[compiler-rt] [win/asan] GetInstructionSize: Support some more 2 byte instructions. (PR #120235)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-compiler-rt-sanitizer

Author: None (bernhardu)

<details>
<summary>Changes</summary>

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: https://github.com/llvm/llvm-project/issues/96270

Co-authored-by: Roman Pišl <rpisl@<!-- -->seznam.cz>
                https://bugs.winehq.org/show_bug.cgi?id=50993
                https://bugs.winehq.org/attachment.cgi?id=70233
Co-authored-by: Eric Pouech <eric.pouech@<!-- -->gmail.com>
                https://bugs.winehq.org/show_bug.cgi?id=52386
                https://bugs.winehq.org/attachment.cgi?id=71626
```

CC: @<!-- -->zmodem

---
Full diff: https://github.com/llvm/llvm-project/pull/120235.diff


2 Files Affected:

- (modified) compiler-rt/lib/interception/interception_win.cpp (+5) 
- (modified) compiler-rt/lib/interception/tests/interception_win_test.cpp (+5) 


``````````diff
diff --git a/compiler-rt/lib/interception/interception_win.cpp b/compiler-rt/lib/interception/interception_win.cpp
index a5897274521e92..cc85087d08b71b 100644
--- a/compiler-rt/lib/interception/interception_win.cpp
+++ b/compiler-rt/lib/interception/interception_win.cpp
@@ -624,12 +624,17 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
     case 0xFF8B:  // 8B FF : mov edi, edi
     case 0xEC8B:  // 8B EC : mov ebp, esp
     case 0xc889:  // 89 C8 : mov eax, ecx
+    case 0xD189:  // 89 D1 : mov ecx, edx
     case 0xE589:  // 89 E5 : mov ebp, esp
     case 0xC18B:  // 8B C1 : mov eax, ecx
+    case 0xC031:  // 31 C0 : xor eax, eax
+    case 0xC931:  // 31 C9 : xor ecx, ecx
+    case 0xD231:  // 31 D2 : xor edx, edx
     case 0xC033:  // 33 C0 : xor eax, eax
     case 0xC933:  // 33 C9 : xor ecx, ecx
     case 0xD233:  // 33 D2 : xor edx, edx
     case 0xDB84:  // 84 DB : test bl,bl
+    case 0xC084:  // 84 C0 : test al,al
     case 0xC984:  // 84 C9 : test cl,cl
     case 0xD284:  // 84 D2 : test dl,dl
       return 2;
diff --git a/compiler-rt/lib/interception/tests/interception_win_test.cpp b/compiler-rt/lib/interception/tests/interception_win_test.cpp
index 04d9a6766f65ad..9cb577f2c9b916 100644
--- a/compiler-rt/lib/interception/tests/interception_win_test.cpp
+++ b/compiler-rt/lib/interception/tests/interception_win_test.cpp
@@ -839,14 +839,19 @@ const struct InstructionSizeData {
     { 1, {0x90}, 0, "90 : nop"},
     { 1, {0xC3}, 0, "C3 : ret   (for small/empty function interception"},
     { 1, {0xCC}, 0, "CC : int 3  i.e. registering weak functions)"},
+    { 2, {0x31, 0xC0}, 0, "31 C0 : xor eax, eax"},
+    { 2, {0x31, 0xC9}, 0, "31 C9 : xor ecx, ecx"},
+    { 2, {0x31, 0xD2}, 0, "31 D2 : xor edx, edx"},
     { 2, {0x33, 0xC0}, 0, "33 C0 : xor eax, eax"},
     { 2, {0x33, 0xC9}, 0, "33 C9 : xor ecx, ecx"},
     { 2, {0x33, 0xD2}, 0, "33 D2 : xor edx, edx"},
     { 2, {0x6A, 0x71}, 0, "6A XX : push XX"},
+    { 2, {0x84, 0xC0}, 0, "84 C0 : test al,al"},
     { 2, {0x84, 0xC9}, 0, "84 C9 : test cl,cl"},
     { 2, {0x84, 0xD2}, 0, "84 D2 : test dl,dl"},
     { 2, {0x84, 0xDB}, 0, "84 DB : test bl,bl"},
     { 2, {0x89, 0xc8}, 0, "89 C8 : mov eax, ecx"},
+    { 2, {0x89, 0xD1}, 0, "89 D1 : mov ecx, edx"},
     { 2, {0x89, 0xE5}, 0, "89 E5 : mov ebp, esp"},
     { 2, {0x8A, 0x01}, 0, "8A 01 : mov al, byte ptr [ecx]"},
     { 2, {0x8B, 0xC1}, 0, "8B C1 : mov eax, ecx"},

``````````

</details>


https://github.com/llvm/llvm-project/pull/120235