#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/WinEHFuncInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCSymbol.h"
-#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Support/Debug.h"
#include <cstdlib>
using namespace llvm;
-// FIXME: completely move here.
-extern cl::opt<bool> ForceStackAlign;
+X86FrameLowering::X86FrameLowering(const X86Subtarget &STI,
+ unsigned StackAlignOverride)
+ : TargetFrameLowering(StackGrowsDown, StackAlignOverride,
+ STI.is64Bit() ? -8 : -4),
+ STI(STI), TII(*STI.getInstrInfo()), TRI(STI.getRegisterInfo()) {
+ // Cache a bunch of frame-related predicates for this subtarget.
+ SlotSize = TRI->getSlotSize();
+ Is64Bit = STI.is64Bit();
+ IsLP64 = STI.isTarget64BitLP64();
+ // standard x86_64 and NaCl use 64-bit frame/stack pointers, x32 - 32-bit.
+ Uses64BitFramePtr = STI.isTarget64BitLP64() || STI.isTargetNaCl64();
+ StackPtr = TRI->getStackRegister();
+}
bool X86FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const {
- return !MF.getFrameInfo()->hasVarSizedObjects();
+ return !MF.getFrameInfo()->hasVarSizedObjects() &&
+ !MF.getInfo<X86MachineFunctionInfo>()->getHasPushSequences();
+}
+
+/// canSimplifyCallFramePseudos - If there is a reserved call frame, the
+/// call frame pseudos can be simplified. Having a FP, as in the default
+/// implementation, is not sufficient here since we can't always use it.
+/// Use a more nuanced condition.
+bool
+X86FrameLowering::canSimplifyCallFramePseudos(const MachineFunction &MF) const {
+ return hasReservedCallFrame(MF) ||
+ (hasFP(MF) && !TRI->needsStackRealignment(MF)) ||
+ TRI->hasBasePointer(MF);
+}
+
+// needsFrameIndexResolution - Do we need to perform FI resolution for
+// this function. Normally, this is required only when the function
+// has any stack objects. However, FI resolution actually has another job,
+// not apparent from the title - it resolves callframesetup/destroy
+// that were not simplified earlier.
+// So, this is required for x86 functions that have push sequences even
+// when there are no stack objects.
+bool
+X86FrameLowering::needsFrameIndexResolution(const MachineFunction &MF) const {
+ return MF.getFrameInfo()->hasStackObjects() ||
+ MF.getInfo<X86MachineFunctionInfo>()->getHasPushSequences();
}
/// hasFP - Return true if the specified function should have a dedicated frame
bool X86FrameLowering::hasFP(const MachineFunction &MF) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
const MachineModuleInfo &MMI = MF.getMMI();
- const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
return (MF.getTarget().Options.DisableFramePointerElim(MF) ||
- RegInfo->needsStackRealignment(MF) ||
+ TRI->needsStackRealignment(MF) ||
MFI->hasVarSizedObjects() ||
- MFI->isFrameAddressTaken() || MFI->hasInlineAsmWithSPAdjust() ||
+ MFI->isFrameAddressTaken() || MFI->hasOpaqueSPAdjustment() ||
MF.getInfo<X86MachineFunctionInfo>()->getForceFramePointer() ||
- MMI.callsUnwindInit() || MMI.callsEHReturn() ||
+ MMI.callsUnwindInit() || MMI.hasEHFunclets() || MMI.callsEHReturn() ||
MFI->hasStackMap() || MFI->hasPatchPoint());
}
}
}
+static unsigned getSUBrrOpcode(unsigned isLP64) {
+ return isLP64 ? X86::SUB64rr : X86::SUB32rr;
+}
+
+static unsigned getADDrrOpcode(unsigned isLP64) {
+ return isLP64 ? X86::ADD64rr : X86::ADD32rr;
+}
+
static unsigned getANDriOpcode(bool IsLP64, int64_t Imm) {
if (IsLP64) {
if (isInt<8>(Imm))
return X86::AND32ri;
}
-static unsigned getPUSHiOpcode(bool IsLP64, MachineOperand MO) {
- // We don't support LP64 for now.
- assert(!IsLP64);
-
- if (MO.isImm() && isInt<8>(MO.getImm()))
- return X86::PUSH32i8;
-
- return X86::PUSHi32;;
-}
-
static unsigned getLEArOpcode(unsigned IsLP64) {
return IsLP64 ? X86::LEA64r : X86::LEA32r;
}
/// to this register without worry about clobbering it.
static unsigned findDeadCallerSavedReg(MachineBasicBlock &MBB,
MachineBasicBlock::iterator &MBBI,
- const TargetRegisterInfo &TRI,
+ const TargetRegisterInfo *TRI,
bool Is64Bit) {
const MachineFunction *MF = MBB.getParent();
const Function *F = MF->getFunction();
unsigned Reg = MO.getReg();
if (!Reg)
continue;
- for (MCRegAliasIterator AI(Reg, &TRI, true); AI.isValid(); ++AI)
+ for (MCRegAliasIterator AI(Reg, TRI, true); AI.isValid(); ++AI)
Uses.insert(*AI);
}
return 0;
}
+static bool isEAXLiveIn(MachineFunction &MF) {
+ for (MachineRegisterInfo::livein_iterator II = MF.getRegInfo().livein_begin(),
+ EE = MF.getRegInfo().livein_end(); II != EE; ++II) {
+ unsigned Reg = II->first;
+
+ if (Reg == X86::RAX || Reg == X86::EAX || Reg == X86::AX ||
+ Reg == X86::AH || Reg == X86::AL)
+ return true;
+ }
+
+ return false;
+}
+
+/// Check whether or not the terminators of \p MBB needs to read EFLAGS.
+static bool terminatorsNeedFlagsAsInput(const MachineBasicBlock &MBB) {
+ for (const MachineInstr &MI : MBB.terminators()) {
+ bool BreakNext = false;
+ for (const MachineOperand &MO : MI.operands()) {
+ if (!MO.isReg())
+ continue;
+ unsigned Reg = MO.getReg();
+ if (Reg != X86::EFLAGS)
+ continue;
+
+ // This terminator needs an eflag that is not defined
+ // by a previous terminator.
+ if (!MO.isDef())
+ return true;
+ BreakNext = true;
+ }
+ if (BreakNext)
+ break;
+ }
+ return false;
+}
/// emitSPUpdate - Emit a series of instructions to increment / decrement the
/// stack pointer by a constant value.
-static
-void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
- unsigned StackPtr, int64_t NumBytes,
- bool Is64BitTarget, bool Is64BitStackPtr, bool UseLEA,
- const TargetInstrInfo &TII, const TargetRegisterInfo &TRI) {
+void X86FrameLowering::emitSPUpdate(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator &MBBI,
+ int64_t NumBytes, bool InEpilogue) const {
bool isSub = NumBytes < 0;
uint64_t Offset = isSub ? -NumBytes : NumBytes;
- unsigned Opc;
- if (UseLEA)
- Opc = getLEArOpcode(Is64BitStackPtr);
- else
- Opc = isSub
- ? getSUBriOpcode(Is64BitStackPtr, Offset)
- : getADDriOpcode(Is64BitStackPtr, Offset);
uint64_t Chunk = (1LL << 31) - 1;
DebugLoc DL = MBB.findDebugLoc(MBBI);
while (Offset) {
- uint64_t ThisVal = (Offset > Chunk) ? Chunk : Offset;
- if (ThisVal == (Is64BitTarget ? 8 : 4)) {
+ if (Offset > Chunk) {
+ // Rather than emit a long series of instructions for large offsets,
+ // load the offset into a register and do one sub/add
+ unsigned Reg = 0;
+
+ if (isSub && !isEAXLiveIn(*MBB.getParent()))
+ Reg = (unsigned)(Is64Bit ? X86::RAX : X86::EAX);
+ else
+ Reg = findDeadCallerSavedReg(MBB, MBBI, TRI, Is64Bit);
+
+ if (Reg) {
+ unsigned Opc = Is64Bit ? X86::MOV64ri : X86::MOV32ri;
+ BuildMI(MBB, MBBI, DL, TII.get(Opc), Reg)
+ .addImm(Offset);
+ Opc = isSub
+ ? getSUBrrOpcode(Is64Bit)
+ : getADDrrOpcode(Is64Bit);
+ MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
+ .addReg(StackPtr)
+ .addReg(Reg);
+ MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
+ Offset = 0;
+ continue;
+ }
+ }
+
+ uint64_t ThisVal = std::min(Offset, Chunk);
+ if (ThisVal == (Is64Bit ? 8 : 4)) {
// Use push / pop instead.
unsigned Reg = isSub
- ? (unsigned)(Is64BitTarget ? X86::RAX : X86::EAX)
- : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64BitTarget);
+ ? (unsigned)(Is64Bit ? X86::RAX : X86::EAX)
+ : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64Bit);
if (Reg) {
- Opc = isSub
- ? (Is64BitTarget ? X86::PUSH64r : X86::PUSH32r)
- : (Is64BitTarget ? X86::POP64r : X86::POP32r);
+ unsigned Opc = isSub
+ ? (Is64Bit ? X86::PUSH64r : X86::PUSH32r)
+ : (Is64Bit ? X86::POP64r : X86::POP32r);
MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc))
.addReg(Reg, getDefRegState(!isSub) | getUndefRegState(isSub));
if (isSub)
MI->setFlag(MachineInstr::FrameSetup);
+ else
+ MI->setFlag(MachineInstr::FrameDestroy);
Offset -= ThisVal;
continue;
}
}
- MachineInstr *MI = nullptr;
-
- if (UseLEA) {
- MI = addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr),
- StackPtr, false, isSub ? -ThisVal : ThisVal);
- } else {
- MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
- .addReg(StackPtr)
- .addImm(ThisVal);
- MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
- }
-
+ MachineInstrBuilder MI = BuildStackAdjustment(
+ MBB, MBBI, DL, isSub ? -ThisVal : ThisVal, InEpilogue);
if (isSub)
- MI->setFlag(MachineInstr::FrameSetup);
+ MI.setMIFlag(MachineInstr::FrameSetup);
+ else
+ MI.setMIFlag(MachineInstr::FrameDestroy);
Offset -= ThisVal;
}
}
-/// mergeSPUpdatesUp - Merge two stack-manipulating instructions upper iterator.
-static
-void mergeSPUpdatesUp(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
- unsigned StackPtr, uint64_t *NumBytes = nullptr) {
- if (MBBI == MBB.begin()) return;
+MachineInstrBuilder X86FrameLowering::BuildStackAdjustment(
+ MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI, DebugLoc DL,
+ int64_t Offset, bool InEpilogue) const {
+ assert(Offset != 0 && "zero offset stack adjustment requested");
- MachineBasicBlock::iterator PI = std::prev(MBBI);
- unsigned Opc = PI->getOpcode();
- if ((Opc == X86::ADD64ri32 || Opc == X86::ADD64ri8 ||
- Opc == X86::ADD32ri || Opc == X86::ADD32ri8 ||
- Opc == X86::LEA32r || Opc == X86::LEA64_32r) &&
- PI->getOperand(0).getReg() == StackPtr) {
- if (NumBytes)
- *NumBytes += PI->getOperand(2).getImm();
- MBB.erase(PI);
- } else if ((Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
- Opc == X86::SUB32ri || Opc == X86::SUB32ri8) &&
- PI->getOperand(0).getReg() == StackPtr) {
- if (NumBytes)
- *NumBytes -= PI->getOperand(2).getImm();
- MBB.erase(PI);
+ // On Atom, using LEA to adjust SP is preferred, but using it in the epilogue
+ // is tricky.
