//===-- RISCVAsmParser.cpp - Parse RISCV assembly to MCInst instructions --===// // // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. // See https://llvm.org/LICENSE.txt for license information. // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception // //===----------------------------------------------------------------------===// #include "MCTargetDesc/RISCVAsmBackend.h" #include "MCTargetDesc/RISCVMCExpr.h" #include "MCTargetDesc/RISCVMCTargetDesc.h" #include "MCTargetDesc/RISCVTargetStreamer.h" #include "RISCVInstrInfo.h" #include "TargetInfo/RISCVTargetInfo.h" #include "Utils/RISCVBaseInfo.h" #include "Utils/RISCVMatInt.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/SmallBitVector.h" #include "llvm/ADT/SmallString.h" #include "llvm/ADT/SmallVector.h" #include "llvm/ADT/Statistic.h" #include "llvm/ADT/StringSwitch.h" #include "llvm/CodeGen/Register.h" #include "llvm/MC/MCAssembler.h" #include "llvm/MC/MCContext.h" #include "llvm/MC/MCExpr.h" #include "llvm/MC/MCInst.h" #include "llvm/MC/MCInstBuilder.h" #include "llvm/MC/MCObjectFileInfo.h" #include "llvm/MC/MCParser/MCAsmLexer.h" #include "llvm/MC/MCParser/MCParsedAsmOperand.h" #include "llvm/MC/MCParser/MCTargetAsmParser.h" #include "llvm/MC/MCRegisterInfo.h" #include "llvm/MC/MCStreamer.h" #include "llvm/MC/MCSubtargetInfo.h" #include "llvm/Support/Casting.h" #include "llvm/Support/MathExtras.h" #include "llvm/Support/RISCVAttributes.h" #include "llvm/Support/TargetRegistry.h" #include using namespace llvm; #define DEBUG_TYPE "riscv-asm-parser" // Include the auto-generated portion of the compress emitter. #define GEN_COMPRESS_INSTR #include "RISCVGenCompressInstEmitter.inc" STATISTIC(RISCVNumInstrsCompressed, "Number of RISC-V Compressed instructions emitted"); namespace { struct RISCVOperand; struct ParserOptionsSet { bool IsPicEnabled; }; class RISCVAsmParser : public MCTargetAsmParser { SmallVector FeatureBitStack; SmallVector ParserOptionsStack; ParserOptionsSet ParserOptions; SMLoc getLoc() const { return getParser().getTok().getLoc(); } bool isRV64() const { return getSTI().hasFeature(RISCV::Feature64Bit); } bool isRV32E() const { return getSTI().hasFeature(RISCV::FeatureRV32E); } RISCVTargetStreamer &getTargetStreamer() { MCTargetStreamer &TS = *getParser().getStreamer().getTargetStreamer(); return static_cast(TS); } unsigned validateTargetOperandClass(MCParsedAsmOperand &Op, unsigned Kind) override; bool generateImmOutOfRangeError(OperandVector &Operands, uint64_t ErrorInfo, int64_t Lower, int64_t Upper, Twine Msg); bool MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode, OperandVector &Operands, MCStreamer &Out, uint64_t &ErrorInfo, bool MatchingInlineAsm) override; bool ParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc) override; OperandMatchResultTy tryParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc) override; bool ParseInstruction(ParseInstructionInfo &Info, StringRef Name, SMLoc NameLoc, OperandVector &Operands) override; bool ParseDirective(AsmToken DirectiveID) override; // Helper to actually emit an instruction to the MCStreamer. Also, when // possible, compression of the instruction is performed. void emitToStreamer(MCStreamer &S, const MCInst &Inst); // Helper to emit a combination of LUI, ADDI(W), and SLLI instructions that // synthesize the desired immedate value into the destination register. void emitLoadImm(Register DestReg, int64_t Value, MCStreamer &Out); // Helper to emit a combination of AUIPC and SecondOpcode. Used to implement // helpers such as emitLoadLocalAddress and emitLoadAddress. void emitAuipcInstPair(MCOperand DestReg, MCOperand TmpReg, const MCExpr *Symbol, RISCVMCExpr::VariantKind VKHi, unsigned SecondOpcode, SMLoc IDLoc, MCStreamer &Out); // Helper to emit pseudo instruction "lla" used in PC-rel addressing. void emitLoadLocalAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out); // Helper to emit pseudo instruction "la" used in GOT/PC-rel addressing. void emitLoadAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out); // Helper to emit pseudo instruction "la.tls.ie" used in initial-exec TLS // addressing. void emitLoadTLSIEAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out); // Helper to emit pseudo instruction "la.tls.gd" used in global-dynamic TLS // addressing. void emitLoadTLSGDAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out); // Helper to emit pseudo load/store instruction with a symbol. void emitLoadStoreSymbol(MCInst &Inst, unsigned Opcode, SMLoc IDLoc, MCStreamer &Out, bool HasTmpReg); // Checks that a PseudoAddTPRel is using x4/tp in its second input operand. // Enforcing this using a restricted register class for the second input // operand of PseudoAddTPRel results in a poor diagnostic due to the fact // 'add' is an overloaded mnemonic. bool checkPseudoAddTPRel(MCInst &Inst, OperandVector &Operands); // Check instruction constraints. bool validateInstruction(MCInst &Inst, OperandVector &Operands); /// Helper for processing MC instructions that have been successfully matched /// by MatchAndEmitInstruction. Modifications to the emitted instructions, /// like the expansion of pseudo instructions (e.g., "li"), can be performed /// in this method. bool processInstruction(MCInst &Inst, SMLoc IDLoc, OperandVector &Operands, MCStreamer &Out); // Auto-generated instruction matching functions #define GET_ASSEMBLER_HEADER #include "RISCVGenAsmMatcher.inc" OperandMatchResultTy parseCSRSystemRegister(OperandVector &Operands); OperandMatchResultTy parseImmediate(OperandVector &Operands); OperandMatchResultTy parseRegister(OperandVector &Operands, bool AllowParens = false); OperandMatchResultTy parseMemOpBaseReg(OperandVector &Operands); OperandMatchResultTy parseAtomicMemOp(OperandVector &Operands); OperandMatchResultTy parseOperandWithModifier(OperandVector &Operands); OperandMatchResultTy parseBareSymbol(OperandVector &Operands); OperandMatchResultTy parseCallSymbol(OperandVector &Operands); OperandMatchResultTy parsePseudoJumpSymbol(OperandVector &Operands); OperandMatchResultTy parseJALOffset(OperandVector &Operands); OperandMatchResultTy parseVTypeI(OperandVector &Operands); OperandMatchResultTy parseMaskReg(OperandVector &Operands); bool parseOperand(OperandVector &Operands, StringRef Mnemonic); bool parseDirectiveOption(); bool parseDirectiveAttribute(); void setFeatureBits(uint64_t Feature, StringRef FeatureString) { if (!(getSTI().getFeatureBits()[Feature])) { MCSubtargetInfo &STI = copySTI(); setAvailableFeatures( ComputeAvailableFeatures(STI.ToggleFeature(FeatureString))); } } bool getFeatureBits(uint64_t Feature) { return getSTI().getFeatureBits()[Feature]; } void clearFeatureBits(uint64_t Feature, StringRef FeatureString) { if (getSTI().getFeatureBits()[Feature]) { MCSubtargetInfo &STI = copySTI(); setAvailableFeatures( ComputeAvailableFeatures(STI.ToggleFeature(FeatureString))); } } void pushFeatureBits() { assert(FeatureBitStack.size() == ParserOptionsStack.size() && "These two stacks must be kept synchronized"); FeatureBitStack.push_back(getSTI().getFeatureBits()); ParserOptionsStack.push_back(ParserOptions); } bool popFeatureBits() { assert(FeatureBitStack.size() == ParserOptionsStack.size() && "These two stacks must be kept synchronized"); if (FeatureBitStack.empty()) return true; FeatureBitset FeatureBits = FeatureBitStack.pop_back_val(); copySTI().setFeatureBits(FeatureBits); setAvailableFeatures(ComputeAvailableFeatures(FeatureBits)); ParserOptions = ParserOptionsStack.pop_back_val(); return false; } std::unique_ptr defaultMaskRegOp() const; public: enum RISCVMatchResultTy { Match_Dummy = FIRST_TARGET_MATCH_RESULT_TY, #define GET_OPERAND_DIAGNOSTIC_TYPES #include "RISCVGenAsmMatcher.inc" #undef GET_OPERAND_DIAGNOSTIC_TYPES }; static bool classifySymbolRef(const MCExpr *Expr, RISCVMCExpr::VariantKind &Kind, int64_t &Addend); RISCVAsmParser(const MCSubtargetInfo &STI, MCAsmParser &Parser, const MCInstrInfo &MII, const MCTargetOptions &Options) : MCTargetAsmParser(Options, STI, MII) { Parser.addAliasForDirective(".half", ".2byte"); Parser.addAliasForDirective(".hword", ".2byte"); Parser.addAliasForDirective(".word", ".4byte"); Parser.addAliasForDirective(".dword", ".8byte"); setAvailableFeatures(ComputeAvailableFeatures(STI.getFeatureBits())); auto ABIName = StringRef(Options.ABIName); if (ABIName.endswith("f") && !getSTI().getFeatureBits()[RISCV::FeatureStdExtF]) { errs() << "Hard-float 'f' ABI can't be used for a target that " "doesn't support the F instruction set extension (ignoring " "target-abi)\n"; } else if (ABIName.endswith("d") && !getSTI().getFeatureBits()[RISCV::FeatureStdExtD]) { errs() << "Hard-float 'd' ABI can't be used for a target that " "doesn't support the D