bool Thumb1FrameLowering::needPopSpecialFixUp(const MachineFunction &MF) const {
ARMFunctionInfo *AFI =
const_cast<MachineFunction *>(&MF)->getInfo<ARMFunctionInfo>();
if (AFI->getArgRegsSaveSize())
return true;
bool IsV4PopReturn = false;
for (const CalleeSavedInfo &CSI : MF.getFrameInfo()->getCalleeSavedInfo())
if (CSI.getReg() == ARM::LR)
IsV4PopReturn = true;
return IsV4PopReturn && STI.hasV4TOps() && !STI.hasV5TOps();
}
bool Thumb1FrameLowering::needPopSpecialFixUp(const MachineFunction &MF) const {
ARMFunctionInfo *AFI =
const_cast<MachineFunction *>(&MF)->getInfo<ARMFunctionInfo>();
if (AFI->getArgRegsSaveSize())
return true;
// LR cannot be encoded with Thumb1, i.e., it requires a special fix-up.
for (const CalleeSavedInfo &CSI : MF.getFrameInfo().getCalleeSavedInfo())
if (CSI.getReg() == ARM::LR)
return true;
return false;
}
bool Thumb1FrameLowering::
restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
if (CSI.empty())
return false;
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const TargetInstrInfo &TII = *STI.getInstrInfo();
bool isVarArg = AFI->getArgRegsSaveSize() > 0;
DebugLoc DL = MI != MBB.end() ? MI->getDebugLoc() : DebugLoc();
MachineInstrBuilder MIB = BuildMI(MF, DL, TII.get(ARM::tPOP));
AddDefaultPred(MIB);
bool NeedsPop = false;
for (unsigned i = CSI.size(); i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
if (Reg == ARM::LR) {
if (MBB.succ_empty()) {
// Special epilogue for vararg functions. See emitEpilogue
if (isVarArg)
continue;
// ARMv4T requires BX, see emitEpilogue
if (!STI.hasV5TOps())
continue;
Reg = ARM::PC;
(*MIB).setDesc(TII.get(ARM::tPOP_RET));
if (MI != MBB.end())
MIB.copyImplicitOps(*MI);
MI = MBB.erase(MI);
} else
// LR may only be popped into PC, as part of return sequence.
// If this isn't the return sequence, we'll need emitPopSpecialFixUp
// to restore LR the hard way.
continue;
}
MIB.addReg(Reg, getDefRegState(true));
NeedsPop = true;
}
// It's illegal to emit pop instruction without operands.
if (NeedsPop)
MBB.insert(MI, &*MIB);
else
MF.DeleteMachineInstr(MIB);
return true;
}
bool Thumb1FrameLowering::needPopSpecialFixUp(const MachineFunction &MF) const {
ARMFunctionInfo *AFI =
const_cast<MachineFunction *>(&MF)->getInfo<ARMFunctionInfo>();
if (AFI->getArgRegsSaveSize())
return true;
// FIXME: this doesn't make sense, and the following patch will remove it.
if (!STI.hasV4TOps()) return false;
// LR cannot be encoded with Thumb1, i.e., it requires a special fix-up.
for (const CalleeSavedInfo &CSI : MF.getFrameInfo()->getCalleeSavedInfo())
if (CSI.getReg() == ARM::LR)
return true;
return false;
}
bool Thumb1FrameLowering::
restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
if (CSI.empty())
return false;
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const TargetInstrInfo &TII = *STI.getInstrInfo();
bool isVarArg = AFI->getArgRegsSaveSize() > 0;
DebugLoc DL = MI->getDebugLoc();
MachineInstrBuilder MIB = BuildMI(MF, DL, TII.get(ARM::tPOP));
AddDefaultPred(MIB);
bool NumRegs = false;
for (unsigned i = CSI.size(); i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
if (Reg == ARM::LR) {
// Special epilogue for vararg functions. See emitEpilogue
if (isVarArg)
continue;
// ARMv4T requires BX, see emitEpilogue
if (STI.hasV4TOps() && !STI.hasV5TOps())
continue;
Reg = ARM::PC;
(*MIB).setDesc(TII.get(ARM::tPOP_RET));
MIB.copyImplicitOps(&*MI);
MI = MBB.erase(MI);
}
MIB.addReg(Reg, getDefRegState(true));
NumRegs = true;
}
// It's illegal to emit pop instruction without operands.
if (NumRegs)
MBB.insert(MI, &*MIB);
else
MF.DeleteMachineInstr(MIB);
return true;
}
void Thumb1FrameLowering::emitPrologue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
MachineModuleInfo &MMI = MF.getMMI();
const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
unsigned NumBytes = MFI->getStackSize();
assert(NumBytes >= ArgRegsSaveSize &&
"ArgRegsSaveSize is included in NumBytes");
const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
// Debug location must be unknown since the first debug location is used
// to determine the end of the prologue.
DebugLoc dl;
unsigned FramePtr = RegInfo->getFrameRegister(MF);
unsigned BasePtr = RegInfo->getBaseRegister();
int CFAOffset = 0;
// Thumb add/sub sp, imm8 instructions implicitly multiply the offset by 4.
NumBytes = (NumBytes + 3) & ~3;
MFI->setStackSize(NumBytes);
// Determine the sizes of each callee-save spill areas and record which frame
// belongs to which callee-save spill areas.
unsigned GPRCS1Size = 0, GPRCS2Size = 0, DPRCSSize = 0;
int FramePtrSpillFI = 0;
if (ArgRegsSaveSize) {
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize,
MachineInstr::FrameSetup);
CFAOffset -= ArgRegsSaveSize;
unsigned CFIIndex = MMI.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
if (!AFI->hasStackFrame()) {
if (NumBytes - ArgRegsSaveSize != 0) {
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -(NumBytes - ArgRegsSaveSize),
MachineInstr::FrameSetup);
CFAOffset -= NumBytes - ArgRegsSaveSize;
unsigned CFIIndex = MMI.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
return;
}
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
unsigned Reg = CSI[i].getReg();
int FI = CSI[i].getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
if (STI.isTargetMachO()) {
GPRCS2Size += 4;
break;
}
// fallthrough
case ARM::R4:
case ARM::R5:
case ARM::R6:
case ARM::R7:
case ARM::LR:
if (Reg == FramePtr)
FramePtrSpillFI = FI;
GPRCS1Size += 4;
break;
default:
DPRCSSize += 8;
}
}
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
++MBBI;
}
// Determine starting offsets of spill areas.