+ bool UseLEA;
+ if (!InEpilogue) {
+ UseLEA = STI.useLeaForSP();
+ } else {
+ // If we can use LEA for SP but we shouldn't, check that none
+ // of the terminators uses the eflags. Otherwise we will insert
+ // a ADD that will redefine the eflags and break the condition.
+ // Alternatively, we could move the ADD, but this may not be possible
+ // and is an optimization anyway.
+ UseLEA = canUseLEAForSPInEpilogue(*MBB.getParent());
+ if (UseLEA && !STI.useLeaForSP())
+ UseLEA = terminatorsNeedFlagsAsInput(MBB);
+ // If that assert breaks, that means we do not do the right thing
+ // in canUseAsEpilogue.
+ assert((UseLEA || !terminatorsNeedFlagsAsInput(MBB)) &&
+ "We shouldn't have allowed this insertion point");
}
-}
-
-/// mergeSPUpdatesDown - Merge two stack-manipulating instructions lower
-/// iterator.
-static
-void mergeSPUpdatesDown(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator &MBBI,
- unsigned StackPtr, uint64_t *NumBytes = nullptr) {
- // FIXME: THIS ISN'T RUN!!!
- return;
- if (MBBI == MBB.end()) return;
-
- MachineBasicBlock::iterator NI = std::next(MBBI);
- if (NI == MBB.end()) return;
-
- unsigned Opc = NI->getOpcode();
- if ((Opc == X86::ADD64ri32 || Opc == X86::ADD64ri8 ||
- Opc == X86::ADD32ri || Opc == X86::ADD32ri8) &&
- NI->getOperand(0).getReg() == StackPtr) {
- if (NumBytes)
- *NumBytes -= NI->getOperand(2).getImm();
- MBB.erase(NI);
- MBBI = NI;
- } else if ((Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
- Opc == X86::SUB32ri || Opc == X86::SUB32ri8) &&
- NI->getOperand(0).getReg() == StackPtr) {
- if (NumBytes)
- *NumBytes += NI->getOperand(2).getImm();
- MBB.erase(NI);
- MBBI = NI;
+ MachineInstrBuilder MI;
+ if (UseLEA) {
+ MI = addRegOffset(BuildMI(MBB, MBBI, DL,
+ TII.get(getLEArOpcode(Uses64BitFramePtr)),
+ StackPtr),
+ StackPtr, false, Offset);
+ } else {
+ bool IsSub = Offset < 0;
+ uint64_t AbsOffset = IsSub ? -Offset : Offset;
+ unsigned Opc = IsSub ? getSUBriOpcode(Uses64BitFramePtr, AbsOffset)
+ : getADDriOpcode(Uses64BitFramePtr, AbsOffset);
+ MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
+ .addReg(StackPtr)
+ .addImm(AbsOffset);
+ MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
}
+ return MI;
}
-/// mergeSPUpdates - Checks the instruction before/after the passed
-/// instruction. If it is an ADD/SUB/LEA instruction it is deleted argument and
-/// the stack adjustment is returned as a positive value for ADD/LEA and a
-/// negative for SUB.
-static int mergeSPUpdates(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator &MBBI, unsigned StackPtr,
- bool doMergeWithPrevious) {
+int X86FrameLowering::mergeSPUpdates(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator &MBBI,
+ bool doMergeWithPrevious) const {
if ((doMergeWithPrevious && MBBI == MBB.begin()) ||
(!doMergeWithPrevious && MBBI == MBB.end()))
return 0;
return Offset;
}
-static bool isEAXLiveIn(MachineFunction &MF) {
- for (MachineRegisterInfo::livein_iterator II = MF.getRegInfo().livein_begin(),
- EE = MF.getRegInfo().livein_end(); II != EE; ++II) {
- unsigned Reg = II->first;
-
- if (Reg == X86::EAX || Reg == X86::AX ||
- Reg == X86::AH || Reg == X86::AL)
- return true;
- }
-
- return false;
+void X86FrameLowering::BuildCFI(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI, DebugLoc DL,
+ MCCFIInstruction CFIInst) const {
+ MachineFunction &MF = *MBB.getParent();
+ unsigned CFIIndex = MF.getMMI().addFrameInst(CFIInst);
+ BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex);
}
void
MachineFrameInfo *MFI = MF.getFrameInfo();
MachineModuleInfo &MMI = MF.getMMI();
const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo();
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
// Add callee saved registers to move list.
const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
unsigned Reg = I->getReg();
unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
- unsigned CFIIndex =
- MMI.addFrameInst(MCCFIInstruction::createOffset(nullptr, DwarfReg,
- Offset));
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ BuildCFI(MBB, MBBI, DL,
+ MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
}
}
return false;
}
-void X86FrameLowering::getStackProbeFunction(const X86Subtarget &STI,
- unsigned &CallOp,
- const char *&Symbol) {
- CallOp = STI.is64Bit() ? X86::W64ALLOCA : X86::CALLpcrel32;
+void X86FrameLowering::emitStackProbeCall(MachineFunction &MF,
+ MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI,
+ DebugLoc DL) const {
+ bool IsLargeCodeModel = MF.getTarget().getCodeModel() == CodeModel::Large;
+
+ unsigned CallOp;
+ if (Is64Bit)
+ CallOp = IsLargeCodeModel ? X86::CALL64r : X86::CALL64pcrel32;
+ else
+ CallOp = X86::CALLpcrel32;
- if (STI.is64Bit()) {
+ const char *Symbol;
+ if (Is64Bit) {
if (STI.isTargetCygMing()) {
Symbol = "___chkstk_ms";
} else {
Symbol = "_alloca";
else
Symbol = "_chkstk";
+
+ MachineInstrBuilder CI;
+
+ // All current stack probes take AX and SP as input, clobber flags, and
+ // preserve all registers. x86_64 probes leave RSP unmodified.
+ if (Is64Bit && MF.getTarget().getCodeModel() == CodeModel::Large) {
+ // For the large code model, we have to call through a register. Use R11,
+ // as it is scratch in all supported calling conventions.
+ BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::R11)
+ .addExternalSymbol(Symbol);
+ CI = BuildMI(MBB, MBBI, DL, TII.get(CallOp)).addReg(X86::R11);
+ } else {
+ CI = BuildMI(MBB, MBBI, DL, TII.get(CallOp)).addExternalSymbol(Symbol);
+ }
+
+ unsigned AX = Is64Bit ? X86::RAX : X86::EAX;
+ unsigned SP = Is64Bit ? X86::RSP : X86::ESP;
+ CI.addReg(AX, RegState::Implicit)
+ .addReg(SP, RegState::Implicit)
+ .addReg(AX, RegState::Define | RegState::Implicit)
+ .addReg(SP, RegState::Define | RegState::Implicit)
+ .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit);
+
+ if (Is64Bit) {
+ // MSVC x64's __chkstk and cygwin/mingw's ___chkstk_ms do not adjust %rsp
+ // themselves. It also does not clobber %rax so we can reuse it when
+ // adjusting %rsp.
+ BuildMI(MBB, MBBI, DL, TII.get(X86::SUB64rr), X86::RSP)
+ .addReg(X86::RSP)
+ .addReg(X86::RAX);
+ }
+}
+
+static unsigned calculateSetFPREG(uint64_t SPAdjust) {
+ // Win64 ABI has a less restrictive limitation of 240; 128 works equally well
+ // and might require smaller successive adjustments.
+ const uint64_t Win64MaxSEHOffset = 128;
+ uint64_t SEHFrameOffset = std::min(SPAdjust, Win64MaxSEHOffset);
+ // Win64 ABI requires 16-byte alignment for the UWOP_SET_FPREG opcode.
+ return SEHFrameOffset & -16;
+}
+
+// If we're forcing a stack realignment we can't rely on just the frame
+// info, we need to know the ABI stack alignment as well in case we
+// have a call out. Otherwise just make sure we have some alignment - we'll
+// go with the minimum SlotSize.
+uint64_t X86FrameLowering::calculateMaxStackAlign(const MachineFunction &MF) const {
+ const MachineFrameInfo *MFI = MF.getFrameInfo();
+ uint64_t MaxAlign = MFI->getMaxAlignment(); // Desired stack alignment.
+ unsigned StackAlign = getStackAlignment();
+ if (MF.getFunction()->hasFnAttribute("stackrealign")) {
+ if (MFI->hasCalls())
+ MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
+ else if (MaxAlign < SlotSize)
+ MaxAlign = SlotSize;
+ }
+ return MaxAlign;
+}
+
+void X86FrameLowering::BuildStackAlignAND(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI,
+ DebugLoc DL,
+ uint64_t MaxAlign) const {
+ uint64_t Val = -MaxAlign;
+ MachineInstr *MI =
+ BuildMI(MBB, MBBI, DL, TII.get(getANDriOpcode(Uses64BitFramePtr, Val)),
+ StackPtr)
+ .addReg(StackPtr)
+ .addImm(Val)
+ .setMIFlag(MachineInstr::FrameSetup);
+
+ // The EFLAGS implicit def is dead.
+ MI->getOperand(3).setIsDead();
}
/// emitPrologue - Push callee-saved registers onto the stack, which
- for 32-bit code, substitute %e?? registers for %r??
*/
-void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
- MachineBasicBlock &MBB = MF.front(); // Prologue goes in entry BB.
+void X86FrameLowering::emitPrologue(MachineFunction &MF,
+ MachineBasicBlock &MBB) const {
+ assert(&STI == &MF.getSubtarget<X86Subtarget>() &&
+ "MF used frame lowering for wrong subtarget");
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineFrameInfo *MFI = MF.getFrameInfo();
const Function *Fn = MF.getFunction();
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
MachineModuleInfo &MMI = MF.getMMI();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
- uint64_t MaxAlign = MFI->getMaxAlignment(); // Desired stack alignment.
+ uint64_t MaxAlign = calculateMaxStackAlign(MF); // Desired stack alignment.
uint64_t StackSize = MFI->getStackSize(); // Number of bytes to allocate.
bool HasFP = hasFP(MF);
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
- bool Is64Bit = STI.is64Bit();
- // standard x86_64 and NaCl use 64-bit frame/stack pointers, x32 - 32-bit.
- const bool Uses64BitFramePtr = STI.isTarget64BitLP64() || STI.isTargetNaCl64();
- bool IsWin64 = STI.isTargetWin64();
- // Not necessarily synonymous with IsWin64.
