diff options
Diffstat (limited to 'contrib/llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp')
| -rw-r--r-- | contrib/llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp | 2310 |
1 files changed, 2310 insertions, 0 deletions
diff --git a/contrib/llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp new file mode 100644 index 000000000000..34a44b3b7fa9 --- /dev/null +++ b/contrib/llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -0,0 +1,2310 @@ +//===-- llvm-objdump.cpp - Object file dumping utility for llvm -----------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +// This program is a utility that works like binutils "objdump", that is, it +// dumps out a plethora of information about an object file depending on the +// flags. +// +// The flags and output of this program should be near identical to those of +// binutils objdump. +// +//===----------------------------------------------------------------------===// + +#include "llvm-objdump.h" +#include "llvm/ADT/Optional.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/SetOperations.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/StringSet.h" +#include "llvm/ADT/Triple.h" +#include "llvm/CodeGen/FaultMaps.h" +#include "llvm/DebugInfo/DWARF/DWARFContext.h" +#include "llvm/DebugInfo/Symbolize/Symbolize.h" +#include "llvm/Demangle/Demangle.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCDisassembler/MCDisassembler.h" +#include "llvm/MC/MCDisassembler/MCRelocationInfo.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCObjectFileInfo.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Object/Archive.h" +#include "llvm/Object/COFF.h" +#include "llvm/Object/COFFImportFile.h" +#include "llvm/Object/ELFObjectFile.h" +#include "llvm/Object/MachO.h" +#include "llvm/Object/MachOUniversal.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Object/Wasm.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/Errc.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/FormatVariadic.h" +#include "llvm/Support/GraphWriter.h" +#include "llvm/Support/Host.h" +#include "llvm/Support/InitLLVM.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/SourceMgr.h" +#include "llvm/Support/StringSaver.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/WithColor.h" +#include "llvm/Support/raw_ostream.h" +#include <algorithm> +#include <cctype> +#include <cstring> +#include <system_error> +#include <unordered_map> +#include <utility> + +using namespace llvm::object; + +namespace llvm { + +cl::OptionCategory ObjdumpCat("llvm-objdump Options"); + +// MachO specific +extern cl::OptionCategory MachOCat; +extern cl::opt<bool> Bind; +extern cl::opt<bool> DataInCode; +extern cl::opt<bool> DylibsUsed; +extern cl::opt<bool> DylibId; +extern cl::opt<bool> ExportsTrie; +extern cl::opt<bool> FirstPrivateHeader; +extern cl::opt<bool> IndirectSymbols; +extern cl::opt<bool> InfoPlist; +extern cl::opt<bool> LazyBind; +extern cl::opt<bool> LinkOptHints; +extern cl::opt<bool> ObjcMetaData; +extern cl::opt<bool> Rebase; +extern cl::opt<bool> UniversalHeaders; +extern cl::opt<bool> WeakBind; + +static cl::opt<uint64_t> AdjustVMA( + "adjust-vma", + cl::desc("Increase the displayed address by the specified offset"), + cl::value_desc("offset"), cl::init(0), cl::cat(ObjdumpCat)); + +static cl::opt<bool> + AllHeaders("all-headers", + cl::desc("Display all available header information"), + cl::cat(ObjdumpCat)); +static cl::alias AllHeadersShort("x", cl::desc("Alias for --all-headers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(AllHeaders)); + +static cl::opt<std::string> + ArchName("arch-name", + cl::desc("Target arch to disassemble for, " + "see -version for available targets"), + cl::cat(ObjdumpCat)); + +cl::opt<bool> ArchiveHeaders("archive-headers", + cl::desc("Display archive header information"), + cl::cat(ObjdumpCat)); +static cl::alias ArchiveHeadersShort("a", + cl::desc("Alias for --archive-headers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(ArchiveHeaders)); + +cl::opt<bool> Demangle("demangle", cl::desc("Demangle symbols names"), + cl::init(false), cl::cat(ObjdumpCat)); +static cl::alias DemangleShort("C", cl::desc("Alias for --demangle"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(Demangle)); + +cl::opt<bool> Disassemble( + "disassemble", + cl::desc("Display assembler mnemonics for the machine instructions"), + cl::cat(ObjdumpCat)); +static cl::alias DisassembleShort("d", cl::desc("Alias for --disassemble"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(Disassemble)); + +cl::opt<bool> DisassembleAll( + "disassemble-all", + cl::desc("Display assembler mnemonics for the machine instructions"), + cl::cat(ObjdumpCat)); +static cl::alias DisassembleAllShort("D", + cl::desc("Alias for --disassemble-all"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(DisassembleAll)); + +static cl::list<std::string> + DisassembleFunctions("disassemble-functions", cl::CommaSeparated, + cl::desc("List of functions to disassemble. " + "Accept demangled names when --demangle is " + "specified, otherwise accept mangled names"), + cl::cat(ObjdumpCat)); + +static cl::opt<bool> DisassembleZeroes( + "disassemble-zeroes", + cl::desc("Do not skip blocks of zeroes when disassembling"), + cl::cat(ObjdumpCat)); +static cl::alias + DisassembleZeroesShort("z", cl::desc("Alias for --disassemble-zeroes"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(DisassembleZeroes)); + +static cl::list<std::string> + DisassemblerOptions("disassembler-options", + cl::desc("Pass target specific disassembler options"), + cl::value_desc("options"), cl::CommaSeparated, + cl::cat(ObjdumpCat)); +static cl::alias + DisassemblerOptionsShort("M", cl::desc("Alias for --disassembler-options"), + cl::NotHidden, cl::Grouping, cl::Prefix, + cl::CommaSeparated, + cl::aliasopt(DisassemblerOptions)); + +cl::opt<DIDumpType> DwarfDumpType( + "dwarf", cl::init(DIDT_Null), cl::desc("Dump of dwarf debug sections:"), + cl::values(clEnumValN(DIDT_DebugFrame, "frames", ".debug_frame")), + cl::cat(ObjdumpCat)); + +static cl::opt<bool> DynamicRelocations( + "dynamic-reloc", + cl::desc("Display the dynamic relocation entries in the file"), + cl::cat(ObjdumpCat)); +static cl::alias DynamicRelocationShort("R", + cl::desc("Alias for --dynamic-reloc"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(DynamicRelocations)); + +static cl::opt<bool> + FaultMapSection("fault-map-section", + cl::desc("Display contents of faultmap section"), + cl::cat(ObjdumpCat)); + +static cl::opt<bool> + FileHeaders("file-headers", + cl::desc("Display the contents of the overall file header"), + cl::cat(ObjdumpCat)); +static cl::alias FileHeadersShort("f", cl::desc("Alias for --file-headers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(FileHeaders)); + +cl::opt<bool> SectionContents("full-contents", + cl::desc("Display the content of each section"), + cl::cat(ObjdumpCat)); +static cl::alias SectionContentsShort("s", + cl::desc("Alias for --full-contents"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(SectionContents)); + +static cl::list<std::string> InputFilenames(cl::Positional, + cl::desc("<input object files>"), + cl::ZeroOrMore, + cl::cat(ObjdumpCat)); + +static cl::opt<bool> + PrintLines("line-numbers", + cl::desc("Display source line numbers with " + "disassembly. Implies disassemble object"), + cl::cat(ObjdumpCat)); +static cl::alias PrintLinesShort("l", cl::desc("Alias for --line-numbers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(PrintLines)); + +static cl::opt<bool> MachOOpt("macho", + cl::desc("Use MachO specific object file parser"), + cl::cat(ObjdumpCat)); +static cl::alias MachOm("m", cl::desc("Alias for --macho"), cl::NotHidden, + cl::Grouping, cl::aliasopt(MachOOpt)); + +cl::opt<std::string> + MCPU("mcpu", + cl::desc("Target a specific cpu type (-mcpu=help for details)"), + cl::value_desc("cpu-name"), cl::init(""), cl::cat(ObjdumpCat)); + +cl::list<std::string> MAttrs("mattr", cl::CommaSeparated, + cl::desc("Target specific attributes"), + cl::value_desc("a1,+a2,-a3,..."), + cl::cat(ObjdumpCat)); + +cl::opt<bool> NoShowRawInsn("no-show-raw-insn", + cl::desc("When disassembling " + "instructions, do not print " + "the instruction bytes."), + cl::cat(ObjdumpCat)); +cl::opt<bool> NoLeadingAddr("no-leading-addr", + cl::desc("Print no leading address"), + cl::cat(ObjdumpCat)); + +static cl::opt<bool> RawClangAST( + "raw-clang-ast", + cl::desc("Dump the raw binary contents of the clang AST section"), + cl::cat(ObjdumpCat)); + +cl::opt<bool> + Relocations("reloc", cl::desc("Display the relocation entries in the file"), + cl::cat(ObjdumpCat)); +static cl::alias RelocationsShort("r", cl::desc("Alias for --reloc"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(Relocations)); + +cl::opt<bool> PrintImmHex("print-imm-hex", + cl::desc("Use hex format for immediate values"), + cl::cat(ObjdumpCat)); + +cl::opt<bool> PrivateHeaders("private-headers", + cl::desc("Display format specific file headers"), + cl::cat(ObjdumpCat)); +static cl::alias PrivateHeadersShort("p", + cl::desc("Alias for --private-headers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(PrivateHeaders)); + +cl::list<std::string> + FilterSections("section", + cl::desc("Operate on the specified sections only. " + "With -macho dump segment,section"), + cl::cat(ObjdumpCat)); +static cl::alias FilterSectionsj("j", cl::desc("Alias for --section"), + cl::NotHidden, cl::Grouping, cl::Prefix, + cl::aliasopt(FilterSections)); + +cl::opt<bool> SectionHeaders("section-headers", + cl::desc("Display summaries of the " + "headers for each section."), + cl::cat(ObjdumpCat)); +static cl::alias SectionHeadersShort("headers", + cl::desc("Alias for --section-headers"), + cl::NotHidden, + cl::aliasopt(SectionHeaders)); +static cl::alias SectionHeadersShorter("h", + cl::desc("Alias for --section-headers"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(SectionHeaders)); + +static cl::opt<bool> + ShowLMA("show-lma", + cl::desc("Display LMA column when dumping ELF section headers"), + cl::cat(ObjdumpCat)); + +static cl::opt<bool> PrintSource( + "source", + cl::desc( + "Display source inlined with disassembly. Implies disassemble object"), + cl::cat(ObjdumpCat)); +static cl::alias PrintSourceShort("S", cl::desc("Alias for -source"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(PrintSource)); + +static cl::opt<uint64_t> + StartAddress("start-address", cl::desc("Disassemble beginning at address"), + cl::value_desc("address"), cl::init(0), cl::cat(ObjdumpCat)); +static cl::opt<uint64_t> StopAddress("stop-address", + cl::desc("Stop disassembly at address"), + cl::value_desc("address"), + cl::init(UINT64_MAX), cl::cat(ObjdumpCat)); + +cl::opt<bool> SymbolTable("syms", cl::desc("Display the symbol table"), + cl::cat(ObjdumpCat)); +static cl::alias SymbolTableShort("t", cl::desc("Alias for --syms"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(SymbolTable)); + +cl::opt<std::string> TripleName("triple", + cl::desc("Target triple to disassemble for, " + "see -version for available targets"), + cl::cat(ObjdumpCat)); + +cl::opt<bool> UnwindInfo("unwind-info", cl::desc("Display unwind information"), + cl::cat(ObjdumpCat)); +static cl::alias UnwindInfoShort("u", cl::desc("Alias for --unwind-info"), + cl::NotHidden, cl::Grouping, + cl::aliasopt(UnwindInfo)); + +static cl::opt<bool> + Wide("wide", cl::desc("Ignored for compatibility with GNU objdump"), + cl::cat(ObjdumpCat)); +static cl::alias WideShort("w", cl::Grouping, cl::aliasopt(Wide)); + +static cl::extrahelp + HelpResponse("\nPass @FILE as argument to read options from FILE.\n"); + +static StringSet<> DisasmFuncsSet; +static StringSet<> FoundSectionSet; +static StringRef ToolName; + +typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy; + +namespace { +struct FilterResult { + // True if the section should not be skipped. + bool Keep; + + // True if the index counter should be incremented, even if the section should + // be skipped. For example, sections may be skipped if they are not included + // in the --section flag, but we still want those to count toward the section + // count. + bool IncrementIndex; +}; +} // namespace + +static FilterResult checkSectionFilter(object::SectionRef S) { + if (FilterSections.empty()) + return {/*Keep=*/true, /*IncrementIndex=*/true}; + + Expected<StringRef> SecNameOrErr = S.getName(); + if (!SecNameOrErr) { + consumeError(SecNameOrErr.takeError()); + return {/*Keep=*/false, /*IncrementIndex=*/false}; + } + StringRef SecName = *SecNameOrErr; + + // StringSet does not allow empty key so avoid adding sections with + // no name (such as the section with index 0) here. + if (!SecName.empty()) + FoundSectionSet.insert(SecName); + + // Only show the section if it's in the FilterSections list, but always + // increment so the indexing is stable. + return {/*Keep=*/is_contained(FilterSections, SecName), + /*IncrementIndex=*/true}; +} + +SectionFilter ToolSectionFilter(object::ObjectFile const &O, uint64_t *Idx) { + // Start at UINT64_MAX so that the first index returned after an increment is + // zero (after the unsigned wrap). + if (Idx) + *Idx = UINT64_MAX; + return SectionFilter( + [Idx](object::SectionRef S) { + FilterResult Result = checkSectionFilter(S); + if (Idx != nullptr && Result.IncrementIndex) + *Idx += 1; + return Result.Keep; + }, + O); +} + +std::string getFileNameForError(const object::Archive::Child &C, + unsigned Index) { + Expected<StringRef> NameOrErr = C.getName(); + if (NameOrErr) + return NameOrErr.get(); + // If we have an error getting the name then we print the index of the archive + // member. Since we are already in an error state, we just ignore this error. + consumeError(NameOrErr.takeError()); + return "<file index: " + std::to_string(Index) + ">"; +} + +void reportWarning(Twine Message, StringRef File) { + // Output order between errs() and outs() matters especially for archive + // files where the output is per member object. + outs().flush(); + WithColor::warning(errs(), ToolName) + << "'" << File << "': " << Message << "\n"; + errs().flush(); +} + +LLVM_ATTRIBUTE_NORETURN void reportError(StringRef File, Twine Message) { + WithColor::error(errs(), ToolName) << "'" << File << "': " << Message << "\n"; + exit(1); +} + +LLVM_ATTRIBUTE_NORETURN void reportError(Error E, StringRef FileName, + StringRef ArchiveName, + StringRef ArchitectureName) { + assert(E); + WithColor::error(errs(), ToolName); + if (ArchiveName != "") + errs() << ArchiveName << "(" << FileName << ")"; + else + errs() << "'" << FileName << "'"; + if (!ArchitectureName.empty()) + errs() << " (for architecture " << ArchitectureName << ")"; + std::string Buf; + raw_string_ostream OS(Buf); + logAllUnhandledErrors(std::move(E), OS); + OS.flush(); + errs() << ": " << Buf; + exit(1); +} + +static void reportCmdLineWarning(Twine Message) { + WithColor::warning(errs(), ToolName) << Message << "\n"; +} + +LLVM_ATTRIBUTE_NORETURN static void reportCmdLineError(Twine Message) { + WithColor::error(errs(), ToolName) << Message << "\n"; + exit(1); +} + +static void warnOnNoMatchForSections() { + SetVector<StringRef> MissingSections; + for (StringRef S : FilterSections) { + if (FoundSectionSet.count(S)) + return; + // User may specify a unnamed section. Don't warn for it. + if (!S.empty()) + MissingSections.insert(S); + } + + // Warn only if no section in FilterSections is matched. + for (StringRef S : MissingSections) + reportCmdLineWarning("section '" + S + + "' mentioned in a -j/--section option, but not " + "found in any input file"); +} + +static const Target *getTarget(const ObjectFile *Obj) { + // Figure out the target triple. + Triple TheTriple("unknown-unknown-unknown"); + if (TripleName.empty()) { + TheTriple = Obj->makeTriple(); + } else { + TheTriple.setTriple(Triple::normalize(TripleName)); + auto Arch = Obj->getArch(); + if (Arch == Triple::arm || Arch == Triple::armeb) + Obj->setARMSubArch(TheTriple); + } + + // Get the target specific parser. + std::string Error; + const Target *TheTarget = TargetRegistry::lookupTarget(ArchName, TheTriple, + Error); + if (!TheTarget) + reportError(Obj->getFileName(), "can't find target: " + Error); + + // Update the triple name and return the found target. + TripleName = TheTriple.getTriple(); + return TheTarget; +} + +bool isRelocAddressLess(RelocationRef A, RelocationRef B) { + return A.getOffset() < B.getOffset(); +} + +static Error getRelocationValueString(const RelocationRef &Rel, + SmallVectorImpl<char> &Result) { + const ObjectFile *Obj = Rel.getObject(); + if (auto *ELF = dyn_cast<ELFObjectFileBase>(Obj)) + return getELFRelocationValueString(ELF, Rel, Result); + if (auto *COFF = dyn_cast<COFFObjectFile>(Obj)) + return getCOFFRelocationValueString(COFF, Rel, Result); + if (auto *Wasm = dyn_cast<WasmObjectFile>(Obj)) + return getWasmRelocationValueString(Wasm, Rel, Result); + if (auto *MachO = dyn_cast<MachOObjectFile>(Obj)) + return getMachORelocationValueString(MachO, Rel, Result); + llvm_unreachable("unknown object file format"); +} + +/// Indicates whether this relocation should hidden when listing +/// relocations, usually because it is the trailing part of a multipart +/// relocation that will be printed as part of the leading relocation. +static bool getHidden(RelocationRef RelRef) { + auto *MachO = dyn_cast<MachOObjectFile>(RelRef.getObject()); + if (!MachO) + return false; + + unsigned Arch = MachO->getArch(); + DataRefImpl Rel = RelRef.getRawDataRefImpl(); + uint64_t Type = MachO->getRelocationType(Rel); + + // On arches that use the generic relocations, GENERIC_RELOC_PAIR + // is always hidden. + if (Arch == Triple::x86 || Arch == Triple::arm || Arch == Triple::ppc) + return Type == MachO::GENERIC_RELOC_PAIR; + + if (Arch == Triple::x86_64) { + // On x86_64, X86_64_RELOC_UNSIGNED is hidden only when it follows + // an X86_64_RELOC_SUBTRACTOR. + if (Type == MachO::X86_64_RELOC_UNSIGNED && Rel.d.a > 0) { + DataRefImpl RelPrev = Rel; + RelPrev.d.a--; + uint64_t PrevType = MachO->getRelocationType(RelPrev); + if (PrevType == MachO::X86_64_RELOC_SUBTRACTOR) + return true; + } + } + + return false; +} + +namespace { +class SourcePrinter { +protected: + DILineInfo OldLineInfo; + const ObjectFile *Obj = nullptr; + std::unique_ptr<symbolize::LLVMSymbolizer> Symbolizer; + // File name to file contents of source. + std::unordered_map<std::string, std::unique_ptr<MemoryBuffer>> SourceCache; + // Mark the line endings of the cached source. + std::unordered_map<std::string, std::vector<StringRef>> LineCache; + // Keep track of missing sources. + StringSet<> MissingSources; + // Only emit 'no debug info' warning once. + bool WarnedNoDebugInfo; + +private: + bool cacheSource(const DILineInfo& LineInfoFile); + +public: + SourcePrinter() = default; + SourcePrinter(const