//===- PrologEpilogInserter.cpp - Insert Prolog/Epilog code in function ---===//
//
// 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 pass is responsible for finalizing the functions frame layout, saving
// callee saved registers, and for emitting prolog & epilog code for the
// function.
//
// This pass must be run after register allocation.  After this pass is
// executed, it is illegal to construct MO_FrameIndex operands.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/DepthFirstIterator.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineLoopInfo.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/RegisterScavenging.h"
#include "llvm/CodeGen/TargetFrameLowering.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetOpcodes.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/CodeGen/WinEHFuncInfo.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DebugInfoMetadata.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/Pass.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <functional>
#include <limits>
#include <utility>
#include <vector>

using namespace llvm;

#define DEBUG_TYPE "prologepilog"

using MBBVector = SmallVector<MachineBasicBlock *, 4>;

STATISTIC(NumLeafFuncWithSpills, "Number of leaf functions with CSRs");
STATISTIC(NumFuncSeen, "Number of functions seen in PEI");


namespace {

class PEI : public MachineFunctionPass {
public:
  static char ID;

  PEI() : MachineFunctionPass(ID) {
    initializePEIPass(*PassRegistry::getPassRegistry());
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override;

  /// runOnMachineFunction - Insert prolog/epilog code and replace abstract
  /// frame indexes with appropriate references.
  bool runOnMachineFunction(MachineFunction &MF) override;

private:
  RegScavenger *RS;

  // MinCSFrameIndex, MaxCSFrameIndex - Keeps the range of callee saved
  // stack frame indexes.
  unsigned MinCSFrameIndex = std::numeric_limits<unsigned>::max();
  unsigned MaxCSFrameIndex = 0;

  // Save and Restore blocks of the current function. Typically there is a
  // single save block, unless Windows EH funclets are involved.
  MBBVector SaveBlocks;
  MBBVector RestoreBlocks;

  // Flag to control whether to use the register scavenger to resolve
  // frame index materialization registers. Set according to
  // TRI->requiresFrameIndexScavenging() for the current function.
  bool FrameIndexVirtualScavenging;

  // Flag to control whether the scavenger should be passed even though
  // FrameIndexVirtualScavenging is used.
  bool FrameIndexEliminationScavenging;

  // Emit remarks.
  MachineOptimizationRemarkEmitter *ORE = nullptr;

  void calculateCallFrameInfo(MachineFunction &MF);
  void calculateSaveRestoreBlocks(MachineFunction &MF);
  void spillCalleeSavedRegs(MachineFunction &MF);

  void calculateFrameObjectOffsets(MachineFunction &MF);
  void replaceFrameIndices(MachineFunction &MF);
  void replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &MF,
                           int &SPAdj);
  void insertPrologEpilogCode(MachineFunction &MF);
};

} // end anonymous namespace

char PEI::ID = 0;

char &llvm::PrologEpilogCodeInserterID = PEI::ID;

static cl::opt<unsigned>
WarnStackSize("warn-stack-size", cl::Hidden, cl::init((unsigned)-1),
              cl::desc("Warn for stack size bigger than the given"
                       " number"));

INITIALIZE_PASS_BEGIN(PEI, DEBUG_TYPE, "Prologue/Epilogue Insertion", false,
                      false)
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
INITIALIZE_PASS_DEPENDENCY(MachineOptimizationRemarkEmitterPass)
INITIALIZE_PASS_END(PEI, DEBUG_TYPE,
                    "Prologue/Epilogue Insertion & Frame Finalization", false,
                    false)

MachineFunctionPass *llvm::createPrologEpilogInserterPass() {
  return new PEI();
}

STATISTIC(NumBytesStackSpace,
          "Number of bytes used for stack in all functions");

void PEI::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.setPreservesCFG();
  AU.addPreserved<MachineLoopInfo>();
  AU.addPreserved<MachineDominatorTree>();
  AU.addRequired<MachineOptimizationRemarkEmitterPass>();
  MachineFunctionPass::getAnalysisUsage(AU);
}

/// StackObjSet - A set of stack object indexes
using StackObjSet = SmallSetVector<int, 8>;

using SavedDbgValuesMap =
    SmallDenseMap<MachineBasicBlock *, SmallVector<MachineInstr *, 4>, 4>;

/// Stash DBG_VALUEs that describe parameters and which are placed at the start
/// of the block. Later on, after the prologue code has been emitted, the
/// stashed DBG_VALUEs will be reinserted at the start of the block.
static void stashEntryDbgValues(MachineBasicBlock &MBB,
                                SavedDbgValuesMap &EntryDbgValues) {
  SmallVector<const MachineInstr *, 4> FrameIndexValues;

  for (auto &MI : MBB) {
    if (!MI.isDebugInstr())
      break;
    if (!MI.isDebugValue() || !MI.getDebugVariable()->isParameter())
      continue;
    if (MI.getOperand(0).isFI()) {
      // We can only emit valid locations for frame indices after the frame
      // setup, so do not stash away them.
      FrameIndexValues.push_back(&MI);
      continue;
    }
    const DILocalVariable *Var = MI.getDebugVariable();
    const DIExpression *Expr = MI.getDebugExpression();
    auto Overlaps = [Var, Expr](const MachineInstr *DV) {
      return Var == DV->getDebugVariable() &&
             Expr->fragmentsOverlap(DV->getDebugExpression());
    };
    // See if the debug value overlaps with any preceding debug value that will
    // not be stashed. If that is the case, then we can't stash this value, as
    // we would then reorder the values at reinsertion.
    if (llvm::none_of(FrameIndexValues, Overlaps))
      EntryDbgValues[&MBB].push_back(&MI);
  }

  // Remove stashed debug values from the block.
  if (EntryDbgValues.count(&MBB))
    for (auto *MI : EntryDbgValues[&MBB])
      MI->removeFromParent();
}

/// runOnMachineFunction - Insert prolog/epilog code and replace abstract
/// frame indexes with appropriate references.
bool PEI::runOnMachineFunction(MachineFunction &MF) {
  NumFuncSeen++;
  const Function &F = MF.getFunction();
  const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();

  RS = TRI->requiresRegisterScavenging(MF) ? new RegScavenger() : nullptr;
  FrameIndexVirtualScavenging = TRI->requiresFrameIndexScavenging(MF);
  ORE = &getAnalysis<MachineOptimizationRemarkEmitterPass>().getORE();

  // Calculate the MaxCallFrameSize and AdjustsStack variables for the
  // function's frame information. Also eliminates call frame pseudo
  // instructions.
  calculateCallFrameInfo(MF);

