vmkit/vmkit-llvm-svn.patch

Index: include/llvm/Target/TargetOptions.h
===================================================================
--- include/llvm/Target/TargetOptions.h	(revision 48143)
+++ include/llvm/Target/TargetOptions.h	(working copy)
@@ -74,10 +74,15 @@
   /// be emitted.
   extern bool ExceptionHandling;
 
+  /// SizedMemoryCode - This flags indicates that memory for code is allocated by
+  /// an external allocator which requires the size to allocate
+  extern bool SizedMemoryCode;
+
   /// PerformTailCallOpt - This flag is enabled when -tailcallopt is specified
   /// on the commandline. When the flag is on, the target will perform tail call
   /// optimization (pop the caller's stack) providing it supports it.
   extern bool PerformTailCallOpt;
+
 } // End llvm namespace
 
 #endif
Index: include/llvm/CodeGen/SizeEmitter.h
===================================================================
--- include/llvm/CodeGen/SizeEmitter.h	(revision 0)
+++ include/llvm/CodeGen/SizeEmitter.h	(revision 0)
@@ -0,0 +1,116 @@
+//===-- llvm/CodeGen/MachineCodeEmitter.h - Code emission -------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file was developed by the LLVM research group and is distributed under
+// the University of Illinois Open Source License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines an abstract interface that is used by the machine code
+// emission framework to output the code.  This allows machine code emission to
+// be separated from concerns such as resolution of call targets, and where the
+// machine code will be written (memory or disk, f.e.).
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_SIZEEMITTER_H
+#define LLVM_CODEGEN_SIZEEMITTER_H
+
+#include "llvm/CodeGen/MachineCodeEmitter.h"
+#include "llvm/CodeGen/MachineFunction.h"
+
+namespace llvm {
+  /// SizeEmitter - The JIT implementation of the MachineCodeEmitter, which is
+  /// used to output functions to memory for execution.
+class SizeEmitter : public MachineCodeEmitter {
+  MachineFunction * Fn;
+  void* ConstantPoolBase;
+  void* JumpTableBase;
+  MachineConstantPool *ConstantPool;
+  MachineJumpTableInfo *JumpTable;
+  std::vector<intptr_t> LabelLocations;
+  MachineCodeEmitter* MCE;
+
+public:
+  SizeEmitter(MachineCodeEmitter* mce) { 
+    CurBufferPtr = 0; 
+    BufferBegin = 0; 
+    BufferEnd = (unsigned char*)-1;
+    MCE = mce;
+  }
+
+  SizeEmitter(std::vector<intptr_t> locations) {
+    LabelLocations = locations;
+    CurBufferPtr = 0; 
+    BufferBegin = 0; 
+    BufferEnd = (unsigned char*)-1;
+  }
+  
+  void initConstantPool(MachineConstantPool *MCP);
+
+  void initJumpTableInfo(MachineJumpTableInfo *MJTI);
+
+
+  virtual void startFunction(MachineFunction &F) { 
+    CurBufferPtr = 0; 
+    Fn = &F;
+  
+    // Ensure the constant pool/jump table info is at least 4-byte aligned.
+    emitAlignment(16);
+
+    initConstantPool(F.getConstantPool());
+    initJumpTableInfo(F.getJumpTableInfo());
+   
+    ConstantPoolBase  = (void*)(((unsigned) ConstantPoolBase) + CurBufferPtr);
+    JumpTableBase     = (void*)(((unsigned) JumpTableBase) + CurBufferPtr);
+  }
+
+  virtual bool finishFunction(MachineFunction &F) { 
+    MCE->setCurrentPtr(CurBufferPtr);
+    return false;
+  }
+  virtual void startFunctionStub(unsigned StubSize, unsigned Alignment) {}
+  virtual void *finishFunctionStub(const Function *F) { return 0; }
+  virtual void addRelocation(const llvm::MachineRelocation&) { }
+  virtual void emitByte(unsigned char B) {
+    CurBufferPtr++;
+  }
+  virtual void emitWordLE(unsigned W) {
+    CurBufferPtr+=4;
+  }   
+  virtual void emitWordBE(unsigned W) {
+    CurBufferPtr+=4;
+  }
+  virtual void emitInt32(int Value) {
+    CurBufferPtr += 4;
+  }
+  virtual void emitInt64(uint64_t Value) {
+    CurBufferPtr += 8;
+  }
+  virtual void emitAt(uintptr_t *Addr, uintptr_t Value) {
+  }  
+
+
+
+  virtual void StartMachineBasicBlock(MachineBasicBlock *MBB) {}
+  virtual intptr_t getConstantPoolEntryAddress(unsigned ConstantNum) const;
+
+  virtual intptr_t getJumpTableEntryAddress(unsigned Index) const;
+
+  virtual intptr_t getMachineBasicBlockAddress(MachineBasicBlock *MBB) const {
+    assert(0 && "Should not be in getMachineBasicBlockAddress of SizeEmitter");
+  }
+  
+  virtual void emitLabel(uint64_t) {}
+  virtual intptr_t getLabelAddress(uint64_t LabelID) const {
+    assert(LabelLocations.size() > (unsigned)LabelID && 
+             LabelLocations[LabelID] && "Label not emitted!");
+      return LabelLocations[LabelID];
+  }
+  virtual void setModuleInfo(llvm::MachineModuleInfo*) {}
+};
+
+} // end llvm namespace
+
+#endif
Index: include/llvm/CodeGen/MachineCodeEmitter.h
===================================================================
--- include/llvm/CodeGen/MachineCodeEmitter.h	(revision 48143)
+++ include/llvm/CodeGen/MachineCodeEmitter.h	(working copy)
@@ -18,6 +18,7 @@
 #define LLVM_CODEGEN_MACHINECODEEMITTER_H
 
