2011-09-19 17:56:04 +00:00
|
|
|
//===-- MachODump.cpp - Object file dumping utility for llvm --------------===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file implements the MachO-specific dumper for llvm-objdump.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "llvm-objdump.h"
|
|
|
|
#include "MCFunction.h"
|
|
|
|
#include "llvm/Support/MachO.h"
|
|
|
|
#include "llvm/Object/MachOObject.h"
|
|
|
|
#include "llvm/ADT/OwningPtr.h"
|
|
|
|
#include "llvm/ADT/Triple.h"
|
|
|
|
#include "llvm/ADT/STLExtras.h"
|
2011-09-21 01:13:19 +00:00
|
|
|
#include "llvm/DebugInfo/DIContext.h"
|
2011-09-19 17:56:04 +00:00
|
|
|
#include "llvm/MC/MCAsmInfo.h"
|
|
|
|
#include "llvm/MC/MCDisassembler.h"
|
|
|
|
#include "llvm/MC/MCInst.h"
|
|
|
|
#include "llvm/MC/MCInstPrinter.h"
|
|
|
|
#include "llvm/MC/MCInstrAnalysis.h"
|
|
|
|
#include "llvm/MC/MCInstrDesc.h"
|
|
|
|
#include "llvm/MC/MCInstrInfo.h"
|
|
|
|
#include "llvm/MC/MCSubtargetInfo.h"
|
|
|
|
#include "llvm/Support/CommandLine.h"
|
|
|
|
#include "llvm/Support/Debug.h"
|
|
|
|
#include "llvm/Support/Format.h"
|
|
|
|
#include "llvm/Support/GraphWriter.h"
|
|
|
|
#include "llvm/Support/MemoryBuffer.h"
|
|
|
|
#include "llvm/Support/TargetRegistry.h"
|
|
|
|
#include "llvm/Support/TargetSelect.h"
|
|
|
|
#include "llvm/Support/raw_ostream.h"
|
|
|
|
#include "llvm/Support/system_error.h"
|
|
|
|
#include <algorithm>
|
|
|
|
#include <cstring>
|
|
|
|
using namespace llvm;
|
|
|
|
using namespace object;
|
|
|
|
|
|
|
|
static cl::opt<bool>
|
|
|
|
CFG("cfg", cl::desc("Create a CFG for every symbol in the object file and"
|
|
|
|
"write it to a graphviz file (MachO-only)"));
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
static cl::opt<bool>
|
|
|
|
UseDbg("g", cl::desc("Print line information from debug info if available"));
|
|
|
|
|
|
|
|
static cl::opt<std::string>
|
|
|
|
DSYMFile("dsym", cl::desc("Use .dSYM file for debug info"));
|
|
|
|
|
2011-09-19 17:56:04 +00:00
|
|
|
static const Target *GetTarget(const MachOObject *MachOObj) {
|
|
|
|
// Figure out the target triple.
|
|
|
|
llvm::Triple TT("unknown-unknown-unknown");
|
|
|
|
switch (MachOObj->getHeader().CPUType) {
|
|
|
|
case llvm::MachO::CPUTypeI386:
|
|
|
|
TT.setArch(Triple::ArchType(Triple::x86));
|
|
|
|
break;
|
|
|
|
case llvm::MachO::CPUTypeX86_64:
|
|
|
|
TT.setArch(Triple::ArchType(Triple::x86_64));
|
|
|
|
break;
|
|
|
|
case llvm::MachO::CPUTypeARM:
|
|
|
|
TT.setArch(Triple::ArchType(Triple::arm));
|
|
|
|
break;
|
|
|
|
case llvm::MachO::CPUTypePowerPC:
|
|
|
|
TT.setArch(Triple::ArchType(Triple::ppc));
|
|
|
|
break;
|
|
|
|
case llvm::MachO::CPUTypePowerPC64:
|
|
|
|
TT.setArch(Triple::ArchType(Triple::ppc64));
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
TripleName = TT.str();
|
|
|
|
|
|
|
|
// Get the target specific parser.
