bool DWARFDebugLine::Prologue::parse(DataExtractor debug_line_data,
uint32_t *offset_ptr) {
const uint32_t prologue_offset = *offset_ptr;
clear();
TotalLength = debug_line_data.getU32(offset_ptr);
Version = debug_line_data.getU16(offset_ptr);
if (Version < 2)
return false;
PrologueLength = debug_line_data.getU32(offset_ptr);
const uint32_t end_prologue_offset = PrologueLength + *offset_ptr;
MinInstLength = debug_line_data.getU8(offset_ptr);
if (Version >= 4)
MaxOpsPerInst = debug_line_data.getU8(offset_ptr);
DefaultIsStmt = debug_line_data.getU8(offset_ptr);
LineBase = debug_line_data.getU8(offset_ptr);
LineRange = debug_line_data.getU8(offset_ptr);
OpcodeBase = debug_line_data.getU8(offset_ptr);
StandardOpcodeLengths.reserve(OpcodeBase - 1);
for (uint32_t i = 1; i < OpcodeBase; ++i) {
uint8_t op_len = debug_line_data.getU8(offset_ptr);
StandardOpcodeLengths.push_back(op_len);
}
while (*offset_ptr < end_prologue_offset) {
const char *s = debug_line_data.getCStr(offset_ptr);
if (s && s[0])
IncludeDirectories.push_back(s);
else
break;
}
while (*offset_ptr < end_prologue_offset) {
const char *name = debug_line_data.getCStr(offset_ptr);
if (name && name[0]) {
FileNameEntry fileEntry;
fileEntry.Name = name;
fileEntry.DirIdx = debug_line_data.getULEB128(offset_ptr);
fileEntry.ModTime = debug_line_data.getULEB128(offset_ptr);
fileEntry.Length = debug_line_data.getULEB128(offset_ptr);
FileNames.push_back(fileEntry);
} else {
break;
}
}
if (*offset_ptr != end_prologue_offset) {
fprintf(stderr, "warning: parsing line table prologue at 0x%8.8x should"
" have ended at 0x%8.8x but it ended at 0x%8.8x\n",
prologue_offset, end_prologue_offset, *offset_ptr);
return false;
}
return true;
}
void DWARFDebugMacro::parse(DataExtractor data) {
uint32_t Offset = 0;
while (data.isValidOffset(Offset)) {
// A macro list entry consists of:
Entry E;
// 1. Macinfo type
E.Type = data.getULEB128(&Offset);
if (E.Type == 0) {
// Reached end of ".debug_macinfo" section.
return;
}
switch (E.Type) {
default:
// Got a corrupted ".debug_macinfo" section (invalid macinfo type).
// Push the corrupted entry to the list and halt parsing.
E.Type = DW_MACINFO_invalid;
Macros.push_back(E);
return;
case DW_MACINFO_define:
case DW_MACINFO_undef:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Macro string
E.MacroStr = data.getCStr(&Offset);
break;
case DW_MACINFO_start_file:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Source file id
E.File = data.getULEB128(&Offset);
break;
case DW_MACINFO_end_file:
break;
case DW_MACINFO_vendor_ext:
// 2. Vendor extension constant
E.ExtConstant = data.getULEB128(&Offset);
// 3. Vendor extension string
E.ExtStr = data.getCStr(&Offset);
break;
}
Macros.push_back(E);
}
}
static Expected<const char *>
getIndexedString(uint32_t Form, DataExtractor InfoData, uint32_t &InfoOffset,
StringRef StrOffsets, StringRef Str) {
if (Form == dwarf::DW_FORM_string)
return InfoData.getCStr(&InfoOffset);
if (Form != dwarf::DW_FORM_GNU_str_index)
return make_error<DWPError>(
"string field encoded without DW_FORM_string or DW_FORM_GNU_str_index");
auto StrIndex = InfoData.getULEB128(&InfoOffset);
DataExtractor StrOffsetsData(StrOffsets, true, 0);
uint32_t StrOffsetsOffset = 4 * StrIndex;
uint32_t StrOffset = StrOffsetsData.getU32(&StrOffsetsOffset);
DataExtractor StrData(Str, true, 0);
return StrData.getCStr(&StrOffset);
}