 #include "llvm/Support/DataTypes.h"
+#include <string>
 #include <vector>
 
 namespace llvm {
@@ -92,7 +93,7 @@
   /// emitByte - This callback is invoked when a byte needs to be written to the
   /// output stream.
   ///
-  void emitByte(unsigned char B) {
+  virtual void emitByte(unsigned char B) {
     if (CurBufferPtr != BufferEnd)
       *CurBufferPtr++ = B;
   }
@@ -100,7 +101,7 @@
   /// emitWordLE - This callback is invoked when a 32-bit word needs to be
   /// written to the output stream in little-endian format.
   ///
-  void emitWordLE(unsigned W) {
+  virtual void emitWordLE(unsigned W) {
     if (CurBufferPtr+4 <= BufferEnd) {
       *CurBufferPtr++ = (unsigned char)(W >>  0);
       *CurBufferPtr++ = (unsigned char)(W >>  8);
@@ -114,7 +115,7 @@
   /// emitWordBE - This callback is invoked when a 32-bit word needs to be
   /// written to the output stream in big-endian format.
   ///
-  void emitWordBE(unsigned W) {
+  virtual void emitWordBE(unsigned W) {
     if (CurBufferPtr+4 <= BufferEnd) {
       *CurBufferPtr++ = (unsigned char)(W >> 24);
       *CurBufferPtr++ = (unsigned char)(W >> 16);
@@ -175,7 +176,7 @@
   }
   
   /// emitInt32 - Emit a int32 directive.
-  void emitInt32(int Value) {
+  virtual void emitInt32(int Value) {
     if (CurBufferPtr+4 <= BufferEnd) {
       *((uint32_t*)CurBufferPtr) = Value;
       CurBufferPtr += 4;
@@ -185,7 +186,7 @@
   }
 
   /// emitInt64 - Emit a int64 directive.
-  void emitInt64(uint64_t Value) {
+  virtual void emitInt64(uint64_t Value) {
     if (CurBufferPtr+8 <= BufferEnd) {
       *((uint64_t*)CurBufferPtr) = Value;
       CurBufferPtr += 8;
@@ -195,7 +196,7 @@
   }
   
   /// emitAt - Emit Value in Addr
-  void emitAt(uintptr_t *Addr, uintptr_t Value) {
+  virtual void emitAt(uintptr_t *Addr, uintptr_t Value) {
     if (Addr >= (uintptr_t*)BufferBegin && Addr < (uintptr_t*)BufferEnd)
       (*Addr) = Value;
   }
@@ -270,6 +271,11 @@
   /// Specifies the MachineModuleInfo object. This is used for exception handling
   /// purposes.
   virtual void setModuleInfo(MachineModuleInfo* Info) = 0;
+
+  void setCurrentPtr(unsigned char* Ptr) {
+    CurBufferPtr = Ptr;
+  }
+
 };
 
 } // End llvm namespace
Index: lib/CodeGen/LLVMTargetMachine.cpp
===================================================================
--- lib/CodeGen/LLVMTargetMachine.cpp	(revision 48143)
+++ lib/CodeGen/LLVMTargetMachine.cpp	(working copy)
@@ -17,6 +17,7 @@
 #include "llvm/Assembly/PrintModulePass.h"
 #include "llvm/Analysis/LoopPass.h"
 #include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/SizeEmitter.h"
 #include "llvm/CodeGen/Collector.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Transforms/Scalar.h"
@@ -257,7 +258,13 @@
   
   if (addPreEmitPass(PM, Fast) && PrintMachineCode)
     PM.add(createMachineFunctionPrinterPass(cerr));
+  
+  if (SizedMemoryCode) {
+    SizeEmitter * SE = new SizeEmitter(&MCE);
+    addSimpleCodeEmitter(PM, Fast, false, *SE);
+  }
 
+
   addCodeEmitter(PM, Fast, PrintEmittedAsm, MCE);
   
