//===-- RISCVISelLowering.cpp - RISCV DAG Lowering Implementation  --------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that RISCV uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//

#include "RISCVISelLowering.h"
#include "RISCV.h"
#include "RISCVMachineFunctionInfo.h"
#include "RISCVRegisterInfo.h"
#include "RISCVSubtarget.h"
#include "RISCVTargetMachine.h"
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"

using namespace llvm;

#define DEBUG_TYPE "riscv-lower"

RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
                                         const RISCVSubtarget &STI)
    : TargetLowering(TM), Subtarget(STI) {

  MVT XLenVT = Subtarget.getXLenVT();

  // Set up the register classes.
  addRegisterClass(XLenVT, &RISCV::GPRRegClass);

  // Compute derived properties from the register classes.
  computeRegisterProperties(STI.getRegisterInfo());

  setStackPointerRegisterToSaveRestore(RISCV::X2);

  for (auto N : {ISD::EXTLOAD, ISD::SEXTLOAD, ISD::ZEXTLOAD})
    setLoadExtAction(N, XLenVT, MVT::i1, Promote);

  // TODO: add all necessary setOperationAction calls.
  setOperationAction(ISD::DYNAMIC_STACKALLOC, XLenVT, Expand);

  setOperationAction(ISD::BR_JT, MVT::Other, Expand);
  setOperationAction(ISD::BR_CC, XLenVT, Expand);
  setOperationAction(ISD::SELECT, XLenVT, Custom);
  setOperationAction(ISD::SELECT_CC, XLenVT, Expand);

  setOperationAction(ISD::STACKSAVE, MVT::Other, Expand);
  setOperationAction(ISD::STACKRESTORE, MVT::Other, Expand);

  setOperationAction(ISD::VASTART, MVT::Other, Custom);
  setOperationAction(ISD::VAARG, MVT::Other, Expand);
  setOperationAction(ISD::VACOPY, MVT::Other, Expand);
  setOperationAction(ISD::VAEND, MVT::Other, Expand);

  for (auto VT : {MVT::i1, MVT::i8, MVT::i16})
    setOperationAction(ISD::SIGN_EXTEND_INREG, VT, Expand);

  setOperationAction(ISD::ADDC, XLenVT, Expand);
  setOperationAction(ISD::ADDE, XLenVT, Expand);
  setOperationAction(ISD::SUBC, XLenVT, Expand);
  setOperationAction(ISD::SUBE, XLenVT, Expand);

  setOperationAction(ISD::SREM, XLenVT, Expand);
  setOperationAction(ISD::SDIVREM, XLenVT, Expand);
  setOperationAction(ISD::SDIV, XLenVT, Expand);
  setOperationAction(ISD::UREM, XLenVT, Expand);
  setOperationAction(ISD::UDIVREM, XLenVT, Expand);
  setOperationAction(ISD::UDIV, XLenVT, Expand);

  setOperationAction(ISD::MUL, XLenVT, Expand);
  setOperationAction(ISD::SMUL_LOHI, XLenVT, Expand);
  setOperationAction(ISD::UMUL_LOHI, XLenVT, Expand);
  setOperationAction(ISD::MULHS, XLenVT, Expand);
  setOperationAction(ISD::MULHU, XLenVT, Expand);

  setOperationAction(ISD::SHL_PARTS, XLenVT, Expand);
  setOperationAction(ISD::SRL_PARTS, XLenVT, Expand);
  setOperationAction(ISD::SRA_PARTS, XLenVT, Expand);

  setOperationAction(ISD::ROTL, XLenVT, Expand);
  setOperationAction(ISD::ROTR, XLenVT, Expand);
  setOperationAction(ISD::BSWAP, XLenVT, Expand);
  setOperationAction(ISD::CTTZ, XLenVT, Expand);
  setOperationAction(ISD::CTLZ, XLenVT, Expand);
  setOperationAction(ISD::CTPOP, XLenVT, Expand);

  setOperationAction(ISD::GlobalAddress, XLenVT, Custom);
  setOperationAction(ISD::BlockAddress, XLenVT, Custom);

  setBooleanContents(ZeroOrOneBooleanContent);

  // Function alignments (log2).
  setMinFunctionAlignment(3);
  setPrefFunctionAlignment(3);

  // Effectively disable jump table generation.
  setMinimumJumpTableEntries(INT_MAX);
}

// Changes the condition code and swaps operands if necessary, so the SetCC
// operation matches one of the comparisons supported directly in the RISC-V
// ISA.
static void normaliseSetCC(SDValue &LHS, SDValue &RHS, ISD::CondCode &CC) {
  switch (CC) {
  default:
    break;
  case ISD::SETGT:
  case ISD::SETLE:
  case ISD::SETUGT:
  case ISD::SETULE:
    CC = ISD::getSetCCSwappedOperands(CC);
    std::swap(LHS, RHS);
    break;
  }
}

// Return the RISC-V branch opcode that matches the given DAG integer
// condition code. The CondCode must be one of those supported by the RISC-V
// ISA (see normaliseSetCC).
static unsigned getBranchOpcodeForIntCondCode(ISD::CondCode CC) {
  switch (CC) {
  default:
    llvm_unreachable("Unsupported CondCode");
  case ISD::SETEQ:
    return RISCV::BEQ;
  case ISD::SETNE:
    return RISCV::BNE;
  case ISD::SETLT:
    return RISCV::BLT;
  case ISD::SETGE:
    return RISCV::BGE;
  case ISD::SETULT:
    return RISCV::BLTU;
  case ISD::SETUGE:
    return RISCV::BGEU;
  }
}