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);
}
}
}
bool
DWARFFormValue::skipValue(uint16_t form, DataExtractor debug_info_data,
uint32_t *offset_ptr, const DWARFUnit *cu) {
bool indirect = false;
do {
switch (form) {
// Blocks if inlined data that have a length field and the data bytes
// inlined in the .debug_info
case DW_FORM_exprloc:
case DW_FORM_block: {
uint64_t size = debug_info_data.getULEB128(offset_ptr);
*offset_ptr += size;
return true;
}
case DW_FORM_block1: {
uint8_t size = debug_info_data.getU8(offset_ptr);
*offset_ptr += size;
return true;
}
case DW_FORM_block2: {
uint16_t size = debug_info_data.getU16(offset_ptr);
*offset_ptr += size;
return true;
}
case DW_FORM_block4: {
uint32_t size = debug_info_data.getU32(offset_ptr);
*offset_ptr += size;
return true;
}
// Inlined NULL terminated C-strings
case DW_FORM_string:
debug_info_data.getCStr(offset_ptr);
return true;
// Compile unit address sized values
case DW_FORM_addr:
*offset_ptr += cu->getAddressByteSize();
return true;
case DW_FORM_ref_addr:
*offset_ptr += getRefAddrSize(cu->getAddressByteSize(), cu->getVersion());
return true;
// 0 byte values - implied from the form.
case DW_FORM_flag_present:
return true;
// 1 byte values
case DW_FORM_data1:
case DW_FORM_flag:
case DW_FORM_ref1:
*offset_ptr += 1;
return true;
// 2 byte values
case DW_FORM_data2:
case DW_FORM_ref2:
*offset_ptr += 2;
return true;
// 4 byte values
case DW_FORM_strp:
case DW_FORM_data4:
case DW_FORM_ref4:
*offset_ptr += 4;
return true;
// 8 byte values
case DW_FORM_data8:
case DW_FORM_ref8:
case DW_FORM_ref_sig8:
*offset_ptr += 8;
return true;
// signed or unsigned LEB 128 values
// case DW_FORM_APPLE_db_str:
case DW_FORM_sdata:
case DW_FORM_udata:
case DW_FORM_ref_udata:
case DW_FORM_GNU_str_index:
case DW_FORM_GNU_addr_index:
debug_info_data.getULEB128(offset_ptr);
return true;
case DW_FORM_indirect:
indirect = true;
form = debug_info_data.getULEB128(offset_ptr);
break;
// FIXME: 4 for DWARF32, 8 for DWARF64.
case DW_FORM_sec_offset:
*offset_ptr += 4;
return true;
default:
return false;
}
} while (indirect);
return true;
}
bool DWARFFormValue::extractValue(DataExtractor data, uint32_t *offset_ptr,
const DWARFUnit *cu) {
bool indirect = false;
bool is_block = false;
Value.data = nullptr;
// Read the value for the form into value and follow and DW_FORM_indirect
// instances we run into
do {
indirect = false;
switch (Form) {
case DW_FORM_addr:
case DW_FORM_ref_addr: {
uint16_t AddrSize =
(Form == DW_FORM_addr)
? cu->getAddressByteSize()
: getRefAddrSize(cu->getAddressByteSize(), cu->getVersion());
RelocAddrMap::const_iterator AI = cu->getRelocMap()->find(*offset_ptr);
if (AI != cu->getRelocMap()->end()) {
const std::pair<uint8_t, int64_t> &R = AI->second;
Value.uval = data.getUnsigned(offset_ptr, AddrSize) + R.second;
} else
Value.uval = data.getUnsigned(offset_ptr, AddrSize);
break;
}
case DW_FORM_exprloc:
case DW_FORM_block:
Value.uval = data.getULEB128(offset_ptr);
is_block = true;
break;
case DW_FORM_block1:
Value.uval = data.getU8(offset_ptr);
is_block = true;
break;
case DW_FORM_block2:
Value.uval = data.getU16(offset_ptr);
is_block = true;
break;
case DW_FORM_block4:
Value.uval = data.getU32(offset_ptr);
is_block = true;
break;
case DW_FORM_data1:
case DW_FORM_ref1:
case DW_FORM_flag:
Value.uval = data.getU8(offset_ptr);
break;
case DW_FORM_data2:
case DW_FORM_ref2:
