[clang][DebugInfo] Allow function-local type-like entities to be scoped within a lexical block (5/5)

[krisb]

Summary

This is a part from D113743 split to make it easier to test and review.

It also enables lexical blocks as a scope for types and type-like entities
only if -debugger-tunning=gdb. lldb can't (yet) handle lexical block scoped
types (see D115277 for details), other debuggers were not verified (yet).

[aprantl]

Sgtm.

[dblaikie]

clang/lib/CodeGen/CGDebugInfo.cpp

231–234

Rather than doing an extra lookup in the assert, could probably check the return value of insert instead and assert based on that?

[krisb]

Applied review comments.

clang/lib/CodeGen/CGDebugInfo.h

#include "clang/Basic/OpenCLExtensionTypes.def"
 
   /// Cache of replaceable forward declarations (functions and
   /// variables) to RAUW at the end of compilation.
   std::vector<std::pair<const DeclaratorDecl *, llvm::TrackingMDRef>>
       FwdDeclReplaceMap;
 
   /// Keep track of our current nested lexical block.
   std::vector<llvm::TypedTrackingMDRef<llvm::DIScope>> LexicalBlockStack;
+
+  /// Map of AST declaration to its lexical block scope.
+  llvm::DenseMap<const Decl *, llvm::TypedTrackingMDRef<llvm::DIScope>>
+      LexicalBlockMap;
+
   llvm::DenseMap<const Decl *, llvm::TrackingMDRef> RegionMap;
   /// Keep track of LexicalBlockStack counter at the beginning of a
   /// function. This is used to pop unbalanced regions at the end of a
   /// function.
   std::vector<unsigned> FnBeginRegionCount;
 
   /// This is a storage for names that are constructed on demand. For
   /// example, C++ destructors, C++ operators etc..
public:
   llvm::DIImportedEntity *EmitNamespaceAlias(const NamespaceAliasDecl &NA);
 
   /// Emit record type's standalone debug info.
   llvm::DIType *getOrCreateRecordType(QualType Ty, SourceLocation L);
 
   /// Emit an Objective-C interface type standalone debug info.
   llvm::DIType *getOrCreateInterfaceType(QualType Ty, SourceLocation Loc);
 
+  /// Map AST declaration to its lexical block scope if available.
+  void recordDeclarationLexicalScope(const Decl &D);
+
+  /// Get lexical scope of AST declaration.
+  llvm::DIScope *getDeclarationLexicalScope(const Decl *D);
+
   /// Emit standalone debug info for a type.
   llvm::DIType *getOrCreateStandaloneType(QualType Ty, SourceLocation Loc);
 
   /// Add heapallocsite metadata for MSAllocator calls.
   void addHeapAllocSiteMetadata(llvm::CallBase *CallSite, QualType AllocatedTy,
                                 SourceLocation Loc);
 
   void completeType(const EnumDecl *ED);

clang/lib/CodeGen/CGDebugInfo.cpp

llvm::DIScope *CGDebugInfo::getContextDescriptor(const Decl *Context,
 
   if (const auto *RDecl = dyn_cast<RecordDecl>(Context))
     if (!RDecl->isDependentType())
       return getOrCreateType(CGM.getContext().getTypeDeclType(RDecl),
                              TheCU->getFile());
   return Default;
 }
 
+void CGDebugInfo::recordDeclarationLexicalScope(const Decl &D) {
+  assert(LexicalBlockMap.find(&D) == LexicalBlockMap.end() &&
+         "D is already mapped to a lexical block scope");
+  if (!LexicalBlockStack.empty())
+    LexicalBlockMap.insert({&D, LexicalBlockStack.back()});
+}
+
+llvm::DIScope *CGDebugInfo::getDeclarationLexicalScope(const Decl *D) {
+  if (CGM.getCodeGenOpts().getDebuggerTuning() == llvm::DebuggerKind::GDB) {
+    auto I = LexicalBlockMap.find(D);
+    if (I != LexicalBlockMap.end())
+      return I->second;
+  }
+  return getDeclContextDescriptor(cast<Decl>(D));
+}
+
 PrintingPolicy CGDebugInfo::getPrintingPolicy() const {
   PrintingPolicy PP = CGM.getContext().getPrintingPolicy();
 
   // If we're emitting codeview, it's important to try to match MSVC's naming so
   // that visualizers written for MSVC will trigger for our class names. In
   // particular, we can't have spaces between arguments of standard templates
   // like basic_string and vector, but we must have spaces between consecutive
   // angle brackets that close nested template argument lists.
llvm::DIType *CGDebugInfo::CreateType(const TypedefType *Ty,
 
   if (Ty->getDecl()->hasAttr<NoDebugAttr>())
     return Underlying;
 
   // We don't set size information, but do specify where the typedef was
   // declared.
   SourceLocation Loc = Ty->getDecl()->getLocation();
 
