C++ DataExtractor::getAddress方法代码示例

bool DWARFDebugRangeList::extract(DataExtractor data, uint32_t *offset_ptr) {
  clear();
  if (!data.isValidOffset(*offset_ptr))
    return false;
  AddressSize = data.getAddressSize();
  if (AddressSize != 4 && AddressSize != 8)
    return false;
  Offset = *offset_ptr;
  while (true) {
    RangeListEntry entry;
    uint32_t prev_offset = *offset_ptr;
    entry.StartAddress = data.getAddress(offset_ptr);
    entry.EndAddress = data.getAddress(offset_ptr);
    // Check that both values were extracted correctly.
    if (*offset_ptr != prev_offset + 2 * AddressSize) {
      clear();
      return false;
    }
    if (entry.isEndOfListEntry())
      break;
    Entries.push_back(entry);
  }
  return true;
}

void FrameEntry::parseInstructions(DataExtractor Data, uint32_t *Offset,
                                   uint32_t EndOffset) {
  while (*Offset < EndOffset) {
    uint8_t Opcode = Data.getU8(Offset);
    // Some instructions have a primary opcode encoded in the top bits.
    uint8_t Primary = Opcode & DWARF_CFI_PRIMARY_OPCODE_MASK;

    if (Primary) {
      // If it's a primary opcode, the first operand is encoded in the bottom
      // bits of the opcode itself.
      uint64_t Op1 = Opcode & DWARF_CFI_PRIMARY_OPERAND_MASK;
      switch (Primary) {
        default: llvm_unreachable("Impossible primary CFI opcode");
        case DW_CFA_advance_loc:
        case DW_CFA_restore:
          addInstruction(Primary, Op1);
          break;
        case DW_CFA_offset:
          addInstruction(Primary, Op1, Data.getULEB128(Offset));
          break;
      }
    } else {
      // Extended opcode - its value is Opcode itself.
      switch (Opcode) {
        default: llvm_unreachable("Invalid extended CFI opcode");
        case DW_CFA_nop:
        case DW_CFA_remember_state:
        case DW_CFA_restore_state:
        case DW_CFA_GNU_window_save:
          // No operands
          addInstruction(Opcode);
          break;
        case DW_CFA_set_loc:
          // Operands: Address
          addInstruction(Opcode, Data.getAddress(Offset));
          break;
        case DW_CFA_advance_loc1:
          // Operands: 1-byte delta
          addInstruction(Opcode, Data.getU8(Offset));
          break;
        case DW_CFA_advance_loc2:
          // Operands: 2-byte delta
          addInstruction(Opcode, Data.getU16(Offset));
          break;
        case DW_CFA_advance_loc4:
          // Operands: 4-byte delta
          addInstruction(Opcode, Data.getU32(Offset));
          break;
        case DW_CFA_restore_extended:
        case DW_CFA_undefined:
        case DW_CFA_same_value:
        case DW_CFA_def_cfa_register:
        case DW_CFA_def_cfa_offset:
          // Operands: ULEB128
          addInstruction(Opcode, Data.getULEB128(Offset));
          break;
        case DW_CFA_def_cfa_offset_sf:
          // Operands: SLEB128
          addInstruction(Opcode, Data.getSLEB128(Offset));
          break;
        case DW_CFA_offset_extended:
        case DW_CFA_register:
        case DW_CFA_def_cfa:
        case DW_CFA_val_offset:
          // Operands: ULEB128, ULEB128
          addInstruction(Opcode, Data.getULEB128(Offset),
                                 Data.getULEB128(Offset));
          break;
        case DW_CFA_offset_extended_sf:
        case DW_CFA_def_cfa_sf:
        case DW_CFA_val_offset_sf:
          // Operands: ULEB128, SLEB128
          addInstruction(Opcode, Data.getULEB128(Offset),
                                 Data.getSLEB128(Offset));
          break;
        case DW_CFA_def_cfa_expression:
        case DW_CFA_expression:
        case DW_CFA_val_expression:
          // TODO: implement this
          report_fatal_error("Values with expressions not implemented yet!");
      }
    }
  }
}

void DWARFDebugFrame::parse(DataExtractor Data) {
  uint32_t Offset = 0;
  DenseMap<uint32_t, CIE *> CIEs;

  while (Data.isValidOffset(Offset)) {
    uint32_t StartOffset = Offset;

    bool IsDWARF64 = false;
    uint64_t Length = Data.getU32(&Offset);
    uint64_t Id;

    if (Length == UINT32_MAX) {
      // DWARF-64 is distinguished by the first 32 bits of the initial length
      // field being 0xffffffff. Then, the next 64 bits are the actual entry
      // length.
      IsDWARF64 = true;
      Length = Data.getU64(&Offset);
    }

