#include "ARMFrameLowering.h"
#include "ARMBaseInstrInfo.h"
#include "ARMBaseRegisterInfo.h"
+#include "ARMConstantPoolValue.h"
#include "ARMMachineFunctionInfo.h"
#include "MCTargetDesc/ARMAddressingModes.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
skipAlignedDPRCS2Spills(MachineBasicBlock::iterator MI,
unsigned NumAlignedDPRCS2Regs);
+ARMFrameLowering::ARMFrameLowering(const ARMSubtarget &sti)
+ : TargetFrameLowering(StackGrowsDown, sti.getStackAlignment(), 0, 4),
+ STI(sti) {}
+
/// hasFP - Return true if the specified function should have a dedicated frame
/// pointer register. This is true if the function has variable sized allocas
/// or if frame pointer elimination is disabled.
bool ARMFrameLowering::hasFP(const MachineFunction &MF) const {
- const TargetRegisterInfo *RegInfo = MF.getTarget().getRegisterInfo();
+ const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
// iOS requires FP not to be clobbered for backtracing purpose.
if (STI.isTargetIOS())
static bool isCSRestore(MachineInstr *MI,
const ARMBaseInstrInfo &TII,
- const uint16_t *CSRegs) {
+ const MCPhysReg *CSRegs) {
// Integer spill area is handled with "pop".
if (isPopOpcode(MI->getOpcode())) {
// The first two operands are predicates. The last two are
return count;
}
+static bool WindowsRequiresStackProbe(const MachineFunction &MF,
+ size_t StackSizeInBytes) {
+ const MachineFrameInfo *MFI = MF.getFrameInfo();
+ if (MFI->getStackProtectorIndex() > 0)
+ return StackSizeInBytes >= 4080;
+ return StackSizeInBytes >= 4096;
+}
+
void ARMFrameLowering::emitPrologue(MachineFunction &MF) const {
MachineBasicBlock &MBB = MF.front();
MachineBasicBlock::iterator MBBI = MBB.begin();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
MachineModuleInfo &MMI = MF.getMMI();
MCContext &Context = MMI.getContext();
+ const TargetMachine &TM = MF.getTarget();
const MCRegisterInfo *MRI = Context.getRegisterInfo();
- const ARMBaseRegisterInfo *RegInfo =
- static_cast<const ARMBaseRegisterInfo*>(MF.getTarget().getRegisterInfo());
- const ARMBaseInstrInfo &TII =
- *static_cast<const ARMBaseInstrInfo*>(MF.getTarget().getInstrInfo());
+ const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
+ TM.getSubtargetImpl()->getRegisterInfo());
+ const ARMBaseInstrInfo &TII = *static_cast<const ARMBaseInstrInfo *>(
+ TM.getSubtargetImpl()->getInstrInfo());
assert(!AFI->isThumb1OnlyFunction() &&
"This emitPrologue does not support Thumb1!");
bool isARM = !AFI->isThumbFunction();
- unsigned Align = MF.getTarget().getFrameLowering()->getStackAlignment();
+ unsigned Align =
+ TM.getSubtargetImpl()->getFrameLowering()->getStackAlignment();
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize(Align);
unsigned NumBytes = MFI->getStackSize();
const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
if (MF.getFunction()->getCallingConv() == CallingConv::GHC)
return;
- // Allocate the vararg register save area. This is not counted in NumBytes.
+ // Allocate the vararg register save area.
if (ArgRegsSaveSize) {
emitSPUpdate(isARM, MBB, MBBI, dl, TII, -ArgRegsSaveSize,
MachineInstr::FrameSetup);
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
CFAOffset -= ArgRegsSaveSize;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(SPLabel, CFAOffset));
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
- if (!AFI->hasStackFrame()) {
- if (NumBytes != 0) {
- emitSPUpdate(isARM, MBB, MBBI, dl, TII, -NumBytes,
+ if (!AFI->hasStackFrame() &&
+ (!STI.isTargetWindows() || !WindowsRequiresStackProbe(MF, NumBytes))) {
+ if (NumBytes - ArgRegsSaveSize != 0) {
+ emitSPUpdate(isARM, MBB, MBBI, dl, TII, -(NumBytes - ArgRegsSaveSize),
MachineInstr::FrameSetup);
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
- CFAOffset -= NumBytes;
- MMI.addFrameInst(MCCFIInstruction::createDefCfaOffset(SPLabel,
- CFAOffset));
+ CFAOffset -= NumBytes - ArgRegsSaveSize;
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
return;
}
case ARM::R10:
case ARM::R11:
case ARM::R12:
- if (STI.isTargetMachO()) {
+ if (STI.isTargetDarwin()) {
GPRCS2Size += 4;
break;
}
// Determine starting offsets of spill areas.
