[MC][X86] Enhance X86 Register expression handling to more closely match GCC.

[niravd]

Summary

Allow the comparison of x86 registers in the evaluation of assembler
directives. This generalizes and simplifies the extension from r334022 to catch another case
found in the Linux kernel.

[rnk]

Sure, we can handle some more weird stuff. :)

[rnk]

llvm/lib/MC/MCExpr.cpp

765

This is a bit of an odd construct, maybe just do default: break; like normal.

llvm/include/llvm/MC/MCExpr.h

protected:
   MCTargetExpr() : MCExpr(Target, SMLoc()) {}
   virtual ~MCTargetExpr() = default;
 
 public:
   virtual void printImpl(raw_ostream &OS, const MCAsmInfo *MAI) const = 0;
   virtual bool evaluateAsRelocatableImpl(MCValue &Res,
                                          const MCAsmLayout *Layout,
                                          const MCFixup *Fixup) const = 0;
+  // allow Target Expressions to be checked for equality
+  virtual bool isEqualTo(const MCExpr *x) const { return false; }
   // This should be set when assigned expressions are not valid ".set"
   // expressions, e.g. registers, and must be inlined.
   virtual bool inlineAssignedExpr() const { return false; }
   virtual void visitUsedExpr(MCStreamer& Streamer) const = 0;
   virtual MCFragment *findAssociatedFragment() const = 0;
 
   virtual void fixELFSymbolsInTLSFixups(MCAssembler &) const = 0;
 
   static bool classof(const MCExpr *E) {
     return E->getKind() == MCExpr::Target;
   }
 };
 
 } // end namespace llvm
 
 #endif // LLVM_MC_MCEXPR_H

llvm/include/llvm/MC/MCParser/MCAsmParserUtils.h

 namespace MCParserUtils {
 
 /// Parse a value expression and return whether it can be assigned to a symbol
 /// with the given name.
 ///
 /// On success, returns false and sets the Symbol and Value output parameters.
 bool parseAssignmentExpression(StringRef Name, bool allow_redef,
                                MCAsmParser &Parser, MCSymbol *&Symbol,
-                               const MCExpr *&Value, bool AllowExtendedExpr = false);
+                               const MCExpr *&Value);
 
 } // namespace MCParserUtils
 
 } // namespace llvm
 
 #endif // LLVM_MC_MCPARSER_MCASMPARSERUTILS_H

llvm/include/llvm/MC/MCParser/MCTargetAsmParser.h

public:
   void setParsingInlineAsm (bool Value) { ParsingInlineAsm = Value; }
 
   MCTargetOptions getTargetOptions() const { return MCOptions; }
 
   void setSemaCallback(MCAsmParserSemaCallback *Callback) {
     SemaCallback = Callback;
   }
 
-  // Target-specific parsing of assembler-level variable assignment.
-  virtual bool parseAssignmentExpression(const MCExpr *&Res, SMLoc &EndLoc) {
-    return getParser().parseExpression(Res, EndLoc);
+  // Target-specific parsing of expression.
+  virtual bool parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) {
+    return getParser().parsePrimaryExpr(Res, EndLoc);
   }
 
   virtual bool ParseRegister(unsigned &RegNo, SMLoc &StartLoc,
                              SMLoc &EndLoc) = 0;
 
   /// Sets frame register corresponding to the current MachineFunction.
   virtual void SetFrameRegister(unsigned RegNo) {}
 

llvm/lib/MC/MCExpr.cpp

bool MCExpr::evaluateAsRelocatableImpl(MCValue &Res, const MCAssembler *Asm,
 
   case Binary: {
     const MCBinaryExpr *ABE = cast<MCBinaryExpr>(this);
     MCValue LHSValue, RHSValue;
 
     if (!ABE->getLHS()->evaluateAsRelocatableImpl(LHSValue, Asm, Layout, Fixup,
                                                   Addrs, InSet) ||
         !ABE->getRHS()->evaluateAsRelocatableImpl(RHSValue, Asm, Layout, Fixup,
-                                                  Addrs, InSet))
+                                                  Addrs, InSet)) {
+      // Check if both are Target Expressions, see if we can compare them.
+      if (const MCTargetExpr *L = dyn_cast<MCTargetExpr>(ABE->getLHS()))
+        if (const MCTargetExpr *R = cast<MCTargetExpr>(ABE->getRHS())) {
+          switch (ABE->getOpcode()) {
+          case MCBinaryExpr::EQ:
+            Res = MCValue::get((L->isEqualTo(R)) ? -1 : 0);
+            return true;
+          case MCBinaryExpr::NE:
+            Res = MCValue::get((R->isEqualTo(R)) ? 0 : -1);
+            return true;
+          default: {}
+          }
+        }
       return false;
+    }
 
     // We only support a few operations on non-constant expressions, handle
     // those first.
     if (!LHSValue.isAbsolute() || !RHSValue.isAbsolute()) {
       switch (ABE->getOpcode()) {
       default:
         return false;
       case MCBinaryExpr::Sub:

llvm/lib/MC/MCParser/AsmParser.cpp

private:
   /// will be either the EndOfStatement or EOF.
   StringRef parseStringToEndOfStatement() override;
 
