#include "X86Subtarget.h"
#include "X86TargetMachine.h"
#include "llvm/ADT/SmallSet.h"
+#include "llvm/Analysis/LibCallSemantics.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
return false;
}
-void X86FrameLowering::emitStackProbeCall(MachineFunction &MF,
- MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MBBI,
- DebugLoc DL) const {
+MachineInstr *X86FrameLowering::emitStackProbe(MachineFunction &MF,
+ MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI,
+ DebugLoc DL,
+ bool InProlog) const {
+ const X86Subtarget &STI = MF.getSubtarget<X86Subtarget>();
+ if (STI.isTargetWindowsCoreCLR()) {
+ if (InProlog) {
+ return emitStackProbeInlineStub(MF, MBB, MBBI, DL, true);
+ } else {
+ return emitStackProbeInline(MF, MBB, MBBI, DL, false);
+ }
+ } else {
+ return emitStackProbeCall(MF, MBB, MBBI, DL, InProlog);
+ }
+}
+
+void X86FrameLowering::inlineStackProbe(MachineFunction &MF,
+ MachineBasicBlock &PrologMBB) const {
+ const StringRef ChkStkStubSymbol = "__chkstk_stub";
+ MachineInstr *ChkStkStub = nullptr;
+
+ for (MachineInstr &MI : PrologMBB) {
+ if (MI.isCall() && MI.getOperand(0).isSymbol() &&
+ ChkStkStubSymbol == MI.getOperand(0).getSymbolName()) {
+ ChkStkStub = &MI;
+ break;
+ }
+ }
+
+ if (ChkStkStub != nullptr) {
+ MachineBasicBlock::iterator MBBI = std::next(ChkStkStub->getIterator());
+ assert(std::prev(MBBI).operator==(ChkStkStub) &&
+ "MBBI expected after __chkstk_stub.");
+ DebugLoc DL = PrologMBB.findDebugLoc(MBBI);
+ emitStackProbeInline(MF, PrologMBB, MBBI, DL, true);
+ ChkStkStub->eraseFromParent();
+ }
+}
+
+MachineInstr *X86FrameLowering::emitStackProbeInline(
+ MachineFunction &MF, MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI, DebugLoc DL, bool InProlog) const {
+ const X86Subtarget &STI = MF.getSubtarget<X86Subtarget>();
+ assert(STI.is64Bit() && "different expansion needed for 32 bit");
+ assert(STI.isTargetWindowsCoreCLR() && "custom expansion expects CoreCLR");
+ const TargetInstrInfo &TII = *STI.getInstrInfo();
+ const BasicBlock *LLVM_BB = MBB.getBasicBlock();
+
+ // RAX contains the number of bytes of desired stack adjustment.
+ // The handling here assumes this value has already been updated so as to
+ // maintain stack alignment.
+ //
+ // We need to exit with RSP modified by this amount and execute suitable
+ // page touches to notify the OS that we're growing the stack responsibly.
+ // All stack probing must be done without modifying RSP.
+ //
+ // MBB:
+ // SizeReg = RAX;
+ // ZeroReg = 0
+ // CopyReg = RSP
+ // Flags, TestReg = CopyReg - SizeReg
+ // FinalReg = !Flags.Ovf ? TestReg : ZeroReg
+ // LimitReg = gs magic thread env access
+ // if FinalReg >= LimitReg goto ContinueMBB
+ // RoundBB:
+ // RoundReg = page address of FinalReg
+ // LoopMBB:
+ // LoopReg = PHI(LimitReg,ProbeReg)
+ // ProbeReg = LoopReg - PageSize
+ // [ProbeReg] = 0
+ // if (ProbeReg > RoundReg) goto LoopMBB
+ // ContinueMBB:
+ // RSP = RSP - RAX
+ // [rest of original MBB]
+
+ // Set up the new basic blocks
+ MachineBasicBlock *RoundMBB = MF.CreateMachineBasicBlock(LLVM_BB);
+ MachineBasicBlock *LoopMBB = MF.CreateMachineBasicBlock(LLVM_BB);
+ MachineBasicBlock *ContinueMBB = MF.CreateMachineBasicBlock(LLVM_BB);
+
+ MachineFunction::iterator MBBIter = std::next(MBB.getIterator());
+ MF.insert(MBBIter, RoundMBB);
+ MF.insert(MBBIter, LoopMBB);
+ MF.insert(MBBIter, ContinueMBB);
+
+ // Split MBB and move the tail portion down to ContinueMBB.
