[APINotes] Upstream dependencies of Sema logic to apply API Notes to …

…decls

This upstreams more of the Clang API Notes functionality that is
currently implemented in the Apple fork:
https://github.com/apple/llvm-project/tree/next/clang/lib/APINotes

This is the largest chunk of the API Notes functionality in the
upstreaming process. I will soon submit a follow-up patch to actually
enable usage of this functionality by having a Clang driver flag that
enables API Notes, along with tests.

clang/include/clang/Basic/Attr.td

@@ -306,6 +306,9 @@ class VariadicEnumArgument<string name, string type, list<string> values,
   bit IsExternalType = isExternalType;
 }
 
+// Represents an attribute wrapped by another attribute.
+class WrappedAttr<string name, bit opt = 0> : Argument<name, opt>;
+
 // This handles one spelling of an attribute.
 class Spelling<string name, string variety, int version = 1> {
   string Name = name;
@@ -2291,7 +2294,7 @@ def ObjCBridgeRelated : InheritableAttr {
 def NSErrorDomain : InheritableAttr {
   let Spellings = [GNU<"ns_error_domain">];
   let Subjects = SubjectList<[Enum], ErrorDiag>;
-  let Args = [DeclArgument<Var, "ErrorDomain">];
+  let Args = [IdentifierArgument<"ErrorDomain">];
   let Documentation = [NSErrorDomainDocs];
 }
 
@@ -2648,6 +2651,22 @@ def SwiftError : InheritableAttr {
   let Documentation = [SwiftErrorDocs];
 }
 
+def SwiftImportAsNonGeneric : InheritableAttr {
+  // This attribute has no spellings as it is only ever created implicitly
+  // from API notes.
+  let Spellings = [];
+  let SemaHandler = 0;
+  let Documentation = [InternalOnly];
+}
+
+def SwiftImportPropertyAsAccessors : InheritableAttr {
+  // This attribute has no spellings as it is only ever created implicitly
+  // from API notes.
+  let Spellings = [];
+  let SemaHandler = 0;
+  let Documentation = [InternalOnly];
+}
+
 def SwiftName : InheritableAttr {
   let Spellings = [GNU<"swift_name">];
   let Args = [StringArgument<"Name">];
@@ -2669,6 +2688,31 @@ def SwiftPrivate : InheritableAttr {
   let SimpleHandler = 1;
 }
 
+def SwiftVersionedAddition : Attr {
+  // This attribute has no spellings as it is only ever created implicitly
+  // from API notes.
+  let Spellings = [];
+  let Args = [VersionArgument<"Version">, WrappedAttr<"AdditionalAttr">,
+              BoolArgument<"IsReplacedByActive">];
+  let SemaHandler = 0;
+  let Documentation = [InternalOnly];
+}
+
+def SwiftVersionedRemoval : Attr {
+  // This attribute has no spellings as it is only ever created implicitly
+  // from API notes.
+  let Spellings = [];
+  let Args = [VersionArgument<"Version">, UnsignedArgument<"RawKind">,
+              BoolArgument<"IsReplacedByActive">];
+  let SemaHandler = 0;
+  let Documentation = [InternalOnly];
+  let AdditionalMembers = [{
+    attr::Kind getAttrKindToRemove() const {
+      return static_cast<attr::Kind>(getRawKind());
+    }
+  }];
+}
+
 def NoDeref : TypeAttr {
   let Spellings = [Clang<"noderef">];
   let Documentation = [NoDerefDocs];

clang/include/clang/Basic/DiagnosticParseKinds.td

@@ -1617,6 +1617,9 @@ def err_pragma_invalid_keyword : Error<
 def err_pragma_pipeline_invalid_keyword : Error<
     "invalid argument; expected 'disable'">;
 
+// API notes.
+def err_type_unparsed : Error<"unparsed tokens following type">;
+
 // Pragma unroll support.
 def warn_pragma_unroll_cuda_value_in_parens : Warning<
   "argument to '#pragma unroll' should not be in parentheses in CUDA C/C++">,

clang/include/clang/Lex/Lexer.h

@@ -198,11 +198,11 @@ class Lexer : public PreprocessorLexer {
   /// from.  Currently this is only used by _Pragma handling.
   SourceLocation getFileLoc() const { return FileLoc; }
 
