MIR Serialization: Change MIR syntax - use custom syntax for MBBs.

This commit modifies the way the machine basic blocks are serialized - now the
machine basic blocks are serialized using a custom syntax instead of relying on
YAML primitives. Instead of using YAML mappings to represent the individual
machine basic blocks in a machine function's body, the new syntax uses a single
YAML block scalar which contains all of the machine basic blocks and
instructions for that function.

This is an example of a function's body that uses the old syntax:

    body:
      - id: 0
        name: entry
        instructions:
          - '%eax = MOV32r0 implicit-def %eflags'
          - 'RETQ %eax'
    ...

The same body is now written like this:

    body: |
      bb.0.entry:
        %eax = MOV32r0 implicit-def %eflags
        RETQ %eax
    ...

This syntax change is motivated by the fact that the bundled machine
instructions didn't map that well to the old syntax which was using a single
YAML sequence to store all of the machine instructions in a block. The bundled
machine instructions internally use flags like BundledPred and BundledSucc to
determine the bundles, and serializing them as MI flags using the old syntax
would have had a negative impact on the readability and the ease of editing
for MIR files. The new syntax allows me to serialize the bundled machine
instructions using a block construct without relying on the internal flags,
for example:

   BUNDLE implicit-def dead %itstate, implicit-def %s1 ... {
      t2IT 1, 24, implicit-def %itstate
      %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate
   }

This commit also converts the MIR testcases to the new syntax. I developed
a script that can convert from the old syntax to the new one. I will post the
script on the llvm-commits mailing list in the thread for this commit.

llvm-svn: 244982

5 files changed, 378 insertions, 152 deletions

diff --git a/llvm/lib/CodeGen/MIRParser/MILexer.cpp b/llvm/lib/CodeGen/MIRParser/MILexer.cpp
index 25afedff973..450d318f8c8 100644
--- a/llvm/lib/CodeGen/MIRParser/MILexer.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MILexer.cpp
@@ -79,7 +79,18 @@ MIToken &MIToken::setIntegerValue(APSInt IntVal) {
 
 /// Skip the leading whitespace characters and return the updated cursor.
 static Cursor skipWhitespace(Cursor C) {
-  while (isspace(C.peek()))
+  while (isblank(C.peek()))
+    C.advance();
+  return C;
+}
+
+static bool isNewlineChar(char C) { return C == '\n' || C == '\r'; }
+
+/// Skip a line comment and return the updated cursor.
+static Cursor skipComment(Cursor C) {
+  if (C.peek() != ';')
+    return C;
+  while (!isNewlineChar(C.peek()) && !C.isEOF())
     C.advance();
   return C;
 }
@@ -127,7 +138,7 @@ static Cursor lexStringConstant(
     function_ref<void(StringRef::iterator Loc, const Twine &)> ErrorCallback) {
   assert(C.peek() == '"');
   for (C.advance(); C.peek() != '"'; C.advance()) {
-    if (C.isEOF()) {
+    if (C.isEOF() || isNewlineChar(C.peek())) {
       ErrorCallback(
           C.location(),
           "end of machine instruction reached before the closing '\"'");
@@ -206,6 +217,10 @@ static MIToken::TokenKind getIdentifierKind(StringRef Identifier) {
       .Case("jump-table", MIToken::kw_jump_table)
       .Case("constant-pool", MIToken::kw_constant_pool)
       .Case("liveout", MIToken::kw_liveout)
+      .Case("address-taken", MIToken::kw_address_taken)
+      .Case("landing-pad", MIToken::kw_landing_pad)
+      .Case("liveins", MIToken::kw_liveins)
+      .Case("successors", MIToken::kw_successors)
       .Default(MIToken::Identifier);
 }
 