|
|
|
|
std::string Error;
|
|
|
|
const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error);
|
|
|
|
if (TheTarget)
|
|
|
|
return TheTarget;
|
|
|
|
|
|
|
|
errs() << "llvm-objdump: error: unable to get target for '" << TripleName
|
|
|
|
<< "', see --version and --triple.\n";
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct Section {
|
|
|
|
char Name[16];
|
|
|
|
uint64_t Address;
|
|
|
|
uint64_t Size;
|
|
|
|
uint32_t Offset;
|
|
|
|
uint32_t NumRelocs;
|
|
|
|
uint64_t RelocTableOffset;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct Symbol {
|
|
|
|
uint64_t Value;
|
|
|
|
uint32_t StringIndex;
|
|
|
|
uint8_t SectionIndex;
|
|
|
|
bool operator<(const Symbol &RHS) const { return Value < RHS.Value; }
|
|
|
|
};
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
template <typename T>
|
|
|
|
static Section copySection(const T &Sect) {
|
|
|
|
Section S;
|
|
|
|
memcpy(S.Name, Sect->Name, 16);
|
|
|
|
S.Address = Sect->Address;
|
|
|
|
S.Size = Sect->Size;
|
|
|
|
S.Offset = Sect->Offset;
|
|
|
|
S.NumRelocs = Sect->NumRelocationTableEntries;
|
|
|
|
S.RelocTableOffset = Sect->RelocationTableOffset;
|
|
|
|
return S;
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename T>
|
|
|
|
static Symbol copySymbol(const T &STE) {
|
|
|
|
Symbol S;
|
|
|
|
S.StringIndex = STE->StringIndex;
|
|
|
|
S.SectionIndex = STE->SectionIndex;
|
|
|
|
S.Value = STE->Value;
|
|
|
|
return S;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Print addtitional information about an address, if available.
|
2011-09-19 17:56:04 +00:00
|
|
|
static void DumpAddress(uint64_t Address, ArrayRef<Section> Sections,
|
|
|
|
MachOObject *MachOObj, raw_ostream &OS) {
|
|
|
|
for (unsigned i = 0; i != Sections.size(); ++i) {
|
|
|
|
uint64_t addr = Address-Sections[i].Address;
|
|
|
|
if (Sections[i].Address <= Address &&
|
|
|
|
Sections[i].Address + Sections[i].Size > Address) {
|
|
|
|
StringRef bytes = MachOObj->getData(Sections[i].Offset,
|
|
|
|
Sections[i].Size);
|
2011-09-20 17:53:01 +00:00
|
|
|
// Print constant strings.
|
2011-09-19 17:56:04 +00:00
|
|
|
if (!strcmp(Sections[i].Name, "__cstring"))
|
|
|
|
OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"';
|
2011-09-20 17:53:01 +00:00
|
|
|
// Print constant CFStrings.
|
2011-09-19 17:56:04 +00:00
|
|
|
if (!strcmp(Sections[i].Name, "__cfstring"))
|
|
|
|
OS << "@\"" << bytes.substr(addr, bytes.find('\0', addr)) << '"';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
typedef std::map<uint64_t, MCFunction*> FunctionMapTy;
|
|
|
|
typedef SmallVector<MCFunction, 16> FunctionListTy;
|
|
|
|
static void createMCFunctionAndSaveCalls(StringRef Name,
|
|
|
|
const MCDisassembler *DisAsm,
|
|
|
|
MemoryObject &Object, uint64_t Start,
|
|
|
|
uint64_t End,
|
|
|
|
MCInstrAnalysis *InstrAnalysis,
|
|
|
|
uint64_t Address,
|
|
|
|
raw_ostream &DebugOut,
|
|
|
|
FunctionMapTy &FunctionMap,
|
|
|
|
FunctionListTy &Functions) {
|
|
|
|
SmallVector<uint64_t, 16> Calls;
|
|
|
|
MCFunction f =
|
|
|
|
MCFunction::createFunctionFromMC(Name, DisAsm, Object, Start, End,
|
|
|
|
InstrAnalysis, DebugOut, Calls);
|
|
|
|
Functions.push_back(f);
|
|
|
|
FunctionMap[Address] = &Functions.back();
|
|
|
|
|
|
|
|
// Add the gathered callees to the map.
