summaryrefslogtreecommitdiffstats
path: root/lib/Target/X86/AsmParser/X86AsmParser.cpp
blob: c357b4d0dee1533c55a3a1cd4ba27e7123f8e8a7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
//===-- 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 "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/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(X86Operand &Op);

  bool ParseOperand(X86Operand &Op);

  bool ParseMemOperand(X86Operand &Op);

  bool ParseDirectiveWord(unsigned Size, SMLoc L);

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

  bool MatchInstruction(SmallVectorImpl<X86Operand> &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, MCInst &Inst);

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


namespace {

/// X86Operand - Instances of this class represent a parsed X86 machine
/// instruction.
struct X86Operand {
  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(X86Operand &Op) {
  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.
  unsigned RegNo;

  RegNo = MatchRegisterName(Tok.getString());
  if (RegNo == 0)
    return Error(Tok.getLoc(), "invalid register name");

  Op = X86Operand::CreateReg(RegNo);
  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.
    return ParseRegister(Op);
  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(Op))
      return true;
    BaseReg = Op.getReg();
  }
  
  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(Op))
        return true;
      IndexReg = Op.getReg();
    
      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, MCInst &Inst) {
  SmallVector<X86Operand, 8> Operands;

  Operands.push_back(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(X86Operand::CreateToken("*"));
    }

    // Read the first operand.
    Operands.push_back(X86Operand());
    if (ParseOperand(Operands.back()))
      return true;

    while (getLexer().is(AsmToken::Comma)) {
      getLexer().Lex();  // Eat the comma.

      // Parse and remember the operand.
      Operands.push_back(X86Operand());
      if (ParseOperand(Operands.back()))
        return true;
    }
  }

  if (!MatchInstruction(Operands, Inst))
    return false;

  // FIXME: We should give nicer diagnostics about the exact failure.

  Error(Loc, "unrecognized instruction");
  return true;
}

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"
OpenPOWER on IntegriCloud