@@ -224,10 +239,12 @@ static Cursor maybeLexIdentifier(Cursor C, MIToken &Token) {
 static Cursor maybeLexMachineBasicBlock(
     Cursor C, MIToken &Token,
     function_ref<void(StringRef::iterator Loc, const Twine &)> ErrorCallback) {
-  if (!C.remaining().startswith("%bb."))
+  bool IsReference = C.remaining().startswith("%bb.");
+  if (!IsReference && !C.remaining().startswith("bb."))
     return None;
   auto Range = C;
-  C.advance(4); // Skip '%bb.'
+  unsigned PrefixLength = IsReference ? 4 : 3;
+  C.advance(PrefixLength); // Skip '%bb.' or 'bb.'
   if (!isdigit(C.peek())) {
     Token.reset(MIToken::Error, C.remaining());
     ErrorCallback(C.location(), "expected a number after '%bb.'");
@@ -237,14 +254,16 @@ static Cursor maybeLexMachineBasicBlock(
   while (isdigit(C.peek()))
     C.advance();
   StringRef Number = NumberRange.upto(C);
-  unsigned StringOffset = 4 + Number.size(); // Drop '%bb.<id>'
+  unsigned StringOffset = PrefixLength + Number.size(); // Drop '%bb.<id>'
   if (C.peek() == '.') {
     C.advance(); // Skip '.'
     ++StringOffset;
     while (isIdentifierChar(C.peek()))
       C.advance();
   }
-  Token.reset(MIToken::MachineBasicBlock, Range.upto(C))
+  Token.reset(IsReference ? MIToken::MachineBasicBlock
+                          : MIToken::MachineBasicBlockLabel,
+              Range.upto(C))
       .setIntegerValue(APSInt(Number))
       .setStringValue(Range.upto(C).drop_front(StringOffset));
   return C;
@@ -460,10 +479,19 @@ static Cursor maybeLexSymbol(Cursor C, MIToken &Token) {
   return C;
 }
 
+static Cursor maybeLexNewline(Cursor C, MIToken &Token) {
+  if (!isNewlineChar(C.peek()))
+    return None;
+  auto Range = C;
+  C.advance();
+  Token.reset(MIToken::Newline, Range.upto(C));
+  return C;
+}
+
 StringRef llvm::lexMIToken(
     StringRef Source, MIToken &Token,
     function_ref<void(StringRef::iterator Loc, const Twine &)> ErrorCallback) {
-  auto C = skipWhitespace(Cursor(Source));
+  auto C = skipComment(skipWhitespace(Cursor(Source)));
   if (C.isEOF()) {
     Token.reset(MIToken::Eof, C.remaining());
     return C.remaining();
@@ -471,10 +499,10 @@ StringRef llvm::lexMIToken(
 
   if (Cursor R = maybeLexIntegerType(C, Token))
     return R.remaining();
-  if (Cursor R = maybeLexIdentifier(C, Token))
-    return R.remaining();
   if (Cursor R = maybeLexMachineBasicBlock(C, Token, ErrorCallback))
     return R.remaining();
+  if (Cursor R = maybeLexIdentifier(C, Token))
+    return R.remaining();
   if (Cursor R = maybeLexJumpTableIndex(C, Token))
     return R.remaining();
   if (Cursor R = maybeLexStackObject(C, Token))
@@ -499,6 +527,8 @@ StringRef llvm::lexMIToken(
     return R.remaining();
   if (Cursor R = maybeLexSymbol(C, Token))
     return R.remaining();
+  if (Cursor R = maybeLexNewline(C, Token))
+    return R.remaining();
 
   Token.reset(MIToken::Error, C.remaining());
   ErrorCallback(C.location(),
diff --git a/llvm/lib/CodeGen/MIRParser/MILexer.h b/llvm/lib/CodeGen/MIRParser/MILexer.h
index d0ae379097c..07bdc3e4549 100644
--- a/llvm/lib/CodeGen/MIRParser/MILexer.h
+++ b/llvm/lib/CodeGen/MIRParser/MILexer.h
@@ -30,6 +30,7 @@ struct MIToken {
     // Markers
     Eof,
     Error,
+    Newline,
 
     // Tokens with no info.
     comma,
@@ -75,11 +76,16 @@ struct MIToken {
     kw_jump_table,
     kw_constant_pool,
     kw_liveout,
+    kw_address_taken,
+    kw_landing_pad,
+    kw_liveins,
+    kw_successors,
 
     // Identifier tokens
     Identifier,
     IntegerType,
     NamedRegister,
+    MachineBasicBlockLabel,
     MachineBasicBlock,
     StackObject,
     FixedStackObject,
@@ -118,6 +124,10 @@ public:
 
   bool isError() const { return Kind == Error; }
 
+  bool isNewlineOrEOF() const { return Kind == Newline || Kind == Eof; }
+
+  bool isErrorOrEOF() const { return Kind == Error || Kind == Eof; }
+
   bool isRegister() const {
     return Kind == NamedRegister || Kind == underscore ||
            Kind == VirtualRegister;
@@ -149,10 +159,10 @@ public:
 
   bool hasIntegerValue() const {
     return Kind == IntegerLiteral || Kind == MachineBasicBlock ||
-           Kind == StackObject || Kind == FixedStackObject ||
-           Kind == GlobalValue || Kind == VirtualRegister ||
-           Kind == ConstantPoolItem || Kind == JumpTableIndex ||
-           Kind == IRBlock;
+           Kind == MachineBasicBlockLabel || Kind == StackObject ||
+           Kind == FixedStackObject || Kind == GlobalValue ||
+           Kind == VirtualRegister || Kind == ConstantPoolItem ||
+           Kind == JumpTableIndex || Kind == IRBlock;
   }
 };
 
