diff --git a/clang/lib/Lex/TokenLexer.cpp b/clang/lib/Lex/TokenLexer.cpp
--- a/clang/lib/Lex/TokenLexer.cpp
+++ b/clang/lib/Lex/TokenLexer.cpp
@@ -993,14 +993,25 @@
   llvm::MutableArrayRef<Token> All(begin_tokens, end_tokens);
   llvm::MutableArrayRef<Token> Partition;
 
+  // The maximum distance between two consecutive tokens in a partition.
+  // This is am important trick to avoid using too much SourceLocation address
+  // space!
+  const static int MaxDistance = 50;
   // Partition the tokens by their FileID.
   // This is a hot function, and calling getFileID can be expensive, the
   // implementation is optimized by reducing the number of getFileID.
   if (BeginLoc.isFileID()) {
     // Consecutive tokens not written in macros must be from the same file.
     // (Neither #include nor eof can occur inside a macro argument.)
+    SourceLocation LastLoc = BeginLoc;
     Partition = All.take_while([&](const Token &T) {
-      return T.getLocation().isFileID();
+      if (T.getLocation().isFileID()) {
+        unsigned distance =
+            T.getLocation().getRawEncoding() - LastLoc.getRawEncoding();
+        LastLoc = T.getLocation();
+        return distance <= MaxDistance;
+      }
+      return false;
     });
   } else {
     // Call getFileID once to calculate the bounds, and use the cheaper
@@ -1008,8 +1019,15 @@
     FileID BeginFID = SM.getFileID(BeginLoc);
     SourceLocation Limit =
         SM.getComposedLoc(BeginFID, SM.getFileIDSize(BeginFID));
+    SourceLocation LastLoc = BeginLoc;
     Partition = All.take_while([&](const Token &T) {
-      return T.getLocation() >= BeginLoc && T.getLocation() < Limit;
+      if (T.getLocation() >= BeginLoc && T.getLocation() < Limit) {
+        unsigned distance =
+            T.getLocation().getRawEncoding() - LastLoc.getRawEncoding();
+        LastLoc = T.getLocation();
+        return distance <= MaxDistance;
+      }
+      return false;
     });
   }
   assert(!Partition.empty());