Target/RISCV/RISCVFrameLowering.cpp

//===-- RISCVFrameLowering.cpp - RISCV Frame Information ------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file contains the RISCV implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//

#include "RISCVFrameLowering.h"
#include "RISCVMachineFunctionInfo.h"
#include "RISCVSubtarget.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/RegisterScavenging.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/MC/MCDwarf.h"

using namespace llvm;

bool RISCVFrameLowering::hasFP(const MachineFunction &MF) const {
  const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();

  const MachineFrameInfo &MFI = MF.getFrameInfo();
  return MF.getTarget().Options.DisableFramePointerElim(MF) ||
         RegInfo->needsStackRealignment(MF) || MFI.hasVarSizedObjects() ||
         MFI.isFrameAddressTaken();
}

bool RISCVFrameLowering::hasBP(const MachineFunction &MF) const {
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const TargetRegisterInfo *TRI = STI.getRegisterInfo();

  return MFI.hasVarSizedObjects() && TRI->needsStackRealignment(MF);
}

// Determines the size of the frame and maximum call frame size.
void RISCVFrameLowering::determineFrameLayout(MachineFunction &MF) const {
  MachineFrameInfo &MFI = MF.getFrameInfo();
  const RISCVRegisterInfo *RI = STI.getRegisterInfo();

  // Get the number of bytes to allocate from the FrameInfo.
  uint64_t FrameSize = MFI.getStackSize();

  // Get the alignment.
  unsigned StackAlign = getStackAlignment();
  if (RI->needsStackRealignment(MF)) {
    unsigned MaxStackAlign = std::max(StackAlign, MFI.getMaxAlignment());
    FrameSize += (MaxStackAlign - StackAlign);
    StackAlign = MaxStackAlign;
  }

  // Set Max Call Frame Size
  uint64_t MaxCallSize = alignTo(MFI.getMaxCallFrameSize(), StackAlign);
  MFI.setMaxCallFrameSize(MaxCallSize);

  // Make sure the frame is aligned.
  FrameSize = alignTo(FrameSize, StackAlign);

  // Update frame info.
  MFI.setStackSize(FrameSize);
}

void RISCVFrameLowering::adjustReg(MachineBasicBlock &MBB,
                                   MachineBasicBlock::iterator MBBI,
                                   const DebugLoc &DL, Register DestReg,
                                   Register SrcReg, int64_t Val,
                                   MachineInstr::MIFlag Flag) const {
  MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
  const RISCVInstrInfo *TII = STI.getInstrInfo();

  if (DestReg == SrcReg && Val == 0)
    return;

  if (isInt<12>(Val)) {
    BuildMI(MBB, MBBI, DL, TII->get(RISCV::ADDI), DestReg)
        .addReg(SrcReg)
        .addImm(Val)
        .setMIFlag(Flag);
  } else {
    unsigned Opc = RISCV::ADD;
    bool isSub = Val < 0;
    if (isSub) {
      Val = -Val;
      Opc = RISCV::SUB;
    }

    Register ScratchReg = MRI.createVirtualRegister(&RISCV::GPRRegClass);
    TII->movImm(MBB, MBBI, DL, ScratchReg, Val, Flag);
    BuildMI(MBB, MBBI, DL, TII->get(Opc), DestReg)
        .addReg(SrcReg)
        .addReg(ScratchReg, RegState::Kill)
        .setMIFlag(Flag);
  }
}

// Returns the register used to hold the frame pointer.
static Register getFPReg(const RISCVSubtarget &STI) { return RISCV::X8; }

// Returns the register used to hold the stack pointer.
static Register getSPReg(const RISCVSubtarget &STI) { return RISCV::X2; }

void RISCVFrameLowering::emitPrologue(MachineFunction &MF,
                                      MachineBasicBlock &MBB) const {
  assert(&MF.front() == &MBB && "Shrink-wrapping not yet supported");

