maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert r211399, "Generate native unwind info on Win64" 

It broke Legacy JIT Tests on x86_64-{mingw32|msvc}, aka Windows x64.

llvm-svn: 211480
This commit is contained in:
NAKAMURA Takumi 2014-06-22 22:00:56 +00:00
parent ac4e8e5fca
commit d77cefe633
19 changed files with 222 additions and 639 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/include/llvm/CodeGen/MachineFrameInfo.h
View File

@ -484,9 +484,6 @@ public:
///
int CreateFixedObject(uint64_t Size, int64_t SPOffset, bool Immutable);
/// CreateFixedSpillStackObject - Create a spill slot at a fixed location
/// on the stack. Returns an index with a negative value.
int CreateFixedSpillStackObject(uint64_t Size, int64_t SPOffset);
/// isFixedObjectIndex - Returns true if the specified index corresponds to a
/// fixed stack object.

1
llvm/include/llvm/MC/MCAsmInfo.h
View File

@ -481,7 +481,6 @@ public:
bool isExceptionHandlingDwarf() const {
return (ExceptionsType == ExceptionHandling::DwarfCFI ||
ExceptionsType == ExceptionHandling::ARM ||
// Win64 handler data still uses DWARF LSDA encoding.
ExceptionsType == ExceptionHandling::Win64);
}
bool doesDwarfUseRelocationsAcrossSections() const {

13
llvm/include/llvm/Target/TargetFrameLowering.h
View File

@ -93,19 +93,6 @@ public:
/// stack pointer.
virtual bool isFPCloseToIncomingSP() const { return true; }
/// assignCalleeSavedSpillSlots - Allows target to override spill slot
/// assignment logic. If implemented, assignCalleeSavedSpillSlots() should
/// assign frame slots to all CSI entries and return true. If this method
/// returns false, spill slots will be assigned using generic implementation.
/// assignCalleeSavedSpillSlots() may add, delete or rearrange elements of
/// CSI.
virtual bool
assignCalleeSavedSpillSlots(MachineFunction &MF,
const TargetRegisterInfo *TRI,
std::vector<CalleeSavedInfo> &CSI) const {
return false;
}
/// getCalleeSavedSpillSlots - This method returns a pointer to an array of
/// pairs, that contains an entry for each callee saved register that must be
/// spilled to a particular stack location if it is spilled.

13
llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp
View File

@ -77,9 +77,9 @@ void Win64Exception::beginFunction(const MachineFunction *MF) {
if (!shouldEmitPersonality)
return;
const MCSymbol *PersHandlerSym =
TLOF.getCFIPersonalitySymbol(Per, *Asm->Mang, Asm->TM, MMI);
Asm->OutStreamer.EmitWin64EHHandler(PersHandlerSym, true, true);
MCSymbol *GCCHandlerSym =
Asm->GetExternalSymbolSymbol("_GCC_specific_handler");
Asm->OutStreamer.EmitWin64EHHandler(GCCHandlerSym, true, true);
Asm->OutStreamer.EmitLabel(Asm->GetTempSymbol("eh_func_begin",
Asm->getFunctionNumber()));
@ -98,8 +98,15 @@ void Win64Exception::endFunction(const MachineFunction *) {
MMI->TidyLandingPads();
if (shouldEmitPersonality) {
const TargetLoweringObjectFile &TLOF = Asm->getObjFileLowering();
const Function *Per = MMI->getPersonalities()[MMI->getPersonalityIndex()];
const MCSymbol *Sym =
TLOF.getCFIPersonalitySymbol(Per, *Asm->Mang, Asm->TM, MMI);
Asm->OutStreamer.PushSection();
Asm->OutStreamer.EmitWin64EHHandlerData();
Asm->OutStreamer.EmitValue(MCSymbolRefExpr::Create(Sym, Asm->OutContext),
4);
emitExceptionTable();
Asm->OutStreamer.PopSection();
}