instruction set extension (ignoring " "target-abi)\n"; } const MCObjectFileInfo *MOFI = Parser.getContext().getObjectFileInfo(); ParserOptions.IsPicEnabled = MOFI->isPositionIndependent(); } }; /// RISCVOperand - Instances of this class represent a parsed machine /// instruction struct RISCVOperand : public MCParsedAsmOperand { enum class KindTy { Token, Register, Immediate, SystemRegister, VType, } Kind; bool IsRV64; struct RegOp { Register RegNum; }; struct ImmOp { const MCExpr *Val; }; struct SysRegOp { const char *Data; unsigned Length; unsigned Encoding; // FIXME: Add the Encoding parsed fields as needed for checks, // e.g.: read/write or user/supervisor/machine privileges. }; enum class VSEW { SEW_8 = 0, SEW_16, SEW_32, SEW_64, SEW_128, SEW_256, SEW_512, SEW_1024, }; enum class VLMUL { LMUL_1 = 0, LMUL_2, LMUL_4, LMUL_8 }; struct VTypeOp { VSEW Sew; VLMUL Lmul; unsigned Encoding; }; SMLoc StartLoc, EndLoc; union { StringRef Tok; RegOp Reg; ImmOp Imm; struct SysRegOp SysReg; struct VTypeOp VType; }; RISCVOperand(KindTy K) : MCParsedAsmOperand(), Kind(K) {} public: RISCVOperand(const RISCVOperand &o) : MCParsedAsmOperand() { Kind = o.Kind; IsRV64 = o.IsRV64; StartLoc = o.StartLoc; EndLoc = o.EndLoc; switch (Kind) { case KindTy::Register: Reg = o.Reg; break; case KindTy::Immediate: Imm = o.Imm; break; case KindTy::Token: Tok = o.Tok; break; case KindTy::SystemRegister: SysReg = o.SysReg; break; case KindTy::VType: VType = o.VType; break; } } bool isToken() const override { return Kind == KindTy::Token; } bool isReg() const override { return Kind == KindTy::Register; } bool isV0Reg() const { return Kind == KindTy::Register && Reg.RegNum == RISCV::V0; } bool isImm() const override { return Kind == KindTy::Immediate; } bool isMem() const override { return false; } bool isSystemRegister() const { return Kind == KindTy::SystemRegister; } bool isVType() const { return Kind == KindTy::VType; } bool isGPR() const { return Kind == KindTy::Register && RISCVMCRegisterClasses[RISCV::GPRRegClassID].contains(Reg.RegNum); } static bool evaluateConstantImm(const MCExpr *Expr, int64_t &Imm, RISCVMCExpr::VariantKind &VK) { if (auto *RE = dyn_cast(Expr)) { VK = RE->getKind(); return RE->evaluateAsConstant(Imm); } if (auto CE = dyn_cast(Expr)) { VK = RISCVMCExpr::VK_RISCV_None; Imm = CE->getValue(); return true; } return false; } // True if operand is a symbol with no modifiers, or a constant with no // modifiers and isShiftedInt(Op). template bool isBareSimmNLsb0() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); bool IsValid; if (!IsConstantImm) IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm); else IsValid = isShiftedInt(Imm); return IsValid && VK == RISCVMCExpr::VK_RISCV_None; } // Predicate methods for AsmOperands defined in RISCVInstrInfo.td bool isBareSymbol() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; // Must be of 'immediate' type but not a constant. if (!isImm() || evaluateConstantImm(getImm(), Imm, VK)) return false; return RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isCallSymbol() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; // Must be of 'immediate' type but not a constant. if (!isImm() || evaluateConstantImm(getImm(), Imm, VK)) return false; return RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm) && (VK == RISCVMCExpr::VK_RISCV_CALL || VK == RISCVMCExpr::VK_RISCV_CALL_PLT); } bool isPseudoJumpSymbol() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; // Must be of 'immediate' type but not a constant. if (!isImm() || evaluateConstantImm(getImm(), Imm, VK)) return false; return RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm) && VK == RISCVMCExpr::VK_RISCV_CALL; } bool isTPRelAddSymbol() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; // Must be of 'immediate' type but not a constant. if (!isImm() || evaluateConstantImm(getImm(), Imm, VK)) return false; return RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm) && VK == RISCVMCExpr::VK_RISCV_TPREL_ADD; } bool isCSRSystemRegister() const { return isSystemRegister(); } bool isVTypeI() const { return isVType(); } /// Return true if the operand is a valid for the fence instruction e.g. /// ('iorw'). bool isFenceArg() const { if (!isImm()) return false; const MCExpr *Val = getImm(); auto *SVal = dyn_cast(Val); if (!SVal || SVal->getKind() != MCSymbolRefExpr::VK_None) return false; StringRef Str = SVal->getSymbol().getName(); // Letters must be unique, taken from 'iorw', and in ascending order. This // holds as long as each individual character is one of 'iorw' and is // greater than the previous character. char Prev = '\0'; for (char c : Str) { if (c != 'i' && c != 'o' && c != 'r' && c != 'w') return false; if (c <= Prev) return false; Prev = c; } return true; } /// Return true if the operand is a valid floating point rounding mode. bool isFRMArg() const { if (!isImm()) return false; const MCExpr *Val = getImm(); auto *SVal = dyn_cast(Val); if (!SVal || SVal->getKind() != MCSymbolRefExpr::VK_None) return false; StringRef Str = SVal->getSymbol().getName(); return RISCVFPRndMode::stringToRoundingMode(Str) != RISCVFPRndMode::Invalid; } bool isImmXLenLI() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); if (VK == RISCVMCExpr::VK_RISCV_LO || VK == RISCVMCExpr::VK_RISCV_PCREL_LO) return true; // Given only Imm, ensuring that the actually specified constant is either // a signed or unsigned 64-bit number is unfortunately impossible. return IsConstantImm && VK == RISCVMCExpr::VK_RISCV_None && (isRV64() || (isInt<32>(Imm) || isUInt<32>(Imm))); } bool isUImmLog2XLen() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; if (!evaluateConstantImm(getImm(), Imm, VK) || VK != RISCVMCExpr::VK_RISCV_None) return false; return (isRV64() && isUInt<6>(Imm)) || isUInt<5>(Imm); } bool isUImmLog2XLenNonZero() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; if (!evaluateConstantImm(getImm(), Imm, VK) || VK != RISCVMCExpr::VK_RISCV_None) return false; if (Imm == 0) return false; return (isRV64() && isUInt<6>(Imm)) || isUInt<5>(Imm); } bool isUImmLog2XLenHalf() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; if (!evaluateConstantImm(getImm(), Imm, VK) || VK != RISCVMCExpr::VK_RISCV_None) return false; return (isRV64() && isUInt<5>(Imm)) || isUInt<4>(Imm); } bool isUImm5() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isUInt<5>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm5NonZero() const { int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isUInt<5>(Imm) && (Imm != 0) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm5() const { if (!isImm()) return false; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isInt<5>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm6() const { if (!isImm()) return false; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isInt<6>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm6NonZero() const { if (!isImm()) return false; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isInt<6>(Imm) && (Imm != 0) && VK == RISCVMCExpr::VK_RISCV_None; } bool isCLUIImm() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && (Imm != 0) && (isUInt<5>(Imm) || (Imm >= 0xfffe0 && Imm <= 0xfffff)) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm7Lsb00() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isShiftedUInt<5, 2>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm8Lsb00() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isShiftedUInt<6, 2>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm8Lsb000() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isShiftedUInt<5, 3>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm9Lsb0() const { return isBareSimmNLsb0<9>(); } bool isUImm9Lsb000() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isShiftedUInt<6, 3>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm10Lsb00NonZero() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isShiftedUInt<8, 2>(Imm) && (Imm != 0) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm12() const { RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsValid; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); if (!IsConstantImm) IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm); else IsValid = isInt<12>(Imm); return IsValid && ((IsConstantImm && VK == RISCVMCExpr::VK_RISCV_None) || VK == RISCVMCExpr::VK_RISCV_LO || VK == RISCVMCExpr::VK_RISCV_PCREL_LO || VK == RISCVMCExpr::VK_RISCV_TPREL_LO); } bool isSImm12Lsb0() const { return isBareSimmNLsb0<12>(); } bool isSImm13Lsb0() const { return isBareSimmNLsb0<13>(); } bool isSImm10Lsb0000NonZero() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && (Imm != 0) && isShiftedInt<6, 4>(Imm) && VK == RISCVMCExpr::VK_RISCV_None; } bool isUImm20LUI() const { RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsValid; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); if (!IsConstantImm) { IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm); return IsValid && (VK == RISCVMCExpr::VK_RISCV_HI || VK == RISCVMCExpr::VK_RISCV_TPREL_HI); } else { return isUInt<20>(Imm) && (VK == RISCVMCExpr::VK_RISCV_None || VK == RISCVMCExpr::VK_RISCV_HI || VK == RISCVMCExpr::VK_RISCV_TPREL_HI); } } bool isUImm20AUIPC() const { RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsValid; if (!isImm()) return false; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); if (!IsConstantImm) { IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm); return IsValid && (VK == RISCVMCExpr::VK_RISCV_PCREL_HI || VK == RISCVMCExpr::VK_RISCV_GOT_HI || VK == RISCVMCExpr::VK_RISCV_TLS_GOT_HI || VK == RISCVMCExpr::VK_RISCV_TLS_GD_HI); } else { return isUInt<20>(Imm) && (VK == RISCVMCExpr::VK_RISCV_None || VK == RISCVMCExpr::VK_RISCV_PCREL_HI || VK == RISCVMCExpr::VK_RISCV_GOT_HI || VK == RISCVMCExpr::VK_RISCV_TLS_GOT_HI || VK == RISCVMCExpr::VK_RISCV_TLS_GD_HI); } } bool isSImm21Lsb0JAL() const { return isBareSimmNLsb0<21>(); } bool isImmZero() const { if (!isImm()) return false; int64_t Imm; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && (Imm == 0) && VK == RISCVMCExpr::VK_RISCV_None; } bool isSImm5Plus1() const { if (!isImm()) return false; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; int64_t Imm; bool IsConstantImm = evaluateConstantImm(getImm(), Imm, VK); return IsConstantImm && isInt<5>(Imm - 1) && VK == RISCVMCExpr::VK_RISCV_None; } /// getStartLoc - Gets location of the first token of this operand SMLoc getStartLoc() const override { return StartLoc; } /// getEndLoc - Gets location of the last token of this operand SMLoc getEndLoc() const override { return EndLoc; } /// True if this operand is for an RV64 instruction bool isRV64() const { return IsRV64; } unsigned getReg() const override { assert(Kind == KindTy::Register && "Invalid type access!"); return Reg.RegNum.id(); } StringRef getSysReg() const { assert(Kind == KindTy::SystemRegister && "Invalid access!"); return StringRef(SysReg.Data, SysReg.Length); } const MCExpr *getImm() const { assert(Kind == KindTy::Immediate && "Invalid type access!"); return Imm.Val; } StringRef getToken() const { assert(Kind == KindTy::Token && "Invalid type access!"); return Tok; } static StringRef getSEWStr(VSEW Sew) { switch (Sew) { case VSEW::SEW_8: return "e8"; case VSEW::SEW_16: return "e16"; case VSEW::SEW_32: return "e32"; case VSEW::SEW_64: return "e64"; case VSEW::SEW_128: return "e128"; case VSEW::SEW_256: return "e256"; case VSEW::SEW_512: return "e512"; case VSEW::SEW_1024: return "e1024"; } return ""; } static StringRef getLMULStr(VLMUL Lmul) { switch (Lmul) { case VLMUL::LMUL_1: return "m1"; case VLMUL::LMUL_2: return "m2"; case VLMUL::LMUL_4: return "m4"; case VLMUL::LMUL_8: return "m8"; } return ""; } StringRef getVType(SmallString<32> &Buf) const { assert(Kind == KindTy::VType && "Invalid access!"); Buf.append(getSEWStr(VType.Sew)); Buf.append(","); Buf.append(getLMULStr(VType.Lmul)); return Buf.str(); } void print(raw_ostream &OS) const override { switch (Kind) { case KindTy::Immediate: OS << *getImm(); break; case KindTy::Register: OS << ""; break; case KindTy::Token: OS << "'" << getToken() << "'"; break; case KindTy::SystemRegister: OS << "'; break; case KindTy::VType: SmallString<32> VTypeBuf; OS << "'; break; } } static std::unique_ptr createToken(StringRef Str, SMLoc S, bool IsRV64) { auto Op = std::make_unique(KindTy::Token); Op->Tok = Str; Op->StartLoc = S; Op->EndLoc = S; Op->IsRV64 = IsRV64; return Op; } static std::unique_ptr createReg(unsigned RegNo, SMLoc S, SMLoc E, bool IsRV64) { auto Op = std::make_unique(KindTy::Register); Op->Reg.RegNum = RegNo; Op->StartLoc = S; Op->EndLoc = E; Op->IsRV64 = IsRV64; return Op; } static std::unique_ptr createImm(const MCExpr *Val, SMLoc S, SMLoc E, bool IsRV64) { auto Op = std::make_unique(KindTy::Immediate); Op->Imm.Val = Val; Op->StartLoc = S; Op->EndLoc = E; Op->IsRV64 = IsRV64; return Op; } static std::unique_ptr createSysReg(StringRef Str, SMLoc S, unsigned Encoding, bool IsRV64) { auto Op = std::make_unique(KindTy::SystemRegister); Op->SysReg.Data = Str.data(); Op->SysReg.Length = Str.size(); Op->SysReg.Encoding = Encoding; Op->StartLoc = S; Op->IsRV64 = IsRV64; return Op; } static std::unique_ptr createVType(APInt Sew, APInt Lmul, SMLoc S, bool IsRV64) { auto Op = std::make_unique(KindTy::VType); Sew.ashrInPlace(3); unsigned SewLog2 = Sew.logBase2(); unsigned LmulLog2 = Lmul.logBase2(); Op->VType.Sew = static_cast(SewLog2); Op->VType.Lmul = static_cast(LmulLog2); Op->VType.Encoding = (SewLog2 << 2) | LmulLog2; Op->StartLoc = S; Op->IsRV64 = IsRV64; return Op; } void addExpr(MCInst &Inst, const MCExpr *Expr) const { assert(Expr && "Expr shouldn't be null!"); int64_t Imm = 0; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstant = evaluateConstantImm(Expr, Imm, VK); if (IsConstant) Inst.addOperand(MCOperand::createImm(Imm)); else Inst.addOperand(MCOperand::createExpr(Expr)); } // Used by the TableGen Code 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!"); addExpr(Inst, getImm()); } void addSImm5Plus1Operands(MCInst &Inst, unsigned N) const { assert(N == 1 && "Invalid number of operands!"); int64_t Imm = 0; RISCVMCExpr::VariantKind VK = RISCVMCExpr::VK_RISCV_None; bool IsConstant = evaluateConstantImm(getImm(), Imm, VK); assert(IsConstant && "Expect constant value!"); (void)IsConstant; Inst.addOperand(MCOperand::createImm(Imm - 1)); } void addFenceArgOperands(MCInst &Inst, unsigned N) const { assert(N == 1 && "Invalid number of operands!"); // isFenceArg has validated the operand, meaning this cast is safe auto SE = cast(getImm()); unsigned Imm = 0; for (char c : SE->getSymbol().getName()) { switch (c) { default: llvm_unreachable("FenceArg must contain only [iorw]"); case 'i': Imm |= RISCVFenceField::I; break; case 'o': Imm |= RISCVFenceField::O; break; case 'r': Imm |= RISCVFenceField::R; break; case 'w': Imm |= RISCVFenceField::W; break; } } Inst.addOperand(MCOperand::createImm(Imm)); } void addCSRSystemRegisterOperands(MCInst &Inst, unsigned N) const { assert(N == 1 && "Invalid number of operands!"); Inst.addOperand(MCOperand::createImm(SysReg.Encoding)); } void addVTypeIOperands(MCInst &Inst, unsigned N) const { assert(N == 1 && "Invalid number of operands!"); Inst.addOperand(MCOperand::createImm(VType.Encoding)); } // Returns the rounding mode represented by this RISCVOperand. Should only // be called after checking isFRMArg. RISCVFPRndMode::RoundingMode getRoundingMode() const { // isFRMArg has validated the operand, meaning this cast is safe. auto SE = cast(getImm()); RISCVFPRndMode::RoundingMode FRM = RISCVFPRndMode::stringToRoundingMode(SE->getSymbol().getName()); assert(FRM != RISCVFPRndMode::Invalid && "Invalid rounding mode"); return FRM; } void addFRMArgOperands(MCInst &Inst, unsigned N) const { assert(N == 1 && "Invalid number of operands!"); Inst.addOperand(MCOperand::createImm(getRoundingMode())); } }; } // end anonymous namespace. #define GET_REGISTER_MATCHER #define GET_SUBTARGET_FEATURE_NAME #define GET_MATCHER_IMPLEMENTATION #define GET_MNEMONIC_SPELL_CHECKER #include "RISCVGenAsmMatcher.inc" static Register convertFPR64ToFPR32(Register Reg) { assert(Reg >= RISCV::F0_D && Reg <= RISCV::F31_D && "Invalid register"); return Reg - RISCV::F0_D + RISCV::F0_F; } unsigned RISCVAsmParser::validateTargetOperandClass(MCParsedAsmOperand &AsmOp, unsigned Kind) { RISCVOperand &Op = static_cast(AsmOp); if (!Op.isReg()) return Match_InvalidOperand; Register Reg = Op.getReg(); bool IsRegFPR64 = RISCVMCRegisterClasses[RISCV::FPR64RegClassID].contains(Reg); bool IsRegFPR64C = RISCVMCRegisterClasses[RISCV::FPR64CRegClassID].contains(Reg); // As the parser couldn't differentiate an FPR32 from an FPR64, coerce the // register from FPR64 to FPR32 or FPR64C to FPR32C if necessary. if ((IsRegFPR64 && Kind == MCK_FPR32) || (IsRegFPR64C && Kind == MCK_FPR32C)) { Op.Reg.RegNum = convertFPR64ToFPR32(Reg); return Match_Success; } return Match_InvalidOperand; } bool RISCVAsmParser::generateImmOutOfRangeError( OperandVector &Operands, uint64_t ErrorInfo, int64_t Lower, int64_t Upper, Twine Msg = "immediate must be an integer in the range") { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, Msg + " [" + Twine(Lower) + ", " + Twine(Upper) + "]"); } static std::string RISCVMnemonicSpellCheck(StringRef S, const FeatureBitset &FBS, unsigned VariantID = 0); bool RISCVAsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode, OperandVector &Operands, MCStreamer &Out, uint64_t &ErrorInfo, bool MatchingInlineAsm) { MCInst