ObjectFile *Obj, StringRef DefaultArch) + : Obj(Obj), WarnedNoDebugInfo(false) { + symbolize::LLVMSymbolizer::Options SymbolizerOpts; + SymbolizerOpts.PrintFunctions = DILineInfoSpecifier::FunctionNameKind::None; + SymbolizerOpts.Demangle = false; + SymbolizerOpts.DefaultArch = DefaultArch; + Symbolizer.reset(new symbolize::LLVMSymbolizer(SymbolizerOpts)); + } + virtual ~SourcePrinter() = default; + virtual void printSourceLine(raw_ostream &OS, + object::SectionedAddress Address, + StringRef ObjectFilename, + StringRef Delimiter = "; "); +}; + +bool SourcePrinter::cacheSource(const DILineInfo &LineInfo) { + std::unique_ptr<MemoryBuffer> Buffer; + if (LineInfo.Source) { + Buffer = MemoryBuffer::getMemBuffer(*LineInfo.Source); + } else { + auto BufferOrError = MemoryBuffer::getFile(LineInfo.FileName); + if (!BufferOrError) { + if (MissingSources.insert(LineInfo.FileName).second) + reportWarning("failed to find source " + LineInfo.FileName, + Obj->getFileName()); + return false; + } + Buffer = std::move(*BufferOrError); + } + // Chomp the file to get lines + const char *BufferStart = Buffer->getBufferStart(), + *BufferEnd = Buffer->getBufferEnd(); + std::vector<StringRef> &Lines = LineCache[LineInfo.FileName]; + const char *Start = BufferStart; + for (const char *I = BufferStart; I != BufferEnd; ++I) + if (*I == '\n') { + Lines.emplace_back(Start, I - Start - (BufferStart < I && I[-1] == '\r')); + Start = I + 1; + } + if (Start < BufferEnd) + Lines.emplace_back(Start, BufferEnd - Start); + SourceCache[LineInfo.FileName] = std::move(Buffer); + return true; +} + +void SourcePrinter::printSourceLine(raw_ostream &OS, + object::SectionedAddress Address, + StringRef ObjectFilename, + StringRef Delimiter) { + if (!Symbolizer) + return; + + DILineInfo LineInfo = DILineInfo(); + auto ExpectedLineInfo = Symbolizer->symbolizeCode(*Obj, Address); + std::string ErrorMessage; + if (!ExpectedLineInfo) + ErrorMessage = toString(ExpectedLineInfo.takeError()); + else + LineInfo = *ExpectedLineInfo; + + if (LineInfo.FileName == DILineInfo::BadString) { + if (!WarnedNoDebugInfo) { + std::string Warning = + "failed to parse debug information for " + ObjectFilename.str(); + if (!ErrorMessage.empty()) + Warning += ": " + ErrorMessage; + reportWarning(Warning, ObjectFilename); + WarnedNoDebugInfo = true; + } + return; + } + + if (LineInfo.Line == 0 || ((OldLineInfo.Line == LineInfo.Line) && + (OldLineInfo.FileName == LineInfo.FileName))) + return; + + if (PrintLines) + OS << Delimiter << LineInfo.FileName << ":" << LineInfo.Line << "\n"; + if (PrintSource) { + if (SourceCache.find(LineInfo.FileName) == SourceCache.end()) + if (!cacheSource(LineInfo)) + return; + auto LineBuffer = LineCache.find(LineInfo.FileName); + if (LineBuffer != LineCache.end()) { + if (LineInfo.Line > LineBuffer->second.size()) { + reportWarning( + formatv( + "debug info line number {0} exceeds the number of lines in {1}", + LineInfo.Line, LineInfo.FileName), + ObjectFilename); + return; + } + // Vector begins at 0, line numbers are non-zero + OS << Delimiter << LineBuffer->second[LineInfo.Line - 1] << '\n'; + } + } + OldLineInfo = LineInfo; +} + +static bool isAArch64Elf(const ObjectFile *Obj) { + const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj); + return Elf && Elf->getEMachine() == ELF::EM_AARCH64; +} + +static bool isArmElf(const ObjectFile *Obj) { + const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj); + return Elf && Elf->getEMachine() == ELF::EM_ARM; +} + +static bool hasMappingSymbols(const ObjectFile *Obj) { + return isArmElf(Obj) || isAArch64Elf(Obj); +} + +static void printRelocation(StringRef FileName, const RelocationRef &Rel, + uint64_t Address, bool Is64Bits) { + StringRef Fmt = Is64Bits ? "\t\t%016" PRIx64 ": " : "\t\t\t%08" PRIx64 ": "; + SmallString<16> Name; + SmallString<32> Val; + Rel.getTypeName(Name); + if (Error E = getRelocationValueString(Rel, Val)) + reportError(std::move(E), FileName); + outs() << format(Fmt.data(), Address) << Name << "\t" << Val << "\n"; +} + +class PrettyPrinter { +public: + virtual ~PrettyPrinter() = default; + virtual void printInst(MCInstPrinter &IP, const MCInst *MI, + ArrayRef<uint8_t> Bytes, + object::SectionedAddress Address, raw_ostream &OS, + StringRef Annot, MCSubtargetInfo const &STI, + SourcePrinter *SP, StringRef ObjectFilename, + std::vector<RelocationRef> *Rels = nullptr) { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ObjectFilename); + + size_t Start = OS.tell(); + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address.Address); + if (!NoShowRawInsn) { + OS << ' '; + dumpBytes(Bytes, OS); + } + + // The output of printInst starts with a tab. Print some spaces so that + // the tab has 1 column and advances to the target tab stop. + unsigned TabStop = NoShowRawInsn ? 16 : 40; + unsigned Column = OS.tell() - Start; + OS.indent(Column < TabStop - 1 ? TabStop - 1 - Column : 7 - Column % 8); + + if (MI) + IP.printInst(MI, OS, "", STI); + else + OS << "\t<unknown>"; + } +}; +PrettyPrinter PrettyPrinterInst; + +class HexagonPrettyPrinter : public PrettyPrinter { +public: + void printLead(ArrayRef<uint8_t> Bytes, uint64_t Address, + raw_ostream &OS) { + uint32_t opcode = + (Bytes[3] << 24) | (Bytes[2] << 16) | (Bytes[1] << 8) | Bytes[0]; + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address); + if (!NoShowRawInsn) { + OS << "\t"; + dumpBytes(Bytes.slice(0, 4), OS); + OS << format("\t%08" PRIx32, opcode); + } + } + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + object::SectionedAddress Address, raw_ostream &OS, + StringRef Annot, MCSubtargetInfo const &STI, SourcePrinter *SP, + StringRef ObjectFilename, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ObjectFilename, ""); + if (!MI) { + printLead(Bytes, Address.Address, OS); + OS << " <unknown>"; + return; + } + std::string Buffer; + { + raw_string_ostream TempStream(Buffer); + IP.printInst(MI, TempStream, "", STI); + } + StringRef Contents(Buffer); + // Split off bundle attributes + auto PacketBundle = Contents.rsplit('\n'); + // Split off first instruction from the rest + auto HeadTail = PacketBundle.first.split('\n'); + auto Preamble = " { "; + auto Separator = ""; + + // Hexagon's packets require relocations to be inline rather than + // clustered at the end of the packet. + std::vector<RelocationRef>::const_iterator RelCur = Rels->begin(); + std::vector<RelocationRef>::const_iterator RelEnd = Rels->end(); + auto PrintReloc = [&]() -> void { + while ((RelCur != RelEnd) && (RelCur->getOffset() <= Address.Address)) { + if (RelCur->getOffset() == Address.Address) { + printRelocation(ObjectFilename, *RelCur, Address.Address, false); + return; + } + ++RelCur; + } + }; + + while (!HeadTail.first.empty()) { + OS << Separator; + Separator = "\n"; + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ObjectFilename, ""); + printLead(Bytes, Address.Address, OS); + OS << Preamble; + Preamble = " "; + StringRef Inst; + auto Duplex = HeadTail.first.split('\v'); + if (!Duplex.second.empty()) { + OS << Duplex.first; + OS << "; "; + Inst = Duplex.second; + } + else + Inst = HeadTail.first; + OS << Inst; + HeadTail = HeadTail.second.split('\n'); + if (HeadTail.first.empty()) + OS << " } " << PacketBundle.second; + PrintReloc(); + Bytes = Bytes.slice(4); + Address.Address += 4; + } + } +}; +HexagonPrettyPrinter HexagonPrettyPrinterInst; + +class AMDGCNPrettyPrinter : public PrettyPrinter { +public: + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + object::SectionedAddress Address, raw_ostream &OS, + StringRef Annot, MCSubtargetInfo const &STI, SourcePrinter *SP, + StringRef ObjectFilename, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ObjectFilename); + + if (MI) { + SmallString<40> InstStr; + raw_svector_ostream IS(InstStr); + + IP.printInst(MI, IS, "", STI); + + OS << left_justify(IS.str(), 60); + } else { + // an unrecognized encoding - this is probably data so represent it + // using the .long directive, or .byte directive if fewer than 4 bytes + // remaining + if (Bytes.size() >= 4) { + OS << format("\t.long 0x%08" PRIx32 " ", + support::endian::read32<support::little>(Bytes.data())); + OS.indent(42); + } else { + OS << format("\t.byte 0x%02" PRIx8, Bytes[0]); + for (unsigned int i = 1; i < Bytes.size(); i++) + OS << format(", 0x%02" PRIx8, Bytes[i]); + OS.indent(55 - (6 * Bytes.size())); + } + } + + OS << format("// %012" PRIX64 ":", Address.Address); + if (Bytes.size() >= 4) { + // D should be casted to uint32_t here as it is passed by format to + // snprintf as vararg. + for (uint32_t D : makeArrayRef( + reinterpret_cast<const support::little32_t *>(Bytes.data()), + Bytes.size() / 4)) + OS << format(" %08" PRIX32, D); + } else { + for (unsigned char B : Bytes) + OS << format(" %02" PRIX8, B); + } + + if (!Annot.empty()) + OS << " // " << Annot; + } +}; +AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst; + +class BPFPrettyPrinter : public PrettyPrinter { +public: + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + object::SectionedAddress Address, raw_ostream &OS, + StringRef Annot, MCSubtargetInfo const &STI, SourcePrinter *SP, + StringRef ObjectFilename, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ObjectFilename); + if (!NoLeadingAddr) + OS << format("%8" PRId64 ":", Address.Address / 8); + if (!NoShowRawInsn) { + OS << "\t"; + dumpBytes(Bytes, OS); + } + if (MI) + IP.printInst(MI, OS, "", STI); + else + OS << "\t<unknown>"; + } +}; +BPFPrettyPrinter BPFPrettyPrinterInst; + +PrettyPrinter &selectPrettyPrinter(Triple const &Triple) { + switch(Triple.getArch()) { + default: + return PrettyPrinterInst; + case Triple::hexagon: + return HexagonPrettyPrinterInst; + case Triple::amdgcn: + return AMDGCNPrettyPrinterInst; + case Triple::bpfel: + case Triple::bpfeb: + return BPFPrettyPrinterInst; + } +} +} + +static uint8_t getElfSymbolType(const ObjectFile *Obj, const SymbolRef &Sym) { + assert(Obj->isELF()); + if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj)) + return Elf32LEObj->getSymbol(Sym.getRawDataRefImpl())->getType(); + if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj)) + return Elf64LEObj->getSymbol(Sym.getRawDataRefImpl())->getType(); + if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj)) + return Elf32BEObj->getSymbol(Sym.getRawDataRefImpl())->getType(); + if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj)) + return Elf64BEObj->getSymbol(Sym.getRawDataRefImpl())->getType(); + llvm_unreachable("Unsupported binary format"); +} + +template <class ELFT> static void +addDynamicElfSymbols(const ELFObjectFile<ELFT> *Obj, + std::map<SectionRef, SectionSymbolsTy> &AllSymbols) { + for (auto Symbol : Obj->getDynamicSymbolIterators()) { + uint8_t SymbolType = Symbol.getELFType(); + if (SymbolType == ELF::STT_SECTION) + continue; + + uint64_t Address = unwrapOrError(Symbol.getAddress(), Obj->getFileName()); + // ELFSymbolRef::getAddress() returns size instead of value for common + // symbols which is not desirable for disassembly output. Overriding. + if (SymbolType == ELF::STT_COMMON) + Address = Obj->getSymbol(Symbol.getRawDataRefImpl())->st_value; + + StringRef Name = unwrapOrError(Symbol.getName(), Obj->getFileName()); + if (Name.empty()) + continue; + + section_iterator SecI = + unwrapOrError(Symbol.getSection(), Obj->getFileName()); + if (SecI == Obj->section_end()) + continue; + + AllSymbols[*SecI].emplace_back(Address, Name, SymbolType); + } +} + +static void +addDynamicElfSymbols(const ObjectFile *Obj, + std::map<SectionRef, SectionSymbolsTy> &AllSymbols) { + assert(Obj->isELF()); + if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj)) + addDynamicElfSymbols(Elf32LEObj, AllSymbols); + else if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj)) + addDynamicElfSymbols(Elf64LEObj, AllSymbols); + else if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj)) + addDynamicElfSymbols(Elf32BEObj, AllSymbols); + else if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj)) + addDynamicElfSymbols(Elf64BEObj, AllSymbols); + else + llvm_unreachable("Unsupported binary format"); +} + +static void addPltEntries(const ObjectFile *Obj, + std::map<SectionRef, SectionSymbolsTy> &AllSymbols, + StringSaver &Saver) { + Optional<SectionRef> Plt = None; + for (const SectionRef &Section : Obj->sections()) { + Expected<StringRef> SecNameOrErr = Section.getName(); + if (!SecNameOrErr) { + consumeError(SecNameOrErr.takeError()); + continue; + } + if (*SecNameOrErr == ".plt") + Plt = Section; + } + if (!Plt) + return; + if (auto *ElfObj = dyn_cast<ELFObjectFileBase>(Obj)) { + for (auto PltEntry : ElfObj->getPltAddresses()) { + SymbolRef Symbol(PltEntry.first, ElfObj); + uint8_t SymbolType = getElfSymbolType(Obj, Symbol); + + StringRef Name = unwrapOrError(Symbol.getName(), Obj->getFileName()); + if (!Name.empty()) + AllSymbols[*Plt].emplace_back( + PltEntry.second, Saver.save((Name + "@plt").str()), SymbolType); + } + } +} + +// Normally the disassembly output will skip blocks of zeroes. This function +// returns the number of zero bytes that can be skipped when dumping the +// disassembly of the instructions in Buf. +static size_t countSkippableZeroBytes(ArrayRef<uint8_t> Buf) { + // Find the number of leading zeroes. + size_t N = 0; + while (N < Buf.size() && !Buf[N]) + ++N; + + // We may want to skip blocks of zero bytes, but unless we see + // at least 8 of them in a row. + if (N < 8) + return 0; + + // We skip zeroes in multiples of 4 because do not want to truncate an + // instruction if it starts with a zero byte. + return N & ~0x3; +} + +// Returns a map from sections to their relocations. +static std::map<SectionRef, std::vector<RelocationRef>> +getRelocsMap(object::ObjectFile const &Obj) { + std::map<SectionRef, std::vector<RelocationRef>> Ret; + uint64_t I = (uint64_t)-1; + for (SectionRef Sec : Obj.sections()) { + ++I; + Expected<section_iterator> RelocatedOrErr = Sec.getRelocatedSection(); + if (!RelocatedOrErr) + reportError(Obj.getFileName(), + "section (" + Twine(I) + + "): failed to get a relocated section: " + + toString(RelocatedOrErr.takeError())); + + section_iterator Relocated = *RelocatedOrErr; + if (Relocated == Obj.section_end() || !checkSectionFilter(*Relocated).Keep) + continue; + std::vector<RelocationRef> &V = Ret[*Relocated]; + for (const RelocationRef &R : Sec.relocations()) + V.push_back(R); + // Sort relocations by address. + llvm::stable_sort(V, isRelocAddressLess); + } + return Ret; +} + +// Used for --adjust-vma to check if address should be adjusted by the +// specified value for a given section. +// For ELF we do not adjust non-allocatable sections like debug ones, +// because they are not loadable. +// TODO: implement for other file formats. +static bool shouldAdjustVA(const SectionRef &Section) { + const ObjectFile *Obj = Section.getObject(); + if (isa<object::ELFObjectFileBase>(Obj)) + return ELFSectionRef(Section).getFlags() & ELF::SHF_ALLOC; + return false; +} + + +typedef std::pair<uint64_t, char> MappingSymbolPair; +static char getMappingSymbolKind(ArrayRef<MappingSymbolPair> MappingSymbols, + uint64_t Address) { + auto It = + partition_point(MappingSymbols, [Address](const MappingSymbolPair &Val) { + return Val.first <= Address; + }); + // Return zero for any address before the first mapping symbol; this means + // we should use the default disassembly mode, depending on the target. + if (It == MappingSymbols.begin()) + return '\x00'; + return (It - 1)->second; +} + +static uint64_t +dumpARMELFData(uint64_t SectionAddr, uint64_t Index, uint64_t End, + const ObjectFile *Obj, ArrayRef<uint8_t> Bytes, + ArrayRef<MappingSymbolPair> MappingSymbols) { + support::endianness Endian = + Obj->isLittleEndian() ? support::little : support::big; + while (Index < End) { + outs() << format("%8" PRIx64 ":", SectionAddr + Index); + outs() << "\t"; + if (Index + 4 <= End) { + dumpBytes(Bytes.slice(Index, 4), outs()); + outs() << "\t.word\t" + << format_hex( + support::endian::read32(Bytes.data() + Index, Endian), 10); + Index += 4; + } else if (Index + 2 <= End) { + dumpBytes(Bytes.slice(Index, 2), outs()); + outs() << "\t\t.short\t" + << format_hex( + support::endian::read16(Bytes.data() + Index, Endian), 6); + Index += 2; + } else { + dumpBytes(Bytes.slice(Index, 1), outs()); + outs() << "\t\t.byte\t" << format_hex(Bytes[0], 4); + ++Index; + } + outs() << "\n"; + if (getMappingSymbolKind(MappingSymbols, Index) != 'd') + break; + } + return Index; +} + +static void dumpELFData(uint64_t SectionAddr, uint64_t Index, uint64_t End, + ArrayRef<uint8_t> Bytes) { + // print out data up to 8 bytes at a time in hex and ascii + uint8_t AsciiData[9] = {'\0'}; + uint8_t Byte; + int NumBytes = 0; + + for (; Index < End; ++Index) { + if (NumBytes == 0) + outs() << format("%8" PRIx64 ":", SectionAddr + Index); + Byte = Bytes.slice(Index)[0]; + outs() << format(" %02x", Byte); + AsciiData[NumBytes] = isPrint(Byte) ? Byte : '.'; + + uint8_t IndentOffset = 0; + NumBytes++; + if (Index == End - 1 || NumBytes > 8) { + // Indent the space for less than 8 bytes data. + // 2 spaces for byte and one for space between bytes + IndentOffset = 3 * (8 - NumBytes); + for (int Excess = NumBytes; Excess < 8; Excess++) + AsciiData[Excess] = '\0'; + NumBytes = 8; + } + if (NumBytes == 8) { + AsciiData[8] = '\0'; + outs() << std::string(IndentOffset, ' ') << " "; + outs() << reinterpret_cast<char *>(AsciiData); + outs() << '\n'; + NumBytes = 0; + } + } +} + +static void disassembleObject(const Target *TheTarget, const ObjectFile *Obj, + MCContext &Ctx, MCDisassembler *PrimaryDisAsm, + MCDisassembler *SecondaryDisAsm, + const MCInstrAnalysis *MIA, MCInstPrinter *IP, + const MCSubtargetInfo *PrimarySTI, + const MCSubtargetInfo *SecondarySTI, + PrettyPrinter &PIP, + SourcePrinter &SP, bool InlineRelocs) { + const MCSubtargetInfo *STI = PrimarySTI; + MCDisassembler *DisAsm = PrimaryDisAsm; + bool PrimaryIsThumb = false; + if (isArmElf(Obj)) + PrimaryIsThumb = STI->checkFeatures("+thumb-mode"); + + std::map<SectionRef, std::vector<RelocationRef>> RelocMap; + if (InlineRelocs) + RelocMap = getRelocsMap(*Obj); + bool Is64Bits = Obj->getBytesInAddress() > 4; + + // Create a mapping from virtual address to symbol name. This is used to + // pretty print the symbols while disassembling. + std::map<SectionRef, SectionSymbolsTy> AllSymbols; + SectionSymbolsTy AbsoluteSymbols; + const StringRef FileName = Obj->getFileName(); + for (const SymbolRef &Symbol : Obj->symbols()) { + uint64_t Address = unwrapOrError(Symbol.getAddress(), FileName); + + StringRef Name = unwrapOrError(Symbol.getName(), FileName); + if (Name.empty()) + continue; + + uint8_t SymbolType = ELF::STT_NOTYPE; + if (Obj->isELF()) { + SymbolType = getElfSymbolType(Obj, Symbol); + if (SymbolType == ELF::STT_SECTION) + continue; + } + + section_iterator