#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;
bool X86FrameLowering::hasFP(const MachineFunction &MF) const {
const MachineFrameInfo *MFI = MF.getFrameInfo();
const MachineModuleInfo &MMI = MF.getMMI();
- const TargetRegisterInfo *RegInfo = MF.getTarget().getRegisterInfo();
+ const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
return (MF.getTarget().Options.DisableFramePointerElim(MF) ||
RegInfo->needsStackRealignment(MF) ||
MFI->hasVarSizedObjects() ||
MFI->isFrameAddressTaken() || MFI->hasInlineAsmWithSPAdjust() ||
MF.getInfo<X86MachineFunctionInfo>()->getForceFramePointer() ||
- MMI.callsUnwindInit() || MMI.callsEHReturn());
+ MMI.callsUnwindInit() || MMI.callsEHReturn() ||
+ MFI->hasStackMap() || MFI->hasPatchPoint());
}
static unsigned getSUBriOpcode(unsigned IsLP64, int64_t Imm) {
}
}
+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;
}
static
void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
unsigned StackPtr, int64_t NumBytes,
- bool Is64Bit, bool IsLP64, bool UseLEA,
+ bool Is64BitTarget, bool Is64BitStackPtr, bool UseLEA,
const TargetInstrInfo &TII, const TargetRegisterInfo &TRI) {
bool isSub = NumBytes < 0;
uint64_t Offset = isSub ? -NumBytes : NumBytes;
unsigned Opc;
if (UseLEA)
- Opc = getLEArOpcode(IsLP64);
+ Opc = getLEArOpcode(Is64BitStackPtr);
else
Opc = isSub
- ? getSUBriOpcode(IsLP64, Offset)
- : getADDriOpcode(IsLP64, Offset);
+ ? 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 == (Is64Bit ? 8 : 4)) {
+ if (ThisVal == (Is64BitTarget ? 8 : 4)) {
// Use push / pop instead.
unsigned Reg = isSub
- ? (unsigned)(Is64Bit ? X86::RAX : X86::EAX)
- : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64Bit);
+ ? (unsigned)(Is64BitTarget ? X86::RAX : X86::EAX)
+ : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64BitTarget);
if (Reg) {
Opc = isSub
- ? (Is64Bit ? X86::PUSH64r : X86::PUSH32r)
- : (Is64Bit ? X86::POP64r : X86::POP32r);
+ ? (Is64BitTarget ? X86::PUSH64r : X86::PUSH32r)
+ : (Is64BitTarget ? X86::POP64r : X86::POP32r);
MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc))
.addReg(Reg, getDefRegState(!isSub) | getUndefRegState(isSub));
if (isSub)
return false;
}
-void X86FrameLowering::emitCalleeSavedFrameMoves(
- MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI, DebugLoc DL,
- unsigned FramePtr) const {
+void
+X86FrameLowering::emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI,
+ DebugLoc DL) const {
MachineFunction &MF = *MBB.getParent();
MachineFrameInfo *MFI = MF.getFrameInfo();
MachineModuleInfo &MMI = MF.getMMI();
const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
// Add callee saved registers to move list.
const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
if (CSI.empty()) return;
- const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
- bool HasFP = hasFP(MF);
-
- // Calculate amount of bytes used for return address storing.
- int stackGrowth = -RegInfo->getSlotSize();
-
- // FIXME: This is dirty hack. The code itself is pretty mess right now.
- // It should be rewritten from scratch and generalized sometimes.
-
- // Determine maximum offset (minimum due to stack growth).
- int64_t MaxOffset = 0;
- for (std::vector<CalleeSavedInfo>::const_iterator
- I = CSI.begin(), E = CSI.end(); I != E; ++I)
- MaxOffset = std::min(MaxOffset,
- MFI->getObjectOffset(I->getFrameIdx()));
-
// Calculate offsets.