bool HasFP = hasFP(MF);
- unsigned DPRCSOffset = NumBytes - (GPRCS1Size + GPRCS2Size + DPRCSSize);
+ unsigned DPRCSOffset = NumBytes - (ArgRegsSaveSize + GPRCS1Size
+ + GPRCS2Size + DPRCSSize);
unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
unsigned GPRCS1Offset = GPRCS2Offset + GPRCS2Size;
int FramePtrOffsetInPush = 0;
if (HasFP) {
- FramePtrOffsetInPush = MFI->getObjectOffset(FramePtrSpillFI) + GPRCS1Size;
+ FramePtrOffsetInPush = MFI->getObjectOffset(FramePtrSpillFI)
+ + GPRCS1Size + ArgRegsSaveSize;
AFI->setFramePtrSpillOffset(MFI->getObjectOffset(FramePtrSpillFI) +
NumBytes);
}
} else
NumBytes = DPRCSOffset;
+ if (STI.isTargetWindows() && WindowsRequiresStackProbe(MF, NumBytes)) {
+ uint32_t NumWords = NumBytes >> 2;
+
+ if (NumWords < 65536)
+ AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::t2MOVi16), ARM::R4)
+ .addImm(NumWords)
+ .setMIFlags(MachineInstr::FrameSetup));
+ else
+ BuildMI(MBB, MBBI, dl, TII.get(ARM::t2MOVi32imm), ARM::R4)
+ .addImm(NumWords)
+ .setMIFlags(MachineInstr::FrameSetup);
+
+ switch (TM.getCodeModel()) {
+ case CodeModel::Small:
+ case CodeModel::Medium:
+ case CodeModel::Default:
+ case CodeModel::Kernel:
+ BuildMI(MBB, MBBI, dl, TII.get(ARM::tBL))
+ .addImm((unsigned)ARMCC::AL).addReg(0)
+ .addExternalSymbol("__chkstk")
+ .addReg(ARM::R4, RegState::Implicit)
+ .setMIFlags(MachineInstr::FrameSetup);
+ break;
+ case CodeModel::Large:
+ case CodeModel::JITDefault:
+ BuildMI(MBB, MBBI, dl, TII.get(ARM::t2MOVi32imm), ARM::R12)
+ .addExternalSymbol("__chkstk")
+ .setMIFlags(MachineInstr::FrameSetup);
+
+ BuildMI(MBB, MBBI, dl, TII.get(ARM::tBLXr))
+ .addImm((unsigned)ARMCC::AL).addReg(0)
+ .addReg(ARM::R12, RegState::Kill)
+ .addReg(ARM::R4, RegState::Implicit)
+ .setMIFlags(MachineInstr::FrameSetup);
+ break;
+ }
+
+ AddDefaultCC(AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::t2SUBrr),
+ ARM::SP)
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::R4, RegState::Kill)
+ .setMIFlags(MachineInstr::FrameSetup)));
+ NumBytes = 0;
+ }
+
unsigned adjustedGPRCS1Size = GPRCS1Size;
if (NumBytes) {
// Adjust SP after all the callee-save spills.
}
if (adjustedGPRCS1Size > 0) {
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, ++GPRCS1Push, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
CFAOffset -= adjustedGPRCS1Size;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(SPLabel, CFAOffset));
- for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
- E = CSI.end(); I != E; ++I) {
- unsigned Reg = I->getReg();
- int FI = I->getFrameIdx();
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ MachineBasicBlock::iterator Pos = ++GPRCS1Push;
+ BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ for (const auto &Entry : CSI) {
+ unsigned Reg = Entry.getReg();
+ int FI = Entry.getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
case ARM::R12:
- if (STI.isTargetMachO())
+ if (STI.isTargetDarwin())
break;
// fallthrough
case ARM::R0:
case ARM::R6:
case ARM::R7:
case ARM::LR:
- MMI.addFrameInst(MCCFIInstruction::createOffset(SPLabel,
- MRI->getDwarfRegNum(Reg, true),
- MFI->getObjectOffset(FI) - ArgRegsSaveSize));
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createOffset(
+ nullptr, MRI->getDwarfRegNum(Reg, true), MFI->getObjectOffset(FI)));
+ BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
break;
}
}
emitRegPlusImmediate(!AFI->isThumbFunction(), MBB, GPRCS1Push, dl, TII,
FramePtr, ARM::SP, FramePtrOffsetInPush,
MachineInstr::FrameSetup);
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, GPRCS1Push, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
if (FramePtrOffsetInPush) {
CFAOffset += FramePtrOffsetInPush;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfa(SPLabel,
- MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
- } else
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaRegister(SPLabel,
- MRI->getDwarfRegNum(FramePtr, true)));
+ unsigned CFIIndex = MMI.addFrameInst(MCCFIInstruction::createDefCfa(
+ nullptr, MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
+ BuildMI(MBB, GPRCS1Push, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ } else {
+ unsigned CFIIndex =
+ MMI.addFrameInst(MCCFIInstruction::createDefCfaRegister(
+ nullptr, MRI->getDwarfRegNum(FramePtr, true)));
+ BuildMI(MBB, GPRCS1Push, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ }
}
if (GPRCS2Size > 0) {
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, ++GPRCS2Push, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
+ MachineBasicBlock::iterator Pos = ++GPRCS2Push;
if (!HasFP) {
CFAOffset -= GPRCS2Size;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(SPLabel, CFAOffset));
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
- for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
- E = CSI.end(); I != E; ++I) {
- unsigned Reg = I->getReg();
- int FI = I->getFrameIdx();
+ for (const auto &Entry : CSI) {
+ unsigned Reg = Entry.getReg();
+ int FI = Entry.getFrameIdx();
switch (Reg) {
case ARM::R8:
case ARM::R9:
case ARM::R10:
case ARM::R11:
case ARM::R12:
- if (STI.isTargetMachO()) {
+ if (STI.isTargetDarwin()) {
unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
- unsigned Offset = MFI->getObjectOffset(FI) - ArgRegsSaveSize;
- MMI.addFrameInst(
- MCCFIInstruction::createOffset(SPLabel, DwarfReg, Offset));
+ unsigned Offset = MFI->getObjectOffset(FI);
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
+ BuildMI(MBB, Pos, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
break;
}
if (DPRCSSize > 0) {
// Since vpush register list cannot have gaps, there may be multiple vpush
// instructions in the prologue.
- MCSymbol *SPLabel = NULL;
do {
MachineBasicBlock::iterator Push = DPRCSPush++;
if (!HasFP) {
- SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, DPRCSPush, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
- CFAOffset -= sizeOfSPAdjustment(Push);;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(SPLabel, CFAOffset));
+ CFAOffset -= sizeOfSPAdjustment(Push);
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ BuildMI(MBB, DPRCSPush, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
} while (DPRCSPush->getOpcode() == ARM::VSTMDDB_UPD);
- if (!SPLabel) {
- SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, DPRCSPush, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
- }
- for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
- E = CSI.end(); I != E; ++I) {
- unsigned Reg = I->getReg();
- int FI = I->getFrameIdx();
+ for (const auto &Entry : CSI) {
+ unsigned Reg = Entry.getReg();
+ int FI = Entry.getFrameIdx();
if ((Reg >= ARM::D0 && Reg <= ARM::D31) &&
(Reg < ARM::D8 || Reg >= ARM::D8 + AFI->getNumAlignedDPRCS2Regs())) {
unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
unsigned Offset = MFI->getObjectOffset(FI);
- MMI.addFrameInst(MCCFIInstruction::createOffset(SPLabel, DwarfReg,
- Offset));
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
+ BuildMI(MBB, DPRCSPush, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
}
}
if (NumBytes) {
if (!HasFP) {
- MCSymbol *SPLabel = Context.CreateTempSymbol();
- BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::PROLOG_LABEL))
- .addSym(SPLabel);
CFAOffset -= NumBytes;
- MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(SPLabel, CFAOffset));
+ unsigned CFIIndex = MMI.addFrameInst(
+ MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
+ BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
}
DebugLoc dl = MBBI->getDebugLoc();
MachineFrameInfo *MFI = MF.getFrameInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
- const TargetRegisterInfo *RegInfo = MF.getTarget().getRegisterInfo();
+ const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
const ARMBaseInstrInfo &TII =
- *static_cast<const ARMBaseInstrInfo*>(MF.getTarget().getInstrInfo());
+ *static_cast<const ARMBaseInstrInfo *>(MF.getSubtarget().getInstrInfo());
assert(!AFI->isThumb1OnlyFunction() &&
"This emitEpilogue does not support Thumb1!");
bool isARM = !AFI->isThumbFunction();
- unsigned Align = MF.getTarget().getFrameLowering()->getStackAlignment();
+ unsigned Align = MF.getTarget()
+ .getSubtargetImpl()
+ ->getFrameLowering()
+ ->getStackAlignment();
unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize(Align);
int NumBytes = (int)MFI->getStackSize();
unsigned FramePtr = RegInfo->getFrameRegister(MF);
return;
if (!AFI->hasStackFrame()) {
- if (NumBytes != 0)
- emitSPUpdate(isARM, MBB, MBBI, dl, TII, NumBytes);
+ if (NumBytes - ArgRegsSaveSize != 0)
+ emitSPUpdate(isARM, MBB, MBBI, dl, TII, NumBytes - ArgRegsSaveSize);
} else {
// Unwind MBBI to point to first LDR / VLDRD.