    // At this point, Offset points to the next field after Length.
    // Length is the structure size excluding itself. Compute an offset one
    // past the end of the structure (needed to know how many instructions to
    // read).
    // TODO: For honest DWARF64 support, DataExtractor will have to treat
    //       offset_ptr as uint64_t*
    uint32_t EndStructureOffset = Offset + static_cast<uint32_t>(Length);

    // The Id field's size depends on the DWARF format
    Id = Data.getUnsigned(&Offset, IsDWARF64 ? 8 : 4);
    bool IsCIE = ((IsDWARF64 && Id == DW64_CIE_ID) || Id == DW_CIE_ID);

    if (IsCIE) {
      uint8_t Version = Data.getU8(&Offset);
      const char *Augmentation = Data.getCStr(&Offset);
      uint8_t AddressSize = Version < 4 ? Data.getAddressSize() : Data.getU8(&Offset);
      Data.setAddressSize(AddressSize);
      uint8_t SegmentDescriptorSize = Version < 4 ? 0 : Data.getU8(&Offset);
      uint64_t CodeAlignmentFactor = Data.getULEB128(&Offset);
      int64_t DataAlignmentFactor = Data.getSLEB128(&Offset);
      uint64_t ReturnAddressRegister = Data.getULEB128(&Offset);

      auto Cie = make_unique<CIE>(StartOffset, Length, Version,
                                  StringRef(Augmentation), AddressSize,
                                  SegmentDescriptorSize, CodeAlignmentFactor,
                                  DataAlignmentFactor, ReturnAddressRegister);
      CIEs[StartOffset] = Cie.get();
      Entries.emplace_back(std::move(Cie));
    } else {
      // FDE
      uint64_t CIEPointer = Id;
      uint64_t InitialLocation = Data.getAddress(&Offset);
      uint64_t AddressRange = Data.getAddress(&Offset);

      Entries.emplace_back(new FDE(StartOffset, Length, CIEPointer,
                                   InitialLocation, AddressRange,
                                   CIEs[CIEPointer]));
    }

    Entries.back()->parseInstructions(Data, &Offset, EndStructureOffset);

    if (Offset != EndStructureOffset) {
      std::string Str;
      raw_string_ostream OS(Str);
      OS << format("Parsing entry instructions at %lx failed", StartOffset);
      report_fatal_error(Str);
    }
  }
}

void DWARFDebugFrame::parse(DataExtractor Data) {
  uint32_t Offset = 0;

  while (Data.isValidOffset(Offset)) {
    uint32_t StartOffset = Offset;

    bool IsDWARF64 = false;
    uint64_t Length = Data.getU32(&Offset);
    uint64_t Id;

    if (Length == UINT32_MAX) {
      // DWARF-64 is distinguished by the first 32 bits of the initial length
      // field being 0xffffffff. Then, the next 64 bits are the actual entry
      // length.
      IsDWARF64 = true;
      Length = Data.getU64(&Offset);
    }

    // At this point, Offset points to the next field after Length.
    // Length is the structure size excluding itself. Compute an offset one
    // past the end of the structure (needed to know how many instructions to
    // read).
    // TODO: For honest DWARF64 support, DataExtractor will have to treat
    //       offset_ptr as uint64_t*
    uint32_t EndStructureOffset = Offset + static_cast<uint32_t>(Length);

    // The Id field's size depends on the DWARF format
    Id = Data.getUnsigned(&Offset, IsDWARF64 ? 8 : 4);
    bool IsCIE = ((IsDWARF64 && Id == DW64_CIE_ID) || Id == DW_CIE_ID);

    if (IsCIE) {
      // Note: this is specifically DWARFv3 CIE header structure. It was
      // changed in DWARFv4. We currently don't support reading DWARFv4
      // here because LLVM itself does not emit it (and LLDB doesn't
      // support it either).
      uint8_t Version = Data.getU8(&Offset);
      const char *Augmentation = Data.getCStr(&Offset);
      uint64_t CodeAlignmentFactor = Data.getULEB128(&Offset);
      int64_t DataAlignmentFactor = Data.getSLEB128(&Offset);
      uint64_t ReturnAddressRegister = Data.getULEB128(&Offset);