Value.uval = data.getU16(offset_ptr);
break;
case DW_FORM_data4:
case DW_FORM_ref4: {
RelocAddrMap::const_iterator AI = cu->getRelocMap()->find(*offset_ptr);
Value.uval = data.getU32(offset_ptr);
if (AI != cu->getRelocMap()->end())
Value.uval += AI->second.second;
break;
}
case DW_FORM_data8:
case DW_FORM_ref8:
Value.uval = data.getU64(offset_ptr);
break;
case DW_FORM_sdata:
Value.sval = data.getSLEB128(offset_ptr);
break;
case DW_FORM_strp: {
RelocAddrMap::const_iterator AI
= cu->getRelocMap()->find(*offset_ptr);
if (AI != cu->getRelocMap()->end()) {
const std::pair<uint8_t, int64_t> &R = AI->second;
Value.uval = data.getU32(offset_ptr) + R.second;
} else
Value.uval = data.getU32(offset_ptr);
break;
}
case DW_FORM_udata:
case DW_FORM_ref_udata:
Value.uval = data.getULEB128(offset_ptr);
break;
case DW_FORM_string:
Value.cstr = data.getCStr(offset_ptr);
break;
case DW_FORM_indirect:
Form = data.getULEB128(offset_ptr);
indirect = true;
break;
case DW_FORM_sec_offset: {
// FIXME: This is 64-bit for DWARF64.
RelocAddrMap::const_iterator AI
= cu->getRelocMap()->find(*offset_ptr);
if (AI != cu->getRelocMap()->end()) {
const std::pair<uint8_t, int64_t> &R = AI->second;
Value.uval = data.getU32(offset_ptr) + R.second;
} else
Value.uval = data.getU32(offset_ptr);
break;
}
case DW_FORM_flag_present:
Value.uval = 1;
break;
case DW_FORM_ref_sig8:
Value.uval = data.getU64(offset_ptr);
break;
case DW_FORM_GNU_addr_index:
case DW_FORM_GNU_str_index:
Value.uval = data.getULEB128(offset_ptr);
break;
default:
return false;
}
} while (indirect);
if (is_block) {
StringRef str = data.getData().substr(*offset_ptr, Value.uval);
Value.data = nullptr;
if (!str.empty()) {
Value.data = reinterpret_cast<const uint8_t *>(str.data());
*offset_ptr += Value.uval;
}
}
return true;
}
bool DWARFFormValue::skipValue(dwarf::Form Form, DataExtractor DebugInfoData,
uint32_t *OffsetPtr,
const DWARFFormParams Params) {
bool Indirect = false;
do {
switch (Form) {
// Blocks of inlined data that have a length field and the data bytes
// inlined in the .debug_info.
case DW_FORM_exprloc:
case DW_FORM_block: {
uint64_t size = DebugInfoData.getULEB128(OffsetPtr);
*OffsetPtr += size;
return true;
}
case DW_FORM_block1: {
uint8_t size = DebugInfoData.getU8(OffsetPtr);
*OffsetPtr += size;
return true;
}
case DW_FORM_block2: {
uint16_t size = DebugInfoData.getU16(OffsetPtr);
*OffsetPtr += size;
return true;
}
case DW_FORM_block4: {
uint32_t size = DebugInfoData.getU32(OffsetPtr);
*OffsetPtr += size;
return true;
}
// Inlined NULL terminated C-strings.
case DW_FORM_string:
DebugInfoData.getCStr(OffsetPtr);
return true;
case DW_FORM_addr:
case DW_FORM_ref_addr:
case DW_FORM_flag_present:
case DW_FORM_data1:
case DW_FORM_data2:
case DW_FORM_data4:
case DW_FORM_data8:
case DW_FORM_data16:
case DW_FORM_flag:
case DW_FORM_ref1:
case DW_FORM_ref2:
case DW_FORM_ref4:
case DW_FORM_ref8:
case DW_FORM_ref_sig8:
case DW_FORM_ref_sup4:
case DW_FORM_ref_sup8:
case DW_FORM_strx1:
case DW_FORM_strx2:
case DW_FORM_strx4:
case DW_FORM_addrx1:
case DW_FORM_addrx2:
case DW_FORM_addrx4:
case DW_FORM_sec_offset:
case DW_FORM_strp:
case DW_FORM_strp_sup:
case DW_FORM_line_strp:
case DW_FORM_GNU_ref_alt:
case DW_FORM_GNU_strp_alt:
if (Optional<uint8_t> FixedSize =
DWARFFormValue::getFixedByteSize(Form, Params)) {
*OffsetPtr += *FixedSize;
return true;
}
return false;
// signed or unsigned LEB 128 values.