- bool IsWinEH = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
- bool NeedsWinEH = IsWinEH && Fn->needsUnwindTableEntry();
+ bool IsWin64CC = STI.isCallingConvWin64(Fn->getCallingConv());
+ bool IsWin64Prologue = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
+ bool NeedsWinCFI = IsWin64Prologue && Fn->needsUnwindTableEntry();
bool NeedsDwarfCFI =
- !IsWinEH && (MMI.hasDebugInfo() || Fn->needsUnwindTableEntry());
- bool UseLEA = STI.useLeaForSP();
- unsigned StackAlign = getStackAlignment();
- unsigned SlotSize = RegInfo->getSlotSize();
- unsigned FramePtr = RegInfo->getFrameRegister(MF);
- const unsigned MachineFramePtr = STI.isTarget64BitILP32() ?
- getX86SubSuperRegister(FramePtr, MVT::i64, false) : FramePtr;
- unsigned StackPtr = RegInfo->getStackRegister();
- unsigned BasePtr = RegInfo->getBaseRegister();
+ !IsWin64Prologue && (MMI.hasDebugInfo() || Fn->needsUnwindTableEntry());
+ unsigned FramePtr = TRI->getFrameRegister(MF);
+ const unsigned MachineFramePtr =
+ STI.isTarget64BitILP32()
+ ? getX86SubSuperRegister(FramePtr, MVT::i64, false)
+ : FramePtr;
+ unsigned BasePtr = TRI->getBaseRegister();
DebugLoc DL;
- // If we're forcing a stack realignment we can't rely on just the frame
- // info, we need to know the ABI stack alignment as well in case we
- // have a call out. Otherwise just make sure we have some alignment - we'll
- // go with the minimum SlotSize.
- if (ForceStackAlign) {
- if (MFI->hasCalls())
- MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
- else if (MaxAlign < SlotSize)
- MaxAlign = SlotSize;
- }
-
// Add RETADDR move area to callee saved frame size.
int TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
+ if (TailCallReturnAddrDelta && IsWin64Prologue)
+ report_fatal_error("Can't handle guaranteed tail call under win64 yet");
+
if (TailCallReturnAddrDelta < 0)
X86FI->setCalleeSavedFrameSize(
X86FI->getCalleeSavedFrameSize() - TailCallReturnAddrDelta);
bool UseStackProbe = (STI.isOSWindows() && !STI.isTargetMachO());
+ // The default stack probe size is 4096 if the function has no stackprobesize
+ // attribute.
+ unsigned StackProbeSize = 4096;
+ if (Fn->hasFnAttribute("stack-probe-size"))
+ Fn->getFnAttribute("stack-probe-size")
+ .getValueAsString()
+ .getAsInteger(0, StackProbeSize);
+
// If this is x86-64 and the Red Zone is not disabled, if we are a leaf
// function, and use up to 128 bytes of stack space, don't have a frame
// pointer, calls, or dynamic alloca then we do not need to adjust the
// stack pointer (we fit in the Red Zone). We also check that we don't
// push and pop from the stack.
- if (Is64Bit && !Fn->getAttributes().hasAttribute(AttributeSet::FunctionIndex,
- Attribute::NoRedZone) &&
- !RegInfo->needsStackRealignment(MF) &&
- !MFI->hasVarSizedObjects() && // No dynamic alloca.
- !MFI->adjustsStack() && // No calls.
- !IsWin64 && // Win64 has no Red Zone
- !usesTheStack(MF) && // Don't push and pop.
- !MF.shouldSplitStack()) { // Regular stack
+ if (Is64Bit && !Fn->hasFnAttribute(Attribute::NoRedZone) &&
+ !TRI->needsStackRealignment(MF) &&
+ !MFI->hasVarSizedObjects() && // No dynamic alloca.
+ !MFI->adjustsStack() && // No calls.
+ !IsWin64CC && // Win64 has no Red Zone
+ !usesTheStack(MF) && // Don't push and pop.
+ !MF.shouldSplitStack()) { // Regular stack
uint64_t MinSize = X86FI->getCalleeSavedFrameSize();
if (HasFP) MinSize += SlotSize;
StackSize = std::max(MinSize, StackSize > 128 ? StackSize - 128 : 0);
// applies to tail call optimized functions where the callee argument stack
// size is bigger than the callers.
if (TailCallReturnAddrDelta < 0) {
- MachineInstr *MI =
- BuildMI(MBB, MBBI, DL,
- TII.get(getSUBriOpcode(Uses64BitFramePtr, -TailCallReturnAddrDelta)),
- StackPtr)
- .addReg(StackPtr)
- .addImm(-TailCallReturnAddrDelta)
+ BuildStackAdjustment(MBB, MBBI, DL, TailCallReturnAddrDelta,
+ /*InEpilogue=*/false)
.setMIFlag(MachineInstr::FrameSetup);
- MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
}
// Mapping for machine moves:
uint64_t NumBytes = 0;
int stackGrowth = -SlotSize;
- if (HasFP) {
+ if (MBB.isEHFuncletEntry()) {
+ assert(STI.isOSWindows() && "funclets only supported on Windows");
+
+ // Set up the FramePtr and BasePtr physical registers using the address
+ // passed as EBP or RDX by the MSVC EH runtime.
+ if (STI.is32Bit()) {
+ // PUSH32r %ebp
+ BuildMI(MBB, MBBI, DL, TII.get(X86::PUSH32r))
+ .addReg(MachineFramePtr, RegState::Kill)
+ .setMIFlag(MachineInstr::FrameSetup);
+ // Reset EBP / ESI to something good.
+ MBBI = restoreWin32EHFrameAndBasePtr(MBB, MBBI, DL);
+ } else {
+ // FIXME: Add SEH directives.
+ NeedsWinCFI = false;
+ // Immediately spill RDX into the home slot. The runtime cares about this.
+ unsigned RDX = Uses64BitFramePtr ? X86::RDX : X86::EDX;
+ // MOV64mr %rdx, 16(%rsp)
+ unsigned MOVmr = Uses64BitFramePtr ? X86::MOV64mr : X86::MOV32mr;
+ addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(MOVmr)),
+ StackPtr, true, 16)
+ .addReg(RDX)
+ .setMIFlag(MachineInstr::FrameSetup);
+ // PUSH64r %rbp
+ BuildMI(MBB, MBBI, DL, TII.get(X86::PUSH64r))
+ .addReg(MachineFramePtr, RegState::Kill)
+ .setMIFlag(MachineInstr::FrameSetup);
+ // MOV64rr %rdx, %rbp
+ unsigned MOVrr = Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr;
+ BuildMI(MBB, MBBI, DL, TII.get(MOVrr), FramePtr)
+ .addReg(RDX)
+ .setMIFlag(MachineInstr::FrameSetup);
+ assert(!TRI->hasBasePointer(MF) &&
+ "x64 funclets with base ptrs not yet implemented");
+ }
+
+ // For EH funclets, only allocate enough space for outgoing calls.
+ NumBytes = MFI->getMaxCallFrameSize();
+ } else if (HasFP) {
// Calculate required stack adjustment.
uint64_t FrameSize = StackSize - SlotSize;
// If required, include space for extra hidden slot for stashing base pointer.
if (X86FI->getRestoreBasePointer())
FrameSize += SlotSize;
- if (RegInfo->needsStackRealignment(MF)) {
- // Callee-saved registers are pushed on stack before the stack
- // is realigned.
- FrameSize -= X86FI->getCalleeSavedFrameSize();
- NumBytes = (FrameSize + MaxAlign - 1) / MaxAlign * MaxAlign;
- } else {
- NumBytes = FrameSize - X86FI->getCalleeSavedFrameSize();
- }
+
+ NumBytes = FrameSize - X86FI->getCalleeSavedFrameSize();
+
+ // Callee-saved registers are pushed on stack before the stack is realigned.
+ if (TRI->needsStackRealignment(MF) && !IsWin64Prologue)
+ NumBytes = RoundUpToAlignment(NumBytes, MaxAlign);
// Get the offset of the stack slot for the EBP register, which is
// guaranteed to be the last slot by processFunctionBeforeFrameFinalized.
// Mark the place where EBP/RBP was saved.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
- unsigned CFIIndex = MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(nullptr, 2 * stackGrowth));
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ BuildCFI(MBB, MBBI, DL,
+ MCCFIInstruction::createDefCfaOffset(nullptr, 2 * stackGrowth));
// Change the rule for the FramePtr to be an "offset" rule.
- unsigned DwarfFramePtr = RegInfo->getDwarfRegNum(MachineFramePtr, true);
- CFIIndex = MMI.addFrameInst(
- MCCFIInstruction::createOffset(nullptr,
- DwarfFramePtr, 2 * stackGrowth));
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ unsigned DwarfFramePtr = TRI->getDwarfRegNum(MachineFramePtr, true);
+ BuildCFI(MBB, MBBI, DL, MCCFIInstruction::createOffset(
+ nullptr, DwarfFramePtr, 2 * stackGrowth));
}
- if (NeedsWinEH) {
+ if (NeedsWinCFI) {
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_PushReg))
.addImm(FramePtr)
.setMIFlag(MachineInstr::FrameSetup);
}
- // Update EBP with the new base value.
- BuildMI(MBB, MBBI, DL,
- TII.get(Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr), FramePtr)
- .addReg(StackPtr)
- .setMIFlag(MachineInstr::FrameSetup);
+ if (!IsWin64Prologue) {
+ // Update EBP with the new base value.
+ BuildMI(MBB, MBBI, DL,
+ TII.get(Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr),
+ FramePtr)
+ .addReg(StackPtr)
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
if (NeedsDwarfCFI) {
// Mark effective beginning of when frame pointer becomes valid.
// Define the current CFA to use the EBP/RBP register.
- unsigned DwarfFramePtr = RegInfo->getDwarfRegNum(MachineFramePtr, true);
- unsigned CFIIndex = MMI.addFrameInst(
- MCCFIInstruction::createDefCfaRegister(nullptr, DwarfFramePtr));
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ unsigned DwarfFramePtr = TRI->getDwarfRegNum(MachineFramePtr, true);
+ BuildCFI(MBB, MBBI, DL,
+ MCCFIInstruction::createDefCfaRegister(nullptr, DwarfFramePtr));
}
// Mark the FramePtr as live-in in every block.
int StackOffset = 2 * stackGrowth;
while (MBBI != MBB.end() &&
+ MBBI->getFlag(MachineInstr::FrameSetup) &&
(MBBI->getOpcode() == X86::PUSH32r ||
MBBI->getOpcode() == X86::PUSH64r)) {
PushedRegs = true;
// Mark callee-saved push instruction.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
- unsigned CFIIndex = MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(nullptr, StackOffset));
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ BuildCFI(MBB, MBBI, DL,
+ MCCFIInstruction::createDefCfaOffset(nullptr, StackOffset));
StackOffset += stackGrowth;
}
- if (NeedsWinEH) {
+ if (NeedsWinCFI) {
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_PushReg)).addImm(Reg).setMIFlag(
MachineInstr::FrameSetup);
}
// Realign stack after we pushed callee-saved registers (so that we'll be
// able to calculate their offsets from the frame pointer).
- if (RegInfo->needsStackRealignment(MF)) {
+ // Don't do this for Win64, it needs to realign the stack after the prologue.
