llvm-6502/lib/Target/X86/AsmParser/X86AsmParser.cpp

477 lines
14 KiB
C++
Raw Normal View History

//===-- 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);
bool ParseOperand(X86Operand &Op);
bool ParseMemOperand(X86Operand &Op);
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 {
Token,
Register,
Immediate,
Memory
} Kind;
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;
};
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) {
X86Operand Res;
Res.Kind = Token;
Res.Tok.Data = Str.data();
Res.Tok.Length = Str.size();
return Res;
}
static X86Operand CreateReg(unsigned RegNo) {
X86Operand Res;
Res.Kind = Register;
Res.Reg.RegNo = RegNo;
return Res;
}
static X86Operand CreateImm(const MCExpr *Val) {
X86Operand Res;
Res.Kind = Immediate;
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;
Res.Kind = 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) {
RegNo = 0;
const AsmToken &TokPercent = getLexer().getTok();
(void)TokPercent; // Avoid warning when assertions are disabled.
assert(TokPercent.is(AsmToken::Percent) && "Invalid token kind!");
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");
getLexer().Lex(); // Eat identifier token.
return false;
}
bool X86ATTAsmParser::ParseOperand(X86Operand &Op) {
switch (getLexer().getKind()) {
default:
return ParseMemOperand(Op);
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;
if (ParseRegister(RegNo)) return true;
Op = X86Operand::CreateReg(RegNo);
return false;
}
case AsmToken::Dollar: {
// $42 -> immediate.
getLexer().Lex();
const MCExpr *Val;
if (getParser().ParseExpression(Val))
return true;
Op = X86Operand::CreateImm(Val);
return false;
}
}
}
/// ParseMemOperand: segment: disp(basereg, indexreg, scale)
bool X86ATTAsmParser::ParseMemOperand(X86Operand &Op) {
// 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)) {
if (getParser().ParseExpression(Disp)) return true;
// 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)
Op = X86Operand::CreateMem(SegReg, Disp, 0, 0, 1);
else
Op = X86Operand::CreateImm(Disp);
return false;
}
// 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.
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 {
// It must be an parenthesized expression, parse it now.
if (getParser().ParseParenExpression(Disp))
return true;
// 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)
Op = X86Operand::CreateMem(SegReg, Disp, 0, 0, 1);
else
Op = X86Operand::CreateImm(Disp);
return false;
}
// 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))
if (ParseRegister(BaseReg)) return true;
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)) {
if (ParseRegister(IndexReg)) return true;
if (getLexer().isNot(AsmToken::RParen)) {
// Parse the scale amount:
// ::= ',' [scale-expression]
if (getLexer().isNot(AsmToken::Comma))
return true;
getLexer().Lex(); // Eat the comma.
if (getLexer().isNot(AsmToken::RParen)) {
SMLoc Loc = getLexer().getTok().getLoc();
int64_t ScaleVal;
if (getParser().ParseAbsoluteExpression(ScaleVal))
return true;
// Validate the scale amount.
if (ScaleVal != 1 && ScaleVal != 2 && ScaleVal != 4 && ScaleVal != 8)
return Error(Loc, "scale factor in address must be 1, 2, 4 or 8");
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 true;
return Error(Loc, "cannot have scale factor without index register");
}
}
// Ok, we've eaten the memory operand, verify we have a ')' and eat it too.
if (getLexer().isNot(AsmToken::RParen))
return Error(getLexer().getTok().getLoc(),
"unexpected token in memory operand");
getLexer().Lex(); // Eat the ')'.
Op = X86Operand::CreateMem(SegReg, Disp, BaseReg, IndexReg, Scale);
return false;
}
bool X86ATTAsmParser::
ParseInstruction(const StringRef &Name, SMLoc NameLoc,
SmallVectorImpl<MCParsedAsmOperand*> &Operands) {
Operands.push_back(new X86Operand(X86Operand::CreateToken(Name)));
SMLoc Loc = getLexer().getTok().getLoc();
if (getLexer().isNot(AsmToken::EndOfStatement)) {
// Parse '*' modifier.
if (getLexer().is(AsmToken::Star)) {
getLexer().Lex(); // Eat the star.
Operands.push_back(new X86Operand(X86Operand::CreateToken("*")));
}
// Read the first operand.
X86Operand Op;
if (ParseOperand(Op))
return true;
Operands.push_back(new X86Operand(Op));
while (getLexer().is(AsmToken::Comma)) {
getLexer().Lex(); // Eat the comma.
// Parse and remember the operand.
if (ParseOperand(Op))
return true;
Operands.push_back(new X86Operand(Op));
}
}
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"