diff options
Diffstat (limited to 'tools/llvm-objdump/MachODump.cpp')
| -rw-r--r-- | tools/llvm-objdump/MachODump.cpp | 456 |
1 files changed, 156 insertions, 300 deletions
diff --git a/tools/llvm-objdump/MachODump.cpp b/tools/llvm-objdump/MachODump.cpp index 6797e2dc5b86..86923fd1d7f5 100644 --- a/tools/llvm-objdump/MachODump.cpp +++ b/tools/llvm-objdump/MachODump.cpp @@ -12,9 +12,9 @@ //===----------------------------------------------------------------------===// #include "llvm-objdump.h" -#include "MCFunction.h" #include "llvm/ADT/OwningPtr.h" #include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" #include "llvm/ADT/Triple.h" #include "llvm/DebugInfo/DIContext.h" #include "llvm/MC/MCAsmInfo.h" @@ -44,10 +44,6 @@ using namespace llvm; using namespace object; static cl::opt<bool> - CFG("cfg", cl::desc("Create a CFG for every symbol in the object file and" - " write it to a graphviz file (MachO-only)")); - -static cl::opt<bool> UseDbg("g", cl::desc("Print line information from debug info if available")); static cl::opt<std::string> @@ -91,105 +87,73 @@ struct SymbolSorter { } }; -// Print additional information about an address, if available. -static void DumpAddress(uint64_t Address, ArrayRef<SectionRef> Sections, - const MachOObjectFile *MachOObj, raw_ostream &OS) { - for (unsigned i = 0; i != Sections.size(); ++i) { - uint64_t SectAddr = 0, SectSize = 0; - Sections[i].getAddress(SectAddr); - Sections[i].getSize(SectSize); - uint64_t addr = SectAddr; - if (SectAddr <= Address && - SectAddr + SectSize > Address) { - StringRef bytes, name; - Sections[i].getContents(bytes); - Sections[i].getName(name); - // Print constant strings. - if (!name.compare("__cstring")) - OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"'; - // Print constant CFStrings. - if (!name.compare("__cfstring")) - OS << "@\"" << bytes.substr(addr, bytes.find('\0', addr)) << '"'; - } - } -} +// Types for the storted data in code table that is built before disassembly +// and the predicate function to sort them. +typedef std::pair<uint64_t, DiceRef> DiceTableEntry; +typedef std::vector<DiceTableEntry> DiceTable; +typedef DiceTable::iterator dice_table_iterator; -typedef std::map<uint64_t, MCFunction*> FunctionMapTy; -typedef SmallVector<MCFunction, 16> FunctionListTy; -static void createMCFunctionAndSaveCalls(StringRef Name, - const MCDisassembler *DisAsm, - MemoryObject &Object, uint64_t Start, - uint64_t End, - MCInstrAnalysis *InstrAnalysis, - uint64_t Address, - raw_ostream &DebugOut, - FunctionMapTy &FunctionMap, - FunctionListTy &Functions) { - SmallVector<uint64_t, 16> Calls; - MCFunction f = - MCFunction::createFunctionFromMC(Name, DisAsm, Object, Start, End, - InstrAnalysis, DebugOut, Calls); - Functions.push_back(f); - FunctionMap[Address] = &Functions.back(); - - // Add the gathered callees to the map. - for (unsigned i = 0, e = Calls.size(); i != e; ++i) - FunctionMap.insert(std::make_pair(Calls[i], (MCFunction*)0)); +static bool +compareDiceTableEntries(const DiceTableEntry i, + const DiceTableEntry j) { + return i.first == j.first; } -// Write a graphviz file for the CFG inside an MCFunction. -static void emitDOTFile(const char *FileName, const MCFunction &f, - MCInstPrinter *IP) { - // Start a new dot file. - std::string Error; - raw_fd_ostream Out(FileName, Error); - if (!Error.empty()) { - errs() << "llvm-objdump: warning: " << Error << '\n'; - return; - } - - Out << "digraph " << f.getName() << " {\n"; - Out << "graph [ rankdir = \"LR\" ];\n"; - for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) { - bool hasPreds = false; - // Only print blocks that have predecessors. - // FIXME: Slow. - for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe; - ++pi) - if (pi->second.contains(i->first)) { - hasPreds = true; - break; - } - - if (!hasPreds && i != f.begin()) - continue; - - Out << '"' << i->first << "\" [ label=\"<a>"; - // Print instructions. - for (unsigned ii = 0, ie = i->second.getInsts().size(); ii != ie; - ++ii) { - // Escape special chars and print the instruction in mnemonic form. - std::string Str; - raw_string_ostream OS(Str); - IP->printInst(&i->second.getInsts()[ii].Inst, OS, ""); - Out << DOT::EscapeString(OS.str()) << '|'; +static void DumpDataInCode(const char *bytes, uint64_t Size, + unsigned short Kind) { + uint64_t Value; + + switch (Kind) { + case MachO::DICE_KIND_DATA: + switch (Size) { + case 4: + Value = bytes[3] << 24 | + bytes[2] << 16 | + bytes[1] << 8 | + bytes[0]; + outs() << "\t.long " << Value; + break; + case 2: + Value = bytes[1] << 8 | + bytes[0]; + outs() << "\t.short " << Value; + break; + case 1: + Value = bytes[0]; + outs() << "\t.byte " << Value; + break; } - Out << "<o>\" shape=\"record\" ];\n"; - - // Add edges. - for (MCBasicBlock::succ_iterator si = i->second.succ_begin(), - se = i->second.succ_end(); si != se; ++si) - Out << i->first << ":o -> " << *si <<":a\n"; + outs() << "\t@ KIND_DATA\n"; + break; + case MachO::DICE_KIND_JUMP_TABLE8: + Value = bytes[0]; + outs() << "\t.byte " << Value << "\t@ KIND_JUMP_TABLE8"; + break; + case MachO::DICE_KIND_JUMP_TABLE16: + Value = bytes[1] << 8 | + bytes[0]; + outs() << "\t.short " << Value << "\t@ KIND_JUMP_TABLE16"; + break; + case MachO::DICE_KIND_JUMP_TABLE32: + Value = bytes[3] << 24 | + bytes[2] << 16 | + bytes[1] << 8 | + bytes[0]; + outs() << "\t.long " << Value << "\t@ KIND_JUMP_TABLE32"; + break; + default: + outs() << "\t@ data in code kind = " << Kind << "\n"; + break; } - Out << "}\n"; } static void -getSectionsAndSymbols(const macho::Header Header, +getSectionsAndSymbols(const MachO::mach_header Header, MachOObjectFile *MachOObj, std::vector<SectionRef> &Sections, std::vector<SymbolRef> &Symbols, - SmallVectorImpl<uint64_t> &FoundFns) { + SmallVectorImpl<uint64_t> &FoundFns, + uint64_t &BaseSegmentAddress) { error_code ec; for (symbol_iterator SI = MachOObj->begin_symbols(), SE = MachOObj->end_symbols(); SI != SE; SI.increment(ec)) @@ -205,17 +169,27 @@ getSectionsAndSymbols(const macho::Header Header, MachOObjectFile::LoadCommandInfo Command = MachOObj->getFirstLoadCommandInfo(); + bool BaseSegmentAddressSet = false; for (unsigned i = 0; ; ++i) { - if (Command.C.Type == macho::LCT_FunctionStarts) { + if (Command.C.cmd == MachO::LC_FUNCTION_STARTS) { // We found a function starts segment, parse the addresses for later // consumption. - macho::LinkeditDataLoadCommand LLC = + MachO::linkedit_data_command LLC = MachOObj->getLinkeditDataLoadCommand(Command); - MachOObj->ReadULEB128s(LLC.DataOffset, FoundFns); + MachOObj->ReadULEB128s(LLC.dataoff, FoundFns); + } + else if (Command.C.cmd == MachO::LC_SEGMENT) { + MachO::segment_command SLC = + MachOObj->getSegmentLoadCommand(Command); + StringRef SegName = SLC.segname; + if(!BaseSegmentAddressSet && SegName != "__PAGEZERO") { + BaseSegmentAddressSet = true; + BaseSegmentAddress = SLC.vmaddr; + } } - if (i == Header.NumLoadCommands - 1) + if (i == Header.ncmds - 1) break; else Command = MachOObj->getNextLoadCommandInfo(Command); @@ -251,11 +225,12 @@ static void DisassembleInputMachO2(StringRef Filename, InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo.get())); // Set up disassembler. - OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName)); + 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)); - OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(AsmPrinterVariant, *AsmInfo, *InstrInfo, @@ -269,19 +244,41 @@ static void DisassembleInputMachO2(StringRef Filename, outs() << '\n' << Filename << ":\n\n"; - macho::Header Header = MachOOF->getHeader(); + MachO::mach_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; + uint64_t BaseSegmentAddress; - getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns); + getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns, + BaseSegmentAddress); - // 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()); + // Build a data in code table that is sorted on by the address of each entry. + uint64_t BaseAddress = 0; + if (Header.filetype == MachO::MH_OBJECT) + Sections[0].getAddress(BaseAddress); + else + BaseAddress = BaseSegmentAddress; + DiceTable Dices; + error_code ec; + for (dice_iterator DI = MachOOF->begin_dices(), DE = MachOOF->end_dices(); + DI != DE; DI.increment(ec)){ + uint32_t Offset; + DI->getOffset(Offset); + Dices.push_back(std::make_pair(BaseAddress + Offset, *DI)); + } + array_pod_sort(Dices.begin(), Dices.end()); + #ifndef NDEBUG raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); #else @@ -296,7 +293,7 @@ static void DisassembleInputMachO2(StringRef Filename, // 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)) { + if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile, Buf)) { errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n'; return; } @@ -307,31 +304,24 @@ static void DisassembleInputMachO2(StringRef Filename, diContext.reset(DIContext::getDWARFContext(DbgObj)); } - FunctionMapTy FunctionMap; - FunctionListTy Functions; - 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; - // 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); @@ -347,10 +337,9 @@ static void DisassembleInputMachO2(StringRef Filename, Sections[SectIdx].getAddress(SectionAddress); RelocOffset -= SectionAddress; - SymbolRef RelocSym; - RI->getSymbol(RelocSym); + symbol_iterator RelocSym = RI->getSymbol(); - Relocs.push_back(std::make_pair(RelocOffset, RelocSym)); + Relocs.push_back(std::make_pair(RelocOffset, *RelocSym)); } array_pod_sort(Relocs.begin(), Relocs.end()); @@ -402,52 +391,56 @@ static void DisassembleInputMachO2(StringRef Filename, 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 + outs() << SymName << ":\n"; + DILineInfo lastLine; + for (uint64_t Index = Start; Index < End; Index += Size) { + MCInst Inst; + + uint64_t SectAddress = 0; + Sections[SectIdx].getAddress(SectAddress); + outs() << format("%8" PRIx64 ":\t", SectAddress + Index); + + // Check the data in code table here to see if this is data not an + // instruction to be disassembled. + DiceTable Dice; + Dice.push_back(std::make_pair(SectAddress + Index, DiceRef())); + dice_table_iterator DTI = std::search(Dices.begin(), Dices.end(), + Dice.begin(), Dice.end(), + compareDiceTableEntries); + if (DTI != Dices.end()){ + uint16_t Length; + DTI->second.getLength(Length); + DumpBytes(StringRef(Bytes.data() + Index, Length)); + uint16_t Kind; + DTI->second.getKind(Kind); + DumpDataInCode(Bytes.data() + Index, Length, Kind); + continue; + } + + if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, + DebugOut, nulls())) { + 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) { + if (!symbolTableWorked) { // Reading the symbol table didn't work, disassemble the whole section. uint64_t SectAddress; Sections[SectIdx].getAddress(SectAddress); @@ -470,142 +463,5 @@ static void DisassembleInputMachO2(StringRef Filename, } } } - - 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, MachOOF, 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, MachOOF, 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()); - } - } } } |