diff --git a/clang/include/clang/Basic/TokenKinds.def b/clang/include/clang/Basic/TokenKinds.def
--- a/clang/include/clang/Basic/TokenKinds.def
+++ b/clang/include/clang/Basic/TokenKinds.def
@@ -937,6 +937,9 @@
 // into the name of a header unit.
 ANNOTATION(header_unit)
 
+// Annotation for end of input in clang-repl.
+ANNOTATION(input_end)
+
 #undef PRAGMA_ANNOTATION
 #undef ANNOTATION
 #undef TESTING_KEYWORD
diff --git a/clang/include/clang/Parse/Parser.h b/clang/include/clang/Parse/Parser.h
--- a/clang/include/clang/Parse/Parser.h
+++ b/clang/include/clang/Parse/Parser.h
@@ -692,7 +692,8 @@
   bool isEofOrEom() {
     tok::TokenKind Kind = Tok.getKind();
     return Kind == tok::eof || Kind == tok::annot_module_begin ||
-           Kind == tok::annot_module_end || Kind == tok::annot_module_include;
+           Kind == tok::annot_module_end || Kind == tok::annot_module_include ||
+           Kind == tok::annot_input_end;
   }
 
   /// Checks if the \p Level is valid for use in a fold expression.
diff --git a/clang/lib/Frontend/PrintPreprocessedOutput.cpp b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
--- a/clang/lib/Frontend/PrintPreprocessedOutput.cpp
+++ b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
@@ -663,7 +663,8 @@
   // them.
   if (Tok.is(tok::eof) ||
       (Tok.isAnnotation() && !Tok.is(tok::annot_header_unit) &&
-       !Tok.is(tok::annot_module_begin) && !Tok.is(tok::annot_module_end)))
+       !Tok.is(tok::annot_module_begin) && !Tok.is(tok::annot_module_end) &&
+       !Tok.is(tok::annot_input_end)))
     return;
 
   // EmittedDirectiveOnThisLine takes priority over RequireSameLine.
@@ -819,6 +820,9 @@
       // -traditional-cpp the lexer keeps /all/ whitespace, including comments.
       PP.Lex(Tok);
       continue;
+    } else if (Tok.is(tok::annot_input_end)) {
+      PP.Lex(Tok);
+      continue;
     } else if (Tok.is(tok::eod)) {
       // Don't print end of directive tokens, since they are typically newlines
       // that mess up our line tracking. These come from unknown pre-processor
diff --git a/clang/lib/Interpreter/IncrementalParser.cpp b/clang/lib/Interpreter/IncrementalParser.cpp
--- a/clang/lib/Interpreter/IncrementalParser.cpp
+++ b/clang/lib/Interpreter/IncrementalParser.cpp
@@ -158,8 +158,8 @@
   LastPTU.TUPart = C.getTranslationUnitDecl();
 
   // Skip previous eof due to last incremental input.
-  if (P->getCurToken().is(tok::eof)) {
-    P->ConsumeToken();
+  if (P->getCurToken().is(tok::annot_input_end)) {
+    P->ConsumeAnyToken();
     // FIXME: Clang does not call ExitScope on finalizing the regular TU, we
     // might want to do that around HandleEndOfTranslationUnit.
     P->ExitScope();
@@ -259,12 +259,12 @@
     Token Tok;
     do {
       PP.Lex(Tok);
-    } while (Tok.isNot(tok::eof));
+    } while (Tok.isNot(tok::annot_input_end));
   }
 
   Token AssertTok;
   PP.Lex(AssertTok);
-  assert(AssertTok.is(tok::eof) &&
+  assert(AssertTok.is(tok::annot_input_end) &&
          "Lexer must be EOF when starting incremental parse!");
 
   if (CodeGenerator *CG = getCodeGen(Act.get())) {
diff --git a/clang/lib/Lex/PPLexerChange.cpp b/clang/lib/Lex/PPLexerChange.cpp
--- a/clang/lib/Lex/PPLexerChange.cpp
+++ b/clang/lib/Lex/PPLexerChange.cpp
@@ -535,13 +535,19 @@
       return LeavingSubmodule;
     }
   }
-
   // If this is the end of the main file, form an EOF token.
   assert(CurLexer && "Got EOF but no current lexer set!");
   const char *EndPos = getCurLexerEndPos();
   Result.startToken();
   CurLexer->BufferPtr = EndPos;
-  CurLexer->FormTokenWithChars(Result, EndPos, tok::eof);
+
+  if (isIncrementalProcessingEnabled()) {
+    CurLexer->FormTokenWithChars(Result, EndPos, tok::annot_input_end);
+    Result.setAnnotationEndLoc(Result.getLocation());
+    Result.setAnnotationValue(nullptr);
+  } else {
+    CurLexer->FormTokenWithChars(Result, EndPos, tok::eof);
+  }
 
   if (isCodeCompletionEnabled()) {
     // Inserting the code-completion point increases the source buffer by 1,
diff --git a/clang/lib/Parse/ParseCXXInlineMethods.cpp b/clang/lib/Parse/ParseCXXInlineMethods.cpp
--- a/clang/lib/Parse/ParseCXXInlineMethods.cpp
+++ b/clang/lib/Parse/ParseCXXInlineMethods.cpp
@@ -836,6 +836,7 @@
     case tok::annot_module_begin:
     case tok::annot_module_end:
     case tok::annot_module_include:
+    case tok::annot_input_end:
       // Ran out of tokens.
       return false;
 
@@ -1242,6 +1243,7 @@
     case tok::annot_module_begin:
     case tok::annot_module_end:
     case tok::annot_module_include:
+    case tok::annot_input_end:
       // Ran out of tokens.
       return false;
 
diff --git a/clang/lib/Parse/ParseDecl.cpp b/clang/lib/Parse/ParseDecl.cpp
--- a/clang/lib/Parse/ParseDecl.cpp
+++ b/clang/lib/Parse/ParseDecl.cpp
@@ -2061,6 +2061,7 @@
     case tok::annot_module_begin:
     case tok::annot_module_end:
     case tok::annot_module_include:
+    case tok::annot_input_end:
       return;
 
     default:
diff --git a/clang/lib/Parse/Parser.cpp b/clang/lib/Parse/Parser.cpp
--- a/clang/lib/Parse/Parser.cpp
+++ b/clang/lib/Parse/Parser.cpp
@@ -320,6 +320,7 @@
     case tok::annot_module_begin:
     case tok::annot_module_end:
     case tok::annot_module_include:
+    case tok::annot_input_end:
       // Stop before we change submodules. They generally indicate a "good"
       // place to pick up parsing again (except in the special case where
       // we're trying to skip to EOF).
@@ -616,8 +617,8 @@
 
   // Skip over the EOF token, flagging end of previous input for incremental
   // processing
-  if (PP.isIncrementalProcessingEnabled() && Tok.is(tok::eof))
-    ConsumeToken();
+  if (PP.isIncrementalProcessingEnabled() && Tok.is(tok::annot_input_end))
+    ConsumeAnyToken();
 
   Result = nullptr;
   switch (Tok.getKind()) {
@@ -697,6 +698,7 @@
     return false;
 
   case tok::eof:
+  case tok::annot_input_end:
     // Check whether -fmax-tokens= was reached.
     if (PP.getMaxTokens() != 0 && PP.getTokenCount() > PP.getMaxTokens()) {
       PP.Diag(Tok.getLocation(), diag::warn_max_tokens_total)