Vendor import of llvm trunk r130700:

http://llvm.org/svn/llvm-project/llvm/trunk@130700

8 files changed, 471 insertions, 176 deletions

diff --git a/tools/lto/CMakeLists.txt b/tools/lto/CMakeLists.txt
new file mode 100644
index 0000000..7e2c5f0
--- /dev/null
+++ b/tools/lto/CMakeLists.txt
@@ -0,0 +1,27 @@
+set(LLVM_LINK_COMPONENTS
+  ${LLVM_TARGETS_TO_BUILD}
+  ipo scalaropts linker bitreader bitwriter mcdisassembler)
+
+add_definitions( -DLLVM_VERSION_INFO=\"${PACKAGE_VERSION}\" )
+
+set(SOURCES
+  LTOCodeGenerator.cpp
+  lto.cpp
+  LTOModule.cpp
+  )
+
+if( NOT WIN32 AND LLVM_ENABLE_PIC )
+  set(bsl ${BUILD_SHARED_LIBS})
+  set(BUILD_SHARED_LIBS ON)
+  add_llvm_library(LTO ${SOURCES})
+  set_property(TARGET LTO PROPERTY OUTPUT_NAME "LTO")
+  set(BUILD_SHARED_LIBS ${bsl})
+  set(LTO_STATIC_TARGET_NAME LTO_static)
+else()
+  set(LTO_STATIC_TARGET_NAME LTO)
+endif()
+
+if( NOT BUILD_SHARED_LIBS )
+  add_llvm_library(${LTO_STATIC_TARGET_NAME} ${SOURCES})
+  set_property(TARGET ${LTO_STATIC_TARGET_NAME} PROPERTY OUTPUT_NAME "LTO")
+endif()
diff --git a/tools/lto/LTOCodeGenerator.cpp b/tools/lto/LTOCodeGenerator.cpp
index f72fdb0..d95f354 100644
--- a/tools/lto/LTOCodeGenerator.cpp
+++ b/tools/lto/LTOCodeGenerator.cpp
@@ -75,7 +75,6 @@ LTOCodeGenerator::LTOCodeGenerator()
 {
     InitializeAllTargets();
     InitializeAllAsmPrinters();
-    InitializeAllAsmParsers();
 }
 
 LTOCodeGenerator::~LTOCodeGenerator()
@@ -88,7 +87,17 @@ LTOCodeGenerator::~LTOCodeGenerator()
 
 bool LTOCodeGenerator::addModule(LTOModule* mod, std::string& errMsg)
 {
-    return _linker.LinkInModule(mod->getLLVVMModule(), &errMsg);
+
+  if(mod->getLLVVMModule()->MaterializeAllPermanently(&errMsg))
+    return true;
+
+  bool ret = _linker.LinkInModule(mod->getLLVVMModule(), &errMsg);
+
+  const std::vector<const char*> &undefs = mod->getAsmUndefinedRefs();
+  for (int i = 0, e = undefs.size(); i != e; ++i)
+    _asmUndefinedRefs[undefs[i]] = 1;
+
+  return ret;
 }
     
 
@@ -167,51 +176,63 @@ bool LTOCodeGenerator::writeMergedModules(const char *path,
 }
 
 
-const void* LTOCodeGenerator::compile(size_t* length, std::string& errMsg)
+bool LTOCodeGenerator::compile_to_file(const char** name, std::string& errMsg)
 {
-    // make unique temp .o file to put generated object file
-    sys::PathWithStatus uniqueObjPath("lto-llvm.o");
-    if ( uniqueObjPath.createTemporaryFileOnDisk(false, &errMsg) ) {
-        uniqueObjPath.eraseFromDisk();
-        return NULL;
-    }
-    sys::RemoveFileOnSignal(uniqueObjPath);
-
-    // generate object file
-    bool genResult = false;
-    tool_output_file objFile(uniqueObjPath.c_str(), errMsg);
-    if (!errMsg.empty())
-      return NULL;
-    genResult = this->generateObjectFile(objFile.os(), errMsg);
-    objFile.os().close();
-    if (objFile.os().has_error()) {
-      objFile.os().clear_error();
-      return NULL;
-    }
-    objFile.keep();
-    if ( genResult ) {
-      uniqueObjPath.eraseFromDisk();
-      return NULL;
-    }
+  // make unique temp .o file to put generated object file
+  sys::PathWithStatus uniqueObjPath("lto-llvm.o");
+  if ( uniqueObjPath.createTemporaryFileOnDisk(false, &errMsg) ) {
+    uniqueObjPath.eraseFromDisk();
+    return true;
+  }
+  sys::RemoveFileOnSignal(uniqueObjPath);
+
+  // generate object file
+  bool genResult = false;
+  tool_output_file objFile(uniqueObjPath.c_str(), errMsg);
+  if (!errMsg.empty())
+    return NULL;
+  genResult = this->generateObjectFile(objFile.os(), errMsg);
+  objFile.os().close();
+  if (objFile.os().has_error()) {
+    objFile.os().clear_error();
+    return true;
+  }
+  objFile.keep();
+  if ( genResult ) {
+    uniqueObjPath.eraseFromDisk();
+    return true;
+  }
 
