示例#1
0
void llvm::DisassembleInputMachO(StringRef Filename) {
  OwningPtr<MemoryBuffer> Buff;

  if (error_code ec = MemoryBuffer::getFileOrSTDIN(Filename, Buff)) {
    errs() << "llvm-objdump: " << Filename << ": " << ec.message() << "\n";
    return;
  }

  OwningPtr<MachOObject> MachOObj(MachOObject::LoadFromBuffer(Buff.take()));

  const Target *TheTarget = GetTarget(MachOObj.get());
  if (!TheTarget) {
    // GetTarget prints out stuff.
    return;
  }
  OwningPtr<const MCInstrInfo> InstrInfo(TheTarget->createMCInstrInfo());
  OwningPtr<MCInstrAnalysis>
    InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo.get()));

  // Set up disassembler.
  OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName));
  OwningPtr<const MCSubtargetInfo>
    STI(TheTarget->createMCSubtargetInfo(TripleName, "", ""));
  OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI));
  int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
  OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
                              AsmPrinterVariant, *AsmInfo, *STI));

  if (!InstrAnalysis || !AsmInfo || !STI || !DisAsm || !IP) {
    errs() << "error: couldn't initialize disassembler for target "
           << TripleName << '\n';
    return;
  }

  outs() << '\n' << Filename << ":\n\n";

  const macho::Header &Header = MachOObj->getHeader();

  const MachOObject::LoadCommandInfo *SymtabLCI = 0;
  // First, find the symbol table segment.
  for (unsigned i = 0; i != Header.NumLoadCommands; ++i) {
    const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i);
    if (LCI.Command.Type == macho::LCT_Symtab) {
      SymtabLCI = &LCI;
      break;
    }
  }

  // Read and register the symbol table data.
  InMemoryStruct<macho::SymtabLoadCommand> SymtabLC;
  MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC);
  MachOObj->RegisterStringTable(*SymtabLC);

  std::vector<Section> Sections;
  std::vector<Symbol> Symbols;
  SmallVector<uint64_t, 8> FoundFns;

  getSectionsAndSymbols(Header, MachOObj.get(), &SymtabLC, Sections, Symbols,
                        FoundFns);

  // Make a copy of the unsorted symbol list. FIXME: duplication
  std::vector<Symbol> UnsortedSymbols(Symbols);
  // Sort the symbols by address, just in case they didn't come in that way.
  array_pod_sort(Symbols.begin(), Symbols.end());

#ifndef NDEBUG
  raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
#else
  raw_ostream &DebugOut = nulls();
#endif

  StringRef DebugAbbrevSection, DebugInfoSection, DebugArangesSection,
            DebugLineSection, DebugStrSection;
  OwningPtr<DIContext> diContext;
  OwningPtr<MachOObject> DSYMObj;
  MachOObject *DbgInfoObj = MachOObj.get();
  // Try to find debug info and set up the DIContext for it.
  if (UseDbg) {
    ArrayRef<Section> DebugSections = Sections;
    std::vector<Section> DSYMSections;

    // A separate DSym file path was specified, parse it as a macho file,
    // get the sections and supply it to the section name parsing machinery.
    if (!DSYMFile.empty()) {
      OwningPtr<MemoryBuffer> Buf;
      if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile.c_str(), Buf)) {
        errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n';
        return;
      }
      DSYMObj.reset(MachOObject::LoadFromBuffer(Buf.take()));
      const macho::Header &Header = DSYMObj->getHeader();

      std::vector<Symbol> Symbols;
      SmallVector<uint64_t, 8> FoundFns;
      getSectionsAndSymbols(Header, DSYMObj.get(), 0, DSYMSections, Symbols,
                            FoundFns);
      DebugSections = DSYMSections;
      DbgInfoObj = DSYMObj.get();
    }

    // Find the named debug info sections.
    for (unsigned SectIdx = 0; SectIdx != DebugSections.size(); SectIdx++) {
      if (!strcmp(DebugSections[SectIdx].Name, "__debug_abbrev"))
        DebugAbbrevSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
                                                 DebugSections[SectIdx].Size);
      else if (!strcmp(DebugSections[SectIdx].Name, "__debug_info"))
        DebugInfoSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
                                               DebugSections[SectIdx].Size);
      else if (!strcmp(DebugSections[SectIdx].Name, "__debug_aranges"))
        DebugArangesSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
                                                  DebugSections[SectIdx].Size);
      else if (!strcmp(DebugSections[SectIdx].Name, "__debug_line"))
        DebugLineSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
                                               DebugSections[SectIdx].Size);
      else if (!strcmp(DebugSections[SectIdx].Name, "__debug_str"))
        DebugStrSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
                                              DebugSections[SectIdx].Size);
    }