   PM.add(createCollectorMetadataDeleter());
Index: lib/CodeGen/SizeEmitter.cpp
===================================================================
--- lib/CodeGen/SizeEmitter.cpp	(revision 0)
+++ lib/CodeGen/SizeEmitter.cpp	(revision 0)
@@ -0,0 +1,77 @@
+#include "llvm/CodeGen/SizeEmitter.h"
+#include "llvm/Constant.h"
+#include "llvm/Constants.h"
+#include "llvm/DerivedTypes.h"
+#include "llvm/Module.h"
+#include "llvm/Type.h"
+#include "llvm/CodeGen/MachineCodeEmitter.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
+#include "llvm/CodeGen/MachineJumpTableInfo.h"
+#include "llvm/CodeGen/MachineRelocation.h"
+#include "llvm/ExecutionEngine/GenericValue.h"
+#include "llvm/Target/TargetData.h"
+#include "llvm/Target/TargetJITInfo.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Target/TargetOptions.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/MutexGuard.h"
+#include "llvm/System/Disassembler.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/System/Memory.h"
+#include <algorithm>
+using namespace llvm;
+
+
+void SizeEmitter::initConstantPool(MachineConstantPool *MCP) {
+  const std::vector<MachineConstantPoolEntry> &Constants = MCP->getConstants();
+  if (Constants.empty()) return;
+
+  MachineConstantPoolEntry CPE = Constants.back();
+  unsigned Size = CPE.Offset;
+  const Type *Ty = CPE.isMachineConstantPoolEntry()
+    ? CPE.Val.MachineCPVal->getType() : CPE.Val.ConstVal->getType();
+  Size += Fn->getTarget().getTargetData()->getABITypeSize(Ty);
+  ConstantPoolBase = allocateSpace(Size, 1 << MCP->getConstantPoolAlignment());
+  ConstantPool = MCP;
+}
+
+void SizeEmitter::initJumpTableInfo(MachineJumpTableInfo *MJTI) {
+  const std::vector<MachineJumpTableEntry> &JT = MJTI->getJumpTables();
+  if (JT.empty()) return;
+  
+  unsigned NumEntries = 0;
+  for (unsigned i = 0, e = JT.size(); i != e; ++i)
+    NumEntries += JT[i].MBBs.size();
+
+  unsigned EntrySize = MJTI->getEntrySize();
+
+  // Just allocate space for all the jump tables now.  We will fix up the actual
+  // MBB entries in the tables after we emit the code for each block, since then
+  // we will know the final locations of the MBBs in memory.
+  JumpTable = MJTI;
+  JumpTableBase = allocateSpace(NumEntries * EntrySize, MJTI->getAlignment());
+}
+
+intptr_t SizeEmitter::getConstantPoolEntryAddress(unsigned ConstantNum) const {
+  assert(ConstantNum < ConstantPool->getConstants().size() &&
+         "Invalid ConstantPoolIndex!");
+  return (intptr_t)ConstantPoolBase +
+         ConstantPool->getConstants()[ConstantNum].Offset;
+}
+
+intptr_t SizeEmitter::getJumpTableEntryAddress(unsigned Index) const {
+  const std::vector<MachineJumpTableEntry> &JT = JumpTable->getJumpTables();
+  assert(Index < JT.size() && "Invalid jump table index!");
+  
+  unsigned Offset = 0;
+  unsigned EntrySize = JumpTable->getEntrySize();
+  
+  for (unsigned i = 0; i < Index; ++i)
+    Offset += JT[i].MBBs.size();
+  
+   Offset *= EntrySize;
+  
+  return (intptr_t)((char *)JumpTableBase + Offset);
+}
+
Index: lib/Target/PowerPC/PPCInstrInfo.td
===================================================================
--- lib/Target/PowerPC/PPCInstrInfo.td	(revision 48143)
+++ lib/Target/PowerPC/PPCInstrInfo.td	(working copy)
@@ -1189,6 +1189,8 @@
           (BL_ELF texternalsym:$dst)>;
 
 // Hi and Lo for Darwin Global Addresses.
+def : Pat<(PPChi texternalsym:$in, 0), (LIS texternalsym:$in)>;
+def : Pat<(PPClo texternalsym:$in, 0), (LI texternalsym:$in)>;
 def : Pat<(PPChi tglobaladdr:$in, 0), (LIS tglobaladdr:$in)>;
 def : Pat<(PPClo tglobaladdr:$in, 0), (LI tglobaladdr:$in)>;
 def : Pat<(PPChi tconstpool:$in, 0), (LIS tconstpool:$in)>;
Index: lib/Target/PowerPC/PPCJITInfo.cpp
===================================================================
--- lib/Target/PowerPC/PPCJITInfo.cpp	(revision 48143)
+++ lib/Target/PowerPC/PPCJITInfo.cpp	(working copy)
@@ -13,11 +13,15 @@
 
 #define DEBUG_TYPE "jit"
 #include "PPCJITInfo.h"
+#include "PPCRegisterInfo.h"
 #include "PPCRelocations.h"
 #include "PPCTargetMachine.h"
 #include "llvm/CodeGen/MachineCodeEmitter.h"
 #include "llvm/Config/alloca.h"
+#include "llvm/ExecutionEngine/ExecutionEngine.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/Dwarf.h"
+#include "llvm/Target/TargetOptions.h"
 #include <set>
 using namespace llvm;
 
@@ -52,24 +56,27 @@
   if (Offset >= -(1 << 23) && Offset < (1 << 23)) {   // In range?
     AtI[0] = BUILD_B(Offset, isCall);     // b/bl target
   } else if (!is64Bit) {
-    AtI[0] = BUILD_LIS(12, To >> 16);     // lis r12, hi16(address)
+    AtI[0] = BUILD_B(0, false);           // thread safety
     AtI[1] = BUILD_ORI(12, 12, To);       // ori r12, r12, lo16(address)
     AtI[2] = BUILD_MTCTR(12);             // mtctr r12
     AtI[3] = BUILD_BCTR(isCall);          // bctr/bctrl
+    AtI[0] = BUILD_LIS(12, To >> 16);     // lis r12, hi16(address)
   } else {
-    AtI[0] = BUILD_LIS(12, To >> 48);      // lis r12, hi16(address)
+    AtI[0] = BUILD_B(0, false);            // thread safety
     AtI[1] = BUILD_ORI(12, 12, To >> 32);  // ori r12, r12, lo16(address)
     AtI[2] = BUILD_SLDI(12, 12, 32);       // sldi r12, r12, 32
     AtI[3] = BUILD_ORIS(12, 12, To >> 16); // oris r12, r12, hi16(address)
     AtI[4] = BUILD_ORI(12, 12, To);        // ori r12, r12, lo16(address)
     AtI[5] = BUILD_MTCTR(12);              // mtctr r12
     AtI[6] = BUILD_BCTR(isCall);           // bctr/bctrl
+    AtI[0] = BUILD_LIS(12, To >> 48);      // lis r12, hi16(address)
   }
 }
 