- const uint16_t *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
+ const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
if (MBBI != MBB.begin()) {
do {
--MBBI;
}
// Move SP to start of FP callee save spill area.
- NumBytes -= (AFI->getGPRCalleeSavedArea1Size() +
+ NumBytes -= (ArgRegsSaveSize +
+ AFI->getGPRCalleeSavedArea1Size() +
AFI->getGPRCalleeSavedArea2Size() +
AFI->getDPRCalleeSavedAreaSize());
int FI, unsigned &FrameReg,
int SPAdj) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
- const ARMBaseRegisterInfo *RegInfo =
- static_cast<const ARMBaseRegisterInfo*>(MF.getTarget().getRegisterInfo());
+ const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
+ MF.getSubtarget().getRegisterInfo());
const ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
int Offset = MFI->getObjectOffset(FI) + MFI->getStackSize();
int FPOffset = Offset - AFI->getFramePtrSpillOffset();
unsigned NumAlignedDPRCS2Regs,
unsigned MIFlags) const {
MachineFunction &MF = *MBB.getParent();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
DebugLoc DL;
if (MI != MBB.end()) DL = MI->getDebugLoc();
unsigned LastReg = 0;
for (; i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
- if (!(Func)(Reg, STI.isTargetMachO())) continue;
+ if (!(Func)(Reg, STI.isTargetDarwin())) continue;
// D-registers in the aligned area DPRCS2 are NOT spilled here.
if (Reg >= ARM::D8 && Reg < ARM::D8 + NumAlignedDPRCS2Regs)
AddDefaultPred(MIB);
}
Regs.clear();
+
+ // Put any subsequent vpush instructions before this one: they will refer to
+ // higher register numbers so need to be pushed first in order to preserve
+ // monotonicity.
+ --MI;
}
}
bool(*Func)(unsigned, bool),
unsigned NumAlignedDPRCS2Regs) const {
MachineFunction &MF = *MBB.getParent();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
DebugLoc DL = MI->getDebugLoc();
unsigned RetOpcode = MI->getOpcode();
bool DeleteRet = false;
for (; i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
- if (!(Func)(Reg, STI.isTargetMachO())) continue;
+ if (!(Func)(Reg, STI.isTargetDarwin())) continue;
// The aligned reloads from area DPRCS2 are not inserted here.
if (Reg >= ARM::D8 && Reg < ARM::D8 + NumAlignedDPRCS2Regs)
AddDefaultPred(MIB);
}
Regs.clear();
+
+ // Put any subsequent vpop instructions after this one: they will refer to
+ // higher register numbers so need to be popped afterwards.
+ ++MI;
}
}
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
DebugLoc DL = MI->getDebugLoc();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
MachineFrameInfo &MFI = *MF.getFrameInfo();
// Mark the D-register spill slots as properly aligned. Since MFI computes
MachineFunction &MF = *MBB.getParent();
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
DebugLoc DL = MI->getDebugLoc();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
// Find the frame index assigned to d8.
int D8SpillFI = 0;
static unsigned GetFunctionSizeInBytes(const MachineFunction &MF,
const ARMBaseInstrInfo &TII) {
unsigned FnSize = 0;
- for (MachineFunction::const_iterator MBBI = MF.begin(), E = MF.end();
- MBBI != E; ++MBBI) {
- const MachineBasicBlock &MBB = *MBBI;
- for (MachineBasicBlock::const_iterator I = MBB.begin(),E = MBB.end();
- I != E; ++I)
- FnSize += TII.GetInstSizeInBytes(I);
+ for (auto &MBB : MF) {
+ for (auto &MI : MBB)
+ FnSize += TII.GetInstSizeInBytes(&MI);
}
return FnSize;
}
const TargetFrameLowering *TFI) {
const ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
unsigned Limit = (1 << 12) - 1;
- for (MachineFunction::iterator BB = MF.begin(),E = MF.end(); BB != E; ++BB) {
- for (MachineBasicBlock::iterator I = BB->begin(), E = BB->end();
- I != E; ++I) {
- for (unsigned i = 0, e = I->getNumOperands(); i != e; ++i) {
- if (!I->getOperand(i).isFI()) continue;
+ for (auto &MBB : MF) {
+ for (auto &MI : MBB) {
+ for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) {
+ if (!MI.getOperand(i).isFI())
+ continue;
// When using ADDri to get the address of a stack object, 255 is the
// largest offset guaranteed to fit in the immediate offset.
- if (I->getOpcode() == ARM::ADDri) {
+ if (MI.getOpcode() == ARM::ADDri) {
Limit = std::min(Limit, (1U << 8) - 1);
break;
}
// Otherwise check the addressing mode.