+ if (!IsWin64Prologue && TRI->needsStackRealignment(MF)) {
assert(HasFP && "There should be a frame pointer if stack is realigned.");
- uint64_t Val = -MaxAlign;
- MachineInstr *MI =
- BuildMI(MBB, MBBI, DL,
- TII.get(getANDriOpcode(Uses64BitFramePtr, Val)), StackPtr)
- .addReg(StackPtr)
- .addImm(Val)
- .setMIFlag(MachineInstr::FrameSetup);
-
- // The EFLAGS implicit def is dead.
- MI->getOperand(3).setIsDead();
+ BuildStackAlignAND(MBB, MBBI, DL, MaxAlign);
}
// If there is an SUB32ri of ESP immediately before this instruction, merge
// the two. This can be the case when tail call elimination is enabled and
// the callee has more arguments then the caller.
- NumBytes -= mergeSPUpdates(MBB, MBBI, StackPtr, true);
-
- // If there is an ADD32ri or SUB32ri of ESP immediately after this
- // instruction, merge the two instructions.
- mergeSPUpdatesDown(MBB, MBBI, StackPtr, &NumBytes);
+ NumBytes -= mergeSPUpdates(MBB, MBBI, true);
// Adjust stack pointer: ESP -= numbytes.
- static const size_t PageSize = 4096;
-
// Windows and cygwin/mingw require a prologue helper routine when allocating
// more than 4K bytes on the stack. Windows uses __chkstk and cygwin/mingw
// uses __alloca. __alloca and the 32-bit version of __chkstk will probe the
// responsible for adjusting the stack pointer. Touching the stack at 4K
// increments is necessary to ensure that the guard pages used by the OS
// virtual memory manager are allocated in correct sequence.
- if (NumBytes >= PageSize && UseStackProbe) {
- const char *StackProbeSymbol;
- unsigned CallOp;
-
- getStackProbeFunction(STI, CallOp, StackProbeSymbol);
-
+ uint64_t AlignedNumBytes = NumBytes;
+ if (IsWin64Prologue && TRI->needsStackRealignment(MF))
+ AlignedNumBytes = RoundUpToAlignment(AlignedNumBytes, MaxAlign);
+ if (AlignedNumBytes >= StackProbeSize && UseStackProbe) {
// Check whether EAX is livein for this function.
bool isEAXAlive = isEAXLiveIn(MF);
if (Is64Bit) {
// Handle the 64-bit Windows ABI case where we need to call __chkstk.
// Function prologue is responsible for adjusting the stack pointer.
- BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::RAX)
- .addImm(NumBytes)
- .setMIFlag(MachineInstr::FrameSetup);
+ if (isUInt<32>(NumBytes)) {
+ BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
+ .addImm(NumBytes)
+ .setMIFlag(MachineInstr::FrameSetup);
+ } else if (isInt<32>(NumBytes)) {
+ BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri32), X86::RAX)
+ .addImm(NumBytes)
+ .setMIFlag(MachineInstr::FrameSetup);
+ } else {
+ BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::RAX)
+ .addImm(NumBytes)
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
} else {
// Allocate NumBytes-4 bytes on stack in case of isEAXAlive.
// We'll also use 4 already allocated bytes for EAX.
.setMIFlag(MachineInstr::FrameSetup);
}
- BuildMI(MBB, MBBI, DL,
- TII.get(CallOp))
- .addExternalSymbol(StackProbeSymbol)
- .addReg(StackPtr, RegState::Define | RegState::Implicit)
- .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
- .setMIFlag(MachineInstr::FrameSetup);
+ // Save a pointer to the MI where we set AX.
+ MachineBasicBlock::iterator SetRAX = MBBI;
+ --SetRAX;
+
+ // Call __chkstk, __chkstk_ms, or __alloca.
+ emitStackProbeCall(MF, MBB, MBBI, DL);
+
+ // Apply the frame setup flag to all inserted instrs.
+ for (; SetRAX != MBBI; ++SetRAX)
+ SetRAX->setFlag(MachineInstr::FrameSetup);
- if (Is64Bit) {
- // MSVC x64's __chkstk and cygwin/mingw's ___chkstk_ms do not adjust %rsp
- // themself. It also does not clobber %rax so we can reuse it when
- // adjusting %rsp.
- BuildMI(MBB, MBBI, DL, TII.get(X86::SUB64rr), StackPtr)
- .addReg(StackPtr)
- .addReg(X86::RAX)
- .setMIFlag(MachineInstr::FrameSetup);
- }
if (isEAXAlive) {
// Restore EAX
MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
MBB.insert(MBBI, MI);
}
} else if (NumBytes) {
- emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, Uses64BitFramePtr,
- UseLEA, TII, *RegInfo);
+ emitSPUpdate(MBB, MBBI, -(int64_t)NumBytes, /*InEpilogue=*/false);
}
+ if (NeedsWinCFI && NumBytes)
+ BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_StackAlloc))
+ .addImm(NumBytes)
+ .setMIFlag(MachineInstr::FrameSetup);
+
int SEHFrameOffset = 0;
- if (NeedsWinEH) {
- if (HasFP) {
- // We need to set frame base offset low enough such that all saved
- // register offsets would be positive relative to it, but we can't
- // just use NumBytes, because .seh_setframe offset must be <=240.
- // So we pretend to have only allocated enough space to spill the
- // non-volatile registers.
- // We don't care about the rest of stack allocation, because unwinder
- // will restore SP to (BP - SEHFrameOffset)
- for (const CalleeSavedInfo &Info : MFI->getCalleeSavedInfo()) {
- int offset = MFI->getObjectOffset(Info.getFrameIdx());
- SEHFrameOffset = std::max(SEHFrameOffset, std::abs(offset));
- }
- SEHFrameOffset += SEHFrameOffset % 16; // ensure alignmant
-
- // This only needs to account for XMM spill slots, GPR slots
- // are covered by the .seh_pushreg's emitted above.
- unsigned Size = SEHFrameOffset - X86FI->getCalleeSavedFrameSize();
- if (Size) {
- BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_StackAlloc))
- .addImm(Size)
- .setMIFlag(MachineInstr::FrameSetup);
- }
+ if (IsWin64Prologue && HasFP) {
+ SEHFrameOffset = calculateSetFPREG(NumBytes);
+ if (SEHFrameOffset)
+ addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(X86::LEA64r), FramePtr),
+ StackPtr, false, SEHFrameOffset);
+ else
+ BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64rr), FramePtr).addReg(StackPtr);
+ if (NeedsWinCFI)
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_SetFrame))
.addImm(FramePtr)
.addImm(SEHFrameOffset)
.setMIFlag(MachineInstr::FrameSetup);
- } else {
- // SP will be the base register for restoring XMMs
- if (NumBytes) {
- BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_StackAlloc))
- .addImm(NumBytes)
- .setMIFlag(MachineInstr::FrameSetup);
- }
- }
}
- // Skip the rest of register spilling code
- while (MBBI != MBB.end() && MBBI->getFlag(MachineInstr::FrameSetup))
+ while (MBBI != MBB.end() && MBBI->getFlag(MachineInstr::FrameSetup)) {
+ const MachineInstr *FrameInstr = &*MBBI;
++MBBI;
- // Emit SEH info for non-GPRs
- if (NeedsWinEH) {
- for (const CalleeSavedInfo &Info : MFI->getCalleeSavedInfo()) {
- unsigned Reg = Info.getReg();
- if (X86::GR64RegClass.contains(Reg) || X86::GR32RegClass.contains(Reg))
- continue;
- assert(X86::FR64RegClass.contains(Reg) && "Unexpected register class");
-
- int Offset = getFrameIndexOffset(MF, Info.getFrameIdx());
- Offset += SEHFrameOffset;
-
- BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_SaveXMM))
- .addImm(Reg)
- .addImm(Offset)
- .setMIFlag(MachineInstr::FrameSetup);
+ if (NeedsWinCFI) {
+ int FI;
+ if (unsigned Reg = TII.isStoreToStackSlot(FrameInstr, FI)) {
+ if (X86::FR64RegClass.contains(Reg)) {
+ unsigned IgnoredFrameReg;
+ int Offset = getFrameIndexReference(MF, FI, IgnoredFrameReg);
+ Offset += SEHFrameOffset;
+
+ BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_SaveXMM))
+ .addImm(Reg)
+ .addImm(Offset)
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
+ }
}
+ }
+ if (NeedsWinCFI)
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_EndPrologue))
.setMIFlag(MachineInstr::FrameSetup);
+
+ // Realign stack after we spilled callee-saved registers (so that we'll be
+ // able to calculate their offsets from the frame pointer).
+ // Win64 requires aligning the stack after the prologue.
+ if (IsWin64Prologue && TRI->needsStackRealignment(MF)) {
+ assert(HasFP && "There should be a frame pointer if stack is realigned.");
+ BuildStackAlignAND(MBB, MBBI, DL, MaxAlign);
}
// 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)) {
+ if (TRI->hasBasePointer(MF)) {
// Update the base pointer with the current stack pointer.
unsigned Opc = Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr;
BuildMI(MBB, MBBI, DL, TII.get(Opc), BasePtr)
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
if (X86FI->getRestoreBasePointer()) {
- // Stash value of base pointer. Saving RSP instead of EBP shortens dependence chain.
+ // Stash value of base pointer. Saving RSP instead of EBP shortens
+ // dependence chain. Used by SjLj EH.
unsigned Opm = Uses64BitFramePtr ? X86::MOV64mr : X86::MOV32mr;
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opm)),
FramePtr, true, X86FI->getRestoreBasePointerOffset())
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
}
+
+ if (X86FI->getHasSEHFramePtrSave()) {
+ // Stash the value of the frame pointer relative to the base pointer for
+ // Win32 EH. This supports Win32 EH, which does the inverse of the above:
+ // it recovers the frame pointer from the base pointer rather than the
+ // other way around.
+ unsigned Opm = Uses64BitFramePtr ? X86::MOV64mr : X86::MOV32mr;
+ unsigned UsedReg;
+ int Offset =
+ getFrameIndexReference(MF, X86FI->getSEHFramePtrSaveIndex(), UsedReg);
+ assert(UsedReg == BasePtr);
+ addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opm)), UsedReg, true, Offset)
+ .addReg(FramePtr)
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
}
if (((!HasFP && NumBytes) || PushedRegs) && NeedsDwarfCFI) {
if (!HasFP && NumBytes) {
// Define the current CFA rule to use the provided offset.
assert(StackSize);
- unsigned CFIIndex = MMI.addFrameInst(
- MCCFIInstruction::createDefCfaOffset(nullptr,
- -StackSize + stackGrowth));
-
- BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
- .addCFIIndex(CFIIndex);
+ BuildCFI(MBB, MBBI, DL, MCCFIInstruction::createDefCfaOffset(
+ nullptr, -StackSize + stackGrowth));
}
// Emit DWARF info specifying the offsets of the callee-saved registers.
}
}
+bool X86FrameLowering::canUseLEAForSPInEpilogue(
+ const MachineFunction &MF) const {
+ // We can't use LEA instructions for adjusting the stack pointer if this is a
+ // leaf function in the Win64 ABI. Only ADD instructions may be used to
+ // deallocate the stack.
+ // This means that we can use LEA for SP in two situations:
+ // 1. We *aren't* using the Win64 ABI which means we are free to use LEA.