  // Determine placement of CSR spill/restore code and prolog/epilog code:
  // place all spills in the entry block, all restores in return blocks.
  calculateSaveRestoreBlocks(MF);

  // Stash away DBG_VALUEs that should not be moved by insertion of prolog code.
  SavedDbgValuesMap EntryDbgValues;
  for (MachineBasicBlock *SaveBlock : SaveBlocks)
    stashEntryDbgValues(*SaveBlock, EntryDbgValues);

  // Handle CSR spilling and restoring, for targets that need it.
  if (MF.getTarget().usesPhysRegsForPEI())
    spillCalleeSavedRegs(MF);

  // Allow the target machine to make final modifications to the function
  // before the frame layout is finalized.
  TFI->processFunctionBeforeFrameFinalized(MF, RS);

  // Calculate actual frame offsets for all abstract stack objects...
  calculateFrameObjectOffsets(MF);

  // Add prolog and epilog code to the function.  This function is required
  // to align the stack frame as necessary for any stack variables or
  // called functions.  Because of this, calculateCalleeSavedRegisters()
  // must be called before this function in order to set the AdjustsStack
  // and MaxCallFrameSize variables.
  if (!F.hasFnAttribute(Attribute::Naked))
    insertPrologEpilogCode(MF);

  // Reinsert stashed debug values at the start of the entry blocks.
  for (auto &I : EntryDbgValues)
    I.first->insert(I.first->begin(), I.second.begin(), I.second.end());

  // Replace all MO_FrameIndex operands with physical register references
  // and actual offsets.
  //
  replaceFrameIndices(MF);

  // If register scavenging is needed, as we've enabled doing it as a
  // post-pass, scavenge the virtual registers that frame index elimination
  // inserted.
  if (TRI->requiresRegisterScavenging(MF) && FrameIndexVirtualScavenging)
    scavengeFrameVirtualRegs(MF, *RS);

  // Warn on stack size when we exceeds the given limit.
  MachineFrameInfo &MFI = MF.getFrameInfo();
  uint64_t StackSize = MFI.getStackSize();
  if (WarnStackSize.getNumOccurrences() > 0 && WarnStackSize < StackSize) {
    DiagnosticInfoStackSize DiagStackSize(F, StackSize);
    F.getContext().diagnose(DiagStackSize);
  }
  ORE->emit([&]() {
    return MachineOptimizationRemarkAnalysis(DEBUG_TYPE, "StackSize",
                                             MF.getFunction().getSubprogram(),
                                             &MF.front())
           << ore::NV("NumStackBytes", StackSize) << " stack bytes in function";
  });

  delete RS;
  SaveBlocks.clear();
  RestoreBlocks.clear();
  MFI.setSavePoint(nullptr);
  MFI.setRestorePoint(nullptr);
  return true;
}

/// Calculate the MaxCallFrameSize and AdjustsStack
/// variables for the function's frame information and eliminate call frame
/// pseudo instructions.
void PEI::calculateCallFrameInfo(MachineFunction &MF) {
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();
  MachineFrameInfo &MFI = MF.getFrameInfo();

  unsigned MaxCallFrameSize = 0;
  bool AdjustsStack = MFI.adjustsStack();

  // Get the function call frame set-up and tear-down instruction opcode
  unsigned FrameSetupOpcode = TII.getCallFrameSetupOpcode();
  unsigned FrameDestroyOpcode = TII.getCallFrameDestroyOpcode();

  // Early exit for targets which have no call frame setup/destroy pseudo
  // instructions.
  if (FrameSetupOpcode == ~0u && FrameDestroyOpcode == ~0u)
    return;

  std::vector<MachineBasicBlock::iterator> FrameSDOps;
  for (MachineFunction::iterator BB = MF.begin(), E = MF.end(); BB != E; ++BB)
    for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ++I)
      if (TII.isFrameInstr(*I)) {
        unsigned Size = TII.getFrameSize(*I);
        if (Size > MaxCallFrameSize) MaxCallFrameSize = Size;
        AdjustsStack = true;
        FrameSDOps.push_back(I);
      } else if (I->isInlineAsm()) {
        // Some inline asm's need a stack frame, as indicated by operand 1.
        unsigned ExtraInfo = I->getOperand(InlineAsm::MIOp_ExtraInfo).getImm();
        if (ExtraInfo & InlineAsm::Extra_IsAlignStack)
          AdjustsStack = true;
      }

  assert(!MFI.isMaxCallFrameSizeComputed() ||
         (MFI.getMaxCallFrameSize() == MaxCallFrameSize &&
          MFI.adjustsStack() == AdjustsStack));
  MFI.setAdjustsStack(AdjustsStack);
  MFI.setMaxCallFrameSize(MaxCallFrameSize);

  for (std::vector<MachineBasicBlock::iterator>::iterator
         i = FrameSDOps.begin(), e = FrameSDOps.end(); i != e; ++i) {
    MachineBasicBlock::iterator I = *i;

    // If call frames are not being included as part of the stack frame, and
    // the target doesn't indicate otherwise, remove the call frame pseudos
    // here. The sub/add sp instruction pairs are still inserted, but we don't
    // need to track the SP adjustment for frame index elimination.
    if (TFI->canSimplifyCallFramePseudos(MF))
      TFI->eliminateCallFramePseudoInstr(MF, *I->getParent(), I);
  }
}

/// Compute the sets of entry and return blocks for saving and restoring
/// callee-saved registers, and placing prolog and epilog code.
void PEI::calculateSaveRestoreBlocks(MachineFunction &MF) {
  const MachineFrameInfo &MFI = MF.getFrameInfo();

  // Even when we do not change any CSR, we still want to insert the
  // prologue and epilogue of the function.
  // So set the save points for those.