- int64_t saveAreaOffset = (HasFP ? 3 : 2) * stackGrowth;
for (std::vector<CalleeSavedInfo>::const_iterator
I = CSI.begin(), E = CSI.end(); I != E; ++I) {
int64_t Offset = MFI->getObjectOffset(I->getFrameIdx());
unsigned Reg = I->getReg();
- Offset = MaxOffset - Offset + saveAreaOffset;
-
- // Don't output a new machine move if we're re-saving the frame
- // pointer. This happens when the PrologEpilogInserter has inserted an extra
- // "PUSH" of the frame pointer -- the "emitPrologue" method automatically
- // generates one when frame pointers are used. If we generate a "machine
- // move" for this extra "PUSH", the linker will lose track of the fact that
- // the frame pointer should have the value of the first "PUSH" when it's
- // trying to unwind.
- //
- // FIXME: This looks inelegant. It's possibly correct, but it's covering up
- // another bug. I.e., one where we generate a prolog like this:
- //
- // pushl %ebp
- // movl %esp, %ebp
- // pushl %ebp
- // pushl %esi
- // ...
- //
- // The immediate re-push of EBP is unnecessary. At the least, it's an
- // optimization bug. EBP can be used as a scratch register in certain
- // cases, but probably not when we have a frame pointer.
- if (HasFP && FramePtr == Reg)
- continue;
unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
unsigned CFIIndex =
return false;
}
+void X86FrameLowering::getStackProbeFunction(const X86Subtarget &STI,
+ unsigned &CallOp,
+ const char *&Symbol) {
+ CallOp = STI.is64Bit() ? X86::W64ALLOCA : X86::CALLpcrel32;
+
+ if (STI.is64Bit()) {
+ if (STI.isTargetCygMing()) {
+ Symbol = "___chkstk_ms";
+ } else {
+ Symbol = "__chkstk";
+ }
+ } else if (STI.isTargetCygMing())
+ Symbol = "_alloca";
+ else
+ Symbol = "_chkstk";
+}
+
/// emitPrologue - Push callee-saved registers onto the stack, which
/// automatically adjust the stack pointer. Adjust the stack pointer to allocate
/// space for local variables. Also emit labels used by the exception handler to
/// generate the exception handling frames.
+
+/*
+ Here's a gist of what gets emitted:
+
+ ; Establish frame pointer, if needed
+ [if needs FP]
+ push %rbp
+ .cfi_def_cfa_offset 16
+ .cfi_offset %rbp, -16
+ .seh_pushreg %rpb
+ mov %rsp, %rbp
+ .cfi_def_cfa_register %rbp
+
+ ; Spill general-purpose registers
+ [for all callee-saved GPRs]
+ pushq %<reg>
+ [if not needs FP]
+ .cfi_def_cfa_offset (offset from RETADDR)
+ .seh_pushreg %<reg>
+
+ ; If the required stack alignment > default stack alignment
+ ; rsp needs to be re-aligned. This creates a "re-alignment gap"
+ ; of unknown size in the stack frame.
+ [if stack needs re-alignment]
+ and $MASK, %rsp
+
+ ; Allocate space for locals
+ [if target is Windows and allocated space > 4096 bytes]
+ ; Windows needs special care for allocations larger
+ ; than one page.