|
|
|
|
for (unsigned i = 0, e = Calls.size(); i != e; ++i)
|
|
|
|
FunctionMap.insert(std::make_pair(Calls[i], (MCFunction*)0));
|
|
|
|
}
|
|
|
|
|
|
|
|
// Write a graphviz file for the CFG inside an MCFunction.
|
|
|
|
static void emitDOTFile(const char *FileName, const MCFunction &f,
|
|
|
|
MCInstPrinter *IP) {
|
|
|
|
// Start a new dot file.
|
|
|
|
std::string Error;
|
|
|
|
raw_fd_ostream Out(FileName, Error);
|
|
|
|
if (!Error.empty()) {
|
|
|
|
errs() << "llvm-objdump: warning: " << Error << '\n';
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
Out << "digraph " << f.getName() << " {\n";
|
|
|
|
Out << "graph [ rankdir = \"LR\" ];\n";
|
|
|
|
for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) {
|
|
|
|
bool hasPreds = false;
|
|
|
|
// Only print blocks that have predecessors.
|
|
|
|
// FIXME: Slow.
|
|
|
|
for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe;
|
|
|
|
++pi)
|
|
|
|
if (pi->second.contains(i->first)) {
|
|
|
|
hasPreds = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!hasPreds && i != f.begin())
|
|
|
|
continue;
|
|
|
|
|
|
|
|
Out << '"' << i->first << "\" [ label=\"<a>";
|
|
|
|
// Print instructions.
|
|
|
|
for (unsigned ii = 0, ie = i->second.getInsts().size(); ii != ie;
|
|
|
|
++ii) {
|
|
|
|
// Escape special chars and print the instruction in mnemonic form.
|
|
|
|
std::string Str;
|
|
|
|
raw_string_ostream OS(Str);
|
|
|
|
IP->printInst(&i->second.getInsts()[ii].Inst, OS, "");
|
|
|
|
Out << DOT::EscapeString(OS.str()) << '|';
|
|
|
|
}
|
|
|
|
Out << "<o>\" shape=\"record\" ];\n";
|
|
|
|
|
|
|
|
// Add edges.
|
|
|
|
for (MCBasicBlock::succ_iterator si = i->second.succ_begin(),
|
|
|
|
se = i->second.succ_end(); si != se; ++si)
|
|
|
|
Out << i->first << ":o -> " << *si <<":a\n";
|
|
|
|
}
|
|
|
|
Out << "}\n";
|
|
|
|
}
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
static void getSectionsAndSymbols(const macho::Header &Header,
|
|
|
|
MachOObject *MachOObj,
|
|
|
|
InMemoryStruct<macho::SymtabLoadCommand> *SymtabLC,
|
|
|
|
std::vector<Section> &Sections,
|
|
|
|
std::vector<Symbol> &Symbols,
|
|
|
|
SmallVectorImpl<uint64_t> &FoundFns) {
|
|
|
|
// Make a list of all symbols in the object file.
|
|
|
|
for (unsigned i = 0; i != Header.NumLoadCommands; ++i) {
|
|
|
|
const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i);
|
|
|
|
if (LCI.Command.Type == macho::LCT_Segment) {
|
|
|
|
InMemoryStruct<macho::SegmentLoadCommand> SegmentLC;
|
|
|
|
MachOObj->ReadSegmentLoadCommand(LCI, SegmentLC);
|
|
|
|
|
|
|
|
// Store the sections in this segment.
|
|
|
|
for (unsigned SectNum = 0; SectNum != SegmentLC->NumSections; ++SectNum) {
|
|
|
|
InMemoryStruct<macho::Section> Sect;
|
|
|
|
MachOObj->ReadSection(LCI, SectNum, Sect);
|
|
|
|
Sections.push_back(copySection(Sect));
|
|
|
|
|
|
|
|
}
|
|
|
|
} else if (LCI.Command.Type == macho::LCT_Segment64) {
|
|
|
|
InMemoryStruct<macho::Segment64LoadCommand> Segment64LC;
|
|
|
|
MachOObj->ReadSegment64LoadCommand(LCI, Segment64LC);
|
|
|
|
|
|
|
|
// Store the sections in this segment.