  MachineFrameInfo &MFI = MF.getFrameInfo();
  auto *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();
  const RISCVRegisterInfo *RI = STI.getRegisterInfo();
  const RISCVInstrInfo *TII = STI.getInstrInfo();
  MachineBasicBlock::iterator MBBI = MBB.begin();

  Register FPReg = getFPReg(STI);
  Register SPReg = getSPReg(STI);
  Register BPReg = RISCVABI::getBPReg();

  // Debug location must be unknown since the first debug location is used
  // to determine the end of the prologue.
  DebugLoc DL;

  // Determine the correct frame layout
  determineFrameLayout(MF);

  // FIXME (note copied from Lanai): This appears to be overallocating.  Needs
  // investigation. Get the number of bytes to allocate from the FrameInfo.
  uint64_t StackSize = MFI.getStackSize();

  // Early exit if there is no need to allocate on the stack
  if (StackSize == 0 && !MFI.adjustsStack())
    return;

  // If the stack pointer has been marked as reserved, then produce an error if
  // the frame requires stack allocation
  if (STI.isRegisterReservedByUser(SPReg))
    MF.getFunction().getContext().diagnose(DiagnosticInfoUnsupported{
        MF.getFunction(), "Stack pointer required, but has been reserved."});

  uint64_t FirstSPAdjustAmount = getFirstSPAdjustAmount(MF);
  // Split the SP adjustment to reduce the offsets of callee saved spill.
  if (FirstSPAdjustAmount)
    StackSize = FirstSPAdjustAmount;

  // Allocate space on the stack if necessary.
  adjustReg(MBB, MBBI, DL, SPReg, SPReg, -StackSize, MachineInstr::FrameSetup);

  // Emit ".cfi_def_cfa_offset StackSize"
  unsigned CFIIndex = MF.addFrameInst(
      MCCFIInstruction::createDefCfaOffset(nullptr, -StackSize));
  BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
      .addCFIIndex(CFIIndex);

  // The frame pointer is callee-saved, and code has been generated for us to
  // save it to the stack. We need to skip over the storing of callee-saved
  // registers as the frame pointer must be modified after it has been saved
  // to the stack, not before.
  // FIXME: assumes exactly one instruction is used to save each callee-saved
  // register.
  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
  std::advance(MBBI, CSI.size());

  // Iterate over list of callee-saved registers and emit .cfi_offset
  // directives.
  for (const auto &Entry : CSI) {
    int64_t Offset = MFI.getObjectOffset(Entry.getFrameIdx());
    Register Reg = Entry.getReg();
    unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createOffset(
        nullptr, RI->getDwarfRegNum(Reg, true), Offset));
    BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex);
  }

  // Generate new FP.
  if (hasFP(MF)) {
    if (STI.isRegisterReservedByUser(FPReg))
      MF.getFunction().getContext().diagnose(DiagnosticInfoUnsupported{
          MF.getFunction(), "Frame pointer required, but has been reserved."});

    adjustReg(MBB, MBBI, DL, FPReg, SPReg,
              StackSize - RVFI->getVarArgsSaveSize(), MachineInstr::FrameSetup);

    // Emit ".cfi_def_cfa $fp, 0"
    unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
        nullptr, RI->getDwarfRegNum(FPReg, true), 0));
    BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex);
  }

  // Emit the second SP adjustment after saving callee saved registers.
  if (FirstSPAdjustAmount) {
    uint64_t SecondSPAdjustAmount = MFI.getStackSize() - FirstSPAdjustAmount;
    assert(SecondSPAdjustAmount > 0 &&
           "SecondSPAdjustAmount should be greater than zero");
    adjustReg(MBB, MBBI, DL, SPReg, SPReg, -SecondSPAdjustAmount,
              MachineInstr::FrameSetup);

