13 files changed, 133 insertions, 73 deletions
diff --git a/lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp b/lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp
index 8cab24c..caf84b6 100644
--- a/lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp
+++ b/lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp
@@ -26,6 +26,7 @@
 #include "llvm/Module.h"
 #include "llvm/Type.h"
 #include "llvm/Assembly/Writer.h"
+#include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCSectionMachO.h"
@@ -36,7 +37,6 @@
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/FormattedStream.h"
-#include "llvm/MC/MCAsmInfo.h"
 #include "llvm/Target/Mangler.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Target/TargetRegistry.h"
@@ -56,7 +56,11 @@ void X86AsmPrinter::PrintPICBaseSymbol() const {
 MCSymbol *X86AsmPrinter::GetGlobalValueSymbol(const GlobalValue *GV) const {
   SmallString<60> NameStr;
   Mang->getNameWithPrefix(NameStr, GV, false);
-  MCSymbol *Symb = OutContext.GetOrCreateSymbol(NameStr.str());
+  MCSymbol *Symb;
+  if (GV->hasPrivateLinkage())
+    Symb = OutContext.GetOrCreateTemporarySymbol(NameStr.str());
+  else
+    Symb = OutContext.GetOrCreateSymbol(NameStr.str());
 
   if (Subtarget->isTargetCygMing()) {
     X86COFFMachineModuleInfo &COFFMMI =
diff --git a/lib/Target/X86/AsmPrinter/X86MCInstLower.cpp b/lib/Target/X86/AsmPrinter/X86MCInstLower.cpp
index fa8d13d..b8a6eeb 100644
--- a/lib/Target/X86/AsmPrinter/X86MCInstLower.cpp
+++ b/lib/Target/X86/AsmPrinter/X86MCInstLower.cpp
@@ -89,7 +89,7 @@ GetSymbolFromOperand(const MachineOperand &MO) const {
   case X86II::MO_DARWIN_NONLAZY:
   case X86II::MO_DARWIN_NONLAZY_PIC_BASE: {
     Name += "$non_lazy_ptr";
-    MCSymbol *Sym = Ctx.GetOrCreateSymbol(Name.str());
+    MCSymbol *Sym = Ctx.GetOrCreateTemporarySymbol(Name.str());
 
     MCSymbol *&StubSym = getMachOMMI().getGVStubEntry(Sym);
     if (StubSym == 0) {
@@ -100,7 +100,7 @@ GetSymbolFromOperand(const MachineOperand &MO) const {
   }
   case X86II::MO_DARWIN_HIDDEN_NONLAZY_PIC_BASE: {
     Name += "$non_lazy_ptr";
-    MCSymbol *Sym = Ctx.GetOrCreateSymbol(Name.str());
+    MCSymbol *Sym = Ctx.GetOrCreateTemporarySymbol(Name.str());
     MCSymbol *&StubSym = getMachOMMI().getHiddenGVStubEntry(Sym);
     if (StubSym == 0) {
       assert(MO.isGlobal() && "Extern symbol not handled yet");
@@ -110,7 +110,7 @@ GetSymbolFromOperand(const MachineOperand &MO) const {
   }
   case X86II::MO_DARWIN_STUB: {
     Name += "$stub";
-    MCSymbol *Sym = Ctx.GetOrCreateSymbol(Name.str());
+    MCSymbol *Sym = Ctx.GetOrCreateTemporarySymbol(Name.str());
     MCSymbol *&StubSym = getMachOMMI().getFnStubEntry(Sym);
     if (StubSym)
       return Sym;
@@ -119,7 +119,7 @@ GetSymbolFromOperand(const MachineOperand &MO) const {
       StubSym = AsmPrinter.GetGlobalValueSymbol(MO.getGlobal());
     } else {
       Name.erase(Name.end()-5, Name.end());
-      StubSym = Ctx.GetOrCreateSymbol(Name.str());
+      StubSym = Ctx.GetOrCreateTemporarySymbol(Name.str());
     }
     return Sym;
   }
@@ -394,7 +394,8 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
     // However, we can't generate a ".", so just emit a new label here and refer
     // to it.  We know that this operand flag occurs at most once per function.
     const char *Prefix = MAI->getPrivateGlobalPrefix();
-    MCSymbol *DotSym = OutContext.GetOrCreateSymbol(Twine(Prefix)+"picbaseref"+
+    MCSymbol *DotSym = OutContext.GetOrCreateTemporarySymbol(Twine(Prefix)+
+                                                             "picbaseref" +
                                                     Twine(getFunctionNumber()));
     OutStreamer.EmitLabel(DotSym);
     