|
|
|
|
for (unsigned SectNum = 0; SectNum != Segment64LC->NumSections;
|
|
|
|
++SectNum) {
|
|
|
|
InMemoryStruct<macho::Section64> Sect64;
|
|
|
|
MachOObj->ReadSection64(LCI, SectNum, Sect64);
|
|
|
|
Sections.push_back(copySection(Sect64));
|
|
|
|
}
|
|
|
|
} else if (LCI.Command.Type == macho::LCT_FunctionStarts) {
|
|
|
|
// We found a function starts segment, parse the addresses for later
|
|
|
|
// consumption.
|
|
|
|
InMemoryStruct<macho::LinkeditDataLoadCommand> LLC;
|
|
|
|
MachOObj->ReadLinkeditDataLoadCommand(LCI, LLC);
|
|
|
|
|
|
|
|
MachOObj->ReadULEB128s(LLC->DataOffset, FoundFns);
|
|
|
|
}
|
|
|
|
}
|
2011-09-21 22:16:43 +00:00
|
|
|
// Store the symbols.
|
|
|
|
if (SymtabLC) {
|
|
|
|
for (unsigned i = 0; i != (*SymtabLC)->NumSymbolTableEntries; ++i) {
|
|
|
|
if (MachOObj->is64Bit()) {
|
|
|
|
InMemoryStruct<macho::Symbol64TableEntry> STE;
|
|
|
|
MachOObj->ReadSymbol64TableEntry((*SymtabLC)->SymbolTableOffset, i,
|
|
|
|
STE);
|
|
|
|
Symbols.push_back(copySymbol(STE));
|
|
|
|
} else {
|
|
|
|
InMemoryStruct<macho::SymbolTableEntry> STE;
|
|
|
|
MachOObj->ReadSymbolTableEntry((*SymtabLC)->SymbolTableOffset, i,
|
|
|
|
STE);
|
|
|
|
Symbols.push_back(copySymbol(STE));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2011-09-21 01:13:19 +00:00
|
|
|
}
|
|
|
|
|
2011-09-19 17:56:04 +00:00
|
|
|
void llvm::DisassembleInputMachO(StringRef Filename) {
|
|
|
|
OwningPtr<MemoryBuffer> Buff;
|
|
|
|
|
|
|
|
if (error_code ec = MemoryBuffer::getFileOrSTDIN(Filename, Buff)) {
|
|
|
|
errs() << "llvm-objdump: " << Filename << ": " << ec.message() << "\n";
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
OwningPtr<MachOObject> MachOObj(MachOObject::LoadFromBuffer(Buff.take()));
|
|
|
|
|
|
|
|
const Target *TheTarget = GetTarget(MachOObj.get());
|
|
|
|
if (!TheTarget) {
|
|
|
|
// GetTarget prints out stuff.
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
const MCInstrInfo *InstrInfo = TheTarget->createMCInstrInfo();
|
|
|
|
OwningPtr<MCInstrAnalysis>
|
|
|
|
InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo));
|
|
|
|
|
|
|
|
// Set up disassembler.
|
|
|
|
OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName));
|
|
|
|
OwningPtr<const MCSubtargetInfo>
|
|
|
|
STI(TheTarget->createMCSubtargetInfo(TripleName, "", ""));
|
|
|
|
OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI));
|
|
|
|
int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
|
|
|
|
OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
|
2011-09-20 17:53:01 +00:00
|
|
|
AsmPrinterVariant, *AsmInfo, *STI));
|
|
|
|
|
|
|
|
if (!InstrAnalysis || !AsmInfo || !STI || !DisAsm || !IP) {
|
|
|
|
errs() << "error: couldn't initialize disassmbler for target "
|
|
|
|
<< TripleName << '\n';
|
2011-09-19 17:56:04 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
outs() << '\n' << Filename << ":\n\n";
|
2011-09-19 17:56:04 +00:00
|
|
|
|
|
|
|
const macho::Header &Header = MachOObj->getHeader();
|
|
|
|
|
|
|
|
const MachOObject::LoadCommandInfo *SymtabLCI = 0;
|
2011-09-20 17:53:01 +00:00
|
|
|
// First, find the symbol table segment.