-private:
   /// Lex - Return the next token in the file.  If this is the end of file, it
   /// return the tok::eof token.  This implicitly involves the preprocessor.
   bool Lex(Token &Result);
 
+private:
   /// Called when the preprocessor is in 'dependency scanning lexing mode'.
   bool LexDependencyDirectiveToken(Token &Result);
 

clang/include/clang/Parse/Parser.h

@@ -3656,6 +3656,18 @@ class Parser : public CodeCompletionHandler {
   ParseConceptDefinition(const ParsedTemplateInfo &TemplateInfo,
                          SourceLocation &DeclEnd);
 
+  /// Parse the given string as a type.
+  ///
+  /// This is a dangerous utility function currently employed only by API notes.
+  /// It is not a general entry-point for safely parsing types from strings.
+  ///
+  /// \param TypeStr The string to be parsed as a type.
+  /// \param Context The name of the context in which this string is being
+  /// parsed, which will be used in diagnostics.
+  /// \param IncludeLoc The location at which this parse was triggered.
+  TypeResult ParseTypeFromString(StringRef TypeStr, StringRef Context,
+                                 SourceLocation IncludeLoc);
+
   //===--------------------------------------------------------------------===//
   // Modules
   DeclGroupPtrTy ParseModuleDecl(Sema::ModuleImportState &ImportState);

clang/include/clang/Sema/Sema.h

@@ -955,6 +955,10 @@ class Sema final {
     OpaqueParser = P;
   }
 
+  /// Callback to the parser to parse a type expressed as a string.
+  std::function<TypeResult(StringRef, StringRef, SourceLocation)>
+      ParseTypeFromStringCallback;
+
   class DelayedDiagnostics;
 
   class DelayedDiagnosticsState {
@@ -3017,6 +3021,9 @@ class Sema final {
   ParmVarDecl *BuildParmVarDeclForTypedef(DeclContext *DC,
                                           SourceLocation Loc,
                                           QualType T);
+  QualType AdjustParameterTypeForObjCAutoRefCount(QualType T,
+                                                  SourceLocation NameLoc,
+                                                  TypeSourceInfo *TSInfo);
   ParmVarDecl *CheckParameter(DeclContext *DC, SourceLocation StartLoc,
                               SourceLocation NameLoc, IdentifierInfo *Name,
                               QualType T, TypeSourceInfo *TSInfo,
@@ -4816,6 +4823,29 @@ class Sema final {
   /// Valid types should not have multiple attributes with different CCs.
   const AttributedType *getCallingConvAttributedType(QualType T) const;
 
+  /// Check whether a nullability type specifier can be added to the given
+  /// type through some means not written in source (e.g. API notes).
+  ///
+  /// \param Type The type to which the nullability specifier will be
+  /// added. On success, this type will be updated appropriately.
+  ///
+  /// \param Nullability The nullability specifier to add.
+  ///
+  /// \param DiagLoc The location to use for diagnostics.
+  ///
+  /// \param AllowArrayTypes Whether to accept nullability specifiers on an
+  /// array type (e.g., because it will decay to a pointer).
+  ///
+  /// \param OverrideExisting Whether to override an existing, locally-specified
+  /// nullability specifier rather than complaining about the conflict.
+  ///
+  /// \returns true if nullability cannot be applied, false otherwise.
+  bool CheckImplicitNullabilityTypeSpecifier(QualType &Type,
+                                             NullabilityKind Nullability,
+                                             SourceLocation DiagLoc,
+                                             bool AllowArrayTypes,
+                                             bool OverrideExisting);
+
   /// Process the attributes before creating an attributed statement. Returns
   /// the semantic attributes that have been processed.
   void ProcessStmtAttributes(Stmt *Stmt, const ParsedAttributes &InAttrs,

clang/lib/Parse/ParseDecl.cpp

@@ -8051,6 +8051,71 @@ bool Parser::TryAltiVecTokenOutOfLine(DeclSpec &DS, SourceLocation Loc,
   return false;
 }
 