+  llvm::DIScope *TDContext = getDeclarationLexicalScope(Ty->getDecl());
   uint32_t Align = getDeclAlignIfRequired(Ty->getDecl(), CGM.getContext());
   // Typedefs are derived from some other type.
   llvm::DINodeArray Annotations = CollectBTFDeclTagAnnotations(Ty->getDecl());
   return DBuilder.createTypedef(Underlying, Ty->getDecl()->getName(),
                                 getOrCreateFile(Loc), getLineNumber(Loc),
-                                getDeclContextDescriptor(Ty->getDecl()), Align,
-                                Annotations);
+                                TDContext, Align, Annotations);
 }
 
 static unsigned getDwarfCC(CallingConv CC) {
   switch (CC) {
   case CC_C:
     // Avoid emitting DW_AT_calling_convention if the C convention was used.
     return 0;
 
llvm::DIType *CGDebugInfo::CreateEnumType(const EnumType *Ty) {
   // marked node and just return it.
   if (isImportedFromModule || !ED->getDefinition()) {
     // Note that it is possible for enums to be created as part of
     // their own declcontext. In this case a FwdDecl will be created
     // twice. This doesn't cause a problem because both FwdDecls are
     // entered into the ReplaceMap: finalize() will replace the first
     // FwdDecl with the second and then replace the second with
     // complete type.
-    llvm::DIScope *EDContext = getDeclContextDescriptor(ED);
+    llvm::DIScope *EDContext = getDeclarationLexicalScope(ED);
     llvm::DIFile *DefUnit = getOrCreateFile(ED->getLocation());
     llvm::TempDIScope TmpContext(DBuilder.createReplaceableCompositeType(
         llvm::dwarf::DW_TAG_enumeration_type, "", TheCU, DefUnit, 0));
 
     unsigned Line = getLineNumber(ED->getLocation());
     StringRef EDName = ED->getName();
     llvm::DIType *RetTy = DBuilder.createReplaceableCompositeType(
         llvm::dwarf::DW_TAG_enumeration_type, EDName, EDContext, DefUnit, Line,
Enumerators.push_back(
         DBuilder.createEnumerator(Enum->getName(), Enum->getInitVal()));
   }
 
   // Return a CompositeType for the enum itself.
   llvm::DINodeArray EltArray = DBuilder.getOrCreateArray(Enumerators);
 
   llvm::DIFile *DefUnit = getOrCreateFile(ED->getLocation());
   unsigned Line = getLineNumber(ED->getLocation());
-  llvm::DIScope *EnumContext = getDeclContextDescriptor(ED);
+  llvm::DIScope *EnumContext = getDeclarationLexicalScope(ED);
   llvm::DIType *ClassTy = getOrCreateType(ED->getIntegerType(), DefUnit);
   return DBuilder.createEnumerationType(EnumContext, ED->getName(), DefUnit,
                                         Line, Size, Align, EltArray, ClassTy,
                                         Identifier, ED->isScoped());
 }
 
 llvm::DIMacro *CGDebugInfo::CreateMacro(llvm::DIMacroFile *Parent,
                                         unsigned MType, SourceLocation LineLoc,
llvm::DICompositeType *CGDebugInfo::CreateLimitedType(const RecordType *Ty) {
   const SourceLocation Loc = RD->getLocation();
   llvm::DIFile *DefUnit = nullptr;
   unsigned Line = 0;
   if (Loc.isValid()) {
     DefUnit = getOrCreateFile(Loc);
     Line = getLineNumber(Loc);
   }
 
-  llvm::DIScope *RDContext = getDeclContextDescriptor(RD);
+  llvm::DIScope *RDContext = getDeclarationLexicalScope(RD);
 
   // If we ended up creating the type during the context chain construction,
   // just return that.
   auto *T = cast_or_null<llvm::DICompositeType>(
       getTypeOrNull(CGM.getContext().getRecordType(RD)));
   if (T && (!T->isForwardDecl() || !RD->getDefinition()))
     return T;
 

