Index: lib/CodeGen/MIRParser/CMakeLists.txt
===================================================================
--- lib/CodeGen/MIRParser/CMakeLists.txt
+++ lib/CodeGen/MIRParser/CMakeLists.txt
@@ -1,4 +1,5 @@
 add_llvm_library(LLVMMIRParser
+  MILexer.cpp
   MIParser.cpp
   MIRParser.cpp
   )
Index: lib/CodeGen/MIRParser/MILexer.h
===================================================================
--- /dev/null
+++ lib/CodeGen/MIRParser/MILexer.h
@@ -0,0 +1,76 @@
+//===- MILexer.h - Lexer for machine instructions -------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file declares the class that lexes the machine instructions.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_CODEGEN_MIRPARSER_MILEXER_H
+#define LLVM_LIB_CODEGEN_MIRPARSER_MILEXER_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/SourceMgr.h"
+
+namespace llvm {
+
+namespace mitok {
+
+enum Kind {
+  // Markers
+  Eof,
+  Error,
+
+  // Identifier tokens
+  Identifier
+};
+
+} // end namespace mitok
+
+class MILexer {
+  SourceMgr &SM;
+  SMDiagnostic &Error;
+  const char *BufStart;
+  const char *CurPtr;
+  const char *BufEnd;
+  /// The location of the current token.
+  SMLoc CurLoc;
+  mitok::Kind CurKind;
+  StringRef StrVal;
+
+public:
+  MILexer(SourceMgr &SM, SMDiagnostic &Error, StringRef Source);
+
+  /// Report an error at the current location with the given message, and return
+  /// mitok::Error.
+  mitok::Kind error(const Twine &Msg);
+
+  /// Report an error at the given location with the given message, and return
+  /// mitok::Error.
+  mitok::Kind error(SMLoc Loc, const Twine &Msg);
+
+  bool isError() const { return CurKind == mitok::Error; }
+
+  SMLoc getLoc() const { return CurLoc; }
+
+  mitok::Kind getKind() const { return CurKind; }
+
+  StringRef getStringValue() const { return StrVal; }
+
+  void lex() { CurKind = lexToken(); }
+
+private:
+  bool isEOF() const;
+  void skipWhitespace();
+  mitok::Kind lexToken();
+  mitok::Kind lexIdentifier();
+};
+
+} // end namespace llvm
+
+#endif
Index: lib/CodeGen/MIRParser/MILexer.cpp
===================================================================
--- /dev/null
+++ lib/CodeGen/MIRParser/MILexer.cpp
@@ -0,0 +1,68 @@
+//===- MILexer.cpp - Machine instructions lexer implementation ----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the lexing of machine instructions.
+//
+//===----------------------------------------------------------------------===//
+
+#include "MILexer.h"
+#include <cctype>
+
+using namespace llvm;
+
+static bool isIdentifierChar(char C) {
+  return isalpha(C) || isdigit(C) || C == '_' || C == '-' || C == '.';
+}
+
+MILexer::MILexer(SourceMgr &SM, SMDiagnostic &Error, StringRef Source)
+    : SM(SM), Error(Error) {
+  CurPtr = BufStart = Source.data();
+  BufEnd = CurPtr + Source.size();
+}
+
+mitok::Kind MILexer::error(const Twine &Msg) { return error(getLoc(), Msg); }
+
+mitok::Kind MILexer::error(SMLoc Loc, const Twine &Msg) {
+  // TODO: Get the proper location in the MIR file, not just a location inside
+  // the string.
+  const char *Ptr = Loc.getPointer();
+  assert(Ptr >= BufStart && Ptr <= BufEnd);
+  Error = SMDiagnostic(SM, SMLoc(), SM.getMemoryBuffer(SM.getMainFileID())
+                                        ->getBufferIdentifier(),
+                       1, Ptr - BufStart, SourceMgr::DK_Error, Msg.str(),
+                       StringRef(BufStart, BufEnd - BufStart), None, None);
+  return mitok::Error;
+}
+
+bool MILexer::isEOF() const { return CurPtr >= BufEnd; }
+
+void MILexer::skipWhitespace() {
+  while (!isEOF() && isspace(*CurPtr))
+    ++CurPtr;
+}
+
+mitok::Kind MILexer::lexIdentifier() {
+  auto Start = CurPtr - 1;
+  while (!isEOF() && isIdentifierChar(*CurPtr))
+    ++CurPtr;
+  StrVal = StringRef(Start, CurPtr - Start);
+  return mitok::Identifier;
+}
+
+mitok::Kind MILexer::lexToken() {
+  skipWhitespace();
+  CurLoc = SMLoc::getFromPointer(CurPtr);
+  if (isEOF())
+    return mitok::Eof;
+
+  char CurChar = *CurPtr++;
+  if (isalpha(CurChar) || CurChar == '_')
+    return lexIdentifier();
+  return error(Twine("unexpected character '") + Twine(CurChar) + "'");
+}
Index: lib/CodeGen/MIRParser/MIParser.cpp
===================================================================
--- lib/CodeGen/MIRParser/MIParser.cpp
+++ lib/CodeGen/MIRParser/MIParser.cpp
@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "MIParser.h"
+#include "MILexer.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFunction.h"
@@ -26,10 +27,8 @@
 namespace {
 