+ mov $NNN, %rax
+ call ___chkstk_ms/___chkstk
+ sub %rax, %rsp
+ [else]
+ sub $NNN, %rsp
+
+ [if needs FP]
+ .seh_stackalloc (size of XMM spill slots)
+ .seh_setframe %rbp, SEHFrameOffset ; = size of all spill slots
+ [else]
+ .seh_stackalloc NNN
+
+ ; Spill XMMs
+ ; Note, that while only Windows 64 ABI specifies XMMs as callee-preserved,
+ ; they may get spilled on any platform, if the current function
+ ; calls @llvm.eh.unwind.init
+ [if needs FP]
+ [for all callee-saved XMM registers]
+ movaps %<xmm reg>, -MMM(%rbp)
+ [for all callee-saved XMM registers]
+ .seh_savexmm %<xmm reg>, (-MMM + SEHFrameOffset)
+ ; i.e. the offset relative to (%rbp - SEHFrameOffset)
+ [else]
+ [for all callee-saved XMM registers]
+ movaps %<xmm reg>, KKK(%rsp)
+ [for all callee-saved XMM registers]
+ .seh_savexmm %<xmm reg>, KKK
+
+ .seh_endprologue
+
+ [if needs base pointer]
+ mov %rsp, %rbx
+ [if needs to restore base pointer]
+ mov %rsp, -MMM(%rbp)
+
+ ; Emit CFI info
+ [if needs FP]
+ [for all callee-saved registers]
+ .cfi_offset %<reg>, (offset from %rbp)
+ [else]
+ .cfi_def_cfa_offset (offset from RETADDR)
+ [for all callee-saved registers]
+ .cfi_offset %<reg>, (offset from %rsp)
+
+ Notes:
+ - .seh directives are emitted only for Windows 64 ABI
+ - .cfi directives are emitted for all other ABIs
+ - for 32-bit code, substitute %e?? registers for %r??
+*/
+
void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
MachineBasicBlock &MBB = MF.front(); // Prologue goes in entry BB.
MachineBasicBlock::iterator MBBI = MBB.begin();
MachineFrameInfo *MFI = MF.getFrameInfo();
const Function *Fn = MF.getFunction();
const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
MachineModuleInfo &MMI = MF.getMMI();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
- bool needsFrameMoves = MMI.hasDebugInfo() ||
- Fn->needsUnwindTableEntry();
uint64_t MaxAlign = MFI->getMaxAlignment(); // 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();
- bool IsLP64 = STI.isTarget64BitLP64();
+ // 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 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();
DebugLoc DL;
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
if (TailCallReturnAddrDelta < 0) {
MachineInstr *MI =
BuildMI(MBB, MBBI, DL,
- TII.get(getSUBriOpcode(IsLP64, -TailCallReturnAddrDelta)),
+ TII.get(getSUBriOpcode(Uses64BitFramePtr, -TailCallReturnAddrDelta)),
StackPtr)
.addReg(StackPtr)
.addImm(-TailCallReturnAddrDelta)
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.
// Save EBP/RBP into the appropriate stack slot.
BuildMI(MBB, MBBI, DL, TII.get(Is64Bit ? X86::PUSH64r : X86::PUSH32r))
- .addReg(FramePtr, RegState::Kill)
+ .addReg(MachineFramePtr, RegState::Kill)
.setMIFlag(MachineInstr::FrameSetup);
- if (needsFrameMoves) {
+ if (NeedsDwarfCFI) {
// Mark the place where EBP/RBP was saved.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
.addCFIIndex(CFIIndex);
// Change the rule for the FramePtr to be an "offset" rule.
- unsigned DwarfFramePtr = RegInfo->getDwarfRegNum(FramePtr, true);
+ unsigned DwarfFramePtr = RegInfo->getDwarfRegNum(MachineFramePtr, true);
CFIIndex = MMI.addFrameInst(
MCCFIInstruction::createOffset(nullptr,
DwarfFramePtr, 2 * stackGrowth));
.addCFIIndex(CFIIndex);
}
+ if (NeedsWinEH) {
+ 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(Is64Bit ? X86::MOV64rr : X86::MOV32rr), FramePtr)
+ TII.get(Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr), FramePtr)
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
- if (needsFrameMoves) {
+ 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(FramePtr, true);
+ 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);
}
- // Mark the FramePtr as live-in in every block except the entry.
- for (MachineFunction::iterator I = std::next(MF.begin()), E = MF.end();
- I != E; ++I)
- I->addLiveIn(FramePtr);
+ // Mark the FramePtr as live-in in every block.
