lib/Target/X86/AsmParser/X86AsmParser.cpp

//===-- X86AsmParser.cpp - Parse X86 assembly to MCInst instructions ------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

#include "llvm/Target/TargetAsmParser.h"
#include "X86.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Twine.h"
#include "llvm/MC/MCAsmLexer.h"
#include "llvm/MC/MCAsmParser.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCExpr.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCParsedAsmOperand.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Target/TargetRegistry.h"
#include "llvm/Target/TargetAsmParser.h"
using namespace llvm;

namespace {
struct X86Operand;

class X86ATTAsmParser : public TargetAsmParser {
  MCAsmParser &Parser;

private:
  MCAsmParser &getParser() const { return Parser; }

  MCAsmLexer &getLexer() const { return Parser.getLexer(); }

  void Warning(SMLoc L, const Twine &Msg) { Parser.Warning(L, Msg); }

  bool Error(SMLoc L, const Twine &Msg) { return Parser.Error(L, Msg); }

  bool ParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc);

  X86Operand *ParseOperand();
  X86Operand *ParseMemOperand();

  bool ParseDirectiveWord(unsigned Size, SMLoc L);

  /// @name Auto-generated Match Functions
  /// {  

  bool MatchInstruction(const SmallVectorImpl<MCParsedAsmOperand*> &Operands,
                        MCInst &Inst);

  /// MatchRegisterName - Match the given string to a register name, or 0 if
  /// there is no match.
  unsigned MatchRegisterName(const StringRef &Name);

  /// }

public:
  X86ATTAsmParser(const Target &T, MCAsmParser &_Parser)
    : TargetAsmParser(T), Parser(_Parser) {}

  virtual bool ParseInstruction(const StringRef &Name, SMLoc NameLoc,
                                SmallVectorImpl<MCParsedAsmOperand*> &Operands);

  virtual bool ParseDirective(AsmToken DirectiveID);
};
  
} // end anonymous namespace


namespace {

/// X86Operand - Instances of this class represent a parsed X86 machine
/// instruction.
struct X86Operand : public MCParsedAsmOperand {
  enum KindTy {
    Token,
    Register,
    Immediate,
    Memory
  } Kind;

  SMLoc StartLoc, EndLoc;
  
  union {
    struct {
      const char *Data;
      unsigned Length;
    } Tok;

    struct {
      unsigned RegNo;
    } Reg;

    struct {
      const MCExpr *Val;
    } Imm;

    struct {
      unsigned SegReg;
      const MCExpr *Disp;
      unsigned BaseReg;
      unsigned IndexReg;
      unsigned Scale;
    } Mem;
  };

  X86Operand(KindTy K, SMLoc Start = SMLoc(), SMLoc End = SMLoc())
    : Kind(K), StartLoc(Start), EndLoc(End) {}
  
  /// getStartLoc - Get the location of the first token of this operand.
  SMLoc getStartLoc() const { return StartLoc; }
  /// getEndLoc - Get the location of the last token of this operand.
  SMLoc getEndLoc() const { return EndLoc; }

  StringRef getToken() const {
    assert(Kind == Token && "Invalid access!");
    return StringRef(Tok.Data, Tok.Length);
  }

  unsigned getReg() const {
    assert(Kind == Register && "Invalid access!");
    return Reg.RegNo;
  }

  const MCExpr *getImm() const {
    assert(Kind == Immediate && "Invalid access!");
    return Imm.Val;
  }

  const MCExpr *getMemDisp() const {
    assert(Kind == Memory && "Invalid access!");
    return Mem.Disp;
  }
  unsigned getMemSegReg() const {
    assert(Kind == Memory && "Invalid access!");
    return Mem.SegReg;
  }
  unsigned getMemBaseReg() const {
    assert(Kind == Memory && "Invalid access!");
    return Mem.BaseReg;
  }
  unsigned getMemIndexReg() const {
    assert(Kind == Memory && "Invalid access!");
    return Mem.IndexReg;
  }
  unsigned getMemScale() const {
    assert(Kind == Memory && "Invalid access!");
    return Mem.Scale;
  }