SDValue RISCVTargetLowering::LowerOperation(SDValue Op,
                                            SelectionDAG &DAG) const {
  switch (Op.getOpcode()) {
  default:
    report_fatal_error("unimplemented operand");
  case ISD::GlobalAddress:
    return lowerGlobalAddress(Op, DAG);
  case ISD::BlockAddress:
    return lowerBlockAddress(Op, DAG);
  case ISD::SELECT:
    return lowerSELECT(Op, DAG);
  case ISD::VASTART:
    return lowerVASTART(Op, DAG);
  case ISD::FRAMEADDR:
    return LowerFRAMEADDR(Op, DAG);
  case ISD::RETURNADDR:
    return LowerRETURNADDR(Op, DAG);
  }
}

SDValue RISCVTargetLowering::lowerGlobalAddress(SDValue Op,
                                                SelectionDAG &DAG) const {
  SDLoc DL(Op);
  EVT Ty = Op.getValueType();
  GlobalAddressSDNode *N = cast<GlobalAddressSDNode>(Op);
  const GlobalValue *GV = N->getGlobal();
  int64_t Offset = N->getOffset();

  if (isPositionIndependent() || Subtarget.is64Bit())
    report_fatal_error("Unable to lowerGlobalAddress");

  SDValue GAHi =
    DAG.getTargetGlobalAddress(GV, DL, Ty, Offset, RISCVII::MO_HI);
  SDValue GALo =
    DAG.getTargetGlobalAddress(GV, DL, Ty, Offset, RISCVII::MO_LO);
  SDValue MNHi = SDValue(DAG.getMachineNode(RISCV::LUI, DL, Ty, GAHi), 0);
  SDValue MNLo =
    SDValue(DAG.getMachineNode(RISCV::ADDI, DL, Ty, MNHi, GALo), 0);
  return MNLo;
}

SDValue RISCVTargetLowering::lowerBlockAddress(SDValue Op,
                                               SelectionDAG &DAG) const {
  SDLoc DL(Op);
  EVT Ty = Op.getValueType();
  BlockAddressSDNode *N = cast<BlockAddressSDNode>(Op);
  const BlockAddress *BA = N->getBlockAddress();
  int64_t Offset = N->getOffset();

  if (isPositionIndependent() || Subtarget.is64Bit())
    report_fatal_error("Unable to lowerBlockAddress");

  SDValue BAHi = DAG.getTargetBlockAddress(BA, Ty, Offset, RISCVII::MO_HI);
  SDValue BALo = DAG.getTargetBlockAddress(BA, Ty, Offset, RISCVII::MO_LO);
  SDValue MNHi = SDValue(DAG.getMachineNode(RISCV::LUI, DL, Ty, BAHi), 0);
  SDValue MNLo =
    SDValue(DAG.getMachineNode(RISCV::ADDI, DL, Ty, MNHi, BALo), 0);
  return MNLo;
}

SDValue RISCVTargetLowering::lowerExternalSymbol(SDValue Op,
                                                 SelectionDAG &DAG) const {
  SDLoc DL(Op);
  EVT Ty = Op.getValueType();
  ExternalSymbolSDNode *N = cast<ExternalSymbolSDNode>(Op);
  const char *Sym = N->getSymbol();

  // TODO: should also handle gp-relative loads.

  if (isPositionIndependent() || Subtarget.is64Bit())
    report_fatal_error("Unable to lowerExternalSymbol");

  SDValue GAHi = DAG.getTargetExternalSymbol(Sym, Ty, RISCVII::MO_HI);
  SDValue GALo = DAG.getTargetExternalSymbol(Sym, Ty, RISCVII::MO_LO);
  SDValue MNHi = SDValue(DAG.getMachineNode(RISCV::LUI, DL, Ty, GAHi), 0);
  SDValue MNLo =
    SDValue(DAG.getMachineNode(RISCV::ADDI, DL, Ty, MNHi, GALo), 0);
  return MNLo;
}

SDValue RISCVTargetLowering::lowerSELECT(SDValue Op, SelectionDAG &DAG) const {
  SDValue CondV = Op.getOperand(0);
  SDValue TrueV = Op.getOperand(1);
  SDValue FalseV = Op.getOperand(2);
  SDLoc DL(Op);
  MVT XLenVT = Subtarget.getXLenVT();

  // If the result type is XLenVT and CondV is the output of a SETCC node
  // which also operated on XLenVT inputs, then merge the SETCC node into the
  // lowered RISCVISD::SELECT_CC to take advantage of the integer
  // compare+branch instructions. i.e.:
  // (select (setcc lhs, rhs, cc), truev, falsev)
  // -> (riscvisd::select_cc lhs, rhs, cc, truev, falsev)
  if (Op.getSimpleValueType() == XLenVT && CondV.getOpcode() == ISD::SETCC &&
      CondV.getOperand(0).getSimpleValueType() == XLenVT) {
    SDValue LHS = CondV.getOperand(0);
    SDValue RHS = CondV.getOperand(1);
    auto CC = cast<CondCodeSDNode>(CondV.getOperand(2));
    ISD::CondCode CCVal = CC->get();

    normaliseSetCC(LHS, RHS, CCVal);

    SDValue TargetCC = DAG.getConstant(CCVal, DL, XLenVT);
    SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
    SDValue Ops[] = {LHS, RHS, TargetCC, TrueV, FalseV};
    return DAG.getNode(RISCVISD::SELECT_CC, DL, VTs, Ops);
  }

  // Otherwise:
  // (select condv, truev, falsev)
  // -> (riscvisd::select_cc condv, zero, setne, truev, falsev)
  SDValue Zero = DAG.getConstant(0, DL, XLenVT);
  SDValue SetNE = DAG.getConstant(ISD::SETNE, DL, XLenVT);

  SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
  SDValue Ops[] = {CondV, Zero, SetNE, TrueV, FalseV};

  return DAG.getNode(RISCVISD::SELECT_CC, DL, VTs, Ops);
}

SDValue RISCVTargetLowering::lowerVASTART(SDValue Op, SelectionDAG &DAG) const {
  MachineFunction &MF = DAG.getMachineFunction();
  RISCVMachineFunctionInfo *FuncInfo = MF.getInfo<RISCVMachineFunctionInfo>();

