Update comments to use unreachable instead of llvm.trap, as implemented now

[rnk]

Summary

win64: Call __chkstk through a register with the large code model

Fixes half of PR18582. True dynamic allocas will still have a
CALL64pcrel32 which will fail.

[majnemer]

LGTM

llvm/trunk/lib/Target/X86/X86FrameLowering.h

 class X86TargetMachine;
 class X86Subtarget;
 
 class X86FrameLowering : public TargetFrameLowering {
 public:
   explicit X86FrameLowering(StackDirection D, unsigned StackAl, int LAO)
     : TargetFrameLowering(StackGrowsDown, StackAl, LAO) {}
 
-  static void getStackProbeFunction(const X86Subtarget &STI,
-                                    unsigned &CallOp,
+  static void getStackProbeFunction(const MachineFunction &MF,
+                                    const X86Subtarget &STI, unsigned &CallOp,
                                     const char *&Symbol);
 
   void emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
                                  MachineBasicBlock::iterator MBBI,
                                  DebugLoc DL) const;
 
   /// emitProlog/emitEpilog - These methods insert prolog and epilog code into
   /// the function.

llvm/trunk/lib/Target/X86/X86FrameLowering.cpp

for (MachineRegisterInfo::reg_instr_iterator
        ri = MRI.reg_instr_begin(X86::EFLAGS), re = MRI.reg_instr_end();
        ri != re; ++ri)
     if (ri->isCopy())
       return true;
 
   return false;
 }
 
-void X86FrameLowering::getStackProbeFunction(const X86Subtarget &STI,
+void X86FrameLowering::getStackProbeFunction(const MachineFunction &MF,
+                                             const X86Subtarget &STI,
                                              unsigned &CallOp,
                                              const char *&Symbol) {
-  CallOp = STI.is64Bit() ? X86::W64ALLOCA : X86::CALLpcrel32;
+  if (STI.is64Bit())
+    CallOp = MF.getTarget().getCodeModel() == CodeModel::Large
+                 ? X86::CALL64r
+                 : X86::W64ALLOCA;
+  else
+    CallOp = X86::CALLpcrel32;
 
   if (STI.is64Bit()) {
     if (STI.isTargetCygMing()) {
       Symbol = "___chkstk_ms";
     } else {
       Symbol = "__chkstk";
     }
   } else if (STI.isTargetCygMing())
void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
   // __chkstk is only responsible for probing the stack.  The 64-bit prologue is
   // 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 >= StackProbeSize && UseStackProbe) {
     const char *StackProbeSymbol;
     unsigned CallOp;
 
-    getStackProbeFunction(STI, CallOp, StackProbeSymbol);
+    getStackProbeFunction(MF, STI, CallOp, StackProbeSymbol);
 
     // Check whether EAX is livein for this function.
     bool isEAXAlive = isEAXLiveIn(MF);
 
     if (isEAXAlive) {
       // Sanity check that EAX is not livein for this function.
       // It should not be, so throw an assert.
       assert(!Is64Bit && "EAX is livein in x64 case!");
if (NumBytes >= StackProbeSize && UseStackProbe) {
     } else {
       // Allocate NumBytes-4 bytes on stack in case of isEAXAlive.
       // We'll also use 4 already allocated bytes for EAX.
       BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
         .addImm(isEAXAlive ? NumBytes - 4 : NumBytes)
         .setMIFlag(MachineInstr::FrameSetup);
     }
 
-    BuildMI(MBB, MBBI, DL,
-            TII.get(CallOp))
+    if (Is64Bit && MF.getTarget().getCodeModel() == CodeModel::Large) {
+      // For the large code model, we have to call through a register. Use R11,
+      // as it is unused and clobbered by all probe functions.
+      BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::R11)
+          .addExternalSymbol(StackProbeSymbol);
+      BuildMI(MBB, MBBI, DL, TII.get(CallOp))
+          .addReg(X86::R11)
+          .addReg(StackPtr, RegState::Define | RegState::Implicit)
+          .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
+          .setMIFlag(MachineInstr::FrameSetup);
+    } else {
+      BuildMI(MBB, MBBI, DL, TII.get(CallOp))
           .addExternalSymbol(StackProbeSymbol)
-      .addReg(StackPtr,    RegState::Define | RegState::Implicit)
+          .addReg(StackPtr, RegState::Define | RegState::Implicit)
           .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
           .setMIFlag(MachineInstr::FrameSetup);
+    }
 