+ MachineBasicBlock::iterator BeforeMBBI = std::prev(MBBI);
+ ContinueMBB->splice(ContinueMBB->begin(), &MBB, MBBI, MBB.end());
+ ContinueMBB->transferSuccessorsAndUpdatePHIs(&MBB);
+
+ // Some useful constants
+ const int64_t ThreadEnvironmentStackLimit = 0x10;
+ const int64_t PageSize = 0x1000;
+ const int64_t PageMask = ~(PageSize - 1);
+
+ // Registers we need. For the normal case we use virtual
+ // registers. For the prolog expansion we use RAX, RCX and RDX.
+ MachineRegisterInfo &MRI = MF.getRegInfo();
+ const TargetRegisterClass *RegClass = &X86::GR64RegClass;
+ const unsigned SizeReg = InProlog ? (unsigned)X86::RAX
+ : MRI.createVirtualRegister(RegClass),
+ ZeroReg = InProlog ? (unsigned)X86::RCX
+ : MRI.createVirtualRegister(RegClass),
+ CopyReg = InProlog ? (unsigned)X86::RDX
+ : MRI.createVirtualRegister(RegClass),
+ TestReg = InProlog ? (unsigned)X86::RDX
+ : MRI.createVirtualRegister(RegClass),
+ FinalReg = InProlog ? (unsigned)X86::RDX
+ : MRI.createVirtualRegister(RegClass),
+ RoundedReg = InProlog ? (unsigned)X86::RDX
+ : MRI.createVirtualRegister(RegClass),
+ LimitReg = InProlog ? (unsigned)X86::RCX
+ : MRI.createVirtualRegister(RegClass),
+ JoinReg = InProlog ? (unsigned)X86::RCX
+ : MRI.createVirtualRegister(RegClass),
+ ProbeReg = InProlog ? (unsigned)X86::RCX
+ : MRI.createVirtualRegister(RegClass);
+
+ // SP-relative offsets where we can save RCX and RDX.
+ int64_t RCXShadowSlot = 0;
+ int64_t RDXShadowSlot = 0;
+
+ // If inlining in the prolog, save RCX and RDX.
+ // Future optimization: don't save or restore if not live in.
+ if (InProlog) {
+ // Compute the offsets. We need to account for things already
+ // pushed onto the stack at this point: return address, frame
+ // pointer (if used), and callee saves.
+ X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
+ const int64_t CalleeSaveSize = X86FI->getCalleeSavedFrameSize();
+ const bool HasFP = hasFP(MF);
+ RCXShadowSlot = 8 + CalleeSaveSize + (HasFP ? 8 : 0);
+ RDXShadowSlot = RCXShadowSlot + 8;
+ // Emit the saves.
+ addRegOffset(BuildMI(&MBB, DL, TII.get(X86::MOV64mr)), X86::RSP, false,
+ RCXShadowSlot)
+ .addReg(X86::RCX);
+ addRegOffset(BuildMI(&MBB, DL, TII.get(X86::MOV64mr)), X86::RSP, false,
+ RDXShadowSlot)
+ .addReg(X86::RDX);
+ } else {
+ // Not in the prolog. Copy RAX to a virtual reg.
+ BuildMI(&MBB, DL, TII.get(X86::MOV64rr), SizeReg).addReg(X86::RAX);
+ }
+
+ // Add code to MBB to check for overflow and set the new target stack pointer
+ // to zero if so.