+ for (MachineFunction::iterator I = MF.begin(), E = MF.end(); I != E; ++I)
+ I->addLiveIn(MachineFramePtr);
} else {
NumBytes = StackSize - X86FI->getCalleeSavedFrameSize();
}
(MBBI->getOpcode() == X86::PUSH32r ||
MBBI->getOpcode() == X86::PUSH64r)) {
PushedRegs = true;
- MBBI->setFlag(MachineInstr::FrameSetup);
+ unsigned Reg = MBBI->getOperand(0).getReg();
++MBBI;
- if (!HasFP && needsFrameMoves) {
+ if (!HasFP && NeedsDwarfCFI) {
// Mark callee-saved push instruction.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
.addCFIIndex(CFIIndex);
StackOffset += stackGrowth;
}
+
+ if (NeedsWinEH) {
+ 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).
-
- // NOTE: We push the registers before realigning the stack, so
- // vector callee-saved (xmm) registers may be saved w/o proper
- // alignment in this way. However, currently these regs are saved in
- // stack slots (see X86FrameLowering::spillCalleeSavedRegisters()), so
- // this shouldn't be a problem.
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(Is64Bit ? 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.
// 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 >= 4096 && STI.isOSWindows() && !STI.isTargetMacho()) {
+ if (NumBytes >= StackProbeSize && UseStackProbe) {
const char *StackProbeSymbol;
+ unsigned CallOp;
- if (Is64Bit) {
- if (STI.isTargetCygMing()) {
- StackProbeSymbol = "___chkstk_ms";
- } else {
- StackProbeSymbol = "__chkstk";
- }
- } else if (STI.isTargetCygMing())
- StackProbeSymbol = "_alloca";
- else
- StackProbeSymbol = "_chkstk";
+ getStackProbeFunction(STI, CallOp, StackProbeSymbol);
// Check whether EAX is livein for this function.
bool isEAXAlive = isEAXLiveIn(MF);
}
BuildMI(MBB, MBBI, DL,
- TII.get(Is64Bit ? X86::W64ALLOCA : X86::CALLpcrel32))
+ TII.get(CallOp))
.addExternalSymbol(StackProbeSymbol)
.addReg(StackPtr, RegState::Define | RegState::Implicit)
.addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
.setMIFlag(MachineInstr::FrameSetup);
}
if (isEAXAlive) {
- // Restore EAX
- MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
- X86::EAX),
- StackPtr, false, NumBytes - 4);
- MI->setFlag(MachineInstr::FrameSetup);
- MBB.insert(MBBI, MI);
+ // Restore EAX
+ MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
+ X86::EAX),
+ StackPtr, false, NumBytes - 4);
+ MI->setFlag(MachineInstr::FrameSetup);
+ MBB.insert(MBBI, MI);
}
- } else if (NumBytes)
- emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, IsLP64,
+ } else if (NumBytes) {
+ emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, Uses64BitFramePtr,
UseLEA, TII, *RegInfo);
+ }
+
+ 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);
+ }
+
+ 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))
+ ++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);
+ }
+
+ BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_EndPrologue))
+ .setMIFlag(MachineInstr::FrameSetup);
+ }
// 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)) {
- // Update the frame pointer with the current stack pointer.
- unsigned Opc = Is64Bit ? X86::MOV64rr : X86::MOV32rr;
+ // 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.
+ 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) && needsFrameMoves) {
+ if (((!HasFP && NumBytes) || PushedRegs) && NeedsDwarfCFI) {
// Mark end of stack pointer adjustment.
if (!HasFP && NumBytes) {
// Define the current CFA rule to use the provided offset.
// Emit DWARF info specifying the offsets of the callee-saved registers.
if (PushedRegs)
- emitCalleeSavedFrameMoves(MBB, MBBI, DL, HasFP ? FramePtr : StackPtr);
+ emitCalleeSavedFrameMoves(MBB, MBBI, DL);
}
}
const MachineFrameInfo *MFI = MF.getFrameInfo();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ 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();
- bool IsLP64 = STI.isTarget64BitLP64();
+ // 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();
+
switch (RetOpcode) {
default:
llvm_unreachable("Can only insert epilog into returning blocks");
// Pop EBP.
