[clang][DebugInfo] Allow function-local statics and types to be scoped within a lexical block

This is almost a reincarnation of https://reviews.llvm.org/D15977 originally
implemented by Amjad Aboud. It was discussed on llvm-dev [0], committed
with its backend counterpart [1], but finally reverted [2].

This patch makes clang to emit debug info for function-local static variables,
records (classes, structs and unions) and typdefs correctly scoped if
those function-local entites defined within a lexical (bracketed) block.

Before this patch, clang emits all those entities directly scoped in
DISubprogram no matter where they were really defined, causing
debug info loss (reported several times in [3], [4], [5]).

[0] https://lists.llvm.org/pipermail/llvm-dev/2015-November/092551.html
[1] https://reviews.llvm.org/rG30e7a8f694a19553f64b3a3a5de81ce317b9ec2f
[2] https://reviews.llvm.org/rGdc4531e552af6c880a69d226d3666756198fbdc8
[3] https://bugs.llvm.org/show_bug.cgi?id=19238
[4] https://bugs.llvm.org/show_bug.cgi?id=23164
[5] https://bugs.llvm.org/show_bug.cgi?id=44695

Reviewed By: dblaikie

Differential Revision: https://reviews.llvm.org/D113743

Author: chbessonova

clang/lib/CodeGen/CGDebugInfo.cpp

@@ -227,6 +227,20 @@ llvm::DIScope *CGDebugInfo::getContextDescriptor(const Decl *Context,
   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) {
+  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();
 
@@ -1346,13 +1360,13 @@ llvm::DIType *CGDebugInfo::CreateType(const TypedefType *Ty,
   // 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) {
@@ -3251,7 +3265,7 @@ llvm::DIType *CGDebugInfo::CreateEnumType(const EnumType *Ty) {
     // 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));
@@ -3294,7 +3308,7 @@ llvm::DIType *CGDebugInfo::CreateTypeDefinition(const EnumType *Ty) {
 
   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,
@@ -3597,7 +3611,7 @@ llvm::DICompositeType *CGDebugInfo::CreateLimitedType(const RecordType *Ty) {
     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.
@@ -3790,6 +3804,14 @@ void CGDebugInfo::collectVarDeclProps(const VarDecl *VD, llvm::DIFile *&Unit,
     TemplateParameters = nullptr;
   }
 
+  // Get context for static locals (that are technically globals) the same way
+  // we do for "local" locals -- by using current lexical block.
+  if (VD->isStaticLocal()) {
+    assert(!LexicalBlockStack.empty() && "Region stack mismatch, stack empty!");
+    VDContext = LexicalBlockStack.back();
+    return;
+  }
+
   // Since we emit declarations (DW_AT_members) for static members, place the
   // definition of those static members in the namespace they were declared in
   // in the source code (the lexical decl context).

clang/lib/CodeGen/CGDebugInfo.h

@@ -139,6 +139,11 @@ class CGDebugInfo {
 
   /// 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
@@ -543,6 +548,12 @@ class CGDebugInfo {
   /// 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);
 

clang/lib/CodeGen/CGDecl.cpp

@@ -103,17 +103,21 @@ void CodeGenFunction::EmitDecl(const Decl &D) {
     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:
@@ -132,11 +136,11 @@ void CodeGenFunction::EmitDecl(const Decl &D) {
 
   case Decl::NamespaceAlias:
     if (CGDebugInfo *DI = getDebugInfo())
-        DI->EmitNamespaceAlias(cast<NamespaceAliasDecl>(D));
+      DI->EmitNamespaceAlias(cast<NamespaceAliasDecl>(D));
     return;
   case Decl::Using:          // using X; [C++]
     if (CGDebugInfo *DI = getDebugInfo())
-        DI->EmitUsingDecl(cast<UsingDecl>(D));
+      DI->EmitUsingDecl(cast<UsingDecl>(D));
     return;
   case Decl::UsingEnum: // using enum X; [C++]
     if (CGDebugInfo *DI = getDebugInfo())
@@ -172,8 +176,10 @@ void CodeGenFunction::EmitDecl(const Decl &D) {
   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;

clang/test/CodeGenCXX/debug-info-lexcial-block.cpp

@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 -triple x86_64-none-linux-gnu -emit-llvm -debug-info-kind=limited %s -o - | FileCheck %s
+
+void foo() {
+  static int bar = 1;
+  {
+    struct X {};
+    typedef char Y;
+    static int bar = 0;
+    // The following basic block is intended, in order to check the case where
+    // types "X", "Y" are defined in a different scope than where they are used.
+    // They should have the scope they are defined at as their parent scope.
+    {
+      X a;
+      Y b;
+    }
+  }
+}
+
+// CHECK: !{{[0-9]+}} = distinct !DIGlobalVariable(name: "bar", scope: [[FSCOPE:![0-9]+]]
+// CHECK: [[FSCOPE]] = distinct !DISubprogram(name: "foo"
+// CHECK: !{{[0-9]+}} = distinct !DIGlobalVariable(name: "bar", scope: [[LBSCOPE:![0-9]+]]
+// CHECK: [[LBSCOPE]] = distinct !DILexicalBlock(scope: [[FSCOPE]]
+// CHECK: !{{[0-9]+}} = !DILocalVariable(name: "a", scope: [[LBSCOPE2:![0-9]+]], {{.*}} type: [[STRUCT:![0-9]+]]
+// CHECK: [[LBSCOPE2]] = distinct !DILexicalBlock(scope: [[LBSCOPE]]
+// CHECK: [[STRUCT]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "X", scope: [[LBSCOPE]]
+// CHECK: !{{[0-9]+}} = !DILocalVariable(name: "b", scope: [[LBSCOPE2]], {{.*}} type: [[TYPEDEF:![0-9]+]]
+// CHECK: [[TYPEDEF]] = !DIDerivedType(tag: DW_TAG_typedef, name: "Y", scope: [[LBSCOPE]]