 extern "C" void PPC32CompilationCallback();
 extern "C" void PPC64CompilationCallback();
 
+
 #if (defined(__POWERPC__) || defined (__ppc__) || defined(_POWER)) && \
     !defined(__ppc64__)
 // CompilationCallback stub - We can't use a C function with inline assembly in
@@ -143,6 +150,9 @@
 // it, because we the prolog/epilog inserted by GCC won't work for us.  Instead,
 // write our own wrapper, which does things our way, so we have complete control
 // over register saving and restoring.
+
+# define CFI(x) x
+
 asm(
     ".text\n"
     ".align 2\n"
@@ -155,19 +165,29 @@
     // FIXME Layout
     //   8 double registers       -  64 bytes
     //   8 int registers          -  32 bytes
+    CFI(".cfi_startproc\n")    
+    "stwu 1, -104(1)\n"
+    CFI(".cfi_adjust_cfa_offset 104\n")
     "mflr 0\n"
-    "stw 0,  4(1)\n"
-    "stwu 1, -104(1)\n"
+    "stw 0,  108(1)\n"
+    CFI(".cfi_offset lr, 4\n")
     // Save all int arg registers
-    "stw 10, 100(1)\n"   "stw 9,  96(1)\n"
-    "stw 8,  92(1)\n"    "stw 7,  88(1)\n"
-    "stw 6,  84(1)\n"    "stw 5,  80(1)\n"
-    "stw 4,  76(1)\n"    "stw 3,  72(1)\n"
+    "stw 10, 100(1)\n"   
+    "stw 9,  96(1)\n"
+    "stw 8,  92(1)\n"    
+    "stw 7,  88(1)\n"
+    "stw 6,  84(1)\n"    
+    "stw 5,  80(1)\n"
+    "stw 4,  76(1)\n"    
+    "stw 3,  72(1)\n"
     // Save all call-clobbered FP regs.
     "stfd 8,  64(1)\n"
-    "stfd 7,  56(1)\n"   "stfd 6,  48(1)\n"
-    "stfd 5,  40(1)\n"   "stfd 4,  32(1)\n"
-    "stfd 3,  24(1)\n"   "stfd 2,  16(1)\n"
+    "stfd 7,  56(1)\n"   
+    "stfd 6,  48(1)\n"
+    "stfd 5,  40(1)\n"   
+    "stfd 4,  32(1)\n"
+    "stfd 3,  24(1)\n"   
+    "stfd 2,  16(1)\n"
     "stfd 1,  8(1)\n"
     // Arguments to Compilation Callback:
     // r3 - our lr (address of the call instruction in stub plus 4)
@@ -180,21 +200,29 @@
     "bl PPCCompilationCallbackC\n"
     "mtctr 3\n"
     // Restore all int arg registers
-    "lwz 10, 100(1)\n"   "lwz 9,  96(1)\n"
-    "lwz 8,  92(1)\n"    "lwz 7,  88(1)\n"
-    "lwz 6,  84(1)\n"    "lwz 5,  80(1)\n"
-    "lwz 4,  76(1)\n"    "lwz 3,  72(1)\n"
+    "lwz 10, 100(1)\n"   
+    "lwz 9,  96(1)\n"
+    "lwz 8,  92(1)\n"    
+    "lwz 7,  88(1)\n"
+    "lwz 6,  84(1)\n"    
+    "lwz 5,  80(1)\n"
+    "lwz 4,  76(1)\n"    
+    "lwz 3,  72(1)\n"
     // Restore all FP arg registers
     "lfd 8,  64(1)\n"
-    "lfd 7,  56(1)\n"    "lfd 6,  48(1)\n"
-    "lfd 5,  40(1)\n"    "lfd 4,  32(1)\n"
-    "lfd 3,  24(1)\n"    "lfd 2,  16(1)\n"
+    "lfd 7,  56(1)\n"    
+    "lfd 6,  48(1)\n"
+    "lfd 5,  40(1)\n"    
+    "lfd 4,  32(1)\n"
+    "lfd 3,  24(1)\n"    
+    "lfd 2,  16(1)\n"
     "lfd 1,  8(1)\n"
     // Pop 3 frames off the stack and branch to target
     "lwz  1, 104(1)\n"
     "lwz  0, 4(1)\n"
     "mtlr 0\n"
     "bctr\n"
+    CFI(".cfi_endproc\n")    
     );
 #else
 void PPC32CompilationCallback() {
@@ -324,6 +352,31 @@
   return is64Bit ? PPC64CompilationCallback : PPC32CompilationCallback;
 }
 