  SDLoc DL(Op);
  SDValue FI = DAG.getFrameIndex(FuncInfo->getVarArgsFrameIndex(),
                                 getPointerTy(MF.getDataLayout()));

  // vastart just stores the address of the VarArgsFrameIndex slot into the
  // memory location argument.
  const Value *SV = cast<SrcValueSDNode>(Op.getOperand(2))->getValue();
  return DAG.getStore(Op.getOperand(0), DL, FI, Op.getOperand(1),
                      MachinePointerInfo(SV));
}

SDValue RISCVTargetLowering::LowerFRAMEADDR(SDValue Op,
                                            SelectionDAG &DAG) const {
  const RISCVRegisterInfo &RI = *Subtarget.getRegisterInfo();
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MFI.setFrameAddressIsTaken(true);
  unsigned FrameReg = RI.getFrameRegister(MF);
  int XLenInBytes = Subtarget.getXLen() / 8;

  EVT VT = Op.getValueType();
  SDLoc DL(Op);
  SDValue FrameAddr = DAG.getCopyFromReg(DAG.getEntryNode(), DL, FrameReg, VT);
  unsigned Depth = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
  while (Depth--) {
    int Offset = -(XLenInBytes * 2);
    SDValue Ptr = DAG.getNode(ISD::ADD, DL, VT, FrameAddr,
                              DAG.getIntPtrConstant(Offset, DL));
    FrameAddr =
        DAG.getLoad(VT, DL, DAG.getEntryNode(), Ptr, MachinePointerInfo());
  }
  return FrameAddr;
}

SDValue RISCVTargetLowering::LowerRETURNADDR(SDValue Op,
                                             SelectionDAG &DAG) const {
  const RISCVRegisterInfo &RI = *Subtarget.getRegisterInfo();
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MFI.setReturnAddressIsTaken(true);
  MVT XLenVT = Subtarget.getXLenVT();
  int XLenInBytes = Subtarget.getXLen() / 8;

  if (verifyReturnAddressArgumentIsConstant(Op, DAG))
    return SDValue();

  EVT VT = Op.getValueType();
  SDLoc DL(Op);
  unsigned Depth = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
  if (Depth) {
    int Off = -XLenInBytes;
    SDValue FrameAddr = LowerFRAMEADDR(Op, DAG);
    SDValue Offset = DAG.getConstant(Off, DL, VT);
    return DAG.getLoad(VT, DL, DAG.getEntryNode(),
                       DAG.getNode(ISD::ADD, DL, VT, FrameAddr, Offset),
                       MachinePointerInfo());
  }

  // Return the value of the return address register, marking it an implicit
  // live-in.
  unsigned Reg = MF.addLiveIn(RI.getRARegister(), getRegClassFor(XLenVT));
  return DAG.getCopyFromReg(DAG.getEntryNode(), DL, Reg, XLenVT);
}

MachineBasicBlock *
RISCVTargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
                                                 MachineBasicBlock *BB) const {
  const TargetInstrInfo &TII = *BB->getParent()->getSubtarget().getInstrInfo();
  DebugLoc DL = MI.getDebugLoc();

  assert(MI.getOpcode() == RISCV::Select_GPR_Using_CC_GPR &&
         "Unexpected instr type to insert");

  // To "insert" a SELECT instruction, we actually have to insert the triangle
  // control-flow pattern.  The incoming instruction knows the destination vreg
  // to set, the condition code register to branch on, the true/false values to
  // select between, and the condcode to use to select the appropriate branch.
  //
  // We produce the following control flow:
  //     HeadMBB
  //     |  \
  //     |  IfFalseMBB
  //     | /
  //    TailMBB
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineFunction::iterator I = ++BB->getIterator();

  MachineBasicBlock *HeadMBB = BB;
  MachineFunction *F = BB->getParent();
  MachineBasicBlock *TailMBB = F->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *IfFalseMBB = F->CreateMachineBasicBlock(LLVM_BB);

  F->insert(I, IfFalseMBB);
  F->insert(I, TailMBB);
  // Move all remaining instructions to TailMBB.
  TailMBB->splice(TailMBB->begin(), HeadMBB,
                  std::next(MachineBasicBlock::iterator(MI)), HeadMBB->end());
  // Update machine-CFG edges by transferring all successors of the current
  // block to the new block which will contain the Phi node for the select.
  TailMBB->transferSuccessorsAndUpdatePHIs(HeadMBB);
  // Set the successors for HeadMBB.
  HeadMBB->addSuccessor(IfFalseMBB);
  HeadMBB->addSuccessor(TailMBB);

  // Insert appropriate branch.
  unsigned LHS = MI.getOperand(1).getReg();
  unsigned RHS = MI.getOperand(2).getReg();
  auto CC = static_cast<ISD::CondCode>(MI.getOperand(3).getImm());
  unsigned Opcode = getBranchOpcodeForIntCondCode(CC);

  BuildMI(HeadMBB, DL, TII.get(Opcode))
    .addReg(LHS)
    .addReg(RHS)
    .addMBB(TailMBB);

  // IfFalseMBB just falls through to TailMBB.
  IfFalseMBB->addSuccessor(TailMBB);

  // %Result = phi [ %TrueValue, HeadMBB ], [ %FalseValue, IfFalseMBB ]
  BuildMI(*TailMBB, TailMBB->begin(), DL, TII.get(RISCV::PHI),
          MI.getOperand(0).getReg())
      .addReg(MI.getOperand(4).getReg())
      .addMBB(HeadMBB)
      .addReg(MI.getOperand(5).getReg())
      .addMBB(IfFalseMBB);