unsigned DPRCSOffset = NumBytes - ArgRegsSaveSize - (GPRCS1Size + GPRCS2Size + DPRCSSize);
unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
unsigned GPRCS1Offset = GPRCS2Offset + GPRCS2Size;
bool HasFP = hasFP(MF);
if (HasFP)
AFI->setFramePtrSpillOffset(MFI->getObjectOffset(FramePtrSpillFI) +
NumBytes);
AFI->setGPRCalleeSavedArea1Offset(GPRCS1Offset);
AFI->setGPRCalleeSavedArea2Offset(GPRCS2Offset);
AFI->setDPRCalleeSavedAreaOffset(DPRCSOffset);
NumBytes = DPRCSOffset;
int FramePtrOffsetInBlock = 0;
unsigned adjustedGPRCS1Size = GPRCS1Size;
if (tryFoldSPUpdateIntoPushPop(STI, MF, std::prev(MBBI), NumBytes)) {
FramePtrOffsetInBlock = NumBytes;
adjustedGPRCS1Size += NumBytes;
NumBytes = 0;
}
if (adjustedGPRCS1Size) {
CFAOffset -= adjustedGPRCS1Size;
unsigned CFIIndex = MMI.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
E = CSI.end(); I != E; ++I) {
unsigned Reg = I->getReg();
int FI = I->getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
case ARM::R12:
if (STI.isTargetMachO())
break;
// fallthough
case ARM::R0:
case ARM::R1:
case ARM::R2:
case ARM::R3:
case ARM::R4:
case ARM::R5:
case ARM::R6:
case ARM::R7:
case ARM::LR:
unsigned CFIIndex = MMI.addFrameInst(MCCFIInstruction::createOffset(
nullptr, MRI->getDwarfRegNum(Reg, true), MFI->getObjectOffset(FI)));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
break;
}
}
// Adjust FP so it point to the stack slot that contains the previous FP.
if (HasFP) {
FramePtrOffsetInBlock +=
MFI->getObjectOffset(FramePtrSpillFI) + GPRCS1Size + ArgRegsSaveSize;
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
.addReg(ARM::SP).addImm(FramePtrOffsetInBlock / 4)
.setMIFlags(MachineInstr::FrameSetup));
if(FramePtrOffsetInBlock) {
CFAOffset += FramePtrOffsetInBlock;
unsigned CFIIndex = MMI.addFrameInst(MCCFIInstruction::createDefCfa(
nullptr, MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
} else {
unsigned CFIIndex =
MMI.addFrameInst(MCCFIInstruction::createDefCfaRegister(
nullptr, MRI->getDwarfRegNum(FramePtr, true)));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
if (NumBytes > 508)
// If offset is > 508 then sp cannot be adjusted in a single instruction,
// try restoring from fp instead.
AFI->setShouldRestoreSPFromFP(true);
}
if (NumBytes) {
// Insert it after all the callee-save spills.
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
MachineInstr::FrameSetup);
if (!HasFP) {
CFAOffset -= NumBytes;
unsigned CFIIndex = MMI.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
}
if (STI.isTargetELF() && HasFP)
MFI->setOffsetAdjustment(MFI->getOffsetAdjustment() -
AFI->getFramePtrSpillOffset());
AFI->setGPRCalleeSavedArea1Size(GPRCS1Size);
AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
AFI->setDPRCalleeSavedAreaSize(DPRCSSize);
// Thumb1 does not currently support dynamic stack realignment. Report a
// fatal error rather then silently generate bad code.
if (RegInfo->needsStackRealignment(MF))
report_fatal_error("Dynamic stack realignment not supported for thumb1.");
// If we need a base pointer, set it up here. It's whatever the value
// of the stack pointer is at this point. Any variable size objects
// will be allocated after this, so we can still use the base pointer
// to reference locals.
if (RegInfo->hasBasePointer(MF))
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), BasePtr)
.addReg(ARM::SP));
// If the frame has variable sized objects then the epilogue must restore
// the sp from fp. We can assume there's an FP here since hasFP already
// checks for hasVarSizedObjects.
if (MFI->hasVarSizedObjects())
AFI->setShouldRestoreSPFromFP(true);
}
bool Thumb1FrameLowering::emitPopSpecialFixUp(MachineBasicBlock &MBB,
bool DoIt) const {
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
const TargetInstrInfo &TII = *STI.getInstrInfo();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
// If MBBI is a return instruction, we may be able to directly restore
// LR in the PC.
// This is possible if we do not need to emit any SP update.
// Otherwise, we need a temporary register to pop the value
// and copy that value into LR.
auto MBBI = MBB.getFirstTerminator();
if (!ArgRegsSaveSize && MBBI != MBB.end() &&
MBBI->getOpcode() == ARM::tBX_RET) {
if (!DoIt)
return true;
MachineInstrBuilder MIB =
AddDefaultPred(
BuildMI(MBB, MBBI, MBBI->getDebugLoc(), TII.get(ARM::tPOP_RET)))
.addReg(ARM::PC, RegState::Define);
MIB.copyImplicitOps(&*MBBI);
// erase the old tBX_RET instruction
MBB.erase(MBBI);
return true;
}
// Look for a temporary register to use.
// First, compute the liveness information.
LivePhysRegs UsedRegs(STI.getRegisterInfo());
UsedRegs.addLiveOuts(&MBB, /*AddPristines*/ true);
// The semantic of pristines changed recently and now,
// the callee-saved registers that are touched in the function
// are not part of the pristines set anymore.
// Add those callee-saved now.
const TargetRegisterInfo *TRI = STI.getRegisterInfo();
const MCPhysReg *CSRegs = TRI->getCalleeSavedRegs(&MF);
for (unsigned i = 0; CSRegs[i]; ++i)
UsedRegs.addReg(CSRegs[i]);
DebugLoc dl = DebugLoc();
if (MBBI != MBB.end()) {
dl = MBBI->getDebugLoc();
auto InstUpToMBBI = MBB.end();
// The post-decrement is on purpose here.