+static const char* GetCommonFrame32() {
+    /*
+    // Size of common frame
+    MCE.emitWordBE(16);
+    // Common frame
+    MCE.emitWordBE(0);
+    MCE.emitByte(1);
+    MCE.emitByte('z');
+    MCE.emitByte('R');
+    MCE.emitByte(0);
+    MCE.emitByte(1);
+    MCE.emitByte(-4 & 0x7f);
+    MCE.emitByte(0x41);
+    MCE.emitByte(1);
+    MCE.emitByte(16);
+    MCE.emitByte(0xc);
+    MCE.emitByte(1);
+    MCE.emitByte(0);*/
+  static const char CF[] = {
+    0, 0, 0, 16, 0, 0, 0, 0, 1, 'z', 'R', 0, 1, -4 & 0x7f, 
+    0x41, 1, 16, 0xc, 1, 0
+  };
+  return CF;
+}
+
 #if (defined(__POWERPC__) || defined (__ppc__) || defined(_POWER)) && \
 defined(__APPLE__)
 extern "C" void sys_icache_invalidate(const void *Addr, size_t len);
@@ -356,21 +409,26 @@
     SyncICache((void*)Addr, 7*4);
     return MCE.finishFunctionStub(0);
   }
-
-  MCE.startFunctionStub(10*4);
+  
+  if (ExceptionHandling && !is64Bit) {
+    MCE.startFunctionStub(10*4 + 44);
+  } else {
+    MCE.startFunctionStub(10*4);
+  }
+  intptr_t BeginAddr = (intptr_t)MCE.getCurrentPCValue();
   intptr_t Addr = (intptr_t)MCE.getCurrentPCValue();
   if (is64Bit) {
+    MCE.emitWordBE(0x7d6802a6);     // mflr r11
+    MCE.emitWordBE(0xf9610010);     // std r11, 16(r1)
     MCE.emitWordBE(0xf821ffb1);     // stdu r1,-80(r1)
+  } else if (TM.getSubtargetImpl()->isMachoABI()){
     MCE.emitWordBE(0x7d6802a6);     // mflr r11
-    MCE.emitWordBE(0xf9610060);     // std r11, 96(r1)
-  } else if (TM.getSubtargetImpl()->isMachoABI()){
+    MCE.emitWordBE(0x91610008);     // stw r11, 8(r1)
     MCE.emitWordBE(0x9421ffe0);     // stwu r1,-32(r1)
+  } else {
     MCE.emitWordBE(0x7d6802a6);     // mflr r11
-    MCE.emitWordBE(0x91610028);     // stw r11, 40(r1)
-  } else {
+    MCE.emitWordBE(0x91610004);     // stw r11, 4(r1)
     MCE.emitWordBE(0x9421ffe0);     // stwu r1,-32(r1)
-    MCE.emitWordBE(0x7d6802a6);     // mflr r11
-    MCE.emitWordBE(0x91610024);     // stw r11, 36(r1)
   }
   intptr_t BranchAddr = (intptr_t)MCE.getCurrentPCValue();
   MCE.emitWordBE(0);
@@ -382,6 +440,42 @@
   MCE.emitWordBE(0);
   EmitBranchToAt(BranchAddr, (intptr_t)Fn, true, is64Bit);
   SyncICache((void*)Addr, 10*4);
+  intptr_t EndAddr = (intptr_t)MCE.getCurrentPCValue();
+  
+  if (ExceptionHandling && !is64Bit) {
+    // Size of Eh section
+    MCE.emitWordBE(32);
+    // Eh section
+    MCE.emitWordBE(MCE.getCurrentPCValue() - (intptr_t)GetCommonFrame32());
+    MCE.emitWordBE(BeginAddr - MCE.getCurrentPCValue());
+    MCE.emitWordBE(EndAddr - BeginAddr);
+    MCE.emitByte(0);
+    MCE.emitByte(dwarf::DW_CFA_advance_loc4);
+    MCE.emitWordBE(8);
+    MCE.emitByte(dwarf::DW_CFA_def_cfa_offset);
+    MCE.emitByte(32);
+    MCE.emitByte(dwarf::DW_CFA_offset_extended_sf);
+    MCE.emitByte(TM.getRegisterInfo()->getDwarfRegNum(PPC::LR, true));
+    if (TM.getSubtargetImpl()->isMachoABI()){
+      MCE.emitByte(-2 & 0x7f);
+    } else {
+      MCE.emitByte(-1 & 0x7f);
+    }
+    MCE.emitByte(dwarf::DW_CFA_advance_loc4);
+    MCE.emitWordBE(4);
+    MCE.emitByte(dwarf::DW_CFA_def_cfa_register);
+    MCE.emitByte(1);
+    // Alignment
+    MCE.emitByte(0);
+    MCE.emitByte(0);
+    
+    // Two zero for the unwind runtime
+    MCE.emitWordBE(0);
+    MCE.emitWordBE(0);
+    
+    SyncICache((void*)EndAddr, 44);
+    ExecutionEngine::RegisterTable((void*)EndAddr);
+  }
   return MCE.finishFunctionStub(0);
 }
 