|
2011-09-19 17:56:04 +00:00
|
|
|
for (unsigned i = 0; i != Header.NumLoadCommands; ++i) {
|
|
|
|
const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i);
|
2011-09-20 17:53:01 +00:00
|
|
|
if (LCI.Command.Type == macho::LCT_Symtab) {
|
2011-09-19 17:56:04 +00:00
|
|
|
SymtabLCI = &LCI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Read and register the symbol table data.
|
|
|
|
InMemoryStruct<macho::SymtabLoadCommand> SymtabLC;
|
|
|
|
MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC);
|
|
|
|
MachOObj->RegisterStringTable(*SymtabLC);
|
|
|
|
|
|
|
|
std::vector<Section> Sections;
|
|
|
|
std::vector<Symbol> Symbols;
|
|
|
|
SmallVector<uint64_t, 8> FoundFns;
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
getSectionsAndSymbols(Header, MachOObj.get(), &SymtabLC, Sections, Symbols,
|
|
|
|
FoundFns);
|
2011-09-19 17:56:04 +00:00
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
// Make a copy of the unsorted symbol list. FIXME: duplication
|
|
|
|
std::vector<Symbol> UnsortedSymbols(Symbols);
|
2011-09-19 17:56:04 +00:00
|
|
|
// Sort the symbols by address, just in case they didn't come in that way.
|
|
|
|
array_pod_sort(Symbols.begin(), Symbols.end());
|
|
|
|
|
|
|
|
#ifndef NDEBUG
|
|
|
|
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
|
|
|
|
#else
|
|
|
|
raw_ostream &DebugOut = nulls();
|
|
|
|
#endif
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
StringRef DebugAbbrevSection, DebugInfoSection, DebugArangesSection,
|
|
|
|
DebugLineSection, DebugStrSection;
|
|
|
|
OwningPtr<DIContext> diContext;
|
2011-09-21 04:01:19 +00:00
|
|
|
OwningPtr<MachOObject> DSYMObj;
|
2011-09-21 18:18:53 +00:00
|
|
|
MachOObject *DbgInfoObj = MachOObj.get();
|
2011-09-21 01:13:19 +00:00
|
|
|
// Try to find debug info and set up the DIContext for it.
|
|
|
|
if (UseDbg) {
|
|
|
|
ArrayRef<Section> DebugSections = Sections;
|
|
|
|
std::vector<Section> DSYMSections;
|
|
|
|
|
|
|
|
// A separate DSym file path was specified, parse it as a macho file,
|
|
|
|
// get the sections and supply it to the section name parsing machinery.
|
|
|
|
if (!DSYMFile.empty()) {
|
|
|
|
OwningPtr<MemoryBuffer> Buf;
|
|
|
|
if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile.c_str(), Buf)) {
|
|
|
|
errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n';
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
DSYMObj.reset(MachOObject::LoadFromBuffer(Buf.take()));
|
|
|
|
const macho::Header &Header = DSYMObj->getHeader();
|
|
|
|
|
|
|
|
std::vector<Symbol> Symbols;
|
|
|
|
SmallVector<uint64_t, 8> FoundFns;
|
|
|
|
getSectionsAndSymbols(Header, DSYMObj.get(), 0, DSYMSections, Symbols,
|
|
|
|
FoundFns);
|
|
|
|
DebugSections = DSYMSections;
|
2011-09-21 18:18:53 +00:00
|
|
|
DbgInfoObj = DSYMObj.get();
|
2011-09-21 01:13:19 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// Find the named debug info sections.
|
|
|
|
for (unsigned SectIdx = 0; SectIdx != DebugSections.size(); SectIdx++) {
|
|
|
|
if (!strcmp(DebugSections[SectIdx].Name, "__debug_abbrev"))
|
2011-09-21 18:18:53 +00:00
|
|
|
DebugAbbrevSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
|
|
|
|
DebugSections[SectIdx].Size);
|
2011-09-21 01:13:19 +00:00
|
|
|
else if (!strcmp(DebugSections[SectIdx].Name, "__debug_info"))
|
2011-09-21 18:18:53 +00:00
|
|
|
DebugInfoSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
|
2011-09-21 01:13:19 +00:00
|
|
|
DebugSections[SectIdx].Size);
|
2011-09-21 18:18:53 +00:00
|
|
|
else if (!strcmp(DebugSections[SectIdx].Name, "__debug_aranges"))
|
|
|
|
DebugArangesSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
|
|
|
|
DebugSections[SectIdx].Size);
|
2011-09-21 01:13:19 +00:00
|
|
|
else if (!strcmp(DebugSections[SectIdx].Name, "__debug_line"))
|
2011-09-21 18:18:53 +00:00
|
|
|
DebugLineSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
|
|
|
|
DebugSections[SectIdx].Size);
|
2011-09-21 01:13:19 +00:00
|
|
|
else if (!strcmp(DebugSections[SectIdx].Name, "__debug_str"))
|
2011-09-21 18:18:53 +00:00
|
|
|
DebugStrSection = DbgInfoObj->getData(DebugSections[SectIdx].Offset,
|
|
|
|
DebugSections[SectIdx].Size);
|
2011-09-21 01:13:19 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
// Setup the DIContext.
