}
}
+static unsigned getANDriOpcode(bool IsLP64, int64_t Imm) {
+ if (IsLP64) {
+ if (isInt<8>(Imm))
+ return X86::AND64ri8;
+ return X86::AND64ri32;
+ }
+ if (isInt<8>(Imm))
+ return X86::AND32ri8;
+ 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;
}
[if needs base pointer]
mov %rsp, %rbx
+ [if needs to restore base pointer]
+ mov %rsp, -MMM(%rbp)
; Emit CFI info
[if needs FP]
// 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();
- bool IsWinEH =
- MF.getTarget().getMCAsmInfo()->getExceptionHandlingType() ==
- ExceptionHandling::WinEH; // Not necessarily synonymous with IsWin64.
+ // Not necessarily synonymous with IsWin64.
+ bool IsWinEH = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
bool NeedsWinEH = IsWinEH && Fn->needsUnwindTableEntry();
bool NeedsDwarfCFI =
!IsWinEH && (MMI.hasDebugInfo() || Fn->needsUnwindTableEntry());
X86FI->setCalleeSavedFrameSize(
X86FI->getCalleeSavedFrameSize() - TailCallReturnAddrDelta);
- bool UseStackProbe = (STI.isOSWindows() && !STI.isTargetMacho());
-
+ 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
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.
// able to calculate their offsets from the frame pointer).
if (RegInfo->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(Uses64BitFramePtr ? X86::AND64ri32 : X86::AND32ri), StackPtr)
+ TII.get(getANDriOpcode(Uses64BitFramePtr, Val)), StackPtr)
.addReg(StackPtr)
- .addImm(-MaxAlign)
+ .addImm(Val)
.setMIFlag(MachineInstr::FrameSetup);
// The EFLAGS implicit def is dead.
// 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) {
+ if (NumBytes >= StackProbeSize && UseStackProbe) {
const char *StackProbeSymbol;
unsigned CallOp;
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.
+ 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 (((!HasFP && NumBytes) || PushedRegs) && NeedsDwarfCFI) {
getX86SubSuperRegister(FramePtr, MVT::i64, false) : FramePtr;
unsigned StackPtr = RegInfo->getStackRegister();
- bool IsWinEH =
- MF.getTarget().getMCAsmInfo()->getExceptionHandlingType() ==
- ExceptionHandling::WinEH;
+ bool IsWinEH = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
bool NeedsWinEH = IsWinEH && MF.getFunction()->needsUnwindTableEntry();
switch (RetOpcode) {
return getFrameIndexOffset(MF, FI);
}
+// Simplified from getFrameIndexOffset keeping only StackPointer cases
+int X86FrameLowering::getFrameIndexOffsetFromSP(const MachineFunction &MF, int FI) 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)
+ // 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(!RegInfo->hasBasePointer(MF) && "we don't handle this case");
+
+ // 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!");
+#endif
+ }
+
+ // This is how the math works out:
+ //
+ // %rsp grows (i.e. gets lower) left to right. Each box below is
+ // one word (eight bytes). Obj0 is the stack slot we're trying to
+ // get to.
+ //
+ // ----------------------------------
+ // | BP | Obj0 | Obj1 | ... | ObjN |
+ // ----------------------------------
+ // ^ ^ ^ ^
+ // A B C E
+ //
+ // A is the incoming stack pointer.