      Entries.emplace_back(new CIE(StartOffset, Length, Version,
                                   StringRef(Augmentation), CodeAlignmentFactor,
                                   DataAlignmentFactor, ReturnAddressRegister));
    } else {
      // FDE
      uint64_t CIEPointer = Id;
      uint64_t InitialLocation = Data.getAddress(&Offset);
      uint64_t AddressRange = Data.getAddress(&Offset);

      Entries.emplace_back(new FDE(StartOffset, Length, CIEPointer,
                                   InitialLocation, AddressRange));
    }

    Entries.back()->parseInstructions(Data, &Offset, EndStructureOffset);

    if (Offset != EndStructureOffset) {
      string_ostream Str;
      Str << format("Parsing entry instructions at %lx failed", StartOffset);
      report_fatal_error(Str.str());
    }
  }
}

void FrameEntry::parseInstructions(DataExtractor Data, uint32_t *Offset,
                                   uint32_t EndOffset) {
  while (*Offset < EndOffset) {
    uint8_t Opcode = Data.getU8(Offset);
    // Some instructions have a primary opcode encoded in the top bits.
    uint8_t Primary = Opcode & DWARF_CFI_PRIMARY_OPCODE_MASK;

    if (Primary) {
      // If it's a primary opcode, the first operand is encoded in the bottom
      // bits of the opcode itself.
      uint64_t Op1 = Opcode & DWARF_CFI_PRIMARY_OPERAND_MASK;
      switch (Primary) {
        default: llvm_unreachable("Impossible primary CFI opcode");
        case DW_CFA_advance_loc:
        case DW_CFA_restore:
          addInstruction(Primary, Op1);
          break;
        case DW_CFA_offset:
          addInstruction(Primary, Op1, Data.getULEB128(Offset));
          break;
      }
    } else {
      // Extended opcode - its value is Opcode itself.
      switch (Opcode) {
        default: llvm_unreachable("Invalid extended CFI opcode");
        case DW_CFA_nop:
        case DW_CFA_remember_state:
        case DW_CFA_restore_state:
        case DW_CFA_GNU_window_save:
          // No operands
          addInstruction(Opcode);
          break;
        case DW_CFA_set_loc:
          // Operands: Address
          addInstruction(Opcode, Data.getAddress(Offset));
          break;
        case DW_CFA_advance_loc1:
          // Operands: 1-byte delta
          addInstruction(Opcode, Data.getU8(Offset));
          break;
        case DW_CFA_advance_loc2:
          // Operands: 2-byte delta
          addInstruction(Opcode, Data.getU16(Offset));
          break;
        case DW_CFA_advance_loc4:
          // Operands: 4-byte delta
          addInstruction(Opcode, Data.getU32(Offset));
          break;
        case DW_CFA_restore_extended:
        case DW_CFA_undefined:
        case DW_CFA_same_value:
        case DW_CFA_def_cfa_register:
        case DW_CFA_def_cfa_offset:
        case DW_CFA_GNU_args_size:
          // Operands: ULEB128
          addInstruction(Opcode, Data.getULEB128(Offset));
          break;
        case DW_CFA_def_cfa_offset_sf:
          // Operands: SLEB128
          addInstruction(Opcode, Data.getSLEB128(Offset));
          break;
        case DW_CFA_offset_extended:
        case DW_CFA_register:
        case DW_CFA_def_cfa:
        case DW_CFA_val_offset: {
          // Operands: ULEB128, ULEB128
          // Note: We can not embed getULEB128 directly into function
          // argument list. getULEB128 changes Offset and order of evaluation
          // for arguments is unspecified.
          auto op1 = Data.getULEB128(Offset);
          auto op2 = Data.getULEB128(Offset);
          addInstruction(Opcode, op1, op2);
          break;
        }
        case DW_CFA_offset_extended_sf:
        case DW_CFA_def_cfa_sf:
        case DW_CFA_val_offset_sf: {
          // Operands: ULEB128, SLEB128
          // Note: see comment for the previous case
          auto op1 = Data.getULEB128(Offset);
          auto op2 = (uint64_t)Data.getSLEB128(Offset);
          addInstruction(Opcode, op1, op2);
          break;
        }
        case DW_CFA_def_cfa_expression:
          // FIXME: Parse the actual instruction.
          *Offset += Data.getULEB128(Offset);
          break;
        case DW_CFA_expression:
        case DW_CFA_val_expression: {
          // FIXME: Parse the actual instruction.
          Data.getULEB128(Offset);
          *Offset += Data.getULEB128(Offset);
          break;
        }
      }
    }
  }
}