45
llvm/lib/CodeGen/MachineFunction.cpp
View File

@ -457,7 +457,7 @@ unsigned MachineFunction::addLiveIn(unsigned PReg,
/// getJTISymbol - Return the MCSymbol for the specified non-empty jump table.
/// If isLinkerPrivate is specified, an 'l' label is returned, otherwise a
/// normal 'L' label is returned.
MCSymbol *MachineFunction::getJTISymbol(unsigned JTI, MCContext &Ctx,
MCSymbol *MachineFunction::getJTISymbol(unsigned JTI, MCContext &Ctx,
bool isLinkerPrivate) const {
const DataLayout *DL = getTarget().getDataLayout();
assert(JumpTableInfo && "No jump tables");
@ -530,9 +530,10 @@ int MachineFrameInfo::CreateStackObject(uint64_t Size, unsigned Alignment,
///
int MachineFrameInfo::CreateSpillStackObject(uint64_t Size,
unsigned Alignment) {
Alignment = clampStackAlignment(
!getFrameLowering()->isStackRealignable() || !RealignOption, Alignment,
getFrameLowering()->getStackAlignment());
Alignment =
clampStackAlignment(!getFrameLowering()->isStackRealignable() ||
!RealignOption,
Alignment, getFrameLowering()->getStackAlignment());
CreateStackObject(Size, Alignment, true);
int Index = (int)Objects.size() - NumFixedObjects - 1;
ensureMaxAlignment(Alignment);
@ -547,9 +548,10 @@ int MachineFrameInfo::CreateSpillStackObject(uint64_t Size,
int MachineFrameInfo::CreateVariableSizedObject(unsigned Alignment,
const AllocaInst *Alloca) {
HasVarSizedObjects = true;
Alignment = clampStackAlignment(
!getFrameLowering()->isStackRealignable() || !RealignOption, Alignment,
getFrameLowering()->getStackAlignment());
Alignment =
clampStackAlignment(!getFrameLowering()->isStackRealignable() ||
!RealignOption,
Alignment, getFrameLowering()->getStackAlignment());
Objects.push_back(StackObject(0, Alignment, 0, false, false, Alloca));
ensureMaxAlignment(Alignment);
return (int)Objects.size()-NumFixedObjects-1;
@ -569,30 +571,16 @@ int MachineFrameInfo::CreateFixedObject(uint64_t Size, int64_t SPOffset,
// object is 16-byte aligned.
unsigned StackAlign = getFrameLowering()->getStackAlignment();
unsigned Align = MinAlign(SPOffset, StackAlign);
Align = clampStackAlignment(!getFrameLowering()->isStackRealignable() ||
!RealignOption,
Align, getFrameLowering()->getStackAlignment());
Align =
clampStackAlignment(!getFrameLowering()->isStackRealignable() ||
!RealignOption,
Align, getFrameLowering()->getStackAlignment());
Objects.insert(Objects.begin(), StackObject(Size, Align, SPOffset, Immutable,
/*isSS*/ false,
/*Alloca*/ nullptr));
return -++NumFixedObjects;
}
/// CreateFixedSpillStackObject - Create a spill slot at a fixed location
/// on the stack. Returns an index with a negative value.
int MachineFrameInfo::CreateFixedSpillStackObject(uint64_t Size,
int64_t SPOffset) {
unsigned StackAlign = getFrameLowering()->getStackAlignment();
unsigned Align = MinAlign(SPOffset, StackAlign);
Align = clampStackAlignment(!getFrameLowering()->isStackRealignable() ||
!RealignOption,
Align, getFrameLowering()->getStackAlignment());
Objects.insert(Objects.begin(), StackObject(Size, Align, SPOffset,
/*Immutable*/ true,
/*isSS*/ true,
/*Alloca*/ nullptr));
return -++NumFixedObjects;
}
BitVector
MachineFrameInfo::getPristineRegs(const MachineBasicBlock *MBB) const {
@ -861,10 +849,11 @@ static bool CanShareConstantPoolEntry(const Constant *A, const Constant *B,
if (isa<StructType>(A->getType()) || isa<ArrayType>(A->getType()) ||
isa<StructType>(B->getType()) || isa<ArrayType>(B->getType()))
return false;
// For now, only support constants with the same size.
uint64_t StoreSize = TD->getTypeStoreSize(A->getType());
if (StoreSize != TD->getTypeStoreSize(B->getType()) || StoreSize > 128)
if (StoreSize != TD->getTypeStoreSize(B->getType()) ||
StoreSize > 128)
return false;
Type *IntTy = IntegerType::get(A->getContext(), StoreSize*8);
@ -893,7 +882,7 @@ static bool CanShareConstantPoolEntry(const Constant *A, const Constant *B,
/// an existing one. User must specify the log2 of the minimum required
/// alignment for the object.
///
unsigned MachineConstantPool::getConstantPoolIndex(const Constant *C,
unsigned MachineConstantPool::getConstantPoolIndex(const Constant *C,
unsigned Alignment) {
assert(Alignment && "Alignment must be specified!");
if (Alignment > PoolAlignment) PoolAlignment = Alignment;