// We want to have the liveness right before MBBI.
while (InstUpToMBBI-- != MBBI)
UsedRegs.stepBackward(*InstUpToMBBI);
}
// Look for a register that can be directly use in the POP.
unsigned PopReg = 0;
// And some temporary register, just in case.
unsigned TemporaryReg = 0;
BitVector PopFriendly =
TRI->getAllocatableSet(MF, TRI->getRegClass(ARM::tGPRRegClassID));
assert(PopFriendly.any() && "No allocatable pop-friendly register?!");
// Rebuild the GPRs from the high registers because they are removed
// form the GPR reg class for thumb1.
BitVector GPRsNoLRSP =
TRI->getAllocatableSet(MF, TRI->getRegClass(ARM::hGPRRegClassID));
GPRsNoLRSP |= PopFriendly;
GPRsNoLRSP.reset(ARM::LR);
GPRsNoLRSP.reset(ARM::SP);
GPRsNoLRSP.reset(ARM::PC);
for (int Register = GPRsNoLRSP.find_first(); Register != -1;
Register = GPRsNoLRSP.find_next(Register)) {
if (!UsedRegs.contains(Register)) {
// Remember the first pop-friendly register and exit.
if (PopFriendly.test(Register)) {
PopReg = Register;
TemporaryReg = 0;
break;
}
// Otherwise, remember that the register will be available to
// save a pop-friendly register.
TemporaryReg = Register;
}
}
if (!DoIt && !PopReg && !TemporaryReg)
return false;
assert((PopReg || TemporaryReg) && "Cannot get LR");
if (TemporaryReg) {
assert(!PopReg && "Unnecessary MOV is about to be inserted");
PopReg = PopFriendly.find_first();
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(TemporaryReg, RegState::Define)
.addReg(PopReg, RegState::Kill));
}
assert(PopReg && "Do not know how to get LR");
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
.addReg(PopReg, RegState::Define);
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
if (!TemporaryReg && MBBI != MBB.end() && MBBI->getOpcode() == ARM::tBX_RET) {
MachineInstrBuilder MIB = BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX))
.addReg(PopReg, RegState::Kill);
AddDefaultPred(MIB);
MIB.copyImplicitOps(&*MBBI);
// erase the old tBX_RET instruction
MBB.erase(MBBI);
return true;
}
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::LR, RegState::Define)
.addReg(PopReg, RegState::Kill));
if (TemporaryReg) {
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(PopReg, RegState::Define)
.addReg(TemporaryReg, RegState::Kill));
}
return true;
}
void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
DebugLoc dl = MBBI != MBB.end() ? MBBI->getDebugLoc() : DebugLoc();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
int NumBytes = (int)MFI->getStackSize();
assert((unsigned)NumBytes >= ArgRegsSaveSize &&
"ArgRegsSaveSize is included in NumBytes");
const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
unsigned FramePtr = RegInfo->getFrameRegister(MF);
if (!AFI->hasStackFrame()) {
if (NumBytes - ArgRegsSaveSize != 0)
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes - ArgRegsSaveSize);
} else {
// Unwind MBBI to point to first LDR / VLDRD.
if (MBBI != MBB.begin()) {
do
--MBBI;
while (MBBI != MBB.begin() && isCSRestore(MBBI, CSRegs));
if (!isCSRestore(MBBI, CSRegs))
++MBBI;
}
// Move SP to start of FP callee save spill area.
NumBytes -= (AFI->getGPRCalleeSavedArea1Size() +
AFI->getGPRCalleeSavedArea2Size() +
AFI->getDPRCalleeSavedAreaSize() +
ArgRegsSaveSize);
if (AFI->shouldRestoreSPFromFP()) {
NumBytes = AFI->getFramePtrSpillOffset() - NumBytes;
// Reset SP based on frame pointer only if the stack frame extends beyond
// frame pointer stack slot, the target is ELF and the function has FP, or
// the target uses var sized objects.
if (NumBytes) {
assert(!MFI->getPristineRegs(MF).test(ARM::R4) &&
"No scratch register to restore SP from FP!");
emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
TII, *RegInfo);
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(ARM::R4));
} else
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(FramePtr));
} else {
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tBX_RET &&
&MBB.front() != MBBI && std::prev(MBBI)->getOpcode() == ARM::tPOP) {
MachineBasicBlock::iterator PMBBI = std::prev(MBBI);
if (!tryFoldSPUpdateIntoPushPop(STI, MF, PMBBI, NumBytes))
emitSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes);
} else if (!tryFoldSPUpdateIntoPushPop(STI, MF, MBBI, NumBytes))
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes);
}
}
if (needPopSpecialFixUp(MF)) {
bool Done = emitPopSpecialFixUp(MBB, /* DoIt */ true);
(void)Done;
assert(Done && "Emission of the special fixup failed!?");
}
}
bool Thumb1FrameLowering::
restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
if (CSI.empty())
return false;
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const TargetInstrInfo &TII = *STI.getInstrInfo();
const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
MF.getSubtarget().getRegisterInfo());
bool isVarArg = AFI->getArgRegsSaveSize() > 0;
DebugLoc DL = MI != MBB.end() ? MI->getDebugLoc() : DebugLoc();
ARMRegSet LoRegsToRestore;
ARMRegSet HiRegsToRestore;
// Low registers (r0-r7) which can be used to restore the high registers.
