6 files changed, 9 insertions, 1 deletions
diff --git a/clang/lib/AST/StmtPrinter.cpp b/clang/lib/AST/StmtPrinter.cpp
index e55b2fc19a1..69f52f52b66 100644
--- a/clang/lib/AST/StmtPrinter.cpp
+++ b/clang/lib/AST/StmtPrinter.cpp
@@ -1165,6 +1165,7 @@ void StmtPrinter::VisitCharacterLiteral(CharacterLiteral *Node) {
   switch (Node->getKind()) {
   case CharacterLiteral::Ascii: break; // no prefix.
   case CharacterLiteral::Wide:  OS << 'L'; break;
+  case CharacterLiteral::UTF8:  OS << "u8"; break;
   case CharacterLiteral::UTF16: OS << 'u'; break;
   case CharacterLiteral::UTF32: OS << 'U'; break;
   }
diff --git a/clang/lib/Lex/LiteralSupport.cpp b/clang/lib/Lex/LiteralSupport.cpp
index 1e7858af894..5b1c49344e8 100644
--- a/clang/lib/Lex/LiteralSupport.cpp
+++ b/clang/lib/Lex/LiteralSupport.cpp
@@ -983,6 +983,7 @@ NumericLiteralParser::GetFloatValue(llvm::APFloat &Result) {
 ///         u' c-char-sequence '
 ///         U' c-char-sequence '
 ///         L' c-char-sequence '
+///         u8' c-char-sequence ' [C++1z lex.ccon]
 ///       c-char-sequence:
 ///         c-char
 ///         c-char-sequence c-char
diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index 67d5db15cf2..76d0ca56c0c 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -3084,6 +3084,8 @@ ExprResult Sema::ActOnCharacterConstant(const Token &Tok, Scope *UDLScope) {
     Kind = CharacterLiteral::UTF16;
   else if (Literal.isUTF32())
     Kind = CharacterLiteral::UTF32;
+  else if (Literal.isUTF8())
+    Kind = CharacterLiteral::UTF8;
 
   Expr *Lit = new (Context) CharacterLiteral(Literal.getValue(), Kind, Ty,
                                              Tok.getLocation());
diff --git a/clang/lib/Sema/SemaExprObjC.cpp b/clang/lib/Sema/SemaExprObjC.cpp
index 57a08b94f5e..1d86ca35412 100644
--- a/clang/lib/Sema/SemaExprObjC.cpp
+++ b/clang/lib/Sema/SemaExprObjC.cpp
@@ -319,6 +319,7 @@ ExprResult Sema::BuildObjCNumericLiteral(SourceLocation AtLoc, Expr *Number) {
     // to use to determine the Objective-c literal kind.
     switch (Char->getKind()) {
     case CharacterLiteral::Ascii:
+    case CharacterLiteral::UTF8:
       NumberType = Context.CharTy;
       break;
       
@@ -577,6 +578,7 @@ ExprResult Sema::BuildObjCBoxedExpr(SourceRange SR, Expr *ValueExpr) {
       // to use to determine the Objective-c literal kind.
       switch (Char->getKind()) {
       case CharacterLiteral::Ascii:
+      case CharacterLiteral::UTF8:
         ValueType = Context.CharTy;
         break;
         
diff --git a/clang/lib/Sema/SemaTemplate.cpp b/clang/lib/Sema/SemaTemplate.cpp
index 6cc85883345..9775e4d940a 100644
--- a/clang/lib/Sema/SemaTemplate.cpp
+++ b/clang/lib/Sema/SemaTemplate.cpp
@@ -5503,6 +5503,8 @@ Sema::BuildExpressionFromIntegralTemplateArgument(const TemplateArgument &Arg,
 
   Expr *E;
   if (T->isAnyCharacterType()) {
+    // This does not need to handle u8 character literals because those are
+    // of type char, and so can also be covered by an ASCII character literal.
     CharacterLiteral::CharacterKind Kind;
     if (T->isWideCharType())
       Kind = CharacterLiteral::Wide;
diff --git a/clang/lib/Serialization/ASTWriterDecl.cpp b/clang/lib/Serialization/ASTWriterDecl.cpp
index 20ca6d6fd51..54bba282ab8 100644
--- a/clang/lib/Serialization/ASTWriterDecl.cpp
+++ b/clang/lib/Serialization/ASTWriterDecl.cpp
@@ -2033,7 +2033,7 @@ void ASTWriter::WriteDeclAbbrevs() {
   //Character Literal
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // getValue
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
-  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 2)); // getKind
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); // getKind
   CharacterLiteralAbbrev = Stream.EmitAbbrev(Abv);
 
   // Abbreviation for EXPR_IMPLICIT_CAST