- switch (I->getDesc().TSFlags & ARMII::AddrModeMask) {
+ switch (MI.getDesc().TSFlags & ARMII::AddrModeMask) {
case ARMII::AddrMode3:
case ARMII::AddrModeT2_i8:
Limit = std::min(Limit, (1U << 8) - 1);
return;
// Don't bother if the default stack alignment is sufficiently high.
- if (MF.getTarget().getFrameLowering()->getStackAlignment() >= 8)
+ if (MF.getTarget()
+ .getSubtargetImpl()
+ ->getFrameLowering()
+ ->getStackAlignment() >= 8)
return;
// Aligned spills require stack realignment.
- const ARMBaseRegisterInfo *RegInfo =
- static_cast<const ARMBaseRegisterInfo*>(MF.getTarget().getRegisterInfo());
+ const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
+ MF.getSubtarget().getRegisterInfo());
if (!RegInfo->canRealignStack(MF))
return;
unsigned NumGPRSpills = 0;
SmallVector<unsigned, 4> UnspilledCS1GPRs;
SmallVector<unsigned, 4> UnspilledCS2GPRs;
- const ARMBaseRegisterInfo *RegInfo =
- static_cast<const ARMBaseRegisterInfo*>(MF.getTarget().getRegisterInfo());
+ const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
+ MF.getSubtarget().getRegisterInfo());
const ARMBaseInstrInfo &TII =
- *static_cast<const ARMBaseInstrInfo*>(MF.getTarget().getInstrInfo());
+ *static_cast<const ARMBaseInstrInfo *>(MF.getSubtarget().getInstrInfo());
ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
MachineFrameInfo *MFI = MF.getFrameInfo();
MachineRegisterInfo &MRI = MF.getRegInfo();
// Don't spill FP if the frame can be eliminated. This is determined
// by scanning the callee-save registers to see if any is used.
- const uint16_t *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
+ const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
for (unsigned i = 0; CSRegs[i]; ++i) {
unsigned Reg = CSRegs[i];
bool Spilled = false;
if (Spilled) {
NumGPRSpills++;
- if (!STI.isTargetMachO()) {
+ if (!STI.isTargetDarwin()) {
if (Reg == ARM::LR)
LRSpilled = true;
CS1Spilled = true;
break;
}
} else {
- if (!STI.isTargetMachO()) {
+ if (!STI.isTargetDarwin()) {
UnspilledCS1GPRs.push_back(Reg);
continue;
}
if (hasFP(MF)) {
MRI.setPhysRegUsed(FramePtr);
+ auto FPPos = std::find(UnspilledCS1GPRs.begin(), UnspilledCS1GPRs.end(),
+ FramePtr);
+ if (FPPos != UnspilledCS1GPRs.end())
+ UnspilledCS1GPRs.erase(FPPos);
NumGPRSpills++;
}
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
MachineBasicBlock::iterator I) const {
const ARMBaseInstrInfo &TII =
- *static_cast<const ARMBaseInstrInfo*>(MF.getTarget().getInstrInfo());
+ *static_cast<const ARMBaseInstrInfo *>(MF.getSubtarget().getInstrInfo());
if (!hasReservedCallFrame(MF)) {
// If we have alloca, convert as follows:
// ADJCALLSTACKDOWN -> sub, sp, sp, amount
MBB.erase(I);
}
+/// Get the minimum constant for ARM that is greater than or equal to the
+/// argument. In ARM, constants can have any value that can be produced by
+/// rotating an 8-bit value to the right by an even number of bits within a
+/// 32-bit word.
+static uint32_t alignToARMConstant(uint32_t Value) {
+ unsigned Shifted = 0;
+
+ if (Value == 0)
+ return 0;
+
+ while (!(Value & 0xC0000000)) {
+ Value = Value << 2;
+ Shifted += 2;
+ }
+
+ bool Carry = (Value & 0x00FFFFFF);
+ Value = ((Value & 0xFF000000) >> 24) + Carry;
+
+ if (Value & 0x0000100)
+ Value = Value & 0x000001FC;
+
+ if (Shifted > 24)
+ Value = Value >> (Shifted - 24);
+ else
+ Value = Value << (24 - Shifted);
+
+ return Value;
+}
+
+// The stack limit in the TCB is set to this many bytes above the actual
+// stack limit.
+static const uint64_t kSplitStackAvailable = 256;
+
+// Adjust the function prologue to enable split stacks. This currently only
+// supports android and linux.
+//
+// The ABI of the segmented stack prologue is a little arbitrarily chosen, but
+// must be well defined in order to allow for consistent implementations of the
+// __morestack helper function. The ABI is also not a normal ABI in that it
+// doesn't follow the normal calling conventions because this allows the
+// prologue of each function to be optimized further.
