[X86][MS-compatability] allow MS TYPE/SIZE/LENGTH operators as a part of a compound expression

[coby]

Summary

This patch introduces X86AsmParser with the ability to handle the aforementioned ops within compound "MS" arithmetical expressions. Currently - only supported as a stand alone Operand, e.g.:
"TYPE X"
now allowed :
"4 + TYPE X * 128"

Clang side: https://reviews.llvm.org/D31174

[rnk]

lgtm

lib/Target/X86/AsmParser/X86AsmParser.cpp

1791–1792

Add FIXME: here, since this should be addressed eventually.

lib/Target/X86/AsmParser/X86AsmParser.cpp

enum InfixCalculatorTok {
     IC_MULTIPLY,
     IC_DIVIDE,
     IC_RPAREN,
     IC_LPAREN,
     IC_IMM,
     IC_REGISTER
   };
 
+  enum IntelOperatorKind {
+    IOK_INVALID = 0,
+    IOK_LENGTH,
+    IOK_SIZE,
+    IOK_TYPE,
+    IOK_OFFSET
+  };
+
   class InfixCalculator {
     typedef std::pair< InfixCalculatorTok, int64_t > ICToken;
     SmallVector<InfixCalculatorTok, 4> InfixOperatorStack;
     SmallVector<ICToken, 4> PostfixStack;
 
   public:
     int64_t popOperand() {
       assert (!PostfixStack.empty() && "Poped an empty stack!");
AddDefaultSrcDestOperands(OperandVector &Operands,
                             std::unique_ptr<llvm::MCParsedAsmOperand> &&Dst);
   bool VerifyAndAdjustOperands(OperandVector &OrigOperands,
                                OperandVector &FinalOperands);
   std::unique_ptr<X86Operand> ParseOperand();
   std::unique_ptr<X86Operand> ParseATTOperand();
   std::unique_ptr<X86Operand> ParseIntelOperand();
   std::unique_ptr<X86Operand> ParseIntelOffsetOfOperator();
   bool ParseIntelDotOperator(const MCExpr *Disp, const MCExpr *&NewDisp);
-  std::unique_ptr<X86Operand> ParseIntelOperator(unsigned OpKind);
+  unsigned IdentifyIntelOperator(StringRef Name);
+  unsigned ParseIntelOperator(unsigned OpKind);
   std::unique_ptr<X86Operand>
   ParseIntelSegmentOverride(unsigned SegReg, SMLoc Start, unsigned Size);
   std::unique_ptr<X86Operand> ParseRoundingModeOp(SMLoc Start, SMLoc End);
   bool ParseIntelExpression(IntelExprStateMachine &SM, SMLoc &End);
   std::unique_ptr<X86Operand>
   ParseIntelBracExpression(unsigned SegReg, SMLoc Start, int64_t ImmDisp,
                            bool isSymbol, unsigned Size);
   bool ParseIntelIdentifier(const MCExpr *&Val, StringRef &Identifier,
private:
   /// {
 
 #define GET_ASSEMBLER_HEADER
 #include "X86GenAsmMatcher.inc"
 
   /// }
 
 public:
+
   X86AsmParser(const MCSubtargetInfo &sti, MCAsmParser &Parser,
                const MCInstrInfo &mii, const MCTargetOptions &Options)
       : MCTargetAsmParser(Options, sti), MII(mii), InstInfo(nullptr),
         Code16GCC(false) {
 