Inst; FeatureBitset MissingFeatures; auto Result = MatchInstructionImpl(Operands, Inst, ErrorInfo, MissingFeatures, MatchingInlineAsm); switch (Result) { default: break; case Match_Success: if (validateInstruction(Inst, Operands)) return true; return processInstruction(Inst, IDLoc, Operands, Out); case Match_MissingFeature: { assert(MissingFeatures.any() && "Unknown missing features!"); bool FirstFeature = true; std::string Msg = "instruction requires the following:"; for (unsigned i = 0, e = MissingFeatures.size(); i != e; ++i) { if (MissingFeatures[i]) { Msg += FirstFeature ? " " : ", "; Msg += getSubtargetFeatureName(i); FirstFeature = false; } } return Error(IDLoc, Msg); } case Match_MnemonicFail: { FeatureBitset FBS = ComputeAvailableFeatures(getSTI().getFeatureBits()); std::string Suggestion = RISCVMnemonicSpellCheck( ((RISCVOperand &)*Operands[0]).getToken(), FBS); return Error(IDLoc, "unrecognized instruction mnemonic" + Suggestion); } case Match_InvalidOperand: { SMLoc ErrorLoc = IDLoc; if (ErrorInfo != ~0U) { if (ErrorInfo >= Operands.size()) return Error(ErrorLoc, "too few operands for instruction"); ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); if (ErrorLoc == SMLoc()) ErrorLoc = IDLoc; } return Error(ErrorLoc, "invalid operand for instruction"); } } // Handle the case when the error message is of specific type // other than the generic Match_InvalidOperand, and the // corresponding operand is missing. if (Result > FIRST_TARGET_MATCH_RESULT_TY) { SMLoc ErrorLoc = IDLoc; if (ErrorInfo != ~0U && ErrorInfo >= Operands.size()) return Error(ErrorLoc, "too few operands for instruction"); } switch(Result) { default: break; case Match_InvalidImmXLenLI: if (isRV64()) { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be a constant 64-bit integer"); } return generateImmOutOfRangeError(Operands, ErrorInfo, std::numeric_limits::min(), std::numeric_limits::max()); case Match_InvalidImmZero: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "immediate must be zero"); } case Match_InvalidUImmLog2XLen: if (isRV64()) return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 6) - 1); return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 5) - 1); case Match_InvalidUImmLog2XLenNonZero: if (isRV64()) return generateImmOutOfRangeError(Operands, ErrorInfo, 1, (1 << 6) - 1); return generateImmOutOfRangeError(Operands, ErrorInfo, 1, (1 << 5) - 1); case Match_InvalidUImmLog2XLenHalf: if (isRV64()) return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 5) - 1); return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 4) - 1); case Match_InvalidUImm5: return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 5) - 1); case Match_InvalidSImm6: return generateImmOutOfRangeError(Operands, ErrorInfo, -(1 << 5), (1 << 5) - 1); case Match_InvalidSImm6NonZero: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 5), (1 << 5) - 1, "immediate must be non-zero in the range"); case Match_InvalidCLUIImm: return generateImmOutOfRangeError( Operands, ErrorInfo, 1, (1 << 5) - 1, "immediate must be in [0xfffe0, 0xfffff] or"); case Match_InvalidUImm7Lsb00: return generateImmOutOfRangeError( Operands, ErrorInfo, 0, (1 << 7) - 4, "immediate must be a multiple of 4 bytes in the range"); case Match_InvalidUImm8Lsb00: return generateImmOutOfRangeError( Operands, ErrorInfo, 0, (1 << 8) - 4, "immediate must be a multiple of 4 bytes in the range"); case Match_InvalidUImm8Lsb000: return generateImmOutOfRangeError( Operands, ErrorInfo, 0, (1 << 8) - 8, "immediate must be a multiple of 8 bytes in the range"); case Match_InvalidSImm9Lsb0: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 8), (1 << 8) - 2, "immediate must be a multiple of 2 bytes in the range"); case Match_InvalidUImm9Lsb000: return generateImmOutOfRangeError( Operands, ErrorInfo, 0, (1 << 9) - 8, "immediate must be a multiple of 8 bytes in the range"); case Match_InvalidUImm10Lsb00NonZero: return generateImmOutOfRangeError( Operands, ErrorInfo, 4, (1 << 10) - 4, "immediate must be a multiple of 4 bytes in the range"); case Match_InvalidSImm10Lsb0000NonZero: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 9), (1 << 9) - 16, "immediate must be a multiple of 16 bytes and non-zero in the range"); case Match_InvalidSImm12: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 11), (1 << 11) - 1, "operand must be a symbol with %lo/%pcrel_lo/%tprel_lo modifier or an " "integer in the range"); case Match_InvalidSImm12Lsb0: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 11), (1 << 11) - 2, "immediate must be a multiple of 2 bytes in the range"); case Match_InvalidSImm13Lsb0: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 12), (1 << 12) - 2, "immediate must be a multiple of 2 bytes in the range"); case Match_InvalidUImm20LUI: return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 20) - 1, "operand must be a symbol with " "%hi/%tprel_hi modifier or an integer in " "the range"); case Match_InvalidUImm20AUIPC: return generateImmOutOfRangeError( Operands, ErrorInfo, 0, (1 << 20) - 1, "operand must be a symbol with a " "%pcrel_hi/%got_pcrel_hi/%tls_ie_pcrel_hi/%tls_gd_pcrel_hi modifier or " "an integer in the range"); case Match_InvalidSImm21Lsb0JAL: return generateImmOutOfRangeError( Operands, ErrorInfo, -(1 << 20), (1 << 20) - 2, "immediate must be a multiple of 2 bytes in the range"); case Match_InvalidCSRSystemRegister: { return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 12) - 1, "operand must be a valid system register " "name or an integer in the range"); } case Match_InvalidFenceArg: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error( ErrorLoc, "operand must be formed of letters selected in-order from 'iorw'"); } case Match_InvalidFRMArg: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error( ErrorLoc, "operand must be a valid floating point rounding mode mnemonic"); } case Match_InvalidBareSymbol: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be a bare symbol name"); } case Match_InvalidPseudoJumpSymbol: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be a valid jump target"); } case Match_InvalidCallSymbol: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be a bare symbol name"); } case Match_InvalidTPRelAddSymbol: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be a symbol with %tprel_add modifier"); } case Match_InvalidVTypeI: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be e[8|16|32|64|128|256|512|1024],m[1|2|4|8]"); } case Match_InvalidVMaskRegister: { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[ErrorInfo]).getStartLoc(); return Error(ErrorLoc, "operand must be v0.t"); } case Match_InvalidSImm5Plus1: { return generateImmOutOfRangeError(Operands, ErrorInfo, -(1 << 4) + 1, (1 << 4), "immediate must be in the range"); } } llvm_unreachable("Unknown match type detected!"); } // Attempts to match Name as a register (either using the default name or // alternative ABI names), setting RegNo to the matching register. Upon // failure, returns true and sets RegNo to 0. If IsRV32E then registers // x16-x31 will be rejected. static bool matchRegisterNameHelper(bool IsRV32E, Register &RegNo, StringRef Name) { RegNo = MatchRegisterName(Name); // The 32- and 64-bit FPRs have the same asm name. Check that the initial // match always matches the 64-bit variant, and not the 32-bit one. assert(!(RegNo >= RISCV::F0_F && RegNo <= RISCV::F31_F)); // The default FPR register class is based on the tablegen enum ordering. static_assert(RISCV::F0_D < RISCV::F0_F, "FPR matching must be updated"); if (RegNo == RISCV::NoRegister) RegNo = MatchRegisterAltName(Name); if (IsRV32E && RegNo >= RISCV::X16 && RegNo <= RISCV::X31) RegNo = RISCV::NoRegister; return RegNo == RISCV::NoRegister; } bool RISCVAsmParser::ParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc) { if (tryParseRegister(RegNo, StartLoc, EndLoc) != MatchOperand_Success) return Error(StartLoc, "invalid register name"); return false; } OperandMatchResultTy RISCVAsmParser::tryParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc) { const AsmToken &Tok = getParser().getTok(); StartLoc = Tok.getLoc(); EndLoc = Tok.getEndLoc(); RegNo = 0; StringRef Name = getLexer().getTok().getIdentifier(); if (matchRegisterNameHelper(isRV32E(), (Register &)RegNo, Name)) return MatchOperand_NoMatch; getParser().Lex(); // Eat identifier token. return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseRegister(OperandVector &Operands, bool AllowParens) { SMLoc FirstS = getLoc(); bool HadParens = false; AsmToken LParen; // If this is an LParen and a parenthesised register name is allowed, parse it // atomically. if (AllowParens && getLexer().is(AsmToken::LParen)) { AsmToken Buf[2]; size_t ReadCount = getLexer().peekTokens(Buf); if (ReadCount == 2 && Buf[1].getKind() == AsmToken::RParen) { HadParens = true; LParen = getParser().getTok(); getParser().Lex(); // Eat '(' } } switch (getLexer().getKind()) { default: if (HadParens) getLexer().UnLex(LParen); return MatchOperand_NoMatch; case AsmToken::Identifier: StringRef Name = getLexer().getTok().getIdentifier(); Register RegNo; matchRegisterNameHelper(isRV32E(), RegNo, Name); if (RegNo == RISCV::NoRegister) { if (HadParens) getLexer().UnLex(LParen); return MatchOperand_NoMatch; } if (HadParens) Operands.push_back(RISCVOperand::createToken("(", FirstS, isRV64())); SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); getLexer().Lex(); Operands.push_back(RISCVOperand::createReg(RegNo, S, E, isRV64())); } if (HadParens) { getParser().Lex(); // Eat ')' Operands.push_back(RISCVOperand::createToken(")", getLoc(), isRV64())); } return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseCSRSystemRegister(OperandVector &Operands) { SMLoc S = getLoc(); const MCExpr *Res; switch (getLexer().getKind()) { default: return MatchOperand_NoMatch; case AsmToken::LParen: case AsmToken::Minus: case AsmToken::Plus: case AsmToken::Exclaim: case AsmToken::Tilde: case AsmToken::Integer: case AsmToken::String: { if (getParser().parseExpression(Res)) return MatchOperand_ParseFail; auto *CE = dyn_cast(Res); if (CE) { int64_t Imm = CE->getValue(); if (isUInt<12>(Imm)) { auto SysReg = RISCVSysReg::lookupSysRegByEncoding(Imm); // Accept an immediate representing a named or un-named Sys Reg // if the range is valid, regardless of the required features. Operands.push_back(RISCVOperand::createSysReg( SysReg ? SysReg->Name : "", S, Imm, isRV64())); return MatchOperand_Success; } } Twine Msg = "immediate must be an integer in the range"; Error(S, Msg + " [" + Twine(0) + ", " + Twine((1 << 12) - 1) + "]"); return MatchOperand_ParseFail; } case AsmToken::Identifier: { StringRef Identifier; if (getParser().parseIdentifier(Identifier)) return MatchOperand_ParseFail; auto SysReg = RISCVSysReg::lookupSysRegByName(Identifier); if (!SysReg) SysReg = RISCVSysReg::lookupSysRegByAltName(Identifier); // Accept a named Sys Reg if the required features are present. if (SysReg) { if (!SysReg->haveRequiredFeatures(getSTI().getFeatureBits())) { Error(S, "system register use requires an option to be enabled"); return MatchOperand_ParseFail; } Operands.push_back(RISCVOperand::createSysReg( Identifier, S, SysReg->Encoding, isRV64())); return MatchOperand_Success; } Twine Msg = "operand must be a valid system register name " "or an integer in the range"; Error(S, Msg + " [" + Twine(0) + ", " + Twine((1 << 12) - 1) + "]"); return MatchOperand_ParseFail; } case AsmToken::Percent: { // Discard operand with modifier. Twine Msg = "immediate must be an integer in the range"; Error(S, Msg + " [" + Twine(0) + ", " + Twine((1 << 12) - 1) + "]"); return MatchOperand_ParseFail; } } return MatchOperand_NoMatch; } OperandMatchResultTy RISCVAsmParser::parseImmediate(OperandVector &Operands) { SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); const MCExpr *Res; switch (getLexer().getKind()) { default: return MatchOperand_NoMatch; case AsmToken::LParen: case AsmToken::Dot: case AsmToken::Minus: case AsmToken::Plus: case AsmToken::Exclaim: case AsmToken::Tilde: case AsmToken::Integer: case AsmToken::String: case AsmToken::Identifier: if (getParser().parseExpression(Res)) return MatchOperand_ParseFail; break; case AsmToken::Percent: return parseOperandWithModifier(Operands); } Operands.push_back(RISCVOperand::createImm(Res, S, E, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseOperandWithModifier(OperandVector &Operands) { SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); if (getLexer().getKind() != AsmToken::Percent) { Error(getLoc(), "expected '%' for operand modifier"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat '%' if (getLexer().getKind() != AsmToken::Identifier) { Error(getLoc(), "expected valid identifier for operand modifier"); return MatchOperand_ParseFail; } StringRef Identifier = getParser().getTok().getIdentifier(); RISCVMCExpr::VariantKind VK = RISCVMCExpr::getVariantKindForName(Identifier); if (VK == RISCVMCExpr::VK_RISCV_Invalid) { Error(getLoc(), "unrecognized operand modifier"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat the identifier if (getLexer().getKind() != AsmToken::LParen) { Error(getLoc(), "expected '('"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat '(' const MCExpr *SubExpr; if (getParser().parseParenExpression(SubExpr, E)) { return MatchOperand_ParseFail; } const MCExpr *ModExpr = RISCVMCExpr::create(SubExpr, VK, getContext()); Operands.push_back(RISCVOperand::createImm(ModExpr, S, E, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseBareSymbol(OperandVector &Operands) { SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); const MCExpr *Res; if (getLexer().getKind() != AsmToken::Identifier) return MatchOperand_NoMatch; StringRef Identifier; AsmToken Tok = getLexer().getTok(); if (getParser().parseIdentifier(Identifier)) return MatchOperand_ParseFail; if (Identifier.consume_back("@plt")) { Error(getLoc(), "'@plt' operand not valid for instruction"); return MatchOperand_ParseFail; } MCSymbol *Sym = getContext().getOrCreateSymbol(Identifier); if (Sym->isVariable()) { const MCExpr *V = Sym->getVariableValue(/*SetUsed=*/false); if (!isa(V)) { getLexer().UnLex(Tok); // Put back if it's not a bare symbol. return MatchOperand_NoMatch; } Res = V; } else Res = MCSymbolRefExpr::create(Sym, MCSymbolRefExpr::VK_None, getContext()); MCBinaryExpr::Opcode Opcode; switch (getLexer().getKind()) { default: Operands.push_back(RISCVOperand::createImm(Res, S, E, isRV64())); return MatchOperand_Success; case AsmToken::Plus: Opcode = MCBinaryExpr::Add; break; case AsmToken::Minus: Opcode = MCBinaryExpr::Sub; break; } const MCExpr *Expr; if (getParser().parseExpression(Expr)) return MatchOperand_ParseFail; Res = MCBinaryExpr::create(Opcode, Res, Expr, getContext()); Operands.push_back(RISCVOperand::createImm(Res, S, E, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseCallSymbol(OperandVector &Operands) { SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); const MCExpr *Res; if (getLexer().getKind() != AsmToken::Identifier) return MatchOperand_NoMatch; // Avoid parsing the register in `call rd, foo` as a call symbol. if (getLexer().peekTok().getKind() != AsmToken::EndOfStatement) return MatchOperand_NoMatch; StringRef Identifier; if (getParser().parseIdentifier(Identifier)) return MatchOperand_ParseFail; RISCVMCExpr::VariantKind Kind = RISCVMCExpr::VK_RISCV_CALL; if (Identifier.consume_back("@plt")) Kind = RISCVMCExpr::VK_RISCV_CALL_PLT; MCSymbol *Sym = getContext().getOrCreateSymbol(Identifier); Res = MCSymbolRefExpr::create(Sym, MCSymbolRefExpr::VK_None, getContext()); Res = RISCVMCExpr::create(Res, Kind, getContext()); Operands.push_back(RISCVOperand::createImm(Res, S, E, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parsePseudoJumpSymbol(OperandVector &Operands) { SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); const MCExpr *Res; if (getParser().parseExpression(Res)) return MatchOperand_ParseFail; if (Res->getKind() != MCExpr::ExprKind::SymbolRef || cast(Res)->getKind() == MCSymbolRefExpr::VariantKind::VK_PLT) { Error(S, "operand must be a valid jump target"); return MatchOperand_ParseFail; } Res = RISCVMCExpr::create(Res, RISCVMCExpr::VK_RISCV_CALL, getContext()); Operands.push_back(RISCVOperand::createImm(Res, S, E, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseJALOffset(OperandVector &Operands) { // Parsing jal operands is fiddly due to the `jal foo` and `jal ra, foo` // both being acceptable forms. When parsing `jal ra, foo` this function // will be called for the `ra` register operand in an attempt to match the // single-operand alias. parseJALOffset must fail for this case. It would // seem logical to try parse the operand using parseImmediate and return // NoMatch if the next token is a comma (meaning we must be parsing a jal in // the second form rather than the first). We can't do this as there's no // way of rewinding the lexer state. Instead, return NoMatch if this operand // is an identifier and is followed by a comma. if (getLexer().is(AsmToken::Identifier) && getLexer().peekTok().is(AsmToken::Comma)) return MatchOperand_NoMatch; return parseImmediate(Operands); } OperandMatchResultTy RISCVAsmParser::parseVTypeI(OperandVector &Operands) { SMLoc S = getLoc(); if (getLexer().getKind() != AsmToken::Identifier) return MatchOperand_NoMatch; // Parse "e8,m1" StringRef Name = getLexer().getTok().getIdentifier(); if (!Name.consume_front("e")) return MatchOperand_NoMatch; APInt Sew(16, Name, 10); if (Sew != 