[llvm-debuginfo-analyzer] Add support for parsing DWARF / CodeView source language

Author: jalopezg-git

llvm/include/llvm/DebugInfo/LogicalView/Core/LVElement.h

@@ -14,10 +14,13 @@
 #ifndef LLVM_DEBUGINFO_LOGICALVIEW_CORE_LVELEMENT_H
 #define LLVM_DEBUGINFO_LOGICALVIEW_CORE_LVELEMENT_H
 
+#include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/DebugInfo/CodeView/CodeView.h"
 #include "llvm/DebugInfo/LogicalView/Core/LVObject.h"
 #include "llvm/Support/Casting.h"
 #include <map>
 #include <set>
+#include <variant>
 #include <vector>
 
 namespace llvm {
@@ -64,6 +67,22 @@ using LVElementKindSet = std::set<LVElementKind>;
 using LVElementDispatch = std::map<LVElementKind, LVElementGetFunction>;
 using LVElementRequest = std::vector<LVElementGetFunction>;
 
+/// A source language supported by any of the debug info representations.
+struct LVSourceLanguage {
+  LVSourceLanguage() = default;
+  LVSourceLanguage(llvm::dwarf::SourceLanguage SL) : Language(SL) {}
+  LVSourceLanguage(llvm::codeview::SourceLanguage SL) : Language(SL) {}
+
+  bool isValid() const { return Language.index() != 0; }
+  template <typename T> T getAs() { return std::get<T>(Language); }
+  StringRef getName() const;
+
+private:
+  std::variant<std::monostate, llvm::dwarf::SourceLanguage,
+               llvm::codeview::SourceLanguage>
+      Language;
+};
+
 class LVElement : public LVObject {
   enum class Property {
     IsLine,   // A logical line.
@@ -214,6 +233,9 @@ class LVElement : public LVObject {
   virtual StringRef getProducer() const { return StringRef(); }
   virtual void setProducer(StringRef ProducerName) {}
 
+  virtual LVSourceLanguage getSourceLanguage() const { return {}; }
+  virtual void setSourceLanguage(LVSourceLanguage SL) {}
+
   virtual bool isCompileUnit() const { return false; }
   virtual bool isRoot() const { return false; }
 

llvm/include/llvm/DebugInfo/LogicalView/Core/LVScope.h

@@ -407,6 +407,9 @@ class LVScopeCompileUnit final : public LVScope {
   // Toolchain producer.
   size_t ProducerIndex = 0;
 
+  // Source language.
+  LVSourceLanguage SourceLanguage{};
+
   // Compilation directory name.
   size_t CompilationDirectoryIndex = 0;
 
@@ -540,6 +543,9 @@ class LVScopeCompileUnit final : public LVScope {
     ProducerIndex = getStringPool().getIndex(ProducerName);
   }
 
+  LVSourceLanguage getSourceLanguage() const override { return SourceLanguage; }
+  void setSourceLanguage(LVSourceLanguage SL) override { SourceLanguage = SL; }
+
   void setCPUType(codeview::CPUType Type) { CompilationCPUType = Type; }
   codeview::CPUType getCPUType() { return CompilationCPUType; }
 

llvm/lib/DebugInfo/LogicalView/Core/LVElement.cpp

@@ -11,6 +11,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/DebugInfo/LogicalView/Core/LVElement.h"
+#include "llvm/DebugInfo/CodeView/EnumTables.h"
 #include "llvm/DebugInfo/LogicalView/Core/LVReader.h"
 #include "llvm/DebugInfo/LogicalView/Core/LVScope.h"
 #include "llvm/DebugInfo/LogicalView/Core/LVType.h"
@@ -19,6 +20,23 @@ using namespace llvm;
 using namespace llvm::codeview;
 using namespace llvm::logicalview;
 
+StringRef LVSourceLanguage::getName() const {
+  if (!isValid())
+    return {};
+  switch (Language.index()) {
+  case 1: // DWARF
+    return llvm::dwarf::LanguageString(
+        std::get<llvm::dwarf::SourceLanguage>(Language));
+  case 2: // CodeView
+  {
+    static auto LangNames = llvm::codeview::getSourceLanguageNames();
+    return LangNames[std::get<llvm::codeview::SourceLanguage>(Language)].Name;
+  }
+  default:
+    llvm_unreachable("Unsupported language");
+  }
+}
+
 #define DEBUG_TYPE "Element"
 