-    const std::string& uniqueObjStr = uniqueObjPath.str();
-    // remove old buffer if compile() called twice
-    delete _nativeObjectFile;
+  _nativeObjectPath = uniqueObjPath.str();
+  *name = _nativeObjectPath.c_str();
+  return false;
+}
 
-    // read .o file into memory buffer
-    OwningPtr<MemoryBuffer> BuffPtr;
-    if (error_code ec = MemoryBuffer::getFile(uniqueObjStr.c_str(),BuffPtr))
-      errMsg = ec.message();
-    _nativeObjectFile = BuffPtr.take();
+const void* LTOCodeGenerator::compile(size_t* length, std::string& errMsg)
+{
+  const char *name;
+  if (compile_to_file(&name, errMsg))
+    return NULL;
+
+  // remove old buffer if compile() called twice
+  delete _nativeObjectFile;
+
+  // read .o file into memory buffer
+  OwningPtr<MemoryBuffer> BuffPtr;
+  if (error_code ec = MemoryBuffer::getFile(name, BuffPtr, -1, false)) {
+    errMsg = ec.message();
+    return NULL;
+  }
+  _nativeObjectFile = BuffPtr.take();
 
-    // remove temp files
-    uniqueObjPath.eraseFromDisk();
+  // remove temp files
+  sys::Path(_nativeObjectPath).eraseFromDisk();
 
-    // return buffer, unless error
-    if ( _nativeObjectFile == NULL )
-        return NULL;
-    *length = _nativeObjectFile->getBufferSize();
-    return _nativeObjectFile->getBufferStart();
+  // return buffer, unless error
+  if ( _nativeObjectFile == NULL )
+    return NULL;
+  *length = _nativeObjectFile->getBufferSize();
+  return _nativeObjectFile->getBufferStart();
 }
 
 bool LTOCodeGenerator::determineTarget(std::string& errMsg)
@@ -249,6 +270,34 @@ bool LTOCodeGenerator::determineTarget(std::string& errMsg)
     return false;
 }
 
+void LTOCodeGenerator::applyRestriction(GlobalValue &GV,
+                                     std::vector<const char*> &mustPreserveList,
+                                        SmallPtrSet<GlobalValue*, 8> &asmUsed,
+                                        Mangler &mangler) {
+  SmallString<64> Buffer;
+  mangler.getNameWithPrefix(Buffer, &GV, false);
+
+  if (GV.isDeclaration())
+    return;
+  if (_mustPreserveSymbols.count(Buffer))
+    mustPreserveList.push_back(GV.getName().data());
+  if (_asmUndefinedRefs.count(Buffer))
+    asmUsed.insert(&GV);
+}
+
+static void findUsedValues(GlobalVariable *LLVMUsed,
+                           SmallPtrSet<GlobalValue*, 8> &UsedValues) {
+  if (LLVMUsed == 0) return;
+
+  ConstantArray *Inits = dyn_cast<ConstantArray>(LLVMUsed->getInitializer());
+  if (Inits == 0) return;
+
+  for (unsigned i = 0, e = Inits->getNumOperands(); i != e; ++i)
+    if (GlobalValue *GV = 
+          dyn_cast<GlobalValue>(Inits->getOperand(i)->stripPointerCasts()))
+      UsedValues.insert(GV);
+}
+
 void LTOCodeGenerator::applyScopeRestrictions() {
   if (_scopeRestrictionsDone) return;
   Module *mergedModule = _linker.getModule();
@@ -258,38 +307,47 @@ void LTOCodeGenerator::applyScopeRestrictions() {
   passes.add(createVerifierPass());
 