+ // (B - A) is the local area offset (-8 for x86-64) [1]
+ // (C - A) is the Offset returned by MFI->getObjectOffset for Obj0 [2]
+ //
+ // |(E - B)| is the StackSize (absolute value, positive). For a
+ // stack that grown down, this works out to be (B - E). [3]
+ //
+ // E is also the value of %rsp after stack has been set up, and we
+ // want (C - E) -- the value we can add to %rsp to get to Obj0. Now
+ // (C - E) == (C - A) - (B - A) + (B - E)
+ // { Using [1], [2] and [3] above }
+ // == getObjectOffset - LocalAreaOffset + StackSize
+ //
+
+ // Get the Offset from the StackPointer
+ int Offset = MFI->getObjectOffset(FI) - getOffsetOfLocalArea();
+
+ 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 {
if (MF.getFunction()->isVarArg())
report_fatal_error("Segmented stacks do not support vararg functions.");
- if (!STI.isTargetLinux() && !STI.isTargetDarwin() &&
- !STI.isTargetWin32() && !STI.isTargetWin64() && !STI.isTargetFreeBSD())
+ if (!STI.isTargetLinux() && !STI.isTargetDarwin() && !STI.isTargetWin32() &&
+ !STI.isTargetWin64() && !STI.isTargetFreeBSD() &&
+ !STI.isTargetDragonFly())
report_fatal_error("Segmented stacks not supported on this platform.");
// Eventually StackSize will be calculated by a link-time pass; which will
} else if (STI.isTargetFreeBSD()) {
TlsReg = X86::FS;
TlsOffset = 0x18;
+ } else if (STI.isTargetDragonFly()) {
+ TlsReg = X86::FS;
+ TlsOffset = 0x20; // use tls_tcb.tcb_segstack
} else {
report_fatal_error("Segmented stacks not supported on this platform.");
}
} else if (STI.isTargetWin32()) {
TlsReg = X86::FS;
TlsOffset = 0x14; // pvArbitrary, reserved for application use
+ } else if (STI.isTargetDragonFly()) {
+ TlsReg = X86::FS;
+ TlsOffset = 0x10; // use tls_tcb.tcb_segstack
} else if (STI.isTargetFreeBSD()) {
report_fatal_error("Segmented stacks not supported on FreeBSD i386.");
} else {
BuildMI(checkMBB, DL, TII.get(X86::LEA32r), ScratchReg).addReg(X86::ESP)
.addImm(1).addReg(0).addImm(-StackSize).addReg(0);
- if (STI.isTargetLinux() || STI.isTargetWin32() || STI.isTargetWin64()) {
+ if (STI.isTargetLinux() || STI.isTargetWin32() || STI.isTargetWin64() ||
+ STI.isTargetDragonFly()) {
BuildMI(checkMBB, DL, TII.get(X86::CMP32rm)).addReg(ScratchReg)
.addReg(0).addImm(0).addReg(0).addImm(TlsOffset).addReg(TlsReg);
} else if (STI.isTargetDarwin()) {
// 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.
}
// __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));
// 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(incStackMBB, 1);
#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())
+ return false;
+ if (!I->isCall())
+ return false;
+ MachineBasicBlock::iterator Call = I;
+ if ((++I)->getOpcode() != TII.getCallFrameDestroyOpcode())
+ 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();
+
+ // 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();
+ }
+
+ // 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);
+
+ // Replace MOVmr with PUSH32r, and MOVmi with PUSHi of appropriate size
+ int PushOpcode = X86::PUSH32r;
+ if (MOV->getOpcode() == X86::MOV32mi)
+ PushOpcode = getPUSHiOpcode(false, PushOp);
+
+ BuildMI(MBB, Call, DL, TII.get(PushOpcode)).addOperand(PushOp);
+ MBB.erase(MOV);
+ }
+
+ return true;
+}
+
void X86FrameLowering::
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
MachineBasicBlock::iterator I) const {
const X86RegisterInfo &RegInfo = *static_cast<const X86RegisterInfo *>(
MF.getSubtarget().getRegisterInfo());
unsigned StackPtr = RegInfo.getStackRegister();
- bool reseveCallFrame = hasReservedCallFrame(MF);
+ bool reserveCallFrame = hasReservedCallFrame(MF);
int 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 = !reseveCallFrame ? I->getOperand(0).getImm() : 0;
+ uint64_t Amount = !reserveCallFrame ? I->getOperand(0).getImm() : 0;
uint64_t CalleeAmt = isDestroy ? I->getOperand(1).getImm() : 0;
I = MBB.erase(I);
- if (!reseveCallFrame) {
+ if (!reserveCallFrame) {
// If the stack pointer can be changed after prologue, turn the
// adjcallstackup instruction into a 'sub ESP, <amt>' and the
// adjcallstackdown instruction into 'add ESP, <amt>'
- // TODO: consider using push / pop instead of sub + store / add
if (Amount == 0)
return;
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)
projects / oota-llvm.git / blobdiff