// Parse v2-v4 directory and file tables.
static void
parseV2DirFileTables(const DWARFDataExtractor &DebugLineData,
uint32_t *OffsetPtr, uint64_t EndPrologueOffset,
DWARFDebugLine::ContentTypeTracker &ContentTypes,
std::vector<DWARFFormValue> &IncludeDirectories,
std::vector<DWARFDebugLine::FileNameEntry> &FileNames) {
while (*OffsetPtr < EndPrologueOffset) {
StringRef S = DebugLineData.getCStrRef(OffsetPtr);
if (S.empty())
break;
DWARFFormValue Dir =
DWARFFormValue::createFromPValue(dwarf::DW_FORM_string, S.data());
IncludeDirectories.push_back(Dir);
}
while (*OffsetPtr < EndPrologueOffset) {
StringRef Name = DebugLineData.getCStrRef(OffsetPtr);
if (Name.empty())
break;
DWARFDebugLine::FileNameEntry FileEntry;
FileEntry.Name =
DWARFFormValue::createFromPValue(dwarf::DW_FORM_string, Name.data());
FileEntry.DirIdx = DebugLineData.getULEB128(OffsetPtr);
FileEntry.ModTime = DebugLineData.getULEB128(OffsetPtr);
FileEntry.Length = DebugLineData.getULEB128(OffsetPtr);
FileNames.push_back(FileEntry);
}
ContentTypes.HasModTime = true;
ContentTypes.HasLength = true;
}
// Parse v5 directory/file entry content descriptions.
// Returns the descriptors, or an empty vector if we did not find a path or
// ran off the end of the prologue.
static ContentDescriptors
parseV5EntryFormat(const DWARFDataExtractor &DebugLineData, uint32_t *OffsetPtr,
uint64_t EndPrologueOffset, bool *HasMD5) {
ContentDescriptors Descriptors;
int FormatCount = DebugLineData.getU8(OffsetPtr);
bool HasPath = false;
for (int I = 0; I != FormatCount; ++I) {
if (*OffsetPtr >= EndPrologueOffset)
return ContentDescriptors();
ContentDescriptor Descriptor;
Descriptor.Type =
dwarf::LineNumberEntryFormat(DebugLineData.getULEB128(OffsetPtr));
Descriptor.Form = dwarf::Form(DebugLineData.getULEB128(OffsetPtr));
if (Descriptor.Type == dwarf::DW_LNCT_path)
HasPath = true;
else if (Descriptor.Type == dwarf::DW_LNCT_MD5 && HasMD5)
*HasMD5 = true;
Descriptors.push_back(Descriptor);
}
return HasPath ? Descriptors : ContentDescriptors();
}
// Parse v2-v4 directory and file tables.
static void
parseV2DirFileTables(const DWARFDataExtractor &DebugLineData,
uint32_t *OffsetPtr, uint64_t EndPrologueOffset,
std::vector<StringRef> &IncludeDirectories,
std::vector<DWARFDebugLine::FileNameEntry> &FileNames) {
while (*OffsetPtr < EndPrologueOffset) {
StringRef S = DebugLineData.getCStrRef(OffsetPtr);
if (S.empty())
break;
IncludeDirectories.push_back(S);
}
while (*OffsetPtr < EndPrologueOffset) {
StringRef Name = DebugLineData.getCStrRef(OffsetPtr);
if (Name.empty())
break;
DWARFDebugLine::FileNameEntry FileEntry;
FileEntry.Name = Name;
FileEntry.DirIdx = DebugLineData.getULEB128(OffsetPtr);
FileEntry.ModTime = DebugLineData.getULEB128(OffsetPtr);
FileEntry.Length = DebugLineData.getULEB128(OffsetPtr);
FileNames.push_back(FileEntry);
}
}
bool DWARFFormValue::extractValue(const DWARFDataExtractor &Data,
uint32_t *OffsetPtr, DWARFFormParams FP,
const DWARFUnit *CU) {
U = CU;
bool Indirect = false;
bool IsBlock = 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 Size =
(Form == DW_FORM_addr) ? FP.AddrSize : FP.getRefAddrByteSize();
Value.uval = Data.getRelocatedValue(Size, OffsetPtr, &Value.SectionIndex);
break;
}
case DW_FORM_exprloc:
case DW_FORM_block:
Value.uval = Data.getULEB128(OffsetPtr);
IsBlock = true;
break;
case DW_FORM_block1:
Value.uval = Data.getU8(OffsetPtr);
IsBlock = true;
break;
case DW_FORM_block2:
Value.uval = Data.getU16(OffsetPtr);
IsBlock = true;
break;
case DW_FORM_block4:
Value.uval = Data.getU32(OffsetPtr);
IsBlock = true;
break;
case DW_FORM_data1:
case DW_FORM_ref1:
case DW_FORM_flag:
case DW_FORM_strx1:
case DW_FORM_addrx1:
Value.uval = Data.getU8(OffsetPtr);
break;
case DW_FORM_data2:
case DW_FORM_ref2:
case DW_FORM_strx2:
case DW_FORM_addrx2:
Value.uval = Data.getU16(OffsetPtr);
break;
case DW_FORM_strx3:
Value.uval = Data.getU24(OffsetPtr);
break;
case DW_FORM_data4:
case DW_FORM_ref4:
case DW_FORM_ref_sup4:
case DW_FORM_strx4:
case DW_FORM_addrx4:
Value.uval = Data.getRelocatedValue(4, OffsetPtr);
break;
case DW_FORM_data8:
case DW_FORM_ref8:
case DW_FORM_ref_sup8:
Value.uval = Data.getU64(OffsetPtr);
break;
case DW_FORM_data16:
// Treat this like a 16-byte block.
Value.uval = 16;
IsBlock = true;
break;
case DW_FORM_sdata:
Value.sval = Data.getSLEB128(OffsetPtr);
break;
case DW_FORM_udata:
case DW_FORM_ref_udata:
Value.uval = Data.getULEB128(OffsetPtr);
break;
case DW_FORM_string:
Value.cstr = Data.getCStr(OffsetPtr);
break;
case DW_FORM_indirect:
Form = static_cast<dwarf::Form>(Data.getULEB128(OffsetPtr));
Indirect = true;
break;
case DW_FORM_strp:
case DW_FORM_sec_offset:
case DW_FORM_GNU_ref_alt:
case DW_FORM_GNU_strp_alt:
case DW_FORM_line_strp:
case DW_FORM_strp_sup: {
Value.uval =
Data.getRelocatedValue(FP.getDwarfOffsetByteSize(), OffsetPtr);
break;
}
case DW_FORM_flag_present:
Value.uval = 1;
break;
case DW_FORM_ref_sig8:
Value.uval = Data.getU64(OffsetPtr);
break;
case DW_FORM_GNU_addr_index:
case DW_FORM_GNU_str_index:
case DW_FORM_strx:
Value.uval = Data.getULEB128(OffsetPtr);
break;
default:
// DWARFFormValue::skipValue() will have caught this and caused all
// DWARF DIEs to fail to be parsed, so this code is not be reachable.
llvm_unreachable("unsupported form");
}
} while (Indirect);
if (IsBlock) {
StringRef Str = Data.getData().substr(*OffsetPtr, Value.uval);
Value.data = nullptr;
if (!Str.empty()) {
Value.data = reinterpret_cast<const uint8_t *>(Str.data());
*OffsetPtr += Value.uval;
}
}
return true;
}
bool DWARFDebugLine::LineTable::parse(DWARFDataExtractor &DebugLineData,
uint32_t *OffsetPtr, const DWARFUnit *U,
raw_ostream *OS) {
const uint32_t DebugLineOffset = *OffsetPtr;
clear();
if (!Prologue.parse(DebugLineData, OffsetPtr, U)) {
// Restore our offset and return false to indicate failure!
*OffsetPtr = DebugLineOffset;
return false;
}
if (OS)
Prologue.dump(*OS);
const uint32_t EndOffset =
DebugLineOffset + Prologue.TotalLength + Prologue.sizeofTotalLength();
// See if we should tell the data extractor the address size.
if (DebugLineData.getAddressSize() == 0)
DebugLineData.setAddressSize(Prologue.getAddressSize());
else
assert(Prologue.getAddressSize() == 0 ||
Prologue.getAddressSize() == DebugLineData.getAddressSize());
ParsingState State(this);
while (*OffsetPtr < EndOffset) {
if (OS)
*OS << format("0x%08.08" PRIx32 ": ", *OffsetPtr);
uint8_t Opcode = DebugLineData.getU8(OffsetPtr);
if (OS)
*OS << format("%02.02" PRIx8 " ", Opcode);
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
uint64_t Len = DebugLineData.getULEB128(OffsetPtr);
uint32_t ExtOffset = *OffsetPtr;
// Tolerate zero-length; assume length is correct and soldier on.
