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<MachOObjectFile> MachOOF(static_cast<MachOObjectFile*>(
ObjectFile::createMachOObjectFile(Buff.take())));
MachOObject *MachOObj = MachOOF->getObject();
const Target *TheTarget = GetTarget(MachOObj);
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));
OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
OwningPtr<MCInstPrinter>
IP(TheTarget->createMCInstPrinter(AsmPrinterVariant, *AsmInfo, *InstrInfo,
*MRI, *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;
if (SymtabLCI) {
MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC);
MachOObj->RegisterStringTable(*SymtabLC);
}
std::vector<SectionRef> Sections;
std::vector<SymbolRef> Symbols;
SmallVector<uint64_t, 8> FoundFns;
getSectionsAndSymbols(Header, MachOOF.get(), &SymtabLC, Sections, Symbols,
FoundFns);
// Make a copy of the unsorted symbol list. FIXME: duplication
std::vector<SymbolRef> UnsortedSymbols(Symbols);
// Sort the symbols by address, just in case they didn't come in that way.
std::sort(Symbols.begin(), Symbols.end(), SymbolSorter());
#ifndef NDEBUG
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
#else
raw_ostream &DebugOut = nulls();
#endif
StringRef DebugAbbrevSection, DebugInfoSection, DebugArangesSection,
DebugLineSection, DebugStrSection;
OwningPtr<DIContext> diContext;
OwningPtr<MachOObjectFile> DSYMObj;
MachOObject *DbgInfoObj = MachOObj;
// Try to find debug info and set up the DIContext for it.
if (UseDbg) {
ArrayRef<SectionRef> DebugSections = Sections;
std::vector<SectionRef> 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(static_cast<MachOObjectFile*>(
ObjectFile::createMachOObjectFile(Buf.take())));
const macho::Header &Header = DSYMObj->getObject()->getHeader();
std::vector<SymbolRef> Symbols;
SmallVector<uint64_t, 8> FoundFns;
getSectionsAndSymbols(Header, DSYMObj.get(), 0, DSYMSections, Symbols,
FoundFns);
DebugSections = DSYMSections;
DbgInfoObj = DSYMObj.get()->getObject();
}
// Find the named debug info sections.
for (unsigned SectIdx = 0; SectIdx != DebugSections.size(); SectIdx++) {
StringRef SectName;
if (!DebugSections[SectIdx].getName(SectName)) {
if (SectName.equals("__DWARF,__debug_abbrev"))
DebugSections[SectIdx].getContents(DebugAbbrevSection);
else if (SectName.equals("__DWARF,__debug_info"))
DebugSections[SectIdx].getContents(DebugInfoSection);
else if (SectName.equals("__DWARF,__debug_aranges"))
DebugSections[SectIdx].getContents(DebugArangesSection);
else if (SectName.equals("__DWARF,__debug_line"))
DebugSections[SectIdx].getContents(DebugLineSection);
else if (SectName.equals("__DWARF,__debug_str"))
DebugSections[SectIdx].getContents(DebugStrSection);
}
}
// 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++) {
StringRef SectName;
if (Sections[SectIdx].getName(SectName) ||
SectName.compare("__TEXT,__text"))
continue; // Skip non-text sections
// Insert the functions from the function starts segment into our map.
uint64_t VMAddr;
Sections[SectIdx].getAddress(VMAddr);
for (unsigned i = 0, e = FoundFns.size(); i != e; ++i) {
StringRef SectBegin;
Sections[SectIdx].getContents(SectBegin);
uint64_t Offset = (uint64_t)SectBegin.data();
FunctionMap.insert(std::make_pair(VMAddr + FoundFns[i]-Offset,
(MCFunction*)0));
}
StringRef Bytes;
Sections[SectIdx].getContents(Bytes);
StringRefMemoryObject memoryObject(Bytes);
bool symbolTableWorked = false;
// Parse relocations.