bool
DWARFDebugLine::parseStatementTable(DataExtractor debug_line_data,
                                    uint32_t *offset_ptr, State &state) {
  const uint32_t debug_line_offset = *offset_ptr;

  Prologue *prologue = &state.Prologue;

  if (!parsePrologue(debug_line_data, offset_ptr, prologue)) {
    // Restore our offset and return false to indicate failure!
    *offset_ptr = debug_line_offset;
    return false;
  }

  const uint32_t end_offset = debug_line_offset + prologue->TotalLength +
                              sizeof(prologue->TotalLength);

  state.reset();

  while (*offset_ptr < end_offset) {
    uint8_t opcode = debug_line_data.getU8(offset_ptr);

    if (opcode == 0) {
      // Extended Opcodes always start with a zero opcode followed by
      // a uleb128 length so you can skip ones you don't know about
      uint32_t ext_offset = *offset_ptr;
      uint64_t len = debug_line_data.getULEB128(offset_ptr);
      uint32_t arg_size = len - (*offset_ptr - ext_offset);

      uint8_t sub_opcode = debug_line_data.getU8(offset_ptr);
      switch (sub_opcode) {
      case DW_LNE_end_sequence:
        // Set the end_sequence register of the state machine to true and
        // append a row to the matrix using the current values of the
        // state-machine registers. Then reset the registers to the initial
        // values specified above. Every statement program sequence must end
        // with a DW_LNE_end_sequence instruction which creates a row whose
        // address is that of the byte after the last target machine instruction
        // of the sequence.
        state.EndSequence = true;
        state.appendRowToMatrix(*offset_ptr);
        state.reset();
        break;

      case DW_LNE_set_address:
        // Takes a single relocatable address as an operand. The size of the
        // operand is the size appropriate to hold an address on the target
        // machine. Set the address register to the value given by the
        // relocatable address. All of the other statement program opcodes
        // that affect the address register add a delta to it. This instruction
        // stores a relocatable value into it instead.
        state.Address = debug_line_data.getAddress(offset_ptr);
        break;

      case DW_LNE_define_file:
        // Takes 4 arguments. The first is a null terminated string containing
        // a source file name. The second is an unsigned LEB128 number
        // representing the directory index of the directory in which the file
        // was found. The third is an unsigned LEB128 number representing the
        // time of last modification of the file. The fourth is an unsigned
        // LEB128 number representing the length in bytes of the file. The time
        // and length fields may contain LEB128(0) if the information is not
        // available.
        //
        // The directory index represents an entry in the include_directories
        // section of the statement program prologue. The index is LEB128(0)
        // if the file was found in the current directory of the compilation,
        // LEB128(1) if it was found in the first directory in the
        // include_directories section, and so on. The directory index is
        // ignored for file names that represent full path names.
        //
        // The files are numbered, starting at 1, in the order in which they
        // appear; the names in the prologue come before names defined by
        // the DW_LNE_define_file instruction. These numbers are used in the
        // the file register of the state machine.
        {
          FileNameEntry fileEntry;
          fileEntry.Name = debug_line_data.getCStr(offset_ptr);
          fileEntry.DirIdx = debug_line_data.getULEB128(offset_ptr);
          fileEntry.ModTime = debug_line_data.getULEB128(offset_ptr);
          fileEntry.Length = debug_line_data.getULEB128(offset_ptr);
          prologue->FileNames.push_back(fileEntry);
        }
        break;

      default:
        // Length doesn't include the zero opcode byte or the length itself, but
        // it does include the sub_opcode, so we have to adjust for that below
        (*offset_ptr) += arg_size;
        break;
      }
    } else if (opcode < prologue->OpcodeBase) {
      switch (opcode) {
      // Standard Opcodes
      case DW_LNS_copy:
        // Takes no arguments. Append a row to the matrix using the
        // current values of the state-machine registers. Then set
        // the basic_block register to false.
        state.appendRowToMatrix(*offset_ptr);
        break;