Index: lib/Target/TargetMachine.cpp
===================================================================
--- lib/Target/TargetMachine.cpp	(revision 48143)
+++ lib/Target/TargetMachine.cpp	(working copy)
@@ -31,6 +31,7 @@
   bool UseSoftFloat;
   bool NoZerosInBSS;
   bool ExceptionHandling;
+  bool SizedMemoryCode;
   Reloc::Model RelocationModel;
   CodeModel::Model CMModel;
   bool PerformTailCallOpt;
Index: lib/ExecutionEngine/JIT/JITEmitter.cpp
===================================================================
--- lib/ExecutionEngine/JIT/JITEmitter.cpp	(revision 48143)
+++ lib/ExecutionEngine/JIT/JITEmitter.cpp	(working copy)
@@ -18,12 +18,14 @@
 #include "llvm/Constant.h"
 #include "llvm/Module.h"
 #include "llvm/Type.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/CodeGen/MachineCodeEmitter.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineRelocation.h"
+#include "llvm/CodeGen/SizeEmitter.h"
 #include "llvm/ExecutionEngine/JITMemoryManager.h"
 #include "llvm/Target/TargetData.h"
 #include "llvm/Target/TargetJITInfo.h"
@@ -278,8 +280,10 @@
     DOUT << "JIT: Lazily resolving function '" << F->getName()
          << "' In stub ptr = " << Stub << " actual ptr = "
          << I->first << "\n";
-
+    
+    TheJIT->lock.release();
     Result = TheJIT->getPointerToFunction(F);
+    TheJIT->lock.acquire();
   }
 
   // We don't need to reuse this stub in the future, as F is now compiled.
@@ -357,9 +361,11 @@
         MemMgr->AllocateGOT();
         DOUT << "JIT is managing a GOT\n";
       }
-
-      if (ExceptionHandling) DE = new JITDwarfEmitter(jit);
+      
+      if (ExceptionHandling)
+        DE = new JITDwarfEmitter(jit);
     }
+   
     ~JITEmitter() { 
       delete MemMgr;
       if (ExceptionHandling) delete DE;
@@ -370,6 +376,7 @@
     virtual void startFunction(MachineFunction &F);
     virtual bool finishFunction(MachineFunction &F);
     
+    void initConstantPool(MachineConstantPool *MCP);
     void emitConstantPool(MachineConstantPool *MCP);
     void initJumpTableInfo(MachineJumpTableInfo *MJTI);
     void emitJumpTableInfo(MachineJumpTableInfo *MJTI);
@@ -469,19 +476,47 @@
 
 
 void JITEmitter::startFunction(MachineFunction &F) {
-  uintptr_t ActualSize;
-  BufferBegin = CurBufferPtr = MemMgr->startFunctionBody(F.getFunction(),
-                                                         ActualSize);
-  BufferEnd = BufferBegin+ActualSize;
+  MMI->BeginFunction(&F);
   
-  // Ensure the constant pool/jump table info is at least 4-byte aligned.
-  emitAlignment(16);
+  if (SizedMemoryCode) {
+    BufferBegin = CurBufferPtr;
+    BufferEnd = (unsigned char*) 0xffffffff;
+  
+    // Ensure the constant pool/jump table info is at least 4-byte aligned.
+    emitAlignment(16);
 
-  emitConstantPool(F.getConstantPool());
-  initJumpTableInfo(F.getJumpTableInfo());
+    initConstantPool(F.getConstantPool());
+    initJumpTableInfo(F.getJumpTableInfo());
+    
+    
+    uintptr_t ActualSize = (uintptr_t)CurBufferPtr;
+    CurBufferPtr = MemMgr->startFunctionBody(F.getFunction(),
+                                             ActualSize);
+  
+    ConstantPoolBase  = (void*)(((unsigned) ConstantPoolBase) + CurBufferPtr);
+    JumpTableBase     = (void*)(((unsigned) JumpTableBase) + CurBufferPtr);
 
-  // About to start emitting the machine code for the function.
-  emitAlignment(std::max(F.getFunction()->getAlignment(), 8U));
+    emitConstantPool(F.getConstantPool());
+
+  } else {
+    uintptr_t ActualSize;
+    BufferBegin = CurBufferPtr = MemMgr->startFunctionBody(F.getFunction(),
+                                                           ActualSize);
+    BufferEnd = BufferBegin+ActualSize;
+  
+    // Ensure the constant pool/jump table info is at least 4-byte aligned.
+    emitAlignment(16);
+
+    initConstantPool(F.getConstantPool());
+    emitConstantPool(F.getConstantPool());
+    initJumpTableInfo(F.getJumpTableInfo());
+  
+    // About to start emitting the machine code for the function.
+    emitAlignment(std::max(F.getFunction()->getAlignment(), 8U));
+
+  }
+  
+  
   TheJIT->updateGlobalMapping(F.getFunction(), CurBufferPtr);
 