SecI = unwrapOrError(Symbol.getSection(), FileName); + if (SecI != Obj->section_end()) + AllSymbols[*SecI].emplace_back(Address, Name, SymbolType); + else + AbsoluteSymbols.emplace_back(Address, Name, SymbolType); + } + if (AllSymbols.empty() && Obj->isELF()) + addDynamicElfSymbols(Obj, AllSymbols); + + BumpPtrAllocator A; + StringSaver Saver(A); + addPltEntries(Obj, AllSymbols, Saver); + + // Create a mapping from virtual address to section. + std::vector<std::pair<uint64_t, SectionRef>> SectionAddresses; + for (SectionRef Sec : Obj->sections()) + SectionAddresses.emplace_back(Sec.getAddress(), Sec); + array_pod_sort(SectionAddresses.begin(), SectionAddresses.end()); + + // Linked executables (.exe and .dll files) typically don't include a real + // symbol table but they might contain an export table. + if (const auto *COFFObj = dyn_cast<COFFObjectFile>(Obj)) { + for (const auto &ExportEntry : COFFObj->export_directories()) { + StringRef Name; + if (std::error_code EC = ExportEntry.getSymbolName(Name)) + reportError(errorCodeToError(EC), Obj->getFileName()); + if (Name.empty()) + continue; + + uint32_t RVA; + if (std::error_code EC = ExportEntry.getExportRVA(RVA)) + reportError(errorCodeToError(EC), Obj->getFileName()); + + uint64_t VA = COFFObj->getImageBase() + RVA; + auto Sec = partition_point( + SectionAddresses, [VA](const std::pair<uint64_t, SectionRef> &O) { + return O.first <= VA; + }); + if (Sec != SectionAddresses.begin()) { + --Sec; + AllSymbols[Sec->second].emplace_back(VA, Name, ELF::STT_NOTYPE); + } else + AbsoluteSymbols.emplace_back(VA, Name, ELF::STT_NOTYPE); + } + } + + // Sort all the symbols, this allows us to use a simple binary search to find + // a symbol near an address. + StringSet<> FoundDisasmFuncsSet; + for (std::pair<const SectionRef, SectionSymbolsTy> &SecSyms : AllSymbols) + array_pod_sort(SecSyms.second.begin(), SecSyms.second.end()); + array_pod_sort(AbsoluteSymbols.begin(), AbsoluteSymbols.end()); + + for (const SectionRef &Section : ToolSectionFilter(*Obj)) { + if (FilterSections.empty() && !DisassembleAll && + (!Section.isText() || Section.isVirtual())) + continue; + + uint64_t SectionAddr = Section.getAddress(); + uint64_t SectSize = Section.getSize(); + if (!SectSize) + continue; + + // Get the list of all the symbols in this section. + SectionSymbolsTy &Symbols = AllSymbols[Section]; + std::vector<MappingSymbolPair> MappingSymbols; + if (hasMappingSymbols(Obj)) { + for (const auto &Symb : Symbols) { + uint64_t Address = std::get<0>(Symb); + StringRef Name = std::get<1>(Symb); + if (Name.startswith("$d")) + MappingSymbols.emplace_back(Address - SectionAddr, 'd'); + if (Name.startswith("$x")) + MappingSymbols.emplace_back(Address - SectionAddr, 'x'); + if (Name.startswith("$a")) + MappingSymbols.emplace_back(Address - SectionAddr, 'a'); + if (Name.startswith("$t")) + MappingSymbols.emplace_back(Address - SectionAddr, 't'); + } + } + + llvm::sort(MappingSymbols); + + if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) { + // AMDGPU disassembler uses symbolizer for printing labels + std::unique_ptr<MCRelocationInfo> RelInfo( + TheTarget->createMCRelocationInfo(TripleName, Ctx)); + if (RelInfo) { + std::unique_ptr<MCSymbolizer> Symbolizer( + TheTarget->createMCSymbolizer( + TripleName, nullptr, nullptr, &Symbols, &Ctx, std::move(RelInfo))); + DisAsm->setSymbolizer(std::move(Symbolizer)); + } + } + + StringRef SegmentName = ""; + if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj)) { + DataRefImpl DR = Section.getRawDataRefImpl(); + SegmentName = MachO->getSectionFinalSegmentName(DR); + } + + StringRef SectionName = unwrapOrError(Section.getName(), Obj->getFileName()); + // If the section has no symbol at the start, just insert a dummy one. + if (Symbols.empty() || std::get<0>(Symbols[0]) != 0) { + Symbols.insert( + Symbols.begin(), + std::make_tuple(SectionAddr, SectionName, + Section.isText() ? ELF::STT_FUNC : ELF::STT_OBJECT)); + } + + SmallString<40> Comments; + raw_svector_ostream CommentStream(Comments); + + ArrayRef<uint8_t> Bytes = arrayRefFromStringRef( + unwrapOrError(Section.getContents(), Obj->getFileName())); + + uint64_t VMAAdjustment = 0; + if (shouldAdjustVA(Section)) + VMAAdjustment = AdjustVMA; + + uint64_t Size; + uint64_t Index; + bool PrintedSection = false; + std::vector<RelocationRef> Rels = RelocMap[Section]; + std::vector<RelocationRef>::const_iterator RelCur = Rels.begin(); + std::vector<RelocationRef>::const_iterator RelEnd = Rels.end(); + // Disassemble symbol by symbol. + for (unsigned SI = 0, SE = Symbols.size(); SI != SE; ++SI) { + std::string SymbolName = std::get<1>(Symbols[SI]).str(); + if (Demangle) + SymbolName = demangle(SymbolName); + + // Skip if --disassemble-functions is not empty and the symbol is not in + // the list. + if (!DisasmFuncsSet.empty() && !DisasmFuncsSet.count(SymbolName)) + continue; + + uint64_t Start = std::get<0>(Symbols[SI]); + if (Start < SectionAddr || StopAddress <= Start) + continue; + else + FoundDisasmFuncsSet.insert(SymbolName); + + // The end is the section end, the beginning of the next symbol, or + // --stop-address. + uint64_t End = std::min<uint64_t>(SectionAddr + SectSize, StopAddress); + if (SI + 1 < SE) + End = std::min(End, std::get<0>(Symbols[SI + 1])); + if (Start >= End || End <= StartAddress) + continue; + Start -= SectionAddr; + End -= SectionAddr; + + if (!PrintedSection) { + PrintedSection = true; + outs() << "\nDisassembly of section "; + if (!SegmentName.empty()) + outs() << SegmentName << ","; + outs() << SectionName << ":\n"; + } + + if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) { + if (std::get<2>(Symbols[SI]) == ELF::STT_AMDGPU_HSA_KERNEL) { + // skip amd_kernel_code_t at the begining of kernel symbol (256 bytes) + Start += 256; + } + if (SI == SE - 1 || + std::get<2>(Symbols[SI + 1]) == ELF::STT_AMDGPU_HSA_KERNEL) { + // cut trailing zeroes at the end of kernel + // cut up to 256 bytes + const uint64_t EndAlign = 256; + const auto Limit = End - (std::min)(EndAlign, End - Start); + while (End > Limit && + *reinterpret_cast<const support::ulittle32_t*>(&Bytes[End - 4]) == 0) + End -= 4; + } + } + + outs() << '\n'; + if (!NoLeadingAddr) + outs() << format(Is64Bits ? "%016" PRIx64 " " : "%08" PRIx64 " ", + SectionAddr + Start + VMAAdjustment); + + outs() << SymbolName << ":\n"; + + // Don't print raw contents of a virtual section. A virtual section + // doesn't have any contents in the file. + if (Section.isVirtual()) { + outs() << "...\n"; + continue; + } + +#ifndef NDEBUG + raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); +#else + raw_ostream &DebugOut = nulls(); +#endif + + // Some targets (like WebAssembly) have a special prelude at the start + // of each symbol. + DisAsm->onSymbolStart(SymbolName, Size, Bytes.slice(Start, End - Start), + SectionAddr + Start, DebugOut, CommentStream); + Start += Size; + + Index = Start; + if (SectionAddr < StartAddress) + Index = std::max<uint64_t>(Index, StartAddress - SectionAddr); + + // If there is a data/common symbol inside an ELF text section and we are + // only disassembling text (applicable all architectures), we are in a + // situation where we must print the data and not disassemble it. + if (Obj->isELF() && !DisassembleAll && Section.isText()) { + uint8_t SymTy = std::get<2>(Symbols[SI]); + if (SymTy == ELF::STT_OBJECT || SymTy == ELF::STT_COMMON) { + dumpELFData(SectionAddr, Index, End, Bytes); + Index = End; + } + } + + bool CheckARMELFData = hasMappingSymbols(Obj) && + std::get<2>(Symbols[SI]) != ELF::STT_OBJECT && + !DisassembleAll; + while (Index < End) { + // ARM and AArch64 ELF binaries can interleave data and text in the + // same section. We rely on the markers introduced to understand what + // we need to dump. If the data marker is within a function, it is + // denoted as a word/short etc. + if (CheckARMELFData && + getMappingSymbolKind(MappingSymbols, Index) == 'd') { + Index = dumpARMELFData(SectionAddr, Index, End, Obj, Bytes, + MappingSymbols); + continue; + } + + // When -z or --disassemble-zeroes are given we always dissasemble + // them. Otherwise we might want to skip zero bytes we see. + if (!DisassembleZeroes) { + uint64_t MaxOffset = End - Index; + // For -reloc: print zero blocks patched by relocations, so that + // relocations can be shown in the dump. + if (RelCur != RelEnd) + MaxOffset = RelCur->getOffset() - Index; + + if (size_t N = + countSkippableZeroBytes(Bytes.slice(Index, MaxOffset))) { + outs() << "\t\t..." << '\n'; + Index += N; + continue; + } + } + + if (SecondarySTI) { + if (getMappingSymbolKind(MappingSymbols, Index) == 'a') { + STI = PrimaryIsThumb ? SecondarySTI : PrimarySTI; + DisAsm = PrimaryIsThumb ? SecondaryDisAsm : PrimaryDisAsm; + } else if (getMappingSymbolKind(MappingSymbols, Index) == 't') { + STI = PrimaryIsThumb ? PrimarySTI : SecondarySTI; + DisAsm = PrimaryIsThumb ? PrimaryDisAsm : SecondaryDisAsm; + } + } + + // Disassemble a real instruction or a data when disassemble all is + // provided + MCInst Inst; + bool Disassembled = DisAsm->getInstruction( + Inst, Size, Bytes.slice(Index), SectionAddr + Index, DebugOut, + CommentStream); + if (Size == 0) + Size = 1; + + PIP.printInst(*IP, Disassembled ? &Inst : nullptr, + Bytes.slice(Index, Size), + {SectionAddr + Index + VMAAdjustment, Section.getIndex()}, + outs(), "", *STI, &SP, Obj->getFileName(), &Rels); + outs() << CommentStream.str(); + Comments.clear(); + + // Try