+ BuildMI(&MBB, DL, TII.get(X86::XOR64rr), ZeroReg)
+ .addReg(ZeroReg, RegState::Undef)
+ .addReg(ZeroReg, RegState::Undef);
+ BuildMI(&MBB, DL, TII.get(X86::MOV64rr), CopyReg).addReg(X86::RSP);
+ BuildMI(&MBB, DL, TII.get(X86::SUB64rr), TestReg)
+ .addReg(CopyReg)
+ .addReg(SizeReg);
+ BuildMI(&MBB, DL, TII.get(X86::CMOVB64rr), FinalReg)
+ .addReg(TestReg)
+ .addReg(ZeroReg);
+
+ // FinalReg now holds final stack pointer value, or zero if
+ // allocation would overflow. Compare against the current stack
+ // limit from the thread environment block. Note this limit is the
+ // lowest touched page on the stack, not the point at which the OS
+ // will cause an overflow exception, so this is just an optimization
+ // to avoid unnecessarily touching pages that are below the current
+ // SP but already commited to the stack by the OS.
+ BuildMI(&MBB, DL, TII.get(X86::MOV64rm), LimitReg)
+ .addReg(0)
+ .addImm(1)
+ .addReg(0)
+ .addImm(ThreadEnvironmentStackLimit)
+ .addReg(X86::GS);
+ BuildMI(&MBB, DL, TII.get(X86::CMP64rr)).addReg(FinalReg).addReg(LimitReg);
+ // Jump if the desired stack pointer is at or above the stack limit.
+ BuildMI(&MBB, DL, TII.get(X86::JAE_1)).addMBB(ContinueMBB);
+
+ // Add code to roundMBB to round the final stack pointer to a page boundary.
+ BuildMI(RoundMBB, DL, TII.get(X86::AND64ri32), RoundedReg)
+ .addReg(FinalReg)
+ .addImm(PageMask);
+ BuildMI(RoundMBB, DL, TII.get(X86::JMP_1)).addMBB(LoopMBB);
+
+ // LimitReg now holds the current stack limit, RoundedReg page-rounded
+ // final RSP value. Add code to loopMBB to decrement LimitReg page-by-page
+ // and probe until we reach RoundedReg.
+ if (!InProlog) {
+ BuildMI(LoopMBB, DL, TII.get(X86::PHI), JoinReg)
+ .addReg(LimitReg)
+ .addMBB(RoundMBB)
+ .addReg(ProbeReg)
+ .addMBB(LoopMBB);
+ }
+
+ addRegOffset(BuildMI(LoopMBB, DL, TII.get(X86::LEA64r), ProbeReg), JoinReg,
+ false, -PageSize);
+
+ // Probe by storing a byte onto the stack.
+ BuildMI(LoopMBB, DL, TII.get(X86::MOV8mi))
+ .addReg(ProbeReg)
+ .addImm(1)
+ .addReg(0)
+ .addImm(0)
+ .addReg(0)
+ .addImm(0);
+ BuildMI(LoopMBB, DL, TII.get(X86::CMP64rr))
+ .addReg(RoundedReg)
+ .addReg(ProbeReg);
+ BuildMI(LoopMBB, DL, TII.get(X86::JNE_1)).addMBB(LoopMBB);
+
+ MachineBasicBlock::iterator ContinueMBBI = ContinueMBB->getFirstNonPHI();
+
+ // If in prolog, restore RDX and RCX.
+ if (InProlog) {
+ addRegOffset(BuildMI(*ContinueMBB, ContinueMBBI, DL, TII.get(X86::MOV64rm),
+ X86::RCX),
+ X86::RSP, false, RCXShadowSlot);
+ addRegOffset(BuildMI(*ContinueMBB, ContinueMBBI, DL, TII.get(X86::MOV64rm),
+ X86::RDX),
+ X86::RSP, false, RDXShadowSlot);
+ }
+
+ // Now that the probing is done, add code to continueMBB to update
+ // the stack pointer for real.
+ BuildMI(*ContinueMBB, ContinueMBBI, DL, TII.get(X86::SUB64rr), X86::RSP)
+ .addReg(X86::RSP)
+ .addReg(SizeReg);
+
+ // Add the control flow edges we need.