+ // 2. We *have* a frame pointer which means we are permitted to use LEA.
+ return !MF.getTarget().getMCAsmInfo()->usesWindowsCFI() || hasFP(MF);
+}
+
+static bool isFuncletReturnInstr(MachineInstr *MI) {
+ switch (MI->getOpcode()) {
+ case X86::CATCHRET:
+ case X86::CATCHRET64:
+ case X86::CLEANUPRET:
+ case X86::CLEANUPRET64:
+ return true;
+ default:
+ return false;
+ }
+ llvm_unreachable("impossible");
+}
+
void X86FrameLowering::emitEpilogue(MachineFunction &MF,
MachineBasicBlock &MBB) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
- MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
- assert(MBBI != MBB.end() && "Returning block has no instructions");
- unsigned RetOpcode = MBBI->getOpcode();
- DebugLoc DL = MBBI->getDebugLoc();
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
- bool Is64Bit = STI.is64Bit();
+ MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
+ DebugLoc DL;
+ if (MBBI != MBB.end())
+ DL = MBBI->getDebugLoc();
// standard x86_64 and NaCl use 64-bit frame/stack pointers, x32 - 32-bit.
- const bool Uses64BitFramePtr = STI.isTarget64BitLP64() || STI.isTargetNaCl64();
const bool Is64BitILP32 = STI.isTarget64BitILP32();
- bool UseLEA = STI.useLeaForSP();
- unsigned StackAlign = getStackAlignment();
- unsigned SlotSize = RegInfo->getSlotSize();
- unsigned FramePtr = RegInfo->getFrameRegister(MF);
- unsigned MachineFramePtr = Is64BitILP32 ?
- getX86SubSuperRegister(FramePtr, MVT::i64, false) : FramePtr;
- unsigned StackPtr = RegInfo->getStackRegister();
-
- bool IsWinEH = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
- bool NeedsWinEH = IsWinEH && MF.getFunction()->needsUnwindTableEntry();
+ unsigned FramePtr = TRI->getFrameRegister(MF);
+ unsigned MachineFramePtr =
+ Is64BitILP32 ? getX86SubSuperRegister(FramePtr, MVT::i64, false)
+ : FramePtr;
- switch (RetOpcode) {
- default:
- llvm_unreachable("Can only insert epilog into returning blocks");
- case X86::RETQ:
- case X86::RETL:
- case X86::RETIL:
- case X86::RETIQ:
- case X86::TCRETURNdi:
- case X86::TCRETURNri:
- case X86::TCRETURNmi:
- case X86::TCRETURNdi64:
- case X86::TCRETURNri64:
- case X86::TCRETURNmi64:
- case X86::EH_RETURN:
- case X86::EH_RETURN64:
- break; // These are ok
- }
+ bool IsWin64Prologue = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
+ bool NeedsWinCFI =
+ IsWin64Prologue && MF.getFunction()->needsUnwindTableEntry();
// Get the number of bytes to allocate from the FrameInfo.
uint64_t StackSize = MFI->getStackSize();
- uint64_t MaxAlign = MFI->getMaxAlignment();
+ uint64_t MaxAlign = calculateMaxStackAlign(MF);
unsigned CSSize = X86FI->getCalleeSavedFrameSize();
uint64_t NumBytes = 0;
- // If we're forcing a stack realignment we can't rely on just the frame
- // info, we need to know the ABI stack alignment as well in case we
- // have a call out. Otherwise just make sure we have some alignment - we'll
- // go with the minimum.
- if (ForceStackAlign) {
- if (MFI->hasCalls())
- MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
- else
- MaxAlign = MaxAlign ? MaxAlign : 4;
- }
+ if (isFuncletReturnInstr(MBBI)) {
+ NumBytes = MFI->getMaxCallFrameSize();
+ assert(hasFP(MF) && "win64 EH funclets without FP not yet implemented");
- if (hasFP(MF)) {
+ // Pop EBP.
+ BuildMI(MBB, MBBI, DL, TII.get(Is64Bit ? X86::POP64r : X86::POP32r),
+ MachineFramePtr).setMIFlag(MachineInstr::FrameDestroy);
+ } else if (hasFP(MF)) {
// Calculate required stack adjustment.
uint64_t FrameSize = StackSize - SlotSize;
- if (RegInfo->needsStackRealignment(MF)) {
- // Callee-saved registers were pushed on stack before the stack
- // was realigned.
- FrameSize -= CSSize;
- NumBytes = (FrameSize + MaxAlign - 1) / MaxAlign * MaxAlign;
- } else {
- NumBytes = FrameSize - CSSize;
- }
+ NumBytes = FrameSize - CSSize;
+
+ // Callee-saved registers were pushed on stack before the stack was
+ // realigned.
+ if (TRI->needsStackRealignment(MF) && !IsWin64Prologue)
+ NumBytes = RoundUpToAlignment(FrameSize, MaxAlign);
// Pop EBP.
BuildMI(MBB, MBBI, DL,
- TII.get(Is64Bit ? X86::POP64r : X86::POP32r), MachineFramePtr);
+ TII.get(Is64Bit ? X86::POP64r : X86::POP32r), MachineFramePtr)
+ .setMIFlag(MachineInstr::FrameDestroy);
} else {
NumBytes = StackSize - CSSize;
}
+ uint64_t SEHStackAllocAmt = NumBytes;
// Skip the callee-saved pop instructions.
while (MBBI != MBB.begin()) {
MachineBasicBlock::iterator PI = std::prev(MBBI);
unsigned Opc = PI->getOpcode();
- if (Opc != X86::POP32r && Opc != X86::POP64r && Opc != X86::DBG_VALUE &&
- !PI->isTerminator())
+ if ((Opc != X86::POP32r || !PI->getFlag(MachineInstr::FrameDestroy)) &&
+ (Opc != X86::POP64r || !PI->getFlag(MachineInstr::FrameDestroy)) &&
+ Opc != X86::DBG_VALUE && !PI->isTerminator())
break;
--MBBI;
}
MachineBasicBlock::iterator FirstCSPop = MBBI;
- DL = MBBI->getDebugLoc();
+ if (MBBI != MBB.end())
+ DL = MBBI->getDebugLoc();
// If there is an ADD32ri or SUB32ri of ESP immediately before this
// instruction, merge the two instructions.
if (NumBytes || MFI->hasVarSizedObjects())
- mergeSPUpdatesUp(MBB, MBBI, StackPtr, &NumBytes);
+ NumBytes += mergeSPUpdates(MBB, MBBI, true);
// If dynamic alloca is used, then reset esp to point to the last callee-saved
// slot before popping them off! Same applies for the case, when stack was
// realigned.
- if (RegInfo->needsStackRealignment(MF) || MFI->hasVarSizedObjects()) {
- if (RegInfo->needsStackRealignment(MF))
+ if (TRI->needsStackRealignment(MF) || MFI->hasVarSizedObjects()) {
+ if (TRI->needsStackRealignment(MF))
MBBI = FirstCSPop;
- if (CSSize != 0) {
+ unsigned SEHFrameOffset = calculateSetFPREG(SEHStackAllocAmt);
+ uint64_t LEAAmount =
+ IsWin64Prologue ? SEHStackAllocAmt - SEHFrameOffset : -CSSize;
+
+ // There are only two legal forms of epilogue:
+ // - add SEHAllocationSize, %rsp
+ // - lea SEHAllocationSize(%FramePtr), %rsp
+ //
+ // 'mov %FramePtr, %rsp' will not be recognized as an epilogue sequence.
+ // However, we may use this sequence if we have a frame pointer because the
+ // effects of the prologue can safely be undone.
+ if (LEAAmount != 0) {
unsigned Opc = getLEArOpcode(Uses64BitFramePtr);
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr),
- FramePtr, false, -CSSize);
+ FramePtr, false, LEAAmount);
--MBBI;
} else {
unsigned Opc = (Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr);
}
} else if (NumBytes) {
// Adjust stack pointer back: ESP += numbytes.
- emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, Uses64BitFramePtr, UseLEA,
- TII, *RegInfo);
+ emitSPUpdate(MBB, MBBI, NumBytes, /*InEpilogue=*/true);
--MBBI;
}
// into the epilogue. To cope with that, we insert an epilogue marker here,
// then replace it with a 'nop' if it ends up immediately after a CALL in the
// final emitted code.
- if (NeedsWinEH)
+ if (NeedsWinCFI)
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_Epilogue));
- // We're returning from function via eh_return.
- if (RetOpcode == X86::EH_RETURN || RetOpcode == X86::EH_RETURN64) {
- MBBI = MBB.getLastNonDebugInstr();
- MachineOperand &DestAddr = MBBI->getOperand(0);
- assert(DestAddr.isReg() && "Offset should be in register!");
- BuildMI(MBB, MBBI, DL,
- TII.get(Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr),
- StackPtr).addReg(DestAddr.getReg());
- } else if (RetOpcode == X86::TCRETURNri || RetOpcode == X86::TCRETURNdi ||
- RetOpcode == X86::TCRETURNmi ||
- RetOpcode == X86::TCRETURNri64 || RetOpcode == X86::TCRETURNdi64 ||
- RetOpcode == X86::TCRETURNmi64) {
- bool isMem = RetOpcode == X86::TCRETURNmi || RetOpcode == X86::TCRETURNmi64;
- // Tail call return: adjust the stack pointer and jump to callee.
- MBBI = MBB.getLastNonDebugInstr();
- MachineOperand &JumpTarget = MBBI->getOperand(0);
- MachineOperand &StackAdjust = MBBI->getOperand(isMem ? 5 : 1);
- assert(StackAdjust.isImm() && "Expecting immediate value.");
-
- // Adjust stack pointer.
- int StackAdj = StackAdjust.getImm();
- int MaxTCDelta = X86FI->getTCReturnAddrDelta();
- int Offset = 0;
- assert(MaxTCDelta <= 0 && "MaxTCDelta should never be positive");
-
- // Incoporate the retaddr area.
- Offset = StackAdj-MaxTCDelta;
- assert(Offset >= 0 && "Offset should never be negative");
-
- if (Offset) {
- // Check for possible merge with preceding ADD instruction.
- Offset += mergeSPUpdates(MBB, MBBI, StackPtr, true);
- emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, Uses64BitFramePtr,
- UseLEA, TII, *RegInfo);
- }
-
- // Jump to label or value in register.
- if (RetOpcode == X86::TCRETURNdi || RetOpcode == X86::TCRETURNdi64) {
- MachineInstrBuilder MIB =
- BuildMI(MBB, MBBI, DL, TII.get((RetOpcode == X86::TCRETURNdi)
- ? X86::TAILJMPd : X86::TAILJMPd64));
- if (JumpTarget.isGlobal())
- MIB.addGlobalAddress(JumpTarget.getGlobal(), JumpTarget.getOffset(),
- JumpTarget.getTargetFlags());
- else {
- assert(JumpTarget.isSymbol());
- MIB.addExternalSymbol(JumpTarget.getSymbolName(),
- JumpTarget.getTargetFlags());
- }
- } else if (RetOpcode == X86::TCRETURNmi || RetOpcode == X86::TCRETURNmi64) {
- MachineInstrBuilder MIB =
- BuildMI(MBB, MBBI, DL, TII.get((RetOpcode == X86::TCRETURNmi)
- ? X86::TAILJMPm : X86::TAILJMPm64));
- for (unsigned i = 0; i != 5; ++i)
- MIB.addOperand(MBBI->getOperand(i));
- } else if (RetOpcode == X86::TCRETURNri64) {
- BuildMI(MBB, MBBI, DL, TII.get(X86::TAILJMPr64)).