77
llvm/lib/CodeGen/PrologEpilogInserter.cpp
View File

@ -268,56 +268,51 @@ void PEI::calculateCalleeSavedRegisters(MachineFunction &F) {
}
}
if (!TFI->assignCalleeSavedSpillSlots(F, RegInfo, CSI)) {
// If target doesn't implement this, use generic code.
if (CSI.empty())
return; // Early exit if no callee saved registers are modified!
if (CSI.empty())
return; // Early exit if no callee saved registers are modified!
unsigned NumFixedSpillSlots;
const TargetFrameLowering::SpillSlot *FixedSpillSlots =
TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots);
unsigned NumFixedSpillSlots;
const TargetFrameLowering::SpillSlot *FixedSpillSlots =
TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots);
// Now that we know which registers need to be saved and restored, allocate
// stack slots for them.
for (std::vector<CalleeSavedInfo>::iterator
I = CSI.begin(), E = CSI.end(); I != E; ++I) {
unsigned Reg = I->getReg();
const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg);
// Now that we know which registers need to be saved and restored, allocate
// stack slots for them.
for (std::vector<CalleeSavedInfo>::iterator I = CSI.begin(), E = CSI.end();
I != E; ++I) {
unsigned Reg = I->getReg();
const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg);
int FrameIdx;
if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) {
I->setFrameIdx(FrameIdx);
continue;
}
int FrameIdx;
if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) {
I->setFrameIdx(FrameIdx);
continue;
}
// Check to see if this physreg must be spilled to a particular stack slot
// on this target.
const TargetFrameLowering::SpillSlot *FixedSlot = FixedSpillSlots;
while (FixedSlot != FixedSpillSlots+NumFixedSpillSlots &&
FixedSlot->Reg != Reg)
++FixedSlot;
// Check to see if this physreg must be spilled to a particular stack slot
// on this target.
const TargetFrameLowering::SpillSlot *FixedSlot = FixedSpillSlots;
while (FixedSlot != FixedSpillSlots + NumFixedSpillSlots &&
FixedSlot->Reg != Reg)
++FixedSlot;
if (FixedSlot == FixedSpillSlots + NumFixedSpillSlots) {
// Nope, just spill it anywhere convenient.
unsigned Align = RC->getAlignment();
unsigned StackAlign = TFI->getStackAlignment();
if (FixedSlot == FixedSpillSlots + NumFixedSpillSlots) {
// Nope, just spill it anywhere convenient.
unsigned Align = RC->getAlignment();
unsigned StackAlign = TFI->getStackAlignment();
// We may not be able to satisfy the desired alignment specification of
// the TargetRegisterClass if the stack alignment is smaller. Use the
// min.
Align = std::min(Align, StackAlign);
FrameIdx = MFI->CreateStackObject(RC->getSize(), Align, true);
// We may not be able to satisfy the desired alignment specification of
// the TargetRegisterClass if the stack alignment is smaller. Use the
// min.
Align = std::min(Align, StackAlign);
FrameIdx = MFI->CreateStackObject(RC->getSize(), Align, true);
if ((unsigned)FrameIdx < MinCSFrameIndex) MinCSFrameIndex = FrameIdx;
if ((unsigned)FrameIdx > MaxCSFrameIndex) MaxCSFrameIndex = FrameIdx;
} else {
// Spill it to the stack where we must.
FrameIdx =
MFI->CreateFixedSpillStackObject(RC->getSize(), FixedSlot->Offset);
}
I->setFrameIdx(FrameIdx);
} else {
// Spill it to the stack where we must.
FrameIdx = MFI->CreateFixedObject(RC->getSize(), FixedSlot->Offset, true);
}
I->setFrameIdx(FrameIdx);
}
MFI->setCalleeSavedInfo(CSI);

15
llvm/lib/MC/MCObjectFileInfo.cpp
View File

@ -650,16 +650,11 @@ void MCObjectFileInfo::InitCOFFMCObjectFileInfo(Triple T) {
// though it contains relocatable pointers. In PIC mode, this is probably a
// big runtime hit for C++ apps. Either the contents of the LSDA need to be
// adjusted or this should be a data section.
assert(T.isOSWindows() && "Windows is the only supported COFF target");
if (T.getArch() == Triple::x86_64) {
// On Windows 64 with SEH, the LSDA is emitted into the .xdata section
LSDASection = 0;
} else {
LSDASection = Ctx->getCOFFSection(".gcc_except_table",
COFF::IMAGE_SCN_CNT_INITIALIZED_DATA |
COFF::IMAGE_SCN_MEM_READ,
SectionKind::getReadOnly());
}
LSDASection =
Ctx->getCOFFSection(".gcc_except_table",
COFF::IMAGE_SCN_CNT_INITIALIZED_DATA |
COFF::IMAGE_SCN_MEM_READ,
SectionKind::getReadOnly());
// Debug info.
COFFDebugSymbolsSection =

2
llvm/lib/MC/MCStreamer.cpp
View File

@ -526,8 +526,6 @@ void MCStreamer::EmitWin64EHSetFrame(unsigned Register, unsigned Offset) {
report_fatal_error("Frame register and offset already specified!");
if (Offset & 0x0F)
report_fatal_error("Misaligned frame pointer offset!");
if (Offset > 240)
report_fatal_error("Frame offset must be less than or equal to 240!");
MCSymbol *Label = getContext().CreateTempSymbol();
MCWin64EHInstruction Inst(Win64EH::UOP_SetFPReg, Label, Register, Offset);
EmitLabel(Label);

