[compiler-rt] 213c90d - [win/asan] GetInstructionSize: Fix `41 81 7c ...` to return 9. (#117828)

[via llvm-commits]

Author: bernhardu
Date: 2024-12-09T18:14:55+01:00
New Revision: 213c90d3c1f1517eb7a75ecf834f1faf90c288a8

URL: https://github.com/llvm/llvm-project/commit/213c90d3c1f1517eb7a75ecf834f1faf90c288a8
DIFF: https://github.com/llvm/llvm-project/commit/213c90d3c1f1517eb7a75ecf834f1faf90c288a8.diff

LOG: [win/asan] GetInstructionSize: Fix `41 81 7c ...` to return 9. (#117828)

Trying to populate the recently added test for GetInstructionSize I
stumbled over this.
gdb and bddisasm have the opinion this instruction is 9 bytes.
Also lldb shows this:
```
(lldb) disassemble --bytes --start-address 0x0000555555556004 --end-address 0x0000555555556024
    0x555555556004: 41 81 7b 73 74 75 76 77     cmpl   $0x77767574, 0x73(%r11)   ; imm = 0x77767574 
    0x55555555600c: 41 81 7c 73 74 75 76 77 78  cmpl   $0x78777675, 0x74(%r11,%rsi,2) ; imm = 0x78777675 
    0x555555556015: 41 81 7d 73 74 75 76 77     cmpl   $0x77767574, 0x73(%r13)   ; imm = 0x77767574 
    0x55555555601d: 00 00                       addb   %al, (%rax)
```

There is also a handy tool in llvm to directly feed in the byte sequence
- `41 81 7c` also uses 9 bytes here:
```
$ echo -n -e "0x41, 0x81, 0x7b, 0x73, 0x74, 0x75, 0x76, 0x77, 0x90" | ./llvm/build/bin/llvm-mc --disassemble --show-encoding
        .text
        cmpl    $2004252020, 115(%r11)          # encoding: [0x41,0x81,0x7b,0x73,0x74,0x75,0x76,0x77]
                                        # imm = 0x77767574
        nop                                     # encoding: [0x90]
$ echo -n -e "0x41, 0x81, 0x7c, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x90" | ./llvm/build/bin/llvm-mc --disassemble --show-encoding
        .text
        cmpl    $2021095029, 116(%r11,%rsi,2)   # encoding: [0x41,0x81,0x7c,0x73,0x74,0x75,0x76,0x77,0x78]
                                        # imm = 0x78777675
        nop                                     # encoding: [0x90]
```

Added: 
    

Modified: 
    compiler-rt/lib/interception/interception_win.cpp
    compiler-rt/lib/interception/tests/interception_win_test.cpp

Removed: 
    


################################################################################
diff  --git a/compiler-rt/lib/interception/interception_win.cpp b/compiler-rt/lib/interception/interception_win.cpp
index 93886e79fd88c8..cfa38fe702ebcd 100644
--- a/compiler-rt/lib/interception/interception_win.cpp
+++ b/compiler-rt/lib/interception/interception_win.cpp
@@ -808,7 +808,6 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
     case 0x798141:  // 41 81 79 XX YY YY YY YY : cmp DWORD PTR [r9+YY], XX XX XX XX
     case 0x7a8141:  // 41 81 7a XX YY YY YY YY : cmp DWORD PTR [r10+YY], XX XX XX XX
     case 0x7b8141:  // 41 81 7b XX YY YY YY YY : cmp DWORD PTR [r11+YY], XX XX XX XX
-    case 0x7c8141:  // 41 81 7c XX YY YY YY YY : cmp DWORD PTR [r12+YY], XX XX XX XX
     case 0x7d8141:  // 41 81 7d XX YY YY YY YY : cmp DWORD PTR [r13+YY], XX XX XX XX
     case 0x7e8141:  // 41 81 7e XX YY YY YY YY : cmp DWORD PTR [r14+YY], XX XX XX XX
     case 0x7f8141:  // 41 81 7f YY XX XX XX XX : cmp DWORD PTR [r15+YY], XX XX XX XX
@@ -835,6 +834,10 @@ static size_t GetInstructionSize(uptr address, size_t* rel_offset = nullptr) {
     case 0x2444c7:    // C7 44 24 XX YY YY YY YY
                       //   mov dword ptr [rsp + XX], YYYYYYYY
       return 8;
+
+    case 0x7c8141:  // 41 81 7c ZZ YY XX XX XX XX
+                    // cmp DWORD PTR [reg+reg*n+YY], XX XX XX XX
+      return 9;
   }
 
   switch (*(u32*)(address)) {

diff  --git a/compiler-rt/lib/interception/tests/interception_win_test.cpp b/compiler-rt/lib/interception/tests/interception_win_test.cpp
index 3c60d9c6f49df9..ca61ffd4dd4604 100644
--- a/compiler-rt/lib/interception/tests/interception_win_test.cpp
+++ b/compiler-rt/lib/interception/tests/interception_win_test.cpp
@@ -989,6 +989,7 @@ const struct InstructionSizeData {
     { 8, {0x41, 0x81, 0x7f, 0x73, 0x74, 0x75, 0x76, 0x77}, 0, "41 81 7f YY XX XX XX XX : cmp DWORD PTR [r15+YY], XX XX XX XX"},
     { 8, {0x81, 0x7c, 0x24, 0x73, 0x74, 0x75, 0x76, 0x77}, 0, "81 7c 24 YY XX XX XX XX : cmp DWORD PTR [rsp+YY], XX XX XX XX"},
     { 8, {0xc7, 0x44, 0x24, 0x73, 0x74, 0x75, 0x76, 0x77}, 0, "C7 44 24 XX YY YY YY YY : mov dword ptr [rsp + XX], YYYYYYYY"},
+    { 9, {0x41, 0x81, 0x7c, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78}, 0, "41 81 7c ZZ YY XX XX XX XX : cmp DWORD PTR [reg+reg*n+YY], XX XX XX XX"},
     { 9, {0xA1, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78}, 0, "A1 XX XX XX XX XX XX XX XX : movabs eax, dword ptr ds:[XXXXXXXX]"},
 #else
     // sorted list