   // mark which symbols can not be internalized 
-  if (!_mustPreserveSymbols.empty()) {
-    MCContext Context(*_target->getMCAsmInfo(), NULL);
-    Mangler mangler(Context, *_target->getTargetData());
-    std::vector<const char*> mustPreserveList;
-    SmallString<64> Buffer;
-    for (Module::iterator f = mergedModule->begin(),
-         e = mergedModule->end(); f != e; ++f) {
-      Buffer.clear();
-      mangler.getNameWithPrefix(Buffer, f, false);
-      if (!f->isDeclaration() &&
-          _mustPreserveSymbols.count(Buffer))
-        mustPreserveList.push_back(f->getName().data());
-    }
-    for (Module::global_iterator v = mergedModule->global_begin(), 
-         e = mergedModule->global_end(); v !=  e; ++v) {
-      Buffer.clear();
-      mangler.getNameWithPrefix(Buffer, v, false);
-      if (!v->isDeclaration() &&
-          _mustPreserveSymbols.count(Buffer))
-        mustPreserveList.push_back(v->getName().data());
-    }
-    for (Module::alias_iterator a = mergedModule->alias_begin(),
-         e = mergedModule->alias_end(); a != e; ++a) {
-      Buffer.clear();
-      mangler.getNameWithPrefix(Buffer, a, false);
-      if (!a->isDeclaration() &&
-          _mustPreserveSymbols.count(Buffer))
-        mustPreserveList.push_back(a->getName().data());
-    }
-    passes.add(createInternalizePass(mustPreserveList));
+  MCContext Context(*_target->getMCAsmInfo(), NULL);
+  Mangler mangler(Context, *_target->getTargetData());
+  std::vector<const char*> mustPreserveList;
+  SmallPtrSet<GlobalValue*, 8> asmUsed;
+
+  for (Module::iterator f = mergedModule->begin(),
+         e = mergedModule->end(); f != e; ++f)
+    applyRestriction(*f, mustPreserveList, asmUsed, mangler);
+  for (Module::global_iterator v = mergedModule->global_begin(), 
+         e = mergedModule->global_end(); v !=  e; ++v)
+    applyRestriction(*v, mustPreserveList, asmUsed, mangler);
+  for (Module::alias_iterator a = mergedModule->alias_begin(),
+         e = mergedModule->alias_end(); a != e; ++a)
+    applyRestriction(*a, mustPreserveList, asmUsed, mangler);
+
+  GlobalVariable *LLVMCompilerUsed =
+    mergedModule->getGlobalVariable("llvm.compiler.used");
+  findUsedValues(LLVMCompilerUsed, asmUsed);
+  if (LLVMCompilerUsed)
+    LLVMCompilerUsed->eraseFromParent();
+
+  const llvm::Type *i8PTy = llvm::Type::getInt8PtrTy(_context);
+  std::vector<Constant*> asmUsed2;
+  for (SmallPtrSet<GlobalValue*, 16>::const_iterator i = asmUsed.begin(),
+         e = asmUsed.end(); i !=e; ++i) {
+    GlobalValue *GV = *i;
+    Constant *c = ConstantExpr::getBitCast(GV, i8PTy);
+    asmUsed2.push_back(c);
   }
-  
+
+  llvm::ArrayType *ATy = llvm::ArrayType::get(i8PTy, asmUsed2.size());
+  LLVMCompilerUsed =
+    new llvm::GlobalVariable(*mergedModule, ATy, false,
+                             llvm::GlobalValue::AppendingLinkage,
+                             llvm::ConstantArray::get(ATy, asmUsed2),
+                             "llvm.compiler.used");
+
+  LLVMCompilerUsed->setSection("llvm.metadata");
+
+  passes.add(createInternalizePass(mustPreserveList));
+
   // apply scope restrictions
   passes.run(*mergedModule);
   
diff --git a/tools/lto/LTOCodeGenerator.h b/tools/lto/LTOCodeGenerator.h
index 0556520..f8fd357 100644
--- a/tools/lto/LTOCodeGenerator.h
+++ b/tools/lto/LTOCodeGenerator.h
@@ -19,6 +19,7 @@
 #include "llvm/LLVMContext.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/SmallPtrSet.h"
 
 #include <string>
 
@@ -40,12 +41,17 @@ struct LTOCodeGenerator {
     void                addMustPreserveSymbol(const char* sym);
     bool                writeMergedModules(const char* path, 
                                                            std::string& errMsg);
+    bool                compile_to_file(const char** name, std::string& errMsg);
     const void*         compile(size_t* length, std::string& errMsg);
     void                setCodeGenDebugOptions(const char *opts); 
 private:
     bool                generateObjectFile(llvm::raw_ostream& out, 
                                            std::string& errMsg);
     void                applyScopeRestrictions();
+    void                applyRestriction(llvm::GlobalValue &GV,
+                                     std::vector<const char*> &mustPreserveList,
+                        llvm::SmallPtrSet<llvm::GlobalValue*, 8> &asmUsed,
+                                         llvm::Mangler &mangler);
     bool                determineTarget(std::string& errMsg);
     
     typedef llvm::StringMap<uint8_t> StringSet;
@@ -57,9 +63,11 @@ private:
     bool                        _scopeRestrictionsDone;
     lto_codegen_model           _codeModel;
     StringSet                   _mustPreserveSymbols;
+    StringSet                   _asmUndefinedRefs;
     llvm::MemoryBuffer*         _nativeObjectFile;
     std::vector<const char*>    _codegenOptions;
     std::string                 _mCpu;
+    std::string                 _nativeObjectPath;
 };
 
 #endif // LTO_CODE_GENERATOR_H
diff --git a/tools/lto/LTOModule.cpp b/tools/lto/LTOModule.cpp
index 1eac22c..8f2b1f4 100644
--- a/tools/lto/LTOModule.cpp
+++ b/tools/lto/LTOModule.cpp
@@ -26,11 +26,18 @@
 #include "llvm/Support/Host.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Process.h"
+#include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/system_error.h"
 #include "llvm/Target/Mangler.h"
 #include "llvm/Target/SubtargetFeature.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCParser/MCAsmParser.h"
+#include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSymbol.h"
+#include "llvm/Target/TargetAsmParser.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetRegistry.h"
 #include "llvm/Target/TargetSelect.h"
@@ -73,7 +80,7 @@ bool LTOModule::isTargetMatch(MemoryBuffer *buffer, const char *triplePrefix) {
 
 
 LTOModule::LTOModule(Module *m, TargetMachine *t)
-  : _module(m), _target(t), _symbolsParsed(false)
+  : _module(m), _target(t)
 {
 }
 
