Re-apply r211399, "Generate native unwind info on Win64" with a fix t…

…o ignore SEH pseudo ops in X86 JIT emitter.

--
This patch enables LLVM to emit Win64-native unwind info rather than
DWARF CFI.  It handles all corner cases (I hope), including stack
realignment.

Because the unwind info is not flexible enough to describe stack frames
with a gap of unknown size in the middle, such as the one caused by
stack realignment, I modified register spilling code to place all spills
into the fixed frame slots, so that they can be accessed relative to the
frame pointer.

Patch by Vadim Chugunov!

Reviewed By: rnk

Differential Revision: http://reviews.llvm.org/D4081

llvm-svn: 211691

llvm/include/llvm/CodeGen/MachineFrameInfo.h

@@ -484,6 +484,9 @@ class MachineFrameInfo {
   ///
   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.

llvm/include/llvm/MC/MCAsmInfo.h

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

llvm/include/llvm/Target/TargetFrameLowering.h

@@ -93,6 +93,19 @@ class TargetFrameLowering {
   /// 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.

llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp

@@ -77,9 +77,9 @@ void Win64Exception::beginFunction(const MachineFunction *MF) {
   if (!shouldEmitPersonality)
     return;
 
-  MCSymbol *GCCHandlerSym =
-    Asm->GetExternalSymbolSymbol("_GCC_specific_handler");
-  Asm->OutStreamer.EmitWin64EHHandler(GCCHandlerSym, true, true);
+  const MCSymbol *PersHandlerSym =
+      TLOF.getCFIPersonalitySymbol(Per, *Asm->Mang, Asm->TM, MMI);
+  Asm->OutStreamer.EmitWin64EHHandler(PersHandlerSym, true, true);
 
   Asm->OutStreamer.EmitLabel(Asm->GetTempSymbol("eh_func_begin",
                                                 Asm->getFunctionNumber()));
@@ -98,15 +98,8 @@ 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();
   }

llvm/lib/CodeGen/MachineFunction.cpp

@@ -578,6 +578,21 @@ int MachineFrameInfo::CreateFixedObject(uint64_t Size, int64_t SPOffset,
   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 {

llvm/lib/CodeGen/PrologEpilogInserter.cpp

@@ -268,51 +268,56 @@ void PEI::calculateCalleeSavedRegisters(MachineFunction &F) {
     }
   }
 
-  if (CSI.empty())
-    return;   // Early exit if no callee saved registers are modified!
-
-  unsigned NumFixedSpillSlots;
-  const TargetFrameLowering::SpillSlot *FixedSpillSlots =
-    TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots);
+  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!
+
+    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);
+
+      int FrameIdx;
+      if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) {
+        I->setFrameIdx(FrameIdx);
+        continue;
+      }
 
-  // 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);
+      // 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();
+
+        // 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);
+      }
 
-    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;
-
-    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);
-      if ((unsigned)FrameIdx < MinCSFrameIndex) MinCSFrameIndex = FrameIdx;
-      if ((unsigned)FrameIdx > MaxCSFrameIndex) MaxCSFrameIndex = FrameIdx;
-    } else {
-      // Spill it to the stack where we must.
-      FrameIdx = MFI->CreateFixedObject(RC->getSize(), FixedSlot->Offset, true);
-    }
-
-    I->setFrameIdx(FrameIdx);
   }
 
   MFI->setCalleeSavedInfo(CSI);

llvm/lib/MC/MCObjectFileInfo.cpp

@@ -649,11 +649,16 @@ 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.
-  LSDASection =
-    Ctx->getCOFFSection(".gcc_except_table",
-                        COFF::IMAGE_SCN_CNT_INITIALIZED_DATA |
-                        COFF::IMAGE_SCN_MEM_READ,
-                        SectionKind::getReadOnly());
+  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());
+  }
 
   // Debug info.
   COFFDebugSymbolsSection =

llvm/lib/MC/MCStreamer.cpp

@@ -504,6 +504,8 @@ 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);

llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp

@@ -143,8 +143,11 @@ 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;
 
@@ -158,17 +161,18 @@ 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;
 }

llvm/lib/Target/X86/X86CodeEmitter.cpp

@@ -1131,6 +1131,16 @@ void Emitter<CodeEmitter>::emitInstruction(MachineInstr &MI,
     case TargetOpcode::IMPLICIT_DEF:
     case TargetOpcode::KILL:
       break;
+
+    case X86::SEH_PushReg:
+    case X86::SEH_SaveReg:
+    case X86::SEH_SaveXMM:
+    case X86::SEH_StackAlloc:
+    case X86::SEH_SetFrame:
+    case X86::SEH_PushFrame:
+    case X86::SEH_EndPrologue:
+      break;
+
     case X86::MOVPC32r: {
       // This emits the "call" portion of this pseudo instruction.
       MCE.emitByte(BaseOpcode);