std::vector<std::pair<uint64_t, SymbolRef> > Relocs;
error_code ec;
for (relocation_iterator RI = Sections[SectIdx].begin_relocations(),
RE = Sections[SectIdx].end_relocations(); RI != RE; RI.increment(ec)) {
uint64_t RelocOffset, SectionAddress;
RI->getAddress(RelocOffset);
Sections[SectIdx].getAddress(SectionAddress);
RelocOffset -= SectionAddress;
SymbolRef RelocSym;
RI->getSymbol(RelocSym);
Relocs.push_back(std::make_pair(RelocOffset, RelocSym));
}
array_pod_sort(Relocs.begin(), Relocs.end());
// Disassemble symbol by symbol.
for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
StringRef SymName;
Symbols[SymIdx].getName(SymName);
SymbolRef::Type ST;
Symbols[SymIdx].getType(ST);
if (ST != SymbolRef::ST_Function)
continue;
// Make sure the symbol is defined in this section.
bool containsSym = false;
Sections[SectIdx].containsSymbol(Symbols[SymIdx], containsSym);
if (!containsSym)
continue;
// Start at the address of the symbol relative to the section's address.
uint64_t SectionAddress = 0;
uint64_t Start = 0;
Sections[SectIdx].getAddress(SectionAddress);
Symbols[SymIdx].getAddress(Start);
Start -= SectionAddress;
// Stop disassembling either at the beginning of the next symbol or at
// the end of the section.
bool containsNextSym = false;
uint64_t NextSym = 0;
uint64_t NextSymIdx = SymIdx+1;
while (Symbols.size() > NextSymIdx) {
SymbolRef::Type NextSymType;
Symbols[NextSymIdx].getType(NextSymType);
if (NextSymType == SymbolRef::ST_Function) {
Sections[SectIdx].containsSymbol(Symbols[NextSymIdx],
containsNextSym);
Symbols[NextSymIdx].getAddress(NextSym);
NextSym -= SectionAddress;
break;
}
++NextSymIdx;
}
uint64_t SectSize;
Sections[SectIdx].getSize(SectSize);
uint64_t End = containsNextSym ? NextSym : SectSize;
uint64_t Size;
symbolTableWorked = true;
if (!CFG) {
// Normal disassembly, print addresses, bytes and mnemonic form.
StringRef SymName;
Symbols[SymIdx].getName(SymName);
outs() << SymName << ":\n";
DILineInfo lastLine;
for (uint64_t Index = Start; Index < End; Index += Size) {
MCInst Inst;
if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
DebugOut, nulls())) {
uint64_t SectAddress = 0;
Sections[SectIdx].getAddress(SectAddress);
outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
DumpBytes(StringRef(Bytes.data() + Index, Size));
IP->printInst(&Inst, outs(), "");
// Print debug info.
if (diContext) {
DILineInfo dli =
diContext->getLineInfoForAddress(SectAddress + 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.
StringRef SymName;
Symbols[SymIdx].getName(SymName);
createMCFunctionAndSaveCalls(
SymName, DisAsm.get(), memoryObject, Start, End,
InstrAnalysis.get(), Start, DebugOut, FunctionMap, Functions);
}
}
if (!CFG && !symbolTableWorked) {
// Reading the symbol table didn't work, disassemble the whole section.
uint64_t SectAddress;
Sections[SectIdx].getAddress(SectAddress);
uint64_t SectSize;
Sections[SectIdx].getSize(SectSize);
uint64_t InstSize;
for (uint64_t Index = 0; Index < SectSize; Index += InstSize) {
MCInst Inst;
if (DisAsm->getInstruction(Inst, InstSize, memoryObject, Index,
DebugOut, nulls())) {
outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
DumpBytes(StringRef(Bytes.data() + Index, InstSize));
IP->printInst(&Inst, outs(), "");
outs() << "\n";
} else {
errs() << "llvm-objdump: warning: invalid instruction encoding\n";
if (InstSize == 0)
InstSize = 1; // skip illegible bytes
}
}
}
if (CFG) {
if (!symbolTableWorked) {
// Reading the symbol table didn't work, create a big __TEXT symbol.