|
2011-09-21 18:18:53 +00:00
|
|
|
diContext.reset(DIContext::getDWARFContext(DbgInfoObj->isLittleEndian(),
|
2011-09-21 01:13:19 +00:00
|
|
|
DebugInfoSection,
|
|
|
|
DebugAbbrevSection,
|
|
|
|
DebugArangesSection,
|
|
|
|
DebugLineSection,
|
|
|
|
DebugStrSection));
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
FunctionMapTy FunctionMap;
|
|
|
|
FunctionListTy Functions;
|
2011-09-19 17:56:04 +00:00
|
|
|
|
|
|
|
for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) {
|
|
|
|
if (strcmp(Sections[SectIdx].Name, "__text"))
|
2011-09-20 17:53:01 +00:00
|
|
|
continue; // Skip non-text sections
|
2011-09-19 17:56:04 +00:00
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// Insert the functions from the function starts segment into our map.
|
2011-09-19 17:56:04 +00:00
|
|
|
uint64_t VMAddr = Sections[SectIdx].Address - Sections[SectIdx].Offset;
|
|
|
|
for (unsigned i = 0, e = FoundFns.size(); i != e; ++i)
|
2011-09-19 20:08:52 +00:00
|
|
|
FunctionMap.insert(std::make_pair(FoundFns[i]+VMAddr, (MCFunction*)0));
|
2011-09-19 17:56:04 +00:00
|
|
|
|
|
|
|
StringRef Bytes = MachOObj->getData(Sections[SectIdx].Offset,
|
|
|
|
Sections[SectIdx].Size);
|
|
|
|
StringRefMemoryObject memoryObject(Bytes);
|
|
|
|
bool symbolTableWorked = false;
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// Parse relocations.
|
2011-09-19 17:56:04 +00:00
|
|
|
std::vector<std::pair<uint64_t, uint32_t> > Relocs;
|
|
|
|
for (unsigned j = 0; j != Sections[SectIdx].NumRelocs; ++j) {
|
|
|
|
InMemoryStruct<macho::RelocationEntry> RE;
|
|
|
|
MachOObj->ReadRelocationEntry(Sections[SectIdx].RelocTableOffset, j, RE);
|
|
|
|
Relocs.push_back(std::make_pair(RE->Word0, RE->Word1 & 0xffffff));
|
|
|
|
}
|
|
|
|
array_pod_sort(Relocs.begin(), Relocs.end());
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// Disassemble symbol by symbol.
|
2011-09-19 17:56:04 +00:00
|
|
|
for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
|
2011-09-20 17:53:01 +00:00
|
|
|
// Make sure the symbol is defined in this section.
|
2011-09-19 17:56:04 +00:00
|
|
|
if ((unsigned)Symbols[SymIdx].SectionIndex - 1 != SectIdx)
|
|
|
|
continue;
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// Start at the address of the symbol relative to the section's address.
|
2011-09-19 17:56:04 +00:00
|
|
|
uint64_t Start = Symbols[SymIdx].Value - Sections[SectIdx].Address;
|
2011-09-20 17:53:01 +00:00
|
|
|
// Stop disassembling either at the beginning of the next symbol or at
|
|
|
|
// the end of the section.
|
2011-09-19 17:56:04 +00:00
|
|
|
uint64_t End = (SymIdx+1 == Symbols.size() ||
|
|
|
|
Symbols[SymIdx].SectionIndex != Symbols[SymIdx+1].SectionIndex) ?
|
|
|
|
Sections[SectIdx].Size :
|
|
|
|
Symbols[SymIdx+1].Value - Sections[SectIdx].Address;
|
|
|
|
uint64_t Size;
|
|
|
|
|
|
|
|
if (Start >= End)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
symbolTableWorked = true;
|
|
|
|
|
|
|
|
if (!CFG) {
|
2011-09-20 17:53:01 +00:00
|
|
|
// Normal disassembly, print addresses, bytes and mnemonic form.