     // Initialize the set of available features.
     setAvailableFeatures(ComputeAvailableFeatures(getSTI().getFeatureBits()));
     Instrumentation.reset(
if (ImmDisp != FinalImmDisp) {
     } else {
       // We have a symbolic and an immediate displacement, but no displacement
       // before the bracketed expression.  Put the immediate displacement
       // before the bracketed expression.
       AsmRewrites.emplace_back(AOK_Imm, BracLoc, 0, FinalImmDisp);
     }
   }
   // Remove all the ImmPrefix rewrites within the brackets.
+  // We may have some Imm rewrties as a result of an operator applying,
+  // remove them as well
   for (AsmRewrite &AR : AsmRewrites) {
     if (AR.Loc.getPointer() < StartInBrac.getPointer())
       continue;
-    if (AR.Kind == AOK_ImmPrefix)
+    if (AR.Kind == AOK_ImmPrefix || AR.Kind == AOK_Imm)
       AR.Kind = AOK_Delete;
   }
   const char *SymLocPtr = SymName.data();
   // Skip everything before the symbol.
   if (unsigned Len = SymLocPtr - StartInBrac.getPointer()) {
     assert(Len > 0 && "Expected a non-negative length.");
     AsmRewrites.emplace_back(AOK_Skip, StartInBrac, Len);
   }
while (!Done) {
     }
     case AsmToken::String:
     case AsmToken::Identifier: {
       // This could be a register or a symbolic displacement.
       unsigned TmpReg;
       const MCExpr *Val;
       SMLoc IdentLoc = Tok.getLoc();
       StringRef Identifier = Tok.getString();
+      UpdateLocLex = false;
       if (TK != AsmToken::String && !ParseRegister(TmpReg, IdentLoc, End)) {
         SM.onRegister(TmpReg);
-        UpdateLocLex = false;
-        break;
-      } else {
-        if (!isParsingInlineAsm()) {
-          if (getParser().parsePrimaryExpr(Val, End))
-            return Error(Tok.getLoc(), "Unexpected identifier!");
-        } else {
-          // This is a dot operator, not an adjacent identifier.
-          if (Identifier.find('.') != StringRef::npos &&
-              PrevTK == AsmToken::RBrac) {
-            return false;
-          } else {
-            InlineAsmIdentifierInfo &Info = SM.getIdentifierInfo();
-            if (ParseIntelIdentifier(Val, Identifier, Info,
-                                     /*Unevaluated=*/false, End))
-              return true;
-          }
-        }
+      } else if (!isParsingInlineAsm()) {
+        SM.onIdentifierExpr(Val, Identifier);
+      } else if (unsigned OpKind = IdentifyIntelOperator(Identifier)) {
+        if (OpKind == IOK_OFFSET) 
+          return Error(IdentLoc, "Dealing OFFSET operator as part of"
+            "a compound immediate expression is yet to be supported");
+        int64_t Val = ParseIntelOperator(OpKind);
+        if (!Val)
+          return true;
+        StringRef ErrMsg;
+        if (SM.onInteger(Val, ErrMsg))
+          return Error(IdentLoc, ErrMsg);
+      } else if (Identifier.find('.') != StringRef::npos &&
         SM.onIdentifierExpr(Val, Identifier);
-        UpdateLocLex = false;
-        break;
       }
-      return Error(Tok.getLoc(), "Unexpected identifier!");
+      break;
     }
     case AsmToken::Integer: {
       StringRef ErrMsg;
       if (isParsingInlineAsm() && SM.getAddImmPrefix())
         InstInfo->AsmRewrites->emplace_back(AOK_ImmPrefix, Tok.getLoc());
       // Look for 'b' or 'f' following an Integer as a directional label
       SMLoc Loc = getTok().getLoc();
       int64_t IntVal = getTok().getIntVal();
std::unique_ptr<X86Operand> X86AsmParser::ParseIntelOffsetOfOperator() {
   // the size of a pointer.
   bool Parse32 = is32BitMode() || Code16GCC;
   unsigned RegNo = is64BitMode() ? X86::RBX : (Parse32 ? X86::EBX : X86::BX);
 
   return X86Operand::CreateReg(RegNo, Start, End, /*GetAddress=*/true,
                                OffsetOfLoc, Identifier, Info.OpDecl);
 }
 
-enum IntelOperatorKind {
-  IOK_LENGTH,
-  IOK_SIZE,
-  IOK_TYPE
-};
+// Query a candidate string for being an Intel assembly operator
+// Report back its kind, or IOK_INVALID if does not evaluated as a known one
+unsigned X86AsmParser::IdentifyIntelOperator(StringRef Name) {
+  return StringSwitch<unsigned>(Name)
+    .Cases("TYPE","type",IOK_TYPE)
+    .Cases("SIZE","size",IOK_SIZE)
+    .Cases("LENGTH","length",IOK_LENGTH)
+    .Cases("OFFSET","offset",IOK_OFFSET)
+    .Default(IOK_INVALID);
+}
 