  bool isToken() const {return Kind == Token; }

  bool isImm() const { return Kind == Immediate; }
  
  bool isImmSExt8() const { 
    // Accept immediates which fit in 8 bits when sign extended, and
    // non-absolute immediates.
    if (!isImm())
      return false;

    if (const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(getImm())) {
      int64_t Value = CE->getValue();
      return Value == (int64_t) (int8_t) Value;
    }

    return true;
  }
  
  bool isMem() const { return Kind == Memory; }

  bool isReg() const { return Kind == Register; }

  void addRegOperands(MCInst &Inst, unsigned N) const {
    assert(N == 1 && "Invalid number of operands!");
    Inst.addOperand(MCOperand::CreateReg(getReg()));
  }

  void addImmOperands(MCInst &Inst, unsigned N) const {
    assert(N == 1 && "Invalid number of operands!");
    Inst.addOperand(MCOperand::CreateExpr(getImm()));
  }

  void addImmSExt8Operands(MCInst &Inst, unsigned N) const {
    // FIXME: Support user customization of the render method.
    assert(N == 1 && "Invalid number of operands!");
    Inst.addOperand(MCOperand::CreateExpr(getImm()));
  }

  void addMemOperands(MCInst &Inst, unsigned N) const {
    assert((N == 4 || N == 5) && "Invalid number of operands!");

    Inst.addOperand(MCOperand::CreateReg(getMemBaseReg()));
    Inst.addOperand(MCOperand::CreateImm(getMemScale()));
    Inst.addOperand(MCOperand::CreateReg(getMemIndexReg()));
    Inst.addOperand(MCOperand::CreateExpr(getMemDisp()));

    // FIXME: What a hack.
    if (N == 5)
      Inst.addOperand(MCOperand::CreateReg(getMemSegReg()));
  }

  static X86Operand *CreateToken(StringRef Str, SMLoc Loc) {
    X86Operand *Res = new X86Operand(Token, Loc, Loc);
    Res->Tok.Data = Str.data();
    Res->Tok.Length = Str.size();
    return Res;
  }

  static X86Operand *CreateReg(unsigned RegNo, SMLoc StartLoc, SMLoc EndLoc) {
    X86Operand *Res = new X86Operand(Register, StartLoc, EndLoc);
    Res->Reg.RegNo = RegNo;
    return Res;
  }

  static X86Operand *CreateImm(const MCExpr *Val, SMLoc StartLoc, SMLoc EndLoc){
    X86Operand *Res = new X86Operand(Immediate, StartLoc, EndLoc);
    Res->Imm.Val = Val;
    return Res;
  }

  static X86Operand *CreateMem(unsigned SegReg, const MCExpr *Disp,
                               unsigned BaseReg, unsigned IndexReg,
                               unsigned Scale) {
    // We should never just have a displacement, that would be an immediate.
    assert((SegReg || BaseReg || IndexReg) && "Invalid memory operand!");

    // The scale should always be one of {1,2,4,8}.
    assert(((Scale == 1 || Scale == 2 || Scale == 4 || Scale == 8)) &&
           "Invalid scale!");
    X86Operand *Res = new X86Operand(Memory);
    Res->Mem.SegReg   = SegReg;
    Res->Mem.Disp     = Disp;
    Res->Mem.BaseReg  = BaseReg;
    Res->Mem.IndexReg = IndexReg;
    Res->Mem.Scale    = Scale;
    return Res;
  }
};

} // end anonymous namespace.


bool X86ATTAsmParser::ParseRegister(unsigned &RegNo,
                                    SMLoc &StartLoc, SMLoc &EndLoc) {
  RegNo = 0;
  const AsmToken &TokPercent = getLexer().getTok();
  assert(TokPercent.is(AsmToken::Percent) && "Invalid token kind!");
  StartLoc = TokPercent.getLoc();
  getLexer().Lex(); // Eat percent token.

  const AsmToken &Tok = getLexer().getTok();
  if (Tok.isNot(AsmToken::Identifier))
    return Error(Tok.getLoc(), "invalid register name");

  // FIXME: Validate register for the current architecture; we have to do
  // validation later, so maybe there is no need for this here.
  RegNo = MatchRegisterName(Tok.getString());
  if (RegNo == 0)
    return Error(Tok.getLoc(), "invalid register name");