8 && Sew != 16 && Sew != 32 && Sew != 64 && Sew != 128 && Sew != 256 && Sew != 512 && Sew != 1024) return MatchOperand_NoMatch; getLexer().Lex(); if (getLexer().getKind() == AsmToken::EndOfStatement) { Operands.push_back( RISCVOperand::createVType(Sew, APInt(16, 1), S, isRV64())); return MatchOperand_Success; } if (!getLexer().is(AsmToken::Comma)) return MatchOperand_NoMatch; getLexer().Lex(); Name = getLexer().getTok().getIdentifier(); if (!Name.consume_front("m")) return MatchOperand_NoMatch; APInt Lmul(16, Name, 10); if (Lmul != 1 && Lmul != 2 && Lmul != 4 && Lmul != 8) return MatchOperand_NoMatch; getLexer().Lex(); if (getLexer().getKind() != AsmToken::EndOfStatement) return MatchOperand_NoMatch; Operands.push_back(RISCVOperand::createVType(Sew, Lmul, S, isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseMaskReg(OperandVector &Operands) { switch (getLexer().getKind()) { default: return MatchOperand_NoMatch; case AsmToken::Identifier: StringRef Name = getLexer().getTok().getIdentifier(); if (!Name.consume_back(".t")) { Error(getLoc(), "expected '.t' suffix"); return MatchOperand_ParseFail; } Register RegNo; matchRegisterNameHelper(isRV32E(), RegNo, Name); if (RegNo == RISCV::NoRegister) return MatchOperand_NoMatch; if (RegNo != RISCV::V0) return MatchOperand_NoMatch; SMLoc S = getLoc(); SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1); getLexer().Lex(); Operands.push_back(RISCVOperand::createReg(RegNo, S, E, isRV64())); } return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseMemOpBaseReg(OperandVector &Operands) { if (getLexer().isNot(AsmToken::LParen)) { Error(getLoc(), "expected '('"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat '(' Operands.push_back(RISCVOperand::createToken("(", getLoc(), isRV64())); if (parseRegister(Operands) != MatchOperand_Success) { Error(getLoc(), "expected register"); return MatchOperand_ParseFail; } if (getLexer().isNot(AsmToken::RParen)) { Error(getLoc(), "expected ')'"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat ')' Operands.push_back(RISCVOperand::createToken(")", getLoc(), isRV64())); return MatchOperand_Success; } OperandMatchResultTy RISCVAsmParser::parseAtomicMemOp(OperandVector &Operands) { // Atomic operations such as lr.w, sc.w, and amo*.w accept a "memory operand" // as one of their register operands, such as `(a0)`. This just denotes that // the register (in this case `a0`) contains a memory address. // // Normally, we would be able to parse these by putting the parens into the // instruction string. However, GNU as also accepts a zero-offset memory // operand (such as `0(a0)`), and ignores the 0. Normally this would be parsed // with parseImmediate followed by parseMemOpBaseReg, but these instructions // do not accept an immediate operand, and we do not want to add a "dummy" // operand that is silently dropped. // // Instead, we use this custom parser. This will: allow (and discard) an // offset if it is zero; require (and discard) parentheses; and add only the // parsed register operand to `Operands`. // // These operands are printed with RISCVInstPrinter::printAtomicMemOp, which // will only print the register surrounded by parentheses (which GNU as also // uses as its canonical representation for these operands). std::unique_ptr OptionalImmOp; if (getLexer().isNot(AsmToken::LParen)) { // Parse an Integer token. We do not accept arbritrary constant expressions // in the offset field (because they may include parens, which complicates // parsing a lot). int64_t ImmVal; SMLoc ImmStart = getLoc(); if (getParser().parseIntToken(ImmVal, "expected '(' or optional integer offset")) return MatchOperand_ParseFail; // Create a RISCVOperand for checking later (so the error messages are // nicer), but we don't add it to Operands. SMLoc ImmEnd = getLoc(); OptionalImmOp = RISCVOperand::createImm(MCConstantExpr::create(ImmVal, getContext()), ImmStart, ImmEnd, isRV64()); } if (getLexer().isNot(AsmToken::LParen)) { Error(getLoc(), OptionalImmOp ? "expected '(' after optional integer offset" : "expected '(' or optional integer offset"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat '(' if (parseRegister(Operands) != MatchOperand_Success) { Error(getLoc(), "expected register"); return MatchOperand_ParseFail; } if (getLexer().isNot(AsmToken::RParen)) { Error(getLoc(), "expected ')'"); return MatchOperand_ParseFail; } getParser().Lex(); // Eat ')' // Deferred Handling of non-zero offsets. This makes the error messages nicer. if (OptionalImmOp && !OptionalImmOp->isImmZero()) { Error(OptionalImmOp->getStartLoc(), "optional integer offset must be 0", SMRange(OptionalImmOp->getStartLoc(), OptionalImmOp->getEndLoc())); return MatchOperand_ParseFail; } return MatchOperand_Success; } /// Looks at a token type and creates the relevant operand from this /// information, adding to Operands. If operand was parsed, returns false, else /// true. bool RISCVAsmParser::parseOperand(OperandVector &Operands, StringRef Mnemonic) { // Check if the current operand has a custom associated parser, if so, try to // custom parse the operand, or fallback to the general approach. OperandMatchResultTy Result = MatchOperandParserImpl(Operands, Mnemonic, /*ParseForAllFeatures=*/true); if (Result == MatchOperand_Success) return false; if (Result == MatchOperand_ParseFail) return true; // Attempt to parse token as a register. if (parseRegister(Operands, true) == MatchOperand_Success) return false; // Attempt to parse token as an immediate if (parseImmediate(Operands) == MatchOperand_Success) { // Parse memory base register if present if (getLexer().is(AsmToken::LParen)) return parseMemOpBaseReg(Operands) != MatchOperand_Success; return false; } // Finally we have exhausted all options and must declare defeat. Error(getLoc(), "unknown operand"); return true; } bool RISCVAsmParser::ParseInstruction(ParseInstructionInfo &Info, StringRef Name, SMLoc NameLoc, OperandVector &Operands) { // Ensure that if the instruction occurs when relaxation is enabled, // relocations are forced for the file. Ideally this would be done when there // is enough information to reliably determine if the instruction itself may // cause relaxations. Unfortunately instruction processing stage occurs in the // same pass as relocation emission, so it's too late to set a 'sticky bit' // for the entire file. if (getSTI().getFeatureBits()[RISCV::FeatureRelax]) { auto *Assembler = getTargetStreamer().getStreamer().getAssemblerPtr(); if (Assembler != nullptr) { RISCVAsmBackend &MAB = static_cast(Assembler->getBackend()); MAB.setForceRelocs(); } } // First operand is token for instruction Operands.push_back(RISCVOperand::createToken(Name, NameLoc, isRV64())); // If there are no more operands, then finish if (getLexer().is(AsmToken::EndOfStatement)) return false; // Parse first operand if (parseOperand(Operands, Name)) return true; // Parse until end of statement, consuming commas between operands unsigned OperandIdx = 1; while (getLexer().is(AsmToken::Comma)) { // Consume comma token getLexer().Lex(); // Parse next operand if (parseOperand(Operands, Name)) return true; ++OperandIdx; } if (getLexer().isNot(AsmToken::EndOfStatement)) { SMLoc Loc = getLexer().getLoc(); getParser().eatToEndOfStatement(); return Error(Loc, "unexpected token"); } getParser().Lex(); // Consume the EndOfStatement. return false; } bool RISCVAsmParser::classifySymbolRef(const MCExpr *Expr, RISCVMCExpr::VariantKind &Kind, int64_t &Addend) { Kind = RISCVMCExpr::VK_RISCV_None; Addend = 0; if (const RISCVMCExpr *RE = dyn_cast(Expr)) { Kind = RE->getKind(); Expr = RE->getSubExpr(); } // It's a simple symbol reference or constant with no addend. if (isa(Expr) || isa(Expr)) return true; const MCBinaryExpr *BE = dyn_cast(Expr); if (!BE) return false; if (!isa(BE->getLHS())) return false; if (BE->getOpcode() != MCBinaryExpr::Add && BE->getOpcode() != MCBinaryExpr::Sub) return false; // We are able to support the subtraction of two symbol references if (BE->getOpcode() == MCBinaryExpr::Sub && isa(BE->getRHS())) return true; // See if the addend is a constant, otherwise there's more going // on here than we can deal with. auto AddendExpr = dyn_cast(BE->getRHS()); if (!AddendExpr) return false; Addend = AddendExpr->getValue(); if (BE->getOpcode() == MCBinaryExpr::Sub) Addend = -Addend; // It's some symbol reference + a constant addend return Kind != RISCVMCExpr::VK_RISCV_Invalid; } bool RISCVAsmParser::ParseDirective(AsmToken DirectiveID) { // This returns false if this function recognizes the directive // regardless of whether it is successfully handles or reports an // error. Otherwise it returns true to give the generic parser a // chance at recognizing it. StringRef IDVal = DirectiveID.getString(); if (IDVal == ".option") return parseDirectiveOption(); else if (IDVal == ".attribute") return parseDirectiveAttribute(); return true; } bool RISCVAsmParser::parseDirectiveOption() { MCAsmParser &Parser = getParser(); // Get the option token. AsmToken Tok = Parser.getTok(); // At the moment only identifiers are supported. if (Tok.isNot(AsmToken::Identifier)) return Error(Parser.getTok().getLoc(), "unexpected token, expected identifier"); StringRef Option = Tok.getIdentifier(); if (Option == "push") { getTargetStreamer().emitDirectiveOptionPush(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); pushFeatureBits(); return false; } if (Option == "pop") { SMLoc StartLoc = Parser.getTok().getLoc(); getTargetStreamer().emitDirectiveOptionPop(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); if (popFeatureBits()) return Error(StartLoc, ".option pop with no .option push"); return false; } if (Option == "rvc") { getTargetStreamer().emitDirectiveOptionRVC(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); setFeatureBits(RISCV::FeatureStdExtC, "c"); return false; } if (Option == "norvc") { getTargetStreamer().emitDirectiveOptionNoRVC(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); clearFeatureBits(RISCV::FeatureStdExtC, "c"); return false; } if (Option == "pic") { getTargetStreamer().emitDirectiveOptionPIC(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); ParserOptions.IsPicEnabled = true; return false; } if (Option == "nopic") { getTargetStreamer().emitDirectiveOptionNoPIC(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); ParserOptions.IsPicEnabled = false; return false; } if (Option == "relax") { getTargetStreamer().emitDirectiveOptionRelax(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); setFeatureBits(RISCV::FeatureRelax, "relax"); return false; } if (Option == "norelax") { getTargetStreamer().emitDirectiveOptionNoRelax(); Parser.Lex(); if (Parser.getTok().isNot(AsmToken::EndOfStatement)) return Error(Parser.getTok().getLoc(), "unexpected token, expected end of statement"); clearFeatureBits(RISCV::FeatureRelax, "relax"); return false; } // Unknown option. Warning(Parser.getTok().getLoc(), "unknown option, expected 'push', 'pop', 'rvc', 'norvc', 'relax' or " "'norelax'"); Parser.eatToEndOfStatement(); return false; } /// parseDirectiveAttribute /// ::= .attribute expression ',' ( expression | "string" ) /// ::= .attribute identifier ',' ( expression | "string" ) bool RISCVAsmParser::parseDirectiveAttribute() { MCAsmParser &Parser = getParser(); int64_t Tag; SMLoc TagLoc; TagLoc = Parser.getTok().getLoc(); if (Parser.getTok().is(AsmToken::Identifier)) { StringRef Name = Parser.getTok().getIdentifier(); Optional Ret = ELFAttrs::attrTypeFromString(Name, RISCVAttrs::RISCVAttributeTags); if (!Ret.hasValue()) { Error(TagLoc, "attribute name not recognised: " + Name); return false; } Tag = Ret.getValue(); Parser.Lex(); } else { const MCExpr *AttrExpr; TagLoc = Parser.getTok().getLoc(); if (Parser.parseExpression(AttrExpr)) return true; const MCConstantExpr *CE = dyn_cast(AttrExpr); if (check(!CE, TagLoc, "expected numeric constant")) return true; Tag = CE->getValue(); } if (Parser.parseToken(AsmToken::Comma, "comma expected")) return true; StringRef StringValue; int64_t IntegerValue = 0; bool IsIntegerValue = true; // RISC-V attributes have a string value if the tag number is odd // and an integer value if the tag number is even. if (Tag % 2) IsIntegerValue = false; SMLoc ValueExprLoc = Parser.getTok().getLoc(); if (IsIntegerValue) { const MCExpr *ValueExpr; if (Parser.parseExpression(ValueExpr)) return true; const MCConstantExpr *CE = dyn_cast(ValueExpr); if (!CE) return Error(ValueExprLoc, "expected numeric constant"); IntegerValue = CE->getValue(); } else { if (Parser.getTok().isNot(AsmToken::String)) return Error(Parser.getTok().getLoc(), "expected string constant"); StringValue = Parser.getTok().getStringContents(); Parser.Lex(); } if (Parser.parseToken(AsmToken::EndOfStatement, "unexpected token in '.attribute' directive")) return true; if (Tag == RISCVAttrs::ARCH) { StringRef Arch = StringValue; if (Arch.consume_front("rv32")) clearFeatureBits(RISCV::Feature64Bit, "64bit"); else if (Arch.consume_front("rv64")) setFeatureBits(RISCV::Feature64Bit, "64bit"); else return Error(ValueExprLoc, "bad arch string " + Arch); while (!Arch.empty()) { if (Arch[0] == 'i') clearFeatureBits(RISCV::FeatureRV32E, "e"); else if (Arch[0] == 'e') setFeatureBits(RISCV::FeatureRV32E, "e"); else if (Arch[0] == 'g') { clearFeatureBits(RISCV::FeatureRV32E, "e"); setFeatureBits(RISCV::FeatureStdExtM, "m"); setFeatureBits(RISCV::FeatureStdExtA, "a"); setFeatureBits(RISCV::FeatureStdExtF, "f"); setFeatureBits(RISCV::FeatureStdExtD, "d"); } else if (Arch[0] == 'm') setFeatureBits(RISCV::FeatureStdExtM, "m"); else if (Arch[0] == 'a') setFeatureBits(RISCV::FeatureStdExtA, "a"); else if (Arch[0] == 'f') setFeatureBits(RISCV::FeatureStdExtF, "f"); else if (Arch[0] == 'd') { setFeatureBits(RISCV::FeatureStdExtF, "f"); setFeatureBits(RISCV::FeatureStdExtD, "d"); } else if (Arch[0] == 'c') { setFeatureBits(RISCV::FeatureStdExtC, "c"); } else return Error(ValueExprLoc, "bad arch string " + Arch); Arch = Arch.drop_front(1); int major = 0; int minor = 0; Arch.consumeInteger(10, major); Arch.consume_front("p"); Arch.consumeInteger(10, minor); if (major != 0 || minor != 0) { Arch = Arch.drop_until([](char c) { return c == '_' || c == '"'; }); Arch = Arch.drop_while([](char c) { return c == '_'; }); } } } if (IsIntegerValue) getTargetStreamer().emitAttribute(Tag, IntegerValue); else { if (Tag != RISCVAttrs::ARCH) { getTargetStreamer().emitTextAttribute(Tag, StringValue); } else { std::string formalArchStr = "rv32"; if (getFeatureBits(RISCV::Feature64Bit)) formalArchStr = "rv64"; if (getFeatureBits(RISCV::FeatureRV32E)) formalArchStr = (Twine(formalArchStr) + "e1p9").str(); else formalArchStr = (Twine(formalArchStr) + "i2p0").str(); if (getFeatureBits(RISCV::FeatureStdExtM)) formalArchStr = (Twine(formalArchStr) + "_m2p0").str(); if (getFeatureBits(RISCV::FeatureStdExtA)) formalArchStr = (Twine(formalArchStr) + "_a2p0").str(); if (getFeatureBits(RISCV::FeatureStdExtF)) formalArchStr = (Twine(formalArchStr) + "_f2p0").str(); if (getFeatureBits(RISCV::FeatureStdExtD)) formalArchStr = (Twine(formalArchStr) + "_d2p0").str(); if (getFeatureBits(RISCV::FeatureStdExtC)) formalArchStr = (Twine(formalArchStr) + "_c2p0").str(); getTargetStreamer().emitTextAttribute(Tag, formalArchStr); } } return false; } void RISCVAsmParser::emitToStreamer(MCStreamer &S, const MCInst &Inst) { MCInst CInst; bool Res = compressInst(CInst, Inst, getSTI(), S.getContext()); if (Res) ++RISCVNumInstrsCompressed; S.emitInstruction((Res ? CInst : Inst), getSTI()); } void RISCVAsmParser::emitLoadImm(Register DestReg, int64_t Value, MCStreamer &Out) { RISCVMatInt::InstSeq Seq; RISCVMatInt::generateInstSeq(Value, isRV64(), Seq); Register SrcReg = RISCV::X0; for (RISCVMatInt::Inst &Inst : Seq) { if (Inst.Opc == RISCV::LUI) { emitToStreamer( Out, MCInstBuilder(RISCV::LUI).addReg(DestReg).addImm(Inst.Imm)); } else { emitToStreamer( Out, MCInstBuilder(Inst.Opc).addReg(DestReg).addReg(SrcReg).addImm( Inst.Imm)); } // Only the first instruction has X0 as its source. SrcReg = DestReg; } } void RISCVAsmParser::emitAuipcInstPair(MCOperand DestReg, MCOperand TmpReg, const MCExpr *Symbol, RISCVMCExpr::VariantKind VKHi, unsigned SecondOpcode, SMLoc IDLoc, MCStreamer &Out) { // A pair of instructions for PC-relative addressing; expands to // TmpLabel: AUIPC TmpReg, VKHi(symbol) // OP DestReg, TmpReg, %pcrel_lo(TmpLabel) MCContext &Ctx = getContext(); MCSymbol *TmpLabel = Ctx.createTempSymbol( "pcrel_hi", /* AlwaysAddSuffix */ true, /* CanBeUnnamed */ false); Out.emitLabel(TmpLabel); const RISCVMCExpr *SymbolHi = RISCVMCExpr::create(Symbol, VKHi, Ctx); emitToStreamer( Out, MCInstBuilder(RISCV::AUIPC).addOperand(TmpReg).addExpr(SymbolHi)); const MCExpr *RefToLinkTmpLabel = RISCVMCExpr::create(MCSymbolRefExpr::create(TmpLabel, Ctx), RISCVMCExpr::VK_RISCV_PCREL_LO, Ctx); emitToStreamer(Out, MCInstBuilder(SecondOpcode) .addOperand(DestReg) .addOperand(TmpReg) .addExpr(RefToLinkTmpLabel)); } void RISCVAsmParser::emitLoadLocalAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out) { // The load local address pseudo-instruction "lla" is used in PC-relative // addressing of local symbols: // lla rdest, symbol // expands to // TmpLabel: AUIPC rdest, %pcrel_hi(symbol) // ADDI rdest, rdest, %pcrel_lo(TmpLabel) MCOperand DestReg = Inst.getOperand(0); const MCExpr *Symbol = Inst.getOperand(1).getExpr(); emitAuipcInstPair(DestReg, DestReg, Symbol, RISCVMCExpr::VK_RISCV_PCREL_HI, RISCV::ADDI, IDLoc, Out); } void