+ MBB.addSuccessor(ContinueMBB);
+ MBB.addSuccessor(RoundMBB);
+ RoundMBB->addSuccessor(LoopMBB);
+ LoopMBB->addSuccessor(ContinueMBB);
+ LoopMBB->addSuccessor(LoopMBB);
+
+ // Mark all the instructions added to the prolog as frame setup.
+ if (InProlog) {
+ for (++BeforeMBBI; BeforeMBBI != MBB.end(); ++BeforeMBBI) {
+ BeforeMBBI->setFlag(MachineInstr::FrameSetup);
+ }
+ for (MachineInstr &MI : *RoundMBB) {
+ MI.setFlag(MachineInstr::FrameSetup);
+ }
+ for (MachineInstr &MI : *LoopMBB) {
+ MI.setFlag(MachineInstr::FrameSetup);
+ }
+ for (MachineBasicBlock::iterator CMBBI = ContinueMBB->begin();
+ CMBBI != ContinueMBBI; ++CMBBI) {
+ CMBBI->setFlag(MachineInstr::FrameSetup);
+ }
+ }
+
+ // Possible TODO: physreg liveness for InProlog case.
+
+ return ContinueMBBI;
+}
+
+MachineInstr *X86FrameLowering::emitStackProbeCall(
+ MachineFunction &MF, MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI, DebugLoc DL, bool InProlog) const {
bool IsLargeCodeModel = MF.getTarget().getCodeModel() == CodeModel::Large;
unsigned CallOp;
Symbol = "_chkstk";
MachineInstrBuilder CI;
+ MachineBasicBlock::iterator ExpansionMBBI = std::prev(MBBI);
// All current stack probes take AX and SP as input, clobber flags, and
// preserve all registers. x86_64 probes leave RSP unmodified.
.addReg(X86::RSP)
.addReg(X86::RAX);
}
+
+ if (InProlog) {
+ // Apply the frame setup flag to all inserted instrs.
+ for (++ExpansionMBBI; ExpansionMBBI != MBBI; ++ExpansionMBBI)
+ ExpansionMBBI->setFlag(MachineInstr::FrameSetup);
+ }
+
+ return MBBI;
+}
+
+MachineInstr *X86FrameLowering::emitStackProbeInlineStub(
+ MachineFunction &MF, MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI, DebugLoc DL, bool InProlog) const {
+
+ assert(InProlog && "ChkStkStub called outside prolog!");
+
+ BuildMI(MBB, MBBI, DL, TII.get(X86::CALLpcrel32))
+ .addExternalSymbol("__chkstk_stub");
+
+ return MBBI;
}
static unsigned calculateSetFPREG(uint64_t SPAdjust) {
void X86FrameLowering::BuildStackAlignAND(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MBBI,
- DebugLoc DL,
+ DebugLoc DL, unsigned Reg,
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);
+ unsigned AndOp = getANDriOpcode(Uses64BitFramePtr, Val);
+ MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(AndOp), Reg)
+ .addReg(Reg)
+ .addImm(Val)
+ .setMIFlag(MachineInstr::FrameSetup);
// The EFLAGS implicit def is dead.
MI->getOperand(3).setIsDead();
uint64_t MaxAlign = calculateMaxStackAlign(MF); // Desired stack alignment.
uint64_t StackSize = MFI->getStackSize(); // Number of bytes to allocate.
bool IsFunclet = MBB.isEHFuncletEntry();
+ bool IsClrFunclet =
+ IsFunclet &&
+ classifyEHPersonality(Fn->getPersonalityFn()) == EHPersonality::CoreCLR;
bool HasFP = hasFP(MF);
bool IsWin64CC = STI.isCallingConvWin64(Fn->getCallingConv());
bool IsWin64Prologue = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
? getX86SubSuperRegister(FramePtr, MVT::i64, false)
: FramePtr;
unsigned BasePtr = TRI->getBaseRegister();
+
+ // Debug location must be unknown since the first debug location is used
+ // to determine the end of the prologue.
DebugLoc DL;
// Add RETADDR move area to callee saved frame size.
uint64_t NumBytes = 0;
int stackGrowth = -SlotSize;
- unsigned RDX = Uses64BitFramePtr ? X86::RDX : X86::EDX;
- if (IsWin64Prologue && IsFunclet) {
- // Immediately spill RDX into the home slot. The runtime cares about this.