  EndLoc = Tok.getLoc();
  getLexer().Lex(); // Eat identifier token.
  return false;
}

X86Operand *X86ATTAsmParser::ParseOperand() {
  switch (getLexer().getKind()) {
  default:
    return ParseMemOperand();
  case AsmToken::Percent: {
    // FIXME: if a segment register, this could either be just the seg reg, or
    // the start of a memory operand.
    unsigned RegNo;
    SMLoc Start, End;
    if (ParseRegister(RegNo, Start, End)) return 0;
    return X86Operand::CreateReg(RegNo, Start, End);
  }
  case AsmToken::Dollar: {
    // $42 -> immediate.
    getLexer().Lex();
    const MCExpr *Val;
    SMLoc Start, End;
    if (getParser().ParseExpression(Val, Start, End))
      return 0;
    return X86Operand::CreateImm(Val, Start, End);
  }
  }
}

/// ParseMemOperand: segment: disp(basereg, indexreg, scale)
X86Operand *X86ATTAsmParser::ParseMemOperand() {
  // FIXME: If SegReg ':'  (e.g. %gs:), eat and remember.
  unsigned SegReg = 0;
  
  // We have to disambiguate a parenthesized expression "(4+5)" from the start
  // of a memory operand with a missing displacement "(%ebx)" or "(,%eax)".  The
  // only way to do this without lookahead is to eat the ( and see what is after
  // it.
  const MCExpr *Disp = MCConstantExpr::Create(0, getParser().getContext());
  if (getLexer().isNot(AsmToken::LParen)) {
    SMLoc ExprStart, ExprEnd;
    if (getParser().ParseExpression(Disp, ExprStart, ExprEnd)) return 0;
    
    // After parsing the base expression we could either have a parenthesized
    // memory address or not.  If not, return now.  If so, eat the (.
    if (getLexer().isNot(AsmToken::LParen)) {
      // Unless we have a segment register, treat this as an immediate.
      if (SegReg == 0)
        return X86Operand::CreateImm(Disp, ExprStart, ExprEnd);
      return X86Operand::CreateMem(SegReg, Disp, 0, 0, 1);
    }
    
    // Eat the '('.
    getLexer().Lex();
  } else {
    // Okay, we have a '('.  We don't know if this is an expression or not, but
    // so we have to eat the ( to see beyond it.
    SMLoc LParenLoc = getLexer().getTok().getLoc();
    getLexer().Lex(); // Eat the '('.
    
    if (getLexer().is(AsmToken::Percent) || getLexer().is(AsmToken::Comma)) {
      // Nothing to do here, fall into the code below with the '(' part of the
      // memory operand consumed.
    } else {
      SMLoc ExprEnd;
      
      // It must be an parenthesized expression, parse it now.
      if (getParser().ParseParenExpression(Disp, ExprEnd))
        return 0;
      
      // After parsing the base expression we could either have a parenthesized
      // memory address or not.  If not, return now.  If so, eat the (.
      if (getLexer().isNot(AsmToken::LParen)) {
        // Unless we have a segment register, treat this as an immediate.
        if (SegReg == 0)
          return X86Operand::CreateImm(Disp, LParenLoc, ExprEnd);
        return X86Operand::CreateMem(SegReg, Disp, 0, 0, 1);
      }
      
      // Eat the '('.
      getLexer().Lex();
    }
  }
  
  // If we reached here, then we just ate the ( of the memory operand.  Process
  // the rest of the memory operand.
  unsigned BaseReg = 0, IndexReg = 0, Scale = 1;
  
  if (getLexer().is(AsmToken::Percent)) {
    SMLoc L;
    if (ParseRegister(BaseReg, L, L)) return 0;
  }
  
  if (getLexer().is(AsmToken::Comma)) {
    getLexer().Lex(); // Eat the comma.