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex)
|
|
|
|
<< ":\n";
|
2011-09-21 01:13:19 +00:00
|
|
|
DILineInfo lastLine;
|
2011-09-19 17:56:04 +00:00
|
|
|
for (uint64_t Index = Start; Index < End; Index += Size) {
|
|
|
|
MCInst Inst;
|
|
|
|
|
|
|
|
if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
|
|
|
|
DebugOut, nulls())) {
|
|
|
|
outs() << format("%8llx:\t", Sections[SectIdx].Address + Index);
|
|
|
|
DumpBytes(StringRef(Bytes.data() + Index, Size));
|
|
|
|
IP->printInst(&Inst, outs(), "");
|
2011-09-21 01:13:19 +00:00
|
|
|
|
|
|
|
// Print debug info.
|
|
|
|
if (diContext) {
|
|
|
|
DILineInfo dli =
|
|
|
|
diContext->getLineInfoForAddress(Sections[SectIdx].Address +
|
|
|
|
Index);
|
|
|
|
// Print valid line info if it changed.
|
|
|
|
if (dli != lastLine && dli.getLine() != 0)
|
|
|
|
outs() << "\t## " << dli.getFileName() << ':'
|
|
|
|
<< dli.getLine() << ':' << dli.getColumn();
|
|
|
|
lastLine = dli;
|
|
|
|
}
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << "\n";
|
|
|
|
} else {
|
|
|
|
errs() << "llvm-objdump: warning: invalid instruction encoding\n";
|
|
|
|
if (Size == 0)
|
|
|
|
Size = 1; // skip illegible bytes
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
// Create CFG and use it for disassembly.
|
2011-09-20 17:53:01 +00:00
|
|
|
createMCFunctionAndSaveCalls(
|
|
|
|
MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex),
|
|
|
|
DisAsm.get(), memoryObject, Start, End, InstrAnalysis.get(),
|
|
|
|
Start, DebugOut, FunctionMap, Functions);
|
2011-09-19 17:56:04 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (CFG) {
|
|
|
|
if (!symbolTableWorked) {
|
2011-09-20 17:53:01 +00:00
|
|
|
// Reading the symbol table didn't work, create a big __TEXT symbol.
|
|
|
|
createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject,
|
|
|
|
0, Sections[SectIdx].Size,
|
|
|
|
InstrAnalysis.get(),
|
|
|
|
Sections[SectIdx].Offset, DebugOut,
|
|
|
|
FunctionMap, Functions);
|
2011-09-19 17:56:04 +00:00
|
|
|
}
|
|
|
|
for (std::map<uint64_t, MCFunction*>::iterator mi = FunctionMap.begin(),
|
|
|
|
me = FunctionMap.end(); mi != me; ++mi)
|
|
|
|
if (mi->second == 0) {
|
2011-09-20 17:53:01 +00:00
|
|
|
// Create functions for the remaining callees we have gathered,
|
|
|
|
// but we didn't find a name for them.