+ // Find the funclet establisher parameter
+ unsigned Establisher = X86::NoRegister;
+ if (IsClrFunclet)
+ Establisher = Uses64BitFramePtr ? X86::RCX : X86::ECX;
+ else if (IsFunclet)
+ Establisher = Uses64BitFramePtr ? X86::RDX : X86::EDX;
+
+ if (IsWin64Prologue && IsFunclet & !IsClrFunclet) {
+ // Immediately spill establisher into the home slot.
+ // The runtime cares about this.
// MOV64mr %rdx, 16(%rsp)
unsigned MOVmr = Uses64BitFramePtr ? X86::MOV64mr : X86::MOV32mr;
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(MOVmr)), StackPtr, true, 16)
- .addReg(RDX)
+ .addReg(Establisher)
.setMIFlag(MachineInstr::FrameSetup);
+ MBB.addLiveIn(Establisher);
}
if (HasFP) {
}
}
- // Mark the FramePtr as live-in in every block.
- for (MachineFunction::iterator I = MF.begin(), E = MF.end(); I != E; ++I)
- I->addLiveIn(MachineFramePtr);
+ // Mark the FramePtr as live-in in every block. Don't do this again for
+ // funclet prologues.
+ if (!IsFunclet) {
+ for (MachineBasicBlock &EveryMBB : MF)
+ EveryMBB.addLiveIn(MachineFramePtr);
+ }
} else {
assert(!IsFunclet && "funclets without FPs not yet implemented");
NumBytes = StackSize - X86FI->getCalleeSavedFrameSize();
// Don't do this for Win64, it needs to realign the stack after the prologue.
if (!IsWin64Prologue && !IsFunclet && TRI->needsStackRealignment(MF)) {
assert(HasFP && "There should be a frame pointer if stack is realigned.");
- BuildStackAlignAND(MBB, MBBI, DL, MaxAlign);
+ BuildStackAlignAND(MBB, MBBI, DL, StackPtr, MaxAlign);
}
// If there is an SUB32ri of ESP immediately before this instruction, merge
// Allocate NumBytes-4 bytes on stack in case of isEAXAlive.
// We'll also use 4 already allocated bytes for EAX.
BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
- .addImm(isEAXAlive ? NumBytes - 4 : NumBytes)
- .setMIFlag(MachineInstr::FrameSetup);
+ .addImm(isEAXAlive ? NumBytes - 4 : NumBytes)
+ .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);
+ emitStackProbe(MF, MBB, MBBI, DL, true);
if (isEAXAlive) {
// Restore EAX
- MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
- X86::EAX),
- StackPtr, false, NumBytes - 4);
+ MachineInstr *MI =
+ addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm), X86::EAX),
+ StackPtr, false, NumBytes - 4);
MI->setFlag(MachineInstr::FrameSetup);
MBB.insert(MBBI, MI);
}
.setMIFlag(MachineInstr::FrameSetup);
int SEHFrameOffset = 0;
+ unsigned SPOrEstablisher = IsFunclet ? Establisher : StackPtr;
if (IsWin64Prologue && HasFP) {
// Set RBP to a small fixed offset from RSP. In the funclet case, we base
- // this calculation on the incoming RDX, which holds the value of RSP from
- // the parent frame at the end of the prologue.
- unsigned SPOrRDX = !IsFunclet ? StackPtr : RDX;
+ // this calculation on the incoming establisher, which holds the value of
+ // RSP from the parent frame at the end of the prologue.
SEHFrameOffset = calculateSetFPREG(ParentFrameNumBytes);
if (SEHFrameOffset)
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(X86::LEA64r), FramePtr),
- SPOrRDX, false, SEHFrameOffset);
+ SPOrEstablisher, false, SEHFrameOffset);
else
BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64rr), FramePtr)
- .addReg(SPOrRDX);
+ .addReg(SPOrEstablisher);
// If this is not a funclet, emit the CFI describing our frame pointer.
if (NeedsWinCFI && !IsFunclet)
// 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);
+ BuildStackAlignAND(MBB, MBBI, DL, SPOrEstablisher, MaxAlign);
}
+ // We already dealt with stack realignment and funclets above.