    // Following the comma we should have either an index register, or a scale
    // value. We don't support the later form, but we want to parse it
    // correctly.
    //
    // Not that even though it would be completely consistent to support syntax
    // like "1(%eax,,1)", the assembler doesn't.
    if (getLexer().is(AsmToken::Percent)) {
      SMLoc L;
      if (ParseRegister(IndexReg, L, L)) return 0;
    
      if (getLexer().isNot(AsmToken::RParen)) {
        // Parse the scale amount:
        //  ::= ',' [scale-expression]
        if (getLexer().isNot(AsmToken::Comma)) {
          Error(getLexer().getTok().getLoc(),
                "expected comma in scale expression");
          return 0;
        }
        getLexer().Lex(); // Eat the comma.

        if (getLexer().isNot(AsmToken::RParen)) {
          SMLoc Loc = getLexer().getTok().getLoc();

          int64_t ScaleVal;
          if (getParser().ParseAbsoluteExpression(ScaleVal))
            return 0;
          
          // Validate the scale amount.
          if (ScaleVal != 1 && ScaleVal != 2 && ScaleVal != 4 && ScaleVal != 8){
            Error(Loc, "scale factor in address must be 1, 2, 4 or 8");
            return 0;
          }
          Scale = (unsigned)ScaleVal;
        }
      }
    } else if (getLexer().isNot(AsmToken::RParen)) {
      // Otherwise we have the unsupported form of a scale amount without an
      // index.
      SMLoc Loc = getLexer().getTok().getLoc();

      int64_t Value;
      if (getParser().ParseAbsoluteExpression(Value))
        return 0;
      
      Error(Loc, "cannot have scale factor without index register");
      return 0;
    }
  }
  
  // Ok, we've eaten the memory operand, verify we have a ')' and eat it too.
  if (getLexer().isNot(AsmToken::RParen)) {
    Error(getLexer().getTok().getLoc(), "unexpected token in memory operand");
    return 0;
  }
  getLexer().Lex(); // Eat the ')'.
  
  return X86Operand::CreateMem(SegReg, Disp, BaseReg, IndexReg, Scale);
}

bool X86ATTAsmParser::
ParseInstruction(const StringRef &Name, SMLoc NameLoc,
                 SmallVectorImpl<MCParsedAsmOperand*> &Operands) {

  Operands.push_back(X86Operand::CreateToken(Name, NameLoc));

  if (getLexer().isNot(AsmToken::EndOfStatement)) {

    // Parse '*' modifier.
    if (getLexer().is(AsmToken::Star)) {
      SMLoc Loc = getLexer().getTok().getLoc();
      Operands.push_back(X86Operand::CreateToken("*", Loc));
      getLexer().Lex(); // Eat the star.
    }

    // Read the first operand.
    if (X86Operand *Op = ParseOperand())
      Operands.push_back(Op);
    else
      return true;
    
    while (getLexer().is(AsmToken::Comma)) {
      getLexer().Lex();  // Eat the comma.

      // Parse and remember the operand.
      if (X86Operand *Op = ParseOperand())
        Operands.push_back(Op);
      else
        return true;
    }
  }

  return false;
}

bool X86ATTAsmParser::ParseDirective(AsmToken DirectiveID) {
  StringRef IDVal = DirectiveID.getIdentifier();
  if (IDVal == ".word")
    return ParseDirectiveWord(2, DirectiveID.getLoc());
  return true;
}

/// ParseDirectiveWord
///  ::= .word [ expression (, expression)* ]
bool X86ATTAsmParser::ParseDirectiveWord(unsigned Size, SMLoc L) {
  if (getLexer().isNot(AsmToken::EndOfStatement)) {
    for (;;) {
      const MCExpr *Value;
      if (getParser().ParseExpression(Value))
        return true;

      getParser().getStreamer().EmitValue(Value, Size);

      if (getLexer().is(AsmToken::EndOfStatement))
        break;
      
      // FIXME: Improve diagnostic.
      if (getLexer().isNot(AsmToken::Comma))
        return Error(L, "unexpected token in directive");
      getLexer().Lex();
    }
  }

  getLexer().Lex();
  return false;
}

// Force static initialization.
extern "C" void LLVMInitializeX86AsmParser() {
  RegisterAsmParser<X86ATTAsmParser> X(TheX86_32Target);
  RegisterAsmParser<X86ATTAsmParser> Y(TheX86_64Target);
}

#include "X86GenAsmMatcher.inc"