  // Use the points found by shrink-wrapping, if any.
  if (MFI.getSavePoint()) {
    SaveBlocks.push_back(MFI.getSavePoint());
    assert(MFI.getRestorePoint() && "Both restore and save must be set");
    MachineBasicBlock *RestoreBlock = MFI.getRestorePoint();
    // If RestoreBlock does not have any successor and is not a return block
    // then the end point is unreachable and we do not need to insert any
    // epilogue.
    if (!RestoreBlock->succ_empty() || RestoreBlock->isReturnBlock())
      RestoreBlocks.push_back(RestoreBlock);
    return;
  }

  // Save refs to entry and return blocks.
  SaveBlocks.push_back(&MF.front());
  for (MachineBasicBlock &MBB : MF) {
    if (MBB.isEHFuncletEntry())
      SaveBlocks.push_back(&MBB);
    if (MBB.isReturnBlock())
      RestoreBlocks.push_back(&MBB);
  }
}

static void assignCalleeSavedSpillSlots(MachineFunction &F,
                                        const BitVector &SavedRegs,
                                        unsigned &MinCSFrameIndex,
                                        unsigned &MaxCSFrameIndex) {
  if (SavedRegs.empty())
    return;

  const TargetRegisterInfo *RegInfo = F.getSubtarget().getRegisterInfo();
  const MCPhysReg *CSRegs = F.getRegInfo().getCalleeSavedRegs();

  std::vector<CalleeSavedInfo> CSI;
  for (unsigned i = 0; CSRegs[i]; ++i) {
    unsigned Reg = CSRegs[i];
    if (SavedRegs.test(Reg))
      CSI.push_back(CalleeSavedInfo(Reg));
  }

  const TargetFrameLowering *TFI = F.getSubtarget().getFrameLowering();
  MachineFrameInfo &MFI = F.getFrameInfo();
  if (!TFI->assignCalleeSavedSpillSlots(F, RegInfo, CSI)) {
    // If target doesn't implement this, use generic code.

    if (CSI.empty())
      return; // Early exit if no callee saved registers are modified!

    unsigned NumFixedSpillSlots;
    const TargetFrameLowering::SpillSlot *FixedSpillSlots =
        TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots);

    // Now that we know which registers need to be saved and restored, allocate
    // stack slots for them.
    for (auto &CS : CSI) {
      // If the target has spilled this register to another register, we don't
      // need to allocate a stack slot.
      if (CS.isSpilledToReg())
        continue;

      unsigned Reg = CS.getReg();
      const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg);

      int FrameIdx;
      if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) {
        CS.setFrameIdx(FrameIdx);
        continue;
      }

      // Check to see if this physreg must be spilled to a particular stack slot
      // on this target.
      const TargetFrameLowering::SpillSlot *FixedSlot = FixedSpillSlots;
      while (FixedSlot != FixedSpillSlots + NumFixedSpillSlots &&
             FixedSlot->Reg != Reg)
        ++FixedSlot;

      unsigned Size = RegInfo->getSpillSize(*RC);
      if (FixedSlot == FixedSpillSlots + NumFixedSpillSlots) {
        // Nope, just spill it anywhere convenient.
        unsigned Align = RegInfo->getSpillAlignment(*RC);
        unsigned StackAlign = TFI->getStackAlignment();

        // We may not be able to satisfy the desired alignment specification of
        // the TargetRegisterClass if the stack alignment is smaller. Use the
        // min.
        Align = std::min(Align, StackAlign);
        FrameIdx = MFI.CreateStackObject(Size, Align, true);
        if ((unsigned)FrameIdx < MinCSFrameIndex) MinCSFrameIndex = FrameIdx;
        if ((unsigned)FrameIdx > MaxCSFrameIndex) MaxCSFrameIndex = FrameIdx;
      } else {
        // Spill it to the stack where we must.
        FrameIdx = MFI.CreateFixedSpillStackObject(Size, FixedSlot->Offset);
      }

      CS.setFrameIdx(FrameIdx);
    }
  }

  MFI.setCalleeSavedInfo(CSI);
}

/// Helper function to update the liveness information for the callee-saved
/// registers.
static void updateLiveness(MachineFunction &MF) {
  MachineFrameInfo &MFI = MF.getFrameInfo();
  // Visited will contain all the basic blocks that are in the region
  // where the callee saved registers are alive:
  // - Anything that is not Save or Restore -> LiveThrough.
  // - Save -> LiveIn.
  // - Restore -> LiveOut.
  // The live-out is not attached to the block, so no need to keep
  // Restore in this set.
  SmallPtrSet<MachineBasicBlock *, 8> Visited;
  SmallVector<MachineBasicBlock *, 8> WorkList;
  MachineBasicBlock *Entry = &MF.front();
  MachineBasicBlock *Save = MFI.getSavePoint();

  if (!Save)
    Save = Entry;

  if (Entry != Save) {
    WorkList.push_back(Entry);
    Visited.insert(Entry);
  }
  Visited.insert(Save);

  MachineBasicBlock *Restore = MFI.getRestorePoint();
  if (Restore)
    // By construction Restore cannot be visited, otherwise it
    // means there exists a path to Restore that does not go
    // through Save.
    WorkList.push_back(Restore);

  while (!WorkList.empty()) {
    const MachineBasicBlock *CurBB = WorkList.pop_back_val();
    // By construction, the region that is after the save point is
    // dominated by the Save and post-dominated by the Restore.
    if (CurBB == Save && Save != Restore)
      continue;
    // Enqueue all the successors not already visited.
    // Those are by construction either before Save or after Restore.
    for (MachineBasicBlock *SuccBB : CurBB->successors())
      if (Visited.insert(SuccBB).second)
        WorkList.push_back(SuccBB);
  }

  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();

  MachineRegisterInfo &MRI = MF.getRegInfo();
  for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
    for (MachineBasicBlock *MBB : Visited) {
      MCPhysReg Reg = CSI[i].getReg();
      // Add the callee-saved register as live-in.
      // It's killed at the spill.
      if (!MRI.isReserved(Reg) && !MBB->isLiveIn(Reg))
        MBB->addLiveIn(Reg);
    }
    // If callee-saved register is spilled to another register rather than
    // spilling to stack, the destination register has to be marked as live for
    // each MBB between the prologue and epilogue so that it is not clobbered
    // before it is reloaded in the epilogue. The Visited set contains all
    // blocks outside of the region delimited by prologue/epilogue.
    if (CSI[i].isSpilledToReg()) {
      for (MachineBasicBlock &MBB : MF) {
        if (Visited.count(&MBB))
          continue;
        MCPhysReg DstReg = CSI[i].getDstReg();
        if (!MBB.isLiveIn(DstReg))
          MBB.addLiveIn(DstReg);
      }
    }
  }

}

/// Insert restore code for the callee-saved registers used in the function.
static void insertCSRSaves(MachineBasicBlock &SaveBlock,
                           ArrayRef<CalleeSavedInfo> CSI) {
  MachineFunction &MF = *SaveBlock.getParent();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();
  const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();

  MachineBasicBlock::iterator I = SaveBlock.begin();
  if (!TFI->spillCalleeSavedRegisters(SaveBlock, I, CSI, TRI)) {
    for (const CalleeSavedInfo &CS : CSI) {
      // Insert the spill to the stack frame.
      unsigned Reg = CS.getReg();

      if (CS.isSpilledToReg()) {
        BuildMI(SaveBlock, I, DebugLoc(),
                TII.get(TargetOpcode::COPY), CS.getDstReg())
          .addReg(Reg, getKillRegState(true));
      } else {
        const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
        TII.storeRegToStackSlot(SaveBlock, I, Reg, true, CS.getFrameIdx(), RC,
                                TRI);
      }
    }
  }
}