diff --git a/llvm/lib/CodeGen/MIRParser/MIParser.cpp b/llvm/lib/CodeGen/MIRParser/MIParser.cpp
index 46ad8769fd3..3a0e52491ca 100644
--- a/llvm/lib/CodeGen/MIRParser/MIParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIParser.cpp
@@ -90,11 +90,19 @@ public:
   /// This function always return true.
   bool error(StringRef::iterator Loc, const Twine &Msg);
 
+  bool
+  parseBasicBlockDefinitions(DenseMap<unsigned, MachineBasicBlock *> &MBBSlots);
+  bool parseBasicBlocks();
   bool parse(MachineInstr *&MI);
   bool parseStandaloneMBB(MachineBasicBlock *&MBB);
   bool parseStandaloneNamedRegister(unsigned &Reg);
   bool parseStandaloneVirtualRegister(unsigned &Reg);
-  bool parseStandaloneIRBlockReference(const BasicBlock *&BB);
+
+  bool
+  parseBasicBlockDefinition(DenseMap<unsigned, MachineBasicBlock *> &MBBSlots);
+  bool parseBasicBlock(MachineBasicBlock &MBB);
+  bool parseBasicBlockLiveins(MachineBasicBlock &MBB);
+  bool parseBasicBlockSuccessors(MachineBasicBlock &MBB);
 
   bool parseRegister(unsigned &Reg);
   bool parseRegisterFlag(unsigned &Flags);
@@ -149,6 +157,10 @@ private:
   /// Otherwise report an error and return true.
   bool expectAndConsume(MIToken::TokenKind TokenKind);
 
+  /// If the current token is of the given kind, consume it and return true.
+  /// Otherwise return false.
+  bool consumeIfPresent(MIToken::TokenKind TokenKind);
+
   void initNames2InstrOpCodes();
 
   /// Try to convert an instruction name to an opcode. Return true if the
@@ -217,10 +229,17 @@ bool MIParser::error(const Twine &Msg) { return error(Token.location(), Msg); }
 
 bool MIParser::error(StringRef::iterator Loc, const Twine &Msg) {
   assert(Loc >= Source.data() && Loc <= (Source.data() + Source.size()));
-  Error = SMDiagnostic(
-      SM, SMLoc(),
-      SM.getMemoryBuffer(SM.getMainFileID())->getBufferIdentifier(), 1,
-      Loc - Source.data(), SourceMgr::DK_Error, Msg.str(), Source, None, None);
+  const MemoryBuffer &Buffer = *SM.getMemoryBuffer(SM.getMainFileID());
+  if (Loc >= Buffer.getBufferStart() && Loc <= Buffer.getBufferEnd()) {
+    // Create an ordinary diagnostic when the source manager's buffer is the
+    // source string.
+    Error = SM.GetMessage(SMLoc::getFromPointer(Loc), SourceMgr::DK_Error, Msg);
+    return true;
+  }
+  // Create a diagnostic for a YAML string literal.
+  Error = SMDiagnostic(SM, SMLoc(), Buffer.getBufferIdentifier(), 1,
+                       Loc - Source.data(), SourceMgr::DK_Error, Msg.str(),
+                       Source, None, None);
   return true;
 }
 
@@ -230,6 +249,8 @@ static const char *toString(MIToken::TokenKind TokenKind) {
     return "','";
   case MIToken::equal:
     return "'='";
+  case MIToken::colon:
+    return "':'";
   case MIToken::lparen:
     return "'('";
   case MIToken::rparen:
@@ -246,9 +267,236 @@ bool MIParser::expectAndConsume(MIToken::TokenKind TokenKind) {
   return false;
 }
 