ARMRegSet CopyRegs;
for (CalleeSavedInfo I : CSI) {
unsigned Reg = I.getReg();
if (ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR) {
LoRegsToRestore[Reg] = true;
} else if (ARM::hGPRRegClass.contains(Reg) && Reg != ARM::LR) {
HiRegsToRestore[Reg] = true;
} else {
llvm_unreachable("callee-saved register of unexpected class");
}
// If this is a low register not used as the frame pointer, we may want to
// use it for restoring the high registers.
if ((ARM::tGPRRegClass.contains(Reg)) &&
!(hasFP(MF) && Reg == RegInfo->getFrameRegister(MF)))
CopyRegs[Reg] = true;
}
// If this is a return block, we may be able to use some unused return value
// registers for restoring the high regs.
auto Terminator = MBB.getFirstTerminator();
if (Terminator != MBB.end() && Terminator->getOpcode() == ARM::tBX_RET) {
CopyRegs[ARM::R0] = true;
CopyRegs[ARM::R1] = true;
CopyRegs[ARM::R2] = true;
CopyRegs[ARM::R3] = true;
for (auto Op : Terminator->implicit_operands()) {
if (Op.isReg())
CopyRegs[Op.getReg()] = false;
}
}
static const unsigned AllCopyRegs[] = {ARM::R0, ARM::R1, ARM::R2, ARM::R3,
ARM::R4, ARM::R5, ARM::R6, ARM::R7};
static const unsigned AllHighRegs[] = {ARM::R8, ARM::R9, ARM::R10, ARM::R11};
const unsigned *AllCopyRegsEnd = std::end(AllCopyRegs);
const unsigned *AllHighRegsEnd = std::end(AllHighRegs);
// Find the first register to restore.
auto HiRegToRestore = findNextOrderedReg(std::begin(AllHighRegs),
HiRegsToRestore, AllHighRegsEnd);
while (HiRegToRestore != AllHighRegsEnd) {
assert(!CopyRegs.none());
// Find the first low register to use.
auto CopyReg =
findNextOrderedReg(std::begin(AllCopyRegs), CopyRegs, AllCopyRegsEnd);
// Create the POP instruction.
MachineInstrBuilder PopMIB =
BuildMI(MBB, MI, DL, TII.get(ARM::tPOP)).add(predOps(ARMCC::AL));
while (HiRegToRestore != AllHighRegsEnd && CopyReg != AllCopyRegsEnd) {
// Add the low register to the POP.
PopMIB.addReg(*CopyReg, RegState::Define);
// Create the MOV from low to high register.
BuildMI(MBB, MI, DL, TII.get(ARM::tMOVr))
.addReg(*HiRegToRestore, RegState::Define)
.addReg(*CopyReg, RegState::Kill)
.add(predOps(ARMCC::AL));
CopyReg = findNextOrderedReg(++CopyReg, CopyRegs, AllCopyRegsEnd);
HiRegToRestore =
findNextOrderedReg(++HiRegToRestore, HiRegsToRestore, AllHighRegsEnd);
}
}
MachineInstrBuilder MIB =
BuildMI(MF, DL, TII.get(ARM::tPOP)).add(predOps(ARMCC::AL));
bool NeedsPop = false;
for (unsigned i = CSI.size(); i != 0; --i) {
CalleeSavedInfo &Info = CSI[i-1];
unsigned Reg = Info.getReg();
// High registers (excluding lr) have already been dealt with
if (!(ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR))
continue;
if (Reg == ARM::LR) {
Info.setRestored(false);
if (!MBB.succ_empty() ||
MI->getOpcode() == ARM::TCRETURNdi ||
MI->getOpcode() == ARM::TCRETURNri)
// LR may only be popped into PC, as part of return sequence.
// If this isn't the return sequence, we'll need emitPopSpecialFixUp
// to restore LR the hard way.
// FIXME: if we don't pass any stack arguments it would be actually
// advantageous *and* correct to do the conversion to an ordinary call
// instruction here.
continue;
// Special epilogue for vararg functions. See emitEpilogue
if (isVarArg)
continue;
// ARMv4T requires BX, see emitEpilogue
if (!STI.hasV5TOps())
continue;
// Pop LR into PC.
Reg = ARM::PC;
(*MIB).setDesc(TII.get(ARM::tPOP_RET));
if (MI != MBB.end())
MIB.copyImplicitOps(*MI);
MI = MBB.erase(MI);
}
MIB.addReg(Reg, getDefRegState(true));
NeedsPop = true;
}
// It's illegal to emit pop instruction without operands.
if (NeedsPop)
MBB.insert(MI, &*MIB);
else
MF.DeleteMachineInstr(MIB);
return true;
}
bool Thumb1FrameLowering::emitPopSpecialFixUp(MachineBasicBlock &MBB,
bool DoIt) const {
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
const TargetInstrInfo &TII = *STI.getInstrInfo();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
// If MBBI is a return instruction, or is a tPOP followed by a return
// instruction in the successor BB, we may be able to directly restore
// LR in the PC.
// This is only possible with v5T ops (v4T can't change the Thumb bit via
// a POP PC instruction), and only if we do not need to emit any SP update.
// Otherwise, we need a temporary register to pop the value
// and copy that value into LR.
auto MBBI = MBB.getFirstTerminator();
bool CanRestoreDirectly = STI.hasV5TOps() && !ArgRegsSaveSize;
if (CanRestoreDirectly) {
if (MBBI != MBB.end() && MBBI->getOpcode() != ARM::tB)
CanRestoreDirectly = (MBBI->getOpcode() == ARM::tBX_RET ||
MBBI->getOpcode() == ARM::tPOP_RET);
else {
auto MBBI_prev = MBBI;
MBBI_prev--;
assert(MBBI_prev->getOpcode() == ARM::tPOP);
assert(MBB.succ_size() == 1);
if ((*MBB.succ_begin())->begin()->getOpcode() == ARM::tBX_RET)
MBBI = MBBI_prev; // Replace the final tPOP with a tPOP_RET.
else
CanRestoreDirectly = false;
}
}
if (CanRestoreDirectly) {
if (!DoIt || MBBI->getOpcode() == ARM::tPOP_RET)
return true;
MachineInstrBuilder MIB =
BuildMI(MBB, MBBI, MBBI->getDebugLoc(), TII.get(ARM::tPOP_RET))
.add(predOps(ARMCC::AL));
// Copy implicit ops and popped registers, if any.
for (auto MO: MBBI->operands())
if (MO.isReg() && (MO.isImplicit() || MO.isDef()))
MIB.add(MO);
MIB.addReg(ARM::PC, RegState::Define);
// Erase the old instruction (tBX_RET or tPOP).
MBB.erase(MBBI);
return true;
}
// Look for a temporary register to use.
// First, compute the liveness information.
const TargetRegisterInfo &TRI = *STI.getRegisterInfo();
LivePhysRegs UsedRegs(TRI);
UsedRegs.addLiveOuts(MBB);
// The semantic of pristines changed recently and now,
// the callee-saved registers that are touched in the function
// are not part of the pristines set anymore.