+ if (IsFunclet && STI.is32Bit())
+ return;
+
// 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
// 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)
+ .addReg(SPOrEstablisher)
.setMIFlag(MachineInstr::FrameSetup);
if (X86FI->getRestoreBasePointer()) {
// Stash value of base pointer. Saving RSP instead of EBP shortens
unsigned Opm = Uses64BitFramePtr ? X86::MOV64mr : X86::MOV32mr;
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opm)),
FramePtr, true, X86FI->getRestoreBasePointerOffset())
- .addReg(StackPtr)
+ .addReg(SPOrEstablisher)
.setMIFlag(MachineInstr::FrameSetup);
}
- if (X86FI->getHasSEHFramePtrSave()) {
+ if (X86FI->getHasSEHFramePtrSave() && !IsFunclet) {
// 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
bool NeedsWinCFI =
IsWin64Prologue && MF.getFunction()->needsUnwindTableEntry();
bool IsFunclet = isFuncletReturnInstr(MBBI);
- MachineBasicBlock *RestoreMBB = nullptr;
+ MachineBasicBlock *TargetMBB = nullptr;
// Get the number of bytes to allocate from the FrameInfo.
uint64_t StackSize = MFI->getStackSize();
uint64_t NumBytes = 0;
if (MBBI->getOpcode() == X86::CATCHRET) {
+ // SEH shouldn't use catchret.
+ assert(!isAsynchronousEHPersonality(
+ classifyEHPersonality(MF.getFunction()->getPersonalityFn())) &&
+ "SEH should not use CATCHRET");
+
NumBytes = getWinEHFuncletFrameSize(MF);
assert(hasFP(MF) && "EH funclets without FP not yet implemented");
- MachineBasicBlock *TargetMBB = MBBI->getOperand(0).getMBB();
-
- // If this is SEH, this isn't really a funclet return.
- bool IsSEH = isAsynchronousEHPersonality(
- classifyEHPersonality(MF.getFunction()->getPersonalityFn()));
- if (IsSEH) {
- if (STI.is32Bit())
- restoreWin32EHStackPointers(MBB, MBBI, DL, /*RestoreSP=*/true);
- BuildMI(MBB, MBBI, DL, TII.get(X86::JMP_4)).addMBB(TargetMBB);
- MBBI->eraseFromParent();
- return;
- }
-
- // For 32-bit, create a new block for the restore code.
- RestoreMBB = TargetMBB;
- if (STI.is32Bit()) {
- RestoreMBB = MF.CreateMachineBasicBlock(MBB.getBasicBlock());
- MF.insert(TargetMBB->getIterator(), RestoreMBB);
- MBB.removeSuccessor(TargetMBB);
- MBB.addSuccessor(RestoreMBB);
- RestoreMBB->addSuccessor(TargetMBB);
- MBBI->getOperand(0).setMBB(RestoreMBB);
- }
+ TargetMBB = MBBI->getOperand(0).getMBB();
// Pop EBP.
BuildMI(MBB, MBBI, DL, TII.get(Is64Bit ? X86::POP64r : X86::POP32r),
MachineFramePtr)
.setMIFlag(MachineInstr::FrameDestroy);
-
- // Insert frame restoration code in a new block.
- if (STI.is32Bit()) {
- auto RestoreMBBI = RestoreMBB->begin();
- restoreWin32EHStackPointers(*RestoreMBB, RestoreMBBI, DL,
- /*RestoreSP=*/true);
- BuildMI(*RestoreMBB, RestoreMBBI, DL, TII.get(X86::JMP_4))
- .addMBB(TargetMBB);
- }
} else if (MBBI->getOpcode() == X86::CLEANUPRET) {
NumBytes = getWinEHFuncletFrameSize(MF);
assert(hasFP(MF) && "EH funclets without FP not yet implemented");
}
MachineBasicBlock::iterator FirstCSPop = MBBI;
- if (RestoreMBB) {
+ if (TargetMBB) {
// Fill EAX/RAX with the address of the target block.