BuildMI(MBB, MBBI, DL,
- TII.get(Is64Bit ? X86::POP64r : X86::POP32r), FramePtr);
+ TII.get(Is64Bit ? X86::POP64r : X86::POP32r), MachineFramePtr);
} else {
NumBytes = StackSize - CSSize;
}
if (RegInfo->needsStackRealignment(MF))
MBBI = FirstCSPop;
if (CSSize != 0) {
- unsigned Opc = getLEArOpcode(IsLP64);
+ unsigned Opc = getLEArOpcode(Uses64BitFramePtr);
addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr),
FramePtr, false, -CSSize);
+ --MBBI;
} else {
- unsigned Opc = (Is64Bit ? X86::MOV64rr : X86::MOV32rr);
+ unsigned Opc = (Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr);
BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
.addReg(FramePtr);
+ --MBBI;
}
} else if (NumBytes) {
// Adjust stack pointer back: ESP += numbytes.
- emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, IsLP64, UseLEA,
+ emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, Uses64BitFramePtr, UseLEA,
TII, *RegInfo);
+ --MBBI;
}
+ // Windows unwinder will not invoke function's exception handler if IP is
+ // either in prologue or in epilogue. This behavior causes a problem when a
+ // call immediately precedes an epilogue, because the return address points
+ // 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)
+ 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(Is64Bit ? X86::MOV64rr : X86::MOV32rr),
+ TII.get(Uses64BitFramePtr ? X86::MOV64rr : X86::MOV32rr),
StackPtr).addReg(DestAddr.getReg());
} else if (RetOpcode == X86::TCRETURNri || RetOpcode == X86::TCRETURNdi ||
RetOpcode == X86::TCRETURNmi ||
if (Offset) {
// Check for possible merge with preceding ADD instruction.
Offset += mergeSPUpdates(MBB, MBBI, StackPtr, true);
- emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, IsLP64,
+ emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, Uses64BitFramePtr,
UseLEA, TII, *RegInfo);
}
// Check for possible merge with preceding ADD instruction.
delta += mergeSPUpdates(MBB, MBBI, StackPtr, true);
- emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, IsLP64, UseLEA, TII,
+ emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, Uses64BitFramePtr, UseLEA, TII,
*RegInfo);
}
}
int X86FrameLowering::getFrameIndexOffset(const MachineFunction &MF,
int FI) const {
const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo*>(MF.getTarget().getRegisterInfo());
+ static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
const MachineFrameInfo *MFI = MF.getFrameInfo();
int Offset = MFI->getObjectOffset(FI) - getOffsetOfLocalArea();
uint64_t StackSize = MFI->getStackSize();
int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
unsigned &FrameReg) const {
const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo*>(MF.getTarget().getRegisterInfo());
+ 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.
return getFrameIndexOffset(MF, FI);
}
-bool X86FrameLowering::spillCalleeSavedRegisters(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MI,
- const std::vector<CalleeSavedInfo> &CSI,
- const TargetRegisterInfo *TRI) const {
- if (CSI.empty())
- return false;
+// 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
+ }
- DebugLoc DL = MBB.findDebugLoc(MI);
+ // 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
+ //
- MachineFunction &MF = *MBB.getParent();
+ // 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.getTarget().getRegisterInfo());
- unsigned SlotSize = RegInfo->getSlotSize();
- unsigned FPReg = TRI->getFrameRegister(MF);
- unsigned CalleeFrameSize = 0;
+ static_cast<const X86RegisterInfo*>(MF.getSubtarget().getRegisterInfo());
+
+ assert(!RegInfo->hasBasePointer(MF) && "we don't handle this case");
+
+ FrameReg = RegInfo->getStackRegister();
+ return getFrameIndexOffsetFromSP(MF, FI);
+}
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+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;
+ int SpillSlotOffset = getOffsetOfLocalArea() + X86FI->getTCReturnAddrDelta();
+
+ if (hasFP(MF)) {
+ // emitPrologue always spills frame register the first thing.