@@ -84,32 +91,33 @@ LTOModule *LTOModule::makeLTOModule(const char *path,
     errMsg = ec.message();
     return NULL;
   }
-  return makeLTOModule(buffer.get(), errMsg);
+  return makeLTOModule(buffer.take(), errMsg);
 }
 
 LTOModule *LTOModule::makeLTOModule(int fd, const char *path,
-                                    off_t size,
+                                    size_t size,
+                                    std::string &errMsg) {
+  return makeLTOModule(fd, path, size, size, 0, errMsg);
+}
+
+LTOModule *LTOModule::makeLTOModule(int fd, const char *path,
+                                    size_t file_size,
+                                    size_t map_size,
+                                    off_t offset,
                                     std::string &errMsg) {
   OwningPtr<MemoryBuffer> buffer;
-  if (error_code ec = MemoryBuffer::getOpenFile(fd, path, buffer, size)) {
+  if (error_code ec = MemoryBuffer::getOpenFile(fd, path, buffer, file_size,
+                                                map_size, offset, false)) {
     errMsg = ec.message();
     return NULL;
   }
-  return makeLTOModule(buffer.get(), errMsg);
+  return makeLTOModule(buffer.take(), errMsg);
 }
 
-/// makeBuffer - Create a MemoryBuffer from a memory range.  MemoryBuffer
-/// requires the byte past end of the buffer to be a zero.  We might get lucky
-/// and already be that way, otherwise make a copy.  Also if next byte is on a
-/// different page, don't assume it is readable.
+/// makeBuffer - Create a MemoryBuffer from a memory range.
 MemoryBuffer *LTOModule::makeBuffer(const void *mem, size_t length) {
   const char *startPtr = (char*)mem;
-  const char *endPtr = startPtr+length;
-  if (((uintptr_t)endPtr & (sys::Process::GetPageSize()-1)) == 0 ||
-      *endPtr != 0)
-    return MemoryBuffer::getMemBufferCopy(StringRef(startPtr, length));
-
-  return MemoryBuffer::getMemBuffer(StringRef(startPtr, length));
+  return MemoryBuffer::getMemBuffer(StringRef(startPtr, length), "", false);
 }
 
 
@@ -118,17 +126,25 @@ LTOModule *LTOModule::makeLTOModule(const void *mem, size_t length,
   OwningPtr<MemoryBuffer> buffer(makeBuffer(mem, length));
   if (!buffer)
     return NULL;
-  return makeLTOModule(buffer.get(), errMsg);
+  return makeLTOModule(buffer.take(), errMsg);
 }
 
 LTOModule *LTOModule::makeLTOModule(MemoryBuffer *buffer,
                                     std::string &errMsg) {
-  InitializeAllTargets();
+  static bool Initialized = false;
+  if (!Initialized) {
+    InitializeAllTargets();
+    InitializeAllAsmParsers();
+    Initialized = true;
+  }
 
   // parse bitcode buffer
-  OwningPtr<Module> m(ParseBitcodeFile(buffer, getGlobalContext(), &errMsg));
-  if (!m)
+  OwningPtr<Module> m(getLazyBitcodeModule(buffer, getGlobalContext(),
+                                           &errMsg));
+  if (!m) {
+    delete buffer;
     return NULL;
+  }
 
   std::string Triple = m->getTargetTriple();
   if (Triple.empty())
@@ -139,12 +155,18 @@ LTOModule *LTOModule::makeLTOModule(MemoryBuffer *buffer,
   if (!march)
     return NULL;
 
-  // construct LTModule, hand over ownership of module and target
+  // construct LTOModule, hand over ownership of module and target
   SubtargetFeatures Features;
   Features.getDefaultSubtargetFeatures("" /* cpu */, llvm::Triple(Triple));
   std::string FeatureStr = Features.getString();
   TargetMachine *target = march->createTargetMachine(Triple, FeatureStr);
-  return new LTOModule(m.take(), target);
+  LTOModule *Ret = new LTOModule(m.take(), target);
+  bool Err = Ret->ParseSymbols();
+  if (Err) {
+    delete Ret;
+    return NULL;
+  }
+  return Ret;
 }
 
 
@@ -159,16 +181,6 @@ void LTOModule::setTargetTriple(const char *triple) {
 void LTOModule::addDefinedFunctionSymbol(Function *f, Mangler &mangler) {
   // add to list of defined symbols
   addDefinedSymbol(f, mangler, true);
-
-  // add external symbols referenced by this function.
-  for (Function::iterator b = f->begin(); b != f->end(); ++b) {
-    for (BasicBlock::iterator i = b->begin(); i != b->end(); ++i) {
-      for (unsigned count = 0, total = i->getNumOperands();
-           count != total; ++count) {
-        findExternalRefs(i->getOperand(count), mangler);
-      }
-    }
-  }
 }
 
 // Get string that data pointer points to.
@@ -309,12 +321,6 @@ void LTOModule::addDefinedDataSymbol(GlobalValue *v, Mangler &mangler) {
       }
     }
   }
-
-  // add external symbols referenced by this data.
-  for (unsigned count = 0, total = v->getNumOperands();
-       count != total; ++count) {
-    findExternalRefs(v->getOperand(count), mangler);
-  }
 }
 