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 8384ab7..0cfcbb6 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -1105,8 +1105,8 @@ MCSymbol *
 X86TargetLowering::getPICBaseSymbol(const MachineFunction *MF,
                                     MCContext &Ctx) const {
   const MCAsmInfo &MAI = *getTargetMachine().getMCAsmInfo();
-  return Ctx.GetOrCreateSymbol(Twine(MAI.getPrivateGlobalPrefix())+
-                               Twine(MF->getFunctionNumber())+"$pb");
+  return Ctx.GetOrCreateTemporarySymbol(Twine(MAI.getPrivateGlobalPrefix())+
+                                        Twine(MF->getFunctionNumber())+"$pb");
 }
 
 
@@ -6418,24 +6418,13 @@ X86TargetLowering::LowerDYNAMIC_STACKALLOC(SDValue Op,
   EVT IntPtr = getPointerTy();
   EVT SPTy = Subtarget->is64Bit() ? MVT::i64 : MVT::i32;
 
-  Chain = DAG.getCALLSEQ_START(Chain, DAG.getIntPtrConstant(0, true));
-
   Chain = DAG.getCopyToReg(Chain, dl, X86::EAX, Size, Flag);
   Flag = Chain.getValue(1);
 
-  SDVTList  NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
-  SDValue Ops[] = { Chain,
-                      DAG.getTargetExternalSymbol("_alloca", IntPtr),
-                      DAG.getRegister(X86::EAX, IntPtr),
-                      DAG.getRegister(X86StackPtr, SPTy),
-                      Flag };
-  Chain = DAG.getNode(X86ISD::CALL, dl, NodeTys, Ops, 5);
-  Flag = Chain.getValue(1);
+  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Flag);
 
-  Chain = DAG.getCALLSEQ_END(Chain,
-                             DAG.getIntPtrConstant(0, true),
-                             DAG.getIntPtrConstant(0, true),
-                             Flag);
+  Chain = DAG.getNode(X86ISD::MINGW_ALLOCA, dl, NodeTys, Chain, Flag);
+  Flag = Chain.getValue(1);
 
   Chain = DAG.getCopyFromReg(Chain, dl, X86StackPtr, SPTy).getValue(1);
 
@@ -7741,6 +7730,7 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
   case X86ISD::MUL_IMM:            return "X86ISD::MUL_IMM";
   case X86ISD::PTEST:              return "X86ISD::PTEST";
   case X86ISD::VASTART_SAVE_XMM_REGS: return "X86ISD::VASTART_SAVE_XMM_REGS";
+  case X86ISD::MINGW_ALLOCA:       return "X86ISD::MINGW_ALLOCA";
   }
 }
 
@@ -8410,6 +8400,29 @@ X86TargetLowering::EmitLoweredSelect(MachineInstr *MI,
   return BB;
 }
 
+MachineBasicBlock *
+X86TargetLowering::EmitLoweredMingwAlloca(MachineInstr *MI,
+                                          MachineBasicBlock *BB,
+                   DenseMap<MachineBasicBlock*, MachineBasicBlock*> *EM) const {
+  const TargetInstrInfo *TII = getTargetMachine().getInstrInfo();
+  DebugLoc DL = MI->getDebugLoc();
+  MachineFunction *F = BB->getParent();
+
+  // The lowering is pretty easy: we're just emitting the call to _alloca.  The
+  // non-trivial part is impdef of ESP.
+  // FIXME: The code should be tweaked as soon as we'll try to do codegen for
+  // mingw-w64.
+
+  BuildMI(BB, DL, TII->get(X86::CALLpcrel32))
+    .addExternalSymbol("_alloca")
+    .addReg(X86::EAX, RegState::Implicit)
+    .addReg(X86::ESP, RegState::Implicit)
+    .addReg(X86::EAX, RegState::Define | RegState::Implicit)
+    .addReg(X86::ESP, RegState::Define | RegState::Implicit);
+
+  F->DeleteMachineInstr(MI);   // The pseudo instruction is gone now.
+  return BB;
+}
 