     if (Is64Bit) {
       // MSVC x64's __chkstk and cygwin/mingw's ___chkstk_ms do not adjust %rsp
       // themself. It also does not clobber %rax so we can reuse it when
       // adjusting %rsp.
       BuildMI(MBB, MBBI, DL, TII.get(X86::SUB64rr), StackPtr)
         .addReg(StackPtr)
         .addReg(X86::RAX)

llvm/trunk/lib/Target/X86/X86InstrControl.td

def CALL64m       : I<0xFF, MRM2m, (outs), (ins i64mem:$dst),
                         IIC_CALL_MEM>,
                       Requires<[In64BitMode,FavorMemIndirectCall]>;
 
   def FARCALL64   : RI<0xFF, MRM3m, (outs), (ins opaque80mem:$dst),
                        "lcall{q}\t{*}$dst", [], IIC_CALL_FAR_MEM>;
 }
 
 let isCall = 1, isCodeGenOnly = 1 in
-  // __chkstk(MSVC):     clobber R10, R11 and EFLAGS.
+  // __chkstk(MSVC):     clobber R10, R11 and EFLAGS
+  // ___chkstk_ms(Mingw64): clobber R10, R11 and EFLAGS
   // ___chkstk(Mingw64): clobber R10, R11, RAX and EFLAGS, and update RSP.
   let Defs = [RAX, R10, R11, RSP, EFLAGS],
       Uses = [RSP] in {
     def W64ALLOCA : Ii32PCRel<0xE8, RawFrm,
                       (outs), (ins i64i32imm_pcrel:$dst),
                       "call{q}\t$dst", [], IIC_CALL_RI>,
                     Requires<[IsWin64]>, Sched<[WriteJump]>;
   }

llvm/trunk/test/CodeGen/X86/win_chkstk.ll

 ; RUN: llc < %s -mtriple=i686-pc-win32 | FileCheck %s -check-prefix=WIN_X32
 ; RUN: llc < %s -mtriple=x86_64-pc-win32 | FileCheck %s -check-prefix=WIN_X64
+; RUN: llc < %s -mtriple=x86_64-pc-win32 -code-model=large | FileCheck %s -check-prefix=WIN64_LARGE
 ; RUN: llc < %s -mtriple=i686-pc-mingw32 | FileCheck %s -check-prefix=MINGW_X32
 ; RUN: llc < %s -mtriple=x86_64-pc-mingw32 | FileCheck %s -check-prefix=MINGW_X64
 ; RUN: llc < %s -mtriple=i386-pc-linux | FileCheck %s -check-prefix=LINUX
 ; RUN: llc < %s -mtriple=x86_64-pc-win32-macho | FileCheck %s -check-prefix=LINUX
 
 ; Windows and mingw require a prologue helper routine if more than 4096 bytes area
 ; allocated on the stack.  Windows uses __chkstk and mingw uses __alloca.  __alloca
 ; and the 32-bit version of __chkstk will probe the stack and adjust the stack pointer.
 ; The 64-bit version of __chkstk is only responsible for probing the stack.  The 64-bit
 ; prologue is responsible for adjusting the stack pointer.
 
 ; Stack allocation >= 4096 bytes will require call to __chkstk in the Windows ABI.
 define i32 @main4k() nounwind {
 entry:
 ; WIN_X32:    calll __chkstk
 ; WIN_X64:    callq __chkstk
+; WIN64_LARGE: movabsq $__chkstk, %r11
+; WIN64_LARGE: callq *%r11
 ; MINGW_X32:  calll __alloca
 ; MINGW_X64:  callq ___chkstk_ms
 ; LINUX-NOT:  call __chkstk
   %array4096 = alloca [4096 x i8], align 16       ; <[4096 x i8]*> [#uses=0]
   ret i32 0
 }
 
 ; Make sure we don't call __chkstk or __alloca when we have less than a 4096 stack

 }
 
 ; Make sure we don't call __chkstk or __alloca on non-Windows even if the
 ; caller has the Win64 calling convention.
 define x86_64_win64cc i32 @main4k_win64() nounwind {
 entry:
 ; WIN_X32:    calll __chkstk
 ; WIN_X64:    callq __chkstk
+; WIN64_LARGE: movabsq $__chkstk, %r11
+; WIN64_LARGE: callq *%r11
 ; MINGW_X32:  calll __alloca
 ; MINGW_X64:  callq ___chkstk_ms
 ; LINUX-NOT:  call __chkstk
   %array4096 = alloca [4096 x i8], align 16       ; <[4096 x i8]*> [#uses=0]
   ret i32 0
 }