 
@@ -324,10 +330,6 @@ void LTOModule::addDefinedSymbol(GlobalValue *def, Mangler &mangler,
   if (def->getName().startswith("llvm."))
     return;
 
-  // ignore available_externally
-  if (def->hasAvailableExternallyLinkage())
-    return;
-
   // string is owned by _defines
   SmallString<64> Buffer;
   mangler.getNameWithPrefix(Buffer, def, false);
@@ -383,7 +385,8 @@ void LTOModule::addDefinedSymbol(GlobalValue *def, Mangler &mangler,
   _symbols.push_back(info);
 }
 
-void LTOModule::addAsmGlobalSymbol(const char *name) {
+void LTOModule::addAsmGlobalSymbol(const char *name,
+                                   lto_symbol_attributes scope) {
   StringSet::value_type &entry = _defines.GetOrCreateValue(name);
 
   // only add new define if not already defined
@@ -393,13 +396,32 @@ void LTOModule::addAsmGlobalSymbol(const char *name) {
   entry.setValue(1);
   const char *symbolName = entry.getKey().data();
   uint32_t attr = LTO_SYMBOL_DEFINITION_REGULAR;
-  attr |= LTO_SYMBOL_SCOPE_DEFAULT;
+  attr |= scope;
   NameAndAttributes info;
   info.name = symbolName;
   info.attributes = (lto_symbol_attributes)attr;
   _symbols.push_back(info);
 }
 
+void LTOModule::addAsmGlobalSymbolUndef(const char *name) {
+  StringMap<NameAndAttributes>::value_type &entry =
+    _undefines.GetOrCreateValue(name);
+
+  _asm_undefines.push_back(entry.getKey().data());
+
+  // we already have the symbol
+  if (entry.getValue().name)
+    return;
+
+  uint32_t attr = LTO_SYMBOL_DEFINITION_UNDEFINED;;
+  attr |= LTO_SYMBOL_SCOPE_DEFAULT;
+  NameAndAttributes info;
+  info.name = entry.getKey().data();
+  info.attributes = (lto_symbol_attributes)attr;
+
+  entry.setValue(info);
+}
+
 void LTOModule::addPotentialUndefinedSymbol(GlobalValue *decl,
                                             Mangler &mangler) {
   // ignore all llvm.* symbols
@@ -432,41 +454,211 @@ void LTOModule::addPotentialUndefinedSymbol(GlobalValue *decl,
 }
 
 
+namespace {
+  class RecordStreamer : public MCStreamer {
+  public:
+    enum State { NeverSeen, Global, Defined, DefinedGlobal, Used};
+
+  private:
+    StringMap<State> Symbols;
+
+    void markDefined(const MCSymbol &Symbol) {
+      State &S = Symbols[Symbol.getName()];
+      switch (S) {
+      case DefinedGlobal:
+      case Global:
+        S = DefinedGlobal;
+        break;
+      case NeverSeen:
+      case Defined:
+      case Used:
+        S = Defined;
+        break;
+      }
+    }
+    void markGlobal(const MCSymbol &Symbol) {
+      State &S = Symbols[Symbol.getName()];
+      switch (S) {
+      case DefinedGlobal:
+      case Defined:
+        S = DefinedGlobal;
+        break;
+
+      case NeverSeen:
+      case Global:
+      case Used:
+        S = Global;
+        break;
+      }
+    }
+    void markUsed(const MCSymbol &Symbol) {
+      State &S = Symbols[Symbol.getName()];
+      switch (S) {
+      case DefinedGlobal:
+      case Defined:
+      case Global:
+        break;
+
+      case NeverSeen:
+      case Used:
+        S = Used;
+        break;
+      }
+    }
+
+    // FIXME: mostly copied for the obj streamer.
+    void AddValueSymbols(const MCExpr *Value) {
+      switch (Value->getKind()) {
+      case MCExpr::Target:
+        // FIXME: What should we do in here?
+        break;
+
+      case MCExpr::Constant:
+        break;
+
+      case MCExpr::Binary: {
+        const MCBinaryExpr *BE = cast<MCBinaryExpr>(Value);
+        AddValueSymbols(BE->getLHS());
+        AddValueSymbols(BE->getRHS());
+        break;
+      }
+
+      case MCExpr::SymbolRef:
+        markUsed(cast<MCSymbolRefExpr>(Value)->getSymbol());
+        break;
 
-// Find external symbols referenced by VALUE. This is a recursive function.
-void LTOModule::findExternalRefs(Value *value, Mangler &mangler) {
-  if (GlobalValue *gv = dyn_cast<GlobalValue>(value)) {
-    if (!gv->hasExternalLinkage())
-      addPotentialUndefinedSymbol(gv, mangler);
-    // If this is a variable definition, do not recursively process
-    // initializer.  It might contain a reference to this variable
-    // and cause an infinite loop.  The initializer will be
-    // processed in addDefinedDataSymbol().
-    return;
-  }
+      case MCExpr::Unary:
+        AddValueSymbols(cast<MCUnaryExpr>(Value)->getSubExpr());
+        break;
+      }
+    }
+
+  public:
+    typedef StringMap<State>::const_iterator const_iterator;
+
+    const_iterator begin() {
+      return Symbols.begin();
+    }
 