 MachineBasicBlock *
 X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI,
@@ -8417,6 +8430,8 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI,
                    DenseMap<MachineBasicBlock*, MachineBasicBlock*> *EM) const {
   switch (MI->getOpcode()) {
   default: assert(false && "Unexpected instr type to insert");
+  case X86::MINGW_ALLOCA:
+    return EmitLoweredMingwAlloca(MI, BB, EM);
   case X86::CMOV_GR8:
   case X86::CMOV_V1I64:
   case X86::CMOV_FR32:
diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index ffaf1cf..4c12fcc 100644
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -249,6 +249,9 @@ namespace llvm {
       // with control flow.
       VASTART_SAVE_XMM_REGS,
 
+      // MINGW_ALLOCA - MingW's __alloca call to do stack probing.
+      MINGW_ALLOCA,
+
       // ATOMADD64_DAG, ATOMSUB64_DAG, ATOMOR64_DAG, ATOMAND64_DAG, 
       // ATOMXOR64_DAG, ATOMNAND64_DAG, ATOMSWAP64_DAG - 
       // Atomic 64-bit binary operations.
@@ -259,6 +262,10 @@ namespace llvm {
       ATOMAND64_DAG,
       ATOMNAND64_DAG,
       ATOMSWAP64_DAG
+
+      // WARNING: Do not add anything in the end unless you want the node to
+      // have memop! In fact, starting from ATOMADD64_DAG all opcodes will be
+      // thought as target memory ops!
     };
   }
 
@@ -789,7 +796,11 @@ namespace llvm {
     MachineBasicBlock *EmitLoweredSelect(MachineInstr *I,
                                          MachineBasicBlock *BB,
                     DenseMap<MachineBasicBlock*, MachineBasicBlock*> *EM) const;
-    
+
+    MachineBasicBlock *EmitLoweredMingwAlloca(MachineInstr *MI,
+                                              MachineBasicBlock *BB,
+                    DenseMap<MachineBasicBlock*, MachineBasicBlock*> *EM) const;
+
     /// Emit nodes that will be selected as "test Op0,Op0", or something
     /// equivalent, for use with the given x86 condition code.
     SDValue EmitTest(SDValue Op0, unsigned X86CC, SelectionDAG &DAG);
diff --git a/lib/Target/X86/X86Instr64bit.td b/lib/Target/X86/X86Instr64bit.td
index 8462255..8e684c9 100644
--- a/lib/Target/X86/X86Instr64bit.td
+++ b/lib/Target/X86/X86Instr64bit.td
@@ -2473,7 +2473,7 @@ let isTwoAddress = 1 in {
 defm PINSRQ      : SS41I_insert64<0x22, "pinsrq">;
 
 // -disable-16bit support.
-def : Pat<(truncstorei16 (i64 imm:$src), addr:$dst),
+def : Pat<(truncstorei16 (i16 imm:$src), addr:$dst),
           (MOV16mi addr:$dst, imm:$src)>;
 def : Pat<(truncstorei16 GR64:$src, addr:$dst),
           (MOV16mr addr:$dst, (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit))>;
diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp
index 39bda04..4fd91bb 100644
--- a/lib/Target/X86/X86InstrInfo.cpp
+++ b/lib/Target/X86/X86InstrInfo.cpp
@@ -2525,6 +2525,11 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
     // Folding a V_SET0 or V_SETALLONES as a load, to ease register pressure.
     // Create a constant-pool entry and operands to load from it.
 
+    // Medium and large mode can't fold loads this way.
+    if (TM.getCodeModel() != CodeModel::Small &&
+        TM.getCodeModel() != CodeModel::Kernel)
+      return NULL;
+
     // x86-32 PIC requires a PIC base register for constant pools.
     unsigned PICBase = 0;
     if (TM.getRelocationModel() == Reloc::PIC_) {
diff --git a/lib/Target/X86/X86InstrInfo.td b/lib/Target/X86/X86InstrInfo.td
index d46b946..071c5aa 100644
--- a/lib/Target/X86/X86InstrInfo.td
+++ b/lib/Target/X86/X86InstrInfo.td
@@ -65,7 +65,7 @@ def SDT_X86VASTART_SAVE_XMM_REGS : SDTypeProfile<0, -1, [SDTCisVT<0, i8>,
 
 def SDTX86RepStr  : SDTypeProfile<0, 1, [SDTCisVT<0, OtherVT>]>;
 