  MI.eraseFromParent(); // The pseudo instruction is gone now.
  return TailMBB;
}

// Calling Convention Implementation.
// The expectations for frontend ABI lowering vary from target to target.
// Ideally, an LLVM frontend would be able to avoid worrying about many ABI
// details, but this is a longer term goal. For now, we simply try to keep the
// role of the frontend as simple and well-defined as possible. The rules can
// be summarised as:
// * Never split up large scalar arguments. We handle them here.
// * If a hardfloat calling convention is being used, and the struct may be
// passed in a pair of registers (fp+fp, int+fp), and both registers are
// available, then pass as two separate arguments. If either the GPRs or FPRs
// are exhausted, then pass according to the rule below.
// * If a struct could never be passed in registers or directly in a stack
// slot (as it is larger than 2*XLEN and the floating point rules don't
// apply), then pass it using a pointer with the byval attribute.
// * If a struct is less than 2*XLEN, then coerce to either a two-element
// word-sized array or a 2*XLEN scalar (depending on alignment).
// * The frontend can determine whether a struct is returned by reference or
// not based on its size and fields. If it will be returned by reference, the
// frontend must modify the prototype so a pointer with the sret annotation is
// passed as the first argument. This is not necessary for large scalar
// returns.
// * Struct return values and varargs should be coerced to structs containing
// register-size fields in the same situations they would be for fixed
// arguments.

static const MCPhysReg ArgGPRs[] = {
  RISCV::X10, RISCV::X11, RISCV::X12, RISCV::X13,
  RISCV::X14, RISCV::X15, RISCV::X16, RISCV::X17
};

// Pass a 2*XLEN argument that has been split into two XLEN values through
// registers or the stack as necessary.
static bool CC_RISCVAssign2XLen(unsigned XLen, CCState &State, CCValAssign VA1,
                                ISD::ArgFlagsTy ArgFlags1, unsigned ValNo2,
                                MVT ValVT2, MVT LocVT2,
                                ISD::ArgFlagsTy ArgFlags2) {
  unsigned XLenInBytes = XLen / 8;
  if (unsigned Reg = State.AllocateReg(ArgGPRs)) {
    // At least one half can be passed via register.
    State.addLoc(CCValAssign::getReg(VA1.getValNo(), VA1.getValVT(), Reg,
                                     VA1.getLocVT(), CCValAssign::Full));
  } else {
    // Both halves must be passed on the stack, with proper alignment.
    unsigned StackAlign = std::max(XLenInBytes, ArgFlags1.getOrigAlign());
    State.addLoc(
        CCValAssign::getMem(VA1.getValNo(), VA1.getValVT(),
                            State.AllocateStack(XLenInBytes, StackAlign),
                            VA1.getLocVT(), CCValAssign::Full));
    State.addLoc(CCValAssign::getMem(
        ValNo2, ValVT2, State.AllocateStack(XLenInBytes, XLenInBytes), LocVT2,
        CCValAssign::Full));
    return false;
  }

  if (unsigned Reg = State.AllocateReg(ArgGPRs)) {
    // The second half can also be passed via register.
    State.addLoc(
        CCValAssign::getReg(ValNo2, ValVT2, Reg, LocVT2, CCValAssign::Full));
  } else {
    // The second half is passed via the stack, without additional alignment.
    State.addLoc(CCValAssign::getMem(
        ValNo2, ValVT2, State.AllocateStack(XLenInBytes, XLenInBytes), LocVT2,
        CCValAssign::Full));
  }

  return false;
}

// Implements the RISC-V calling convention. Returns true upon failure.
static bool CC_RISCV(const DataLayout &DL, unsigned ValNo, MVT ValVT, MVT LocVT,
                     CCValAssign::LocInfo LocInfo, ISD::ArgFlagsTy ArgFlags,
                     CCState &State, bool IsFixed, bool IsRet, Type *OrigTy) {
  unsigned XLen = DL.getLargestLegalIntTypeSizeInBits();
  assert(XLen == 32 || XLen == 64);
  MVT XLenVT = XLen == 32 ? MVT::i32 : MVT::i64;
  assert(ValVT == XLenVT && "Unexpected ValVT");
  assert(LocVT == XLenVT && "Unexpected LocVT");

  // Any return value split in to more than two values can't be returned
  // directly.
  if (IsRet && ValNo > 1)
    return true;

  // If this is a variadic argument, the RISC-V calling convention requires
  // that it is assigned an 'even' or 'aligned' register if it has 8-byte
  // alignment (RV32) or 16-byte alignment (RV64). An aligned register should
  // be used regardless of whether the original argument was split during
  // legalisation or not. The argument will not be passed by registers if the
  // original type is larger than 2*XLEN, so the register alignment rule does
  // not apply.
  unsigned TwoXLenInBytes = (2 * XLen) / 8;
  if (!IsFixed && ArgFlags.getOrigAlign() == TwoXLenInBytes &&
      DL.getTypeAllocSize(OrigTy) == TwoXLenInBytes) {
    unsigned RegIdx = State.getFirstUnallocated(ArgGPRs);
    // Skip 'odd' register if necessary.
    if (RegIdx != array_lengthof(ArgGPRs) && RegIdx % 2 == 1)
      State.AllocateReg(ArgGPRs);
  }

  SmallVectorImpl<CCValAssign> &PendingLocs = State.getPendingLocs();
  SmallVectorImpl<ISD::ArgFlagsTy> &PendingArgFlags =
      State.getPendingArgFlags();

  assert(PendingLocs.size() == PendingArgFlags.size() &&
         "PendingLocs and PendingArgFlags out of sync");

  // Split arguments might be passed indirectly, so keep track of the pending
  // values.
  if (ArgFlags.isSplit() || !PendingLocs.empty()) {
    LocVT = XLenVT;
    LocInfo = CCValAssign::Indirect;
    PendingLocs.push_back(
        CCValAssign::getPending(ValNo, ValVT, LocVT, LocInfo));
    PendingArgFlags.push_back(ArgFlags);
    if (!ArgFlags.isSplitEnd()) {
      return false;
    }
  }