-  // GlobalValue, even with InternalLinkage type, may have operands with
-  // ExternalLinkage type. Do not ignore these operands.
-  if (Constant *c = dyn_cast<Constant>(value)) {
-    // Handle ConstantExpr, ConstantStruct, ConstantArry etc.
-    for (unsigned i = 0, e = c->getNumOperands(); i != e; ++i)
-      findExternalRefs(c->getOperand(i), mangler);
+    const_iterator end() {
+      return Symbols.end();
+    }
+
+    RecordStreamer(MCContext &Context) : MCStreamer(Context) {}
+
+    virtual void ChangeSection(const MCSection *Section) {}
+    virtual void InitSections() {}
+    virtual void EmitLabel(MCSymbol *Symbol) {
+      Symbol->setSection(*getCurrentSection());
+      markDefined(*Symbol);
+    }
+    virtual void EmitAssemblerFlag(MCAssemblerFlag Flag) {}
+    virtual void EmitThumbFunc(MCSymbol *Func) {}
+    virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
+      // FIXME: should we handle aliases?
+      markDefined(*Symbol);
+    }
+    virtual void EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute) {
+      if (Attribute == MCSA_Global)
+        markGlobal(*Symbol);
+    }
+    virtual void EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {}
+    virtual void EmitWeakReference(MCSymbol *Alias, const MCSymbol *Symbol) {}
+    virtual void BeginCOFFSymbolDef(const MCSymbol *Symbol) {}
+    virtual void EmitCOFFSymbolStorageClass(int StorageClass) {}
+    virtual void EmitZerofill(const MCSection *Section, MCSymbol *Symbol,
+                              unsigned Size , unsigned ByteAlignment) {
+      markDefined(*Symbol);
+    }
+    virtual void EmitCOFFSymbolType(int Type) {}
+    virtual void EndCOFFSymbolDef() {}
+    virtual void EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
+                                  unsigned ByteAlignment) {
+      markDefined(*Symbol);
+    }
+    virtual void EmitELFSize(MCSymbol *Symbol, const MCExpr *Value) {}
+    virtual void EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size) {}
+    virtual void EmitTBSSSymbol(const MCSection *Section, MCSymbol *Symbol,
+                                uint64_t Size, unsigned ByteAlignment) {}
+    virtual void EmitBytes(StringRef Data, unsigned AddrSpace) {}
+    virtual void EmitValueImpl(const MCExpr *Value, unsigned Size,
+                               unsigned AddrSpace) {}
+    virtual void EmitULEB128Value(const MCExpr *Value) {}
+    virtual void EmitSLEB128Value(const MCExpr *Value) {}
+    virtual void EmitValueToAlignment(unsigned ByteAlignment, int64_t Value,
+                                      unsigned ValueSize,
+                                      unsigned MaxBytesToEmit) {}
+    virtual void EmitCodeAlignment(unsigned ByteAlignment,
+                                   unsigned MaxBytesToEmit) {}
+    virtual void EmitValueToOffset(const MCExpr *Offset,
+                                   unsigned char Value ) {}
+    virtual void EmitFileDirective(StringRef Filename) {}
+    virtual void EmitDwarfAdvanceLineAddr(int64_t LineDelta,
+                                          const MCSymbol *LastLabel,
+                                        const MCSymbol *Label) {}
+
+    virtual void EmitInstruction(const MCInst &Inst) {
+      // Scan for values.
+      for (unsigned i = Inst.getNumOperands(); i--; )
+        if (Inst.getOperand(i).isExpr())
+          AddValueSymbols(Inst.getOperand(i).getExpr());
+    }
+    virtual void Finish() {}
+  };
+}
+
+bool LTOModule::addAsmGlobalSymbols(MCContext &Context) {
+  const std::string &inlineAsm = _module->getModuleInlineAsm();
+
+  OwningPtr<RecordStreamer> Streamer(new RecordStreamer(Context));
+  MemoryBuffer *Buffer = MemoryBuffer::getMemBuffer(inlineAsm);
+  SourceMgr SrcMgr;
+  SrcMgr.AddNewSourceBuffer(Buffer, SMLoc());
+  OwningPtr<MCAsmParser> Parser(createMCAsmParser(_target->getTarget(), SrcMgr,
+                                                  Context, *Streamer,
+                                                  *_target->getMCAsmInfo()));
+  OwningPtr<TargetAsmParser>
+    TAP(_target->getTarget().createAsmParser(*Parser.get(), *_target.get()));
+  Parser->setTargetParser(*TAP);
+  int Res = Parser->Run(false);
+  if (Res)
+    return true;
+
+  for (RecordStreamer::const_iterator i = Streamer->begin(),
+         e = Streamer->end(); i != e; ++i) {
+    StringRef Key = i->first();
+    RecordStreamer::State Value = i->second;
+    if (Value == RecordStreamer::DefinedGlobal)
+      addAsmGlobalSymbol(Key.data(), LTO_SYMBOL_SCOPE_DEFAULT);
+    else if (Value == RecordStreamer::Defined)
+      addAsmGlobalSymbol(Key.data(), LTO_SYMBOL_SCOPE_INTERNAL);
+    else if (Value == RecordStreamer::Global ||
+             Value == RecordStreamer::Used)
+      addAsmGlobalSymbolUndef(Key.data());
   }
+  return false;
 }
 