case DW_FORM_sdata:
DebugInfoData.getSLEB128(OffsetPtr);
return true;
case DW_FORM_udata:
case DW_FORM_ref_udata:
case DW_FORM_strx:
case DW_FORM_addrx:
case DW_FORM_loclistx:
case DW_FORM_rnglistx:
case DW_FORM_GNU_addr_index:
case DW_FORM_GNU_str_index:
DebugInfoData.getULEB128(OffsetPtr);
return true;
case DW_FORM_indirect:
Indirect = true;
Form = static_cast<dwarf::Form>(DebugInfoData.getULEB128(OffsetPtr));
break;
default:
return false;
}
} while (Indirect);
return true;
}
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());
}
}
}
bool
DWARFFormValue::extractValue(DataExtractor data, uint32_t *offset_ptr,
const DWARFCompileUnit *cu) {
bool indirect = false;
bool is_block = false;
Value.data = NULL;
// Read the value for the form into value and follow and DW_FORM_indirect
// instances we run into
do {
indirect = false;
switch (Form) {
case DW_FORM_addr:
case DW_FORM_ref_addr:
Value.uval = data.getUnsigned(offset_ptr, cu->getAddressByteSize());
break;
case DW_FORM_block:
Value.uval = data.getULEB128(offset_ptr);
is_block = true;
break;
case DW_FORM_block1:
Value.uval = data.getU8(offset_ptr);
is_block = true;
break;
case DW_FORM_block2:
Value.uval = data.getU16(offset_ptr);
is_block = true;
break;
case DW_FORM_block4:
Value.uval = data.getU32(offset_ptr);
is_block = true;
break;
case DW_FORM_data1:
case DW_FORM_ref1:
case DW_FORM_flag:
Value.uval = data.getU8(offset_ptr);
break;
case DW_FORM_data2:
case DW_FORM_ref2:
Value.uval = data.getU16(offset_ptr);
break;
case DW_FORM_data4:
case DW_FORM_ref4:
Value.uval = data.getU32(offset_ptr);
break;
case DW_FORM_data8:
case DW_FORM_ref8:
Value.uval = data.getU64(offset_ptr);
break;
case DW_FORM_sdata:
Value.sval = data.getSLEB128(offset_ptr);
break;
case DW_FORM_strp:
Value.uval = data.getU32(offset_ptr);
break;
case DW_FORM_udata:
case DW_FORM_ref_udata:
Value.uval = data.getULEB128(offset_ptr);
break;
case DW_FORM_string:
Value.cstr = data.getCStr(offset_ptr);
// Set the string value to also be the data for inlined cstr form
// values only so we can tell the differnence between DW_FORM_string
// and DW_FORM_strp form values
Value.data = (uint8_t*)Value.cstr;
break;
case DW_FORM_indirect:
Form = data.getULEB128(offset_ptr);
indirect = true;
break;
default:
return false;
}
} while (indirect);
if (is_block) {
StringRef str = data.getData().substr(*offset_ptr, Value.uval);
Value.data = NULL;
if (!str.empty()) {
Value.data = reinterpret_cast<const uint8_t *>(str.data());
*offset_ptr += Value.uval;
}
}
return true;
}
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;
case DW_LNS_advance_pc:
// Takes a single unsigned LEB128 operand, multiplies it by the
// min_inst_length field of the prologue, and adds the
// result to the address register of the state machine.
state.Address += debug_line_data.getULEB128(offset_ptr) *
prologue->MinInstLength;
break;
case DW_LNS_advance_line:
// Takes a single signed LEB128 operand and adds that value to
// the line register of the state machine.
