[compiler-rt] [win/asan] GetInstructionSize: Support some more 4 byte instructions. (PR #123709)

[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/123709.diff


2 Files Affected:

- (modified) compiler-rt/lib/interception/interception_win.cpp (+11) 
- (modified) compiler-rt/lib/interception/tests/interception_win_test.cpp (+10) 


``````````diff
diff --git a/compiler-rt/lib/interception/interception_win.cpp b/compiler-rt/lib/interception/interception_win.cpp
index 0841161ee5c428..59c01e20e835cf 100644
--- a/compiler-rt/lib/interception/interception_win.cpp
+++ b/compiler-rt/lib/interception/interception_win.cpp
@@ -666,6 +666,9 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
   }
 
   switch (0x00FFFFFF & *(u32 *)address) {
+    case 0x244C8D:  // 8D 4C 24 XX : lea ecx, [esp + XX]
+    case 0x2474FF:  // FF 74 24 XX : push qword ptr [rsp + XX]
+      return 4;
     case 0x24A48D:  // 8D A4 24 XX XX XX XX : lea esp, [esp + XX XX XX XX]
       return 7;
   }
@@ -829,6 +832,8 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
     case 0x588948:    // 48 89 58 XX : mov QWORD PTR[rax + XX], rbx
     case 0xec8348:    // 48 83 ec XX : sub rsp, XX
     case 0xf88349:    // 49 83 f8 XX : cmp r8, XX
+    case 0x148d4e:    // 4e 8d 14 XX : lea r10, [rcx+r8*XX]
+    case 0x398366:    // 66 83 39 XX : cmp WORD PTR [rcx], XX
       return 4;
 
     case 0x246483:  // 83 64 24 XX YY :   and    DWORD PTR [rsp+XX], YY
@@ -883,7 +888,13 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
   }
 
   switch (*(u32*)(address)) {
+    case 0x01b60f44:  // 44 0f b6 01 : movzx r8d, BYTE PTR [rcx]
+    case 0x09b60f44:  // 44 0f b6 09 : movzx r9d, BYTE PTR [rcx]
+    case 0x0ab60f44:  // 44 0f b6 0a : movzx r8d, BYTE PTR [rdx]
+    case 0x11b60f44:  // 44 0f b6 11 : movzx r10d, BYTE PTR [rcx]
     case 0x1ab60f44:  // 44 0f b6 1a : movzx r11d, BYTE PTR [rdx]
+    case 0x11048d4c:  // 4c 8d 04 11 : lea r8,[rcx+rdx*1]
+    case 0xff488d49:  // 49 8d 48 ff : lea rcx,[r8-0x1]
       return 4;
     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
diff --git a/compiler-rt/lib/interception/tests/interception_win_test.cpp b/compiler-rt/lib/interception/tests/interception_win_test.cpp
index 9d8dbfcb4285fb..4f833249377300 100644
--- a/compiler-rt/lib/interception/tests/interception_win_test.cpp
+++ b/compiler-rt/lib/interception/tests/interception_win_test.cpp
@@ -864,6 +864,8 @@ const struct InstructionSizeData {
     { 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)"},
+    { 4, {0x8D, 0x4C, 0x24, 0x73}, 0, "8D 4C 24 XX : lea ecx, [esp + XX]"},
+    { 4, {0xFF, 0x74, 0x24, 0x73}, 0, "FF 74 24 XX : push qword ptr [rsp + XX]"},
     { 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"},
     { 5, {0xB9, 0x71, 0x72, 0x73, 0x74}, 0, "b9 XX XX XX XX : mov ecx, XX XX XX XX"},
@@ -961,11 +963,19 @@ const struct InstructionSizeData {
     { 3, {0x4d, 0x85, 0xf6}, 0, "4d 85 f6 : test r14, r14"},
     { 3, {0x4d, 0x85, 0xff}, 0, "4d 85 ff : test r15, r15"},
     { 3, {0xf6, 0xc1, 0x72}, 0, "f6 c1 XX : test cl, XX"},
+    { 4, {0x44, 0x0f, 0xb6, 0x01}, 0, "44 0f b6 01 : movzx r8d, BYTE PTR [rcx]"},
+    { 4, {0x44, 0x0f, 0xb6, 0x09}, 0, "44 0f b6 09 : movzx r9d, BYTE PTR [rcx]"},
+    { 4, {0x44, 0x0f, 0xb6, 0x0a}, 0, "44 0f b6 0a : movzx r8d, BYTE PTR [rdx]"},
+    { 4, {0x44, 0x0f, 0xb6, 0x11}, 0, "44 0f b6 11 : movzx r10d, BYTE PTR [rcx]"},
     { 4, {0x44, 0x0f, 0xb6, 0x1a}, 0, "44 0f b6 1a : movzx r11d, BYTE PTR [rdx]"},
     { 4, {0x44, 0x8d, 0x42, 0x73}, 0, "44 8d 42 XX : lea r8d , [rdx + XX]"},
     { 4, {0x48, 0x83, 0xec, 0x73}, 0, "48 83 ec XX : sub rsp, XX"},
     { 4, {0x48, 0x89, 0x58, 0x73}, 0, "48 89 58 XX : mov QWORD PTR[rax + XX], rbx"},
     { 4, {0x49, 0x83, 0xf8, 0x73}, 0, "49 83 f8 XX : cmp r8, XX"},
+    { 4, {0x49, 0x8d, 0x48, 0xff}, 0, "49 8d 48 ff : lea rcx,[r8-0x1]"},
+    { 4, {0x4c, 0x8d, 0x04, 0x11}, 0, "4c 8d 04 11 : lea r8,[rcx+rdx*1]"},
+    { 4, {0x4e, 0x8d, 0x14, 0x73}, 0, "4e 8d 14 XX : lea r10, [rcx+r8*XX]"},
+    { 4, {0x66, 0x83, 0x39, 0x73}, 0, "66 83 39 XX : cmp WORD PTR [rcx], XX"},
     { 4, {0x80, 0x78, 0x72, 0x73}, 0, "80 78 YY XX : cmp BYTE PTR [rax+YY], XX"},
     { 4, {0x80, 0x79, 0x72, 0x73}, 0, "80 79 YY XX : cmp BYTE ptr [rcx+YY], XX"},
     { 4, {0x80, 0x7A, 0x72, 0x73}, 0, "80 7A YY XX : cmp BYTE PTR [rdx+YY], XX"},

``````````

</details>


https://github.com/llvm/llvm-project/pull/123709