+ SpillSlotOffset -= SlotSize;
+ MFI->CreateFixedSpillStackObject(SlotSize, SpillSlotOffset);
+
+ // 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);
+ for (unsigned i = 0; i < CSI.size(); ++i) {
+ if (TRI->regsOverlap(CSI[i].getReg(),FPReg)) {
+ CSI.erase(CSI.begin() + i);
+ break;
+ }
+ }
+ }
+
+ // Assign slots for GPRs. It increases frame size.
+ for (unsigned i = CSI.size(); i != 0; --i) {
+ unsigned Reg = CSI[i - 1].getReg();
+
+ if (!X86::GR64RegClass.contains(Reg) && !X86::GR32RegClass.contains(Reg))
+ continue;
+
+ SpillSlotOffset -= SlotSize;
+ CalleeSavedFrameSize += SlotSize;
+
+ int SlotIndex = MFI->CreateFixedSpillStackObject(SlotSize, SpillSlotOffset);
+ CSI[i - 1].setFrameIdx(SlotIndex);
+ }
+
+ X86FI->setCalleeSavedFrameSize(CalleeSavedFrameSize);
+
+ // Assign slots for XMMs.
+ for (unsigned i = CSI.size(); i != 0; --i) {
+ unsigned Reg = CSI[i - 1].getReg();
+ if (X86::GR64RegClass.contains(Reg) || X86::GR32RegClass.contains(Reg))
+ continue;
+
+ const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg);
+ // ensure alignment
+ SpillSlotOffset -= std::abs(SpillSlotOffset) % RC->getAlignment();
+ // spill into slot
+ SpillSlotOffset -= RC->getSize();
+ int SlotIndex =
+ MFI->CreateFixedSpillStackObject(RC->getSize(), SpillSlotOffset);
+ CSI[i - 1].setFrameIdx(SlotIndex);
+ MFI->ensureMaxAlignment(RC->getAlignment());
+ }
+
+ return true;
+}
+
+bool X86FrameLowering::spillCalleeSavedRegisters(
+ MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
+ const std::vector<CalleeSavedInfo> &CSI,
+ 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>();
+
// Push GPRs. It increases frame size.
unsigned Opc = STI.is64Bit() ? X86::PUSH64r : X86::PUSH32r;
for (unsigned i = CSI.size(); i != 0; --i) {
- unsigned Reg = CSI[i-1].getReg();
- if (!X86::GR64RegClass.contains(Reg) &&
- !X86::GR32RegClass.contains(Reg))
+ unsigned Reg = CSI[i - 1].getReg();
+
+ 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 (Reg == FPReg)
- // X86RegisterInfo::emitPrologue will handle spilling of frame register.
- continue;
- CalleeFrameSize += SlotSize;
+
BuildMI(MBB, MI, DL, TII.get(Opc)).addReg(Reg, RegState::Kill)
.setMIFlag(MachineInstr::FrameSetup);
}
- X86FI->setCalleeSavedFrameSize(CalleeFrameSize);
-
// Make XMM regs spilled. X86 does not have ability of push/pop XMM.
// It can be done by spilling XMMs to stack frame.
- // Note that only Win64 ABI might spill XMMs.
for (unsigned i = CSI.size(); i != 0; --i) {
unsigned Reg = CSI[i-1].getReg();
if (X86::GR64RegClass.contains(Reg) ||
// Add the callee-saved register as live-in. It's killed at the spill.
MBB.addLiveIn(Reg);
const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- TII.storeRegToStackSlot(MBB, MI, Reg, true, CSI[i-1].getFrameIdx(),
- RC, TRI);
+
+ TII.storeRegToStackSlot(MBB, MI, Reg, true, CSI[i - 1].getFrameIdx(), RC,
+ TRI);
+ --MI;
+ MI->setFlag(MachineInstr::FrameSetup);
+ ++MI;
}
return true;
DebugLoc DL = MBB.findDebugLoc(MI);
MachineFunction &MF = *MBB.getParent();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
+ const X86Subtarget &STI = MF.getTarget().getSubtarget<X86Subtarget>();
// Reload XMMs from stack frame.