-bool MIParser::parse(MachineInstr *&MI) {
+bool MIParser::consumeIfPresent(MIToken::TokenKind TokenKind) {
+  if (Token.isNot(TokenKind))
+    return false;
+  lex();
+  return true;
+}
+
+bool MIParser::parseBasicBlockDefinition(
+    DenseMap<unsigned, MachineBasicBlock *> &MBBSlots) {
+  assert(Token.is(MIToken::MachineBasicBlockLabel));
+  unsigned ID = 0;
+  if (getUnsigned(ID))
+    return true;
+  auto Loc = Token.location();
+  auto Name = Token.stringValue();
+  lex();
+  bool HasAddressTaken = false;
+  bool IsLandingPad = false;
+  unsigned Alignment = 0;
+  BasicBlock *BB = nullptr;
+  if (consumeIfPresent(MIToken::lparen)) {
+    do {
+      // TODO: Report an error when multiple same attributes are specified.
+      switch (Token.kind()) {
+      case MIToken::kw_address_taken:
+        HasAddressTaken = true;
+        lex();
+        break;
+      case MIToken::kw_landing_pad:
+        IsLandingPad = true;
+        lex();
+        break;
+      case MIToken::kw_align:
+        if (parseAlignment(Alignment))
+          return true;
+        break;
+      case MIToken::IRBlock:
+        // TODO: Report an error when both name and ir block are specified.
+        if (parseIRBlock(BB, *MF.getFunction()))
+          return true;
+        lex();
+        break;
+      default:
+        break;
+      }
+    } while (consumeIfPresent(MIToken::comma));
+    if (expectAndConsume(MIToken::rparen))
+      return true;
+  }
+  if (expectAndConsume(MIToken::colon))
+    return true;
+
+  if (!Name.empty()) {
+    BB = dyn_cast_or_null<BasicBlock>(
+        MF.getFunction()->getValueSymbolTable().lookup(Name));
+    if (!BB)
+      return error(Loc, Twine("basic block '") + Name +
+                            "' is not defined in the function '" +
+                            MF.getName() + "'");
+  }
+  auto *MBB = MF.CreateMachineBasicBlock(BB);
+  MF.insert(MF.end(), MBB);
+  bool WasInserted = MBBSlots.insert(std::make_pair(ID, MBB)).second;
+  if (!WasInserted)
+    return error(Loc, Twine("redefinition of machine basic block with id #") +
+                          Twine(ID));
+  if (Alignment)
+    MBB->setAlignment(Alignment);
+  if (HasAddressTaken)
+    MBB->setHasAddressTaken();
+  MBB->setIsLandingPad(IsLandingPad);
+  return false;
+}
+
+bool MIParser::parseBasicBlockDefinitions(
+    DenseMap<unsigned, MachineBasicBlock *> &MBBSlots) {
+  lex();
+  // Skip until the first machine basic block.
+  while (Token.is(MIToken::Newline))
+    lex();
+  if (Token.isErrorOrEOF())
+    return Token.isError();
+  if (Token.isNot(MIToken::MachineBasicBlockLabel))
+    return error("expected a basic block definition before instructions");
+  do {
+    if (parseBasicBlockDefinition(MBBSlots))
+      return true;
+    bool IsAfterNewline = false;
+    // Skip until the next machine basic block.
+    while (true) {
+      if ((Token.is(MIToken::MachineBasicBlockLabel) && IsAfterNewline) ||
+          Token.isErrorOrEOF())
+        break;
+      else if (Token.is(MIToken::MachineBasicBlockLabel))
+        return error("basic block definition should be located at the start of "
+                     "the line");
+      if (Token.is(MIToken::Newline))
+        IsAfterNewline = true;
+      else
+        IsAfterNewline = false;
+      lex();
+    }
+  } while (!Token.isErrorOrEOF());
+  return Token.isError();
+}
+
+bool MIParser::parseBasicBlockLiveins(MachineBasicBlock &MBB) {
+  assert(Token.is(MIToken::kw_liveins));
+  lex();
+  if (expectAndConsume(MIToken::colon))
+    return true;
+  if (Token.isNewlineOrEOF()) // Allow an empty list of liveins.
+    return false;
+  do {
+    if (Token.isNot(MIToken::NamedRegister))
+      return error("expected a named register");
+    unsigned Reg = 0;
+    if (parseRegister(Reg))
+      return true;
+    MBB.addLiveIn(Reg);
+    lex();
+  } while (consumeIfPresent(MIToken::comma));
+  return false;
+}
+
+bool MIParser::parseBasicBlockSuccessors(MachineBasicBlock &MBB) {
+  assert(Token.is(MIToken::kw_successors));
   lex();
+  if (expectAndConsume(MIToken::colon))
+    return true;
+  if (Token.isNewlineOrEOF()) // Allow an empty list of successors.
+    return false;
+  do {
+    if (Token.isNot(MIToken::MachineBasicBlock))
+      return error("expected a machine basic block reference");
+    MachineBasicBlock *SuccMBB = nullptr;
+    if (parseMBBReference(SuccMBB))
+      return true;
+    lex();
+    unsigned Weight = 0;
+    if (consumeIfPresent(MIToken::lparen)) {
+      if (Token.isNot(MIToken::IntegerLiteral))
+        return error("expected an integer literal after '('");
+      if (getUnsigned(Weight))
+        return true;
+      lex();
+      if (expectAndConsume(MIToken::rparen))
+        return true;
+    }
+    MBB.addSuccessor(SuccMBB, Weight);
+  } while (consumeIfPresent(MIToken::comma));
+  return false;
+}
+
+bool MIParser::parseBasicBlock(MachineBasicBlock &MBB) {
+  // Skip the definition.
+  assert(Token.is(MIToken::MachineBasicBlockLabel));
+  lex();
+  if (consumeIfPresent(MIToken::lparen)) {
+    while (Token.isNot(MIToken::rparen) && !Token.isErrorOrEOF())
+      lex();
+    consumeIfPresent(MIToken::rparen);
+  }
+  consumeIfPresent(MIToken::colon);
+
+  // Parse the liveins and successors.
+  // N.B: Multiple lists of successors and liveins are allowed and they're
+  // merged into one.
+  // Example:
+  //   liveins: %edi
+  //   liveins: %esi
+  //
+  // is equivalent to
+  //   liveins: %edi, %esi
+  while (true) {
+    if (Token.is(MIToken::kw_successors)) {
+      if (parseBasicBlockSuccessors(MBB))
+        return true;
+    } else if (Token.is(MIToken::kw_liveins)) {
+      if (parseBasicBlockLiveins(MBB))
+        return true;
+    } else if (consumeIfPresent(MIToken::Newline)) {
+      continue;
+    } else
+      break;
+    if (!Token.isNewlineOrEOF())
+      return error("expected line break at the end of a list");
+    lex();
+  }
+
+  // Parse the instructions.
+  while (true) {
+    if (Token.is(MIToken::MachineBasicBlockLabel) || Token.is(MIToken::Eof))
+      return false;
+    else if (consumeIfPresent(MIToken::Newline))
+      continue;
+    MachineInstr *MI = nullptr;
+    if (parse(MI))
+      return true;
+    MBB.insert(MBB.end(), MI);
+    assert(Token.isNewlineOrEOF() && "MI is not fully parsed");
+    lex();
+  }
+  return false;
+}
+
+bool MIParser::parseBasicBlocks() {
+  lex();
+  // Skip until the first machine basic block.
+  while (Token.is(MIToken::Newline))
+    lex();
+  if (Token.isErrorOrEOF())
+    return Token.isError();
+  // The first parsing pass should have verified that this token is a MBB label
+  // in the 'parseBasicBlockDefinitions' method.
+  assert(Token.is(MIToken::MachineBasicBlockLabel));
+  do {
+    MachineBasicBlock *MBB = nullptr;
+    if (parseMBBReference(MBB))
+      return true;
+    if (parseBasicBlock(*MBB))
+      return true;
+    // The method 'parseBasicBlock' should parse the whole block until the next
+    // block or the end of file.
+    assert(Token.is(MIToken::MachineBasicBlockLabel) || Token.is(MIToken::Eof));
+  } while (Token.isNot(MIToken::Eof));
+  return false;
+}
 