 class MIParser {
-  SourceMgr &SM;
   MachineFunction &MF;
-  SMDiagnostic &Error;
-  StringRef Source;
+  MILexer Lex;
   /// Maps from instruction names to op codes.
   StringMap<unsigned> Names2InstrOpCodes;
 
@@ -50,31 +49,27 @@
   /// Try to convert an instruction name to an opcode. Return true if the
   /// instruction name is invalid.
   bool parseInstrName(StringRef InstrName, unsigned &OpCode);
+
+  bool parseInstruction(unsigned &OpCode);
 };
 
 } // end anonymous namespace
 
 MIParser::MIParser(SourceMgr &SM, MachineFunction &MF, SMDiagnostic &Error,
                    StringRef Source)
-    : SM(SM), MF(MF), Error(Error), Source(Source) {}
+    : MF(MF), Lex(SM, Error, Source) {}
 
 bool MIParser::error(const Twine &Msg) {
-  // TODO: Get the proper location in the MIR file, not just a location inside
-  // the string.
-  Error =
-      SMDiagnostic(SM, SMLoc(), SM.getMemoryBuffer(SM.getMainFileID())
-                                    ->getBufferIdentifier(),
-                   1, 0, SourceMgr::DK_Error, Msg.str(), Source, None, None);
+  Lex.error(Msg);
   return true;
 }
 
 MachineInstr *MIParser::parse() {
-  StringRef InstrName = Source;
+  Lex.lex();
+
   unsigned OpCode;
-  if (parseInstrName(InstrName, OpCode)) {
-    error(Twine("unknown machine instruction name '") + InstrName + "'");
+  if (Lex.isError() || parseInstruction(OpCode))
     return nullptr;
-  }
 
   // TODO: Parse the rest of instruction - machine operands, etc.
   const auto &MCID = MF.getSubtarget().getInstrInfo()->get(OpCode);
@@ -82,6 +77,15 @@
   return MI;
 }
 
+bool MIParser::parseInstruction(unsigned &OpCode) {
+  if (Lex.getKind() != mitok::Identifier)
+    return error("expected a machine instruction");
+  StringRef InstrName = Lex.getStringValue();
+  if (parseInstrName(InstrName, OpCode))
+    return error(Twine("unknown machine instruction name '") + InstrName + "'");
+  return false;
+}
+
 void MIParser::initNames2InstrOpCodes() {
   if (!Names2InstrOpCodes.empty())
     return;
Index: test/CodeGen/MIR/X86/machine-instructions.mir
===================================================================
--- test/CodeGen/MIR/X86/machine-instructions.mir
+++ test/CodeGen/MIR/X86/machine-instructions.mir
@@ -20,5 +20,5 @@
      # CHECK:      - imul32rri8
      # CHECK-NEXT: - retq
      - imul32rri8
-     - retq
+     - ' retq '
 ...
Index: test/CodeGen/MIR/X86/missing-instruction.mir
===================================================================
--- /dev/null
+++ test/CodeGen/MIR/X86/missing-instruction.mir
@@ -0,0 +1,18 @@
+# RUN: not llc -march=x86-64 -start-after branch-folder -stop-after branch-folder -o /dev/null %s 2>&1 | FileCheck %s
+
+--- |
+
+  define void @foo() {
+  entry:
+    ret void
+  }
+
+...
+---
+name:            foo
+body:
+ - name:         entry
+   instructions:
+     # CHECK: 1:1: expected a machine instruction
+     - ''
+...
Index: test/CodeGen/MIR/X86/unrecognized-character.mir
===================================================================
--- /dev/null
+++ test/CodeGen/MIR/X86/unrecognized-character.mir
@@ -0,0 +1,18 @@
+# RUN: not llc -march=x86-64 -start-after branch-folder -stop-after branch-folder -o /dev/null %s 2>&1 | FileCheck %s
+
+--- |
+
+  define void @foo() {
+  entry:
+    ret void
+  }
+
+...
+---
+name:            foo
+body:
+ - name:         entry
+   instructions:
+     # CHECK: 1:1: unexpected character '`'
+     - '` retq'
+...