clang/lib/CodeGen/CGDecl.cpp

void CodeGenFunction::EmitDecl(const Decl &D) {
   case Decl::UsingShadow:
   case Decl::ConstructorUsingShadow:
   case Decl::ObjCTypeParam:
   case Decl::Binding:
   case Decl::UnresolvedUsingIfExists:
     llvm_unreachable("Declaration should not be in declstmts!");
   case Decl::Record:    // struct/union/class X;
   case Decl::CXXRecord: // struct/union/class X; [C++]
-    if (CGDebugInfo *DI = getDebugInfo())
+    if (CGDebugInfo *DI = getDebugInfo()) {
+      DI->recordDeclarationLexicalScope(D);
       if (cast<RecordDecl>(D).getDefinition())
         DI->EmitAndRetainType(getContext().getRecordType(cast<RecordDecl>(&D)));
+    }
     return;
   case Decl::Enum:      // enum X;
-    if (CGDebugInfo *DI = getDebugInfo())
+    if (CGDebugInfo *DI = getDebugInfo()) {
+      DI->recordDeclarationLexicalScope(D);
       if (cast<EnumDecl>(D).getDefinition())
         DI->EmitAndRetainType(getContext().getEnumType(cast<EnumDecl>(&D)));
+    }
     return;
-  case Decl::Function:     // void X();
   case Decl::EnumConstant: // enum ? { X = ? }
+  case Decl::Function:     // void X();
   case Decl::StaticAssert: // static_assert(X, ""); [C++0x]
   case Decl::Label:        // __label__ x;
   case Decl::Import:
   case Decl::MSGuid:    // __declspec(uuid("..."))
   case Decl::UnnamedGlobalConstant:
   case Decl::TemplateParamObject:
   case Decl::OMPThreadPrivate:
   case Decl::OMPAllocate:
   case Decl::OMPCapturedExpr:
   case Decl::OMPRequires:
   case Decl::Empty:
   case Decl::Concept:
   case Decl::LifetimeExtendedTemporary:
   case Decl::RequiresExprBody:
     // None of these decls require codegen support.
     return;
 
   case Decl::NamespaceAlias:
     if (CGDebugInfo *DI = getDebugInfo())
-        DI->EmitNamespaceAlias(cast<NamespaceAliasDecl>(D));
     return;
   case Decl::Using:          // using X; [C++]
     if (CGDebugInfo *DI = getDebugInfo())
-        DI->EmitUsingDecl(cast<UsingDecl>(D));
     return;
   case Decl::UsingEnum: // using enum X; [C++]
     if (CGDebugInfo *DI = getDebugInfo())
       DI->EmitUsingEnumDecl(cast<UsingEnumDecl>(D));
     return;
   case Decl::UsingPack:
     for (auto *Using : cast<UsingPackDecl>(D).expansions())
       EmitDecl(*Using);
case Decl::OMPDeclareReduction:
     return CGM.EmitOMPDeclareReduction(cast<OMPDeclareReductionDecl>(&D), this);
 
   case Decl::OMPDeclareMapper:
     return CGM.EmitOMPDeclareMapper(cast<OMPDeclareMapperDecl>(&D), this);
 
   case Decl::Typedef:      // typedef int X;
   case Decl::TypeAlias: {  // using X = int; [C++0x]
     QualType Ty = cast<TypedefNameDecl>(D).getUnderlyingType();
-    if (CGDebugInfo *DI = getDebugInfo())
+    if (CGDebugInfo *DI = getDebugInfo()) {
+      DI->recordDeclarationLexicalScope(D);
       DI->EmitAndRetainType(Ty);
+    }
     if (Ty->isVariablyModifiedType())
       EmitVariablyModifiedType(Ty);
     return;
   }
   }
 }
 