+bool MIParser::parse(MachineInstr *&MI) {
   // Parse any register operands before '='
   MachineOperand MO = MachineOperand::CreateImm(0);
   SmallVector<MachineOperandWithLocation, 8> Operands;
@@ -271,13 +519,13 @@ bool MIParser::parse(MachineInstr *&MI) {
   // TODO: Parse the bundle instruction flags.
 
   // Parse the remaining machine operands.
-  while (Token.isNot(MIToken::Eof) && Token.isNot(MIToken::kw_debug_location) &&
+  while (!Token.isNewlineOrEOF() && Token.isNot(MIToken::kw_debug_location) &&
          Token.isNot(MIToken::coloncolon)) {
     auto Loc = Token.location();
     if (parseMachineOperandAndTargetFlags(MO))
       return true;
     Operands.push_back(MachineOperandWithLocation(MO, Loc, Token.location()));
-    if (Token.is(MIToken::Eof) || Token.is(MIToken::coloncolon))
+    if (Token.isNewlineOrEOF() || Token.is(MIToken::coloncolon))
       break;
     if (Token.isNot(MIToken::comma))
       return error("expected ',' before the next machine operand");
@@ -299,12 +547,12 @@ bool MIParser::parse(MachineInstr *&MI) {
   SmallVector<MachineMemOperand *, 2> MemOperands;
   if (Token.is(MIToken::coloncolon)) {
     lex();
-    while (Token.isNot(MIToken::Eof)) {
+    while (!Token.isNewlineOrEOF()) {
       MachineMemOperand *MemOp = nullptr;
       if (parseMachineMemoryOperand(MemOp))
         return true;
       MemOperands.push_back(MemOp);
-      if (Token.is(MIToken::Eof))
+      if (Token.isNewlineOrEOF())
         break;
       if (Token.isNot(MIToken::comma))
         return error("expected ',' before the next machine memory operand");
@@ -370,23 +618,6 @@ bool MIParser::parseStandaloneVirtualRegister(unsigned &Reg) {
   return false;
 }
 