12
llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
View File

@ -143,11 +143,8 @@ getNonexecutableStackSection(MCContext &Ctx) const {
void X86MCAsmInfoMicrosoft::anchor() { }
X86MCAsmInfoMicrosoft::X86MCAsmInfoMicrosoft(const Triple &Triple) {
if (Triple.getArch() == Triple::x86_64) {
if (Triple.getArch() == Triple::x86_64)
PrivateGlobalPrefix = ".L";
PointerSize = 8;
ExceptionsType = ExceptionHandling::Win64;
}
AssemblerDialect = AsmWriterFlavor;
@ -161,18 +158,17 @@ X86MCAsmInfoMicrosoft::X86MCAsmInfoMicrosoft(const Triple &Triple) {
void X86MCAsmInfoGNUCOFF::anchor() { }
X86MCAsmInfoGNUCOFF::X86MCAsmInfoGNUCOFF(const Triple &Triple) {
assert(Triple.isOSWindows() && "Windows is the only supported COFF target");
if (Triple.getArch() == Triple::x86_64) {
PrivateGlobalPrefix = ".L";
PointerSize = 8;
ExceptionsType = ExceptionHandling::Win64;
} else {
ExceptionsType = ExceptionHandling::DwarfCFI;
}
AssemblerDialect = AsmWriterFlavor;
TextAlignFillValue = 0x90;
// Exceptions handling
ExceptionsType = ExceptionHandling::DwarfCFI;
UseIntegratedAssembler = true;
}

355
llvm/lib/Target/X86/X86FrameLowering.cpp
View File

@ -29,7 +29,6 @@
#include "llvm/MC/MCSymbol.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Support/Debug.h"
using namespace llvm;
@ -306,10 +305,9 @@ static bool isEAXLiveIn(MachineFunction &MF) {
return false;
}
void
X86FrameLowering::emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MBBI,
DebugLoc DL) const {
void X86FrameLowering::emitCalleeSavedFrameMoves(
MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI, DebugLoc DL,
unsigned FramePtr) const {
MachineFunction &MF = *MBB.getParent();
MachineFrameInfo *MFI = MF.getFrameInfo();
MachineModuleInfo &MMI = MF.getMMI();
@ -320,11 +318,53 @@ X86FrameLowering::emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
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 =
@ -356,84 +396,6 @@ static bool usesTheStack(const MachineFunction &MF) {
/// 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
; 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();
@ -444,6 +406,8 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
const TargetInstrInfo &TII = *MF.getTarget().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);
@ -451,12 +415,6 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
bool Is64Bit = STI.is64Bit();
bool IsLP64 = STI.isTarget64BitLP64();
bool IsWin64 = STI.isTargetWin64();
bool IsSEH =
MF.getTarget().getMCAsmInfo()->getExceptionHandlingType() ==
ExceptionHandling::Win64; // Not necessarily synonymous with IsWin64.
bool NeedsWin64SEH = IsSEH && Fn->needsUnwindTableEntry();
bool NeedsDwarfCFI =
!IsSEH && (MMI.hasDebugInfo() || Fn->needsUnwindTableEntry());
bool UseLEA = STI.useLeaForSP();
unsigned StackAlign = getStackAlignment();
unsigned SlotSize = RegInfo->getSlotSize();
@ -554,7 +512,7 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
.addReg(FramePtr, RegState::Kill)
.setMIFlag(MachineInstr::FrameSetup);
if (NeedsDwarfCFI) {
if (needsFrameMoves) {
// Mark the place where EBP/RBP was saved.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
@ -572,19 +530,13 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
.addCFIIndex(CFIIndex);
}
if (NeedsWin64SEH) {
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)
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
if (NeedsDwarfCFI) {
if (needsFrameMoves) {
// 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);
@ -594,8 +546,9 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
.addCFIIndex(CFIIndex);
}
// Mark the FramePtr as live-in in every block.
for (MachineFunction::iterator I = MF.begin(), E = MF.end(); I != E; ++I)
// 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);
} else {
NumBytes = StackSize - X86FI->getCalleeSavedFrameSize();
@ -609,10 +562,10 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
(MBBI->getOpcode() == X86::PUSH32r ||
MBBI->getOpcode() == X86::PUSH64r)) {
PushedRegs = true;
unsigned Reg = MBBI->getOperand(0).getReg();
MBBI->setFlag(MachineInstr::FrameSetup);
++MBBI;
if (!HasFP && NeedsDwarfCFI) {
if (!HasFP && needsFrameMoves) {
// Mark callee-saved push instruction.
// Define the current CFA rule to use the provided offset.
assert(StackSize);
@ -622,15 +575,16 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
.addCFIIndex(CFIIndex);
StackOffset += stackGrowth;
}
if (NeedsWin64SEH) {
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.");
MachineInstr *MI =
@ -729,85 +683,23 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
MI->setFlag(MachineInstr::FrameSetup);
MBB.insert(MBBI, MI);
}
} else if (NumBytes) {
} else if (NumBytes)
emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, IsLP64,
UseLEA, TII, *RegInfo);
}
int SEHFrameOffset = 0;
if (NeedsWin64SEH) {
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, abs(offset));
}
SEHFrameOffset += SEHFrameOffset % 16; // ensure alignmant
// This only needs to account for XMM spill slots, GPR slots
// are covered by .seh_pushreg's emitted above.
BuildMI(MBB, MBBI, DL, TII.get(X86::SEH_StackAlloc))
.addImm(SEHFrameOffset - X86FI->getCalleeSavedFrameSize())
.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 (NeedsWin64SEH) {
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 base pointer with the current stack pointer.
// Update the frame pointer with the current stack pointer.
unsigned Opc = Is64Bit ? X86::MOV64rr : X86::MOV32rr;
BuildMI(MBB, MBBI, DL, TII.get(Opc), BasePtr)
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
}
if (((!HasFP && NumBytes) || PushedRegs) && NeedsDwarfCFI) {
if (( (!HasFP && NumBytes) || PushedRegs) && needsFrameMoves) {
// Mark end of stack pointer adjustment.
if (!HasFP && NumBytes) {
// Define the current CFA rule to use the provided offset.
@ -822,7 +714,7 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
// Emit DWARF info specifying the offsets of the callee-saved registers.
if (PushedRegs)
emitCalleeSavedFrameMoves(MBB, MBBI, DL);
emitCalleeSavedFrameMoves(MBB, MBBI, DL, HasFP ? FramePtr : StackPtr);
}
}
@ -1082,98 +974,48 @@ int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
return getFrameIndexOffset(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.getTarget().getRegisterInfo());
unsigned SlotSize = RegInfo->getSlotSize();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
bool X86FrameLowering::spillCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,
const TargetRegisterInfo *TRI) const {
if (CSI.empty())
return false;
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 (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 -= 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 X86RegisterInfo *RegInfo =
static_cast<const X86RegisterInfo *>(MF.getTarget().getRegisterInfo());
unsigned SlotSize = RegInfo->getSlotSize();
unsigned FPReg = TRI->getFrameRegister(MF);
unsigned CalleeFrameSize = 0;
const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
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))
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) ||
@ -1182,12 +1024,8 @@ bool X86FrameLowering::spillCalleeSavedRegisters(
// 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);
--MI;
MI->setFlag(MachineInstr::FrameSetup);
++MI;
}
return true;
@ -1212,19 +1050,22 @@ bool X86FrameLowering::restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
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;
@ -1255,6 +1096,22 @@ X86FrameLowering::processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
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());