    // If we are using a frame-pointer, and thus emitted ".cfi_def_cfa fp, 0",
    // don't emit an sp-based .cfi_def_cfa_offset
    if (!hasFP(MF)) {
      // Emit ".cfi_def_cfa_offset StackSize"
      unsigned CFIIndex = MF.addFrameInst(
          MCCFIInstruction::createDefCfaOffset(nullptr, -MFI.getStackSize()));
      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex);
    }
  }

  if (hasFP(MF)) {
    // Realign Stack
    const RISCVRegisterInfo *RI = STI.getRegisterInfo();
    if (RI->needsStackRealignment(MF)) {
      unsigned MaxAlignment = MFI.getMaxAlignment();

      const RISCVInstrInfo *TII = STI.getInstrInfo();
      if (isInt<12>(-(int)MaxAlignment)) {
        BuildMI(MBB, MBBI, DL, TII->get(RISCV::ANDI), SPReg)
            .addReg(SPReg)
            .addImm(-(int)MaxAlignment);
      } else {
        unsigned ShiftAmount = countTrailingZeros(MaxAlignment);
        Register VR =
            MF.getRegInfo().createVirtualRegister(&RISCV::GPRRegClass);
        BuildMI(MBB, MBBI, DL, TII->get(RISCV::SRLI), VR)
            .addReg(SPReg)
            .addImm(ShiftAmount);
        BuildMI(MBB, MBBI, DL, TII->get(RISCV::SLLI), SPReg)
            .addReg(VR)
            .addImm(ShiftAmount);
      }
      // FP will be used to restore the frame in the epilogue, so we need
      // another base register BP to record SP after re-alignment. SP will
      // track the current stack after allocating variable sized objects.
      if (hasBP(MF)) {
        // move BP, SP
        BuildMI(MBB, MBBI, DL, TII->get(RISCV::ADDI), BPReg)
            .addReg(SPReg)
            .addImm(0);
      }
    }
  }
}

void RISCVFrameLowering::emitEpilogue(MachineFunction &MF,
                                      MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
  const RISCVRegisterInfo *RI = STI.getRegisterInfo();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  auto *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();
  DebugLoc DL = MBBI->getDebugLoc();
  Register FPReg = getFPReg(STI);
  Register SPReg = getSPReg(STI);

  // Skip to before the restores of callee-saved registers
  // FIXME: assumes exactly one instruction is used to restore each
  // callee-saved register.
  auto LastFrameDestroy = std::prev(MBBI, MFI.getCalleeSavedInfo().size());

  uint64_t StackSize = MFI.getStackSize();
  uint64_t FPOffset = StackSize - RVFI->getVarArgsSaveSize();

  // Restore the stack pointer using the value of the frame pointer. Only
  // necessary if the stack pointer was modified, meaning the stack size is
  // unknown.
  if (RI->needsStackRealignment(MF) || MFI.hasVarSizedObjects()) {
    assert(hasFP(MF) && "frame pointer should not have been eliminated");
    adjustReg(MBB, LastFrameDestroy, DL, SPReg, FPReg, -FPOffset,
              MachineInstr::FrameDestroy);
  }

  uint64_t FirstSPAdjustAmount = getFirstSPAdjustAmount(MF);
  if (FirstSPAdjustAmount) {
    uint64_t SecondSPAdjustAmount = MFI.getStackSize() - FirstSPAdjustAmount;
    assert(SecondSPAdjustAmount > 0 &&
           "SecondSPAdjustAmount should be greater than zero");

    adjustReg(MBB, LastFrameDestroy, DL, SPReg, SPReg, SecondSPAdjustAmount,
              MachineInstr::FrameDestroy);
  }

  if (FirstSPAdjustAmount)
    StackSize = FirstSPAdjustAmount;

  // Deallocate stack
  adjustReg(MBB, MBBI, DL, SPReg, SPReg, StackSize, MachineInstr::FrameDestroy);
}

int RISCVFrameLowering::getFrameIndexReference(const MachineFunction &MF,
                                               int FI,
                                               unsigned &FrameReg) const {
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const TargetRegisterInfo *RI = MF.getSubtarget().getRegisterInfo();
  const auto *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();