  // If the split argument only had two elements, it should be passed directly
  // in registers or on the stack.
  if (ArgFlags.isSplitEnd() && PendingLocs.size() <= 2) {
    assert(PendingLocs.size() == 2 && "Unexpected PendingLocs.size()");
    // Apply the normal calling convention rules to the first half of the
    // split argument.
    CCValAssign VA = PendingLocs[0];
    ISD::ArgFlagsTy AF = PendingArgFlags[0];
    PendingLocs.clear();
    PendingArgFlags.clear();
    return CC_RISCVAssign2XLen(XLen, State, VA, AF, ValNo, ValVT, LocVT,
                               ArgFlags);
  }

  // Allocate to a register if possible, or else a stack slot.
  unsigned Reg = State.AllocateReg(ArgGPRs);
  unsigned StackOffset = Reg ? 0 : State.AllocateStack(XLen / 8, XLen / 8);

  // If we reach this point and PendingLocs is non-empty, we must be at the
  // end of a split argument that must be passed indirectly.
  if (!PendingLocs.empty()) {
    assert(ArgFlags.isSplitEnd() && "Expected ArgFlags.isSplitEnd()");
    assert(PendingLocs.size() > 2 && "Unexpected PendingLocs.size()");

    for (auto &It : PendingLocs) {
      if (Reg)
        It.convertToReg(Reg);
      else
        It.convertToMem(StackOffset);
      State.addLoc(It);
    }
    PendingLocs.clear();
    PendingArgFlags.clear();
    return false;
  }

  assert(LocVT == XLenVT && "Expected an XLenVT at this stage");

  if (Reg) {
    State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
  } else {
    State.addLoc(
        CCValAssign::getMem(ValNo, ValVT, StackOffset, LocVT, LocInfo));
  }
  return false;
}

void RISCVTargetLowering::analyzeInputArgs(
    MachineFunction &MF, CCState &CCInfo,
    const SmallVectorImpl<ISD::InputArg> &Ins, bool IsRet) const {
  unsigned NumArgs = Ins.size();
  FunctionType *FType = MF.getFunction().getFunctionType();

  for (unsigned i = 0; i != NumArgs; ++i) {
    MVT ArgVT = Ins[i].VT;
    ISD::ArgFlagsTy ArgFlags = Ins[i].Flags;

    Type *ArgTy = nullptr;
    if (IsRet)
      ArgTy = FType->getReturnType();
    else if (Ins[i].isOrigArg())
      ArgTy = FType->getParamType(Ins[i].getOrigArgIndex());

    if (CC_RISCV(MF.getDataLayout(), i, ArgVT, ArgVT, CCValAssign::Full,
                 ArgFlags, CCInfo, /*IsRet=*/true, IsRet, ArgTy)) {
      DEBUG(dbgs() << "InputArg #" << i << " has unhandled type "
                   << EVT(ArgVT).getEVTString() << '\n');
      llvm_unreachable(nullptr);
    }
  }
}

void RISCVTargetLowering::analyzeOutputArgs(
    MachineFunction &MF, CCState &CCInfo,
    const SmallVectorImpl<ISD::OutputArg> &Outs, bool IsRet,
    CallLoweringInfo *CLI) const {
  unsigned NumArgs = Outs.size();

  for (unsigned i = 0; i != NumArgs; i++) {
    MVT ArgVT = Outs[i].VT;
    ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
    Type *OrigTy = CLI ? CLI->getArgs()[Outs[i].OrigArgIndex].Ty : nullptr;

    if (CC_RISCV(MF.getDataLayout(), i, ArgVT, ArgVT, CCValAssign::Full,
                 ArgFlags, CCInfo, Outs[i].IsFixed, IsRet, OrigTy)) {
      DEBUG(dbgs() << "OutputArg #" << i << " has unhandled type "
                   << EVT(ArgVT).getEVTString() << "\n");
      llvm_unreachable(nullptr);
    }
  }
}

// The caller is responsible for loading the full value if the argument is
// passed with CCValAssign::Indirect.
static SDValue unpackFromRegLoc(SelectionDAG &DAG, SDValue Chain,
                                const CCValAssign &VA, const SDLoc &DL) {
  MachineFunction &MF = DAG.getMachineFunction();
  MachineRegisterInfo &RegInfo = MF.getRegInfo();
  EVT LocVT = VA.getLocVT();
  SDValue Val;

  unsigned VReg = RegInfo.createVirtualRegister(&RISCV::GPRRegClass);
  RegInfo.addLiveIn(VA.getLocReg(), VReg);
  Val = DAG.getCopyFromReg(Chain, DL, VReg, LocVT);

  switch (VA.getLocInfo()) {
  default:
    llvm_unreachable("Unexpected CCValAssign::LocInfo");
  case CCValAssign::Full:
  case CCValAssign::Indirect:
    return Val;
  }
}

// The caller is responsible for loading the full value if the argument is
// passed with CCValAssign::Indirect.
static SDValue unpackFromMemLoc(SelectionDAG &DAG, SDValue Chain,
                                const CCValAssign &VA, const SDLoc &DL) {
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  EVT LocVT = VA.getLocVT();
  EVT ValVT = VA.getValVT();
  EVT PtrVT = MVT::getIntegerVT(DAG.getDataLayout().getPointerSizeInBits(0));
  int FI = MFI.CreateFixedObject(ValVT.getSizeInBits() / 8,
                                 VA.getLocMemOffset(), /*Immutable=*/true);
  SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
  SDValue Val;