9
llvm/lib/Target/X86/X86FrameLowering.h
View File

@ -27,8 +27,8 @@ public:
: TargetFrameLowering(StackGrowsDown, StackAl, LAO) {}
void emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MBBI,
DebugLoc DL) const;
MachineBasicBlock::iterator MBBI, DebugLoc DL,
unsigned FramePtr) const;
/// emitProlog/emitEpilog - These methods insert prolog and epilog code into
/// the function.
@ -42,11 +42,6 @@ public:
void processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
RegScavenger *RS = nullptr) const override;
bool
assignCalleeSavedSpillSlots(MachineFunction &MF,
const TargetRegisterInfo *TRI,
std::vector<CalleeSavedInfo> &CSI) const override;
bool spillCalleeSavedRegisters(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MI,
const std::vector<CalleeSavedInfo> &CSI,

5
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -605,8 +605,9 @@ void X86TargetLowering::resetOperationActions() {
}
// FIXME - use subtarget debug flags
if (!Subtarget->isTargetDarwin() && !Subtarget->isTargetELF() &&
!Subtarget->isTargetCygMing() && !Subtarget->isTargetWin64()) {
if (!Subtarget->isTargetDarwin() &&
!Subtarget->isTargetELF() &&
!Subtarget->isTargetCygMing()) {
setOperationAction(ISD::EH_LABEL, MVT::Other, Expand);
}

24
llvm/lib/Target/X86/X86InstrCompiler.td
View File

@ -110,7 +110,7 @@ let Defs = [EAX, ESP, EFLAGS], Uses = [ESP] in
// When using segmented stacks these are lowered into instructions which first
// check if the current stacklet has enough free memory. If it does, memory is
// allocated by bumping the stack pointer. Otherwise memory is allocated from
// allocated by bumping the stack pointer. Otherwise memory is allocated from
// the heap.
let Defs = [EAX, ESP, EFLAGS], Uses = [ESP] in
@ -196,26 +196,6 @@ let isBranch = 1, isTerminator = 1, isCodeGenOnly = 1 in {
"#EH_SjLj_Setup\t$dst", []>;
}
//===----------------------------------------------------------------------===//
// Pseudo instructions used by unwind info.
//
let isPseudo = 1 in {
def SEH_PushReg : I<0, Pseudo, (outs), (ins i32imm:$reg),
"#SEH_PushReg $reg", []>;
def SEH_SaveReg : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$dst),
"#SEH_SaveReg $reg, $dst", []>;
def SEH_SaveXMM : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$dst),
"#SEH_SaveXMM $reg, $dst", []>;
def SEH_StackAlloc : I<0, Pseudo, (outs), (ins i32imm:$size),
"#SEH_StackAlloc $size", []>;
def SEH_SetFrame : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$offset),
"#SEH_SetFrame $reg, $offset", []>;
def SEH_PushFrame : I<0, Pseudo, (outs), (ins i1imm:$mode),
"#SEH_PushFrame $mode", []>;
def SEH_EndPrologue : I<0, Pseudo, (outs), (ins),
"#SEH_EndPrologue", []>;
}
//===----------------------------------------------------------------------===//
// Pseudo instructions used by segmented stacks.
//
@ -391,7 +371,7 @@ let Defs = [RCX,RDI], isCodeGenOnly = 1 in {
def REP_STOSD_64 : I<0xAB, RawFrm, (outs), (ins), "{rep;stosl|rep stosd}",
[(X86rep_stos i32)], IIC_REP_STOS>, REP, OpSize32,
Requires<[In64BitMode]>;
let Uses = [RAX,RCX,RDI] in
def REP_STOSQ_64 : RI<0xAB, RawFrm, (outs), (ins), "{rep;stosq|rep stosq}",
[(X86rep_stos i64)], IIC_REP_STOS>, REP,

