llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp

2343 lines
85 KiB
C++

//===-- 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/MC/MCTargetOptions.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;
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 std::string(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 = std::string(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, Address.Address, "", STI, OS);
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, Address.Address, "", STI, TempStream);
}
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, Address.Address, "", STI, IS);
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, Address.Address, "", STI, OS);
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();
const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj);
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;
}
// Don't ask a Mach-O STAB symbol for its section unless you know that
// STAB symbol's section field refers to a valid section index. Otherwise
// the symbol may error trying to load a section that does not exist.
if (MachO) {
DataRefImpl SymDRI = Symbol.getRawDataRefImpl();
uint8_t NType = (MachO->is64Bit() ?
MachO->getSymbol64TableEntry(SymDRI).n_type:
MachO->getSymbolTableEntry(SymDRI).n_type);
if (NType & MachO::N_STAB)
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 (MachO) {
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;
}
// 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, 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, 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();
// If disassembly has failed, continue with the next instruction, to
// avoid analysing invalid/incomplete instruction information.
if (!Disassembled) {
outs() << "\n";
Index += Size;
continue;
}
// 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.
MCTargetOptions MCOptions;
std::unique_ptr<const MCAsmInfo> AsmInfo(
TheTarget->createMCAsmInfo(*MRI, TripleName, MCOptions));
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();
const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(O);
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();
// Don't ask a Mach-O STAB symbol for its section unless you know that
// STAB symbol's section field refers to a valid section index. Otherwise
// the symbol may error trying to load a section that does not exist.
bool isSTAB = false;
if (MachO) {
DataRefImpl SymDRI = Symbol.getRawDataRefImpl();
uint8_t NType = (MachO->is64Bit() ?
MachO->getSymbol64TableEntry(SymDRI).n_type:
MachO->getSymbolTableEntry(SymDRI).n_type);
if (NType & MachO::N_STAB)
isSTAB = true;
}
section_iterator Section = isSTAB ? O->section_end() :
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(std::string(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;
}