   MBBLocations.clear();
@@ -579,12 +614,18 @@
     DOUT << "Disassembled code:\n"
          << sys::disassembleBuffer(FnStart, FnEnd-FnStart, (uintptr_t)FnStart);
 #endif
+ 
   if (ExceptionHandling) {
     uintptr_t ActualSize;
+    if (SizedMemoryCode) {
+      SizeEmitter sz(LabelLocations);
+      DE->EmitDwarfTable(F, sz, FnStart, FnEnd);
+      ActualSize = sz.getCurrentPCValue();
+    }
     SavedBufferBegin = BufferBegin;
     SavedBufferEnd = BufferEnd;
     SavedCurBufferPtr = CurBufferPtr;
-
+    
     BufferBegin = CurBufferPtr = MemMgr->startExceptionTable(F.getFunction(),
                                                              ActualSize);
     BufferEnd = BufferBegin+ActualSize;
@@ -598,11 +639,10 @@
     TheJIT->RegisterTable(FrameRegister);
   }
   MMI->EndFunction();
- 
   return false;
 }
 
-void JITEmitter::emitConstantPool(MachineConstantPool *MCP) {
+void JITEmitter::initConstantPool(MachineConstantPool *MCP) {
   const std::vector<MachineConstantPoolEntry> &Constants = MCP->getConstants();
   if (Constants.empty()) return;
 
@@ -611,12 +651,15 @@
   const Type *Ty = CPE.isMachineConstantPoolEntry()
     ? CPE.Val.MachineCPVal->getType() : CPE.Val.ConstVal->getType();
   Size += TheJIT->getTargetData()->getABITypeSize(Ty);
-
+   
   ConstantPoolBase = allocateSpace(Size, 1 << MCP->getConstantPoolAlignment());
   ConstantPool = MCP;
+}
 
+void JITEmitter::emitConstantPool(MachineConstantPool *MCP) {
   if (ConstantPoolBase == 0) return;  // Buffer overflow.
 
+  const std::vector<MachineConstantPoolEntry> &Constants = MCP->getConstants();
   // Initialize the memory for all of the constant pool entries.
   for (unsigned i = 0, e = Constants.size(); i != e; ++i) {
     void *CAddr = (char*)ConstantPoolBase+Constants[i].Offset;
Index: lib/ExecutionEngine/JIT/JIT.cpp
===================================================================
--- lib/ExecutionEngine/JIT/JIT.cpp	(revision 48143)
+++ lib/ExecutionEngine/JIT/JIT.cpp	(working copy)
@@ -289,10 +289,10 @@
 /// specified function, compiling it if neccesary.
 ///
 void *JIT::getPointerToFunction(Function *F) {
-  MutexGuard locked(lock);
 
-  if (void *Addr = getPointerToGlobalIfAvailable(F))
-    return Addr;   // Check if function already code gen'd
+  if (void *Addr = getPointerToGlobalIfAvailable(F)) {
+    return Addr;
+  }
 
   // Make sure we read in the function if it exists in this Module.
   if (F->hasNotBeenReadFromBitcode()) {
@@ -314,13 +314,25 @@
       abort();
     }
   }
+  
+  if (void *Addr = getPointerToGlobalIfAvailable(F)) {
+    return Addr;
+  }
 
   if (F->isDeclaration()) {
+    if (void *Addr = getPointerToGlobalIfAvailable(F)) {
+      return Addr;
+    }
     void *Addr = getPointerToNamedFunction(F->getName());
     addGlobalMapping(F, Addr);
     return Addr;
   }
 
+  MutexGuard locked(lock);
+  
+  if (void *Addr = getPointerToGlobalIfAvailable(F))
+    return Addr;   // Check if function already code gen'd
+  
   runJITOnFunction(F);
 
   void *Addr = getPointerToGlobalIfAvailable(F);
Index: lib/ExecutionEngine/ExecutionEngine.cpp
===================================================================
--- lib/ExecutionEngine/ExecutionEngine.cpp	(revision 48143)
+++ lib/ExecutionEngine/ExecutionEngine.cpp	(working copy)
@@ -92,7 +92,7 @@
   // If we are using the reverse mapping, add it too
   if (!state.getGlobalAddressReverseMap(locked).empty()) {
     const GlobalValue *&V = state.getGlobalAddressReverseMap(locked)[Addr];
-    assert((V == 0 || GV == 0) && "GlobalMapping already established!");
+    // assert((V == 0 || GV == 0) && "GlobalMapping already established!");
     V = GV;
   }
 }
@@ -128,7 +128,7 @@
   // If we are using the reverse mapping, add it too
   if (!state.getGlobalAddressReverseMap(locked).empty()) {
     const GlobalValue *&V = state.getGlobalAddressReverseMap(locked)[Addr];
-    assert((V == 0 || GV == 0) && "GlobalMapping already established!");
+    // assert((V == 0 || GV == 0) && "GlobalMapping already established!");
     V = GV;
   }
 }
Index: lib/VMCore/AsmWriter.cpp
===================================================================
--- lib/VMCore/AsmWriter.cpp	(revision 48143)
+++ lib/VMCore/AsmWriter.cpp	(working copy)
@@ -1053,8 +1053,9 @@
   case GlobalValue::ExternalWeakLinkage: Out << "extern_weak "; break;      
   case GlobalValue::ExternalLinkage: break;
   case GlobalValue::GhostLinkage:
-    cerr << "GhostLinkage not allowed in AsmWriter!\n";
-    abort();
+    //cerr << "GhostLinkage not allowed in AsmWriter!\n";
+    //abort();
+    break;
   }
   switch (F->getVisibility()) {
   default: assert(0 && "Invalid visibility style!");
Index: lib/Target/X86/X86JITInfo.cpp
===================================================================
--- lib/Target/X86/X86JITInfo.cpp	(revision 48341)
+++ lib/Target/X86/X86JITInfo.cpp	(working copy)
@@ -57,7 +57,7 @@
 // FIXME: Disable this until we really want to use it. Also, we will
 //        need to add some workarounds for compilers, which support
 //        only subset of these directives.
-# define CFI(x)
+# define CFI(x) x
 #endif
 