37
llvm/lib/Target/X86/X86MCInstLower.cpp
View File

@ -13,7 +13,6 @@
//===----------------------------------------------------------------------===//
#include "X86AsmPrinter.h"
#include "X86RegisterInfo.h"
#include "InstPrinter/X86ATTInstPrinter.h"
#include "MCTargetDesc/X86BaseInfo.h"
#include "llvm/ADT/SmallString.h"
@ -780,9 +779,6 @@ static void LowerPATCHPOINT(MCStreamer &OS, StackMaps &SM,
void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
X86MCInstLower MCInstLowering(*MF, *this);
const X86RegisterInfo *RI =
static_cast<const X86RegisterInfo *>(TM.getRegisterInfo());
switch (MI->getOpcode()) {
case TargetOpcode::DBG_VALUE:
llvm_unreachable("Should be handled target independently");
@ -887,39 +883,6 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
.addReg(X86::R10)
.addReg(X86::RAX));
return;
case X86::SEH_PushReg:
OutStreamer.EmitWin64EHPushReg(
RI->getSEHRegNum(MI->getOperand(0).getImm()));
return;
case X86::SEH_SaveReg:
OutStreamer.EmitWin64EHSaveReg(RI->getSEHRegNum(MI->getOperand(0).getImm()),
MI->getOperand(1).getImm());
return;
case X86::SEH_SaveXMM:
OutStreamer.EmitWin64EHSaveXMM(RI->getSEHRegNum(MI->getOperand(0).getImm()),
MI->getOperand(1).getImm());
return;
case X86::SEH_StackAlloc:
OutStreamer.EmitWin64EHAllocStack(MI->getOperand(0).getImm());
return;
case X86::SEH_SetFrame:
OutStreamer.EmitWin64EHSetFrame(
RI->getSEHRegNum(MI->getOperand(0).getImm()),
MI->getOperand(1).getImm());
return;
case X86::SEH_PushFrame:
OutStreamer.EmitWin64EHPushFrame(MI->getOperand(0).getImm());
return;
case X86::SEH_EndPrologue:
OutStreamer.EmitWin64EHEndProlog();
return;
}
MCInst TmpInst;

6
llvm/test/CodeGen/X86/2007-05-05-Personality.ll
View File

@ -1,14 +1,12 @@
; RUN: llc < %s -mtriple=i686-pc-linux-gnu -o - | FileCheck %s --check-prefix=LIN
; RUN: llc < %s -mtriple=x86_64-pc-windows-gnu -o - | FileCheck %s --check-prefix=LIN
; RUN: llc < %s -mtriple=i386-pc-mingw32 -o - | FileCheck %s --check-prefix=WIN
; RUN: llc < %s -mtriple=i686-pc-windows-gnu -o - | FileCheck %s --check-prefix=WIN
; RUN: llc < %s -mtriple=x86_64-pc-windows-gnu -o - | FileCheck %s --check-prefix=WIN64
; LIN: .cfi_personality 0, __gnat_eh_personality
; LIN: .cfi_lsda 0, .Lexception0
; WIN: .cfi_personality 0, ___gnat_eh_personality
; WIN: .cfi_lsda 0, Lexception0
; WIN64: .seh_handler __gnat_eh_personality
; WIN64: .seh_handlerdata
@error = external global i8
@ -17,7 +15,7 @@ entry:
invoke void @raise()
to label %eh_then unwind label %unwind
unwind: ; preds = %entry
unwind: ; preds = %entry
%eh_ptr = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gnat_eh_personality to i8*)
catch i8* @error
%eh_select = extractvalue { i8*, i32 } %eh_ptr, 1

4
llvm/test/CodeGen/X86/2009-06-03-Win64SpillXMM.ll
View File

@ -1,7 +1,7 @@
; RUN: llc -mcpu=generic -mtriple=x86_64-mingw32 < %s | FileCheck %s
; CHECK: subq $40, %rsp
; CHECK: movaps %xmm8, 16(%rsp)
; CHECK: movaps %xmm7, (%rsp)
; CHECK: movaps %xmm8, (%rsp)
; CHECK: movaps %xmm7, 16(%rsp)
define i32 @a() nounwind {
entry:

60
llvm/test/CodeGen/X86/avx-intel-ocl.ll
View File

@ -7,21 +7,21 @@ declare <16 x float> @func_float16_ptr(<16 x float>, <16 x float> *)
declare <16 x float> @func_float16(<16 x float>, <16 x float>)
declare i32 @func_int(i32, i32)
; WIN64-LABEL: testf16_inp
; WIN64: testf16_inp
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: leaq {{.*}}(%rsp), %rcx
; WIN64: call
; WIN64: ret
; X32-LABEL: testf16_inp
; X32: testf16_inp
; X32: movl %eax, (%esp)
; X32: vaddps {{.*}}, {{%ymm[0-1]}}
; X32: vaddps {{.*}}, {{%ymm[0-1]}}
; X32: call
; X32: ret
; X64-LABEL: testf16_inp
; X64: testf16_inp
; X64: vaddps {{.*}}, {{%ymm[0-1]}}
; X64: vaddps {{.*}}, {{%ymm[0-1]}}
; X64: leaq {{.*}}(%rsp), %rdi
@ -41,14 +41,14 @@ define <16 x float> @testf16_inp(<16 x float> %a, <16 x float> %b) nounwind {
;test calling conventions - preserved registers
; preserved ymm6-ymm15
; WIN64-LABEL: testf16_regs
; WIN64: testf16_regs
; WIN64: call
; WIN64: vaddps {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; WIN64: vaddps {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; WIN64: ret
; preserved ymm8-ymm15
; X64-LABEL: testf16_regs
; X64: testf16_regs
; X64: call
; X64: vaddps {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; X64: vaddps {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
@ -65,30 +65,28 @@ define <16 x float> @testf16_regs(<16 x float> %a, <16 x float> %b) nounwind {
}
; test calling conventions - prolog and epilog
; WIN64-LABEL: test_prolog_epilog
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rbp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: call
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; X64-LABEL: test_prolog_epilog
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
@ -113,14 +111,12 @@ define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x fl
; test functions with integer parameters
; pass parameters on stack for 32-bit platform
; X32-LABEL: test_int
; X32: movl {{.*}}, 4(%esp)
; X32: movl {{.*}}, (%esp)
; X32: call
; X32: addl {{.*}}, %eax
; pass parameters in registers for 64-bit platform
; X64-LABEL: test_int
; X64: leal {{.*}}, %edi
; X64: movl {{.*}}, %esi
; X64: call
@ -132,21 +128,21 @@ define i32 @test_int(i32 %a, i32 %b) nounwind {
ret i32 %c
}
; WIN64-LABEL: test_float4
; WIN64: test_float4
; WIN64-NOT: vzeroupper
; WIN64: call
; WIN64-NOT: vzeroupper
; WIN64: call
; WIN64: ret
; X64-LABEL: test_float4
; X64: test_float4
; X64-NOT: vzeroupper
; X64: call
; X64-NOT: vzeroupper
; X64: call
; X64: ret
; X32-LABEL: test_float4
; X32: test_float4
; X32: vzeroupper
; X32: call
; X32: vzeroupper

10
llvm/test/CodeGen/X86/gcc_except_table.ll
View File

@ -13,14 +13,14 @@ define i32 @main() uwtable optsize ssp {
; APPLE: GCC_except_table0:
; APPLE: Lexception0:
; MINGW64: .seh_proc
; MINGW64: .seh_handler __gxx_personality_v0
; MINGW64: .seh_setframe 5, 0
; MINGW64: .cfi_startproc
; MINGW64: .cfi_personality 0, __gxx_personality_v0
; MINGW64: .cfi_lsda 0, .Lexception0
; MINGW64: .cfi_def_cfa_offset 16
; MINGW64: callq _Unwind_Resume
; MINGW64: .seh_handlerdata
; MINGW64: .cfi_endproc
; MINGW64: GCC_except_table0:
; MINGW64: Lexception0:
; MINGW64: .seh_endproc
; MINGW32: .cfi_startproc
; MINGW32: .cfi_personality 0, ___gxx_personality_v0