   /// Parse until the end of a statement or a comma is encountered,
   /// return the contents from the current token up to the end or comma.
   StringRef parseStringToComma();
 
   bool parseAssignment(StringRef Name, bool allow_redef,
-                       bool NoDeadStrip = false, bool AllowExtendedExpr = false);
+                       bool NoDeadStrip = false);
 
   unsigned getBinOpPrecedence(AsmToken::TokenKind K,
                               MCBinaryExpr::Opcode &Kind);
 
   bool parseBinOpRHS(unsigned Precedence, const MCExpr *&Res, SMLoc &EndLoc);
   bool parseParenExpr(const MCExpr *&Res, SMLoc &EndLoc);
   bool parseBracketExpr(const MCExpr *&Res, SMLoc &EndLoc);
 

 ///  expr ::= expr <<,>> expr
 ///  expr ::= expr +,- expr
 ///  expr ::= expr *,/,% expr               -> highest.
 ///  expr ::= primaryexpr
 ///
 bool AsmParser::parseExpression(const MCExpr *&Res, SMLoc &EndLoc) {
   // Parse the expression.
   Res = nullptr;
-  if (parsePrimaryExpr(Res, EndLoc) || parseBinOpRHS(1, Res, EndLoc))
+  if (getTargetParser().parsePrimaryExpr(Res, EndLoc) ||
+      parseBinOpRHS(1, Res, EndLoc))
     return true;
 
   // As a special case, we support 'a op b @ modifier' by rewriting the
   // expression to include the modifier. This is inefficient, but in general we
   // expect users to use 'a@modifier op b'.
   if (Lexer.getKind() == AsmToken::At) {
     Lex();
 
while (true) {
     // successfully with what we ate already.
     if (TokPrec < Precedence)
       return false;
 
     Lex();
 
     // Eat the next primary expression.
     const MCExpr *RHS;
-    if (parsePrimaryExpr(RHS, EndLoc))
+    if (getTargetParser().parsePrimaryExpr(RHS, EndLoc))
       return true;
 
     // If BinOp binds less tightly with RHS than the operator after RHS, let
     // the pending operator take RHS as its LHS.
     MCBinaryExpr::Opcode Dummy;
     unsigned NextTokPrec = getBinOpPrecedence(Lexer.getKind(), Dummy);
     if (TokPrec < NextTokPrec && parseBinOpRHS(TokPrec + 1, RHS, EndLoc))
       return true;
bool AsmParser::parseStatement(ParseStatementInfo &Info,
   }
 
   case AsmToken::Equal:
     if (!getTargetParser().equalIsAsmAssignment())
       break;
     // identifier '=' ... -> assignment statement
     Lex();
 
-    return parseAssignment(IDVal, true, /*NoDeadStrip*/ false, /*AllowExtendedExpr*/true);
+    return parseAssignment(IDVal, true);
 
   default: // Normal instruction or directive.
     break;
   }
 
   // If macros are enabled, check to see if this is a macro instantiation.
   if (areMacrosEnabled())
     if (const MCAsmMacro *M = getContext().lookupMacro(IDVal)) {
void AsmParser::handleMacroExit() {
   Lex();
 
   // Pop the instantiation entry.
   delete ActiveMacros.back();
   ActiveMacros.pop_back();
 }
 
 bool AsmParser::parseAssignment(StringRef Name, bool allow_redef,
-                                bool NoDeadStrip, bool AllowExtendedExpr) {
+                                bool NoDeadStrip) {
   MCSymbol *Sym;
   const MCExpr *Value;
   if (MCParserUtils::parseAssignmentExpression(Name, allow_redef, *this, Sym,
-                                               Value, AllowExtendedExpr))
+                                               Value))
     return true;
 
   if (!Sym) {
     // In the case where we parse an expression starting with a '.', we will
     // not generate an error, nor will we create a symbol.  In this case we
     // should just return out.
     return false;
   }
return isSymbolUsedInExpression(
         Sym, static_cast<const MCUnaryExpr *>(Value)->getSubExpr());
   }
 
   llvm_unreachable("Unknown expr kind!");
 }
 
 bool parseAssignmentExpression(StringRef Name, bool allow_redef,
                                MCAsmParser &Parser, MCSymbol *&Sym,
-                               const MCExpr *&Value, bool AllowExtendedExpr) {
+                               const MCExpr *&Value) {
 
   // FIXME: Use better location, we should use proper tokens.
   SMLoc EqualLoc = Parser.getTok().getLoc();
   SMLoc EndLoc;
-  if (AllowExtendedExpr) {
-    if (Parser.getTargetParser().parseAssignmentExpression(Value, EndLoc)) {
-      return Parser.TokError("missing expression");
-    }
-  } else if (Parser.parseExpression(Value, EndLoc))
-      return Parser.TokError("missing expression");
+  if (Parser.parseExpression(Value))
 