-def SDTX86RdTsc   : SDTypeProfile<0, 0, []>;
+def SDTX86Void    : SDTypeProfile<0, 0, []>;
 
 def SDTX86Wrapper : SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>, SDTCisPtrTy<0>]>;
 
@@ -143,7 +143,7 @@ def X86rep_movs: SDNode<"X86ISD::REP_MOVS", SDTX86RepStr,
                         [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore,
                          SDNPMayLoad]>;
 
-def X86rdtsc   : SDNode<"X86ISD::RDTSC_DAG",SDTX86RdTsc,
+def X86rdtsc   : SDNode<"X86ISD::RDTSC_DAG", SDTX86Void,
                         [SDNPHasChain, SDNPOutFlag, SDNPSideEffect]>;
 
 def X86Wrapper    : SDNode<"X86ISD::Wrapper",     SDTX86Wrapper>;
@@ -178,6 +178,9 @@ def X86and_flag  : SDNode<"X86ISD::AND",  SDTBinaryArithWithFlags,
 
 def X86mul_imm : SDNode<"X86ISD::MUL_IMM", SDTIntBinOp>;
 
+def X86MingwAlloca : SDNode<"X86ISD::MINGW_ALLOCA", SDTX86Void,
+                            [SDNPHasChain, SDNPInFlag, SDNPOutFlag]>;
+
 //===----------------------------------------------------------------------===//
 // X86 Operand Definitions.
 //
@@ -519,7 +522,7 @@ def ADJCALLSTACKUP32   : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
 }
 
 // x86-64 va_start lowering magic.
-let usesCustomInserter = 1 in
+let usesCustomInserter = 1 in {
 def VASTART_SAVE_XMM_REGS : I<0, Pseudo,
                               (outs),
                               (ins GR8:$al,
@@ -530,6 +533,19 @@ def VASTART_SAVE_XMM_REGS : I<0, Pseudo,
                                                          imm:$regsavefi,
                                                          imm:$offset)]>;
 
+// Dynamic stack allocation yields _alloca call for Cygwin/Mingw targets.  Calls
+// to _alloca is needed to probe the stack when allocating more than 4k bytes in
+// one go. 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.
+// The main point of having separate instruction are extra unmodelled effects
+// (compared to ordinary calls) like stack pointer change.
+
+def MINGW_ALLOCA : I<0, Pseudo, (outs), (ins),
+                     "# dynamic stack allocation",
+                     [(X86MingwAlloca)]>;
+}
+
 // Nop
 let neverHasSideEffects = 1 in {
   def NOOP : I<0x90, RawFrm, (outs), (ins), "nop", []>;
@@ -2631,6 +2647,17 @@ def ADD32rr  : I<0x01, MRMDestReg, (outs GR32:$dst),
 } // end isConvertibleToThreeAddress
 } // end isCommutable
 
+// These are alternate spellings for use by the disassembler, we mark them as
+// code gen only to ensure they aren't matched by the assembler.
+let isCodeGenOnly = 1 in {
+  def ADD8rr_alt: I<0x02, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2),
+                   "add{b}\t{$src2, $dst|$dst, $src2}", []>;
+  def ADD16rr_alt: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
+                    "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize;
+  def ADD32rr_alt: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
+                    "add{l}\t{$src2, $dst|$dst, $src2}", []>;
+}
+
 // Register-Memory Addition
 def ADD8rm   : I<0x02, MRMSrcMem, (outs GR8 :$dst),
                                   (ins GR8 :$src1, i8mem :$src2),
@@ -2648,15 +2675,6 @@ def ADD32rm  : I<0x03, MRMSrcMem, (outs GR32:$dst),
                  [(set GR32:$dst, (add GR32:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>;
                   