170
llvm/test/CodeGen/X86/win64_eh.ll
View File

@ -1,170 +0,0 @@
; RUN: llc < %s -O0 -mcpu=corei7 -mtriple=x86_64-pc-win32 | FileCheck %s -check-prefix=WIN64
; RUN: llc < %s -O0 -mcpu=corei7 -mtriple=x86_64-pc-mingw32 | FileCheck %s -check-prefix=WIN64
; Check function without prolog
define void @foo0() uwtable {
entry:
ret void
}
; WIN64-LABEL: foo0:
; WIN64: .seh_proc foo0
; WIN64: .seh_endprologue
; WIN64: ret
; WIN64: .seh_endproc
; Checks a small stack allocation
define void @foo1() uwtable {
entry:
%baz = alloca [2000 x i16], align 2
ret void
}
; WIN64-LABEL: foo1:
; WIN64: .seh_proc foo1
; WIN64: subq $4000, %rsp
; WIN64: .seh_stackalloc 4000
; WIN64: .seh_endprologue
; WIN64: addq $4000, %rsp
; WIN64: ret
; WIN64: .seh_endproc
; Checks a stack allocation requiring call to __chkstk/___chkstk_ms
define void @foo2() uwtable {
entry:
%baz = alloca [4000 x i16], align 2
ret void
}
; WIN64-LABEL: foo2:
; WIN64: .seh_proc foo2
; WIN64: movabsq $8000, %rax
; WIN64: callq {{__chkstk|___chkstk_ms}}
; WIN64: subq %rax, %rsp
; WIN64: .seh_stackalloc 8000
; WIN64: .seh_endprologue
; WIN64: addq $8000, %rsp
; WIN64: ret
; WIN64: .seh_endproc
; Checks stack push
define i32 @foo3(i32 %f_arg, i32 %e_arg, i32 %d_arg, i32 %c_arg, i32 %b_arg, i32 %a_arg) uwtable {
entry:
%a = alloca i32
%b = alloca i32
%c = alloca i32
%d = alloca i32
%e = alloca i32
%f = alloca i32
store i32 %a_arg, i32* %a
store i32 %b_arg, i32* %b
store i32 %c_arg, i32* %c
store i32 %d_arg, i32* %d
store i32 %e_arg, i32* %e
store i32 %f_arg, i32* %f
%tmp = load i32* %a
%tmp1 = mul i32 %tmp, 2
%tmp2 = load i32* %b
%tmp3 = mul i32 %tmp2, 3
%tmp4 = add i32 %tmp1, %tmp3
%tmp5 = load i32* %c
%tmp6 = mul i32 %tmp5, 5
%tmp7 = add i32 %tmp4, %tmp6
%tmp8 = load i32* %d
%tmp9 = mul i32 %tmp8, 7
%tmp10 = add i32 %tmp7, %tmp9
%tmp11 = load i32* %e
%tmp12 = mul i32 %tmp11, 11
%tmp13 = add i32 %tmp10, %tmp12
%tmp14 = load i32* %f
%tmp15 = mul i32 %tmp14, 13
%tmp16 = add i32 %tmp13, %tmp15
ret i32 %tmp16
}
; WIN64-LABEL: foo3:
; WIN64: .seh_proc foo3
; WIN64: pushq %rsi
; WIN64: .seh_pushreg 6
; WIN64: subq $24, %rsp
; WIN64: .seh_stackalloc 24
; WIN64: .seh_endprologue
; WIN64: addq $24, %rsp
; WIN64: popq %rsi
; WIN64: ret
; WIN64: .seh_endproc
; Check emission of eh handler and handler data
declare i32 @_d_eh_personality(i32, i32, i64, i8*, i8*)
declare void @_d_eh_resume_unwind(i8*)
declare i32 @bar()
define i32 @foo4() #0 {
entry:
%step = alloca i32, align 4
store i32 0, i32* %step
%tmp = load i32* %step
%tmp1 = invoke i32 @bar()
to label %finally unwind label %landingpad
finally:
store i32 1, i32* %step
br label %endtryfinally
landingpad:
%landing_pad = landingpad { i8*, i32 } personality i32 (i32, i32, i64, i8*, i8*)* @_d_eh_personality
cleanup
%tmp3 = extractvalue { i8*, i32 } %landing_pad, 0
store i32 2, i32* %step
call void @_d_eh_resume_unwind(i8* %tmp3)
unreachable
endtryfinally:
%tmp10 = load i32* %step
ret i32 %tmp10
}
; WIN64-LABEL: foo4:
; WIN64: .seh_proc foo4
; WIN64: .seh_handler _d_eh_personality, @unwind, @except
; WIN64: subq $56, %rsp
; WIN64: .seh_stackalloc 56
; WIN64: .seh_endprologue
; WIN64: addq $56, %rsp
; WIN64: ret
; WIN64: .seh_handlerdata
; WIN64: .seh_endproc
; Check stack re-alignment and xmm spilling
define void @foo5() uwtable {
entry:
%s = alloca i32, align 64
call void asm sideeffect "", "~{rbx},~{rdi},~{xmm6},~{xmm7}"()
ret void
}
; WIN64-LABEL: foo5:
; WIN64: .seh_proc foo5
; WIN64: pushq %rbp
; WIN64: .seh_pushreg 5
; WIN64: movq %rsp, %rbp
; WIN64: pushq %rdi
; WIN64: .seh_pushreg 7
; WIN64: pushq %rbx
; WIN64: .seh_pushreg 3
; WIN64: andq $-64, %rsp
; WIN64: subq $128, %rsp
; WIN64: .seh_stackalloc 48
; WIN64: .seh_setframe 5, 64
; WIN64: movaps %xmm7, -32(%rbp) # 16-byte Spill
; WIN64: movaps %xmm6, -48(%rbp) # 16-byte Spill
; WIN64: .seh_savexmm 6, 16
; WIN64: .seh_savexmm 7, 32
; WIN64: .seh_endprologue
; WIN64: movaps -48(%rbp), %xmm6 # 16-byte Reload
; WIN64: movaps -32(%rbp), %xmm7 # 16-byte Reload
; WIN64: leaq -16(%rbp), %rsp
; WIN64: popq %rbx
; WIN64: popq %rdi
; WIN64: popq %rbp
; WIN64: retq
; WIN64: .seh_endproc