+TypeResult Parser::ParseTypeFromString(StringRef TypeStr, StringRef Context,
+                                       SourceLocation IncludeLoc) {
+  // Consume (unexpanded) tokens up to the end-of-directive.
+  SmallVector<Token, 4> Tokens;
+  {
+    // Create a new buffer from which we will parse the type.
+    auto &SourceMgr = PP.getSourceManager();
+    FileID FID = SourceMgr.createFileID(
+        llvm::MemoryBuffer::getMemBufferCopy(TypeStr, Context), SrcMgr::C_User,
+        0, 0, IncludeLoc);
+
+    // Form a new lexer that references the buffer.
+    Lexer L(FID, SourceMgr.getBufferOrFake(FID), PP);
+    L.setParsingPreprocessorDirective(true);
+
+    // Lex the tokens from that buffer.
+    Token Tok;
+    do {
+      L.Lex(Tok);
+      Tokens.push_back(Tok);
+    } while (Tok.isNot(tok::eod));
+  }
+
+  // Replace the "eod" token with an "eof" token identifying the end of
+  // the provided string.
+  Token &EndToken = Tokens.back();
+  EndToken.startToken();
+  EndToken.setKind(tok::eof);
+  EndToken.setLocation(Tok.getLocation());
+  EndToken.setEofData(TypeStr.data());
+
+  // Add the current token back.
+  Tokens.push_back(Tok);
+
+  // Enter the tokens into the token stream.
+  PP.EnterTokenStream(Tokens, /*DisableMacroExpansion=*/false,
+                      /*IsReinject=*/false);
+
+  // Consume the current token so that we'll start parsing the tokens we
+  // added to the stream.
+  ConsumeAnyToken();
+
+  // Enter a new scope.
+  ParseScope LocalScope(this, 0);
+
+  // Parse the type.
+  TypeResult Result = ParseTypeName(nullptr);
+
+  // Check if we parsed the whole thing.
+  if (Result.isUsable() &&
+      (Tok.isNot(tok::eof) || Tok.getEofData() != TypeStr.data())) {
+    Diag(Tok.getLocation(), diag::err_type_unparsed);
+  }
+
+  // There could be leftover tokens (e.g. because of an error).
+  // Skip through until we reach the 'end of directive' token.
+  while (Tok.isNot(tok::eof))
+    ConsumeAnyToken();
+
+  // Consume the end token.
+  if (Tok.is(tok::eof) && Tok.getEofData() == TypeStr.data())
+    ConsumeAnyToken();
+  return Result;
+}
+
 void Parser::DiagnoseBitIntUse(const Token &Tok) {
   // If the token is for _ExtInt, diagnose it as being deprecated. Otherwise,
   // the token is about _BitInt and gets (potentially) diagnosed as use of an

clang/lib/Parse/Parser.cpp

@@ -70,6 +70,11 @@ Parser::Parser(Preprocessor &pp, Sema &actions, bool skipFunctionBodies)
   PP.addCommentHandler(CommentSemaHandler.get());
 
   PP.setCodeCompletionHandler(*this);
+
+  Actions.ParseTypeFromStringCallback =
+      [this](StringRef TypeStr, StringRef Context, SourceLocation IncludeLoc) {
+        return this->ParseTypeFromString(TypeStr, Context, IncludeLoc);
+      };
 }
 
 DiagnosticBuilder Parser::Diag(SourceLocation Loc, unsigned DiagID) {

clang/lib/Sema/SemaDecl.cpp

@@ -15205,6 +15205,37 @@ void Sema::DiagnoseSizeOfParametersAndReturnValue(
   }
 }
 