// Add those callee-saved now.
const MCPhysReg *CSRegs = TRI.getCalleeSavedRegs(&MF);
for (unsigned i = 0; CSRegs[i]; ++i)
UsedRegs.addReg(CSRegs[i]);
DebugLoc dl = DebugLoc();
if (MBBI != MBB.end()) {
dl = MBBI->getDebugLoc();
auto InstUpToMBBI = MBB.end();
while (InstUpToMBBI != MBBI)
// The pre-decrement is on purpose here.
// We want to have the liveness right before MBBI.
UsedRegs.stepBackward(*--InstUpToMBBI);
}
// Look for a register that can be directly use in the POP.
unsigned PopReg = 0;
// And some temporary register, just in case.
unsigned TemporaryReg = 0;
BitVector PopFriendly =
TRI.getAllocatableSet(MF, TRI.getRegClass(ARM::tGPRRegClassID));
assert(PopFriendly.any() && "No allocatable pop-friendly register?!");
// Rebuild the GPRs from the high registers because they are removed
// form the GPR reg class for thumb1.
BitVector GPRsNoLRSP =
TRI.getAllocatableSet(MF, TRI.getRegClass(ARM::hGPRRegClassID));
GPRsNoLRSP |= PopFriendly;
GPRsNoLRSP.reset(ARM::LR);
GPRsNoLRSP.reset(ARM::SP);
GPRsNoLRSP.reset(ARM::PC);
findTemporariesForLR(GPRsNoLRSP, PopFriendly, UsedRegs, PopReg, TemporaryReg);
// If we couldn't find a pop-friendly register, restore LR before popping the
// other callee-saved registers, so we can use one of them as a temporary.
bool UseLDRSP = false;
if (!PopReg && MBBI != MBB.begin()) {
auto PrevMBBI = MBBI;
PrevMBBI--;
if (PrevMBBI->getOpcode() == ARM::tPOP) {
MBBI = PrevMBBI;
UsedRegs.stepBackward(*MBBI);
findTemporariesForLR(GPRsNoLRSP, PopFriendly, UsedRegs, PopReg, TemporaryReg);
UseLDRSP = true;
}
}
if (!DoIt && !PopReg && !TemporaryReg)
return false;
assert((PopReg || TemporaryReg) && "Cannot get LR");
if (UseLDRSP) {
assert(PopReg && "Do not know how to get LR");
// Load the LR via LDR tmp, [SP, #off]
BuildMI(MBB, MBBI, dl, TII.get(ARM::tLDRspi))
.addReg(PopReg, RegState::Define)
.addReg(ARM::SP)
.addImm(MBBI->getNumExplicitOperands() - 2)
.add(predOps(ARMCC::AL));
// Move from the temporary register to the LR.
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::LR, RegState::Define)
.addReg(PopReg, RegState::Kill)
.add(predOps(ARMCC::AL));
// Advance past the pop instruction.
MBBI++;
// Increment the SP.
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize + 4);
return true;
}
if (TemporaryReg) {
assert(!PopReg && "Unnecessary MOV is about to be inserted");
PopReg = PopFriendly.find_first();
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(TemporaryReg, RegState::Define)
.addReg(PopReg, RegState::Kill)
.add(predOps(ARMCC::AL));
}
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPOP_RET) {
// We couldn't use the direct restoration above, so
// perform the opposite conversion: tPOP_RET to tPOP.
MachineInstrBuilder MIB =
BuildMI(MBB, MBBI, MBBI->getDebugLoc(), TII.get(ARM::tPOP))
.add(predOps(ARMCC::AL));
bool Popped = false;
for (auto MO: MBBI->operands())
if (MO.isReg() && (MO.isImplicit() || MO.isDef()) &&
MO.getReg() != ARM::PC) {
MIB.add(MO);
if (!MO.isImplicit())
Popped = true;
}
// Is there anything left to pop?
if (!Popped)
MBB.erase(MIB.getInstr());
// Erase the old instruction.
MBB.erase(MBBI);
MBBI = BuildMI(MBB, MBB.end(), dl, TII.get(ARM::tBX_RET))
.add(predOps(ARMCC::AL));
}
assert(PopReg && "Do not know how to get LR");
BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP))
.add(predOps(ARMCC::AL))
.addReg(PopReg, RegState::Define);
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::LR, RegState::Define)
.addReg(PopReg, RegState::Kill)
.add(predOps(ARMCC::AL));
if (TemporaryReg)
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(PopReg, RegState::Define)
.addReg(TemporaryReg, RegState::Kill)
.add(predOps(ARMCC::AL));
return true;
}
void Thumb1FrameLowering::emitPrologue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineFrameInfo &MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
MachineModuleInfo &MMI = MF.getMMI();
const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
unsigned NumBytes = MFI.getStackSize();
assert(NumBytes >= ArgRegsSaveSize &&
"ArgRegsSaveSize is included in NumBytes");
const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
// Debug location must be unknown since the first debug location is used
// to determine the end of the prologue.
DebugLoc dl;
unsigned FramePtr = RegInfo->getFrameRegister(MF);
unsigned BasePtr = RegInfo->getBaseRegister();
int CFAOffset = 0;
// Thumb add/sub sp, imm8 instructions implicitly multiply the offset by 4.
NumBytes = (NumBytes + 3) & ~3;
MFI.setStackSize(NumBytes);
// Determine the sizes of each callee-save spill areas and record which frame
// belongs to which callee-save spill areas.
unsigned GPRCS1Size = 0, GPRCS2Size = 0, DPRCSSize = 0;
int FramePtrSpillFI = 0;
if (ArgRegsSaveSize) {
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize,
MachineInstr::FrameSetup);
CFAOffset -= ArgRegsSaveSize;
unsigned CFIIndex = MF.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
if (!AFI->hasStackFrame()) {
if (NumBytes - ArgRegsSaveSize != 0) {
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -(NumBytes - ArgRegsSaveSize),
MachineInstr::FrameSetup);
CFAOffset -= NumBytes - ArgRegsSaveSize;
unsigned CFIIndex = MF.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
return;
}
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
unsigned Reg = CSI[i].getReg();
int FI = CSI[i].getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
if (STI.splitFramePushPop(MF)) {
GPRCS2Size += 4;
break;
}
LLVM_FALLTHROUGH;
case ARM::R4:
case ARM::R5:
case ARM::R6:
case ARM::R7:
case ARM::LR:
if (Reg == FramePtr)
FramePtrSpillFI = FI;
GPRCS1Size += 4;
break;
default:
DPRCSSize += 8;
}
}
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
++MBBI;
}
// Determine starting offsets of spill areas.