- addReg(JumpTarget.getReg(), RegState::Kill);
- } else {
- BuildMI(MBB, MBBI, DL, TII.get(X86::TAILJMPr)).
- addReg(JumpTarget.getReg(), RegState::Kill);
- }
-
- MachineInstr *NewMI = std::prev(MBBI);
- NewMI->copyImplicitOps(MF, MBBI);
-
- // Delete the pseudo instruction TCRETURN.
- MBB.erase(MBBI);
- } else if ((RetOpcode == X86::RETQ || RetOpcode == X86::RETL ||
- RetOpcode == X86::RETIQ || RetOpcode == X86::RETIL) &&
- (X86FI->getTCReturnAddrDelta() < 0)) {
- // Add the return addr area delta back since we are not tail calling.
- int delta = -1*X86FI->getTCReturnAddrDelta();
- MBBI = MBB.getLastNonDebugInstr();
+ // Add the return addr area delta back since we are not tail calling.
+ int Offset = -1 * X86FI->getTCReturnAddrDelta();
+ assert(Offset >= 0 && "TCDelta should never be positive");
+ if (Offset) {
+ MBBI = MBB.getFirstTerminator();
// Check for possible merge with preceding ADD instruction.
- delta += mergeSPUpdates(MBB, MBBI, StackPtr, true);
- emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, Uses64BitFramePtr, UseLEA, TII,
- *RegInfo);
+ Offset += mergeSPUpdates(MBB, MBBI, true);
+ emitSPUpdate(MBB, MBBI, Offset, /*InEpilogue=*/true);
}
}
-int X86FrameLowering::getFrameIndexOffset(const MachineFunction &MF,
- int FI) const {
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
+// NOTE: this only has a subset of the full frame index logic. In
+// particular, the FI < 0 and AfterFPPop logic is handled in
+// X86RegisterInfo::eliminateFrameIndex, but not here. Possibly
+// (probably?) it should be moved into here.
+int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
+ unsigned &FrameReg) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
+
+ // We can't calculate offset from frame pointer if the stack is realigned,
+ // so enforce usage of stack/base pointer. The base pointer is used when we
+ // have dynamic allocas in addition to dynamic realignment.
+ if (TRI->hasBasePointer(MF))
+ FrameReg = TRI->getBaseRegister();
+ else if (TRI->needsStackRealignment(MF))
+ FrameReg = TRI->getStackRegister();
+ else
+ FrameReg = TRI->getFrameRegister(MF);
+
+ // Offset will hold the offset from the stack pointer at function entry to the
+ // object.
+ // We need to factor in additional offsets applied during the prologue to the
+ // frame, base, and stack pointer depending on which is used.
int Offset = MFI->getObjectOffset(FI) - getOffsetOfLocalArea();
+ const X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
+ unsigned CSSize = X86FI->getCalleeSavedFrameSize();
uint64_t StackSize = MFI->getStackSize();
+ bool HasFP = hasFP(MF);
+ bool IsWin64Prologue = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
+ int64_t FPDelta = 0;
- if (RegInfo->hasBasePointer(MF)) {
- assert (hasFP(MF) && "VLAs and dynamic stack realign, but no FP?!");
+ if (IsWin64Prologue) {
+ assert(!MFI->hasCalls() || (StackSize % 16) == 8);
+
+ // Calculate required stack adjustment.
+ uint64_t FrameSize = StackSize - SlotSize;
+ // If required, include space for extra hidden slot for stashing base pointer.
+ if (X86FI->getRestoreBasePointer())
+ FrameSize += SlotSize;
+ uint64_t NumBytes = FrameSize - CSSize;
+
+ uint64_t SEHFrameOffset = calculateSetFPREG(NumBytes);
+ if (FI && FI == X86FI->getFAIndex())
+ return -SEHFrameOffset;
+
+ // FPDelta is the offset from the "traditional" FP location of the old base
+ // pointer followed by return address and the location required by the
+ // restricted Win64 prologue.
+ // Add FPDelta to all offsets below that go through the frame pointer.
+ FPDelta = FrameSize - SEHFrameOffset;
+ assert((!MFI->hasCalls() || (FPDelta % 16) == 0) &&
+ "FPDelta isn't aligned per the Win64 ABI!");
+ }
+
+
+ if (TRI->hasBasePointer(MF)) {
+ assert(HasFP && "VLAs and dynamic stack realign, but no FP?!");
if (FI < 0) {
// Skip the saved EBP.
- return Offset + RegInfo->getSlotSize();
+ return Offset + SlotSize + FPDelta;
} else {
assert((-(Offset + StackSize)) % MFI->getObjectAlignment(FI) == 0);
return Offset + StackSize;
}
- } else if (RegInfo->needsStackRealignment(MF)) {
+ } else if (TRI->needsStackRealignment(MF)) {
if (FI < 0) {
// Skip the saved EBP.
- return Offset + RegInfo->getSlotSize();
+ return Offset + SlotSize + FPDelta;
} else {
assert((-(Offset + StackSize)) % MFI->getObjectAlignment(FI) == 0);
return Offset + StackSize;
}
// FIXME: Support tail calls
} else {
- if (!hasFP(MF))
+ if (!HasFP)
return Offset + StackSize;
// Skip the saved EBP.
- Offset += RegInfo->getSlotSize();
+ Offset += SlotSize;
// Skip the RETADDR move area
- const X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
int TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
if (TailCallReturnAddrDelta < 0)
Offset -= TailCallReturnAddrDelta;
}
- return Offset;
+ return Offset + FPDelta;
}
-int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
- unsigned &FrameReg) const {
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
- // We can't calculate offset from frame pointer if the stack is realigned,
- // so enforce usage of stack/base pointer. The base pointer is used when we
- // have dynamic allocas in addition to dynamic realignment.
- if (RegInfo->hasBasePointer(MF))
- FrameReg = RegInfo->getBaseRegister();
- else if (RegInfo->needsStackRealignment(MF))
- FrameReg = RegInfo->getStackRegister();
- else
- FrameReg = RegInfo->getFrameRegister(MF);
- return getFrameIndexOffset(MF, FI);
-}
-
-// Simplified from getFrameIndexOffset keeping only StackPointer cases
-int X86FrameLowering::getFrameIndexOffsetFromSP(const MachineFunction &MF, int FI) const {
+// Simplified from getFrameIndexReference keeping only StackPointer cases
+int X86FrameLowering::getFrameIndexReferenceFromSP(const MachineFunction &MF,
+ int FI,
+ unsigned &FrameReg) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
// Does not include any dynamic realign.
const uint64_t StackSize = MFI->getStackSize();
{
#ifndef NDEBUG
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo*>(MF.getSubtarget().getRegisterInfo());
// Note: LLVM arranges the stack as:
// Args > Saved RetPC (<--FP) > CSRs > dynamic alignment (<--BP)
// > "Stack Slots" (<--SP)
// frame). As a result, THE RESULT OF THIS CALL IS MEANINGLESS FOR CSRs
// AND FixedObjects IFF needsStackRealignment or hasVarSizedObject.
- assert(!RegInfo->hasBasePointer(MF) && "we don't handle this case");
+ assert(!TRI->hasBasePointer(MF) && "we don't handle this case");
// We don't handle tail calls, and shouldn't be seeing them
// either.
#endif
}
+ // Fill in FrameReg output argument.
+ FrameReg = TRI->getStackRegister();
+
// This is how the math works out:
//
// %rsp grows (i.e. gets lower) left to right. Each box below is
return Offset + StackSize;
}
-// Simplified from getFrameIndexReference keeping only StackPointer cases
-int X86FrameLowering::getFrameIndexReferenceFromSP(const MachineFunction &MF, int FI,
- unsigned &FrameReg) const {
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo*>(MF.getSubtarget().getRegisterInfo());
-
- assert(!RegInfo->hasBasePointer(MF) && "we don't handle this case");
-
- FrameReg = RegInfo->getStackRegister();
- return getFrameIndexOffsetFromSP(MF, FI);
-}
bool X86FrameLowering::assignCalleeSavedSpillSlots(
MachineFunction &MF, const TargetRegisterInfo *TRI,
std::vector<CalleeSavedInfo> &CSI) const {
MachineFrameInfo *MFI = MF.getFrameInfo();
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
- unsigned SlotSize = RegInfo->getSlotSize();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
unsigned CalleeSavedFrameSize = 0;
// Since emitPrologue and emitEpilogue will handle spilling and restoring of
// the frame register, we can delete it from CSI list and not have to worry
// about avoiding it later.
- unsigned FPReg = RegInfo->getFrameRegister(MF);
+ unsigned FPReg = TRI->getFrameRegister(MF);
for (unsigned i = 0; i < CSI.size(); ++i) {
if (TRI->regsOverlap(CSI[i].getReg(),FPReg)) {
CSI.erase(CSI.begin() + i);
if (X86::GR64RegClass.contains(Reg) || X86::GR32RegClass.contains(Reg))
continue;
- const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg);
+ const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
// ensure alignment
SpillSlotOffset -= std::abs(SpillSlotOffset) % RC->getAlignment();
// spill into slot
const TargetRegisterInfo *TRI) const {
DebugLoc DL = MBB.findDebugLoc(MI);
- MachineFunction &MF = *MBB.getParent();
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
+ // Don't save CSRs in 32-bit EH funclets. The caller saves EBX, EBP, ESI, EDI
+ // for us, and there are no XMM CSRs on Win32.
+ if (MBB.isEHFuncletEntry() && STI.is32Bit() && STI.isOSWindows())
+ return true;
// Push GPRs. It increases frame size.
unsigned Opc = STI.is64Bit() ? X86::PUSH64r : X86::PUSH32r;
// It can be done by spilling XMMs to stack frame.
for (unsigned i = CSI.size(); i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
- if (X86::GR64RegClass.contains(Reg) ||
- X86::GR32RegClass.contains(Reg))
+ if (X86::GR64RegClass.contains(Reg) || X86::GR32RegClass.contains(Reg))
continue;
// Add the callee-saved register as live-in. It's killed at the spill.
MBB.addLiveIn(Reg);
if (CSI.empty())
return false;
- DebugLoc DL = MBB.findDebugLoc(MI);
+ // Don't restore CSRs in 32-bit EH funclets. Matches
+ // spillCalleeSavedRegisters.
+ if (isFuncletReturnInstr(MI) && STI.is32Bit() && STI.isOSWindows())
+ return true;
- MachineFunction &MF = *MBB.getParent();
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
+ DebugLoc DL = MBB.findDebugLoc(MI);
// Reload XMMs from stack frame.
