[llvm] [AArch64] Fix Arm64EC mangling with C++ symbols using MD5 mangling. (PR #160963)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 26 15:44:23 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: Eli Friedman (efriedma-quic)
<details>
<summary>Changes</summary>
In addition to the usual mangling formats, MSVC uses a special mangling format for very long symbols: instead of actually emitting the mangled name, it hashes the name, and uses the hash as the symbol. This doesn't match any of the usual forms, so it needs special handling.
Fixes a crash/link error when using such symbols.
(Unrelated to this patch, there's something weird about the way MSVC handles these symbols in Arm64EC mode: it looks like MSVC is computing a different hash compared to x64 MSVC, and clang. I think this is bug. Noting this here in case someone wants to compare MSVC vs. clang output.)
---
Full diff: https://github.com/llvm/llvm-project/pull/160963.diff
4 Files Affected:
- (modified) llvm/include/llvm/IR/Mangler.h (+2-1)
- (modified) llvm/lib/IR/Mangler.cpp (+21)
- (modified) llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll (+42)
- (modified) llvm/unittests/IR/ManglerTest.cpp (+3)
``````````diff
diff --git a/llvm/include/llvm/IR/Mangler.h b/llvm/include/llvm/IR/Mangler.h
index 232101a8926b7..386e561e42a89 100644
--- a/llvm/include/llvm/IR/Mangler.h
+++ b/llvm/include/llvm/IR/Mangler.h
@@ -81,7 +81,8 @@ getArm64ECDemangledFunctionName(StringRef Name);
/// Check if an ARM64EC function name is mangled.
bool inline isArm64ECMangledFunctionName(StringRef Name) {
return Name[0] == '#' ||
- (Name[0] == '?' && Name.find("@$$h") != StringRef::npos);
+ (Name[0] == '?' && Name.find("@$$h") != StringRef::npos) ||
+ (Name.starts_with("??@") && Name.ends_with("@$h@"));
}
} // End llvm namespace
diff --git a/llvm/lib/IR/Mangler.cpp b/llvm/lib/IR/Mangler.cpp
index ca6a4804087ac..ea12d76125e86 100644
--- a/llvm/lib/IR/Mangler.cpp
+++ b/llvm/lib/IR/Mangler.cpp
@@ -307,6 +307,23 @@ std::optional<std::string> llvm::getArm64ECMangledFunctionName(StringRef Name) {
if (Name.contains("$$h"))
return std::nullopt;
+ // Handle MD5 mangled names, which use a slightly different rule from
+ // other C++ manglings.
+ //
+ // A non-Arm64EC function:
+ //
+ // ??@aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa@
+ //
+ // An Arm64EC function:
+ //
+ // ??@aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa@$h@
+ if (Name.starts_with("??@")) {
+ if (Name.ends_with("@$h@"))
+ return std::nullopt;
+ else if (Name.ends_with("@"))
+ return (Name + "$h@").str();
+ }
+
// Ask the demangler where we should insert "$$h".
auto InsertIdx = getArm64ECInsertionPointInMangledName(Name);
if (!InsertIdx)
@@ -324,6 +341,10 @@ llvm::getArm64ECDemangledFunctionName(StringRef Name) {
if (Name[0] != '?')
return std::nullopt;
+ // MD5 mangled name; see comment in getArm64ECMangledFunctionName.
+ if (Name.starts_with("??@") && Name.ends_with("@$h@"))
+ return Name.drop_back(3).str();
+
// Drop the ARM64EC "$$h" tag.