/// Insert restore code for the callee-saved registers used in the function.
static void insertCSRRestores(MachineBasicBlock &RestoreBlock,
                              std::vector<CalleeSavedInfo> &CSI) {
  MachineFunction &MF = *RestoreBlock.getParent();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();
  const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();

  // Restore all registers immediately before the return and any
  // terminators that precede it.
  MachineBasicBlock::iterator I = RestoreBlock.getFirstTerminator();

  if (!TFI->restoreCalleeSavedRegisters(RestoreBlock, I, CSI, TRI)) {
    for (const CalleeSavedInfo &CI : reverse(CSI)) {
      unsigned Reg = CI.getReg();
      if (CI.isSpilledToReg()) {
        BuildMI(RestoreBlock, I, DebugLoc(), TII.get(TargetOpcode::COPY), Reg)
          .addReg(CI.getDstReg(), getKillRegState(true));
      } else {
        const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
        TII.loadRegFromStackSlot(RestoreBlock, I, Reg, CI.getFrameIdx(), RC, TRI);
        assert(I != RestoreBlock.begin() &&
               "loadRegFromStackSlot didn't insert any code!");
        // Insert in reverse order.  loadRegFromStackSlot can insert
        // multiple instructions.
      }
    }
  }
}

void PEI::spillCalleeSavedRegs(MachineFunction &MF) {
  // We can't list this requirement in getRequiredProperties because some
  // targets (WebAssembly) use virtual registers past this point, and the pass
  // pipeline is set up without giving the passes a chance to look at the
  // TargetMachine.
  // FIXME: Find a way to express this in getRequiredProperties.
  assert(MF.getProperties().hasProperty(
      MachineFunctionProperties::Property::NoVRegs));

  const Function &F = MF.getFunction();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MinCSFrameIndex = std::numeric_limits<unsigned>::max();
  MaxCSFrameIndex = 0;

  // Determine which of the registers in the callee save list should be saved.
  BitVector SavedRegs;
  TFI->determineCalleeSaves(MF, SavedRegs, RS);

  // Assign stack slots for any callee-saved registers that must be spilled.
  assignCalleeSavedSpillSlots(MF, SavedRegs, MinCSFrameIndex, MaxCSFrameIndex);

  // Add the code to save and restore the callee saved registers.
  if (!F.hasFnAttribute(Attribute::Naked)) {
    MFI.setCalleeSavedInfoValid(true);

    std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
    if (!CSI.empty()) {
      if (!MFI.hasCalls())
        NumLeafFuncWithSpills++;

      for (MachineBasicBlock *SaveBlock : SaveBlocks) {
        insertCSRSaves(*SaveBlock, CSI);
        // Update the live-in information of all the blocks up to the save
        // point.
        updateLiveness(MF);
      }
      for (MachineBasicBlock *RestoreBlock : RestoreBlocks)
        insertCSRRestores(*RestoreBlock, CSI);
    }
  }
}

/// AdjustStackOffset - Helper function used to adjust the stack frame offset.
static inline void
AdjustStackOffset(MachineFrameInfo &MFI, int FrameIdx,
                  bool StackGrowsDown, int64_t &Offset,
                  unsigned &MaxAlign, unsigned Skew) {
  // If the stack grows down, add the object size to find the lowest address.
  if (StackGrowsDown)
    Offset += MFI.getObjectSize(FrameIdx);

  unsigned Align = MFI.getObjectAlignment(FrameIdx);

  // If the alignment of this object is greater than that of the stack, then
  // increase the stack alignment to match.
  MaxAlign = std::max(MaxAlign, Align);

  // Adjust to alignment boundary.
  Offset = alignTo(Offset, Align, Skew);

  if (StackGrowsDown) {
    LLVM_DEBUG(dbgs() << "alloc FI(" << FrameIdx << ") at SP[" << -Offset
                      << "]\n");
    MFI.setObjectOffset(FrameIdx, -Offset); // Set the computed offset
  } else {
    LLVM_DEBUG(dbgs() << "alloc FI(" << FrameIdx << ") at SP[" << Offset
                      << "]\n");
    MFI.setObjectOffset(FrameIdx, Offset);
    Offset += MFI.getObjectSize(FrameIdx);
  }
}

/// Compute which bytes of fixed and callee-save stack area are unused and keep
/// track of them in StackBytesFree.
static inline void
computeFreeStackSlots(MachineFrameInfo &MFI, bool StackGrowsDown,
                      unsigned MinCSFrameIndex, unsigned MaxCSFrameIndex,
                      int64_t FixedCSEnd, BitVector &StackBytesFree) {
  // Avoid undefined int64_t -> int conversion below in extreme case.
  if (FixedCSEnd > std::numeric_limits<int>::max())
    return;

  StackBytesFree.resize(FixedCSEnd, true);

  SmallVector<int, 16> AllocatedFrameSlots;
  // Add fixed objects.
  for (int i = MFI.getObjectIndexBegin(); i != 0; ++i)
    // StackSlot scavenging is only implemented for the default stack.
    if (MFI.getStackID(i) == TargetStackID::Default)
      AllocatedFrameSlots.push_back(i);
  // Add callee-save objects.
  for (int i = MinCSFrameIndex; i <= (int)MaxCSFrameIndex; ++i)
    if (MFI.getStackID(i) == TargetStackID::Default)
      AllocatedFrameSlots.push_back(i);

  for (int i : AllocatedFrameSlots) {
    // These are converted from int64_t, but they should always fit in int
    // because of the FixedCSEnd check above.
    int ObjOffset = MFI.getObjectOffset(i);
    int ObjSize = MFI.getObjectSize(i);
    int ObjStart, ObjEnd;
    if (StackGrowsDown) {
      // ObjOffset is negative when StackGrowsDown is true.
      ObjStart = -ObjOffset - ObjSize;
      ObjEnd = -ObjOffset;
    } else {
      ObjStart = ObjOffset;
      ObjEnd = ObjOffset + ObjSize;
    }
    // Ignore fixed holes that are in the previous stack frame.
    if (ObjEnd > 0)
      StackBytesFree.reset(ObjStart, ObjEnd);
  }
}