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
if (X86::GR64RegClass.contains(Reg) ||
X86::GR32RegClass.contains(Reg))
continue;
+
const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- TII.loadRegFromStackSlot(MBB, MI, Reg, CSI[i].getFrameIdx(),
- RC, TRI);
+ TII.loadRegFromStackSlot(MBB, MI, Reg, CSI[i].getFrameIdx(), RC, TRI);
}
// POP GPRs.
- unsigned FPReg = TRI->getFrameRegister(MF);
unsigned Opc = STI.is64Bit() ? X86::POP64r : X86::POP32r;
for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
unsigned Reg = CSI[i].getReg();
if (!X86::GR64RegClass.contains(Reg) &&
!X86::GR32RegClass.contains(Reg))
continue;
- if (Reg == FPReg)
- // X86RegisterInfo::emitEpilogue will handle restoring of frame register.
- continue;
+
BuildMI(MBB, MI, DL, TII.get(Opc), Reg);
}
return true;
RegScavenger *RS) const {
MachineFrameInfo *MFI = MF.getFrameInfo();
const X86RegisterInfo *RegInfo =
- static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
+ static_cast<const X86RegisterInfo *>(MF.getSubtarget().getRegisterInfo());
unsigned SlotSize = RegInfo->getSlotSize();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
TailCallReturnAddrDelta - SlotSize, true);
}
- if (hasFP(MF)) {
- assert((TailCallReturnAddrDelta <= 0) &&
- "The Delta should always be zero or negative");
- const TargetFrameLowering &TFI = *MF.getTarget().getFrameLowering();
-
- // Create a frame entry for the EBP register that must be saved.
- int FrameIdx = MFI->CreateFixedObject(SlotSize,
- -(int)SlotSize +
- TFI.getOffsetOfLocalArea() +
- TailCallReturnAddrDelta,
- true);
- assert(FrameIdx == MFI->getObjectIndexBegin() &&
- "Slot for EBP register must be last in order to be found!");
- (void)FrameIdx;
- }
-
// Spill the BasePtr if it's used.
if (RegInfo->hasBasePointer(MF))
MF.getRegInfo().setPhysRegUsed(RegInfo->getBaseRegister());
/// and the properties of the function either one or two registers will be
/// needed. Set primary to true for the first register, false for the second.
static unsigned
-GetScratchRegister(bool Is64Bit, const MachineFunction &MF, bool Primary) {
+GetScratchRegister(bool Is64Bit, bool IsLP64, const MachineFunction &MF, bool Primary) {
CallingConv::ID CallingConvention = MF.getFunction()->getCallingConv();
// Erlang stuff.
return Primary ? X86::EBX : X86::EDI;
}
- if (Is64Bit)
- return Primary ? X86::R11 : X86::R12;
+ if (Is64Bit) {
+ if (IsLP64)
+ return Primary ? X86::R11 : X86::R12;
+ else
+ return Primary ? X86::R11D : X86::R12D;
+ }
bool IsNested = HasNestArgument(&MF);
X86FrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
MachineBasicBlock &prologueMBB = MF.front();
MachineFrameInfo *MFI = MF.getFrameInfo();
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ 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;
- unsigned ScratchReg = GetScratchRegister(Is64Bit, MF, true);
+ unsigned ScratchReg = GetScratchRegister(Is64Bit, IsLP64, MF, true);
assert(!MF.getRegInfo().isLiveIn(ScratchReg) &&
"Scratch register is live-in");
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
}
if (IsNested)
- allocMBB->addLiveIn(X86::R10);
+ allocMBB->addLiveIn(IsLP64 ? X86::R10 : X86::R10D);
MF.push_front(allocMBB);
MF.push_front(checkMBB);
if (Is64Bit) {
if (STI.isTargetLinux()) {
TlsReg = X86::FS;
- TlsOffset = 0x70;
+ TlsOffset = IsLP64 ? 0x70 : 0x40;
} else if (STI.isTargetDarwin()) {
TlsReg = X86::GS;
TlsOffset = 0x60 + 90*8; // See pthread_machdep.h. Steal TLS slot 90.