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
!X86::GR32RegClass.contains(Reg))
continue;
- BuildMI(MBB, MI, DL, TII.get(Opc), Reg);
+ BuildMI(MBB, MI, DL, TII.get(Opc), Reg)
+ .setMIFlag(MachineInstr::FrameDestroy);
}
return true;
}
-void
-X86FrameLowering::processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
- RegScavenger *RS) const {
+void X86FrameLowering::determineCalleeSaves(MachineFunction &MF,
+ BitVector &SavedRegs,
+ RegScavenger *RS) const {
+ TargetFrameLowering::determineCalleeSaves(MF, SavedRegs, RS);
+
MachineFrameInfo *MFI = MF.getFrameInfo();
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
- unsigned SlotSize = RegInfo->getSlotSize();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
int64_t TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
}
// Spill the BasePtr if it's used.
- if (RegInfo->hasBasePointer(MF))
- MF.getRegInfo().setPhysRegUsed(RegInfo->getBaseRegister());
+ if (TRI->hasBasePointer(MF)) {
+ SavedRegs.set(TRI->getBaseRegister());
+
+ // Allocate a spill slot for EBP if we have a base pointer and EH funclets.
+ if (MF.getMMI().hasEHFunclets()) {
+ int FI = MFI->CreateSpillStackObject(SlotSize, SlotSize);
+ X86FI->setHasSEHFramePtrSave(true);
+ X86FI->setSEHFramePtrSaveIndex(FI);
+ }
+ }
}
static bool
// limit.
static const uint64_t kSplitStackAvailable = 256;
-void
-X86FrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
- MachineBasicBlock &prologueMBB = MF.front();
+void X86FrameLowering::adjustForSegmentedStacks(
+ MachineFunction &MF, MachineBasicBlock &PrologueMBB) const {
MachineFrameInfo *MFI = MF.getFrameInfo();
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
uint64_t StackSize;
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
- bool Is64Bit = STI.is64Bit();
- const bool IsLP64 = STI.isTarget64BitLP64();
unsigned TlsReg, TlsOffset;
DebugLoc DL;
// The MOV R10, RAX needs to be in a different block, since the RET we emit in
// allocMBB needs to be last (terminating) instruction.
- for (MachineBasicBlock::livein_iterator i = prologueMBB.livein_begin(),
- e = prologueMBB.livein_end(); i != e; i++) {
- allocMBB->addLiveIn(*i);
- checkMBB->addLiveIn(*i);
+ for (const auto &LI : PrologueMBB.liveins()) {
+ allocMBB->addLiveIn(LI);
+ checkMBB->addLiveIn(LI);
}
if (IsNested)
// This jump is taken if SP >= (Stacklet Limit + Stack Space required).
// It jumps to normal execution of the function body.
- BuildMI(checkMBB, DL, TII.get(X86::JA_4)).addMBB(&prologueMBB);
+ BuildMI(checkMBB, DL, TII.get(X86::JA_1)).addMBB(&PrologueMBB);
// On 32 bit we first push the arguments size and then the frame size. On 64
// bit, we pass the stack frame size in r10 and the argument size in r11.
.addImm(StackSize);
BuildMI(allocMBB, DL, TII.get(MOVri), Reg11)
.addImm(X86FI->getArgumentStackSize());
- MF.getRegInfo().setPhysRegUsed(Reg10);
- MF.getRegInfo().setPhysRegUsed(Reg11);
} else {
BuildMI(allocMBB, DL, TII.get(X86::PUSHi32))
.addImm(X86FI->getArgumentStackSize());
}
// __morestack is in libgcc
- if (Is64Bit)
- BuildMI(allocMBB, DL, TII.get(X86::CALL64pcrel32))
- .addExternalSymbol("__morestack");
- else
- BuildMI(allocMBB, DL, TII.get(X86::CALLpcrel32))
- .addExternalSymbol("__morestack");
+ if (Is64Bit && MF.getTarget().getCodeModel() == CodeModel::Large) {
+ // Under the large code model, we cannot assume that __morestack lives
+ // within 2^31 bytes of the call site, so we cannot use pc-relative
+ // addressing. We cannot perform the call via a temporary register,
+ // as the rax register may be used to store the static chain, and all
+ // other suitable registers may be either callee-save or used for
+ // parameter passing. We cannot use the stack at this point either
+ // because __morestack manipulates the stack directly.
+ //
+ // To avoid these issues, perform an indirect call via a read-only memory
+ // location containing the address.
+ //
+ // This solution is not perfect, as it assumes that the .rodata section
+ // is laid out within 2^31 bytes of each function body, but this seems
+ // to be sufficient for JIT.
+ BuildMI(allocMBB, DL, TII.get(X86::CALL64m))
+ .addReg(X86::RIP)
+ .addImm(0)
+ .addReg(0)
+ .addExternalSymbol("__morestack_addr")
+ .addReg(0);
+ MF.getMMI().setUsesMorestackAddr(true);
+ } else {
+ if (Is64Bit)
+ BuildMI(allocMBB, DL, TII.get(X86::CALL64pcrel32))
+ .addExternalSymbol("__morestack");
+ else
+ BuildMI(allocMBB, DL, TII.get(X86::CALLpcrel32))
+ .addExternalSymbol("__morestack");
+ }
if (IsNested)
BuildMI(allocMBB, DL, TII.get(X86::MORESTACK_RET_RESTORE_R10));
else
BuildMI(allocMBB, DL, TII.get(X86::MORESTACK_RET));
- allocMBB->addSuccessor(&prologueMBB);
+ allocMBB->addSuccessor(&PrologueMBB);
checkMBB->addSuccessor(allocMBB);
- checkMBB->addSuccessor(&prologueMBB);
+ checkMBB->addSuccessor(&PrologueMBB);
#ifdef XDEBUG
MF.verify();
/// call inc_stack # doubles the stack space
/// temp0 = sp - MaxStack
/// if( temp0 < SP_LIMIT(P) ) goto IncStack else goto OldStart
-void X86FrameLowering::adjustForHiPEPrologue(MachineFunction &MF) const {
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
+void X86FrameLowering::adjustForHiPEPrologue(
+ MachineFunction &MF, MachineBasicBlock &PrologueMBB) const {
MachineFrameInfo *MFI = MF.getFrameInfo();
- const unsigned SlotSize =
- static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo())
- ->getSlotSize();
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
- const bool Is64Bit = STI.is64Bit();
- const bool IsLP64 = STI.isTarget64BitLP64();
DebugLoc DL;
// HiPE-specific values
const unsigned HipeLeafWords = 24;
// If the stack frame needed is larger than the guaranteed then runtime checks
// and calls to "inc_stack_0" BIF should be inserted in the assembly prologue.
if (MaxStack > Guaranteed) {
- MachineBasicBlock &prologueMBB = MF.front();
MachineBasicBlock *stackCheckMBB = MF.CreateMachineBasicBlock();
MachineBasicBlock *incStackMBB = MF.CreateMachineBasicBlock();
- for (MachineBasicBlock::livein_iterator I = prologueMBB.livein_begin(),
- E = prologueMBB.livein_end(); I != E; I++) {
- stackCheckMBB->addLiveIn(*I);
- incStackMBB->addLiveIn(*I);
+ for (const auto &LI : PrologueMBB.liveins()) {
+ stackCheckMBB->addLiveIn(LI);
+ incStackMBB->addLiveIn(LI);
}
MF.push_front(incStackMBB);
// SPLimitOffset is in a fixed heap location (pointed by BP).
addRegOffset(BuildMI(stackCheckMBB, DL, TII.get(CMPop))
.addReg(ScratchReg), PReg, false, SPLimitOffset);
- BuildMI(stackCheckMBB, DL, TII.get(X86::JAE_4)).addMBB(&prologueMBB);
+ BuildMI(stackCheckMBB, DL, TII.get(X86::JAE_1)).addMBB(&PrologueMBB);
// Create new MBB for IncStack:
BuildMI(incStackMBB, DL, TII.get(CALLop)).
SPReg, false, -MaxStack);
addRegOffset(BuildMI(incStackMBB, DL, TII.get(CMPop))
.addReg(ScratchReg), PReg, false, SPLimitOffset);
- BuildMI(incStackMBB, DL, TII.get(X86::JLE_4)).addMBB(incStackMBB);
+ BuildMI(incStackMBB, DL, TII.get(X86::JLE_1)).addMBB(incStackMBB);
- stackCheckMBB->addSuccessor(&prologueMBB, 99);
+ stackCheckMBB->addSuccessor(&PrologueMBB, 99);
stackCheckMBB->addSuccessor(incStackMBB, 1);
- incStackMBB->addSuccessor(&prologueMBB, 99);
+ incStackMBB->addSuccessor(&PrologueMBB, 99);
incStackMBB->addSuccessor(incStackMBB, 1);
}
#ifdef XDEBUG
#endif
}
-bool X86FrameLowering::
-convertArgMovsToPushes(MachineFunction &MF, MachineBasicBlock &MBB,
- MachineBasicBlock::iterator I, uint64_t Amount) const {
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
- const X86RegisterInfo &RegInfo = *static_cast<const X86RegisterInfo *>(
- MF.getSubtarget().getRegisterInfo());
- unsigned StackPtr = RegInfo.getStackRegister();
-
- // Scan the call setup sequence for the pattern we're looking for.
- // We only handle a simple case now - a sequence of MOV32mi or MOV32mr
- // instructions, that push a sequence of 32-bit values onto the stack, with
- // no gaps.
- std::map<int64_t, MachineBasicBlock::iterator> MovMap;
- do {
- int Opcode = I->getOpcode();
- if (Opcode != X86::MOV32mi && Opcode != X86::MOV32mr)
- break;
-
- // We only want movs of the form:
- // movl imm/r32, k(%ecx)
- // If we run into something else, bail
- // Note that AddrBaseReg may, counterintuitively, not be a register...
- if (!I->getOperand(X86::AddrBaseReg).isReg() ||
- (I->getOperand(X86::AddrBaseReg).getReg() != StackPtr) ||
- !I->getOperand(X86::AddrScaleAmt).isImm() ||
- (I->getOperand(X86::AddrScaleAmt).getImm() != 1) ||
- (I->getOperand(X86::AddrIndexReg).getReg() != X86::NoRegister) ||
- (I->getOperand(X86::AddrSegmentReg).getReg() != X86::NoRegister) ||
- !I->getOperand(X86::AddrDisp).isImm())
- return false;
-
- int64_t StackDisp = I->getOperand(X86::AddrDisp).getImm();
-
- // We don't want to consider the unaligned case.
- if (StackDisp % 4)
- return false;
-
- // If the same stack slot is being filled twice, something's fishy.
- if (!MovMap.insert(std::pair<int64_t, MachineInstr*>(StackDisp, I)).second)
- return false;
-
- ++I;
- } while (I != MBB.end());
-
- // We now expect the end of the sequence - a call and a stack adjust.
- if (I == MBB.end())
+bool X86FrameLowering::adjustStackWithPops(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI, DebugLoc DL, int Offset) const {
+
+ if (Offset <= 0)
return false;
- if (!I->isCall())
+
+ if (Offset % SlotSize)
return false;
- MachineBasicBlock::iterator Call = I;
- if ((++I)->getOpcode() != TII.getCallFrameDestroyOpcode())
+
+ int NumPops = Offset / SlotSize;
+ // This is only worth it if we have at most 2 pops.