/// Assign frame object to an unused portion of the stack in the fixed stack
/// object range.  Return true if the allocation was successful.
static inline bool scavengeStackSlot(MachineFrameInfo &MFI, int FrameIdx,
                                     bool StackGrowsDown, unsigned MaxAlign,
                                     BitVector &StackBytesFree) {
  if (MFI.isVariableSizedObjectIndex(FrameIdx))
    return false;

  if (StackBytesFree.none()) {
    // clear it to speed up later scavengeStackSlot calls to
    // StackBytesFree.none()
    StackBytesFree.clear();
    return false;
  }

  unsigned ObjAlign = MFI.getObjectAlignment(FrameIdx);
  if (ObjAlign > MaxAlign)
    return false;

  int64_t ObjSize = MFI.getObjectSize(FrameIdx);
  int FreeStart;
  for (FreeStart = StackBytesFree.find_first(); FreeStart != -1;
       FreeStart = StackBytesFree.find_next(FreeStart)) {

    // Check that free space has suitable alignment.
    unsigned ObjStart = StackGrowsDown ? FreeStart + ObjSize : FreeStart;
    if (alignTo(ObjStart, ObjAlign) != ObjStart)
      continue;

    if (FreeStart + ObjSize > StackBytesFree.size())
      return false;

    bool AllBytesFree = true;
    for (unsigned Byte = 0; Byte < ObjSize; ++Byte)
      if (!StackBytesFree.test(FreeStart + Byte)) {
        AllBytesFree = false;
        break;
      }
    if (AllBytesFree)
      break;
  }

  if (FreeStart == -1)
    return false;

  if (StackGrowsDown) {
    int ObjStart = -(FreeStart + ObjSize);
    LLVM_DEBUG(dbgs() << "alloc FI(" << FrameIdx << ") scavenged at SP["
                      << ObjStart << "]\n");
    MFI.setObjectOffset(FrameIdx, ObjStart);
  } else {
    LLVM_DEBUG(dbgs() << "alloc FI(" << FrameIdx << ") scavenged at SP["
                      << FreeStart << "]\n");
    MFI.setObjectOffset(FrameIdx, FreeStart);
  }

  StackBytesFree.reset(FreeStart, FreeStart + ObjSize);
  return true;
}

/// AssignProtectedObjSet - Helper function to assign large stack objects (i.e.,
/// those required to be close to the Stack Protector) to stack offsets.
static void
AssignProtectedObjSet(const StackObjSet &UnassignedObjs,
                      SmallSet<int, 16> &ProtectedObjs,
                      MachineFrameInfo &MFI, bool StackGrowsDown,
                      int64_t &Offset, unsigned &MaxAlign, unsigned Skew) {

  for (StackObjSet::const_iterator I = UnassignedObjs.begin(),
        E = UnassignedObjs.end(); I != E; ++I) {
    int i = *I;
    AdjustStackOffset(MFI, i, StackGrowsDown, Offset, MaxAlign, Skew);
    ProtectedObjs.insert(i);
  }
}

/// calculateFrameObjectOffsets - Calculate actual frame offsets for all of the
/// abstract stack objects.
void PEI::calculateFrameObjectOffsets(MachineFunction &MF) {
  const TargetFrameLowering &TFI = *MF.getSubtarget().getFrameLowering();

  bool StackGrowsDown =
    TFI.getStackGrowthDirection() == TargetFrameLowering::StackGrowsDown;

  // Loop over all of the stack objects, assigning sequential addresses...
  MachineFrameInfo &MFI = MF.getFrameInfo();

  // Start at the beginning of the local area.
  // The Offset is the distance from the stack top in the direction
  // of stack growth -- so it's always nonnegative.
  int LocalAreaOffset = TFI.getOffsetOfLocalArea();
  if (StackGrowsDown)
    LocalAreaOffset = -LocalAreaOffset;
  assert(LocalAreaOffset >= 0
         && "Local area offset should be in direction of stack growth");
  int64_t Offset = LocalAreaOffset;

  // Skew to be applied to alignment.
  unsigned Skew = TFI.getStackAlignmentSkew(MF);

#ifdef EXPENSIVE_CHECKS
  for (unsigned i = 0, e = MFI.getObjectIndexEnd(); i != e; ++i)
    if (!MFI.isDeadObjectIndex(i) &&
        MFI.getStackID(i) == TargetStackID::Default)
      assert(MFI.getObjectAlignment(i) <= MFI.getMaxAlignment() &&
             "MaxAlignment is invalid");
#endif

  // If there are fixed sized objects that are preallocated in the local area,
  // non-fixed objects can't be allocated right at the start of local area.
  // Adjust 'Offset' to point to the end of last fixed sized preallocated
  // object.
  for (int i = MFI.getObjectIndexBegin(); i != 0; ++i) {
    if (MFI.getStackID(i) !=
        TargetStackID::Default) // Only allocate objects on the default stack.
      continue;

    int64_t FixedOff;
    if (StackGrowsDown) {
      // The maximum distance from the stack pointer is at lower address of
      // the object -- which is given by offset. For down growing stack
      // the offset is negative, so we negate the offset to get the distance.
      FixedOff = -MFI.getObjectOffset(i);
    } else {
      // The maximum distance from the start pointer is at the upper
      // address of the object.
      FixedOff = MFI.getObjectOffset(i) + MFI.getObjectSize(i);
    }
    if (FixedOff > Offset) Offset = FixedOff;
  }

  // First assign frame offsets to stack objects that are used to spill
  // callee saved registers.
  if (StackGrowsDown) {
    for (unsigned i = MinCSFrameIndex; i <= MaxCSFrameIndex; ++i) {
      if (MFI.getStackID(i) !=
          TargetStackID::Default) // Only allocate objects on the default stack.
        continue;

      // If the stack grows down, we need to add the size to find the lowest
      // address of the object.
      Offset += MFI.getObjectSize(i);

      unsigned Align = MFI.getObjectAlignment(i);
      // Adjust to alignment boundary
      Offset = alignTo(Offset, Align, Skew);

      LLVM_DEBUG(dbgs() << "alloc FI(" << i << ") at SP[" << -Offset << "]\n");
      MFI.setObjectOffset(i, -Offset);        // Set the computed offset
    }
  } else if (MaxCSFrameIndex >= MinCSFrameIndex) {
    // Be careful about underflow in comparisons agains MinCSFrameIndex.
    for (unsigned i = MaxCSFrameIndex; i != MinCSFrameIndex - 1; --i) {
      if (MFI.getStackID(i) !=
          TargetStackID::Default) // Only allocate objects on the default stack.
        continue;

      if (MFI.isDeadObjectIndex(i))
        continue;

      unsigned Align = MFI.getObjectAlignment(i);
      // Adjust to alignment boundary
      Offset = alignTo(Offset, Align, Skew);