RISCVAsmParser::emitLoadAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out) { // The load address pseudo-instruction "la" is used in PC-relative and // GOT-indirect addressing of global symbols: // la rdest, symbol // expands to either (for non-PIC) // TmpLabel: AUIPC rdest, %pcrel_hi(symbol) // ADDI rdest, rdest, %pcrel_lo(TmpLabel) // or (for PIC) // TmpLabel: AUIPC rdest, %got_pcrel_hi(symbol) // Lx rdest, %pcrel_lo(TmpLabel)(rdest) MCOperand DestReg = Inst.getOperand(0); const MCExpr *Symbol = Inst.getOperand(1).getExpr(); unsigned SecondOpcode; RISCVMCExpr::VariantKind VKHi; if (ParserOptions.IsPicEnabled) { SecondOpcode = isRV64() ? RISCV::LD : RISCV::LW; VKHi = RISCVMCExpr::VK_RISCV_GOT_HI; } else { SecondOpcode = RISCV::ADDI; VKHi = RISCVMCExpr::VK_RISCV_PCREL_HI; } emitAuipcInstPair(DestReg, DestReg, Symbol, VKHi, SecondOpcode, IDLoc, Out); } void RISCVAsmParser::emitLoadTLSIEAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out) { // The load TLS IE address pseudo-instruction "la.tls.ie" is used in // initial-exec TLS model addressing of global symbols: // la.tls.ie rdest, symbol // expands to // TmpLabel: AUIPC rdest, %tls_ie_pcrel_hi(symbol) // Lx rdest, %pcrel_lo(TmpLabel)(rdest) MCOperand DestReg = Inst.getOperand(0); const MCExpr *Symbol = Inst.getOperand(1).getExpr(); unsigned SecondOpcode = isRV64() ? RISCV::LD : RISCV::LW; emitAuipcInstPair(DestReg, DestReg, Symbol, RISCVMCExpr::VK_RISCV_TLS_GOT_HI, SecondOpcode, IDLoc, Out); } void RISCVAsmParser::emitLoadTLSGDAddress(MCInst &Inst, SMLoc IDLoc, MCStreamer &Out) { // The load TLS GD address pseudo-instruction "la.tls.gd" is used in // global-dynamic TLS model addressing of global symbols: // la.tls.gd rdest, symbol // expands to // TmpLabel: AUIPC rdest, %tls_gd_pcrel_hi(symbol) // ADDI rdest, rdest, %pcrel_lo(TmpLabel) MCOperand DestReg = Inst.getOperand(0); const MCExpr *Symbol = Inst.getOperand(1).getExpr(); emitAuipcInstPair(DestReg, DestReg, Symbol, RISCVMCExpr::VK_RISCV_TLS_GD_HI, RISCV::ADDI, IDLoc, Out); } void RISCVAsmParser::emitLoadStoreSymbol(MCInst &Inst, unsigned Opcode, SMLoc IDLoc, MCStreamer &Out, bool HasTmpReg) { // The load/store pseudo-instruction does a pc-relative load with // a symbol. // // The expansion looks like this // // TmpLabel: AUIPC tmp, %pcrel_hi(symbol) // [S|L]X rd, %pcrel_lo(TmpLabel)(tmp) MCOperand DestReg = Inst.getOperand(0); unsigned SymbolOpIdx = HasTmpReg ? 2 : 1; unsigned TmpRegOpIdx = HasTmpReg ? 1 : 0; MCOperand TmpReg = Inst.getOperand(TmpRegOpIdx); const MCExpr *Symbol = Inst.getOperand(SymbolOpIdx).getExpr(); emitAuipcInstPair(DestReg, TmpReg, Symbol, RISCVMCExpr::VK_RISCV_PCREL_HI, Opcode, IDLoc, Out); } bool RISCVAsmParser::checkPseudoAddTPRel(MCInst &Inst, OperandVector &Operands) { assert(Inst.getOpcode() == RISCV::PseudoAddTPRel && "Invalid instruction"); assert(Inst.getOperand(2).isReg() && "Unexpected second operand kind"); if (Inst.getOperand(2).getReg() != RISCV::X4) { SMLoc ErrorLoc = ((RISCVOperand &)*Operands[3]).getStartLoc(); return Error(ErrorLoc, "the second input operand must be tp/x4 when using " "%tprel_add modifier"); } return false; } std::unique_ptr RISCVAsmParser::defaultMaskRegOp() const { return RISCVOperand::createReg(RISCV::NoRegister, llvm::SMLoc(), llvm::SMLoc(), isRV64()); } bool RISCVAsmParser::validateInstruction(MCInst &Inst, OperandVector &Operands) { const MCInstrDesc &MCID = MII.get(Inst.getOpcode()); unsigned TargetFlags = (MCID.TSFlags >> RISCV::ConstraintOffset) & RISCV::ConstraintMask; if (TargetFlags == RISCV::NoConstraint) return false; unsigned DestReg = Inst.getOperand(0).getReg(); // Operands[1] will be the first operand, DestReg. SMLoc Loc = Operands[1]->getStartLoc(); if ((TargetFlags == RISCV::WidenV) || (TargetFlags == RISCV::WidenW) || (TargetFlags == RISCV::SlideUp) || (TargetFlags == RISCV::Vrgather) || (TargetFlags == RISCV::Vcompress)) { if (TargetFlags != RISCV::WidenW) { unsigned Src2Reg = Inst.getOperand(1).getReg(); if (DestReg == Src2Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); if (TargetFlags == RISCV::WidenV) { // Assume DestReg LMUL is 2 at least for widening/narrowing operations. if (DestReg + 1 == Src2Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); } } if (Inst.getOperand(2).isReg()) { unsigned Src1Reg = Inst.getOperand(2).getReg(); if (DestReg == Src1Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); if (TargetFlags == RISCV::WidenV || TargetFlags == RISCV::WidenW) { // Assume DestReg LMUL is 2 at least for widening/narrowing operations. if (DestReg + 1 == Src1Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); } } if (Inst.getNumOperands() == 4) { unsigned MaskReg = Inst.getOperand(3).getReg(); if (DestReg == MaskReg) return Error(Loc, "The destination vector register group cannot overlap" " the mask register."); } } else if (TargetFlags == RISCV::Narrow) { unsigned Src2Reg = Inst.getOperand(1).getReg(); if (DestReg == Src2Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); // Assume Src2Reg LMUL is 2 at least for widening/narrowing operations. if (DestReg == Src2Reg + 1) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); } else if (TargetFlags == RISCV::WidenCvt || TargetFlags == RISCV::Iota) { unsigned Src2Reg = Inst.getOperand(1).getReg(); if (DestReg == Src2Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); if (TargetFlags == RISCV::WidenCvt) { // Assume DestReg LMUL is 2 at least for widening/narrowing operations. if (DestReg + 1 == Src2Reg) return Error(Loc, "The destination vector register group cannot overlap" " the source vector register group."); } if (Inst.getNumOperands() == 3) { unsigned MaskReg = Inst.getOperand(2).getReg(); if (DestReg == MaskReg) return Error(Loc, "The destination vector register group cannot overlap" " the mask register."); } } return false; } bool RISCVAsmParser::processInstruction(MCInst &Inst, SMLoc IDLoc, OperandVector &Operands, MCStreamer &Out) { Inst.setLoc(IDLoc); switch (Inst.getOpcode()) { default: break; case RISCV::PseudoLI: { Register Reg = Inst.getOperand(0).getReg(); const MCOperand &Op1 = Inst.getOperand(1); if (Op1.isExpr()) { // We must have li reg, %lo(sym) or li reg, %pcrel_lo(sym) or similar. // Just convert to an addi. This allows compatibility with gas. emitToStreamer(Out, MCInstBuilder(RISCV::ADDI) .addReg(Reg) .addReg(RISCV::X0) .addExpr(Op1.getExpr())); return false; } int64_t Imm = Inst.getOperand(1).getImm(); // On RV32 the immediate here can either be a signed or an unsigned // 32-bit number. Sign extension has to be performed to ensure that Imm // represents the expected signed 64-bit number. if (!isRV64()) Imm = SignExtend64<32>(Imm); emitLoadImm(Reg, Imm, Out); return false; } case RISCV::PseudoLLA: emitLoadLocalAddress(Inst, IDLoc, Out); return false; case RISCV::PseudoLA: emitLoadAddress(Inst, IDLoc, Out); return false; case RISCV::PseudoLA_TLS_IE: emitLoadTLSIEAddress(Inst, IDLoc, Out); return false; case RISCV::PseudoLA_TLS_GD: emitLoadTLSGDAddress(Inst, IDLoc, Out); return false; case RISCV::PseudoLB: emitLoadStoreSymbol(Inst, RISCV::LB, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLBU: emitLoadStoreSymbol(Inst, RISCV::LBU, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLH: emitLoadStoreSymbol(Inst, RISCV::LH, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLHU: emitLoadStoreSymbol(Inst, RISCV::LHU, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLW: emitLoadStoreSymbol(Inst, RISCV::LW, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLWU: emitLoadStoreSymbol(Inst, RISCV::LWU, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoLD: emitLoadStoreSymbol(Inst, RISCV::LD, IDLoc, Out, /*HasTmpReg=*/false); return false; case RISCV::PseudoFLW: emitLoadStoreSymbol(Inst, RISCV::FLW, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoFLD: emitLoadStoreSymbol(Inst, RISCV::FLD, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoSB: emitLoadStoreSymbol(Inst, RISCV::SB, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoSH: emitLoadStoreSymbol(Inst, RISCV::SH, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoSW: emitLoadStoreSymbol(Inst, RISCV::SW, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoSD: emitLoadStoreSymbol(Inst, RISCV::SD, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoFSW: emitLoadStoreSymbol(Inst, RISCV::FSW, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoFSD: emitLoadStoreSymbol(Inst, RISCV::FSD, IDLoc, Out, /*HasTmpReg=*/true); return false; case RISCV::PseudoAddTPRel: if (checkPseudoAddTPRel(Inst, Operands)) return true; break; } emitToStreamer(Out, Inst); return false; } extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeRISCVAsmParser() { RegisterMCAsmParser X(getTheRISCV32Target()); RegisterMCAsmParser Y(getTheRISCV64Target()); }