 /// EmitVarDecl - This method handles emission of any variable declaration

clang/test/CodeGenCXX/debug-info-local-types.cpp

+// RUN: %clang_cc1 -triple x86_64-none-linux-gnu -emit-llvm -debug-info-kind=limited -debugger-tuning=gdb %s -o - | FileCheck %s --check-prefixes=CHECK,LIMITED
+// RUN: %clang_cc1 -triple x86_64-none-linux-gnu -emit-llvm -debug-info-kind=unused-types -debugger-tuning=gdb %s -o - | FileCheck %s --check-prefixes=UNUSED_TYPES
+
+void test() {
+  {
+    struct S { int a; };
+    class C { int b; };
+    S s;
+    {
+      C c;
+    }
+  }
+
+  {
+    typedef char Char;
+    using Int = int;
+    Char c;
+    {
+      Int i;
+    }
+  }
+
+  {
+    enum E { a, b, c };
+    enum class T { aa, bb, cc };
+    E e = E::a;
+    {
+      T t = T::aa;
+    }
+  }
+
+  {
+    union U { int i; char c; };
+    U u = { 256 };
+  }
+}
+
+// LIMITED: distinct !DICompileUnit
+// LIMITED-NOT: retainedTypes:
+
+// CHECK: !DILocalVariable(name: "s", scope: [[LBSCOPE_1:![0-9]+]]
+// CHECK-SAME:                        type: [[STRUCT:![0-9]+]]
+// CHECK: [[LBSCOPE_1]] = distinct !DILexicalBlock({{.*}}, localDecls: [[LB1_DECLS:![0-9]+]]
+// CHECK: [[LB1_DECLS]] = !{[[STRUCT]], [[CLASS:![0-9]+]]}
+// CHECK: [[STRUCT]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "S", scope: [[LBSCOPE_1]]
+// CHECK: [[CLASS]] = distinct !DICompositeType(tag: DW_TAG_class_type, name: "C", scope: [[LBSCOPE_1]]
+// CHECK: !DILocalVariable(name: "c", scope: [[LBSCOPE_11:![0-9]+]]
+// CHECK-SAME:                        type: [[CLASS]]
+// CHECK: [[LBSCOPE_11]] = distinct !DILexicalBlock(scope: [[LBSCOPE_1]]
+//
+// CHECK: !DILocalVariable(name: "c", scope: [[LBSCOPE_2:![0-9]+]]
+// CHECK-SAME:                        type: [[TYPEDEF:![0-9]+]]
+// CHECK: [[LBSCOPE_2]] = distinct !DILexicalBlock({{.*}}, localDecls: [[LB2_DECLS:![0-9]+]]
+// CHECK: [[LB2_DECLS]] = !{[[TYPEDEF]], [[USING:![0-9]+]]}
+// CHECK: [[TYPEDEF]] = !DIDerivedType(tag: DW_TAG_typedef, name: "Char", scope: [[LBSCOPE_2]]
+// CHECK: [[USING]] = !DIDerivedType(tag: DW_TAG_typedef, name: "Int", scope: [[LBSCOPE_2]]
+// CHECK: !DILocalVariable(name: "i", scope: [[LBSCOPE_21:![0-9]+]]
+// CHECK-SAME:                        type: [[USING]]
+// CHECK: [[LBSCOPE_21]] = distinct !DILexicalBlock(scope: [[LBSCOPE_2]]
+//
+// CHECK: !DILocalVariable(name: "e", scope: [[LBSCOPE_3:![0-9]+]]
+// CHECK-SAME:                        type: [[ENUM:![0-9]+]]
+// CHECK: [[LBSCOPE_3]] = distinct !DILexicalBlock({{.*}}, localDecls: [[LB3_DECLS:![0-9]+]]
+// CHECK: [[LB3_DECLS]] = !{[[ENUM]], [[ENUM_CLASS:![0-9]+]]}
+// CHECK: [[ENUM]] = !DICompositeType(tag: DW_TAG_enumeration_type, name: "E", scope: [[LBSCOPE_3]]
+// CHECK: [[ENUM_CLASS]] = !DICompositeType(tag: DW_TAG_enumeration_type, name: "T", scope: [[LBSCOPE_3]]
+// CHECK: !DILocalVariable(name: "t", scope: [[LBSCOPE_31:![0-9]+]]
+// CHECK-SAME:                        type: [[ENUM_CLASS]]
+// CHECK: [[LBSCOPE_31]] = distinct !DILexicalBlock(scope: [[LBSCOPE_3]]
+//
+// CHECK: !DILocalVariable(name: "u", scope: [[LBSCOPE_4:![0-9]+]]
+// CHECK-SAME:                        type: [[UNION:![0-9]+]]
+// CHECK: [[LBSCOPE_4]] = distinct !DILexicalBlock({{.*}}, localDecls: [[LB4_DECLS:![0-9]+]]
+// CHECK: [[LB4_DECLS]] = !{[[UNION]]}
+// CHECK: [[UNION]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "U", scope: [[LBSCOPE_4]]
+
+void test_unused() {
+  {
+    struct X {};
+    typedef int Y; // typedef doesn't go to retainedTypes.
+    enum Z { z };
+  }
+}
+
+// UNUSED_TYPES: distinct !DICompileUnit
+// UNUSED_TYPES-SAME: retainedTypes: [[RETAINED_TYPES:![0-9]+]]
+//
+// struct, class, char, int, enum, enum class, union, unused struct, unused enum, <lambda()>::F
+// UNUSED_TYPES: [[RETAINED_TYPES]] = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, [[UNUSED_STRUCT:![0-9]+]], [[UNUSED_ENUM:![0-9]+]], !{{.*}}}
+// UNUSED_TYPES: [[UNUSED_STRUCT]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "X", scope: [[UNUSED_LB:![0-9]+]]
+// UNUSED_TYPES: [[UNUSED_LB]] = distinct !DILexicalBlock({{.*}}, localDecls: [[UNUSED_LB_DECLS:![0-9]+]]
+// UNUSED_TYPES: [[UNUSED_LB_DECLS]] = !{[[UNUSED_STRUCT]], [[UNUSED_ENUM]]}
+// UNUSED_TYPES: [[UNUSED_ENUM]] = !DICompositeType(tag: DW_TAG_enumeration_type, name: "Z", scope: [[UNUSED_LB]]
+
+void test_lambda() {
+  auto t = []() { struct F {}; return F(); };
+  auto v = t();
+}
+
+// TODO: <lambda()>::F doesn't have its scope specified.
+// CHECK: distinct !DICompositeType(tag: DW_TAG_structure_type, name: "F", file