      LLVM_DEBUG(dbgs() << "alloc FI(" << i << ") at SP[" << Offset << "]\n");
      MFI.setObjectOffset(i, Offset);
      Offset += MFI.getObjectSize(i);
    }
  }

  // FixedCSEnd is the stack offset to the end of the fixed and callee-save
  // stack area.
  int64_t FixedCSEnd = Offset;
  unsigned MaxAlign = MFI.getMaxAlignment();

  // Make sure the special register scavenging spill slot is closest to the
  // incoming stack pointer if a frame pointer is required and is closer
  // to the incoming rather than the final stack pointer.
  const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
  bool EarlyScavengingSlots = (TFI.hasFP(MF) &&
                               TFI.isFPCloseToIncomingSP() &&
                               RegInfo->useFPForScavengingIndex(MF) &&
                               !RegInfo->needsStackRealignment(MF));
  if (RS && EarlyScavengingSlots) {
    SmallVector<int, 2> SFIs;
    RS->getScavengingFrameIndices(SFIs);
    for (SmallVectorImpl<int>::iterator I = SFIs.begin(),
           IE = SFIs.end(); I != IE; ++I)
      AdjustStackOffset(MFI, *I, StackGrowsDown, Offset, MaxAlign, Skew);
  }

  // FIXME: Once this is working, then enable flag will change to a target
  // check for whether the frame is large enough to want to use virtual
  // frame index registers. Functions which don't want/need this optimization
  // will continue to use the existing code path.
  if (MFI.getUseLocalStackAllocationBlock()) {
    unsigned Align = MFI.getLocalFrameMaxAlign().value();

    // Adjust to alignment boundary.
    Offset = alignTo(Offset, Align, Skew);

    LLVM_DEBUG(dbgs() << "Local frame base offset: " << Offset << "\n");

    // Resolve offsets for objects in the local block.
    for (unsigned i = 0, e = MFI.getLocalFrameObjectCount(); i != e; ++i) {
      std::pair<int, int64_t> Entry = MFI.getLocalFrameObjectMap(i);
      int64_t FIOffset = (StackGrowsDown ? -Offset : Offset) + Entry.second;
      LLVM_DEBUG(dbgs() << "alloc FI(" << Entry.first << ") at SP[" << FIOffset
                        << "]\n");
      MFI.setObjectOffset(Entry.first, FIOffset);
    }
    // Allocate the local block
    Offset += MFI.getLocalFrameSize();

    MaxAlign = std::max(Align, MaxAlign);
  }

  // Retrieve the Exception Handler registration node.
  int EHRegNodeFrameIndex = std::numeric_limits<int>::max();
  if (const WinEHFuncInfo *FuncInfo = MF.getWinEHFuncInfo())
    EHRegNodeFrameIndex = FuncInfo->EHRegNodeFrameIndex;

  // Make sure that the stack protector comes before the local variables on the
  // stack.
  SmallSet<int, 16> ProtectedObjs;
  if (MFI.hasStackProtectorIndex()) {
    int StackProtectorFI = MFI.getStackProtectorIndex();
    StackObjSet LargeArrayObjs;
    StackObjSet SmallArrayObjs;
    StackObjSet AddrOfObjs;

    // If we need a stack protector, we need to make sure that
    // LocalStackSlotPass didn't already allocate a slot for it.
    // If we are told to use the LocalStackAllocationBlock, the stack protector
    // is expected to be already pre-allocated.
    if (!MFI.getUseLocalStackAllocationBlock())
      AdjustStackOffset(MFI, StackProtectorFI, StackGrowsDown, Offset, MaxAlign,
                        Skew);
    else if (!MFI.isObjectPreAllocated(MFI.getStackProtectorIndex()))
      llvm_unreachable(
          "Stack protector not pre-allocated by LocalStackSlotPass.");

    // Assign large stack objects first.
    for (unsigned i = 0, e = MFI.getObjectIndexEnd(); i != e; ++i) {
      if (MFI.isObjectPreAllocated(i) && MFI.getUseLocalStackAllocationBlock())
        continue;
      if (i >= MinCSFrameIndex && i <= MaxCSFrameIndex)
        continue;
      if (RS && RS->isScavengingFrameIndex((int)i))
        continue;
      if (MFI.isDeadObjectIndex(i))
        continue;
      if (StackProtectorFI == (int)i || EHRegNodeFrameIndex == (int)i)
        continue;
      if (MFI.getStackID(i) !=
          TargetStackID::Default) // Only allocate objects on the default stack.
        continue;

      switch (MFI.getObjectSSPLayout(i)) {
      case MachineFrameInfo::SSPLK_None:
        continue;
      case MachineFrameInfo::SSPLK_SmallArray:
        SmallArrayObjs.insert(i);
        continue;
      case MachineFrameInfo::SSPLK_AddrOf:
        AddrOfObjs.insert(i);
        continue;
      case MachineFrameInfo::SSPLK_LargeArray:
        LargeArrayObjs.insert(i);
        continue;
      }
      llvm_unreachable("Unexpected SSPLayoutKind.");
    }

    // We expect **all** the protected stack objects to be pre-allocated by
    // LocalStackSlotPass. If it turns out that PEI still has to allocate some
    // of them, we may end up messing up the expected order of the objects.
    if (MFI.getUseLocalStackAllocationBlock() &&
        !(LargeArrayObjs.empty() && SmallArrayObjs.empty() &&
          AddrOfObjs.empty()))
      llvm_unreachable("Found protected stack objects not pre-allocated by "
                       "LocalStackSlotPass.");

    AssignProtectedObjSet(LargeArrayObjs, ProtectedObjs, MFI, StackGrowsDown,
                          Offset, MaxAlign, Skew);
    AssignProtectedObjSet(SmallArrayObjs, ProtectedObjs, MFI, StackGrowsDown,
                          Offset, MaxAlign, Skew);
    AssignProtectedObjSet(AddrOfObjs, ProtectedObjs, MFI, StackGrowsDown,
                          Offset, MaxAlign, Skew);
  }

  SmallVector<int, 8> ObjectsToAllocate;