} 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.");
}
if (CompareStackPointer)
- ScratchReg = X86::RSP;
+ ScratchReg = IsLP64 ? X86::RSP : X86::ESP;
else
- BuildMI(checkMBB, DL, TII.get(X86::LEA64r), ScratchReg).addReg(X86::RSP)
+ BuildMI(checkMBB, DL, TII.get(IsLP64 ? X86::LEA64r : X86::LEA64_32r), ScratchReg).addReg(X86::RSP)
.addImm(1).addReg(0).addImm(-StackSize).addReg(0);
- BuildMI(checkMBB, DL, TII.get(X86::CMP64rm)).addReg(ScratchReg)
+ BuildMI(checkMBB, DL, TII.get(IsLP64 ? X86::CMP64rm : X86::CMP32rm)).addReg(ScratchReg)
.addReg(0).addImm(1).addReg(0).addImm(TlsOffset).addReg(TlsReg);
} else {
if (STI.isTargetLinux()) {
} 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()) {
bool SaveScratch2;
if (CompareStackPointer) {
// The primary scratch register is available for holding the TLS offset.
- ScratchReg2 = GetScratchRegister(Is64Bit, MF, true);
+ ScratchReg2 = GetScratchRegister(Is64Bit, IsLP64, MF, true);
SaveScratch2 = false;
} else {
// Need to use a second register to hold the TLS offset
- ScratchReg2 = GetScratchRegister(Is64Bit, MF, false);
+ ScratchReg2 = GetScratchRegister(Is64Bit, IsLP64, MF, false);
// Unfortunately, with fastcc the second scratch register may hold an
// argument.
// 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.
// Functions with nested arguments use R10, so it needs to be saved across
// the call to _morestack
+ const unsigned RegAX = IsLP64 ? X86::RAX : X86::EAX;
+ const unsigned Reg10 = IsLP64 ? X86::R10 : X86::R10D;
+ const unsigned Reg11 = IsLP64 ? X86::R11 : X86::R11D;
+ const unsigned MOVrr = IsLP64 ? X86::MOV64rr : X86::MOV32rr;
+ const unsigned MOVri = IsLP64 ? X86::MOV64ri : X86::MOV32ri;
+
if (IsNested)
- BuildMI(allocMBB, DL, TII.get(X86::MOV64rr), X86::RAX).addReg(X86::R10);
+ BuildMI(allocMBB, DL, TII.get(MOVrr), RegAX).addReg(Reg10);
- BuildMI(allocMBB, DL, TII.get(X86::MOV64ri), X86::R10)
+ BuildMI(allocMBB, DL, TII.get(MOVri), Reg10)
.addImm(StackSize);
- BuildMI(allocMBB, DL, TII.get(X86::MOV64ri), X86::R11)
+ BuildMI(allocMBB, DL, TII.get(MOVri), Reg11)
.addImm(X86FI->getArgumentStackSize());
- MF.getRegInfo().setPhysRegUsed(X86::R10);
- MF.getRegInfo().setPhysRegUsed(X86::R11);
+ 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));
/// temp0 = sp - MaxStack
/// if( temp0 < SP_LIMIT(P) ) goto IncStack else goto OldStart
void X86FrameLowering::adjustForHiPEPrologue(MachineFunction &MF) const {
- const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
MachineFrameInfo *MFI = MF.getFrameInfo();
const unsigned SlotSize =
- static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo())
+ 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;
SPLimitOffset = 0x4c;
}
- ScratchReg = GetScratchRegister(Is64Bit, MF, true);
+ ScratchReg = GetScratchRegister(Is64Bit, IsLP64, MF, true);
assert(!MF.getRegInfo().isLiveIn(ScratchReg) &&
"HiPE prologue scratch register is live-in");
// 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 TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
- const X86RegisterInfo &RegInfo =
- *static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
+ const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
+ 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;
// 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().getFrameLowering()->getStackAlignment();
+ 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)
projects / oota-llvm.git / blobdiff