state.Line += debug_line_data.getSLEB128(offset_ptr);
break;
case DW_LNS_set_file:
// Takes a single unsigned LEB128 operand and stores it in the file
// register of the state machine.
state.File = debug_line_data.getULEB128(offset_ptr);
break;
case DW_LNS_set_column:
// Takes a single unsigned LEB128 operand and stores it in the
// column register of the state machine.
state.Column = debug_line_data.getULEB128(offset_ptr);
break;
case DW_LNS_negate_stmt:
// Takes no arguments. Set the is_stmt register of the state
// machine to the logical negation of its current value.
state.IsStmt = !state.IsStmt;
break;
case DW_LNS_set_basic_block:
// Takes no arguments. Set the basic_block register of the
// state machine to true
state.BasicBlock = true;
break;
case DW_LNS_const_add_pc:
// Takes no arguments. Add to the address register of the state
// machine the address increment value corresponding to special
// opcode 255. The motivation for DW_LNS_const_add_pc is this:
// when the statement program needs to advance the address by a
// small amount, it can use a single special opcode, which occupies
// a single byte. When it needs to advance the address by up to
// twice the range of the last special opcode, it can use
// DW_LNS_const_add_pc followed by a special opcode, for a total
// of two bytes. Only if it needs to advance the address by more
// than twice that range will it need to use both DW_LNS_advance_pc
// and a special opcode, requiring three or more bytes.
{
uint8_t adjust_opcode = 255 - prologue->OpcodeBase;
uint64_t addr_offset = (adjust_opcode / prologue->LineRange) *
prologue->MinInstLength;
state.Address += addr_offset;
}
break;
case DW_LNS_fixed_advance_pc:
// Takes a single uhalf operand. Add to the address register of
// the state machine the value of the (unencoded) operand. This
// is the only extended opcode that takes an argument that is not
// a variable length number. The motivation for DW_LNS_fixed_advance_pc
// is this: existing assemblers cannot emit DW_LNS_advance_pc or
// special opcodes because they cannot encode LEB128 numbers or
// judge when the computation of a special opcode overflows and
// requires the use of DW_LNS_advance_pc. Such assemblers, however,
// can use DW_LNS_fixed_advance_pc instead, sacrificing compression.
state.Address += debug_line_data.getU16(offset_ptr);
break;
case DW_LNS_set_prologue_end:
// Takes no arguments. Set the prologue_end register of the
// state machine to true
state.PrologueEnd = true;
break;
case DW_LNS_set_epilogue_begin:
// Takes no arguments. Set the basic_block register of the
// state machine to true
state.EpilogueBegin = true;
break;
case DW_LNS_set_isa:
// Takes a single unsigned LEB128 operand and stores it in the
// column register of the state machine.
state.Isa = debug_line_data.getULEB128(offset_ptr);
break;
default:
// Handle any unknown standard opcodes here. We know the lengths
// of such opcodes because they are specified in the prologue
// as a multiple of LEB128 operands for each opcode.
{
assert(opcode - 1U < prologue->StandardOpcodeLengths.size());
uint8_t opcode_length = prologue->StandardOpcodeLengths[opcode - 1];
for (uint8_t i=0; i<opcode_length; ++i)
debug_line_data.getULEB128(offset_ptr);
}
break;
}
} else {
// Special Opcodes
// A special opcode value is chosen based on the amount that needs
// to be added to the line and address registers. The maximum line
// increment for a special opcode is the value of the line_base
// field in the header, plus the value of the line_range field,
// minus 1 (line base + line range - 1). If the desired line
// increment is greater than the maximum line increment, a standard
// opcode must be used instead of a special opcode. The “address
// advance” is calculated by dividing the desired address increment
// by the minimum_instruction_length field from the header. The
// special opcode is then calculated using the following formula:
//
// opcode = (desired line increment - line_base) +
// (line_range * address advance) + opcode_base
//
// If the resulting opcode is greater than 255, a standard opcode
// must be used instead.
