 0xca}, 0, "48 2b ca : sub rcx, rdx"},
{ 3, {0x48, 0x2b, 0xd1}, 0, "48 2b d1 : sub rdx, rcx"},
{ 3, {0x48, 0x3b, 0xca}, 0, "48 3b ca : cmp rcx, rdx"},
@@ -895,6 +908,11 @@ const struct InstructionSizeData {
{ 3, {0x48, 0x85, 0xdb}, 0, "48 85 db : test rbx, rbx"},
{ 3, {0x48, 0x85, 0xe4}, 0, "48 85 e4 : test rsp, rsp"},
{ 3, {0x48, 0x85, 0xed}, 0, "48 85 ed : test rbp, rbp"},
+ { 3, {0x48, 0x89, 0xc8}, 0, "48 89 c8 : mov rax,rcx"},
+ { 3, {0x48, 0x89, 0xcb}, 0, "48 89 cb : mov rbx,rcx"},
+ { 3, {0x48, 0x89, 0xd0}, 0, "48 89 d0 : mov rax,rdx"},
+ { 3, {0x48, 0x89, 0xd1}, 0, "48 89 d1 : mov rcx,rdx"},
+ { 3, {0x48, 0x89, 0xd3}, 0, "48 89 d3 : mov rbx,rdx"},
{ 3, {0x48, 0x89, 0xe5}, 0, "48 89 e5 : mov rbp, rsp"},
{ 3, {0x48, 0x8b, 0xc1}, 0, "48 8b c1 : mov rax, rcx"},
{ 3, {0x48, 0x8b, 0xc4}, 0, "48 8b c4 : mov rax, rsp"},
@@ -906,6 +924,13 @@ const struct InstructionSizeData {
{ 3, {0x48, 0xff, 0xc3}, 0, "48 ff c3 : inc rbx"},
{ 3, {0x48, 0xff, 0xc6}, 0, "48 ff c6 : inc rsi"},
{ 3, {0x48, 0xff, 0xc7}, 0, "48 ff c7 : inc rdi"},
+ { 3, {0x49, 0x89, 0xc8}, 0, "49 89 c8 : mov r8, rcx"},
+ { 3, {0x49, 0x89, 0xc9}, 0, "49 89 c9 : mov r9, rcx"},
+ { 3, {0x49, 0x89, 0xca}, 0, "49 89 ca : mov r10,rcx"},
+ { 3, {0x49, 0x89, 0xd0}, 0, "49 89 d0 : mov r8, rdx"},
+ { 3, {0x49, 0x89, 0xd1}, 0, "49 89 d1 : mov r9, rdx"},
+ { 3, {0x49, 0x89, 0xd2}, 0, "49 89 d2 : mov r10, rdx"},
+ { 3, {0x49, 0x89, 0xd3}, 0, "49 89 d3 : mov r11, rdx"},
{ 3, {0x49, 0xff, 0xc0}, 0, "49 ff c0 : inc r8"},
{ 3, {0x49, 0xff, 0xc1}, 0, "49 ff c1 : inc r9"},
{ 3, {0x49, 0xff, 0xc2}, 0, "49 ff c2 : inc r10"},
|
|
CC: @zmodem |
Thanks for merging all these patches. I had hoped I would come away without making an application for commit rights, because if those GetInstructionSize patches are landed I don't know if I am a great help for the project. What about this PR? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This patch adds several instructions seen when trying to run a
executable built with ASan with llvm-mingw.
(x86 and x86_64, using the git tip in llvm-project).
Also includes instructions collected by
Roman Pišl and Eric Pouech in the Wine bug reports below.