[clang] [llvm] [SystemZ][z/OS] Support both EBCDIC & ASCII form of type_info::name() (PR #179687)

[via cfe-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-clang-codegen

Author: Abhina Sree (abhina-sree)

<details>
<summary>Changes</summary>

On z/OS, typename is stored as 2 encodings: EBCDIC (default system encoding) followed by ASCII.

---
Full diff: https://github.com/llvm/llvm-project/pull/179687.diff


4 Files Affected:

- (modified) clang/lib/CodeGen/ItaniumCXXABI.cpp (+15-2) 
- (added) clang/test/CodeGenCXX/zos-typename.cpp (+14) 
- (modified) llvm/include/llvm/TargetParser/Triple.h (+4) 
- (modified) llvm/lib/TargetParser/Triple.cpp (+7) 


``````````diff
diff --git a/clang/lib/CodeGen/ItaniumCXXABI.cpp b/clang/lib/CodeGen/ItaniumCXXABI.cpp
index a6c80cd083bb8..07ff8da12004c 100644
--- a/clang/lib/CodeGen/ItaniumCXXABI.cpp
+++ b/clang/lib/CodeGen/ItaniumCXXABI.cpp
@@ -36,6 +36,7 @@
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Value.h"
 #include "llvm/Support/ScopedPrinter.h"
+#include "llvm/Support/TextEncoding.h"
 
 #include <optional>
 
@@ -3619,8 +3620,20 @@ llvm::GlobalVariable *ItaniumRTTIBuilder::GetAddrOfTypeName(
   // We know that the mangled name of the type starts at index 4 of the
   // mangled name of the typename, so we can just index into it in order to
   // get the mangled name of the type.
-  llvm::Constant *Init = llvm::ConstantDataArray::getString(VMContext,
-                                                            Name.substr(4));
+  llvm::Constant *Init;
+  if (CGM.getTriple().isOSzOS()) {
+    // On z/OS, typename is stored as 2 encodings: EBCDIC followed by ASCII.
+    SmallString<256> DualEncodedName;
+    llvm::ErrorOr<llvm::TextEncodingConverter> Converter =
+        llvm::TextEncodingConverter::create(
+            "UTF-8", CGM.getTriple().getDefaultNarrowTextEncoding());
+    Converter->convert(Name.substr(4), DualEncodedName);
+    DualEncodedName += '\0';
+    DualEncodedName += Name.substr(4);
+    Init = llvm::ConstantDataArray::getString(VMContext, DualEncodedName);
+  } else
+    Init = llvm::ConstantDataArray::getString(VMContext, Name.substr(4));
+
   auto Align = CGM.getContext().getTypeAlignInChars(CGM.getContext().CharTy);
 
   llvm::GlobalVariable *GV = CGM.CreateOrReplaceCXXRuntimeVariable(
diff --git a/clang/test/CodeGenCXX/zos-typename.cpp b/clang/test/CodeGenCXX/zos-typename.cpp
new file mode 100644
index 0000000000000..dabb9cc25ae60
--- /dev/null
+++ b/clang/test/CodeGenCXX/zos-typename.cpp
@@ -0,0 +1,14 @@
+// RUN: %clang -S -emit-llvm -target s390x-none-zos -I%S -fexec-charset=UTF-8 %s -o - | FileCheck %s
+// RUN: %clang -S -emit-llvm -target s390x-none-zos -I%S %s -o - | FileCheck %s
+// RUN: %clang -S -emit-llvm -target s390x-none-zos -I%S -m32 %s -o - | FileCheck %s
+
+#include <typeinfo>
+
+class TestClass {};
+struct TestStruct {};
+
+const char *A = typeid(TestClass).name();
+const char *B = typeid(TestStruct).name();
+
+// CHECK: @_ZTS9TestClass = {{.*}} c"\F9\E3\85\A2\A3\C3\93\81\A2\A2\009TestClass\00"
+// CHECK: @_ZTS10TestStruct = {{.*}} c"\F1\F0\E3\85\A2\A3\E2\A3\99\A4\83\A3\0010TestStruct\00"
diff --git a/llvm/include/llvm/TargetParser/Triple.h b/llvm/include/llvm/TargetParser/Triple.h
index 8559d7b088ee1..463323e379765 100644
--- a/llvm/include/llvm/TargetParser/Triple.h
+++ b/llvm/include/llvm/TargetParser/Triple.h
@@ -506,6 +506,10 @@ class Triple {
   /// string (separated by a '-' if the environment component is present).
   LLVM_ABI StringRef getOSAndEnvironmentName() const;
 
+  /// Get the default system encoding of the triple.
+  /// For example, "IBM-1047" for z/OS, "UTF-8" for others
+  LLVM_ABI StringRef getDefaultNarrowTextEncoding() const;
+
   /// Get the version component of the environment component as a single
   /// string (the version after the environment).
   ///
diff --git a/llvm/lib/TargetParser/Triple.cpp b/llvm/lib/TargetParser/Triple.cpp
index e6a9eedab5954..8a094b2f2d9ec 100644
--- a/llvm/lib/TargetParser/Triple.cpp
+++ b/llvm/lib/TargetParser/Triple.cpp
@@ -1437,6 +1437,13 @@ StringRef Triple::getOSAndEnvironmentName() const {
   return Tmp.split('-').second;                      // Strip second component
 }
 
+// Default encoding on z/OS is IBM-1047 and UTF-8 otherwise
+StringRef Triple::getDefaultNarrowTextEncoding() const {
+  if (getOS() == llvm::Triple::ZOS)
+    return "IBM-1047";
+  return "UTF-8";
+}
+
 static VersionTuple parseVersionFromName(StringRef Name) {
   VersionTuple Version;
   Version.tryParse(Name);

``````````

</details>


https://github.com/llvm/llvm-project/pull/179687