 LVElementDispatch LVElement::Dispatch = {

llvm/lib/DebugInfo/LogicalView/Core/LVScope.cpp

@@ -1707,11 +1707,17 @@ void LVScopeCompileUnit::print(raw_ostream &OS, bool Full) const {
 
 void LVScopeCompileUnit::printExtra(raw_ostream &OS, bool Full) const {
   OS << formattedKind(kind()) << " '" << getName() << "'\n";
-  if (options().getPrintFormatting() && options().getAttributeProducer())
+  if (options().getPrintFormatting() && options().getAttributeProducer()) {
     printAttributes(OS, Full, "{Producer} ",
                     const_cast<LVScopeCompileUnit *>(this), getProducer(),
                     /*UseQuotes=*/true,
                     /*PrintRef=*/false);
+    if (auto SL = getSourceLanguage(); SL.isValid())
+      printAttributes(OS, Full, "{Language} ",
+                      const_cast<LVScopeCompileUnit *>(this), SL.getName(),
+                      /*UseQuotes=*/true,
+                      /*PrintRef=*/false);
+  }
 
   // Reset file index, to allow its children to print the correct filename.
   options().resetFilenameIndex();

llvm/lib/DebugInfo/LogicalView/Readers/LVCodeViewVisitor.cpp

@@ -947,8 +947,11 @@ Error LVSymbolVisitor::visitKnownRecord(CVSymbol &Record,
     // The name of the CU, was extracted from the 'BuildInfo' subsection.
     Reader->setCompileUnitCPUType(Compile2.Machine);
     Scope->setName(CurrentObjectName);
-    if (options().getAttributeProducer())
+    if (options().getAttributeProducer()) {
       Scope->setProducer(Compile2.Version);
+      Scope->setSourceLanguage(LVSourceLanguage{
+          static_cast<llvm::codeview::SourceLanguage>(Compile2.getLanguage())});
+    }
     getReader().isSystemEntry(Scope, CurrentObjectName);
 
     // The line records in CodeView are recorded per Module ID. Update
@@ -992,8 +995,11 @@ Error LVSymbolVisitor::visitKnownRecord(CVSymbol &Record,
     // The name of the CU, was extracted from the 'BuildInfo' subsection.
     Reader->setCompileUnitCPUType(Compile3.Machine);
     Scope->setName(CurrentObjectName);
-    if (options().getAttributeProducer())
+    if (options().getAttributeProducer()) {
       Scope->setProducer(Compile3.Version);
+      Scope->setSourceLanguage(LVSourceLanguage{
+          static_cast<llvm::codeview::SourceLanguage>(Compile3.getLanguage())});
+    }
     getReader().isSystemEntry(Scope, CurrentObjectName);
 
     // The line records in CodeView are recorded per Module ID. Update

llvm/lib/DebugInfo/LogicalView/Readers/LVDWARFReader.cpp

@@ -383,6 +383,11 @@ void LVDWARFReader::processOneAttribute(const DWARFDie &Die,
     if (options().getAttributeProducer())
       CurrentElement->setProducer(dwarf::toStringRef(FormValue));
     break;
+  case dwarf::DW_AT_language:
+    if (options().getAttributeProducer())
+      CurrentElement->setSourceLanguage(LVSourceLanguage{
+          static_cast<llvm::dwarf::SourceLanguage>(GetAsUnsignedConstant())});
+    break;
   case dwarf::DW_AT_upper_bound:
     CurrentElement->setUpperBound(GetBoundValue(FormValue));
     break;

llvm/unittests/DebugInfo/LogicalView/CodeViewReaderTest.cpp

@@ -78,6 +78,11 @@ void checkElementPropertiesClangCodeview(LVReader *Reader) {
   EXPECT_EQ(CompileUnit->getBaseAddress(), 0u);
   EXPECT_TRUE(CompileUnit->getProducer().starts_with("clang"));
   EXPECT_EQ(CompileUnit->getName(), "test.cpp");
+  LVSourceLanguage Language = CompileUnit->getSourceLanguage();
+  EXPECT_TRUE(Language.isValid());
+  ASSERT_EQ(Language.getAs<llvm::codeview::SourceLanguage>(),
+            llvm::codeview::SourceLanguage::Cpp);
+  ASSERT_EQ(Language.getName(), "Cpp");
 
   EXPECT_EQ(Function->lineCount(), 16u);
   EXPECT_EQ(Function->scopeCount(), 1u);

llvm/unittests/DebugInfo/LogicalView/DWARFReaderTest.cpp

@@ -72,6 +72,11 @@ void checkElementProperties(LVReader *Reader) {
   EXPECT_EQ(CompileUnit->getBaseAddress(), 0u);
   EXPECT_TRUE(CompileUnit->getProducer().starts_with("clang"));
   EXPECT_EQ(CompileUnit->getName(), "test.cpp");
+  LVSourceLanguage Language = CompileUnit->getSourceLanguage();
+  EXPECT_TRUE(Language.isValid());
+  EXPECT_EQ(Language.getAs<llvm::dwarf::SourceLanguage>(),
+            llvm::dwarf::DW_LANG_C_plus_plus_14);
+  EXPECT_EQ(Language.getName(), "DW_LANG_C_plus_plus_14");
 
   EXPECT_EQ(CompileUnit->lineCount(), 0u);
   EXPECT_EQ(CompileUnit->scopeCount(), 1u);