-void LTOModule::lazyParseSymbols() {
-  if (_symbolsParsed)
-    return;
+static bool isDeclaration(const GlobalValue &V) {
+  if (V.hasAvailableExternallyLinkage())
+    return true;
+  if (V.isMaterializable())
+    return false;
+  return V.isDeclaration();
+}
 
-  _symbolsParsed = true;
+static bool isAliasToDeclaration(const GlobalAlias &V) {
+  return isDeclaration(*V.getAliasedGlobal());
+}
 
+bool LTOModule::ParseSymbols() {
   // Use mangler to add GlobalPrefix to names to match linker names.
   MCContext Context(*_target->getMCAsmInfo(), NULL);
   Mangler mangler(Context, *_target->getTargetData());
 
   // add functions
   for (Module::iterator f = _module->begin(); f != _module->end(); ++f) {
-    if (f->isDeclaration())
+    if (isDeclaration(*f))
       addPotentialUndefinedSymbol(f, mangler);
     else
       addDefinedFunctionSymbol(f, mangler);
@@ -475,42 +667,20 @@ void LTOModule::lazyParseSymbols() {
   // add data
   for (Module::global_iterator v = _module->global_begin(),
          e = _module->global_end(); v !=  e; ++v) {
-    if (v->isDeclaration())
+    if (isDeclaration(*v))
       addPotentialUndefinedSymbol(v, mangler);
     else
       addDefinedDataSymbol(v, mangler);
   }
 
   // add asm globals
-  const std::string &inlineAsm = _module->getModuleInlineAsm();
-  const std::string glbl = ".globl";
-  std::string asmSymbolName;
-  std::string::size_type pos = inlineAsm.find(glbl, 0);
-  while (pos != std::string::npos) {
-    // eat .globl
-    pos = pos + 6;
-
-    // skip white space between .globl and symbol name
-    std::string::size_type pbegin = inlineAsm.find_first_not_of(' ', pos);
-    if (pbegin == std::string::npos)
-      break;
-
-    // find end-of-line
-    std::string::size_type pend = inlineAsm.find_first_of('\n', pbegin);
-    if (pend == std::string::npos)
-      break;
-
-    asmSymbolName.assign(inlineAsm, pbegin, pend - pbegin);
-    addAsmGlobalSymbol(asmSymbolName.c_str());
-
-    // search next .globl
-    pos = inlineAsm.find(glbl, pend);
-  }
+  if (addAsmGlobalSymbols(Context))
+    return true;
 
   // add aliases
   for (Module::alias_iterator i = _module->alias_begin(),
          e = _module->alias_end(); i != e; ++i) {
-    if (i->isDeclaration())
+    if (isAliasToDeclaration(*i))
       addPotentialUndefinedSymbol(i, mangler);
     else
       addDefinedDataSymbol(i, mangler);
@@ -526,17 +696,16 @@ void LTOModule::lazyParseSymbols() {
       _symbols.push_back(info);
     }
   }
+  return false;
 }
 
 
 uint32_t LTOModule::getSymbolCount() {
-  lazyParseSymbols();
   return _symbols.size();
 }
 
 
 lto_symbol_attributes LTOModule::getSymbolAttributes(uint32_t index) {
-  lazyParseSymbols();
   if (index < _symbols.size())
     return _symbols[index].attributes;
   else
@@ -544,7 +713,6 @@ lto_symbol_attributes LTOModule::getSymbolAttributes(uint32_t index) {
 }
 
 const char *LTOModule::getSymbolName(uint32_t index) {
-  lazyParseSymbols();
   if (index < _symbols.size())
     return _symbols[index].name;
   else
diff --git a/tools/lto/LTOModule.h b/tools/lto/LTOModule.h
index 1794d81..0b64a90 100644
--- a/tools/lto/LTOModule.h
+++ b/tools/lto/LTOModule.h
@@ -52,7 +52,12 @@ struct LTOModule {
     static LTOModule*        makeLTOModule(const char* path,
                                           std::string& errMsg);
     static LTOModule*        makeLTOModule(int fd, const char *path,
-                                           off_t size,
+                                           size_t size,
+                                           std::string& errMsg);
+    static LTOModule*        makeLTOModule(int fd, const char *path,
+                                           size_t file_size,
+                                           size_t map_size,
+                                           off_t offset,
                                            std::string& errMsg);
     static LTOModule*        makeLTOModule(const void* mem, size_t length,
                                            std::string& errMsg);
@@ -64,23 +69,27 @@ struct LTOModule {
     const char*              getSymbolName(uint32_t index);
     
     llvm::Module *           getLLVVMModule() { return _module.get(); }
+    const std::vector<const char*> &getAsmUndefinedRefs() {
+            return _asm_undefines;
+    }
 
 private:
                             LTOModule(llvm::Module* m, llvm::TargetMachine* t);
 