to resolve the target of a call, tail call, etc. to a specific + // symbol. + if (MIA && (MIA->isCall(Inst) || MIA->isUnconditionalBranch(Inst) || + MIA->isConditionalBranch(Inst))) { + uint64_t Target; + if (MIA->evaluateBranch(Inst, SectionAddr + Index, Size, Target)) { + // In a relocatable object, the target's section must reside in + // the same section as the call instruction or it is accessed + // through a relocation. + // + // In a non-relocatable object, the target may be in any section. + // + // N.B. We don't walk the relocations in the relocatable case yet. + auto *TargetSectionSymbols = &Symbols; + if (!Obj->isRelocatableObject()) { + auto It = partition_point( + SectionAddresses, + [=](const std::pair<uint64_t, SectionRef> &O) { + return O.first <= Target; + }); + if (It != SectionAddresses.begin()) { + --It; + TargetSectionSymbols = &AllSymbols[It->second]; + } else { + TargetSectionSymbols = &AbsoluteSymbols; + } + } + + // Find the last symbol in the section whose offset is less than + // or equal to the target. If there isn't a section that contains + // the target, find the nearest preceding absolute symbol. + auto TargetSym = partition_point( + *TargetSectionSymbols, + [=](const std::tuple<uint64_t, StringRef, uint8_t> &O) { + return std::get<0>(O) <= Target; + }); + if (TargetSym == TargetSectionSymbols->begin()) { + TargetSectionSymbols = &AbsoluteSymbols; + TargetSym = partition_point( + AbsoluteSymbols, + [=](const std::tuple<uint64_t, StringRef, uint8_t> &O) { + return std::get<0>(O) <= Target; + }); + } + if (TargetSym != TargetSectionSymbols->begin()) { + --TargetSym; + uint64_t TargetAddress = std::get<0>(*TargetSym); + StringRef TargetName = std::get<1>(*TargetSym); + outs() << " <" << TargetName; + uint64_t Disp = Target - TargetAddress; + if (Disp) + outs() << "+0x" << Twine::utohexstr(Disp); + outs() << '>'; + } + } + } + outs() << "\n"; + + // Hexagon does this in pretty printer + if (Obj->getArch() != Triple::hexagon) { + // Print relocation for instruction. + while (RelCur != RelEnd) { + uint64_t Offset = RelCur->getOffset(); + // If this relocation is hidden, skip it. + if (getHidden(*RelCur) || SectionAddr + Offset < StartAddress) { + ++RelCur; + continue; + } + + // Stop when RelCur's offset is past the current instruction. + if (Offset >= Index + Size) + break; + + // When --adjust-vma is used, update the address printed. + if (RelCur->getSymbol() != Obj->symbol_end()) { + Expected<section_iterator> SymSI = + RelCur->getSymbol()->getSection(); + if (SymSI && *SymSI != Obj->section_end() && + shouldAdjustVA(**SymSI)) + Offset += AdjustVMA; + } + + printRelocation(Obj->getFileName(), *RelCur, SectionAddr + Offset, + Is64Bits); + ++RelCur; + } + } + + Index += Size; + } + } + } + StringSet<> MissingDisasmFuncsSet = + set_difference(DisasmFuncsSet, FoundDisasmFuncsSet); + for (StringRef MissingDisasmFunc : MissingDisasmFuncsSet.keys()) + reportWarning("failed to disassemble missing function " + MissingDisasmFunc, + FileName); +} + +static void disassembleObject(const ObjectFile *Obj, bool InlineRelocs) { + const Target *TheTarget = getTarget(Obj); + + // Package up features to be passed to target/subtarget + SubtargetFeatures Features = Obj->getFeatures(); + if (!MAttrs.empty()) + for (unsigned I = 0; I != MAttrs.size(); ++I) + Features.AddFeature(MAttrs[I]); + + std::unique_ptr<const MCRegisterInfo> MRI( + TheTarget->createMCRegInfo(TripleName)); + if (!MRI) + reportError(Obj->getFileName(), + "no register info for target " + TripleName); + + // Set up disassembler. + std::unique_ptr<const MCAsmInfo> AsmInfo( + TheTarget->createMCAsmInfo(*MRI, TripleName)); + if (!AsmInfo) + reportError(Obj->getFileName(), + "no assembly info for target " + TripleName); + std::unique_ptr<const MCSubtargetInfo> STI( + TheTarget->createMCSubtargetInfo(TripleName, MCPU, Features.getString())); + if (!STI) + reportError(Obj->getFileName(), + "no subtarget info for target " + TripleName); + std::unique_ptr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo()); + if (!MII) + reportError(Obj->getFileName(), + "no instruction info for target " + TripleName); + MCObjectFileInfo MOFI; + MCContext Ctx(AsmInfo.get(), MRI.get(), &MOFI); + // FIXME: for now initialize MCObjectFileInfo with default values + MOFI.InitMCObjectFileInfo(Triple(TripleName), false, Ctx); + + std::unique_ptr<MCDisassembler> DisAsm( + TheTarget->createMCDisassembler(*STI, Ctx)); + if (!DisAsm) + reportError(Obj->getFileName(), "no disassembler for target " + TripleName); + + // If we have an ARM object file, we need a second disassembler, because + // ARM CPUs have two different instruction sets: ARM mode, and Thumb mode. + // We use mapping symbols to switch between the two assemblers, where + // appropriate. + std::unique_ptr<MCDisassembler> SecondaryDisAsm; + std::unique_ptr<const MCSubtargetInfo> SecondarySTI; + if (isArmElf(Obj) && !STI->checkFeatures("+mclass")) { + if (STI->checkFeatures("+thumb-mode")) + Features.AddFeature("-thumb-mode"); + else + Features.AddFeature("+thumb-mode"); + SecondarySTI.reset(TheTarget->createMCSubtargetInfo(TripleName, MCPU, + Features.getString())); + SecondaryDisAsm.reset(TheTarget->createMCDisassembler(*SecondarySTI, Ctx)); + } + + std::unique_ptr<const MCInstrAnalysis> MIA( + TheTarget->createMCInstrAnalysis(MII.get())); + + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + std::unique_ptr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( + Triple(TripleName), AsmPrinterVariant, *AsmInfo, *MII, *MRI)); + if (!IP) + reportError(Obj->getFileName(), + "no instruction printer for target " + TripleName); + IP->setPrintImmHex(PrintImmHex); + + PrettyPrinter &PIP = selectPrettyPrinter(Triple(TripleName)); + SourcePrinter SP(Obj, TheTarget->getName()); + + for (StringRef Opt : DisassemblerOptions) + if (!IP->applyTargetSpecificCLOption(Opt)) + reportError(Obj->getFileName(), + "Unrecognized disassembler option: " + Opt); + + disassembleObject(TheTarget, Obj, Ctx, DisAsm.get(), SecondaryDisAsm.get(), + MIA.get(), IP.get(), STI.get(), SecondarySTI.get(), PIP, + SP, InlineRelocs); +} + +void printRelocations(const ObjectFile *Obj) { + StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 : + "%08" PRIx64; + // Regular objdump doesn't print relocations in non-relocatable object + // files. + if (!Obj->isRelocatableObject()) + return; + + // Build a mapping from relocation target to a vector of relocation + // sections. Usually, there is an only one relocation section for + // each relocated section. + MapVector<SectionRef, std::vector<SectionRef>> SecToRelSec; + uint64_t Ndx; + for (const SectionRef &Section : ToolSectionFilter(*Obj, &Ndx)) { + if (Section.relocation_begin() == Section.relocation_end()) + continue; + Expected<section_iterator> SecOrErr = Section.getRelocatedSection(); + if (!SecOrErr) + reportError(Obj->getFileName(), + "section (" + Twine(Ndx) + + "): unable to get a relocation target: " + + toString(SecOrErr.takeError())); + SecToRelSec[**SecOrErr].push_back(Section); + } + + for (std::pair<SectionRef, std::vector<SectionRef>> &P : SecToRelSec) { + StringRef SecName = unwrapOrError(P.first.getName(), Obj->getFileName()); + outs() << "RELOCATION RECORDS FOR [" << SecName << "]:\n"; + + for (SectionRef Section : P.second) { + for (const RelocationRef &Reloc : Section.relocations()) { + uint64_t Address = Reloc.getOffset(); + SmallString<32> RelocName; + SmallString<32> ValueStr; + if (Address < StartAddress || Address > StopAddress || getHidden(Reloc)) + continue; + Reloc.getTypeName(RelocName); + if (Error E = getRelocationValueString(Reloc, ValueStr)) + reportError(std::move(E), Obj->getFileName()); + + outs() << format(Fmt.data(), Address) << " " << RelocName << " " + << ValueStr << "\n"; + } + } + outs() << "\n"; + } +} + +void printDynamicRelocations(const ObjectFile *Obj) { + // For the moment, this option is for ELF only + if (!Obj->isELF()) + return; + + const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj); + if (!Elf || Elf->getEType() != ELF::ET_DYN) { + reportError(Obj->getFileName(), "not a dynamic object"); + return; + } + + std::vector<SectionRef> DynRelSec = Obj->dynamic_relocation_sections(); + if (DynRelSec.empty()) + return; + + outs() << "DYNAMIC RELOCATION RECORDS\n"; + StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 : "%08" PRIx64; + for (const SectionRef &Section : DynRelSec) + for (const RelocationRef &Reloc : Section.relocations()) { + uint64_t Address = Reloc.getOffset(); + SmallString<32> RelocName; + SmallString<32> ValueStr; + Reloc.getTypeName(RelocName); + if (Error E = getRelocationValueString(Reloc, ValueStr)) + reportError(std::move(E), Obj->getFileName()); + outs() << format(Fmt.data(), Address) << " " << RelocName << " " + << ValueStr << "\n"; + } +} + +// Returns true if we need to show LMA column when dumping section headers. We +// show it only when the platform is ELF and either we have at least one section +// whose VMA and LMA are different and/or when --show-lma flag is used. +static bool shouldDisplayLMA(const ObjectFile *Obj) { + if (!Obj->isELF()) + return false; + for (const SectionRef &S : ToolSectionFilter(*Obj)) + if (S.getAddress() != getELFSectionLMA(S)) + return true; + return ShowLMA; +} + +static size_t getMaxSectionNameWidth(const ObjectFile *Obj) { + // Default column width for names is 13 even if no names are that long. + size_t MaxWidth = 13; + for (const SectionRef &Section : ToolSectionFilter(*Obj)) { + StringRef Name = unwrapOrError(Section.getName(), Obj->getFileName()); + MaxWidth = std::max(MaxWidth, Name.size()); + } + return MaxWidth; +} + +void printSectionHeaders(const ObjectFile *Obj) { + size_t NameWidth = getMaxSectionNameWidth(Obj); + size_t AddressWidth = 2 * Obj->getBytesInAddress(); + bool HasLMAColumn = shouldDisplayLMA(Obj); + if (HasLMAColumn) + outs() << "Sections:\n" + "Idx " + << left_justify("Name", NameWidth) << " Size " + << left_justify("VMA", AddressWidth) << " " + << left_justify("LMA", AddressWidth) << " Type\n"; + else + outs() << "Sections:\n" + "Idx " + << left_justify("Name", NameWidth) << " Size " + << left_justify("VMA", AddressWidth) << " Type\n"; + + uint64_t Idx; + for (const SectionRef &Section : ToolSectionFilter(*Obj, &Idx)) { + StringRef Name = unwrapOrError(Section.getName(), Obj->getFileName()); + uint64_t VMA = Section.getAddress(); + if (shouldAdjustVA(Section)) + VMA += AdjustVMA; + + uint64_t Size = Section.getSize(); + + std::string Type = Section.isText() ? "TEXT" : ""; + if (Section.isData()) + Type += Type.empty() ? "DATA" : " DATA"; + if (Section.isBSS()) + Type += Type.empty() ? "BSS" : " BSS"; + + if (HasLMAColumn) + outs() << format("%3" PRIu64 " %-*s %08" PRIx64 " ", Idx, NameWidth, + Name.str().c_str(), Size) + << format_hex_no_prefix(VMA, AddressWidth) << " " + << format_hex_no_prefix(getELFSectionLMA(Section), AddressWidth) + << " " << Type << "\n"; + else + outs() << format("%3" PRIu64 " %-*s %08" PRIx64 " ", Idx, NameWidth, + Name.str().c_str(), Size) + << format_hex_no_prefix(VMA, AddressWidth) << " " << Type << "\n"; + } + outs() << "\n"; +} + +void printSectionContents(const ObjectFile *Obj) { + for (const SectionRef &Section : ToolSectionFilter(*Obj)) { + StringRef Name = unwrapOrError(Section.getName(), Obj->getFileName()); + uint64_t BaseAddr = Section.getAddress(); + uint64_t Size = Section.getSize(); + if (!Size) + continue; + + outs() << "Contents of section " << Name << ":\n"; + if (Section.isBSS()) { + outs() << format("<skipping contents of bss section at [%04" PRIx64 + ", %04" PRIx64 ")>\n", + BaseAddr, BaseAddr + Size); + continue; + } + + StringRef Contents = unwrapOrError(Section.getContents(), Obj->getFileName()); + + // Dump out the content as hex and printable ascii characters. + for (std::size_t Addr = 0, End = Contents.size(); Addr < End; Addr += 16) { + outs() << format(" %04" PRIx64 " ", BaseAddr + Addr); + // Dump line of hex. + for (std::size_t I = 0; I < 16; ++I) { + if (I != 0 && I % 4 == 0) + outs() << ' '; + if (Addr + I < End) + outs() << hexdigit((Contents[Addr + I] >> 4) & 0xF, true) + << hexdigit(Contents[Addr + I] & 0xF, true); + else + outs() << " "; + } + // Print ascii. + outs() << " "; + for (std::size_t I = 0; I < 16 && Addr + I < End; ++I) { + if (isPrint(static_cast<unsigned char>(Contents[Addr + I]) & 0xFF)) + outs() << Contents[Addr + I]; + else + outs() << "."; + } + outs() << "\n"; + } + } +} + +void printSymbolTable(const ObjectFile *O, StringRef ArchiveName, + StringRef ArchitectureName) { + outs() << "SYMBOL TABLE:\n"; + + if (const COFFObjectFile *Coff = dyn_cast<const COFFObjectFile>(O)) { + printCOFFSymbolTable(Coff); + return; + } + + const StringRef FileName = O->getFileName(); + for (auto I = O->symbol_begin(), E = O->symbol_end(); I != E; ++I) { + const SymbolRef &Symbol = *I; + uint64_t Address = unwrapOrError(Symbol.getAddress(), FileName, ArchiveName, + ArchitectureName); + if ((Address < StartAddress) || (Address > StopAddress)) + continue; + SymbolRef::Type Type = unwrapOrError(Symbol.getType(), FileName, + ArchiveName, ArchitectureName); + uint32_t Flags = Symbol.getFlags(); + section_iterator Section = unwrapOrError(Symbol.getSection(), FileName, + ArchiveName, ArchitectureName); + StringRef Name; + if (Type == SymbolRef::ST_Debug && Section != O->section_end()) { + if (Expected<StringRef> NameOrErr = Section->getName()) + Name = *NameOrErr; + else + consumeError(NameOrErr.takeError()); + + } else { + Name = unwrapOrError(Symbol.getName(), FileName, ArchiveName, + ArchitectureName); + } + + bool Global = Flags & SymbolRef::SF_Global; + bool Weak = Flags & SymbolRef::SF_Weak; + bool Absolute = Flags & SymbolRef::SF_Absolute; + bool Common = Flags & SymbolRef::SF_Common; + bool Hidden = Flags & SymbolRef::SF_Hidden; + + char GlobLoc = ' '; + if (Type != SymbolRef::ST_Unknown) + GlobLoc = Global ? 'g' : 'l'; + char Debug = (Type == SymbolRef::ST_Debug || Type == SymbolRef::ST_File) + ? 'd' : ' '; + char FileFunc = ' '; + if (Type == SymbolRef::ST_File) + FileFunc = 'f'; + else if (Type == SymbolRef::ST_Function) + FileFunc = 'F'; + else if (Type == SymbolRef::ST_Data) + FileFunc = 'O'; + + const char *Fmt = O->getBytesInAddress() > 4 ? "%016" PRIx64 : + "%08" PRIx64; + + outs() << format(Fmt, Address) << " " + << GlobLoc // Local -> 'l', Global -> 'g', Neither -> ' ' + << (Weak ? 'w' : ' ') // Weak? + << ' ' // Constructor. Not supported yet. + << ' ' // Warning. Not supported yet. + << ' ' // Indirect reference to another symbol. + << Debug // Debugging (d) or dynamic (D) symbol. + << FileFunc // Name of function (F), file (f) or object (O). + << ' '; + if (Absolute) { + outs() << "*ABS*"; + } else if (Common) { + outs() << "*COM*"; + } else if (Section == O->section_end()) { + outs() << "*UND*"; + } else { + if (const MachOObjectFile *MachO = + dyn_cast<const MachOObjectFile>(O)) { + DataRefImpl DR = Section->getRawDataRefImpl(); + StringRef SegmentName = MachO->getSectionFinalSegmentName(DR); + outs() << SegmentName << ","; + } + StringRef SectionName = + unwrapOrError(Section->getName(), O->getFileName()); + outs() << SectionName; + } + + if (Common || isa<ELFObjectFileBase>(O)) { + uint64_t Val = + Common ? Symbol.getAlignment() : ELFSymbolRef(Symbol).getSize(); + outs() << format("\t%08" PRIx64, Val); + } + + if (isa<ELFObjectFileBase>(O)) { + uint8_t Other = ELFSymbolRef(Symbol).getOther(); + switch (Other) { + case ELF::STV_DEFAULT: + break; + case ELF::STV_INTERNAL: + outs() << " .internal"; + break; + case ELF::STV_HIDDEN: + outs() << " .hidden"; + break; + case ELF::STV_PROTECTED: + outs() << " .protected"; + break; + default: + outs() << format(" 0x%02x", Other); + break; + } + } else if (Hidden) { + outs() << " .hidden"; + } + + if (Demangle) + outs() << ' ' << demangle(Name) << '\n'; + else + outs() << ' ' << Name << '\n'; + } +} + +static void printUnwindInfo(const ObjectFile *O) { + outs() << "Unwind info:\n\n"; + + if (const COFFObjectFile *Coff = dyn_cast<COFFObjectFile>(O)) + printCOFFUnwindInfo(Coff); + else if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(O)) + printMachOUnwindInfo(MachO); + else + // TODO: Extract DWARF dump tool to objdump. + WithColor::error(errs(), ToolName) + << "This operation is only currently supported " + "for COFF and MachO object files.\n"; +} + +/// Dump the raw contents of the __clangast section so the output can be piped +/// into llvm-bcanalyzer. +void printRawClangAST(const ObjectFile *Obj) { + if (outs().is_displayed()) { + WithColor::error(errs(), ToolName) + << "The -raw-clang-ast option will dump the raw binary contents of " + "the clang ast section.\n" + "Please redirect the output to a file or another program such as " + "llvm-bcanalyzer.\n"; + return; + } + + StringRef ClangASTSectionName("__clangast"); + if (isa<COFFObjectFile>(Obj)) { + ClangASTSectionName = "clangast"; + } + + Optional<object::SectionRef> ClangASTSection; + for (auto Sec : ToolSectionFilter(*Obj)) { + StringRef Name; + if (Expected<StringRef> NameOrErr = Sec.getName()) + Name = *NameOrErr; + else + consumeError(NameOrErr.takeError()); + + if (Name == ClangASTSectionName) { + ClangASTSection = Sec; + break; + } + } + if (!ClangASTSection) + return; + + StringRef ClangASTContents = unwrapOrError( + ClangASTSection.getValue().getContents(), Obj->getFileName()); + outs().write(ClangASTContents.data(), ClangASTContents.size()); +} + +static void printFaultMaps(const ObjectFile *Obj) { + StringRef FaultMapSectionName; + + if (isa<ELFObjectFileBase>(Obj)) { + FaultMapSectionName = ".llvm_faultmaps"; + } else if (isa<MachOObjectFile>(Obj)) { + FaultMapSectionName = "__llvm_faultmaps"; + } else { + WithColor::error(errs(), ToolName) + << "This operation is only currently supported " + "for ELF and Mach-O executable files.