 // Provide a wrapper for X86CompilationCallback2 that saves non-traditional
Index: lib/Target/PowerPC/PPCISelLowering.cpp
===================================================================
--- lib/Target/PowerPC/PPCISelLowering.cpp	(revision 48651)
+++ lib/Target/PowerPC/PPCISelLowering.cpp	(working copy)
@@ -177,10 +177,12 @@
   // We want to legalize GlobalAddress and ConstantPool nodes into the 
   // appropriate instructions to materialize the address.
   setOperationAction(ISD::GlobalAddress, MVT::i32, Custom);
+  setOperationAction(ISD::ExternalSymbol  , MVT::i32  , Custom);
   setOperationAction(ISD::GlobalTLSAddress, MVT::i32, Custom);
   setOperationAction(ISD::ConstantPool,  MVT::i32, Custom);
   setOperationAction(ISD::JumpTable,     MVT::i32, Custom);
   setOperationAction(ISD::GlobalAddress, MVT::i64, Custom);
+  setOperationAction(ISD::ExternalSymbol  , MVT::i64  , Custom);
   setOperationAction(ISD::GlobalTLSAddress, MVT::i64, Custom);
   setOperationAction(ISD::ConstantPool,  MVT::i64, Custom);
   setOperationAction(ISD::JumpTable,     MVT::i64, Custom);
@@ -735,6 +737,36 @@
   return isIntS16Immediate(Op.Val, Imm);
 }
 
+ static SDOperand LowerExternalSymbol(SDOperand Op, SelectionDAG &DAG) {
+   MVT::ValueType PtrVT = Op.getValueType();
+   ExternalSymbolSDNode *GSDB = dyn_cast<ExternalSymbolSDNode>(Op);
+   SDOperand GA = DAG.getTargetExternalSymbol(GSDB->getSymbol(), PtrVT);
+   SDOperand Zero = DAG.getConstant(0, PtrVT);
+      
+   const TargetMachine &TM = DAG.getTarget();
+ 
+   SDOperand Hi = DAG.getNode(PPCISD::Hi, PtrVT, GA, Zero);
+   SDOperand Lo = DAG.getNode(PPCISD::Lo, PtrVT, GA, Zero);
+ 
+   // If this is a non-darwin platform, we don't support non-static relo models
+   // yet.
+   if (TM.getRelocationModel() == Reloc::Static || 
+       !TM.getSubtarget<PPCSubtarget>().isDarwin()) {
+     // Generate non-pic code that has direct accesses to globals.
+     // The address of the global is just (hi(&g)+lo(&g)).
+     return DAG.getNode(ISD::ADD, PtrVT, Hi, Lo);
+   }  
+      
+   if (TM.getRelocationModel() == Reloc::PIC_) {
+     // With PIC, the first instruction is actually "GR+hi(&G)".
+     Hi = DAG.getNode(ISD::ADD, PtrVT,
+                      DAG.getNode(PPCISD::GlobalBaseReg, PtrVT), Hi);
+   }  
+      
+   Lo = DAG.getNode(ISD::ADD, PtrVT, Hi, Lo);
+      
+   return Lo;
+ }
 
 /// SelectAddressRegReg - Given the specified addressed, check to see if it
 /// can be represented as an indexed [r+r] operation.  Returns false if it
@@ -2116,11 +2148,11 @@
   // If the callee is a GlobalAddress/ExternalSymbol node (quite common, every
   // direct call is) turn it into a TargetGlobalAddress/TargetExternalSymbol
   // node so that legalize doesn't hack it.
-  if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee))
-    Callee = DAG.getTargetGlobalAddress(G->getGlobal(), Callee.getValueType());
-  else if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee))
-    Callee = DAG.getTargetExternalSymbol(S->getSymbol(), Callee.getValueType());
-  else if (SDNode *Dest = isBLACompatibleAddress(Callee, DAG))
+  //if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee))
+  //  Callee = DAG.getTargetGlobalAddress(G->getGlobal(), Callee.getValueType());
+  //if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee))
+  //  Callee = DAG.getTargetExternalSymbol(S->getSymbol(), Callee.getValueType());
+  if (SDNode *Dest = isBLACompatibleAddress(Callee, DAG))
     // If this is an absolute destination address, use the munged value.
     Callee = SDOperand(Dest, 0);
   else {
@@ -3381,6 +3413,7 @@
   default: assert(0 && "Wasn't expecting to be able to lower this!"); 
   case ISD::ConstantPool:       return LowerConstantPool(Op, DAG);
   case ISD::GlobalAddress:      return LowerGlobalAddress(Op, DAG);
+  case ISD::ExternalSymbol:     return LowerExternalSymbol(Op, DAG);
   case ISD::GlobalTLSAddress:   return LowerGlobalTLSAddress(Op, DAG);
   case ISD::JumpTable:          return LowerJumpTable(Op, DAG);
   case ISD::SETCC:              return LowerSETCC(Op, DAG);