  // Callee-saved registers should be referenced relative to the stack
  // pointer (positive offset), otherwise use the frame pointer (negative
  // offset).
  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
  int MinCSFI = 0;
  int MaxCSFI = -1;

  int Offset = MFI.getObjectOffset(FI) - getOffsetOfLocalArea() +
               MFI.getOffsetAdjustment();

  uint64_t FirstSPAdjustAmount = getFirstSPAdjustAmount(MF);

  if (CSI.size()) {
    MinCSFI = CSI[0].getFrameIdx();
    MaxCSFI = CSI[CSI.size() - 1].getFrameIdx();
  }

  if (FI >= MinCSFI && FI <= MaxCSFI) {
    FrameReg = RISCV::X2;

    if (FirstSPAdjustAmount)
      Offset += FirstSPAdjustAmount;
    else
      Offset += MF.getFrameInfo().getStackSize();
  } else if (RI->needsStackRealignment(MF) && !MFI.isFixedObjectIndex(FI)) {
    // If the stack was realigned, the frame pointer is set in order to allow
    // SP to be restored, so we need another base register to record the stack
    // after realignment.
    if (hasBP(MF))
      FrameReg = RISCVABI::getBPReg();
    else
      FrameReg = RISCV::X2;
    Offset += MF.getFrameInfo().getStackSize();
  } else {
    FrameReg = RI->getFrameRegister(MF);
    if (hasFP(MF))
      Offset += RVFI->getVarArgsSaveSize();
    else
      Offset += MF.getFrameInfo().getStackSize();
  }
  return Offset;
}

void RISCVFrameLowering::determineCalleeSaves(MachineFunction &MF,
                                              BitVector &SavedRegs,
                                              RegScavenger *RS) const {
  TargetFrameLowering::determineCalleeSaves(MF, SavedRegs, RS);
  // Unconditionally spill RA and FP only if the function uses a frame
  // pointer.
  if (hasFP(MF)) {
    SavedRegs.set(RISCV::X1);
    SavedRegs.set(RISCV::X8);
  }
  // Mark BP as used if function has dedicated base pointer.
  if (hasBP(MF))
    SavedRegs.set(RISCVABI::getBPReg());

  // If interrupt is enabled and there are calls in the handler,
  // unconditionally save all Caller-saved registers and
  // all FP registers, regardless whether they are used.
  MachineFrameInfo &MFI = MF.getFrameInfo();

  if (MF.getFunction().hasFnAttribute("interrupt") && MFI.hasCalls()) {

    static const MCPhysReg CSRegs[] = { RISCV::X1,      /* ra */
      RISCV::X5, RISCV::X6, RISCV::X7,                  /* t0-t2 */
      RISCV::X10, RISCV::X11,                           /* a0-a1, a2-a7 */
      RISCV::X12, RISCV::X13, RISCV::X14, RISCV::X15, RISCV::X16, RISCV::X17,
      RISCV::X28, RISCV::X29, RISCV::X30, RISCV::X31, 0 /* t3-t6 */
    };

    for (unsigned i = 0; CSRegs[i]; ++i)
      SavedRegs.set(CSRegs[i]);

    if (MF.getSubtarget<RISCVSubtarget>().hasStdExtD() ||
        MF.getSubtarget<RISCVSubtarget>().hasStdExtF()) {