+//
+// Currently, the ABI looks like (when calling __morestack)
+//
+// * r4 holds the minimum stack size requested for this function call
+// * r5 holds the stack size of the arguments to the function
+// * the beginning of the function is 3 instructions after the call to
+// __morestack
+//
+// Implementations of __morestack should use r4 to allocate a new stack, r5 to
+// place the arguments on to the new stack, and the 3-instruction knowledge to
+// jump directly to the body of the function when working on the new stack.
+//
+// An old (and possibly no longer compatible) implementation of __morestack for
+// ARM can be found at [1].
+//
+// [1] - https://github.com/mozilla/rust/blob/86efd9/src/rt/arch/arm/morestack.S
+void ARMFrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
+ unsigned Opcode;
+ unsigned CFIIndex;
+ const ARMSubtarget *ST = &MF.getTarget().getSubtarget<ARMSubtarget>();
+ bool Thumb = ST->isThumb();
+
+ // Sadly, this currently doesn't support varargs, platforms other than
+ // android/linux. Note that thumb1/thumb2 are support for android/linux.
+ if (MF.getFunction()->isVarArg())
+ report_fatal_error("Segmented stacks do not support vararg functions.");
+ if (!ST->isTargetAndroid() && !ST->isTargetLinux())
+ report_fatal_error("Segmented stacks not supported on this platform.");
+
+ MachineBasicBlock &prologueMBB = MF.front();
+ MachineFrameInfo *MFI = MF.getFrameInfo();
+ MachineModuleInfo &MMI = MF.getMMI();
+ MCContext &Context = MMI.getContext();
+ const MCRegisterInfo *MRI = Context.getRegisterInfo();
+ const ARMBaseInstrInfo &TII =
+ *static_cast<const ARMBaseInstrInfo *>(MF.getSubtarget().getInstrInfo());
+ ARMFunctionInfo *ARMFI = MF.getInfo<ARMFunctionInfo>();
+ DebugLoc DL;
+
+ uint64_t StackSize = MFI->getStackSize();
+
+ // Do not generate a prologue for functions with a stack of size zero
+ if (StackSize == 0)
+ return;
+
+ // Use R4 and R5 as scratch registers.
+ // We save R4 and R5 before use and restore them before leaving the function.
+ unsigned ScratchReg0 = ARM::R4;
+ unsigned ScratchReg1 = ARM::R5;
+ uint64_t AlignedStackSize;
+
+ MachineBasicBlock *PrevStackMBB = MF.CreateMachineBasicBlock();
+ MachineBasicBlock *PostStackMBB = MF.CreateMachineBasicBlock();
+ MachineBasicBlock *AllocMBB = MF.CreateMachineBasicBlock();
+ MachineBasicBlock *GetMBB = MF.CreateMachineBasicBlock();
+ MachineBasicBlock *McrMBB = MF.CreateMachineBasicBlock();
+
+ for (MachineBasicBlock::livein_iterator i = prologueMBB.livein_begin(),
+ e = prologueMBB.livein_end();
+ i != e; ++i) {
+ AllocMBB->addLiveIn(*i);
+ GetMBB->addLiveIn(*i);
+ McrMBB->addLiveIn(*i);
+ PrevStackMBB->addLiveIn(*i);
+ PostStackMBB->addLiveIn(*i);
+ }
+
+ MF.push_front(PostStackMBB);
+ MF.push_front(AllocMBB);
+ MF.push_front(GetMBB);
+ MF.push_front(McrMBB);
+ MF.push_front(PrevStackMBB);
+
+ // The required stack size that is aligned to ARM constant criterion.
+ AlignedStackSize = alignToARMConstant(StackSize);
+
+ // When the frame size is less than 256 we just compare the stack
+ // boundary directly to the value of the stack pointer, per gcc.
+ bool CompareStackPointer = AlignedStackSize < kSplitStackAvailable;
+
+ // We will use two of the callee save registers as scratch registers so we
+ // need to save those registers onto the stack.
+ // We will use SR0 to hold stack limit and SR1 to hold the stack size
+ // requested and arguments for __morestack().