+QualType Sema::AdjustParameterTypeForObjCAutoRefCount(QualType T,
+                                                      SourceLocation NameLoc,
+                                                      TypeSourceInfo *TSInfo) {
+  // In ARC, infer a lifetime qualifier for appropriate parameter types.
+  if (!getLangOpts().ObjCAutoRefCount ||
+      T.getObjCLifetime() != Qualifiers::OCL_None || !T->isObjCLifetimeType())
+    return T;
+
+  Qualifiers::ObjCLifetime Lifetime;
+
+  // Special cases for arrays:
+  //   - if it's const, use __unsafe_unretained
+  //   - otherwise, it's an error
+  if (T->isArrayType()) {
+    if (!T.isConstQualified()) {
+      if (DelayedDiagnostics.shouldDelayDiagnostics())
+        DelayedDiagnostics.add(sema::DelayedDiagnostic::makeForbiddenType(
+            NameLoc, diag::err_arc_array_param_no_ownership, T, false));
+      else
+        Diag(NameLoc, diag::err_arc_array_param_no_ownership)
+            << TSInfo->getTypeLoc().getSourceRange();
+    }
+    Lifetime = Qualifiers::OCL_ExplicitNone;
+  } else {
+    Lifetime = T->getObjCARCImplicitLifetime();
+  }
+  T = Context.getLifetimeQualifiedType(T, Lifetime);
+
+  return T;
+}
+
 ParmVarDecl *Sema::CheckParameter(DeclContext *DC, SourceLocation StartLoc,
                                   SourceLocation NameLoc, IdentifierInfo *Name,
                                   QualType T, TypeSourceInfo *TSInfo,

clang/lib/Sema/SemaDeclAttr.cpp

@@ -6236,29 +6236,35 @@ static void handleObjCRequiresSuperAttr(Sema &S, Decl *D,
   D->addAttr(::new (S.Context) ObjCRequiresSuperAttr(S.Context, Attrs));
 }
 
-static void handleNSErrorDomain(Sema &S, Decl *D, const ParsedAttr &AL) {
-  auto *E = AL.getArgAsExpr(0);
-  auto Loc = E ? E->getBeginLoc() : AL.getLoc();
-
-  auto *DRE = dyn_cast<DeclRefExpr>(AL.getArgAsExpr(0));
-  if (!DRE) {
-    S.Diag(Loc, diag::err_nserrordomain_invalid_decl) << 0;
+static void handleNSErrorDomain(Sema &S, Decl *D, const ParsedAttr &Attr) {
+  if (!isa<TagDecl>(D)) {
+    S.Diag(D->getBeginLoc(), diag::err_nserrordomain_invalid_decl) << 0;
     return;
   }
 
-  auto *VD = dyn_cast<VarDecl>(DRE->getDecl());
-  if (!VD) {
-    S.Diag(Loc, diag::err_nserrordomain_invalid_decl) << 1 << DRE->getDecl();
+  IdentifierLoc *IdentLoc =
+      Attr.isArgIdent(0) ? Attr.getArgAsIdent(0) : nullptr;
+  if (!IdentLoc || !IdentLoc->Ident) {
+    // Try to locate the argument directly.
+    SourceLocation Loc = Attr.getLoc();
+    if (Attr.isArgExpr(0) && Attr.getArgAsExpr(0))
+      Loc = Attr.getArgAsExpr(0)->getBeginLoc();
+
+    S.Diag(Loc, diag::err_nserrordomain_invalid_decl) << 0;
     return;
   }
 
-  if (!isNSStringType(VD->getType(), S.Context) &&
-      !isCFStringType(VD->getType(), S.Context)) {
-    S.Diag(Loc, diag::err_nserrordomain_wrong_type) << VD;
+  // Verify that the identifier is a valid decl in the C decl namespace.
+  LookupResult Result(S, DeclarationName(IdentLoc->Ident), SourceLocation(),
+                      Sema::LookupNameKind::LookupOrdinaryName);
+  if (!S.LookupName(Result, S.TUScope) || !Result.getAsSingle<VarDecl>()) {
+    S.Diag(IdentLoc->Loc, diag::err_nserrordomain_invalid_decl)
+        << 1 << IdentLoc->Ident;
     return;
   }
 
-  D->addAttr(::new (S.Context) NSErrorDomainAttr(S.Context, AL, VD));
+  D->addAttr(::new (S.Context)
+                 NSErrorDomainAttr(S.Context, Attr, IdentLoc->Ident));
 }
 
 static void handleObjCBridgeAttr(Sema &S, Decl *D, const ParsedAttr &AL) {