unsigned DPRCSOffset = NumBytes - ArgRegsSaveSize - (GPRCS1Size + GPRCS2Size + DPRCSSize);
unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
unsigned GPRCS1Offset = GPRCS2Offset + GPRCS2Size;
bool HasFP = hasFP(MF);
if (HasFP)
AFI->setFramePtrSpillOffset(MFI.getObjectOffset(FramePtrSpillFI) +
NumBytes);
AFI->setGPRCalleeSavedArea1Offset(GPRCS1Offset);
AFI->setGPRCalleeSavedArea2Offset(GPRCS2Offset);
AFI->setDPRCalleeSavedAreaOffset(DPRCSOffset);
NumBytes = DPRCSOffset;
int FramePtrOffsetInBlock = 0;
unsigned adjustedGPRCS1Size = GPRCS1Size;
if (GPRCS1Size > 0 && GPRCS2Size == 0 &&
tryFoldSPUpdateIntoPushPop(STI, MF, &*std::prev(MBBI), NumBytes)) {
FramePtrOffsetInBlock = NumBytes;
adjustedGPRCS1Size += NumBytes;
NumBytes = 0;
}
if (adjustedGPRCS1Size) {
CFAOffset -= adjustedGPRCS1Size;
unsigned CFIIndex = MF.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
E = CSI.end(); I != E; ++I) {
unsigned Reg = I->getReg();
int FI = I->getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
case ARM::R12:
if (STI.splitFramePushPop(MF))
break;
LLVM_FALLTHROUGH;
case ARM::R0:
case ARM::R1:
case ARM::R2:
case ARM::R3:
case ARM::R4:
case ARM::R5:
case ARM::R6:
case ARM::R7:
case ARM::LR:
unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createOffset(
nullptr, MRI->getDwarfRegNum(Reg, true), MFI.getObjectOffset(FI)));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
break;
}
}
// Adjust FP so it point to the stack slot that contains the previous FP.
if (HasFP) {
FramePtrOffsetInBlock +=
MFI.getObjectOffset(FramePtrSpillFI) + GPRCS1Size + ArgRegsSaveSize;
BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
.addReg(ARM::SP)
.addImm(FramePtrOffsetInBlock / 4)
.setMIFlags(MachineInstr::FrameSetup)
.add(predOps(ARMCC::AL));
if(FramePtrOffsetInBlock) {
CFAOffset += FramePtrOffsetInBlock;
unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
nullptr, MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
} else {
unsigned CFIIndex =
MF.addFrameInst(MCCFIInstruction::createDefCfaRegister(
nullptr, MRI->getDwarfRegNum(FramePtr, true)));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
if (NumBytes > 508)
// If offset is > 508 then sp cannot be adjusted in a single instruction,
// try restoring from fp instead.
AFI->setShouldRestoreSPFromFP(true);
}
// Skip past the spilling of r8-r11, which could consist of multiple tPUSH
// and tMOVr instructions. We don't need to add any call frame information
// in-between these instructions, because they do not modify the high
// registers.
while (true) {
MachineBasicBlock::iterator OldMBBI = MBBI;
// Skip a run of tMOVr instructions
while (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tMOVr)
MBBI++;
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
MBBI++;
} else {
// We have reached an instruction which is not a push, so the previous
// run of tMOVr instructions (which may have been empty) was not part of
// the prologue. Reset MBBI back to the last PUSH of the prologue.
MBBI = OldMBBI;
break;
}
}
// Emit call frame information for the callee-saved high registers.
for (auto &I : CSI) {
unsigned Reg = I.getReg();
int FI = I.getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
case ARM::R12: {
unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createOffset(
nullptr, MRI->getDwarfRegNum(Reg, true), MFI.getObjectOffset(FI)));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
break;
}
default:
break;
}
}
if (NumBytes) {
// Insert it after all the callee-save spills.
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
MachineInstr::FrameSetup);
if (!HasFP) {
CFAOffset -= NumBytes;
unsigned CFIIndex = MF.addFrameInst(
MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
.addCFIIndex(CFIIndex)
.setMIFlags(MachineInstr::FrameSetup);
}
}
if (STI.isTargetELF() && HasFP)
MFI.setOffsetAdjustment(MFI.getOffsetAdjustment() -
AFI->getFramePtrSpillOffset());
AFI->setGPRCalleeSavedArea1Size(GPRCS1Size);
AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
AFI->setDPRCalleeSavedAreaSize(DPRCSSize);
if (RegInfo->needsStackRealignment(MF)) {
const unsigned NrBitsToZero = countTrailingZeros(MFI.getMaxAlignment());
// Emit the following sequence, using R4 as a temporary, since we cannot use
// SP as a source or destination register for the shifts:
// mov r4, sp
// lsrs r4, r4, #NrBitsToZero
// lsls r4, r4, #NrBitsToZero
// mov sp, r4
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::R4)
.addReg(ARM::SP, RegState::Kill)
.add(predOps(ARMCC::AL));
BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSRri), ARM::R4)
.addDef(ARM::CPSR)
.addReg(ARM::R4, RegState::Kill)
.addImm(NrBitsToZero)
.add(predOps(ARMCC::AL));
BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSLri), ARM::R4)
.addDef(ARM::CPSR)
.addReg(ARM::R4, RegState::Kill)
.addImm(NrBitsToZero)
.add(predOps(ARMCC::AL));
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::SP)
.addReg(ARM::R4, RegState::Kill)
.add(predOps(ARMCC::AL));
AFI->setShouldRestoreSPFromFP(true);
}
// If we need a base pointer, set it up here. It's whatever the value
// of the stack pointer is at this point. Any variable size objects
// will be allocated after this, so we can still use the base pointer
// to reference locals.
if (RegInfo->hasBasePointer(MF))
BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), BasePtr)
.addReg(ARM::SP)
.add(predOps(ARMCC::AL));
// If the frame has variable sized objects then the epilogue must restore
// the sp from fp. We can assume there's an FP here since hasFP already
// checks for hasVarSizedObjects.
if (MFI.hasVarSizedObjects())
AFI->setShouldRestoreSPFromFP(true);
// In some cases, virtual registers have been introduced, e.g. by uses of
// emitThumbRegPlusImmInReg.