//
// To decode a special opcode, subtract the opcode_base from the
// opcode itself to give the adjusted opcode. The amount to
// increment the address register is the result of the adjusted
// opcode divided by the line_range multiplied by the
// minimum_instruction_length field from the header. That is:
//
// address increment = (adjusted opcode / line_range) *
// minimum_instruction_length
//
// The amount to increment the line register is the line_base plus
// the result of the adjusted opcode modulo the line_range. That is:
//
// line increment = line_base + (adjusted opcode % line_range)
uint8_t adjust_opcode = opcode - prologue->OpcodeBase;
uint64_t addr_offset = (adjust_opcode / prologue->LineRange) *
prologue->MinInstLength;
int32_t line_offset = prologue->LineBase +
(adjust_opcode % prologue->LineRange);
state.Line += line_offset;
state.Address += addr_offset;
state.appendRowToMatrix(*offset_ptr);
}
}
state.finalize(*offset_ptr);
return end_offset;
}
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");
AugmentationData = Data.getData().slice(StartAugmentationOffset,
EndAugmentationOffset);
}
}
auto Cie = make_unique<CIE>(StartOffset, Length, Version,
AugmentationString, AddressSize,
SegmentDescriptorSize, CodeAlignmentFactor,
DataAlignmentFactor, ReturnAddressRegister,
AugmentationData, FDEPointerEncoding,
LSDAPointerEncoding);
CIEs[StartOffset] = Cie.get();
Entries.emplace_back(std::move(Cie));
} else {
// FDE
uint64_t CIEPointer = Id;
uint64_t InitialLocation = 0;
uint64_t AddressRange = 0;
CIE *Cie = CIEs[IsEH ? (StartStructureOffset - CIEPointer) : CIEPointer];
if (IsEH) {
// The address size is encoded in the CIE we reference.
if (!Cie)
ReportError("Parsing FDE data at %lx failed due to missing CIE");
InitialLocation = readPointer(Data, Offset,
Cie->getFDEPointerEncoding());
AddressRange = readPointer(Data, Offset,
Cie->getFDEPointerEncoding());
StringRef AugmentationString = Cie->getAugmentationString();
if (!AugmentationString.empty()) {
// Parse the augmentation length and data for this FDE.
uint64_t AugmentationLength = Data.getULEB128(&Offset);
uint32_t EndAugmentationOffset =
Offset + static_cast<uint32_t>(AugmentationLength);
// Decode the LSDA if the CIE augmentation string said we should.
if (Cie->getLSDAPointerEncoding() != DW_EH_PE_omit)
readPointer(Data, Offset, Cie->getLSDAPointerEncoding());
if (Offset != EndAugmentationOffset)
ReportError("Parsing augmentation data at %lx failed");
}
} else {
InitialLocation = Data.getAddress(&Offset);
AddressRange = Data.getAddress(&Offset);
}
Entries.emplace_back(new FDE(StartOffset, Length, CIEPointer,
InitialLocation, AddressRange,
Cie));
}
Entries.back()->parseInstructions(Data, &Offset, EndStructureOffset);
if (Offset != EndStructureOffset)
ReportError("Parsing entry instructions at %lx failed");
}
}
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
(*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;
case DW_LNS_advance_pc:
// Takes a single unsigned LEB128 operand, multiplies it by the
// min_inst_length field of the prologue, and adds the
// result to the address register of the state machine.
State.Row.Address +=
debug_line_data.getULEB128(offset_ptr) * Prologue.MinInstLength;
break;
case DW_LNS_advance_line:
// Takes a single signed LEB128 operand and adds that value to
// the line register of the state machine.
State.Row.Line += debug_line_data.getSLEB128(offset_ptr);
break;
case DW_LNS_set_file:
// Takes a single unsigned LEB128 operand and stores it in the file
// register of the state machine.
State.Row.File = debug_line_data.getULEB128(offset_ptr);
break;
case DW_LNS_set_column:
// Takes a single unsigned LEB128 operand and stores it in the
// column register of the state machine.
State.Row.Column = debug_line_data.getULEB128(offset_ptr);
break;
case DW_LNS_negate_stmt:
// Takes no arguments. Set the is_stmt register of the state
// machine to the logical negation of its current value.
