[CIR][Dialect] Add SourceLangAttr (#152511)

This patch upstreams `SourceLangAttr` and its CodeGen logic in the CGM,
which encodes the source language in CIR.

Author: seven-mile

clang/include/clang/CIR/Dialect/IR/CIRAttrs.td

@@ -50,6 +50,45 @@ class CIR_UnitAttr<string name, string attrMnemonic, list<Trait> traits = []>
   let isOptional = 1;
 }
 
+//===----------------------------------------------------------------------===//
+// SourceLanguageAttr
+//===----------------------------------------------------------------------===//
+
+// TODO: Add cases for other languages that Clang supports.
+
+def CIR_SourceLanguage : CIR_I32EnumAttr<"SourceLanguage", "source language", [
+  I32EnumAttrCase<"C", 1, "c">,
+  I32EnumAttrCase<"CXX", 2, "cxx">
+]> {
+  // The enum attr class is defined in `CIR_SourceLanguageAttr` below,
+  // so that it can define extra class methods.
+  let genSpecializedAttr = 0;
+}
+
+def CIR_SourceLanguageAttr : CIR_EnumAttr<CIR_SourceLanguage, "lang"> {
+
+  let summary = "Module source language";
+  let description = [{
+    Represents the source language used to generate the module.
+
+    Example:
+    ```
+    // Module compiled from C.
+    module attributes {cir.lang = cir.lang<c>} {}
+    // Module compiled from C++.
+    module attributes {cir.lang = cir.lang<cxx>} {}
+    ```
+
+    Module source language attribute name is `cir.lang` is defined by
+    `getSourceLanguageAttrName` method in CIRDialect class.
+  }];
+
+  let extraClassDeclaration = [{
+    bool isC() const { return getValue() == SourceLanguage::C; }
+    bool isCXX() const { return getValue() == SourceLanguage::CXX; }
+  }];
+}
+
 //===----------------------------------------------------------------------===//
 // OptInfoAttr
 //===----------------------------------------------------------------------===//

clang/include/clang/CIR/Dialect/IR/CIRDialect.td

@@ -35,6 +35,7 @@ def CIR_Dialect : Dialect {
   let hasConstantMaterializer = 1;
 
   let extraClassDeclaration = [{
+    static llvm::StringRef getSourceLanguageAttrName() { return "cir.lang"; }
     static llvm::StringRef getTripleAttrName() { return "cir.triple"; }
     static llvm::StringRef getOptInfoAttrName() { return "cir.opt_info"; }
     static llvm::StringRef getCalleeAttrName() { return "callee"; }

clang/include/clang/CIR/MissingFeatures.h

@@ -264,6 +264,7 @@ struct MissingFeatures {
   static bool setNonGC() { return false; }
   static bool setObjCGCLValueClass() { return false; }
   static bool setTargetAttributes() { return false; }
+  static bool sourceLanguageCases() { return false; }
   static bool stackBase() { return false; }
   static bool stackSaveOp() { return false; }
   static bool targetCIRGenInfoArch() { return false; }

clang/lib/CIR/CodeGen/CIRGenModule.cpp

@@ -103,6 +103,9 @@ CIRGenModule::CIRGenModule(mlir::MLIRContext &mlirContext,
   PtrDiffTy =
       cir::IntType::get(&getMLIRContext(), sizeTypeSize, /*isSigned=*/true);
 
+  theModule->setAttr(
+      cir::CIRDialect::getSourceLanguageAttrName(),
+      cir::SourceLanguageAttr::get(&mlirContext, getCIRSourceLanguage()));
   theModule->setAttr(cir::CIRDialect::getTripleAttrName(),
                      builder.getStringAttr(getTriple().str()));
 
@@ -510,6 +513,23 @@ void CIRGenModule::setNonAliasAttributes(GlobalDecl gd, mlir::Operation *op) {
   assert(!cir::MissingFeatures::setTargetAttributes());
 }
 
+cir::SourceLanguage CIRGenModule::getCIRSourceLanguage() const {
+  using ClangStd = clang::LangStandard;
+  using CIRLang = cir::SourceLanguage;
+  auto opts = getLangOpts();
+
+  if (opts.CPlusPlus)
+    return CIRLang::CXX;
+  if (opts.C99 || opts.C11 || opts.C17 || opts.C23 || opts.C2y ||
+      opts.LangStd == ClangStd::lang_c89 ||
+      opts.LangStd == ClangStd::lang_gnu89)
+    return CIRLang::C;
+
+  // TODO(cir): support remaining source languages.
+  assert(!cir::MissingFeatures::sourceLanguageCases());
+  errorNYI("CIR does not yet support the given source language");
+}
+
 static void setLinkageForGV(cir::GlobalOp &gv, const NamedDecl *nd) {
   // Set linkage and visibility in case we never see a definition.
   LinkageInfo lv = nd->getLinkageAndVisibility();

clang/lib/CIR/CodeGen/CIRGenModule.h

@@ -461,6 +461,9 @@ class CIRGenModule : public CIRGenTypeCache {
   void replacePointerTypeArgs(cir::FuncOp oldF, cir::FuncOp newF);
 
   void setNonAliasAttributes(GlobalDecl gd, mlir::Operation *op);
+
+  /// Map source language used to a CIR attribute.
+  cir::SourceLanguage getCIRSourceLanguage() const;
 };
 } // namespace CIRGen
 

clang/test/CIR/CodeGen/lang-c-cpp.cpp

@@ -0,0 +1,11 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fclangir -emit-cir %s -o %t.cpp.cir
+// RUN: FileCheck --check-prefix=CIR-CPP --input-file=%t.cpp.cir %s
+// RUN: %clang_cc1 -x c -triple x86_64-unknown-linux-gnu -fclangir -emit-cir %s -o %t.c.cir
+// RUN: FileCheck --check-prefix=CIR-C --input-file=%t.c.cir %s
+
+// CIR-CPP: module attributes {{{.*}}cir.lang = #cir.lang<cxx>{{.*}}}
+// CIR-C: module attributes {{{.*}}cir.lang = #cir.lang<c>{{.*}}}
+
+int main() {
+  return 0;
+}

clang/test/CIR/IR/invalid-lang-attr.cir

@@ -0,0 +1,5 @@
+// RUN: cir-opt %s -verify-diagnostics
+
+// expected-error@below {{expected ::cir::SourceLanguage to be one of}}
+// expected-error@below {{failed to parse CIR_SourceLanguageAttr parameter 'value'}}
+module attributes {cir.lang = #cir.lang<dummy>} { }

clang/test/CIR/IR/module.cir

@@ -0,0 +1,12 @@
+// RUN: cir-opt %s -split-input-file -o %t.cir
+// RUN: FileCheck --input-file=%t.cir %s
+
+// Should parse and print C source language attribute.
+module attributes {cir.lang = #cir.lang<c>} { }
+// CHECK: module attributes {cir.lang = #cir.lang<c>}
+
+// -----
+
+// Should parse and print C++ source language attribute.
+module attributes {cir.lang = #cir.lang<cxx>} { }
+// CHECK: module attributes {cir.lang = #cir.lang<cxx>}