MF.getProperties().reset(MachineFunctionProperties::Property::NoVRegs);
}
void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
assert((MBBI->getOpcode() == ARM::tBX_RET ||
MBBI->getOpcode() == ARM::tPOP_RET) &&
"Can only insert epilog into returning blocks");
DebugLoc dl = MBBI->getDebugLoc();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const ThumbRegisterInfo *RegInfo =
static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
int NumBytes = (int)MFI->getStackSize();
assert((unsigned)NumBytes >= ArgRegsSaveSize &&
"ArgRegsSaveSize is included in NumBytes");
const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
unsigned FramePtr = RegInfo->getFrameRegister(MF);
if (!AFI->hasStackFrame()) {
if (NumBytes - ArgRegsSaveSize != 0)
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes - ArgRegsSaveSize);
} else {
// Unwind MBBI to point to first LDR / VLDRD.
if (MBBI != MBB.begin()) {
do
--MBBI;
while (MBBI != MBB.begin() && isCSRestore(MBBI, CSRegs));
if (!isCSRestore(MBBI, CSRegs))
++MBBI;
}
// Move SP to start of FP callee save spill area.
NumBytes -= (AFI->getGPRCalleeSavedArea1Size() +
AFI->getGPRCalleeSavedArea2Size() +
AFI->getDPRCalleeSavedAreaSize() +
ArgRegsSaveSize);
if (AFI->shouldRestoreSPFromFP()) {
NumBytes = AFI->getFramePtrSpillOffset() - NumBytes;
// Reset SP based on frame pointer only if the stack frame extends beyond
// frame pointer stack slot, the target is ELF and the function has FP, or
// the target uses var sized objects.
if (NumBytes) {
assert(MF.getRegInfo().isPhysRegUsed(ARM::R4) &&
"No scratch register to restore SP from FP!");
emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
TII, *RegInfo);
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(ARM::R4));
} else
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(FramePtr));
} else {
if (MBBI->getOpcode() == ARM::tBX_RET &&
&MBB.front() != MBBI &&
std::prev(MBBI)->getOpcode() == ARM::tPOP) {
MachineBasicBlock::iterator PMBBI = std::prev(MBBI);
if (!tryFoldSPUpdateIntoPushPop(STI, MF, PMBBI, NumBytes))
emitSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes);
} else if (!tryFoldSPUpdateIntoPushPop(STI, MF, MBBI, NumBytes))
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes);
}
}
bool IsV4PopReturn = false;
for (const CalleeSavedInfo &CSI : MFI->getCalleeSavedInfo())
if (CSI.getReg() == ARM::LR)
IsV4PopReturn = true;
IsV4PopReturn &= STI.hasV4TOps() && !STI.hasV5TOps();
// Unlike T2 and ARM mode, the T1 pop instruction cannot restore
// to LR, and we can't pop the value directly to the PC since
// we need to update the SP after popping the value. So instead
// we have to emit:
// POP {r3}
// ADD sp, #offset
// BX r3
// If this would clobber a return value, then generate this sequence instead:
// MOV ip, r3
// POP {r3}
// ADD sp, #offset
// MOV lr, r3
// MOV r3, ip
// BX lr
if (ArgRegsSaveSize || IsV4PopReturn) {
// Get the last instruction, tBX_RET
MBBI = MBB.getLastNonDebugInstr();
assert (MBBI->getOpcode() == ARM::tBX_RET);
DebugLoc dl = MBBI->getDebugLoc();
if (AFI->getReturnRegsCount() <= 3) {
// Epilogue: pop saved LR to R3 and branch off it.
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
.addReg(ARM::R3, RegState::Define);
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
MachineInstrBuilder MIB =
BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX))
.addReg(ARM::R3, RegState::Kill);
AddDefaultPred(MIB);
MIB.copyImplicitOps(&*MBBI);
// erase the old tBX_RET instruction
MBB.erase(MBBI);
} else {
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::R12, RegState::Define)
.addReg(ARM::R3, RegState::Kill));
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
.addReg(ARM::R3, RegState::Define);
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::LR, RegState::Define)
.addReg(ARM::R3, RegState::Kill));
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
.addReg(ARM::R3, RegState::Define)
.addReg(ARM::R12, RegState::Kill));
// Keep the tBX_RET instruction
}
}
}
void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
assert((MBBI->getOpcode() == ARM::tBX_RET ||
MBBI->getOpcode() == ARM::tPOP_RET) &&
"Can only insert epilog into returning blocks");
DebugLoc dl = MBBI->getDebugLoc();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const Thumb1RegisterInfo *RegInfo =
static_cast<const Thumb1RegisterInfo*>(MF.getTarget().getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo*>(MF.getTarget().getInstrInfo());
unsigned Align = MF.getTarget().getFrameLowering()->getStackAlignment();
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize(Align);
int NumBytes = (int)MFI->getStackSize();
const uint16_t *CSRegs = RegInfo->getCalleeSavedRegs();
unsigned FramePtr = RegInfo->getFrameRegister(MF);
if (!AFI->hasStackFrame()) {
if (NumBytes != 0)
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes);
} else {
// Unwind MBBI to point to first LDR / VLDRD.
if (MBBI != MBB.begin()) {
do
--MBBI;
while (MBBI != MBB.begin() && isCSRestore(MBBI, CSRegs));
if (!isCSRestore(MBBI, CSRegs))
++MBBI;
}
// Move SP to start of FP callee save spill area.
