[clang-repl] Names declared in if conditions and for-init statements are local to the inner context (#84150)

Make TopLevelStmtDecl a DeclContext so that variables defined in statements
are attached to the TopLevelDeclContext. This fixes redefinition errors
from variables declared in if conditions and for-init statements. These
must be local to the inner context (C++ 3.3.2p4), but they had generated
definitions on global scope instead.

This PR makes the TopLevelStmtDecl looking more like a FunctionDecl and
that's fine because the FunctionDecl is very close in terms of semantics.

Additionally, ActOnForStmt() requires a CompoundScope when processing a
NullStmt body.

---------

Co-authored-by: Vassil Vassilev <v.g.vassilev@gmail.com>

Author: weliveindetail

clang/include/clang/AST/Decl.h

@@ -4419,15 +4419,15 @@ class FileScopeAsmDecl : public Decl {
 ///
 /// \note This is used in libInterpreter, clang -cc1 -fincremental-extensions
 /// and in tools such as clang-repl.
-class TopLevelStmtDecl : public Decl {
+class TopLevelStmtDecl : public Decl, public DeclContext {
   friend class ASTDeclReader;
   friend class ASTDeclWriter;
 
   Stmt *Statement = nullptr;
   bool IsSemiMissing = false;
 
   TopLevelStmtDecl(DeclContext *DC, SourceLocation L, Stmt *S)
-      : Decl(TopLevelStmt, DC, L), Statement(S) {}
+      : Decl(TopLevelStmt, DC, L), DeclContext(TopLevelStmt), Statement(S) {}
 
   virtual void anchor();
 
@@ -4438,15 +4438,19 @@ class TopLevelStmtDecl : public Decl {
   SourceRange getSourceRange() const override LLVM_READONLY;
   Stmt *getStmt() { return Statement; }
   const Stmt *getStmt() const { return Statement; }
-  void setStmt(Stmt *S) {
-    assert(IsSemiMissing && "Operation supported for printing values only!");
-    Statement = S;
-  }
+  void setStmt(Stmt *S);
   bool isSemiMissing() const { return IsSemiMissing; }
   void setSemiMissing(bool Missing = true) { IsSemiMissing = Missing; }
 
   static bool classof(const Decl *D) { return classofKind(D->getKind()); }
   static bool classofKind(Kind K) { return K == TopLevelStmt; }
+
+  static DeclContext *castToDeclContext(const TopLevelStmtDecl *D) {
+    return static_cast<DeclContext *>(const_cast<TopLevelStmtDecl *>(D));
+  }
+  static TopLevelStmtDecl *castFromDeclContext(const DeclContext *DC) {
+    return static_cast<TopLevelStmtDecl *>(const_cast<DeclContext *>(DC));
+  }
 };
 
 /// Represents a block literal declaration, which is like an

clang/include/clang/AST/DeclBase.h

@@ -2120,6 +2120,7 @@ class DeclContext {
     case Decl::Block:
     case Decl::Captured:
     case Decl::ObjCMethod:
+    case Decl::TopLevelStmt:
       return true;
     default:
       return getDeclKind() >= Decl::firstFunction &&

clang/include/clang/Basic/DeclNodes.td

@@ -95,7 +95,7 @@ def LinkageSpec : DeclNode<Decl>, DeclContext;
 def Export : DeclNode<Decl>, DeclContext;
 def ObjCPropertyImpl : DeclNode<Decl>;
 def FileScopeAsm : DeclNode<Decl>;
-def TopLevelStmt : DeclNode<Decl>;
+def TopLevelStmt : DeclNode<Decl>, DeclContext;
 def AccessSpec : DeclNode<Decl>;
 def Friend : DeclNode<Decl>;
 def FriendTemplate : DeclNode<Decl>;

clang/include/clang/Sema/Sema.h

@@ -3263,7 +3263,8 @@ class Sema final {
   Decl *ActOnFileScopeAsmDecl(Expr *expr, SourceLocation AsmLoc,
                               SourceLocation RParenLoc);
 
-  Decl *ActOnTopLevelStmtDecl(Stmt *Statement);
+  TopLevelStmtDecl *ActOnStartTopLevelStmtDecl(Scope *S);
+  void ActOnFinishTopLevelStmtDecl(TopLevelStmtDecl *D, Stmt *Statement);
 
   void ActOnPopScope(SourceLocation Loc, Scope *S);
 

clang/lib/AST/Decl.cpp

@@ -5552,14 +5552,13 @@ FileScopeAsmDecl *FileScopeAsmDecl::CreateDeserialized(ASTContext &C,
 void TopLevelStmtDecl::anchor() {}
 
 TopLevelStmtDecl *TopLevelStmtDecl::Create(ASTContext &C, Stmt *Statement) {
-  assert(Statement);
   assert(C.getLangOpts().IncrementalExtensions &&
          "Must be used only in incremental mode");
 
-  SourceLocation BeginLoc = Statement->getBeginLoc();
+  SourceLocation Loc = Statement ? Statement->getBeginLoc() : SourceLocation();
   DeclContext *DC = C.getTranslationUnitDecl();
 
-  return new (C, DC) TopLevelStmtDecl(DC, BeginLoc, Statement);
+  return new (C, DC) TopLevelStmtDecl(DC, Loc, Statement);
 }
 
 TopLevelStmtDecl *TopLevelStmtDecl::CreateDeserialized(ASTContext &C,
@@ -5572,6 +5571,12 @@ SourceRange TopLevelStmtDecl::getSourceRange() const {
   return SourceRange(getLocation(), Statement->getEndLoc());
 }
 