-// Register-Register Addition - Equivalent to the normal rr forms (ADD8rr, 
-//   ADD16rr, and ADD32rr), but differently encoded.
-def ADD8mrmrr: I<0x02, MRMSrcReg, (outs GR8:$dst), (ins GR8:$src1, GR8:$src2),
-                 "add{b}\t{$src2, $dst|$dst, $src2}", []>;
-def ADD16mrmrr: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
-                  "add{w}\t{$src2, $dst|$dst, $src2}", []>, OpSize;
-def ADD32mrmrr: I<0x03, MRMSrcReg,(outs GR16:$dst),(ins GR16:$src1, GR16:$src2),
-                  "add{l}\t{$src2, $dst|$dst, $src2}", []>;
-
 // Register-Integer Addition
 def ADD8ri    : Ii8<0x80, MRM0r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
                     "add{b}\t{$src2, $dst|$dst, $src2}",
@@ -3119,16 +3137,16 @@ def IMUL32rmi8 : Ii8<0x6B, MRMSrcMem,                       // GR32 = [mem32]*I8
 //
 let Defs = [EFLAGS] in {
 let isCommutable = 1 in {   // TEST X, Y   --> TEST Y, X
-def TEST8rr  : I<0x84, MRMDestReg, (outs),  (ins GR8:$src1, GR8:$src2),
+def TEST8rr  : I<0x84, MRMSrcReg, (outs),  (ins GR8:$src1, GR8:$src2),
                      "test{b}\t{$src2, $src1|$src1, $src2}",
                      [(X86cmp (and_su GR8:$src1, GR8:$src2), 0),
                       (implicit EFLAGS)]>;
-def TEST16rr : I<0x85, MRMDestReg, (outs),  (ins GR16:$src1, GR16:$src2),
+def TEST16rr : I<0x85, MRMSrcReg, (outs),  (ins GR16:$src1, GR16:$src2),
                      "test{w}\t{$src2, $src1|$src1, $src2}",
                      [(X86cmp (and_su GR16:$src1, GR16:$src2), 0),
                       (implicit EFLAGS)]>,
                  OpSize;
-def TEST32rr : I<0x85, MRMDestReg, (outs),  (ins GR32:$src1, GR32:$src2),
+def TEST32rr : I<0x85, MRMSrcReg, (outs),  (ins GR32:$src1, GR32:$src2),
                      "test{l}\t{$src2, $src1|$src1, $src2}",
                      [(X86cmp (and_su GR32:$src1, GR32:$src2), 0),
                       (implicit EFLAGS)]>;
@@ -3437,12 +3455,18 @@ def CMP32rm : I<0x3B, MRMSrcMem,
                 "cmp{l}\t{$src2, $src1|$src1, $src2}",
                 [(X86cmp GR32:$src1, (loadi32 addr:$src2)),
                  (implicit EFLAGS)]>;
-def CMP8mrmrr : I<0x3A, MRMSrcReg, (outs), (ins GR8:$src1, GR8:$src2),
-                  "cmp{b}\t{$src2, $src1|$src1, $src2}", []>;
-def CMP16mrmrr : I<0x3B, MRMSrcReg, (outs), (ins GR16:$src1, GR16:$src2),
-                   "cmp{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize;
-def CMP32mrmrr : I<0x3B, MRMSrcReg, (outs), (ins GR32:$src1, GR32:$src2),
-                   "cmp{l}\t{$src2, $src1|$src1, $src2}", []>;
+
+// These are alternate spellings for use by the disassembler, we mark them as
+// code gen only to ensure they aren't matched by the assembler.
+let isCodeGenOnly = 1 in {
+  def CMP8rr_alt : I<0x3A, MRMSrcReg, (outs), (ins GR8:$src1, GR8:$src2),
+                    "cmp{b}\t{$src2, $src1|$src1, $src2}", []>;
+  def CMP16rr_alt : I<0x3B, MRMSrcReg, (outs), (ins GR16:$src1, GR16:$src2),
+                     "cmp{w}\t{$src2, $src1|$src1, $src2}", []>, OpSize;
+  def CMP32rr_alt : I<0x3B, MRMSrcReg, (outs), (ins GR32:$src1, GR32:$src2),
+                     "cmp{l}\t{$src2, $src1|$src1, $src2}", []>;
+}
+
 def CMP8ri  : Ii8<0x80, MRM7r,
                   (outs), (ins GR8:$src1, i8imm:$src2),
                   "cmp{b}\t{$src2, $src1|$src1, $src2}",
@@ -4236,7 +4260,7 @@ def VMWRITE32rr : I<0x79, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src),
 // 0F 01 C4
 def VMXOFF : I<0x01, MRM_C4, (outs), (ins), "vmxoff", []>, TB;
 def VMXON : I<0xC7, MRM6m, (outs), (ins i64mem:$vmxon),
-  "vmxon\t{$vmxon}", []>, XD;
+  "vmxon\t{$vmxon}", []>, XS;
 