NumBytes -= (AFI->getGPRCalleeSavedArea1Size() +
AFI->getGPRCalleeSavedArea2Size() +
AFI->getDPRCalleeSavedAreaSize());
if (AFI->shouldRestoreSPFromFP()) {
NumBytes = AFI->getFramePtrSpillOffset() - NumBytes;
// Reset SP based on frame pointer only if the stack frame extends beyond
// frame pointer stack slot, the target is ELF and the function has FP, or
// the target uses var sized objects.
if (NumBytes) {
assert(MF.getRegInfo().isPhysRegUsed(ARM::R4) &&
"No scratch register to restore SP from FP!");
emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
TII, *RegInfo);
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(ARM::R4));
} else
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
ARM::SP)
.addReg(FramePtr));
} else {
if (MBBI->getOpcode() == ARM::tBX_RET &&
&MBB.front() != MBBI &&
std::prev(MBBI)->getOpcode() == ARM::tPOP) {
MachineBasicBlock::iterator PMBBI = std::prev(MBBI);
if (!tryFoldSPUpdateIntoPushPop(STI, MF, PMBBI, NumBytes))
emitSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes);
} else if (!tryFoldSPUpdateIntoPushPop(STI, MF, MBBI, NumBytes))
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes);
}
}
if (ArgRegsSaveSize) {
// Unlike T2 and ARM mode, the T1 pop instruction cannot restore
// to LR, and we can't pop the value directly to the PC since
// we need to update the SP after popping the value. Therefore, we
// pop the old LR into R3 as a temporary.
// Get the last instruction, tBX_RET
MBBI = MBB.getLastNonDebugInstr();
assert (MBBI->getOpcode() == ARM::tBX_RET);
// Epilogue for vararg functions: pop LR to R3 and branch off it.
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
.addReg(ARM::R3, RegState::Define);
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);
MachineInstrBuilder MIB =
BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX_RET_vararg))
.addReg(ARM::R3, RegState::Kill);
AddDefaultPred(MIB);
MIB.copyImplicitOps(&*MBBI);
// erase the old tBX_RET instruction
MBB.erase(MBBI);
}
}
void Thumb1FrameLowering::emitPrologue(MachineFunction &MF) const {
MachineBasicBlock &MBB = MF.front();
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
const Thumb1RegisterInfo *RegInfo =
static_cast<const Thumb1RegisterInfo*>(MF.getTarget().getRegisterInfo());
const Thumb1InstrInfo &TII =
*static_cast<const Thumb1InstrInfo*>(MF.getTarget().getInstrInfo());
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
unsigned NumBytes = MFI->getStackSize();
const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
DebugLoc dl = MBBI != MBB.end() ? MBBI->getDebugLoc() : DebugLoc();
unsigned FramePtr = RegInfo->getFrameRegister(MF);
unsigned BasePtr = RegInfo->getBaseRegister();
// Thumb add/sub sp, imm8 instructions implicitly multiply the offset by 4.
NumBytes = (NumBytes + 3) & ~3;
MFI->setStackSize(NumBytes);
// Determine the sizes of each callee-save spill areas and record which frame
// belongs to which callee-save spill areas.
unsigned GPRCS1Size = 0, GPRCS2Size = 0, DPRCSSize = 0;
int FramePtrSpillFI = 0;
if (ArgRegsSaveSize)
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize,
MachineInstr::FrameSetup);
if (!AFI->hasStackFrame()) {
if (NumBytes != 0)
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
MachineInstr::FrameSetup);
return;
}
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
unsigned Reg = CSI[i].getReg();
int FI = CSI[i].getFrameIdx();
switch (Reg) {
case ARM::R4:
case ARM::R5:
case ARM::R6:
case ARM::R7:
case ARM::LR:
if (Reg == FramePtr)
FramePtrSpillFI = FI;
AFI->addGPRCalleeSavedArea1Frame(FI);
GPRCS1Size += 4;
break;
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
if (Reg == FramePtr)
FramePtrSpillFI = FI;
if (STI.isTargetIOS()) {
AFI->addGPRCalleeSavedArea2Frame(FI);
GPRCS2Size += 4;
} else {
AFI->addGPRCalleeSavedArea1Frame(FI);
GPRCS1Size += 4;
}
break;
default:
AFI->addDPRCalleeSavedAreaFrame(FI);
DPRCSSize += 8;
}
}
if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
++MBBI;
if (MBBI != MBB.end())
dl = MBBI->getDebugLoc();
}
// Determine starting offsets of spill areas.
unsigned DPRCSOffset = NumBytes - (GPRCS1Size + GPRCS2Size + DPRCSSize);
unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
unsigned GPRCS1Offset = GPRCS2Offset + GPRCS2Size;
bool HasFP = hasFP(MF);
if (HasFP)
AFI->setFramePtrSpillOffset(MFI->getObjectOffset(FramePtrSpillFI) +
NumBytes);
AFI->setGPRCalleeSavedArea1Offset(GPRCS1Offset);
AFI->setGPRCalleeSavedArea2Offset(GPRCS2Offset);
AFI->setDPRCalleeSavedAreaOffset(DPRCSOffset);
NumBytes = DPRCSOffset;
// Adjust FP so it point to the stack slot that contains the previous FP.
if (HasFP) {
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
.addFrameIndex(FramePtrSpillFI).addImm(0)
.setMIFlags(MachineInstr::FrameSetup));
if (NumBytes > 508)
// If offset is > 508 then sp cannot be adjusted in a single instruction,
// try restoring from fp instead.
AFI->setShouldRestoreSPFromFP(true);
}
if (NumBytes)
// Insert it after all the callee-save spills.
emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
MachineInstr::FrameSetup);
if (STI.isTargetELF() && HasFP)
MFI->setOffsetAdjustment(MFI->getOffsetAdjustment() -
AFI->getFramePtrSpillOffset());
AFI->setGPRCalleeSavedArea1Size(GPRCS1Size);
AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
AFI->setDPRCalleeSavedAreaSize(DPRCSSize);
// Thumb1 does not currently support dynamic stack realignment. Report a
// fatal error rather then silently generate bad code.
if (RegInfo->needsStackRealignment(MF))
report_fatal_error("Dynamic stack realignment not supported for thumb1.");
// If we need a base pointer, set it up here. It's whatever the value
// of the stack pointer is at this point. Any variable size objects
// will be allocated after this, so we can still use the base pointer
// to reference locals.
if (RegInfo->hasBasePointer(MF))
AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), BasePtr)
.addReg(ARM::SP));
// If the frame has variable sized objects then the epilogue must restore
// the sp from fp. We can assume there's an FP here since hasFP already
// checks for hasVarSizedObjects.
if (MFI->hasVarSizedObjects())
AFI->setShouldRestoreSPFromFP(true);
}