-bool MIParser::parseStandaloneIRBlockReference(const BasicBlock *&BB) {
-  lex();
-  if (Token.isNot(MIToken::IRBlock))
-    return error("expected an IR block reference");
-  unsigned SlotNumber = 0;
-  if (getUnsigned(SlotNumber))
-    return true;
-  BB = getIRBlock(SlotNumber);
-  if (!BB)
-    return error(Twine("use of undefined IR block '%ir-block.") +
-                 Twine(SlotNumber) + "'");
-  lex();
-  if (Token.isNot(MIToken::Eof))
-    return error("expected end of string after the IR block reference");
-  return false;
-}
-
 static const char *printImplicitRegisterFlag(const MachineOperand &MO) {
   assert(MO.isImplicit());
   return MO.isDef() ? "implicit-def" : "implicit";
@@ -621,7 +852,8 @@ bool MIParser::getUnsigned(unsigned &Result) {
 }
 
 bool MIParser::parseMBBReference(MachineBasicBlock *&MBB) {
-  assert(Token.is(MIToken::MachineBasicBlock));
+  assert(Token.is(MIToken::MachineBasicBlock) ||
+         Token.is(MIToken::MachineBasicBlockLabel));
   unsigned Number;
   if (getUnsigned(Number))
     return true;
@@ -1406,11 +1638,27 @@ bool MIParser::getDirectTargetFlag(StringRef Name, unsigned &Flag) {
   return false;
 }
 
-bool llvm::parseMachineInstr(MachineInstr *&MI, SourceMgr &SM,
-                             MachineFunction &MF, StringRef Src,
-                             const PerFunctionMIParsingState &PFS,
-                             const SlotMapping &IRSlots, SMDiagnostic &Error) {
-  return MIParser(SM, MF, Error, Src, PFS, IRSlots).parse(MI);
+bool llvm::parseMachineBasicBlockDefinitions(MachineFunction &MF, StringRef Src,
+                                             PerFunctionMIParsingState &PFS,
+                                             const SlotMapping &IRSlots,
+                                             SMDiagnostic &Error) {
+  SourceMgr SM;
+  SM.AddNewSourceBuffer(
+      MemoryBuffer::getMemBuffer(Src, "", /*RequiresNullTerminator=*/false),
+      SMLoc());
+  return MIParser(SM, MF, Error, Src, PFS, IRSlots)
+      .parseBasicBlockDefinitions(PFS.MBBSlots);
+}
+
+bool llvm::parseMachineInstructions(MachineFunction &MF, StringRef Src,
+                                    const PerFunctionMIParsingState &PFS,
+                                    const SlotMapping &IRSlots,
+                                    SMDiagnostic &Error) {
+  SourceMgr SM;
+  SM.AddNewSourceBuffer(
+      MemoryBuffer::getMemBuffer(Src, "", /*RequiresNullTerminator=*/false),
+      SMLoc());
+  return MIParser(SM, MF, Error, Src, PFS, IRSlots).parseBasicBlocks();
 }
 
 bool llvm::parseMBBReference(MachineBasicBlock *&MBB, SourceMgr &SM,
@@ -1437,12 +1685,3 @@ bool llvm::parseVirtualRegisterReference(unsigned &Reg, SourceMgr &SM,
   return MIParser(SM, MF, Error, Src, PFS, IRSlots)
       .parseStandaloneVirtualRegister(Reg);
 }
-
-bool llvm::parseIRBlockReference(const BasicBlock *&BB, SourceMgr &SM,
-                                 MachineFunction &MF, StringRef Src,
-                                 const PerFunctionMIParsingState &PFS,
-                                 const SlotMapping &IRSlots,
-                                 SMDiagnostic &Error) {
-  return MIParser(SM, MF, Error, Src, PFS, IRSlots)
-      .parseStandaloneIRBlockReference(BB);
-}
diff --git a/llvm/lib/CodeGen/MIRParser/MIParser.h b/llvm/lib/CodeGen/MIRParser/MIParser.h
index 92698f6e6d1..03408991f7c 100644
--- a/llvm/lib/CodeGen/MIRParser/MIParser.h
+++ b/llvm/lib/CodeGen/MIRParser/MIParser.h
@@ -36,9 +36,36 @@ struct PerFunctionMIParsingState {
   DenseMap<unsigned, unsigned> JumpTableSlots;
 };
 