 //===----------------------------------------------------------------------===//
 // Non-Instruction Patterns
@@ -5134,7 +5158,7 @@ def : Pat<(parallel (store (X86and_flag (loadi32 addr:$dst), i32immSExt8:$src2),
           (AND32mi8 addr:$dst, i32immSExt8:$src2)>;
 
 // -disable-16bit support.
-def : Pat<(truncstorei16 (i32 imm:$src), addr:$dst),
+def : Pat<(truncstorei16 (i16 imm:$src), addr:$dst),
           (MOV16mi addr:$dst, imm:$src)>;
 def : Pat<(truncstorei16 GR32:$src, addr:$dst),
           (MOV16mr addr:$dst, (EXTRACT_SUBREG GR32:$src, x86_subreg_16bit))>;
diff --git a/lib/Target/X86/X86InstrMMX.td b/lib/Target/X86/X86InstrMMX.td
index c8e0723..eea0eb8 100644
--- a/lib/Target/X86/X86InstrMMX.td
+++ b/lib/Target/X86/X86InstrMMX.td
@@ -160,7 +160,8 @@ def MMX_MOVQ2DQrr : SSDIi8<0xD6, MRMSrcReg, (outs VR128:$dst), (ins VR64:$src),
                            "movq2dq\t{$src, $dst|$dst, $src}",
           [(set VR128:$dst,
             (movl immAllZerosV,
-                  (v2i64 (scalar_to_vector (i64 (bitconvert VR64:$src))))))]>;
+                  (v2i64 (scalar_to_vector
+                              (i64 (bitconvert (v1i64 VR64:$src)))))))]>;
 
 let neverHasSideEffects = 1 in
 def MMX_MOVQ2FR64rr: SSDIi8<0xD6, MRMSrcReg, (outs FR64:$dst), (ins VR64:$src),
@@ -271,9 +272,9 @@ defm MMX_PSRAD : MMXI_binop_rmi_int<0xE2, 0x72, MRM4r, "psrad",
 
 // Shift up / down and insert zero's.
 def : Pat<(v1i64 (X86vshl     VR64:$src, (i8 imm:$amt))),
-          (v1i64 (MMX_PSLLQri VR64:$src, imm:$amt))>;
+          (MMX_PSLLQri VR64:$src, imm:$amt)>;
 def : Pat<(v1i64 (X86vshr     VR64:$src, (i8 imm:$amt))),
-          (v1i64 (MMX_PSRLQri VR64:$src, imm:$amt))>;
+          (MMX_PSRLQri VR64:$src, imm:$amt)>;
 
 // Comparison Instructions
 defm MMX_PCMPEQB : MMXI_binop_rm_int<0x74, "pcmpeqb", int_x86_mmx_pcmpeq_b>;
@@ -577,7 +578,7 @@ let AddedComplexity = 20 in {
 // Clear top half.
 let AddedComplexity = 15 in {
   def : Pat<(v2i32 (X86vzmovl VR64:$src)),
-            (MMX_PUNPCKLDQrr VR64:$src, (MMX_V_SET0))>;
+            (MMX_PUNPCKLDQrr VR64:$src, (v2i32 (MMX_V_SET0)))>;
 }
 
 // Patterns to perform canonical versions of vector shuffling.
diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index 2743dba..bd6e1b8 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -385,7 +385,7 @@ def MOVSSrr : SSI<0x10, MRMSrcReg,
 // Extract the low 32-bit value from one vector and insert it into another.
 let AddedComplexity = 15 in
 def : Pat<(v4f32 (movl VR128:$src1, VR128:$src2)),
-          (MOVSSrr VR128:$src1,
+          (MOVSSrr (v4f32 VR128:$src1),
                    (EXTRACT_SUBREG (v4f32 VR128:$src2), x86_subreg_ss))>;
 