State.Row.IsStmt = !State.Row.IsStmt;
break;
case DW_LNS_set_basic_block:
// Takes no arguments. Set the basic_block register of the
// state machine to true
State.Row.BasicBlock = true;
break;
case DW_LNS_const_add_pc:
// Takes no arguments. Add to the address register of the state
// machine the address increment value corresponding to special
// opcode 255. The motivation for DW_LNS_const_add_pc is this:
// when the statement program needs to advance the address by a
// small amount, it can use a single special opcode, which occupies
// a single byte. When it needs to advance the address by up to
// twice the range of the last special opcode, it can use
// DW_LNS_const_add_pc followed by a special opcode, for a total
// of two bytes. Only if it needs to advance the address by more
// than twice that range will it need to use both DW_LNS_advance_pc
// and a special opcode, requiring three or more bytes.
{
uint8_t adjust_opcode = 255 - Prologue.OpcodeBase;
uint64_t addr_offset =
(adjust_opcode / Prologue.LineRange) * Prologue.MinInstLength;
State.Row.Address += addr_offset;
}
break;
case DW_LNS_fixed_advance_pc:
// Takes a single uhalf operand. Add to the address register of
// the state machine the value of the (unencoded) operand. This
// is the only extended opcode that takes an argument that is not
// a variable length number. The motivation for DW_LNS_fixed_advance_pc
// is this: existing assemblers cannot emit DW_LNS_advance_pc or
// special opcodes because they cannot encode LEB128 numbers or
// judge when the computation of a special opcode overflows and
// requires the use of DW_LNS_advance_pc. Such assemblers, however,
// can use DW_LNS_fixed_advance_pc instead, sacrificing compression.
State.Row.Address += debug_line_data.getU16(offset_ptr);
break;
case DW_LNS_set_prologue_end:
// Takes no arguments. Set the prologue_end register of the
// state machine to true
State.Row.PrologueEnd = true;
break;
case DW_LNS_set_epilogue_begin:
// Takes no arguments. Set the basic_block register of the
// state machine to true
State.Row.EpilogueBegin = true;
break;
case DW_LNS_set_isa:
// Takes a single unsigned LEB128 operand and stores it in the
// column register of the state machine.
State.Row.Isa = debug_line_data.getULEB128(offset_ptr);
break;
default:
// Handle any unknown standard opcodes here. We know the lengths
// of such opcodes because they are specified in the prologue
// as a multiple of LEB128 operands for each opcode.
{
assert(opcode - 1U < Prologue.StandardOpcodeLengths.size());
uint8_t opcode_length = Prologue.StandardOpcodeLengths[opcode - 1];
for (uint8_t i = 0; i < opcode_length; ++i)
debug_line_data.getULEB128(offset_ptr);
}
break;
}
} else {
// Special Opcodes
// A special opcode value is chosen based on the amount that needs
// to be added to the line and address registers. The maximum line
// increment for a special opcode is the value of the line_base
// field in the header, plus the value of the line_range field,
// minus 1 (line base + line range - 1). If the desired line
// increment is greater than the maximum line increment, a standard
// opcode must be used instead of a special opcode. The "address
// advance" is calculated by dividing the desired address increment
// by the minimum_instruction_length field from the header. The
// special opcode is then calculated using the following formula:
//
// opcode = (desired line increment - line_base) +
// (line_range * address advance) + opcode_base
//
// If the resulting opcode is greater than 255, a standard opcode
// must be used instead.
//
// To decode a special opcode, subtract the opcode_base from the
// opcode itself to give the adjusted opcode. The amount to
// increment the address register is the result of the adjusted
// opcode divided by the line_range multiplied by the
// minimum_instruction_length field from the header. That is:
//
// address increment = (adjusted opcode / line_range) *
// minimum_instruction_length
//
// The amount to increment the line register is the line_base plus
// the result of the adjusted opcode modulo the line_range. That is:
//
// line increment = line_base + (adjusted opcode % line_range)
uint8_t adjust_opcode = opcode - Prologue.OpcodeBase;
uint64_t addr_offset =
(adjust_opcode / Prologue.LineRange) * Prologue.MinInstLength;
int32_t line_offset =
Prologue.LineBase + (adjust_opcode % Prologue.LineRange);
State.Row.Line += line_offset;
State.Row.Address += addr_offset;
State.appendRowToMatrix(*offset_ptr);
// Reset discriminator to 0.