+ if (NumPops != 1 && NumPops != 2)
return false;
- // Now, go through the map, and see that we don't have any gaps,
- // but only a series of 32-bit MOVs.
- // Since std::map provides ordered iteration, the original order
- // of the MOVs doesn't matter.
- int64_t ExpectedDist = 0;
- for (auto MMI = MovMap.begin(), MME = MovMap.end(); MMI != MME;
- ++MMI, ExpectedDist += 4)
- if (MMI->first != ExpectedDist)
- return false;
-
- // Ok, everything looks fine. Do the transformation.
- DebugLoc DL = I->getDebugLoc();
+ // Handle only the trivial case where the adjustment directly follows
+ // a call. This is the most common one, anyway.
+ if (MBBI == MBB.begin())
+ return false;
+ MachineBasicBlock::iterator Prev = std::prev(MBBI);
+ if (!Prev->isCall() || !Prev->getOperand(1).isRegMask())
+ return false;
- // It's possible the original stack adjustment amount was larger than
- // that done by the pushes. If so, we still need a SUB.
- Amount -= ExpectedDist;
- if (Amount) {
- MachineInstr* Sub = BuildMI(MBB, Call, DL,
- TII.get(getSUBriOpcode(false, Amount)), StackPtr)
- .addReg(StackPtr).addImm(Amount);
- Sub->getOperand(3).setIsDead();
- }
+ unsigned Regs[2];
+ unsigned FoundRegs = 0;
+
+ auto RegMask = Prev->getOperand(1);
- // Now, iterate through the map in reverse order, and replace the movs
- // with pushes. MOVmi/MOVmr doesn't have any defs, so need to replace uses.
- for (auto MMI = MovMap.rbegin(), MME = MovMap.rend(); MMI != MME; ++MMI) {
- MachineBasicBlock::iterator MOV = MMI->second;
- MachineOperand PushOp = MOV->getOperand(X86::AddrNumOperands);
+ auto &RegClass =
+ Is64Bit ? X86::GR64_NOREX_NOSPRegClass : X86::GR32_NOREX_NOSPRegClass;
+ // Try to find up to NumPops free registers.
+ for (auto Candidate : RegClass) {
- // Replace MOVmr with PUSH32r, and MOVmi with PUSHi of appropriate size
- int PushOpcode = X86::PUSH32r;
- if (MOV->getOpcode() == X86::MOV32mi)
- PushOpcode = getPUSHiOpcode(false, PushOp);
+ // Poor man's liveness:
+ // Since we're immediately after a call, any register that is clobbered
+ // by the call and not defined by it can be considered dead.
+ if (!RegMask.clobbersPhysReg(Candidate))
+ continue;
+
+ bool IsDef = false;
+ for (const MachineOperand &MO : Prev->implicit_operands()) {
+ if (MO.isReg() && MO.isDef() && MO.getReg() == Candidate) {
+ IsDef = true;
+ break;
+ }
+ }
- BuildMI(MBB, Call, DL, TII.get(PushOpcode)).addOperand(PushOp);
- MBB.erase(MOV);
+ if (IsDef)
+ continue;
+
+ Regs[FoundRegs++] = Candidate;
+ if (FoundRegs == (unsigned)NumPops)
+ break;
}
+ if (FoundRegs == 0)
+ return false;
+
+ // If we found only one free register, but need two, reuse the same one twice.
+ while (FoundRegs < (unsigned)NumPops)
+ Regs[FoundRegs++] = Regs[0];
+
+ for (int i = 0; i < NumPops; ++i)
+ BuildMI(MBB, MBBI, DL,
+ TII.get(STI.is64Bit() ? X86::POP64r : X86::POP32r), Regs[i]);
+
return true;
}
void X86FrameLowering::
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
MachineBasicBlock::iterator I) const {
- const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
- const X86RegisterInfo &RegInfo = *static_cast<const X86RegisterInfo *>(
- MF.getSubtarget().getRegisterInfo());
- unsigned StackPtr = RegInfo.getStackRegister();
bool reserveCallFrame = hasReservedCallFrame(MF);
- int Opcode = I->getOpcode();
+ unsigned Opcode = I->getOpcode();
bool isDestroy = Opcode == TII.getCallFrameDestroyOpcode();
- const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
- bool IsLP64 = STI.isTarget64BitLP64();
DebugLoc DL = I->getDebugLoc();
uint64_t Amount = !reserveCallFrame ? I->getOperand(0).getImm() : 0;
- uint64_t CalleeAmt = isDestroy ? I->getOperand(1).getImm() : 0;
+ uint64_t InternalAmt = (isDestroy || Amount) ? I->getOperand(1).getImm() : 0;
I = MBB.erase(I);
if (!reserveCallFrame) {
// We need to keep the stack aligned properly. To do this, we round the
// amount of space needed for the outgoing arguments up to the next
// alignment boundary.
- unsigned StackAlign = MF.getTarget()
- .getSubtargetImpl()
- ->getFrameLowering()
- ->getStackAlignment();
- Amount = (Amount + StackAlign - 1) / StackAlign * StackAlign;
-
- MachineInstr *New = nullptr;
- if (Opcode == TII.getCallFrameSetupOpcode()) {
- // Try to convert movs to the stack into pushes.
- // We currently only look for a pattern that appears in 32-bit
- // calling conventions.
- if (!IsLP64 && convertArgMovsToPushes(MF, MBB, I, Amount))
- return;
-
- New = BuildMI(MF, DL, TII.get(getSUBriOpcode(IsLP64, Amount)),
- StackPtr)
- .addReg(StackPtr)
- .addImm(Amount);
- } else {
- assert(Opcode == TII.getCallFrameDestroyOpcode());
+ unsigned StackAlign = getStackAlignment();
+ Amount = RoundUpToAlignment(Amount, StackAlign);
- // Factor out the amount the callee already popped.
- Amount -= CalleeAmt;
+ // Factor out the amount that gets handled inside the sequence
+ // (Pushes of argument for frame setup, callee pops for frame destroy)
+ Amount -= InternalAmt;
- if (Amount) {
- unsigned Opc = getADDriOpcode(IsLP64, Amount);
- New = BuildMI(MF, DL, TII.get(Opc), StackPtr)
- .addReg(StackPtr).addImm(Amount);
- }
- }
-
- if (New) {
- // The EFLAGS implicit def is dead.
- New->getOperand(3).setIsDead();
+ if (Amount) {
+ // Add Amount to SP to destroy a frame, and subtract to setup.
+ int Offset = isDestroy ? Amount : -Amount;
- // Replace the pseudo instruction with a new instruction.
- MBB.insert(I, New);
+ if (!(MF.getFunction()->optForMinSize() &&
+ adjustStackWithPops(MBB, I, DL, Offset)))
+ BuildStackAdjustment(MBB, I, DL, Offset, /*InEpilogue=*/false);
}
return;
}
- if (Opcode == TII.getCallFrameDestroyOpcode() && CalleeAmt) {
+ if (isDestroy && InternalAmt) {
// If we are performing frame pointer elimination and if the callee pops
// something off the stack pointer, add it back. We do this until we have
// more advanced stack pointer tracking ability.
- unsigned Opc = getSUBriOpcode(IsLP64, CalleeAmt);
- MachineInstr *New = BuildMI(MF, DL, TII.get(Opc), StackPtr)
- .addReg(StackPtr).addImm(CalleeAmt);
-
- // The EFLAGS implicit def is dead.
- New->getOperand(3).setIsDead();
-
// We are not tracking the stack pointer adjustment by the callee, so make
// sure we restore the stack pointer immediately after the call, there may
// be spill code inserted between the CALL and ADJCALLSTACKUP instructions.
MachineBasicBlock::iterator B = MBB.begin();
while (I != B && !std::prev(I)->isCall())
--I;
- MBB.insert(I, New);
+ BuildStackAdjustment(MBB, I, DL, -InternalAmt, /*InEpilogue=*/false);
}
}
+bool X86FrameLowering::canUseAsEpilogue(const MachineBasicBlock &MBB) const {
+ assert(MBB.getParent() && "Block is not attached to a function!");
+
+ if (canUseLEAForSPInEpilogue(*MBB.getParent()))
+ return true;
+
+ // If we cannot use LEA to adjust SP, we may need to use ADD, which
+ // clobbers the EFLAGS. Check that none of the terminators reads the
+ // EFLAGS, and if one uses it, conservatively assume this is not
+ // safe to insert the epilogue here.
+ return !terminatorsNeedFlagsAsInput(MBB);
+}
+
+MachineBasicBlock::iterator X86FrameLowering::restoreWin32EHFrameAndBasePtr(
+ MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+ DebugLoc DL) const {
+ assert(STI.isTargetWindowsMSVC() && "funclets only supported in MSVC env");
+ assert(STI.isTargetWin32() && "EBP/ESI restoration only required on win32");
+ assert(STI.is32Bit() && !Uses64BitFramePtr &&
+ "restoring EBP/ESI on non-32-bit target");
+
+ MachineFunction &MF = *MBB.getParent();
+ unsigned FramePtr = TRI->getFrameRegister(MF);
+ unsigned BasePtr = TRI->getBaseRegister();
+ MachineModuleInfo &MMI = MF.getMMI();
+ const Function *Fn = MF.getFunction();
+ WinEHFuncInfo &FuncInfo = MMI.getWinEHFuncInfo(Fn);
+ X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
+ MachineFrameInfo *MFI = MF.getFrameInfo();
+
+ // FIXME: Don't set FrameSetup flag in catchret case.
+
+ int FI = FuncInfo.EHRegNodeFrameIndex;
+ unsigned UsedReg;
+ int EHRegOffset = getFrameIndexReference(MF, FI, UsedReg);
+ int EHRegSize = MFI->getObjectSize(FI);
+ int EndOffset = -EHRegOffset - EHRegSize;
+ FuncInfo.EHRegNodeEndOffset = EndOffset;
+ assert(EndOffset >= 0 &&
+ "end of registration object above normal EBP position!");
+ if (UsedReg == FramePtr) {
+ // ADD $offset, %ebp
+ assert(UsedReg == FramePtr);
+ unsigned ADDri = getADDriOpcode(false, EndOffset);
+ BuildMI(MBB, MBBI, DL, TII.get(ADDri), FramePtr)
+ .addReg(FramePtr)
+ .addImm(EndOffset)
+ .setMIFlag(MachineInstr::FrameSetup)
+ ->getOperand(3)
+ .setIsDead();
+ } else {
+ assert(UsedReg == BasePtr);
+ // LEA offset(%ebp), %esi
+ addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(X86::LEA32r), BasePtr),
+ FramePtr, false, EndOffset)
+ .setMIFlag(MachineInstr::FrameSetup);
+ // MOV32mr SavedEBPOffset(%esi), %ebp
+ assert(X86FI->getHasSEHFramePtrSave());
+ int Offset =
+ getFrameIndexReference(MF, X86FI->getSEHFramePtrSaveIndex(), UsedReg);
+ assert(UsedReg == BasePtr);
+ addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32mr)), UsedReg, true,
+ Offset)
+ .addReg(FramePtr)
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
+ return MBBI;
+}