std::pair<StringRef, StringRef> Pair = Name.split("$$h");
if (Pair.second.empty())
diff --git a/llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll b/llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll
index f829227a47cd7..7e165c24c5f27 100644
--- a/llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll
+++ b/llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll
@@ -563,6 +563,41 @@ declare <8 x i16> @large_vector(<8 x i16> %0) nounwind;
; CHECK-NEXT: .seh_endfunclet
; CHECK-NEXT: .seh_endproc
+declare void @"??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"()
+; CHECK-LABEL: .def "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@";
+; CHECK-NEXT: .scl 2;
+; CHECK-NEXT: .type 32;
+; CHECK-NEXT: .endef
+; CHECK-NEXT: .section .wowthk$aa,"xr",discard,"??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: .globl "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@" // -- Begin function ??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@
+; CHECK-NEXT: .p2align 2
+; CHECK-NEXT: "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@": // @"??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: .weak_anti_dep "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"
+; CHECK-NEXT: "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@" = "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: .weak_anti_dep "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@" = "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: .seh_proc "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: // %bb.0:
+; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT: .seh_save_reg_x x30, 16
+; CHECK-NEXT: .seh_endprologue
+; CHECK-NEXT: adrp x8, __os_arm64x_check_icall
+; CHECK-NEXT: adrp x11, "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"
+; CHECK-NEXT: add x11, x11, :lo12:"??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"
+; CHECK-NEXT: ldr x8, [x8, :lo12:__os_arm64x_check_icall]
+; CHECK-NEXT: adrp x10, $iexit_thunk$cdecl$v$v
+; CHECK-NEXT: add x10, x10, :lo12:$iexit_thunk$cdecl$v$v
+; CHECK-NEXT: blr x8
+; CHECK-NEXT: .seh_startepilogue
+; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-NEXT: .seh_save_reg_x x30, 16
+; CHECK-NEXT: .seh_endepilogue
+; CHECK-NEXT: br x11
+; CHECK-NEXT: .seh_endfunclet
+; CHECK-NEXT: .seh_endproc
+
+
+
; CHECK-LABEL: .section .hybmp$x,"yi"
; CHECK-NEXT: .symidx "#func_caller"
; CHECK-NEXT: .symidx $ientry_thunk$cdecl$v$v
@@ -633,6 +668,12 @@ declare <8 x i16> @large_vector(<8 x i16> %0) nounwind;
; CHECK-NEXT: .symidx "#large_vector$exit_thunk"
; CHECK-NEXT: .symidx large_vector
; CHECK-NEXT: .word 0
+; CHECK-NEXT: .symidx "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"
+; CHECK-NEXT: .symidx $iexit_thunk$cdecl$v$v
+; CHECK-NEXT: .word 4
+; CHECK-NEXT: .symidx "??$exit_thunk at md5mangleaaaaaaaaaaaaaaaaaaaaaaa@$h@"
+; CHECK-NEXT: .symidx "??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"
+; CHECK-NEXT: .word 0
define void @func_caller() nounwind {
call void @no_op()
@@ -649,5 +690,6 @@ define void @func_caller() nounwind {
call %T2 @simple_struct(%T1 { i16 0 }, %T2 { i32 0, float 0.0 }, %T3 { i64 0, double 0.0 }, %T4 { i64 0, double 0.0, i8 0 })
call <4 x i8> @small_vector(<4 x i8> <i8 0, i8 0, i8 0, i8 0>)
call <8 x i16> @large_vector(<8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
+ call void @"??@md5mangleaaaaaaaaaaaaaaaaaaaaaaa@"()
ret void
}
diff --git a/llvm/unittests/IR/ManglerTest.cpp b/llvm/unittests/IR/ManglerTest.cpp
index bced6ff10b45d..6cbd050b2691b 100644
--- a/llvm/unittests/IR/ManglerTest.cpp
+++ b/llvm/unittests/IR/ManglerTest.cpp
@@ -243,6 +243,9 @@ TEST(ManglerTest, Arm64EC) {
// public: int __cdecl Wrapper<struct A>::GetValue(struct WW<struct
// A>::Z)const
"?GetValue@?$Wrapper at UA@@@@$$hQEBAHUZ@?$WW at UA@@@@@Z",
+
+ // MD5 symbol
+ "??@aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa@$h@",
};
for (const auto &Arm64ECName : Arm64ECNames) {
``````````
</details>
https://github.com/llvm/llvm-project/pull/160963
More information about the llvm-commits
mailing list