  ISD::LoadExtType ExtType;
  switch (VA.getLocInfo()) {
  default:
    llvm_unreachable("Unexpected CCValAssign::LocInfo");
  case CCValAssign::Full:
  case CCValAssign::Indirect:
    ExtType = ISD::NON_EXTLOAD;
    break;
  }
  Val = DAG.getExtLoad(
      ExtType, DL, LocVT, Chain, FIN,
      MachinePointerInfo::getFixedStack(DAG.getMachineFunction(), FI), ValVT);
  return Val;
}

// Transform physical registers into virtual registers.
SDValue RISCVTargetLowering::LowerFormalArguments(
    SDValue Chain, CallingConv::ID CallConv, bool IsVarArg,
    const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &DL,
    SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const {

  switch (CallConv) {
  default:
    report_fatal_error("Unsupported calling convention");
  case CallingConv::C:
  case CallingConv::Fast:
    break;
  }

  MachineFunction &MF = DAG.getMachineFunction();
  EVT PtrVT = getPointerTy(DAG.getDataLayout());
  MVT XLenVT = Subtarget.getXLenVT();
  unsigned XLenInBytes = Subtarget.getXLen() / 8;
  // Used with vargs to acumulate store chains.
  std::vector<SDValue> OutChains;

  // Assign locations to all of the incoming arguments.
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState CCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());
  analyzeInputArgs(MF, CCInfo, Ins, /*IsRet=*/false);

  for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
    CCValAssign &VA = ArgLocs[i];
    assert(VA.getLocVT() == XLenVT && "Unhandled argument type");
    SDValue ArgValue;
    if (VA.isRegLoc())
      ArgValue = unpackFromRegLoc(DAG, Chain, VA, DL);
    else
      ArgValue = unpackFromMemLoc(DAG, Chain, VA, DL);

    if (VA.getLocInfo() == CCValAssign::Indirect) {
      // If the original argument was split and passed by reference (e.g. i128
      // on RV32), we need to load all parts of it here (using the same
      // address).
      InVals.push_back(DAG.getLoad(VA.getValVT(), DL, Chain, ArgValue,
                                   MachinePointerInfo()));
      unsigned ArgIndex = Ins[i].OrigArgIndex;
      assert(Ins[i].PartOffset == 0);
      while (i + 1 != e && Ins[i + 1].OrigArgIndex == ArgIndex) {
        CCValAssign &PartVA = ArgLocs[i + 1];
        unsigned PartOffset = Ins[i + 1].PartOffset;
        SDValue Address = DAG.getNode(ISD::ADD, DL, PtrVT, ArgValue,
                                      DAG.getIntPtrConstant(PartOffset, DL));
        InVals.push_back(DAG.getLoad(PartVA.getValVT(), DL, Chain, Address,
                                     MachinePointerInfo()));
        ++i;
      }
      continue;
    }
    InVals.push_back(ArgValue);
  }

  if (IsVarArg) {
    ArrayRef<MCPhysReg> ArgRegs = makeArrayRef(ArgGPRs);
    unsigned Idx = CCInfo.getFirstUnallocated(ArgRegs);
    const TargetRegisterClass *RC = &RISCV::GPRRegClass;
    MachineFrameInfo &MFI = MF.getFrameInfo();
    MachineRegisterInfo &RegInfo = MF.getRegInfo();
    RISCVMachineFunctionInfo *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();

    // Offset of the first variable argument from stack pointer, and size of
    // the vararg save area. For now, the varargs save area is either zero or
    // large enough to hold a0-a7.
    int VaArgOffset, VarArgsSaveSize;

    // If all registers are allocated, then all varargs must be passed on the
    // stack and we don't need to save any argregs.
    if (ArgRegs.size() == Idx) {
      VaArgOffset = CCInfo.getNextStackOffset();
      VarArgsSaveSize = 0;
    } else {
      VarArgsSaveSize = XLenInBytes * (ArgRegs.size() - Idx);
      VaArgOffset = -VarArgsSaveSize;
    }

    // Record the frame index of the first variable argument
    // which is a value necessary to VASTART.
    int FI = MFI.CreateFixedObject(XLenInBytes, VaArgOffset, true);
    RVFI->setVarArgsFrameIndex(FI);

    // If saving an odd number of registers then create an extra stack slot to
    // ensure that the frame pointer is 2*XLEN-aligned, which in turn ensures
    // offsets to even-numbered registered remain 2*XLEN-aligned.
    if (Idx % 2) {
      FI = MFI.CreateFixedObject(XLenInBytes, VaArgOffset - (int)XLenInBytes,
                                 true);
      VarArgsSaveSize += XLenInBytes;
    }

    // Copy the integer registers that may have been used for passing varargs
    // to the vararg save area.
    for (unsigned I = Idx; I < ArgRegs.size();
         ++I, VaArgOffset += XLenInBytes) {
      const unsigned Reg = RegInfo.createVirtualRegister(RC);
      RegInfo.addLiveIn(ArgRegs[I], Reg);
      SDValue ArgValue = DAG.getCopyFromReg(Chain, DL, Reg, XLenVT);
      FI = MFI.CreateFixedObject(XLenInBytes, VaArgOffset, true);
      SDValue PtrOff = DAG.getFrameIndex(FI, getPointerTy(DAG.getDataLayout()));
      SDValue Store = DAG.getStore(Chain, DL, ArgValue, PtrOff,
                                   MachinePointerInfo::getFixedStack(MF, FI));
      cast<StoreSDNode>(Store.getNode())
          ->getMemOperand()
          ->setValue((Value *)nullptr);
      OutChains.push_back(Store);
    }
    RVFI->setVarArgsSaveSize(VarArgsSaveSize);
  }