 // Implicitly promote a 32-bit scalar to a vector.
@@ -827,7 +827,7 @@ let Constraints = "$src1 = $dst" in {
 
 
 def : Pat<(movlhps VR128:$src1, (bc_v4i32 (v2i64 (X86vzload addr:$src2)))),
-          (MOVHPSrm VR128:$src1, addr:$src2)>;
+          (MOVHPSrm (v4i32 VR128:$src1), addr:$src2)>;
 
 def MOVLPSmr : PSI<0x13, MRMDestMem, (outs), (ins f64mem:$dst, VR128:$src),
                    "movlps\t{$src, $dst|$dst, $src}",
@@ -860,9 +860,9 @@ def MOVHLPSrr : PSI<0x12, MRMSrcReg, (outs VR128:$dst),
 
 let AddedComplexity = 20 in {
 def : Pat<(v4f32 (movddup VR128:$src, (undef))),
-          (MOVLHPSrr VR128:$src, VR128:$src)>;
+          (MOVLHPSrr (v4f32 VR128:$src), (v4f32 VR128:$src))>;
 def : Pat<(v2i64 (movddup VR128:$src, (undef))),
-          (MOVLHPSrr VR128:$src, VR128:$src)>;
+          (MOVLHPSrr (v2i64 VR128:$src), (v2i64 VR128:$src))>;
 }
 
 
@@ -1011,9 +1011,9 @@ let Constraints = "$src1 = $dst" in {
                                             (memop addr:$src), imm:$cc))]>;
 }
 def : Pat<(v4i32 (X86cmpps (v4f32 VR128:$src1), VR128:$src2, imm:$cc)),
-          (CMPPSrri VR128:$src1, VR128:$src2, imm:$cc)>;
+          (CMPPSrri (v4f32 VR128:$src1), (v4f32 VR128:$src2), imm:$cc)>;
 def : Pat<(v4i32 (X86cmpps (v4f32 VR128:$src1), (memop addr:$src2), imm:$cc)),
-          (CMPPSrmi VR128:$src1, addr:$src2, imm:$cc)>;
+          (CMPPSrmi (v4f32 VR128:$src1), addr:$src2, imm:$cc)>;
 
 // Shuffle and unpack instructions
 let Constraints = "$src1 = $dst" in {
@@ -1090,9 +1090,6 @@ def MOVNTDQ_64mr : PDI<0xE7, MRMDestMem, (outs), (ins f128mem:$dst, VR128:$src),
                     "movntdq\t{$src, $dst|$dst, $src}",
                     [(alignednontemporalstore (v2f64 VR128:$src), addr:$dst)]>;
 
-def : Pat<(alignednontemporalstore (v2i64 VR128:$src), addr:$dst),
-          (MOVNTDQ_64mr VR128:$src, addr:$dst)>;
-
 def MOVNTImr : I<0xC3, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src),
                  "movnti\t{$src, $dst|$dst, $src}",
                  [(nontemporalstore (i32 GR32:$src), addr:$dst)]>,
@@ -1150,7 +1147,7 @@ def MOVSDrr : SDI<0x10, MRMSrcReg,
 // Extract the low 64-bit value from one vector and insert it into another.
 let AddedComplexity = 15 in
 def : Pat<(v2f64 (movl VR128:$src1, VR128:$src2)),
-          (MOVSDrr VR128:$src1,
+          (MOVSDrr (v2f64 VR128:$src1),
                    (EXTRACT_SUBREG (v2f64 VR128:$src2), x86_subreg_sd))>;
 
 // Implicitly promote a 64-bit scalar to a vector.
@@ -2394,9 +2391,6 @@ def MOVNTPDmr : PDI<0x2B, MRMDestMem, (outs), (ins f128mem:$dst, VR128:$src),
 def MOVNTDQmr : PDI<0xE7, MRMDestMem, (outs), (ins f128mem:$dst, VR128:$src),
                     "movntdq\t{$src, $dst|$dst, $src}",
                     [(alignednontemporalstore (v4f32 VR128:$src), addr:$dst)]>;
-
-def : Pat<(alignednontemporalstore (v4i32 VR128:$src), addr:$dst),
-          (MOVNTDQmr VR128:$src, addr:$dst)>;
 }
 
 // Flush cache
diff --git a/lib/Target/X86/X86MCAsmInfo.cpp b/lib/Target/X86/X86MCAsmInfo.cpp
index 250634f..9498810 100644
--- a/lib/Target/X86/X86MCAsmInfo.cpp
+++ b/lib/Target/X86/X86MCAsmInfo.cpp
@@ -68,7 +68,6 @@ X86MCAsmInfoDarwin::X86MCAsmInfoDarwin(const Triple &Triple) {
 
   // Exceptions handling
   ExceptionsType = ExceptionHandling::Dwarf;
-  AbsoluteEHSectionOffsets = false;
 }
 