      // If interrupt is enabled, this list contains all FP registers.
      const MCPhysReg * Regs = MF.getRegInfo().getCalleeSavedRegs();

      for (unsigned i = 0; Regs[i]; ++i)
        if (RISCV::FPR32RegClass.contains(Regs[i]) ||
            RISCV::FPR64RegClass.contains(Regs[i]))
          SavedRegs.set(Regs[i]);
    }
  }
}

void RISCVFrameLowering::processFunctionBeforeFrameFinalized(
    MachineFunction &MF, RegScavenger *RS) const {
  const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  const TargetRegisterClass *RC = &RISCV::GPRRegClass;
  // estimateStackSize has been observed to under-estimate the final stack
  // size, so give ourselves wiggle-room by checking for stack size
  // representable an 11-bit signed field rather than 12-bits.
  // FIXME: It may be possible to craft a function with a small stack that
  // still needs an emergency spill slot for branch relaxation. This case
  // would currently be missed.
  if (!isInt<11>(MFI.estimateStackSize(MF))) {
    int RegScavFI = MFI.CreateStackObject(
        RegInfo->getSpillSize(*RC), RegInfo->getSpillAlignment(*RC), false);
    RS->addScavengingFrameIndex(RegScavFI);
  }
}

// Not preserve stack space within prologue for outgoing variables when the
// function contains variable size objects and let eliminateCallFramePseudoInstr
// preserve stack space for it.
bool RISCVFrameLowering::hasReservedCallFrame(const MachineFunction &MF) const {
  return !MF.getFrameInfo().hasVarSizedObjects();
}

// Eliminate ADJCALLSTACKDOWN, ADJCALLSTACKUP pseudo instructions.
MachineBasicBlock::iterator RISCVFrameLowering::eliminateCallFramePseudoInstr(
    MachineFunction &MF, MachineBasicBlock &MBB,
    MachineBasicBlock::iterator MI) const {
  Register SPReg = RISCV::X2;
  DebugLoc DL = MI->getDebugLoc();

  if (!hasReservedCallFrame(MF)) {
    // If space has not been reserved for a call frame, ADJCALLSTACKDOWN and
    // ADJCALLSTACKUP must be converted to instructions manipulating the stack
    // pointer. This is necessary when there is a variable length stack
    // allocation (e.g. alloca), which means it's not possible to allocate
    // space for outgoing arguments from within the function prologue.
    int64_t Amount = MI->getOperand(0).getImm();

    if (Amount != 0) {
      // Ensure the stack remains aligned after adjustment.
      Amount = alignSPAdjust(Amount);

      if (MI->getOpcode() == RISCV::ADJCALLSTACKDOWN)
        Amount = -Amount;

      adjustReg(MBB, MI, DL, SPReg, SPReg, Amount, MachineInstr::NoFlags);
    }
  }

  return MBB.erase(MI);
}

// We would like to split the SP adjustment to reduce prologue/epilogue
// as following instructions. In this way, the offset of the callee saved
// register could fit in a single store.
//   add     sp,sp,-2032
//   sw      ra,2028(sp)
//   sw      s0,2024(sp)
//   sw      s1,2020(sp)
//   sw      s3,2012(sp)
//   sw      s4,2008(sp)
//   add     sp,sp,-64
uint64_t
RISCVFrameLowering::getFirstSPAdjustAmount(const MachineFunction &MF) const {
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
  uint64_t StackSize = MFI.getStackSize();
  uint64_t StackAlign = getStackAlignment();

  // FIXME: Disable SplitSPAdjust if save-restore libcall enabled when the patch
  //        landing. The callee saved registers will be pushed by the
  //        save-restore libcalls, so we don't have to split the SP adjustment
  //        in this case.
  //
  // Return the FirstSPAdjustAmount if the StackSize can not fit in signed
  // 12-bit and there exists a callee saved register need to be pushed.
  if (!isInt<12>(StackSize) && (CSI.size() > 0)) {
    // FirstSPAdjustAmount is choosed as (2048 - StackAlign)
    // because 2048 will cause sp = sp + 2048 in epilogue split into
    // multi-instructions. The offset smaller than 2048 can fit in signle
    // load/store instruction and we have to stick with the stack alignment.
    // 2048 is 16-byte alignment. The stack alignment for RV32 and RV64 is 16,
    // for RV32E is 4. So (2048 - StackAlign) will satisfy the stack alignment.
    return 2048 - StackAlign;
  }
  return 0;
}