+ // SR0: Scratch Register #0
+ // SR1: Scratch Register #1
+ // push {SR0, SR1}
+ if (Thumb) {
+ AddDefaultPred(BuildMI(PrevStackMBB, DL, TII.get(ARM::tPUSH)))
+ .addReg(ScratchReg0).addReg(ScratchReg1);
+ } else {
+ AddDefaultPred(BuildMI(PrevStackMBB, DL, TII.get(ARM::STMDB_UPD))
+ .addReg(ARM::SP, RegState::Define).addReg(ARM::SP))
+ .addReg(ScratchReg0).addReg(ScratchReg1);
+ }
+
+ // Emit the relevant DWARF information about the change in stack pointer as
+ // well as where to find both r4 and r5 (the callee-save registers)
+ CFIIndex =
+ MMI.addFrameInst(MCCFIInstruction::createDefCfaOffset(nullptr, -8));
+ BuildMI(PrevStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createOffset(
+ nullptr, MRI->getDwarfRegNum(ScratchReg1, true), -4));
+ BuildMI(PrevStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createOffset(
+ nullptr, MRI->getDwarfRegNum(ScratchReg0, true), -8));
+ BuildMI(PrevStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ // mov SR1, sp
+ if (Thumb) {
+ AddDefaultPred(BuildMI(McrMBB, DL, TII.get(ARM::tMOVr), ScratchReg1)
+ .addReg(ARM::SP));
+ } else if (CompareStackPointer) {
+ AddDefaultPred(BuildMI(McrMBB, DL, TII.get(ARM::MOVr), ScratchReg1)
+ .addReg(ARM::SP)).addReg(0);
+ }
+
+ // sub SR1, sp, #StackSize
+ if (!CompareStackPointer && Thumb) {
+ AddDefaultPred(
+ AddDefaultCC(BuildMI(McrMBB, DL, TII.get(ARM::tSUBi8), ScratchReg1))
+ .addReg(ScratchReg1).addImm(AlignedStackSize));
+ } else if (!CompareStackPointer) {
+ AddDefaultPred(BuildMI(McrMBB, DL, TII.get(ARM::SUBri), ScratchReg1)
+ .addReg(ARM::SP).addImm(AlignedStackSize)).addReg(0);
+ }
+
+ if (Thumb && ST->isThumb1Only()) {
+ unsigned PCLabelId = ARMFI->createPICLabelUId();
+ ARMConstantPoolValue *NewCPV = ARMConstantPoolSymbol::Create(
+ MF.getFunction()->getContext(), "__STACK_LIMIT", PCLabelId, 0);
+ MachineConstantPool *MCP = MF.getConstantPool();
+ unsigned CPI = MCP->getConstantPoolIndex(NewCPV, MF.getAlignment());
+
+ // ldr SR0, [pc, offset(STACK_LIMIT)]
+ AddDefaultPred(BuildMI(GetMBB, DL, TII.get(ARM::tLDRpci), ScratchReg0)
+ .addConstantPoolIndex(CPI));
+
+ // ldr SR0, [SR0]
+ AddDefaultPred(BuildMI(GetMBB, DL, TII.get(ARM::tLDRi), ScratchReg0)
+ .addReg(ScratchReg0).addImm(0));
+ } else {
+ // Get TLS base address from the coprocessor
+ // mrc p15, #0, SR0, c13, c0, #3
+ AddDefaultPred(BuildMI(McrMBB, DL, TII.get(ARM::MRC), ScratchReg0)
+ .addImm(15)
+ .addImm(0)
+ .addImm(13)
+ .addImm(0)
+ .addImm(3));
+
+ // Use the last tls slot on android and a private field of the TCP on linux.
+ assert(ST->isTargetAndroid() || ST->isTargetLinux());
+ unsigned TlsOffset = ST->isTargetAndroid() ? 63 : 1;
+
+ // Get the stack limit from the right offset
+ // ldr SR0, [sr0, #4 * TlsOffset]
+ AddDefaultPred(BuildMI(GetMBB, DL, TII.get(ARM::LDRi12), ScratchReg0)
+ .addReg(ScratchReg0).addImm(4 * TlsOffset));
+ }
+
+ // Compare stack limit with stack size requested.
+ // cmp SR0, SR1
+ Opcode = Thumb ? ARM::tCMPr : ARM::CMPrr;
+ AddDefaultPred(BuildMI(GetMBB, DL, TII.get(Opcode))
+ .addReg(ScratchReg0)
+ .addReg(ScratchReg1));
+
+ // This jump is taken if StackLimit < SP - stack required.
+ Opcode = Thumb ? ARM::tBcc : ARM::Bcc;
+ BuildMI(GetMBB, DL, TII.get(Opcode)).addMBB(PostStackMBB)
+ .addImm(ARMCC::LO)
+ .addReg(ARM::CPSR);
+
+
+ // Calling __morestack(StackSize, Size of stack arguments).
+ // __morestack knows that the stack size requested is in SR0(r4)
+ // and amount size of stack arguments is in SR1(r5).
+
+ // Pass first argument for the __morestack by Scratch Register #0.
+ // The amount size of stack required
+ if (Thumb) {
+ AddDefaultPred(AddDefaultCC(BuildMI(AllocMBB, DL, TII.get(ARM::tMOVi8),
+ ScratchReg0)).addImm(AlignedStackSize));
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::MOVi), ScratchReg0)
+ .addImm(AlignedStackSize)).addReg(0);
+ }
+ // Pass second argument for the __morestack by Scratch Register #1.