  // Then prepare to assign frame offsets to stack objects that are not used to
  // spill callee saved registers.
  for (unsigned i = 0, e = MFI.getObjectIndexEnd(); i != e; ++i) {
    if (MFI.isObjectPreAllocated(i) && MFI.getUseLocalStackAllocationBlock())
      continue;
    if (i >= MinCSFrameIndex && i <= MaxCSFrameIndex)
      continue;
    if (RS && RS->isScavengingFrameIndex((int)i))
      continue;
    if (MFI.isDeadObjectIndex(i))
      continue;
    if (MFI.getStackProtectorIndex() == (int)i || EHRegNodeFrameIndex == (int)i)
      continue;
    if (ProtectedObjs.count(i))
      continue;
    if (MFI.getStackID(i) !=
        TargetStackID::Default) // Only allocate objects on the default stack.
      continue;

    // Add the objects that we need to allocate to our working set.
    ObjectsToAllocate.push_back(i);
  }

  // Allocate the EH registration node first if one is present.
  if (EHRegNodeFrameIndex != std::numeric_limits<int>::max())
    AdjustStackOffset(MFI, EHRegNodeFrameIndex, StackGrowsDown, Offset,
                      MaxAlign, Skew);

  // Give the targets a chance to order the objects the way they like it.
  if (MF.getTarget().getOptLevel() != CodeGenOpt::None &&
      MF.getTarget().Options.StackSymbolOrdering)
    TFI.orderFrameObjects(MF, ObjectsToAllocate);

  // Keep track of which bytes in the fixed and callee-save range are used so we
  // can use the holes when allocating later stack objects.  Only do this if
  // stack protector isn't being used and the target requests it and we're
  // optimizing.
  BitVector StackBytesFree;
  if (!ObjectsToAllocate.empty() &&
      MF.getTarget().getOptLevel() != CodeGenOpt::None &&
      MFI.getStackProtectorIndex() < 0 && TFI.enableStackSlotScavenging(MF))
    computeFreeStackSlots(MFI, StackGrowsDown, MinCSFrameIndex, MaxCSFrameIndex,
                          FixedCSEnd, StackBytesFree);

  // Now walk the objects and actually assign base offsets to them.
  for (auto &Object : ObjectsToAllocate)
    if (!scavengeStackSlot(MFI, Object, StackGrowsDown, MaxAlign,
                           StackBytesFree))
      AdjustStackOffset(MFI, Object, StackGrowsDown, Offset, MaxAlign, Skew);

  // Make sure the special register scavenging spill slot is closest to the
  // stack pointer.
  if (RS && !EarlyScavengingSlots) {
    SmallVector<int, 2> SFIs;
    RS->getScavengingFrameIndices(SFIs);
    for (SmallVectorImpl<int>::iterator I = SFIs.begin(),
           IE = SFIs.end(); I != IE; ++I)
      AdjustStackOffset(MFI, *I, StackGrowsDown, Offset, MaxAlign, Skew);
  }

  if (!TFI.targetHandlesStackFrameRounding()) {
    // If we have reserved argument space for call sites in the function
    // immediately on entry to the current function, count it as part of the
    // overall stack size.
    if (MFI.adjustsStack() && TFI.hasReservedCallFrame(MF))
      Offset += MFI.getMaxCallFrameSize();

    // Round up the size to a multiple of the alignment.  If the function has
    // any calls or alloca's, align to the target's StackAlignment value to
    // ensure that the callee's frame or the alloca data is suitably aligned;
    // otherwise, for leaf functions, align to the TransientStackAlignment
    // value.
    unsigned StackAlign;
    if (MFI.adjustsStack() || MFI.hasVarSizedObjects() ||
        (RegInfo->needsStackRealignment(MF) && MFI.getObjectIndexEnd() != 0))
      StackAlign = TFI.getStackAlignment();
    else
      StackAlign = TFI.getTransientStackAlignment();

    // If the frame pointer is eliminated, all frame offsets will be relative to
    // SP not FP. Align to MaxAlign so this works.
    StackAlign = std::max(StackAlign, MaxAlign);
    Offset = alignTo(Offset, StackAlign, Skew);
  }

  // Update frame info to pretend that this is part of the stack...
  int64_t StackSize = Offset - LocalAreaOffset;
  MFI.setStackSize(StackSize);
  NumBytesStackSpace += StackSize;
}

/// insertPrologEpilogCode - Scan the function for modified callee saved
/// registers, insert spill code for these callee saved registers, then add
/// prolog and epilog code to the function.
void PEI::insertPrologEpilogCode(MachineFunction &MF) {
  const TargetFrameLowering &TFI = *MF.getSubtarget().getFrameLowering();

  // Add prologue to the function...
  for (MachineBasicBlock *SaveBlock : SaveBlocks)
    TFI.emitPrologue(MF, *SaveBlock);

  // Add epilogue to restore the callee-save registers in each exiting block.
  for (MachineBasicBlock *RestoreBlock : RestoreBlocks)
    TFI.emitEpilogue(MF, *RestoreBlock);

  for (MachineBasicBlock *SaveBlock : SaveBlocks)
    TFI.inlineStackProbe(MF, *SaveBlock);

  // Emit additional code that is required to support segmented stacks, if
  // we've been asked for it.  This, when linked with a runtime with support
  // for segmented stacks (libgcc is one), will result in allocating stack
  // space in small chunks instead of one large contiguous block.
  if (MF.shouldSplitStack()) {
    for (MachineBasicBlock *SaveBlock : SaveBlocks)
      TFI.adjustForSegmentedStacks(MF, *SaveBlock);
    // Record that there are split-stack functions, so we will emit a
    // special section to tell the linker.
    MF.getMMI().setHasSplitStack(true);
  } else
    MF.getMMI().setHasNosplitStack(true);

  // Emit additional code that is required to explicitly handle the stack in
  // HiPE native code (if needed) when loaded in the Erlang/OTP runtime. The
  // approach is rather similar to that of Segmented Stacks, but it uses a
  // different conditional check and another BIF for allocating more stack
  // space.
  if (MF.getFunction().getCallingConv() == CallingConv::HiPE)
    for (MachineBasicBlock *SaveBlock : SaveBlocks)
      TFI.adjustForHiPEPrologue(MF, *SaveBlock);
}

/// replaceFrameIndices - Replace all MO_FrameIndex operands with physical
/// register references and actual offsets.
void PEI::replaceFrameIndices(MachineFunction &MF) {
  const auto &ST = MF.getSubtarget();
  const TargetFrameLowering &TFI = *ST.getFrameLowering();
  if (!TFI.needsFrameIndexResolution(MF))
    return;

  const TargetRegisterInfo *TRI = ST.getRegisterInfo();

  // Allow the target to determine this after knowing the frame size.
  FrameIndexEliminationScavenging = (RS && !FrameIndexVirtualScavenging) ||
    TRI->requiresFrameIndexReplacementScavenging(MF);