unsigned ReturnReg = STI.is64Bit() ? X86::RAX : X86::EAX;
if (STI.is64Bit()) {
- // LEA64r RestoreMBB(%rip), %rax
+ // LEA64r TargetMBB(%rip), %rax
BuildMI(MBB, FirstCSPop, DL, TII.get(X86::LEA64r), ReturnReg)
.addReg(X86::RIP)
.addImm(0)
.addReg(0)
- .addMBB(RestoreMBB)
+ .addMBB(TargetMBB)
.addReg(0);
} else {
- // MOV32ri $RestoreMBB, %eax
- BuildMI(MBB, FirstCSPop, DL, TII.get(X86::MOV32ri))
- .addReg(ReturnReg)
- .addMBB(RestoreMBB);
+ // MOV32ri $TargetMBB, %eax
+ BuildMI(MBB, FirstCSPop, DL, TII.get(X86::MOV32ri), ReturnReg)
+ .addMBB(TargetMBB);
}
- // Record that we've taken the address of RestoreMBB and no longer just
+ // Record that we've taken the address of TargetMBB and no longer just
// reference it in a terminator.
- RestoreMBB->setHasAddressTaken();
+ TargetMBB->setHasAddressTaken();
}
if (MBBI != MBB.end())
const uint64_t StackSize = MFI->getStackSize();
{
#ifndef NDEBUG
- // Note: LLVM arranges the stack as:
- // Args > Saved RetPC (<--FP) > CSRs > dynamic alignment (<--BP)
- // > "Stack Slots" (<--SP)
- // We can always address StackSlots from RSP. We can usually (unless
- // needsStackRealignment) address CSRs from RSP, but sometimes need to
- // address them from RBP. FixedObjects can be placed anywhere in the stack
- // frame depending on their specific requirements (i.e. we can actually
- // refer to arguments to the function which are stored in the *callers*
- // frame). As a result, THE RESULT OF THIS CALL IS MEANINGLESS FOR CSRs
- // AND FixedObjects IFF needsStackRealignment or hasVarSizedObject.
-
- assert(!TRI->hasBasePointer(MF) && "we don't handle this case");
-
- // We don't handle tail calls, and shouldn't be seeing them
- // either.
+ // LLVM arranges the stack as follows:
+ // ...
+ // ARG2
+ // ARG1
+ // RETADDR
+ // PUSH RBP <-- RBP points here
+ // PUSH CSRs
+ // ~~~~~~~ <-- optional stack realignment dynamic adjustment
+ // ...
+ // STACK OBJECTS
+ // ... <-- RSP after prologue points here
+ //
+ // if (hasVarSizedObjects()):
+ // ... <-- "base pointer" (ESI/RBX) points here
+ // DYNAMIC ALLOCAS
+ // ... <-- RSP points here
+ //
+ // Case 1: In the simple case of no stack realignment and no dynamic
+ // allocas, both "fixed" stack objects (arguments and CSRs) are addressable
+ // with fixed offsets from RSP.
+ //
+ // Case 2: In the case of stack realignment with no dynamic allocas, fixed
+ // stack objects are addressed with RBP and regular stack objects with RSP.
+ //
+ // Case 3: In the case of dynamic allocas and stack realignment, RSP is used
+ // to address stack arguments for outgoing calls and nothing else. The "base
+ // pointer" points to local variables, and RBP points to fixed objects.
+ //
+ // In cases 2 and 3, we can only answer for non-fixed stack objects, and the
+ // answer we give is relative to the SP after the prologue, and not the
+ // SP in the middle of the function.
+
+ assert((!TRI->needsStackRealignment(MF) || !MFI->isFixedObjectIndex(FI)) &&
+ "offset from fixed object to SP is not static");
+
+ // We don't handle tail calls, and shouldn't be seeing them either.
int TailCallReturnAddrDelta =
MF.getInfo<X86MachineFunctionInfo>()->getTCReturnAddrDelta();
assert(!(TailCallReturnAddrDelta < 0) && "we don't handle this case!");