-    void                    lazyParseSymbols();
+    bool                    ParseSymbols();
     void                    addDefinedSymbol(llvm::GlobalValue* def, 
                                                     llvm::Mangler& mangler, 
                                                     bool isFunction);
     void                    addPotentialUndefinedSymbol(llvm::GlobalValue* decl, 
                                                         llvm::Mangler &mangler);
-    void                    findExternalRefs(llvm::Value* value, 
-                                                llvm::Mangler& mangler);
     void                    addDefinedFunctionSymbol(llvm::Function* f, 
                                                         llvm::Mangler &mangler);
     void                    addDefinedDataSymbol(llvm::GlobalValue* v, 
                                                         llvm::Mangler &mangler);
-    void                    addAsmGlobalSymbol(const char *);
+    bool                    addAsmGlobalSymbols(llvm::MCContext &Context);
+    void                    addAsmGlobalSymbol(const char *,
+                                               lto_symbol_attributes scope);
+    void                    addAsmGlobalSymbolUndef(const char *);
     void                    addObjCClass(llvm::GlobalVariable* clgv);
     void                    addObjCCategory(llvm::GlobalVariable* clgv);
     void                    addObjCClassRef(llvm::GlobalVariable* clgv);
@@ -103,11 +112,11 @@ private:
 
     llvm::OwningPtr<llvm::Module>           _module;
     llvm::OwningPtr<llvm::TargetMachine>    _target;
-    bool                                    _symbolsParsed;
     std::vector<NameAndAttributes>          _symbols;
     // _defines and _undefines only needed to disambiguate tentative definitions
     StringSet                               _defines;    
     llvm::StringMap<NameAndAttributes>      _undefines;
+    std::vector<const char*>                _asm_undefines;
 };
 
 #endif // LTO_MODULE_H
diff --git a/tools/lto/Makefile b/tools/lto/Makefile
index 294c81b..46925e7 100644
--- a/tools/lto/Makefile
+++ b/tools/lto/Makefile
@@ -20,7 +20,8 @@ include $(LEVEL)/Makefile.config
 LINK_LIBS_IN_SHARED = 1
 SHARED_LIBRARY = 1
 
-LINK_COMPONENTS := $(TARGETS_TO_BUILD) ipo scalaropts linker bitreader bitwriter
+LINK_COMPONENTS := $(TARGETS_TO_BUILD) ipo scalaropts linker bitreader \
+	bitwriter mcdisassembler
 
 include $(LEVEL)/Makefile.common
 
diff --git a/tools/lto/lto.cpp b/tools/lto/lto.cpp
index f48570c..dd658d1 100644
--- a/tools/lto/lto.cpp
+++ b/tools/lto/lto.cpp
@@ -95,12 +95,25 @@ lto_module_t lto_module_create(const char* path)
 // loads an object file from disk
 // returns NULL on error (check lto_get_error_message() for details)
 //
-lto_module_t lto_module_create_from_fd(int fd, const char *path, off_t size)
+lto_module_t lto_module_create_from_fd(int fd, const char *path, size_t size)
 {
      return LTOModule::makeLTOModule(fd, path, size, sLastErrorString);
 }
 
 //
+// loads an object file from disk
+// returns NULL on error (check lto_get_error_message() for details)
+//
+lto_module_t lto_module_create_from_fd_at_offset(int fd, const char *path,
+                                                 size_t file_size,
+                                                 size_t map_size,
+                                                 off_t offset)
+{
+     return LTOModule::makeLTOModule(fd, path, file_size, map_size,
+                                     offset, sLastErrorString);
+}
+
+//
 // loads an object file from memory 
 // returns NULL on error (check lto_get_error_message() for details)
 //
@@ -268,7 +281,7 @@ bool lto_codegen_write_merged_modules(lto_code_gen_t cg, const char* path)
 
 //
 // Generates code for all added modules into one native object file.
-// On sucess returns a pointer to a generated mach-o/ELF buffer and
+// On success returns a pointer to a generated mach-o/ELF buffer and
 // length set to the buffer size.  The buffer is owned by the 
 // lto_code_gen_t and will be freed when lto_codegen_dispose()
 // is called, or lto_codegen_compile() is called again.
@@ -280,6 +293,12 @@ lto_codegen_compile(lto_code_gen_t cg, size_t* length)
   return cg->compile(length, sLastErrorString);
 }
 
+extern bool
+lto_codegen_compile_to_file(lto_code_gen_t cg, const char **name)
+{
+  return cg->compile_to_file(name, sLastErrorString);
+}
+
 
 //
 // Used to pass extra options to the code generator
diff --git a/tools/lto/lto.exports b/tools/lto/lto.exports
index a374091..b900bfb 100644
--- a/tools/lto/lto.exports
+++ b/tools/lto/lto.exports
@@ -2,6 +2,7 @@ lto_get_error_message
 lto_get_version
 lto_module_create
 lto_module_create_from_fd
+lto_module_create_from_fd_at_offset
 lto_module_create_from_memory
 lto_module_get_num_symbols
 lto_module_get_symbol_attribute
@@ -25,3 +26,7 @@ lto_codegen_debug_options
 lto_codegen_set_assembler_args
 lto_codegen_set_assembler_path
 lto_codegen_set_cpu
+lto_codegen_compile_to_file
+LLVMCreateDisasm
+LLVMDisasmDispose
+LLVMDisasmInstruction