   // Note: we don't count b as used in "a = b". This is to allow
   // a = b
   // b = c
 
   if (Parser.parseToken(AsmToken::EndOfStatement))
     return true;
 

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

X86AsmParser(const MCSubtargetInfo &sti, MCAsmParser &Parser,
     Instrumentation.reset(
         CreateX86AsmInstrumentation(Options, Parser.getContext(), STI));
   }
 
   bool ParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc) override;
 
   void SetFrameRegister(unsigned RegNo) override;
 
-  bool parseAssignmentExpression(const MCExpr *&Res, SMLoc &EndLoc) override;
+  bool parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) override;
 
   bool ParseInstruction(ParseInstructionInfo &Info, StringRef Name,
                         SMLoc NameLoc, OperandVector &Operands) override;
 
   bool ParseDirective(AsmToken DirectiveID) override;
 };
 } // end anonymous namespace
 
std::unique_ptr<X86Operand> X86AsmParser::ParseMemOperand(unsigned SegReg,
   }
 
   if (SegReg || BaseReg || IndexReg)
     return X86Operand::CreateMem(getPointerWidth(), SegReg, Disp, BaseReg,
                                  IndexReg, Scale, MemStart, MemEnd);
   return X86Operand::CreateMem(getPointerWidth(), Disp, MemStart, MemEnd);
 }
 
-// Parse either a standard expression or a register.
-bool X86AsmParser::parseAssignmentExpression(const MCExpr *&Res,
-                                             SMLoc &EndLoc) {
+// Parse either a standard primary expression or a register.
+bool X86AsmParser::parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) {
   MCAsmParser &Parser = getParser();
-  if (Parser.parseExpression(Res, EndLoc)) {
+  if (Parser.parsePrimaryExpr(Res, EndLoc)) {
     SMLoc StartLoc = Parser.getTok().getLoc();
     // Normal Expression parse fails, check if it could be a register.
     unsigned RegNo;
-    if (Parser.getTargetParser().ParseRegister(RegNo, StartLoc, EndLoc))
+    bool TryRegParse =
+        getTok().is(AsmToken::Percent) ||
+        (isParsingIntelSyntax() && getTok().is(AsmToken::Identifier));
+    if (!TryRegParse || ParseRegister(RegNo, StartLoc, EndLoc))
       return true;
     // Clear previous parse error and return correct expression.
     Parser.clearPendingErrors();
     Res = X86MCExpr::create(RegNo, Parser.getContext());
     return false;
   }
 
   return false;

llvm/lib/Target/X86/MCTargetDesc/X86MCExpr.h

public:
   /// @{
 
   /// getSubExpr - Get the child of this expression.
   int64_t getRegNo() const { return RegNo; }
 
   /// @}
 
   void printImpl(raw_ostream &OS, const MCAsmInfo *MAI) const override {
-    if (MAI->getAssemblerDialect() == 0)
+    if (!MAI || MAI->getAssemblerDialect() == 0)
       OS << '%';
     OS << X86ATTInstPrinter::getRegisterName(RegNo);
   }
 
   bool evaluateAsRelocatableImpl(MCValue &Res, const MCAsmLayout *Layout,
                                  const MCFixup *Fixup) const override {
     return false;
   }
   // Register values should be inlined as they are not valid .set expressions.
   bool inlineAssignedExpr() const override { return true; }
+  bool isEqualTo(const MCExpr *X) const override {
+    if (auto *E = dyn_cast<X86MCExpr>(X))
+      return getRegNo() == E->getRegNo();
+    return false;
+  }
   void visitUsedExpr(MCStreamer &Streamer) const override{};
   MCFragment *findAssociatedFragment() const override { return nullptr; }
 
   // There are no TLS X86MCExprs at the moment.
   void fixELFSymbolsInTLSFixups(MCAssembler &Asm) const override {}
 
   static bool classof(const MCExpr *E) {
     return E->getKind() == MCExpr::Target;
   }
 };
 
 } // end namespace llvm
 
 #endif

llvm/test/MC/X86/pr37425.s

-// RUN: llvm-mc -triple x86_64-unknown-unknown -defsym=ERR=0 %s -o -      | FileCheck %s
-// RUN: not llvm-mc -triple x86_64-unknown-unknown -defsym=ERR=1 %s -o - 2>&1 | FileCheck --check-prefix=ERR %s
+// RUN: llvm-mc -triple x86_64-unknown-unknown %s -o -      | FileCheck %s
   
 // CHECK-NOT: .set var_xdata
 var_xdata = %rcx
 
 // CHECK: xorq %rcx, %rcx
 xorq var_xdata, var_xdata
 
-.if (ERR==1)
-// ERR: [[@LINE+2]]:15: error: unknown token in expression in '.set' directive
-// ERR: [[@LINE+1]]:15: error: missing expression in '.set' directive
-.set err_var, %rcx
-.endif  
+// CHECK: .data
+// CHECK-NEXT: .byte 1  
+.data 
+.if var_xdata == %rax
+  .byte 0
+.elseif var_xdata == %rcx
+  .byte 1
+.else
+  .byte 2 
+.endif