+ // The amount size of stack consumed to save function arguments.
+ if (Thumb) {
+ AddDefaultPred(
+ AddDefaultCC(BuildMI(AllocMBB, DL, TII.get(ARM::tMOVi8), ScratchReg1))
+ .addImm(alignToARMConstant(ARMFI->getArgumentStackSize())));
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::MOVi), ScratchReg1)
+ .addImm(alignToARMConstant(ARMFI->getArgumentStackSize())))
+ .addReg(0);
+ }
+
+ // push {lr} - Save return address of this function.
+ if (Thumb) {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::tPUSH)))
+ .addReg(ARM::LR);
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::STMDB_UPD))
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::SP))
+ .addReg(ARM::LR);
+ }
+
+ // Emit the DWARF info about the change in stack as well as where to find the
+ // previous link register
+ CFIIndex =
+ MMI.addFrameInst(MCCFIInstruction::createDefCfaOffset(nullptr, -12));
+ BuildMI(AllocMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createOffset(
+ nullptr, MRI->getDwarfRegNum(ARM::LR, true), -12));
+ BuildMI(AllocMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ // Call __morestack().
+ if (Thumb) {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::tBL)))
+ .addExternalSymbol("__morestack");
+ } else {
+ BuildMI(AllocMBB, DL, TII.get(ARM::BL))
+ .addExternalSymbol("__morestack");
+ }
+
+ // pop {lr} - Restore return address of this original function.
+ if (Thumb) {
+ if (ST->isThumb1Only()) {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::tPOP)))
+ .addReg(ScratchReg0);
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::tMOVr), ARM::LR)
+ .addReg(ScratchReg0));
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::t2LDR_POST))
+ .addReg(ARM::LR, RegState::Define)
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::SP)
+ .addImm(4));
+ }
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::LDMIA_UPD))
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::SP))
+ .addReg(ARM::LR);
+ }
+
+ // Restore SR0 and SR1 in case of __morestack() was called.
+ // __morestack() will skip PostStackMBB block so we need to restore
+ // scratch registers from here.
+ // pop {SR0, SR1}
+ if (Thumb) {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::tPOP)))
+ .addReg(ScratchReg0)
+ .addReg(ScratchReg1);
+ } else {
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(ARM::LDMIA_UPD))
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::SP))
+ .addReg(ScratchReg0)
+ .addReg(ScratchReg1);
+ }
+
+ // Update the CFA offset now that we've popped
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createDefCfaOffset(nullptr, 0));
+ BuildMI(AllocMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ // bx lr - Return from this function.
+ Opcode = Thumb ? ARM::tBX_RET : ARM::BX_RET;
+ AddDefaultPred(BuildMI(AllocMBB, DL, TII.get(Opcode)));
+
+ // Restore SR0 and SR1 in case of __morestack() was not called.
+ // pop {SR0, SR1}
+ if (Thumb) {
+ AddDefaultPred(BuildMI(PostStackMBB, DL, TII.get(ARM::tPOP)))
+ .addReg(ScratchReg0)
+ .addReg(ScratchReg1);
+ } else {
+ AddDefaultPred(BuildMI(PostStackMBB, DL, TII.get(ARM::LDMIA_UPD))
+ .addReg(ARM::SP, RegState::Define)
+ .addReg(ARM::SP))
+ .addReg(ScratchReg0)
+ .addReg(ScratchReg1);
+ }
+
+ // Update the CFA offset now that we've popped
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createDefCfaOffset(nullptr, 0));
+ BuildMI(PostStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ // Tell debuggers that r4 and r5 are now the same as they were in the
+ // previous function, that they're the "Same Value".
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createSameValue(
+ nullptr, MRI->getDwarfRegNum(ScratchReg0, true)));
+ BuildMI(PostStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+ CFIIndex = MMI.addFrameInst(MCCFIInstruction::createSameValue(
+ nullptr, MRI->getDwarfRegNum(ScratchReg1, true)));
+ BuildMI(PostStackMBB, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
+
+ // Organizing MBB lists
+ PostStackMBB->addSuccessor(&prologueMBB);
+
+ AllocMBB->addSuccessor(PostStackMBB);
+
+ GetMBB->addSuccessor(PostStackMBB);
+ GetMBB->addSuccessor(AllocMBB);
+
+ McrMBB->addSuccessor(GetMBB);
+
+ PrevStackMBB->addSuccessor(McrMBB);
+
+#ifdef XDEBUG
+ MF.verify();
+#endif
+}
projects / oota-llvm.git / blobdiff