 /// Parse the 'LENGTH', 'TYPE' and 'SIZE' operators.  The LENGTH operator
 /// returns the number of elements in an array.  It returns the value 1 for
 /// non-array variables.  The SIZE operator returns the size of a C or C++
 /// variable.  A variable's size is the product of its LENGTH and TYPE.  The
 /// TYPE operator returns the size of a C or C++ type or variable. If the
 /// variable is an array, TYPE returns the size of a single element.
-std::unique_ptr<X86Operand> X86AsmParser::ParseIntelOperator(unsigned OpKind) {
+unsigned X86AsmParser::ParseIntelOperator(unsigned OpKind) {
   MCAsmParser &Parser = getParser();
   const AsmToken &Tok = Parser.getTok();
   SMLoc TypeLoc = Tok.getLoc();
   Parser.Lex(); // Eat operator.
 
   const MCExpr *Val = nullptr;
   InlineAsmIdentifierInfo Info;
   SMLoc Start = Tok.getLoc(), End;
   StringRef Identifier = Tok.getString();
   if (ParseIntelIdentifier(Val, Identifier, Info,
                            /*Unevaluated=*/true, End))
-    return nullptr;
+    return 0;
 
-  if (!Info.OpDecl)
-    return ErrorOperand(Start, "unable to lookup expression");
+  if (!Info.OpDecl) {
+    Error(Start, "unable to lookup expression");
+    return 0;
+  }
   
   unsigned CVal = 0;
   switch(OpKind) {
   default: llvm_unreachable("Unexpected operand kind!");
   case IOK_LENGTH: CVal = Info.Length; break;
   case IOK_SIZE: CVal = Info.Size; break;
   case IOK_TYPE: CVal = Info.Type; break;
   }
 
   // Rewrite the type operator and the C or C++ type or variable in terms of an
   // immediate.  E.g. TYPE foo -> $$4
   unsigned Len = End.getPointer() - TypeLoc.getPointer();
   InstInfo->AsmRewrites->emplace_back(AOK_Imm, TypeLoc, Len, CVal);
 
-  const MCExpr *Imm = MCConstantExpr::create(CVal, getContext());
-  return X86Operand::CreateImm(Imm, Start, End);
+  return CVal;
 }
 
 std::unique_ptr<X86Operand> X86AsmParser::ParseIntelOperand() {
   MCAsmParser &Parser = getParser();
   const AsmToken &Tok = Parser.getTok();
   SMLoc Start, End;
 
-  // Offset, length, type and size operators.
-  if (isParsingInlineAsm()) {
-    StringRef AsmTokStr = Tok.getString();
-    if (AsmTokStr == "offset" || AsmTokStr == "OFFSET")
+  // Offset operator
+  // Should be handled as part of immediate expression, as other operators
+  // Currently, only supported as a stand-alone operand
+  if (isParsingInlineAsm())
+    if (IdentifyIntelOperator(Tok.getString()) == IOK_OFFSET)
       return ParseIntelOffsetOfOperator();
-    if (AsmTokStr == "length" || AsmTokStr == "LENGTH")
-      return ParseIntelOperator(IOK_LENGTH);
-    if (AsmTokStr == "size" || AsmTokStr == "SIZE")
-      return ParseIntelOperator(IOK_SIZE);
-    if (AsmTokStr == "type" || AsmTokStr == "TYPE")
-      return ParseIntelOperator(IOK_TYPE);
-  }
 
   bool PtrInOperand = false;
   unsigned Size = getIntelMemOperandSize(Tok.getString());
   if (Size) {
     Parser.Lex(); // Eat operand size (e.g., byte, word).
     if (Tok.getString() != "PTR" && Tok.getString() != "ptr")
       return ErrorOperand(Tok.getLoc(), "Expected 'PTR' or 'ptr' token!");
     Parser.Lex(); // Eat ptr.