\n"; + return; + } + + Optional<object::SectionRef> FaultMapSection; + + for (auto Sec : ToolSectionFilter(*Obj)) { + StringRef Name; + if (Expected<StringRef> NameOrErr = Sec.getName()) + Name = *NameOrErr; + else + consumeError(NameOrErr.takeError()); + + if (Name == FaultMapSectionName) { + FaultMapSection = Sec; + break; + } + } + + outs() << "FaultMap table:\n"; + + if (!FaultMapSection.hasValue()) { + outs() << "<not found>\n"; + return; + } + + StringRef FaultMapContents = + unwrapOrError(FaultMapSection.getValue().getContents(), Obj->getFileName()); + FaultMapParser FMP(FaultMapContents.bytes_begin(), + FaultMapContents.bytes_end()); + + outs() << FMP; +} + +static void printPrivateFileHeaders(const ObjectFile *O, bool OnlyFirst) { + if (O->isELF()) { + printELFFileHeader(O); + printELFDynamicSection(O); + printELFSymbolVersionInfo(O); + return; + } + if (O->isCOFF()) + return printCOFFFileHeader(O); + if (O->isWasm()) + return printWasmFileHeader(O); + if (O->isMachO()) { + printMachOFileHeader(O); + if (!OnlyFirst) + printMachOLoadCommands(O); + return; + } + reportError(O->getFileName(), "Invalid/Unsupported object file format"); +} + +static void printFileHeaders(const ObjectFile *O) { + if (!O->isELF() && !O->isCOFF()) + reportError(O->getFileName(), "Invalid/Unsupported object file format"); + + Triple::ArchType AT = O->getArch(); + outs() << "architecture: " << Triple::getArchTypeName(AT) << "\n"; + uint64_t Address = unwrapOrError(O->getStartAddress(), O->getFileName()); + + StringRef Fmt = O->getBytesInAddress() > 4 ? "%016" PRIx64 : "%08" PRIx64; + outs() << "start address: " + << "0x" << format(Fmt.data(), Address) << "\n\n"; +} + +static void printArchiveChild(StringRef Filename, const Archive::Child &C) { + Expected<sys::fs::perms> ModeOrErr = C.getAccessMode(); + if (!ModeOrErr) { + WithColor::error(errs(), ToolName) << "ill-formed archive entry.\n"; + consumeError(ModeOrErr.takeError()); + return; + } + sys::fs::perms Mode = ModeOrErr.get(); + outs() << ((Mode & sys::fs::owner_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::owner_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::owner_exe) ? "x" : "-"); + outs() << ((Mode & sys::fs::group_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::group_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::group_exe) ? "x" : "-"); + outs() << ((Mode & sys::fs::others_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::others_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::others_exe) ? "x" : "-"); + + outs() << " "; + + outs() << format("%d/%d %6" PRId64 " ", unwrapOrError(C.getUID(), Filename), + unwrapOrError(C.getGID(), Filename), + unwrapOrError(C.getRawSize(), Filename)); + + StringRef RawLastModified = C.getRawLastModified(); + unsigned Seconds; + if (RawLastModified.getAsInteger(10, Seconds)) + outs() << "(date: \"" << RawLastModified + << "\" contains non-decimal chars) "; + else { + // Since ctime(3) returns a 26 character string of the form: + // "Sun Sep 16 01:03:52 1973\n\0" + // just print 24 characters. + time_t t = Seconds; + outs() << format("%.24s ", ctime(&t)); + } + + StringRef Name = ""; + Expected<StringRef> NameOrErr = C.getName(); + if (!NameOrErr) { + consumeError(NameOrErr.takeError()); + Name = unwrapOrError(C.getRawName(), Filename); + } else { + Name = NameOrErr.get(); + } + outs() << Name << "\n"; +} + +// For ELF only now. +static bool shouldWarnForInvalidStartStopAddress(ObjectFile *Obj) { + if (const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj)) { + if (Elf->getEType() != ELF::ET_REL) + return true; + } + return false; +} + +static void checkForInvalidStartStopAddress(ObjectFile *Obj, + uint64_t Start, uint64_t Stop) { + if (!shouldWarnForInvalidStartStopAddress(Obj)) + return; + + for (const SectionRef &Section : Obj->sections()) + if (ELFSectionRef(Section).getFlags() & ELF::SHF_ALLOC) { + uint64_t BaseAddr = Section.getAddress(); + uint64_t Size = Section.getSize(); + if ((Start < BaseAddr + Size) && Stop > BaseAddr) + return; + } + + if (StartAddress.getNumOccurrences() == 0) + reportWarning("no section has address less than 0x" + + Twine::utohexstr(Stop) + " specified by --stop-address", + Obj->getFileName()); + else if (StopAddress.getNumOccurrences() == 0) + reportWarning("no section has address greater than or equal to 0x" + + Twine::utohexstr(Start) + " specified by --start-address", + Obj->getFileName()); + else + reportWarning("no section overlaps the range [0x" + + Twine::utohexstr(Start) + ",0x" + Twine::utohexstr(Stop) + + ") specified by --start-address/--stop-address", + Obj->getFileName()); +} + +static void dumpObject(ObjectFile *O, const Archive *A = nullptr, + const Archive::Child *C = nullptr) { + // Avoid other output when using a raw option. + if (!RawClangAST) { + outs() << '\n'; + if (A) + outs() << A->getFileName() << "(" << O->getFileName() << ")"; + else + outs() << O->getFileName(); + outs() << ":\tfile format " << O->getFileFormatName() << "\n\n"; + } + + if (StartAddress.getNumOccurrences() || StopAddress.getNumOccurrences()) + checkForInvalidStartStopAddress(O, StartAddress, StopAddress); + + // Note: the order here matches GNU objdump for compatability. + StringRef ArchiveName = A ? A->getFileName() : ""; + if (ArchiveHeaders && !MachOOpt && C) + printArchiveChild(ArchiveName, *C); + if (FileHeaders) + printFileHeaders(O); + if (PrivateHeaders || FirstPrivateHeader) + printPrivateFileHeaders(O, FirstPrivateHeader); + if (SectionHeaders) + printSectionHeaders(O); + if (SymbolTable) + printSymbolTable(O, ArchiveName); + if (DwarfDumpType != DIDT_Null) { + std::unique_ptr<DIContext> DICtx = DWARFContext::create(*O); + // Dump the complete DWARF structure. + DIDumpOptions DumpOpts; + DumpOpts.DumpType = DwarfDumpType; + DICtx->dump(outs(), DumpOpts); + } + if (Relocations && !Disassemble) + printRelocations(O); + if (DynamicRelocations) + printDynamicRelocations(O); + if (SectionContents) + printSectionContents(O); + if (Disassemble) + disassembleObject(O, Relocations); + if (UnwindInfo) + printUnwindInfo(O); + + // Mach-O specific options: + if (ExportsTrie) + printExportsTrie(O); + if (Rebase) + printRebaseTable(O); + if (Bind) + printBindTable(O); + if (LazyBind) + printLazyBindTable(O); + if (WeakBind) + printWeakBindTable(O); + + // Other special sections: + if (RawClangAST) + printRawClangAST(O); + if (FaultMapSection) + printFaultMaps(O); +} + +static void dumpObject(const COFFImportFile *I, const Archive *A, + const Archive::Child *C = nullptr) { + StringRef ArchiveName = A ? A->getFileName() : ""; + + // Avoid other output when using a raw option. + if (!RawClangAST) + outs() << '\n' + << ArchiveName << "(" << I->getFileName() << ")" + << ":\tfile format COFF-import-file" + << "\n\n"; + + if (ArchiveHeaders && !MachOOpt && C) + printArchiveChild(ArchiveName, *C); + if (SymbolTable) + printCOFFSymbolTable(I); +} + +/// Dump each object file in \a a; +static void dumpArchive(const Archive *A) { + Error Err = Error::success(); + unsigned I = -1; + for (auto &C : A->children(Err)) { + ++I; + Expected<std::unique_ptr<Binary>> ChildOrErr = C.getAsBinary(); + if (!ChildOrErr) { + if (auto E = isNotObjectErrorInvalidFileType(ChildOrErr.takeError())) + reportError(std::move(E), getFileNameForError(C, I), A->getFileName()); + continue; + } + if (ObjectFile *O = dyn_cast<ObjectFile>(&*ChildOrErr.get())) + dumpObject(O, A, &C); + else if (COFFImportFile *I = dyn_cast<COFFImportFile>(&*ChildOrErr.get())) + dumpObject(I, A, &C); + else + reportError(errorCodeToError(object_error::invalid_file_type), + A->getFileName()); + } + if (Err) + reportError(std::move(Err), A->getFileName()); +} + +/// Open file and figure out how to dump it. +static void dumpInput(StringRef file) { + // If we are using the Mach-O specific object file parser, then let it parse + // the file and process the command line options. So the -arch flags can + // be used to select specific slices, etc. + if (MachOOpt) { + parseInputMachO(file); + return; + } + + // Attempt to open the binary. + OwningBinary<Binary> OBinary = unwrapOrError(createBinary(file), file); + Binary &Binary = *OBinary.getBinary(); + + if (Archive *A = dyn_cast<Archive>(&Binary)) + dumpArchive(A); + else if (ObjectFile *O = dyn_cast<ObjectFile>(&Binary)) + dumpObject(O); + else if (MachOUniversalBinary *UB = dyn_cast<MachOUniversalBinary>(&Binary)) + parseInputMachO(UB); + else + reportError(errorCodeToError(object_error::invalid_file_type), file); +} +} // namespace llvm + +int main(int argc, char **argv) { + using namespace llvm; + InitLLVM X(argc, argv); + const cl::OptionCategory *OptionFilters[] = {&ObjdumpCat, &MachOCat}; + cl::HideUnrelatedOptions(OptionFilters); + + // Initialize targets and assembly printers/parsers. + InitializeAllTargetInfos(); + InitializeAllTargetMCs(); + InitializeAllDisassemblers(); + + // Register the target printer for --version. + cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion); + + cl::ParseCommandLineOptions(argc, argv, "llvm object file dumper\n"); + + if (StartAddress >= StopAddress) + reportCmdLineError("start address should be less than stop address"); + + ToolName = argv[0]; + + // Defaults to a.out if no filenames specified. + if (InputFilenames.empty()) + InputFilenames.push_back("a.out"); + + if (AllHeaders) + ArchiveHeaders = FileHeaders = PrivateHeaders = Relocations = + SectionHeaders = SymbolTable = true; + + if (DisassembleAll || PrintSource || PrintLines || + (!DisassembleFunctions.empty())) + Disassemble = true; + + if (!ArchiveHeaders && !Disassemble && DwarfDumpType == DIDT_Null && + !DynamicRelocations && !FileHeaders && !PrivateHeaders && !RawClangAST && + !Relocations && !SectionHeaders && !SectionContents && !SymbolTable && + !UnwindInfo && !FaultMapSection && + !(MachOOpt && + (Bind || DataInCode || DylibId || DylibsUsed || ExportsTrie || + FirstPrivateHeader || IndirectSymbols || InfoPlist || LazyBind || + LinkOptHints || ObjcMetaData || Rebase || UniversalHeaders || + WeakBind || !FilterSections.empty()))) { + cl::PrintHelpMessage(); + return 2; + } + + DisasmFuncsSet.insert(DisassembleFunctions.begin(), + DisassembleFunctions.end()); + + llvm::for_each(InputFilenames, dumpInput); + + warnOnNoMatchForSections(); + + return EXIT_SUCCESS; +} |