-bool parseMachineInstr(MachineInstr *&MI, SourceMgr &SM, MachineFunction &MF,
-                       StringRef Src, const PerFunctionMIParsingState &PFS,
-                       const SlotMapping &IRSlots, SMDiagnostic &Error);
+/// Parse the machine basic block definitions, and skip the machine
+/// instructions.
+///
+/// This function runs the first parsing pass on the machine function's body.
+/// It parses only the machine basic block definitions and creates the machine
+/// basic blocks in the given machine function.
+///
+/// The machine instructions aren't parsed during the first pass because all
+/// the machine basic blocks aren't defined yet - this makes it impossible to
+/// resolve the machine basic block references.
+///
+/// Return true if an error occurred.
+bool parseMachineBasicBlockDefinitions(MachineFunction &MF, StringRef Src,
+                                       PerFunctionMIParsingState &PFS,
+                                       const SlotMapping &IRSlots,
+                                       SMDiagnostic &Error);
+
+/// Parse the machine instructions.
+///
+/// This function runs the second parsing pass on the machine function's body.
+/// It skips the machine basic block definitions and parses only the machine
+/// instructions and basic block attributes like liveins and successors.
+///
+/// The second parsing pass assumes that the first parsing pass already ran
+/// on the given source string.
+///
+/// Return true if an error occurred.
+bool parseMachineInstructions(MachineFunction &MF, StringRef Src,
+                              const PerFunctionMIParsingState &PFS,
+                              const SlotMapping &IRSlots, SMDiagnostic &Error);
 
 bool parseMBBReference(MachineBasicBlock *&MBB, SourceMgr &SM,
                        MachineFunction &MF, StringRef Src,
@@ -57,11 +84,6 @@ bool parseVirtualRegisterReference(unsigned &Reg, SourceMgr &SM,
                                    const SlotMapping &IRSlots,
                                    SMDiagnostic &Error);
 
-bool parseIRBlockReference(const BasicBlock *&BB, SourceMgr &SM,
-                           MachineFunction &MF, StringRef Src,
-                           const PerFunctionMIParsingState &PFS,
-                           const SlotMapping &IRSlots, SMDiagnostic &Error);
-
 } // end namespace llvm
 
 #endif
diff --git a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
index a9cbbc390d7..a0279fa7119 100644
--- a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
@@ -96,13 +96,6 @@ public:
   /// Return true if error occurred.
   bool initializeMachineFunction(MachineFunction &MF);
 
-  /// Initialize the machine basic block using it's YAML representation.
-  ///
-  /// Return true if an error occurred.
-  bool initializeMachineBasicBlock(MachineFunction &MF, MachineBasicBlock &MBB,
-                                   const yaml::MachineBasicBlock &YamlMBB,
-                                   const PerFunctionMIParsingState &PFS);
-
   bool initializeRegisterInfo(MachineFunction &MF,
                               const yaml::MachineFunction &YamlMF,
                               PerFunctionMIParsingState &PFS);
@@ -294,36 +287,15 @@ bool MIRParserImpl::initializeMachineFunction(MachineFunction &MF) {
       return true;
   }
 
-  const auto &F = *MF.getFunction();
-  for (const auto &YamlMBB : YamlMF.BasicBlocks) {
-    const BasicBlock *BB = nullptr;
-    const yaml::StringValue &Name = YamlMBB.Name;
-    const yaml::StringValue &IRBlock = YamlMBB.IRBlock;
-    if (!Name.Value.empty()) {
-      BB = dyn_cast_or_null<BasicBlock>(
-          F.getValueSymbolTable().lookup(Name.Value));
-      if (!BB)
-        return error(Name.SourceRange.Start,
-                     Twine("basic block '") + Name.Value +
-                         "' is not defined in the function '" + MF.getName() +
-                         "'");
-    }
-    if (!IRBlock.Value.empty()) {
-      // TODO: Report an error when both name and ir block are specified.
-      SMDiagnostic Error;
-      if (parseIRBlockReference(BB, SM, MF, IRBlock.Value, PFS, IRSlots, Error))
-        return error(Error, IRBlock.SourceRange);
-    }
-    auto *MBB = MF.CreateMachineBasicBlock(BB);
-    MF.insert(MF.end(), MBB);
-    bool WasInserted =
-        PFS.MBBSlots.insert(std::make_pair(YamlMBB.ID, MBB)).second;
-    if (!WasInserted)
-      return error(Twine("redefinition of machine basic block with id #") +
-                   Twine(YamlMBB.ID));
+  SMDiagnostic Error;
+  if (parseMachineBasicBlockDefinitions(MF, YamlMF.Body.Value.Value, PFS,
+                                        IRSlots, Error)) {
+    reportDiagnostic(
+        diagFromBlockStringDiag(Error, YamlMF.Body.Value.SourceRange));
+    return true;
   }
 