+void TopLevelStmtDecl::setStmt(Stmt *S) {
+  assert(S);
+  Statement = S;
+  setLocation(Statement->getBeginLoc());
+}
+
 void EmptyDecl::anchor() {}
 
 EmptyDecl *EmptyDecl::Create(ASTContext &C, DeclContext *DC, SourceLocation L) {

clang/lib/AST/DeclBase.cpp

@@ -1352,6 +1352,7 @@ DeclContext *DeclContext::getPrimaryContext() {
   case Decl::ExternCContext:
   case Decl::LinkageSpec:
   case Decl::Export:
+  case Decl::TopLevelStmt:
   case Decl::Block:
   case Decl::Captured:
   case Decl::OMPDeclareReduction:

clang/lib/Parse/ParseDecl.cpp

@@ -5678,24 +5678,32 @@ Parser::DeclGroupPtrTy Parser::ParseTopLevelStmtDecl() {
   // Parse a top-level-stmt.
   Parser::StmtVector Stmts;
   ParsedStmtContext SubStmtCtx = ParsedStmtContext();
-  Actions.PushFunctionScope();
+  ParseScope FnScope(this, Scope::FnScope | Scope::DeclScope |
+                               Scope::CompoundStmtScope);
+  TopLevelStmtDecl *TLSD = Actions.ActOnStartTopLevelStmtDecl(getCurScope());
   StmtResult R = ParseStatementOrDeclaration(Stmts, SubStmtCtx);
-  Actions.PopFunctionScopeInfo();
   if (!R.isUsable())
     return nullptr;
 
-  SmallVector<Decl *, 2> DeclsInGroup;
-  DeclsInGroup.push_back(Actions.ActOnTopLevelStmtDecl(R.get()));
+  Actions.ActOnFinishTopLevelStmtDecl(TLSD, R.get());
 
   if (Tok.is(tok::annot_repl_input_end) &&
       Tok.getAnnotationValue() != nullptr) {
     ConsumeAnnotationToken();
-    cast<TopLevelStmtDecl>(DeclsInGroup.back())->setSemiMissing();
+    TLSD->setSemiMissing();
   }
 
-  // Currently happens for things like  -fms-extensions and use `__if_exists`.
-  for (Stmt *S : Stmts)
-    DeclsInGroup.push_back(Actions.ActOnTopLevelStmtDecl(S));
+  SmallVector<Decl *, 2> DeclsInGroup;
+  DeclsInGroup.push_back(TLSD);
+
+  // Currently happens for things like -fms-extensions and use `__if_exists`.
+  for (Stmt *S : Stmts) {
+    // Here we should be safe as `__if_exists` and friends are not introducing
+    // new variables which need to live outside file scope.
+    TopLevelStmtDecl *D = Actions.ActOnStartTopLevelStmtDecl(getCurScope());
+    Actions.ActOnFinishTopLevelStmtDecl(D, S);
+    DeclsInGroup.push_back(D);
+  }
 
   return Actions.BuildDeclaratorGroup(DeclsInGroup);
 }

clang/lib/Sema/SemaDecl.cpp

@@ -20519,12 +20519,22 @@ Decl *Sema::ActOnFileScopeAsmDecl(Expr *expr,
   return New;
 }
 
-Decl *Sema::ActOnTopLevelStmtDecl(Stmt *Statement) {
-  auto *New = TopLevelStmtDecl::Create(Context, Statement);
-  Context.getTranslationUnitDecl()->addDecl(New);
+TopLevelStmtDecl *Sema::ActOnStartTopLevelStmtDecl(Scope *S) {
+  auto *New = TopLevelStmtDecl::Create(Context, /*Statement=*/nullptr);
+  CurContext->addDecl(New);
+  PushDeclContext(S, New);
+  PushFunctionScope();
+  PushCompoundScope(false);
   return New;
 }
 
+void Sema::ActOnFinishTopLevelStmtDecl(TopLevelStmtDecl *D, Stmt *Statement) {
+  D->setStmt(Statement);
+  PopCompoundScope();
+  PopFunctionScopeInfo();
+  PopDeclContext();
+}
+
 void Sema::ActOnPragmaRedefineExtname(IdentifierInfo* Name,
                                       IdentifierInfo* AliasName,
                                       SourceLocation PragmaLoc,

clang/test/Interpreter/execute-stmts.cpp

@@ -9,7 +9,6 @@
 //CODEGEN-CHECK-COUNT-2: define internal void @__stmts__
 //CODEGEN-CHECK-NOT: define internal void @__stmts__
 
-
 extern "C" int printf(const char*,...);
 
 template <typename T> T call() { printf("called\n"); return T(); }
@@ -41,3 +40,26 @@ for (; i > 4; --i) { printf("i = %d\n", i); };
 
 int j = i; printf("j = %d\n", j);
 // CHECK-NEXT: j = 4
+
+{i = 0; printf("i = %d (global scope)\n", i);}
+// CHECK-NEXT: i = 0
+
+while (int i = 1) { printf("i = %d (while condition)\n", i--); break; }
+// CHECK-NEXT: i = 1
+
+if (int i = 2) printf("i = %d (if condition)\n", i);
+// CHECK-NEXT: i = 2
+
+switch (int i = 3) { default: printf("i = %d (switch condition)\n", i); }
+// CHECK-NEXT: i = 3
+
+for (int i = 4; i > 3; --i) printf("i = %d (for-init)\n", i);
+// CHECK-NEXT: i = 4
+
+for (const auto &i : "5") printf("i = %c (range-based for-init)\n", i);
+// CHECK-NEXT: i = 5
+
+int *aa=nullptr;
+if (auto *b=aa) *b += 1;
+while (auto *b=aa) ;
+for (auto *b=aa; b; *b+=1) ;