    // Setup the DIContext.
    diContext.reset(DIContext::getDWARFContext(DbgInfoObj->isLittleEndian(),
                                               DebugInfoSection,
                                               DebugAbbrevSection,
                                               DebugArangesSection,
                                               DebugLineSection,
                                               DebugStrSection));
  }

  FunctionMapTy FunctionMap;
  FunctionListTy Functions;

  for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) {
    if (strcmp(Sections[SectIdx].Name, "__text"))
      continue; // Skip non-text sections

    // Insert the functions from the function starts segment into our map.
    uint64_t VMAddr = Sections[SectIdx].Address - Sections[SectIdx].Offset;
    for (unsigned i = 0, e = FoundFns.size(); i != e; ++i)
      FunctionMap.insert(std::make_pair(FoundFns[i]+VMAddr, (MCFunction*)0));

    StringRef Bytes = MachOObj->getData(Sections[SectIdx].Offset,
                                        Sections[SectIdx].Size);
    StringRefMemoryObject memoryObject(Bytes);
    bool symbolTableWorked = false;

    // Parse relocations.
    std::vector<std::pair<uint64_t, uint32_t> > Relocs;
    for (unsigned j = 0; j != Sections[SectIdx].NumRelocs; ++j) {
      InMemoryStruct<macho::RelocationEntry> RE;
      MachOObj->ReadRelocationEntry(Sections[SectIdx].RelocTableOffset, j, RE);
      Relocs.push_back(std::make_pair(RE->Word0, RE->Word1 & 0xffffff));
    }
    array_pod_sort(Relocs.begin(), Relocs.end());

    // Disassemble symbol by symbol.
    for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
      // Make sure the symbol is defined in this section.
      if ((unsigned)Symbols[SymIdx].SectionIndex - 1 != SectIdx)
        continue;

      // Start at the address of the symbol relative to the section's address.
      uint64_t Start = Symbols[SymIdx].Value - Sections[SectIdx].Address;
      // Stop disassembling either at the beginning of the next symbol or at
      // the end of the section.
      uint64_t End = (SymIdx+1 == Symbols.size() ||
          Symbols[SymIdx].SectionIndex != Symbols[SymIdx+1].SectionIndex) ?
          Sections[SectIdx].Size :
          Symbols[SymIdx+1].Value - Sections[SectIdx].Address;
      uint64_t Size;

      if (Start >= End)
        continue;

      symbolTableWorked = true;

      if (!CFG) {
        // Normal disassembly, print addresses, bytes and mnemonic form.
        outs() << MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex)
          << ":\n";
        DILineInfo lastLine;
        for (uint64_t Index = Start; Index < End; Index += Size) {
          MCInst Inst;

          if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
                                     DebugOut, nulls())) {
            outs() << format("%8llx:\t", Sections[SectIdx].Address + Index);
            DumpBytes(StringRef(Bytes.data() + Index, Size));
            IP->printInst(&Inst, outs(), "");

            // Print debug info.
            if (diContext) {
              DILineInfo dli =
                diContext->getLineInfoForAddress(Sections[SectIdx].Address +
                                                 Index);
              // Print valid line info if it changed.
              if (dli != lastLine && dli.getLine() != 0)
                outs() << "\t## " << dli.getFileName() << ':'
                       << dli.getLine() << ':' << dli.getColumn();
              lastLine = dli;
            }
            outs() << "\n";
          } else {
            errs() << "llvm-objdump: warning: invalid instruction encoding\n";
            if (Size == 0)
              Size = 1; // skip illegible bytes
          }
        }
      } else {
        // Create CFG and use it for disassembly.
        createMCFunctionAndSaveCalls(
            MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex),
            DisAsm.get(), memoryObject, Start, End, InstrAnalysis.get(),
            Start, DebugOut, FunctionMap, Functions);
      }
    }

    if (CFG) {
      if (!symbolTableWorked) {
        // Reading the symbol table didn't work, create a big __TEXT symbol.
        createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject,
                                     0, Sections[SectIdx].Size,
                                     InstrAnalysis.get(),
                                     Sections[SectIdx].Offset, DebugOut,
                                     FunctionMap, Functions);
      }
      for (std::map<uint64_t, MCFunction*>::iterator mi = FunctionMap.begin(),
           me = FunctionMap.end(); mi != me; ++mi)
        if (mi->second == 0) {
          // Create functions for the remaining callees we have gathered,
          // but we didn't find a name for them.
          SmallVector<uint64_t, 16> Calls;
          MCFunction f =
            MCFunction::createFunctionFromMC("unknown", DisAsm.get(),
                                             memoryObject, mi->first,
                                             Sections[SectIdx].Size,
                                             InstrAnalysis.get(), DebugOut,
                                             Calls);
          Functions.push_back(f);
          mi->second = &Functions.back();
          for (unsigned i = 0, e = Calls.size(); i != e; ++i) {
            std::pair<uint64_t, MCFunction*> p(Calls[i], (MCFunction*)0);
            if (FunctionMap.insert(p).second)
              mi = FunctionMap.begin();
          }
        }