if (Len == 0) {
if (OS)
*OS << "Badly formed extended line op (length 0)\n";
continue;
}
uint8_t SubOpcode = DebugLineData.getU8(OffsetPtr);
if (OS)
*OS << LNExtendedString(SubOpcode);
switch (SubOpcode) {
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(*OffsetPtr);
if (OS) {
*OS << "\n";
OS->indent(12);
State.Row.dump(*OS);
}
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.
//
// Make sure the extractor knows the address size. If not, infer it
// from the size of the operand.
if (DebugLineData.getAddressSize() == 0)
DebugLineData.setAddressSize(Len - 1);
else
assert(DebugLineData.getAddressSize() == Len - 1);
State.Row.Address = DebugLineData.getRelocatedAddress(OffsetPtr);
if (OS)
*OS << format(" (0x%16.16" PRIx64 ")", State.Row.Address);
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 = DebugLineData.getCStr(OffsetPtr);
FileEntry.DirIdx = DebugLineData.getULEB128(OffsetPtr);
FileEntry.ModTime = DebugLineData.getULEB128(OffsetPtr);
FileEntry.Length = DebugLineData.getULEB128(OffsetPtr);
Prologue.FileNames.push_back(FileEntry);
if (OS)
*OS << " (" << FileEntry.Name.str()
<< ", dir=" << FileEntry.DirIdx << ", mod_time="
<< format("(0x%16.16" PRIx64 ")", FileEntry.ModTime)
<< ", length=" << FileEntry.Length << ")";
}
break;
case DW_LNE_set_discriminator:
State.Row.Discriminator = DebugLineData.getULEB128(OffsetPtr);
if (OS)
*OS << " (" << State.Row.Discriminator << ")";
break;
default:
if (OS)
*OS << format("Unrecognized extended op 0x%02.02" PRIx8, SubOpcode)
<< format(" length %" PRIx64, Len);
// Len 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.
(*OffsetPtr) += Len - 1;
break;
}
// Make sure the stated and parsed lengths are the same.
// Otherwise we have an unparseable line-number program.
if (*OffsetPtr - ExtOffset != Len) {
fprintf(stderr, "Unexpected line op length at offset 0x%8.8" PRIx32
" expected 0x%2.2" PRIx64 " found 0x%2.2" PRIx32 "\n",
ExtOffset, Len, *OffsetPtr - ExtOffset);
// Skip the rest of the line-number program.
*OffsetPtr = EndOffset;
return false;
}
} else if (Opcode < Prologue.OpcodeBase) {
if (OS)
*OS << LNStandardString(Opcode);
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(*OffsetPtr);
if (OS) {
*OS << "\n";
OS->indent(12);
State.Row.dump(*OS);
*OS << "\n";
}
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.
{
uint64_t AddrOffset =
DebugLineData.getULEB128(OffsetPtr) * Prologue.MinInstLength;
State.Row.Address += AddrOffset;
if (OS)
*OS << " (" << AddrOffset << ")";
}
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 += DebugLineData.getSLEB128(OffsetPtr);
if (OS)
*OS << " (" << State.Row.Line << ")";
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 = DebugLineData.getULEB128(OffsetPtr);
if (OS)
*OS << " (" << State.Row.File << ")";
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 = DebugLineData.getULEB128(OffsetPtr);
if (OS)
*OS << " (" << State.Row.Column << ")";
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 AdjustOpcode = 255 - Prologue.OpcodeBase;
uint64_t AddrOffset =
(AdjustOpcode / Prologue.LineRange) * Prologue.MinInstLength;
State.Row.Address += AddrOffset;
if (OS)
*OS
<< format(" (0x%16.16" PRIx64 ")", AddrOffset);
}
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.