-  if (YamlMF.BasicBlocks.empty())
+  if (MF.empty())
     return error(Twine("machine function '") + Twine(MF.getName()) +
                  "' requires at least one machine basic block in its body");
   // Initialize the frame information after creating all the MBBs so that the
@@ -335,13 +307,13 @@ bool MIRParserImpl::initializeMachineFunction(MachineFunction &MF) {
   if (!YamlMF.JumpTableInfo.Entries.empty() &&
       initializeJumpTableInfo(MF, YamlMF.JumpTableInfo, PFS))
     return true;
-  // Initialize the machine basic blocks after creating them all so that the
-  // machine instructions parser can resolve the MBB references.
-  unsigned I = 0;
-  for (const auto &YamlMBB : YamlMF.BasicBlocks) {
-    if (initializeMachineBasicBlock(MF, *MF.getBlockNumbered(I++), YamlMBB,
-                                    PFS))
-      return true;
+  // Parse the machine instructions after creating all of the MBBs so that the
+  // parser can resolve the MBB references.
+  if (parseMachineInstructions(MF, YamlMF.Body.Value.Value, PFS, IRSlots,
+                               Error)) {
+    reportDiagnostic(
+        diagFromBlockStringDiag(Error, YamlMF.Body.Value.SourceRange));
+    return true;
   }
   inferRegisterInfo(MF, YamlMF);
   // FIXME: This is a temporary workaround until the reserved registers can be
@@ -351,53 +323,6 @@ bool MIRParserImpl::initializeMachineFunction(MachineFunction &MF) {
   return false;
 }
 
-bool MIRParserImpl::initializeMachineBasicBlock(
-    MachineFunction &MF, MachineBasicBlock &MBB,
-    const yaml::MachineBasicBlock &YamlMBB,
-    const PerFunctionMIParsingState &PFS) {
-  MBB.setAlignment(YamlMBB.Alignment);
-  if (YamlMBB.AddressTaken)
-    MBB.setHasAddressTaken();
-  MBB.setIsLandingPad(YamlMBB.IsLandingPad);
-  SMDiagnostic Error;
-  // Parse the successors.
-  const auto &Weights = YamlMBB.SuccessorWeights;
-  bool HasWeights = !Weights.empty();
-  if (HasWeights && Weights.size() != YamlMBB.Successors.size()) {
-    bool IsFew = Weights.size() < YamlMBB.Successors.size();
-    return error(IsFew ? Weights.back().SourceRange.End
-                       : Weights[YamlMBB.Successors.size()].SourceRange.Start,
-                 Twine("too ") + (IsFew ? "few" : "many") +
-                     " successor weights, expected " +
-                     Twine(YamlMBB.Successors.size()) + ", have " +
-                     Twine(Weights.size()));
-  }
-  size_t SuccessorIndex = 0;
-  for (const auto &MBBSource : YamlMBB.Successors) {
-    MachineBasicBlock *SuccMBB = nullptr;
-    if (parseMBBReference(SuccMBB, MBBSource, MF, PFS))
-      return true;
-    // TODO: Report an error when adding the same successor more than once.
-    MBB.addSuccessor(SuccMBB, HasWeights ? Weights[SuccessorIndex++].Value : 0);
-  }
-  // Parse the liveins.
-  for (const auto &LiveInSource : YamlMBB.LiveIns) {
-    unsigned Reg = 0;
-    if (parseNamedRegisterReference(Reg, SM, MF, LiveInSource.Value, PFS,
-                                    IRSlots, Error))
-      return error(Error, LiveInSource.SourceRange);
-    MBB.addLiveIn(Reg);
-  }
-  // Parse the instructions.
-  for (const auto &MISource : YamlMBB.Instructions) {
-    MachineInstr *MI = nullptr;
-    if (parseMachineInstr(MI, SM, MF, MISource.Value, PFS, IRSlots, Error))
-      return error(Error, MISource.SourceRange);
-    MBB.insert(MBB.end(), MI);
-  }
-  return false;
-}
-
 bool MIRParserImpl::initializeRegisterInfo(MachineFunction &MF,
                                            const yaml::MachineFunction &YamlMF,
                                            PerFunctionMIParsingState &PFS) {