  // Store SPAdj at exit of a basic block.
  SmallVector<int, 8> SPState;
  SPState.resize(MF.getNumBlockIDs());
  df_iterator_default_set<MachineBasicBlock*> Reachable;

  // Iterate over the reachable blocks in DFS order.
  for (auto DFI = df_ext_begin(&MF, Reachable), DFE = df_ext_end(&MF, Reachable);
       DFI != DFE; ++DFI) {
    int SPAdj = 0;
    // Check the exit state of the DFS stack predecessor.
    if (DFI.getPathLength() >= 2) {
      MachineBasicBlock *StackPred = DFI.getPath(DFI.getPathLength() - 2);
      assert(Reachable.count(StackPred) &&
             "DFS stack predecessor is already visited.\n");
      SPAdj = SPState[StackPred->getNumber()];
    }
    MachineBasicBlock *BB = *DFI;
    replaceFrameIndices(BB, MF, SPAdj);
    SPState[BB->getNumber()] = SPAdj;
  }

  // Handle the unreachable blocks.
  for (auto &BB : MF) {
    if (Reachable.count(&BB))
      // Already handled in DFS traversal.
      continue;
    int SPAdj = 0;
    replaceFrameIndices(&BB, MF, SPAdj);
  }
}

void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &MF,
                              int &SPAdj) {
  assert(MF.getSubtarget().getRegisterInfo() &&
         "getRegisterInfo() must be implemented!");
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetRegisterInfo &TRI = *MF.getSubtarget().getRegisterInfo();
  const TargetFrameLowering *TFI = MF.getSubtarget().getFrameLowering();

  if (RS && FrameIndexEliminationScavenging)
    RS->enterBasicBlock(*BB);

  bool InsideCallSequence = false;

  for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ) {
    if (TII.isFrameInstr(*I)) {
      InsideCallSequence = TII.isFrameSetup(*I);
      SPAdj += TII.getSPAdjust(*I);
      I = TFI->eliminateCallFramePseudoInstr(MF, *BB, I);
      continue;
    }

    MachineInstr &MI = *I;
    bool DoIncr = true;
    bool DidFinishLoop = true;
    for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) {
      if (!MI.getOperand(i).isFI())
        continue;

      // Frame indices in debug values are encoded in a target independent
      // way with simply the frame index and offset rather than any
      // target-specific addressing mode.
      if (MI.isDebugValue()) {
        assert(i == 0 && "Frame indices can only appear as the first "
                         "operand of a DBG_VALUE machine instruction");
        unsigned Reg;
        unsigned FrameIdx = MI.getOperand(0).getIndex();
        unsigned Size = MF.getFrameInfo().getObjectSize(FrameIdx);

        int64_t Offset =
            TFI->getFrameIndexReference(MF, FrameIdx, Reg);
        MI.getOperand(0).ChangeToRegister(Reg, false /*isDef*/);
        MI.getOperand(0).setIsDebug();

        const DIExpression *DIExpr = MI.getDebugExpression();

        // If we have a direct DBG_VALUE, and its location expression isn't
        // currently complex, then adding an offset will morph it into a
        // complex location that is interpreted as being a memory address.
        // This changes a pointer-valued variable to dereference that pointer,
        // which is incorrect. Fix by adding DW_OP_stack_value.
        unsigned PrependFlags = DIExpression::ApplyOffset;
        if (!MI.isIndirectDebugValue() && !DIExpr->isComplex())
          PrependFlags |= DIExpression::StackValue;

        // If we have DBG_VALUE that is indirect and has a Implicit location
        // expression need to insert a deref before prepending a Memory
        // location expression. Also after doing this we change the DBG_VALUE
        // to be direct.
        if (MI.isIndirectDebugValue() && DIExpr->isImplicit()) {
          SmallVector<uint64_t, 2> Ops = {dwarf::DW_OP_deref_size, Size};
          bool WithStackValue = true;
          DIExpr = DIExpression::prependOpcodes(DIExpr, Ops, WithStackValue);
          // Make the DBG_VALUE direct.
          MI.getOperand(1).ChangeToRegister(0, false);
        }
        DIExpr = DIExpression::prepend(DIExpr, PrependFlags, Offset);
        MI.getOperand(3).setMetadata(DIExpr);
        continue;
      }

      // TODO: This code should be commoned with the code for
      // PATCHPOINT. There's no good reason for the difference in
      // implementation other than historical accident.  The only
      // remaining difference is the unconditional use of the stack
      // pointer as the base register.
      if (MI.getOpcode() == TargetOpcode::STATEPOINT) {
        assert((!MI.isDebugValue() || i == 0) &&
               "Frame indicies can only appear as the first operand of a "
               "DBG_VALUE machine instruction");
        unsigned Reg;
        MachineOperand &Offset = MI.getOperand(i + 1);
        int refOffset = TFI->getFrameIndexReferencePreferSP(
            MF, MI.getOperand(i).getIndex(), Reg, /*IgnoreSPUpdates*/ false);
        Offset.setImm(Offset.getImm() + refOffset + SPAdj);
        MI.getOperand(i).ChangeToRegister(Reg, false /*isDef*/);
        continue;
      }

      // Some instructions (e.g. inline asm instructions) can have
      // multiple frame indices and/or cause eliminateFrameIndex
      // to insert more than one instruction. We need the register
      // scavenger to go through all of these instructions so that
      // it can update its register information. We keep the
      // iterator at the point before insertion so that we can
      // revisit them in full.
      bool AtBeginning = (I == BB->begin());
      if (!AtBeginning) --I;

      // If this instruction has a FrameIndex operand, we need to
      // use that target machine register info object to eliminate
      // it.
      TRI.eliminateFrameIndex(MI, SPAdj, i,
                              FrameIndexEliminationScavenging ?  RS : nullptr);

      // Reset the iterator if we were at the beginning of the BB.
      if (AtBeginning) {
        I = BB->begin();
        DoIncr = false;
      }

      DidFinishLoop = false;
      break;
    }

    // If we are looking at a call sequence, we need to keep track of
    // the SP adjustment made by each instruction in the sequence.
    // This includes both the frame setup/destroy pseudos (handled above),
    // as well as other instructions that have side effects w.r.t the SP.
    // Note that this must come after eliminateFrameIndex, because
    // if I itself referred to a frame index, we shouldn't count its own
    // adjustment.
    if (DidFinishLoop && InsideCallSequence)
      SPAdj += TII.getSPAdjust(MI);

    if (DoIncr && I != BB->end()) ++I;

    // Update register states.
    if (RS && FrameIndexEliminationScavenging && DidFinishLoop)
      RS->forward(MI);
  }
}