{
uint16_t PCOffset = DebugLineData.getU16(OffsetPtr);
State.Row.Address += PCOffset;
if (OS)
*OS
<< format(" (0x%16.16" PRIx64 ")", PCOffset);
}
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 = DebugLineData.getULEB128(OffsetPtr);
if (OS)
*OS << " (" << State.Row.Isa << ")";
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 OpcodeLength = Prologue.StandardOpcodeLengths[Opcode - 1];
for (uint8_t I = 0; I < OpcodeLength; ++I) {
uint64_t Value = DebugLineData.getULEB128(OffsetPtr);
if (OS)
*OS << format("Skipping ULEB128 value: 0x%16.16" PRIx64 ")\n",
Value);
}
}
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 AdjustOpcode = Opcode - Prologue.OpcodeBase;
uint64_t AddrOffset =
(AdjustOpcode / Prologue.LineRange) * Prologue.MinInstLength;
int32_t LineOffset =
Prologue.LineBase + (AdjustOpcode % Prologue.LineRange);
State.Row.Line += LineOffset;
State.Row.Address += AddrOffset;
if (OS) {
*OS << "address += " << ((uint32_t)AdjustOpcode)
<< ", line += " << LineOffset << "\n";
OS->indent(12);
State.Row.dump(*OS);
}
State.appendRowToMatrix(*OffsetPtr);
// Reset discriminator to 0.
State.Row.Discriminator = 0;
}
if(OS)
*OS << "\n";
}
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 EndOffset;
}
Error RangeListEntry::extract(DWARFDataExtractor Data, uint32_t End,
uint32_t *OffsetPtr) {
Offset = *OffsetPtr;
SectionIndex = -1ULL;
// The caller should guarantee that we have at least 1 byte available, so
// we just assert instead of revalidate.
assert(*OffsetPtr < End &&
"not enough space to extract a rangelist encoding");
uint8_t Encoding = Data.getU8(OffsetPtr);
switch (Encoding) {
case dwarf::DW_RLE_end_of_list:
Value0 = Value1 = 0;
break;
// TODO: Support other encodings.
case dwarf::DW_RLE_base_addressx:
return createError("unsupported rnglists encoding DW_RLE_base_addressx "
"at offset 0x%" PRIx32,
*OffsetPtr - 1);
case dwarf::DW_RLE_startx_endx:
return createError("unsupported rnglists encoding DW_RLE_startx_endx at "
"offset 0x%" PRIx32,
*OffsetPtr - 1);
case dwarf::DW_RLE_startx_length:
return createError("unsupported rnglists encoding DW_RLE_startx_length "
"at offset 0x%" PRIx32,
*OffsetPtr - 1);
case dwarf::DW_RLE_offset_pair: {
uint32_t PreviousOffset = *OffsetPtr - 1;
Value0 = Data.getULEB128(OffsetPtr);
Value1 = Data.getULEB128(OffsetPtr);
if (End < *OffsetPtr)
return createError("read past end of table when reading "
"DW_RLE_offset_pair encoding at offset 0x%" PRIx32,
PreviousOffset);
break;
}
case dwarf::DW_RLE_base_address: {
if ((End - *OffsetPtr) < Data.getAddressSize())
return createError("insufficient space remaining in table for "
"DW_RLE_base_address encoding at offset 0x%" PRIx32,
*OffsetPtr - 1);
Value0 = Data.getRelocatedAddress(OffsetPtr, &SectionIndex);
break;
}
case dwarf::DW_RLE_start_end: {
if ((End - *OffsetPtr) < unsigned(Data.getAddressSize() * 2))
return createError("insufficient space remaining in table for "
"DW_RLE_start_end encoding "
"at offset 0x%" PRIx32,
*OffsetPtr - 1);
Value0 = Data.getRelocatedAddress(OffsetPtr, &SectionIndex);
Value1 = Data.getRelocatedAddress(OffsetPtr);
break;
}
case dwarf::DW_RLE_start_length: {
uint32_t PreviousOffset = *OffsetPtr - 1;
Value0 = Data.getRelocatedAddress(OffsetPtr, &SectionIndex);
Value1 = Data.getULEB128(OffsetPtr);
if (End < *OffsetPtr)
return createError("read past end of table when reading "
"DW_RLE_start_length encoding at offset 0x%" PRIx32,
PreviousOffset);
break;
}
default:
return createError("unknown rnglists encoding 0x%" PRIx32
" at offset 0x%" PRIx32,
uint32_t(Encoding), *OffsetPtr - 1);
}
EntryKind = Encoding;
return Error::success();
}