//.........这里部分代码省略.........

void DWARFDebugFrame::parse(DataExtractor Data) {
  uint32_t Offset = 0;
  DenseMap<uint32_t, CIE *> CIEs;

  while (Data.isValidOffset(Offset)) {
    uint32_t StartOffset = Offset;

    auto ReportError = [StartOffset](const char *ErrorMsg) {
      std::string Str;
      raw_string_ostream OS(Str);
      OS << format(ErrorMsg, StartOffset);
      OS.flush();
      report_fatal_error(Str);
    };

    bool IsDWARF64 = false;
    uint64_t Length = Data.getU32(&Offset);
    uint64_t Id;

    if (Length == UINT32_MAX) {
      // DWARF-64 is distinguished by the first 32 bits of the initial length
      // field being 0xffffffff. Then, the next 64 bits are the actual entry
      // length.
      IsDWARF64 = true;
      Length = Data.getU64(&Offset);
    }

    // At this point, Offset points to the next field after Length.
    // Length is the structure size excluding itself. Compute an offset one
    // past the end of the structure (needed to know how many instructions to
    // read).
    // TODO: For honest DWARF64 support, DataExtractor will have to treat
    //       offset_ptr as uint64_t*
    uint32_t StartStructureOffset = Offset;
    uint32_t EndStructureOffset = Offset + static_cast<uint32_t>(Length);

    // The Id field's size depends on the DWARF format
    Id = Data.getUnsigned(&Offset, (IsDWARF64 && !IsEH) ? 8 : 4);
    bool IsCIE = ((IsDWARF64 && Id == DW64_CIE_ID) ||
                  Id == DW_CIE_ID ||
                  (IsEH && !Id));

    if (IsCIE) {
      uint8_t Version = Data.getU8(&Offset);
      const char *Augmentation = Data.getCStr(&Offset);
      StringRef AugmentationString(Augmentation ? Augmentation : "");
      uint8_t AddressSize = Version < 4 ? Data.getAddressSize() :
                                          Data.getU8(&Offset);
      Data.setAddressSize(AddressSize);
      uint8_t SegmentDescriptorSize = Version < 4 ? 0 : Data.getU8(&Offset);
      uint64_t CodeAlignmentFactor = Data.getULEB128(&Offset);
      int64_t DataAlignmentFactor = Data.getSLEB128(&Offset);
      uint64_t ReturnAddressRegister = Data.getULEB128(&Offset);

      // Parse the augmentation data for EH CIEs
      StringRef AugmentationData("");
      uint32_t FDEPointerEncoding = DW_EH_PE_omit;
      uint32_t LSDAPointerEncoding = DW_EH_PE_omit;
      if (IsEH) {
        Optional<uint32_t> PersonalityEncoding;
        Optional<uint64_t> Personality;

        Optional<uint64_t> AugmentationLength;
        uint32_t StartAugmentationOffset;
        uint32_t EndAugmentationOffset;

        // Walk the augmentation string to get all the augmentation data.
        for (unsigned i = 0, e = AugmentationString.size(); i != e; ++i) {
          switch (AugmentationString[i]) {
            default:
              ReportError("Unknown augmentation character in entry at %lx");
            case 'L':
              LSDAPointerEncoding = Data.getU8(&Offset);
              break;
            case 'P': {
              if (Personality)
                ReportError("Duplicate personality in entry at %lx");
              PersonalityEncoding = Data.getU8(&Offset);
              Personality = readPointer(Data, Offset, *PersonalityEncoding);
              break;
            }
            case 'R':
              FDEPointerEncoding = Data.getU8(&Offset);
              break;
            case 'z':
              if (i)
                ReportError("'z' must be the first character at %lx");
              // Parse the augmentation length first.  We only parse it if
              // the string contains a 'z'.
              AugmentationLength = Data.getULEB128(&Offset);
              StartAugmentationOffset = Offset;
              EndAugmentationOffset = Offset +
                static_cast<uint32_t>(*AugmentationLength);
          }
        }

        if (AugmentationLength.hasValue()) {
          if (Offset != EndAugmentationOffset)
            ReportError("Parsing augmentation data at %lx failed");