uint64_t SectSize = 0, SectAddress = 0;
Sections[SectIdx].getSize(SectSize);
Sections[SectIdx].getAddress(SectAddress);
createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject,
0, SectSize,
InstrAnalysis.get(),
SectAddress, 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.
uint64_t SectSize = 0;
Sections[SectIdx].getSize(SectSize);
SmallVector<uint64_t, 16> Calls;
MCFunction f =
MCFunction::createFunctionFromMC("unknown", DisAsm.get(),
memoryObject, mi->first,
SectSize,
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;
}
uint64_t SectSize = 0, SectAddress;
Sections[SectIdx].getSize(SectSize);
Sections[SectIdx].getAddress(SectAddress);
// No predecessors, this is a data block. Print as .byte directives.
if (!hasPreds) {
uint64_t End = llvm::next(fi) == fe ? SectSize :
llvm::next(fi)->first;
outs() << "# " << End-fi->first << " bytes of data:\n";
for (unsigned pos = fi->first; pos != End; ++pos) {
outs() << format("%8x:\t", SectAddress + 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(SectAddress + Inst.Address) !=
FunctionMap.end())
outs() << FunctionMap[SectAddress + Inst.Address]-> getName()
<< ":\n";
outs() << format("%8" PRIx64 ":\t", SectAddress + 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 >= SectAddress + Inst.Address &&
Relocs[j].first < SectAddress + Inst.Address + Inst.Size) {
StringRef SymName;
uint64_t Addr;
Relocs[j].second.getAddress(Addr);
Relocs[j].second.getName(SymName);
outs() << "\t# " << SymName << ' ';
DumpAddress(Addr, Sections, MachOObj, 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, outs());
// Print debug info.
if (diContext) {
DILineInfo dli =
diContext->getLineInfoForAddress(SectAddress + 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());
}
}
}
}
static void DisassembleInputMachO2(StringRef Filename,
MachOObjectFile *MachOOF) {
const Target *TheTarget = GetTarget(MachOOF);
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 MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
OwningPtr<const MCAsmInfo> AsmInfo(
TheTarget->createMCAsmInfo(*MRI, 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, *InstrInfo,
*MRI, *STI));
if (!InstrAnalysis || !AsmInfo || !STI || !DisAsm || !IP) {
errs() << "error: couldn't initialize disassembler for target "
<< TripleName << '\n';
return;
}
outs() << '\n' << Filename << ":\n\n";
macho::Header Header = MachOOF->getHeader();
// FIXME: FoundFns isn't used anymore. Using symbols/LC_FUNCTION_STARTS to
// determine function locations will eventually go in MCObjectDisassembler.
// FIXME: Using the -cfg command line option, this code used to be able to
// annotate relocations with the referenced symbol's name, and if this was
// inside a __[cf]string section, the data it points to. This is now replaced
// by the upcoming MCSymbolizer, which needs the appropriate setup done above.
std::vector<SectionRef> Sections;
std::vector<SymbolRef> Symbols;
SmallVector<uint64_t, 8> FoundFns;
getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns);
// Make a copy of the unsorted symbol list. FIXME: duplication
std::vector<SymbolRef> UnsortedSymbols(Symbols);
// Sort the symbols by address, just in case they didn't come in that way.
std::sort(Symbols.begin(), Symbols.end(), SymbolSorter());
#ifndef NDEBUG
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
#else
raw_ostream &DebugOut = nulls();
#endif
OwningPtr<DIContext> diContext;
ObjectFile *DbgObj = MachOOF;
// Try to find debug info and set up the DIContext for it.
if (UseDbg) {
// 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;
}
DbgObj = ObjectFile::createMachOObjectFile(Buf.take());
}
// Setup the DIContext
diContext.reset(DIContext::getDWARFContext(DbgObj));
}
for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) {
bool SectIsText = false;
Sections[SectIdx].isText(SectIsText);
if (SectIsText == false)
continue;
StringRef SectName;
if (Sections[SectIdx].getName(SectName) ||
SectName != "__text")
continue; // Skip non-text sections
DataRefImpl DR = Sections[SectIdx].getRawDataRefImpl();
StringRef SegmentName = MachOOF->getSectionFinalSegmentName(DR);
if (SegmentName != "__TEXT")
continue;
StringRef Bytes;
Sections[SectIdx].getContents(Bytes);
StringRefMemoryObject memoryObject(Bytes);
bool symbolTableWorked = false;
// Parse relocations.