State.Row.Discriminator = 0;
}
}
if (!State.Sequence.Empty) {
fprintf(stderr, "warning: last sequence in debug line table is not"
"terminated!\n");
}
// Sort all sequences so that address lookup will work faster.
if (!Sequences.empty()) {
std::sort(Sequences.begin(), Sequences.end(), Sequence::orderByLowPC);
// Note: actually, instruction address ranges of sequences should not
// overlap (in shared objects and executables). If they do, the address
// lookup would still work, though, but result would be ambiguous.
// We don't report warning in this case. For example,
// sometimes .so compiled from multiple object files contains a few
// rudimentary sequences for address ranges [0x0, 0xsomething).
}
return end_offset;
}
bool
DWARFFormValue::extractValue(DataExtractor data, uint32_t *offset_ptr,
const DWARFCompileUnit *cu) {
bool indirect = false;
bool is_block = false;
Value.data = NULL;
// Read the value for the form into value and follow and DW_FORM_indirect
// instances we run into
do {
indirect = false;
switch (Form) {
case DW_FORM_addr:
case DW_FORM_ref_addr: {
RelocAddrMap::const_iterator AI
= cu->getRelocMap()->find(*offset_ptr);
if (AI != cu->getRelocMap()->end()) {
const std::pair<uint8_t, int64_t> &R = AI->second;
Value.uval = data.getUnsigned(offset_ptr, cu->getAddressByteSize()) +
R.second;
} else
Value.uval = data.getUnsigned(offset_ptr, cu->getAddressByteSize());
break;
}
case DW_FORM_exprloc:
case DW_FORM_block:
Value.uval = data.getULEB128(offset_ptr);
is_block = true;
break;
case DW_FORM_block1:
Value.uval = data.getU8(offset_ptr);
is_block = true;
break;
case DW_FORM_block2:
Value.uval = data.getU16(offset_ptr);
is_block = true;
break;
case DW_FORM_block4:
Value.uval = data.getU32(offset_ptr);
is_block = true;
break;
case DW_FORM_data1:
case DW_FORM_ref1:
case DW_FORM_flag:
Value.uval = data.getU8(offset_ptr);
break;
case DW_FORM_data2:
case DW_FORM_ref2:
Value.uval = data.getU16(offset_ptr);
break;
case DW_FORM_data4:
case DW_FORM_ref4:
Value.uval = data.getU32(offset_ptr);
break;
case DW_FORM_data8:
case DW_FORM_ref8:
Value.uval = data.getU64(offset_ptr);
break;
case DW_FORM_sdata:
Value.sval = data.getSLEB128(offset_ptr);
break;
case DW_FORM_strp: {
RelocAddrMap::const_iterator AI
= cu->getRelocMap()->find(*offset_ptr);
if (AI != cu->getRelocMap()->end()) {
const std::pair<uint8_t, int64_t> &R = AI->second;
Value.uval = data.getU32(offset_ptr) + R.second;
} else
Value.uval = data.getU32(offset_ptr);
break;
}
case DW_FORM_udata:
case DW_FORM_ref_udata:
Value.uval = data.getULEB128(offset_ptr);
break;
case DW_FORM_string:
Value.cstr = data.getCStr(offset_ptr);
// Set the string value to also be the data for inlined cstr form
// values only so we can tell the differnence between DW_FORM_string
// and DW_FORM_strp form values
Value.data = (const uint8_t*)Value.cstr;
break;
case DW_FORM_indirect:
Form = data.getULEB128(offset_ptr);
indirect = true;
break;
case DW_FORM_sec_offset:
// FIXME: This is 64-bit for DWARF64.
Value.uval = data.getU32(offset_ptr);
break;
case DW_FORM_flag_present:
Value.uval = 1;
break;
case DW_FORM_ref_sig8:
Value.uval = data.getU64(offset_ptr);
break;
case DW_FORM_GNU_addr_index:
Value.uval = data.getULEB128(offset_ptr);
break;
case DW_FORM_GNU_str_index:
Value.uval = data.getULEB128(offset_ptr);
break;
default:
return false;
}
} while (indirect);
if (is_block) {
StringRef str = data.getData().substr(*offset_ptr, Value.uval);
Value.data = NULL;
if (!str.empty()) {
Value.data = reinterpret_cast<const uint8_t *>(str.data());
*offset_ptr += Value.uval;
}
}
return true;
}