  // All stores are grouped in one node to allow the matching between
  // the size of Ins and InVals. This only happens for vararg functions.
  if (!OutChains.empty()) {
    OutChains.push_back(Chain);
    Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, OutChains);
  }

  return Chain;
}

// Lower a call to a callseq_start + CALL + callseq_end chain, and add input
// and output parameter nodes.
SDValue RISCVTargetLowering::LowerCall(CallLoweringInfo &CLI,
                                       SmallVectorImpl<SDValue> &InVals) const {
  SelectionDAG &DAG = CLI.DAG;
  SDLoc &DL = CLI.DL;
  SmallVectorImpl<ISD::OutputArg> &Outs = CLI.Outs;
  SmallVectorImpl<SDValue> &OutVals = CLI.OutVals;
  SmallVectorImpl<ISD::InputArg> &Ins = CLI.Ins;
  SDValue Chain = CLI.Chain;
  SDValue Callee = CLI.Callee;
  CLI.IsTailCall = false;
  CallingConv::ID CallConv = CLI.CallConv;
  bool IsVarArg = CLI.IsVarArg;
  EVT PtrVT = getPointerTy(DAG.getDataLayout());
  MVT XLenVT = Subtarget.getXLenVT();

  MachineFunction &MF = DAG.getMachineFunction();

  // Analyze the operands of the call, assigning locations to each operand.
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState ArgCCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());
  analyzeOutputArgs(MF, ArgCCInfo, Outs, /*IsRet=*/false, &CLI);

  // Get a count of how many bytes are to be pushed on the stack.
  unsigned NumBytes = ArgCCInfo.getNextStackOffset();

  // Create local copies for byval args
  SmallVector<SDValue, 8> ByValArgs;
  for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
    ISD::ArgFlagsTy Flags = Outs[i].Flags;
    if (!Flags.isByVal())
      continue;

    SDValue Arg = OutVals[i];
    unsigned Size = Flags.getByValSize();
    unsigned Align = Flags.getByValAlign();

    int FI = MF.getFrameInfo().CreateStackObject(Size, Align, /*isSS=*/false);
    SDValue FIPtr = DAG.getFrameIndex(FI, getPointerTy(DAG.getDataLayout()));
    SDValue SizeNode = DAG.getConstant(Size, DL, XLenVT);

    Chain = DAG.getMemcpy(Chain, DL, FIPtr, Arg, SizeNode, Align,
                          /*IsVolatile=*/false,
                          /*AlwaysInline=*/false,
                          /*isTailCall=*/false, MachinePointerInfo(),
                          MachinePointerInfo());
    ByValArgs.push_back(FIPtr);
  }

  Chain = DAG.getCALLSEQ_START(Chain, NumBytes, 0, CLI.DL);

  // Copy argument values to their designated locations.
  SmallVector<std::pair<unsigned, SDValue>, 8> RegsToPass;
  SmallVector<SDValue, 8> MemOpChains;
  SDValue StackPtr;
  for (unsigned i = 0, j = 0, e = ArgLocs.size(); i != e; ++i) {
    CCValAssign &VA = ArgLocs[i];
    SDValue ArgValue = OutVals[i];
    ISD::ArgFlagsTy Flags = Outs[i].Flags;

    // Promote the value if needed.
    // For now, only handle fully promoted and indirect arguments.
    switch (VA.getLocInfo()) {
    case CCValAssign::Full:
      break;
    case CCValAssign::Indirect: {
      // Store the argument in a stack slot and pass its address.
      SDValue SpillSlot = DAG.CreateStackTemporary(Outs[i].ArgVT);
      int FI = cast<FrameIndexSDNode>(SpillSlot)->getIndex();
      MemOpChains.push_back(
          DAG.getStore(Chain, DL, ArgValue, SpillSlot,
                       MachinePointerInfo::getFixedStack(MF, FI)));
      // If the original argument was split (e.g. i128), we need
      // to store all parts of it here (and pass just one address).
      unsigned ArgIndex = Outs[i].OrigArgIndex;
      assert(Outs[i].PartOffset == 0);
      while (i + 1 != e && Outs[i + 1].OrigArgIndex == ArgIndex) {
        SDValue PartValue = OutVals[i + 1];
        unsigned PartOffset = Outs[i + 1].PartOffset;
        SDValue Address = DAG.getNode(ISD::ADD, DL, PtrVT, SpillSlot,
                                      DAG.getIntPtrConstant(PartOffset, DL));
        MemOpChains.push_back(
            DAG.getStore(Chain, DL, PartValue, Address,
                         MachinePointerInfo::getFixedStack(MF, FI)));
        ++i;
      }
      ArgValue = SpillSlot;
      break;
    }
    default:
      llvm_unreachable("Unknown loc info!");
    }

    // Use local copy if it is a byval arg.
    if (Flags.isByVal())
      ArgValue = ByValArgs[j++];

    if (VA.isRegLoc()) {
      // Queue up the argument copies and emit them at the end.
      RegsToPass.push_back(std::make_pair(VA.getLocReg(), ArgValue));
    } else {
      assert(VA.isMemLoc() && "Argument not register or memory");

      // Work out the address of the stack slot.
      if (!StackPtr.getNode())
        StackPtr = DAG.getCopyFromReg(Chain, DL, RISCV::X2, PtrVT);
      SDValue Address =
          DAG.getNode(ISD::ADD, DL, PtrVT, StackPtr,
                      DAG.getIntPtrConstant(VA.getLocMemOffset(), DL));

      // Emit the store.
      MemOpChains.push_back(
          DAG.getStore(Chain, DL, ArgValue, Address, MachinePointerInfo()));
    }
  }

  // Join the stores, which are independent of one another.
  if (!MemOpChains.empty())
    Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, MemOpChains);

  SDValue Glue;

  // Build a sequence of copy-to-reg nodes, chained and glued together.
  for (auto &Reg : RegsToPass) {
    Chain = DAG.getCopyToReg(Chain, DL, Reg.first, Reg.second, Glue);
    Glue = Chain.getValue(1);
  }

  if (isa<GlobalAddressSDNode>(Callee)) {
    Callee = lowerGlobalAddress(Callee, DAG);
  } else if (isa<ExternalSymbolSDNode>(Callee)) {
    Callee = lowerExternalSymbol(Callee, DAG);
  }