std::vector<std::pair<uint64_t, SymbolRef> > Relocs;
error_code ec;
for (relocation_iterator RI = Sections[SectIdx].begin_relocations(),
RE = Sections[SectIdx].end_relocations(); RI != RE; RI.increment(ec)) {
uint64_t RelocOffset, SectionAddress;
RI->getOffset(RelocOffset);
Sections[SectIdx].getAddress(SectionAddress);
RelocOffset -= SectionAddress;
SymbolRef RelocSym;
RI->getSymbol(RelocSym);
Relocs.push_back(std::make_pair(RelocOffset, RelocSym));
}
array_pod_sort(Relocs.begin(), Relocs.end());
// Disassemble symbol by symbol.
for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
StringRef SymName;
Symbols[SymIdx].getName(SymName);
SymbolRef::Type ST;
Symbols[SymIdx].getType(ST);
if (ST != SymbolRef::ST_Function)
continue;
// Make sure the symbol is defined in this section.
bool containsSym = false;
Sections[SectIdx].containsSymbol(Symbols[SymIdx], containsSym);
if (!containsSym)
continue;
// Start at the address of the symbol relative to the section's address.
uint64_t SectionAddress = 0;
uint64_t Start = 0;
Sections[SectIdx].getAddress(SectionAddress);
Symbols[SymIdx].getAddress(Start);
Start -= SectionAddress;
// Stop disassembling either at the beginning of the next symbol or at
// the end of the section.
bool containsNextSym = false;
uint64_t NextSym = 0;
uint64_t NextSymIdx = SymIdx+1;
while (Symbols.size() > NextSymIdx) {
SymbolRef::Type NextSymType;
Symbols[NextSymIdx].getType(NextSymType);
if (NextSymType == SymbolRef::ST_Function) {
Sections[SectIdx].containsSymbol(Symbols[NextSymIdx],
containsNextSym);
Symbols[NextSymIdx].getAddress(NextSym);
NextSym -= SectionAddress;
break;
}
++NextSymIdx;
}
uint64_t SectSize;
Sections[SectIdx].getSize(SectSize);
uint64_t End = containsNextSym ? NextSym : SectSize;
uint64_t Size;
symbolTableWorked = true;
outs() << SymName << ":\n";
DILineInfo lastLine;
for (uint64_t Index = Start; Index < End; Index += Size) {
MCInst Inst;
if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
DebugOut, nulls())) {
uint64_t SectAddress = 0;
Sections[SectIdx].getAddress(SectAddress);
outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
DumpBytes(StringRef(Bytes.data() + Index, Size));
IP->printInst(&Inst, outs(), "");
// Print debug info.
if (diContext) {
DILineInfo dli =
diContext->getLineInfoForAddress(SectAddress + 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
}
}
}
if (!symbolTableWorked) {
// Reading the symbol table didn't work, disassemble the whole section.
uint64_t SectAddress;
Sections[SectIdx].getAddress(SectAddress);
uint64_t SectSize;
Sections[SectIdx].getSize(SectSize);
uint64_t InstSize;
for (uint64_t Index = 0; Index < SectSize; Index += InstSize) {
MCInst Inst;
if (DisAsm->getInstruction(Inst, InstSize, memoryObject, Index,
DebugOut, nulls())) {
outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
DumpBytes(StringRef(Bytes.data() + Index, InstSize));
IP->printInst(&Inst, outs(), "");
outs() << "\n";
} else {
errs() << "llvm-objdump: warning: invalid instruction encoding\n";
if (InstSize == 0)
InstSize = 1; // skip illegible bytes
}
}
}
}
}