      DenseSet<uint64_t> PrintedBlocks;
      for (unsigned ffi = 0, ffe = Functions.size(); ffi != ffe; ++ffi) {
        MCFunction &f = Functions[ffi];
        for (MCFunction::iterator fi = f.begin(), fe = f.end(); fi != fe; ++fi){
          if (!PrintedBlocks.insert(fi->first).second)
            continue; // We already printed this block.

          // We assume a block has predecessors when it's the first block after
          // a symbol.
          bool hasPreds = FunctionMap.find(fi->first) != FunctionMap.end();

          // See if this block has predecessors.
          // FIXME: Slow.
          for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe;
              ++pi)
            if (pi->second.contains(fi->first)) {
              hasPreds = true;
              break;
            }

          // No predecessors, this is a data block. Print as .byte directives.
          if (!hasPreds) {
            uint64_t End = llvm::next(fi) == fe ? Sections[SectIdx].Size :
                                                  llvm::next(fi)->first;
            outs() << "# " << End-fi->first << " bytes of data:\n";
            for (unsigned pos = fi->first; pos != End; ++pos) {
              outs() << format("%8x:\t", Sections[SectIdx].Address + pos);
              DumpBytes(StringRef(Bytes.data() + pos, 1));
              outs() << format("\t.byte 0x%02x\n", (uint8_t)Bytes[pos]);
            }
            continue;
          }

          if (fi->second.contains(fi->first)) // Print a header for simple loops
            outs() << "# Loop begin:\n";

          DILineInfo lastLine;
          // Walk over the instructions and print them.
          for (unsigned ii = 0, ie = fi->second.getInsts().size(); ii != ie;
               ++ii) {
            const MCDecodedInst &Inst = fi->second.getInsts()[ii];

            // If there's a symbol at this address, print its name.
            if (FunctionMap.find(Sections[SectIdx].Address + Inst.Address) !=
                FunctionMap.end())
              outs() << FunctionMap[Sections[SectIdx].Address + Inst.Address]->
                                                             getName() << ":\n";

            outs() << format("%8llx:\t", Sections[SectIdx].Address +
                                         Inst.Address);
            DumpBytes(StringRef(Bytes.data() + Inst.Address, Inst.Size));

            if (fi->second.contains(fi->first)) // Indent simple loops.
              outs() << '\t';

            IP->printInst(&Inst.Inst, outs(), "");

            // Look for relocations inside this instructions, if there is one
            // print its target and additional information if available.
            for (unsigned j = 0; j != Relocs.size(); ++j)
              if (Relocs[j].first >= Sections[SectIdx].Address + Inst.Address &&
                  Relocs[j].first < Sections[SectIdx].Address + Inst.Address +
                                    Inst.Size) {
                outs() << "\t# "
                   << MachOObj->getStringAtIndex(
                                  UnsortedSymbols[Relocs[j].second].StringIndex)
                   << ' ';
                DumpAddress(UnsortedSymbols[Relocs[j].second].Value, Sections,
                            MachOObj.get(), outs());
              }

            // If this instructions contains an address, see if we can evaluate
            // it and print additional information.
            uint64_t targ = InstrAnalysis->evaluateBranch(Inst.Inst,
                                                          Inst.Address,
                                                          Inst.Size);
            if (targ != -1ULL)
              DumpAddress(targ, Sections, MachOObj.get(), outs());

            // Print debug info.
            if (diContext) {
              DILineInfo dli =
                diContext->getLineInfoForAddress(Sections[SectIdx].Address +
                                                 Inst.Address);
              // Print valid line info if it changed.
              if (dli != lastLine && dli.getLine() != 0)
                outs() << "\t## " << dli.getFileName() << ':'
                       << dli.getLine() << ':' << dli.getColumn();
              lastLine = dli;
            }

            outs() << '\n';
          }
        }

        emitDOTFile((f.getName().str() + ".dot").c_str(), f, IP.get());
      }
    }
  }
}
示例#2
0
StringRef MachOObjectFile::getSectionContents(DataRefImpl DRI) const {
  InMemoryStruct<macho::Section> Sect;
  getSection(DRI, Sect);
  return MachOObj->getData(Sect->Offset, Sect->Size);
}