Bitcode: Use unsigned char to record MDStrings

`MDString`s can have arbitrary characters in them.  Prevent an assertion
that fired in `BitcodeWriter` because of sign extension by copying the
characters into the record as `unsigned char`s.

Based on a patch by Keno Fischer; fixes PR21882.

llvm-svn: 224077

4 files changed, 20 insertions, 1 deletions

diff --git a/llvm/include/llvm/ADT/StringRef.h b/llvm/include/llvm/ADT/StringRef.h
index 778fa10a32c..6111c42da9d 100644
--- a/llvm/include/llvm/ADT/StringRef.h
+++ b/llvm/include/llvm/ADT/StringRef.h
@@ -91,6 +91,13 @@ namespace llvm {
 
     iterator end() const { return Data + Length; }
 
+    const unsigned char *bytes_begin() const {
+      return reinterpret_cast<const unsigned char *>(begin());
+    }
+    const unsigned char *bytes_end() const {
+      return reinterpret_cast<const unsigned char *>(end());
+    }
+
     /// @}
     /// @name String Operations
     /// @{
diff --git a/llvm/include/llvm/IR/Metadata.h b/llvm/include/llvm/IR/Metadata.h
index 5e1b294fa1f..fdcff4d6237 100644
--- a/llvm/include/llvm/IR/Metadata.h
+++ b/llvm/include/llvm/IR/Metadata.h
@@ -459,6 +459,9 @@ public:
   /// \brief Pointer to one byte past the end of the string.
   iterator end() const { return getString().end(); }
 
+  const unsigned char *bytes_begin() const { return getString().bytes_begin(); }
+  const unsigned char *bytes_end() const { return getString().bytes_end(); }
+
   /// \brief Methods for support type inquiry through isa, cast, and dyn_cast.
   static bool classof(const Metadata *MD) {
     return MD->getMetadataID() == MDStringKind;
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 90ac1f19b7d..c349d1053de 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -800,7 +800,7 @@ static void WriteModuleMetadata(const Module *M,
       }
 
       // Code: [strchar x N]
-      Record.append(MDS->begin(), MDS->end());
+      Record.append(MDS->bytes_begin(), MDS->bytes_end());
 
       // Emit the finished record.
       Stream.EmitRecord(bitc::METADATA_STRING, Record, MDSAbbrev);
diff --git a/llvm/test/Bitcode/mdstring-high-bits.ll b/llvm/test/Bitcode/mdstring-high-bits.ll
new file mode 100644
index 00000000000..ffc4f6ed184
--- /dev/null
+++ b/llvm/test/Bitcode/mdstring-high-bits.ll
@@ -0,0 +1,9 @@
+; RUN: llvm-as < %s | llvm-dis | FileCheck %s
+
+; PR21882: confirm we don't crash when high bits are set in a character in a
+; metadata string.
+
+; CHECK: !name = !{!0}
+!name = !{!0}
+; CHECK: !0 = metadata !{metadata !"\80"}
+!0 = metadata !{metadata !"\80"}