//.........这里部分代码省略.........

bool DWARFDebugLine::LineTable::parse(DataExtractor debug_line_data,
                                      const RelocAddrMap *RMap,
                                      uint32_t *offset_ptr) {
  const uint32_t debug_line_offset = *offset_ptr;

  clear();

  if (!Prologue.parse(debug_line_data, offset_ptr)) {
    // Restore our offset and return false to indicate failure!
    *offset_ptr = debug_line_offset;
    return false;
  }

  const uint32_t end_offset =
      debug_line_offset + Prologue.TotalLength + Prologue.sizeofTotalLength();

  ParsingState State(this);

  while (*offset_ptr < end_offset) {
    uint8_t opcode = debug_line_data.getU8(offset_ptr);

    if (opcode == 0) {
      // Extended Opcodes always start with a zero opcode followed by
      // a uleb128 length so you can skip ones you don't know about
      uint32_t ext_offset = *offset_ptr;
      uint64_t len = debug_line_data.getULEB128(offset_ptr);
      uint32_t arg_size = len - (*offset_ptr - ext_offset);

      uint8_t sub_opcode = debug_line_data.getU8(offset_ptr);
      switch (sub_opcode) {
      case DW_LNE_end_sequence:
        // Set the end_sequence register of the state machine to true and
        // append a row to the matrix using the current values of the
        // state-machine registers. Then reset the registers to the initial
        // values specified above. Every statement program sequence must end
        // with a DW_LNE_end_sequence instruction which creates a row whose
        // address is that of the byte after the last target machine instruction
        // of the sequence.
        State.Row.EndSequence = true;
        State.appendRowToMatrix(*offset_ptr);
        State.resetRowAndSequence();
        break;

      case DW_LNE_set_address:
        // Takes a single relocatable address as an operand. The size of the
        // operand is the size appropriate to hold an address on the target
        // machine. Set the address register to the value given by the
        // relocatable address. All of the other statement program opcodes
        // that affect the address register add a delta to it. This instruction
        // stores a relocatable value into it instead.
        {
          // If this address is in our relocation map, apply the relocation.
          RelocAddrMap::const_iterator AI = RMap->find(*offset_ptr);
          if (AI != RMap->end()) {
            const std::pair<uint8_t, int64_t> &R = AI->second;
            State.Row.Address =
                debug_line_data.getAddress(offset_ptr) + R.second;
          } else
            State.Row.Address = debug_line_data.getAddress(offset_ptr);
        }
        break;

      case DW_LNE_define_file:
        // Takes 4 arguments. The first is a null terminated string containing
        // a source file name. The second is an unsigned LEB128 number
        // representing the directory index of the directory in which the file
        // was found. The third is an unsigned LEB128 number representing the
        // time of last modification of the file. The fourth is an unsigned
        // LEB128 number representing the length in bytes of the file. The time
        // and length fields may contain LEB128(0) if the information is not
        // available.
        //
        // The directory index represents an entry in the include_directories
        // section of the statement program prologue. The index is LEB128(0)
        // if the file was found in the current directory of the compilation,
        // LEB128(1) if it was found in the first directory in the
        // include_directories section, and so on. The directory index is
        // ignored for file names that represent full path names.
        //
        // The files are numbered, starting at 1, in the order in which they
        // appear; the names in the prologue come before names defined by
        // the DW_LNE_define_file instruction. These numbers are used in the
        // the file register of the state machine.
        {
          FileNameEntry fileEntry;
          fileEntry.Name = debug_line_data.getCStr(offset_ptr);
          fileEntry.DirIdx = debug_line_data.getULEB128(offset_ptr);
          fileEntry.ModTime = debug_line_data.getULEB128(offset_ptr);
          fileEntry.Length = debug_line_data.getULEB128(offset_ptr);
          Prologue.FileNames.push_back(fileEntry);
        }
        break;

      case DW_LNE_set_discriminator:
        State.Row.Discriminator = debug_line_data.getULEB128(offset_ptr);
        break;

      default:
        // Length doesn't include the zero opcode byte or the length itself, but
        // it does include the sub_opcode, so we have to adjust for that below
//.........这里部分代码省略.........