 X86ELFMCAsmInfo::X86ELFMCAsmInfo(const Triple &Triple) {
@@ -90,7 +89,6 @@ X86ELFMCAsmInfo::X86ELFMCAsmInfo(const Triple &Triple) {
 
   // Exceptions handling
   ExceptionsType = ExceptionHandling::Dwarf;
-  AbsoluteEHSectionOffsets = false;
 }
 
 MCSection *X86ELFMCAsmInfo::getNonexecutableStackSection(MCContext &Ctx) const {
diff --git a/lib/Target/X86/X86RegisterInfo.cpp b/lib/Target/X86/X86RegisterInfo.cpp
index 946d6b2..cdb579c 100644
--- a/lib/Target/X86/X86RegisterInfo.cpp
+++ b/lib/Target/X86/X86RegisterInfo.cpp
@@ -589,7 +589,7 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
 
 unsigned
 X86RegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II,
-                                     int SPAdj, int *Value,
+                                     int SPAdj, FrameIndexValue *Value,
                                      RegScavenger *RS) const{
   assert(SPAdj == 0 && "Unexpected");
 
@@ -1057,7 +1057,8 @@ void X86RegisterInfo::emitPrologue(MachineFunction &MF) const {
       BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
         .addImm(NumBytes);
       BuildMI(MBB, MBBI, DL, TII.get(X86::CALLpcrel32))
-        .addExternalSymbol("_alloca");
+        .addExternalSymbol("_alloca")
+        .addReg(StackPtr, RegState::Define | RegState::Implicit);
     } else {
       // Save EAX
       BuildMI(MBB, MBBI, DL, TII.get(X86::PUSH32r))
@@ -1068,7 +1069,8 @@ void X86RegisterInfo::emitPrologue(MachineFunction &MF) const {
       BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
         .addImm(NumBytes - 4);
       BuildMI(MBB, MBBI, DL, TII.get(X86::CALLpcrel32))
-        .addExternalSymbol("_alloca");
+        .addExternalSymbol("_alloca")
+        .addReg(StackPtr, RegState::Define | RegState::Implicit);
 
       // Restore EAX
       MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
diff --git a/lib/Target/X86/X86RegisterInfo.h b/lib/Target/X86/X86RegisterInfo.h
index e4bdb4e..12b2f3e 100644
--- a/lib/Target/X86/X86RegisterInfo.h
+++ b/lib/Target/X86/X86RegisterInfo.h
@@ -143,7 +143,7 @@ public:
                                      MachineBasicBlock::iterator MI) const;
 
   unsigned eliminateFrameIndex(MachineBasicBlock::iterator MI,
-                               int SPAdj, int *Value = NULL,
+                               int SPAdj, FrameIndexValue *Value = NULL,
                                RegScavenger *RS = NULL) const;
 
   void processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
diff --git a/lib/Target/X86/X86TargetObjectFile.cpp b/lib/Target/X86/X86TargetObjectFile.cpp
index 29a0be5..c80ae19 100644
--- a/lib/Target/X86/X86TargetObjectFile.cpp
+++ b/lib/Target/X86/X86TargetObjectFile.cpp
@@ -20,14 +20,19 @@ using namespace dwarf;
 
 const MCExpr *X8664_MachoTargetObjectFile::
 getSymbolForDwarfGlobalReference(const GlobalValue *GV, Mangler *Mang,
-                           MachineModuleInfo *MMI, unsigned Encoding) const {
+                                 MachineModuleInfo *MMI, 
+                                 unsigned Encoding) const {
 
   // On Darwin/X86-64, we can reference dwarf symbols with foo@GOTPCREL+4, which
   // is an indirect pc-relative reference.
   if (Encoding & (DW_EH_PE_indirect | DW_EH_PE_pcrel)) {
     SmallString<128> Name;
     Mang->getNameWithPrefix(Name, GV, false);
-    const MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
+    const MCSymbol *Sym;
+    if (GV->hasPrivateLinkage())
+      Sym = getContext().GetOrCreateTemporarySymbol(Name);
+    else
+      Sym = getContext().GetOrCreateSymbol(Name);
     const MCExpr *Res =
       X86MCTargetExpr::Create(Sym, X86MCTargetExpr::GOTPCREL, getContext());
     const MCExpr *Four = MCConstantExpr::Create(4, getContext());