  // The first call operand is the chain and the second is the target address.
  SmallVector<SDValue, 8> Ops;
  Ops.push_back(Chain);
  Ops.push_back(Callee);

  // Add argument registers to the end of the list so that they are
  // known live into the call.
  for (auto &Reg : RegsToPass)
    Ops.push_back(DAG.getRegister(Reg.first, Reg.second.getValueType()));

  // Add a register mask operand representing the call-preserved registers.
  const TargetRegisterInfo *TRI = Subtarget.getRegisterInfo();
  const uint32_t *Mask = TRI->getCallPreservedMask(MF, CallConv);
  assert(Mask && "Missing call preserved mask for calling convention");
  Ops.push_back(DAG.getRegisterMask(Mask));

  // Glue the call to the argument copies, if any.
  if (Glue.getNode())
    Ops.push_back(Glue);

  // Emit the call.
  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
  Chain = DAG.getNode(RISCVISD::CALL, DL, NodeTys, Ops);
  Glue = Chain.getValue(1);

  // Mark the end of the call, which is glued to the call itself.
  Chain = DAG.getCALLSEQ_END(Chain,
                             DAG.getConstant(NumBytes, DL, PtrVT, true),
                             DAG.getConstant(0, DL, PtrVT, true),
                             Glue, DL);
  Glue = Chain.getValue(1);

  // Assign locations to each value returned by this call.
  SmallVector<CCValAssign, 16> RVLocs;
  CCState RetCCInfo(CallConv, IsVarArg, MF, RVLocs, *DAG.getContext());
  analyzeInputArgs(MF, RetCCInfo, Ins, /*IsRet=*/true);

  // Copy all of the result registers out of their specified physreg.
  for (auto &VA : RVLocs) {
    // Copy the value out, gluing the copy to the end of the call sequence.
    SDValue RetValue = DAG.getCopyFromReg(Chain, DL, VA.getLocReg(),
                                          VA.getLocVT(), Glue);
    Chain = RetValue.getValue(1);
    Glue = RetValue.getValue(2);

    assert(VA.getLocInfo() == CCValAssign::Full && "Unknown loc info!");
    InVals.push_back(RetValue);
  }

  return Chain;
}

bool RISCVTargetLowering::CanLowerReturn(
    CallingConv::ID CallConv, MachineFunction &MF, bool IsVarArg,
    const SmallVectorImpl<ISD::OutputArg> &Outs, LLVMContext &Context) const {
  SmallVector<CCValAssign, 16> RVLocs;
  CCState CCInfo(CallConv, IsVarArg, MF, RVLocs, Context);
  for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
    MVT VT = Outs[i].VT;
    ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
    if (CC_RISCV(MF.getDataLayout(), i, VT, VT, CCValAssign::Full, ArgFlags,
                 CCInfo, /*IsFixed=*/true, /*IsRet=*/true, nullptr))
      return false;
  }
  return true;
}

SDValue
RISCVTargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
                                 bool IsVarArg,
                                 const SmallVectorImpl<ISD::OutputArg> &Outs,
                                 const SmallVectorImpl<SDValue> &OutVals,
                                 const SDLoc &DL, SelectionDAG &DAG) const {
  // Stores the assignment of the return value to a location.
  SmallVector<CCValAssign, 16> RVLocs;

  // Info about the registers and stack slot.
  CCState CCInfo(CallConv, IsVarArg, DAG.getMachineFunction(), RVLocs,
                 *DAG.getContext());

  analyzeOutputArgs(DAG.getMachineFunction(), CCInfo, Outs, /*IsRet=*/true,
                    nullptr);

  SDValue Flag;
  SmallVector<SDValue, 4> RetOps(1, Chain);

  // Copy the result values into the output registers.
  for (unsigned i = 0, e = RVLocs.size(); i < e; ++i) {
    SDValue Val = OutVals[i];
    CCValAssign &VA = RVLocs[i];
    assert(VA.isRegLoc() && "Can only return in registers!");
    assert(VA.getLocInfo() == CCValAssign::Full &&
           "Unexpected CCValAssign::LocInfo");

    Chain = DAG.getCopyToReg(Chain, DL, VA.getLocReg(), Val, Flag);

    // Guarantee that all emitted copies are stuck together.
    Flag = Chain.getValue(1);
    RetOps.push_back(DAG.getRegister(VA.getLocReg(), VA.getLocVT()));
  }

  RetOps[0] = Chain; // Update chain.

  // Add the flag if we have it.
  if (Flag.getNode()) {
    RetOps.push_back(Flag);
  }

  return DAG.getNode(RISCVISD::RET_FLAG, DL, MVT::Other, RetOps);
}

const char *RISCVTargetLowering::getTargetNodeName(unsigned Opcode) const {
  switch ((RISCVISD::NodeType)Opcode) {
  case RISCVISD::FIRST_NUMBER:
    break;
  case RISCVISD::RET_FLAG:
    return "RISCVISD::RET_FLAG";
  case RISCVISD::CALL:
    return "RISCVISD::CALL";
  case RISCVISD::SELECT_CC:
    return "RISCVISD::SELECT_CC";
  }
  return nullptr;
}

std::pair<unsigned, const TargetRegisterClass *>
RISCVTargetLowering::getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
                                                  StringRef Constraint,
                                                  MVT VT) const {
  // First, see if this is a constraint that directly corresponds to a
  // RISCV register class.
  if (Constraint.size() == 1) {
    switch (Constraint[0]) {
    case 'r':
      return std::make_pair(0U, &RISCV::GPRRegClass);
    default:
      break;
    }
  }

  return TargetLowering::getRegForInlineAsmConstraint(TRI, Constraint, VT);
}