|
2011-09-19 17:56:04 +00:00
|
|
|
SmallVector<uint64_t, 16> Calls;
|
|
|
|
MCFunction f =
|
|
|
|
MCFunction::createFunctionFromMC("unknown", DisAsm.get(),
|
|
|
|
memoryObject, mi->first,
|
|
|
|
Sections[SectIdx].Size,
|
|
|
|
InstrAnalysis.get(), DebugOut,
|
|
|
|
Calls);
|
|
|
|
Functions.push_back(f);
|
|
|
|
mi->second = &Functions.back();
|
2011-09-20 17:53:01 +00:00
|
|
|
for (unsigned i = 0, e = Calls.size(); i != e; ++i) {
|
|
|
|
std::pair<uint64_t, MCFunction*> p(Calls[i], (MCFunction*)0);
|
|
|
|
if (FunctionMap.insert(p).second)
|
2011-09-19 17:56:04 +00:00
|
|
|
mi = FunctionMap.begin();
|
2011-09-20 17:53:01 +00:00
|
|
|
}
|
2011-09-19 17:56:04 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
DenseSet<uint64_t> PrintedBlocks;
|
|
|
|
for (unsigned ffi = 0, ffe = Functions.size(); ffi != ffe; ++ffi) {
|
|
|
|
MCFunction &f = Functions[ffi];
|
|
|
|
for (MCFunction::iterator fi = f.begin(), fe = f.end(); fi != fe; ++fi){
|
|
|
|
if (!PrintedBlocks.insert(fi->first).second)
|
2011-09-20 17:53:01 +00:00
|
|
|
continue; // We already printed this block.
|
|
|
|
|
|
|
|
// We assume a block has predecessors when it's the first block after
|
|
|
|
// a symbol.
|
2011-09-19 17:56:04 +00:00
|
|
|
bool hasPreds = FunctionMap.find(fi->first) != FunctionMap.end();
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// See if this block has predecessors.
|
2011-09-19 17:56:04 +00:00
|
|
|
// FIXME: Slow.
|
|
|
|
for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe;
|
|
|
|
++pi)
|
|
|
|
if (pi->second.contains(fi->first)) {
|
|
|
|
hasPreds = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
// No predecessors, this is a data block. Print as .byte directives.
|
|
|
|
if (!hasPreds) {
|
2011-09-19 17:56:04 +00:00
|
|
|
uint64_t End = llvm::next(fi) == fe ? Sections[SectIdx].Size :
|
|
|
|
llvm::next(fi)->first;
|
|
|
|
outs() << "# " << End-fi->first << " bytes of data:\n";
|
|
|
|
for (unsigned pos = fi->first; pos != End; ++pos) {
|
|
|
|
outs() << format("%8x:\t", Sections[SectIdx].Address + pos);
|
|
|
|
DumpBytes(StringRef(Bytes.data() + pos, 1));
|
|
|
|
outs() << format("\t.byte 0x%02x\n", (uint8_t)Bytes[pos]);
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
if (fi->second.contains(fi->first)) // Print a header for simple loops
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << "# Loop begin:\n";
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
DILineInfo lastLine;
|
2011-09-20 17:53:01 +00:00
|
|
|
// Walk over the instructions and print them.
|
2011-09-19 17:56:04 +00:00
|
|
|
for (unsigned ii = 0, ie = fi->second.getInsts().size(); ii != ie;
|
|
|
|
++ii) {
|
|
|
|
const MCDecodedInst &Inst = fi->second.getInsts()[ii];
|
2011-09-20 17:53:01 +00:00
|
|
|
|
|
|
|
// If there's a symbol at this address, print its name.
|
2011-09-19 17:56:04 +00:00
|
|
|
if (FunctionMap.find(Sections[SectIdx].Address + Inst.Address) !=
|
|
|
|
FunctionMap.end())
|
|
|
|
outs() << FunctionMap[Sections[SectIdx].Address + Inst.Address]->
|
|
|
|
getName() << ":\n";
|
2011-09-20 17:53:01 +00:00
|
|
|
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << format("%8llx:\t", Sections[SectIdx].Address +
|
|
|
|
Inst.Address);
|
|
|
|
DumpBytes(StringRef(Bytes.data() + Inst.Address, Inst.Size));
|
2011-09-20 17:53:01 +00:00
|
|
|
|
|
|
|
if (fi->second.contains(fi->first)) // Indent simple loops.
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << '\t';
|
2011-09-20 17:53:01 +00:00
|
|
|
|
2011-09-19 17:56:04 +00:00
|
|
|
IP->printInst(&Inst.Inst, outs(), "");
|
2011-09-20 17:53:01 +00:00
|
|
|
|
|
|
|
// Look for relocations inside this instructions, if there is one
|
|
|
|
// print its target and additional information if availbable.
|
2011-09-19 17:56:04 +00:00
|
|
|
for (unsigned j = 0; j != Relocs.size(); ++j)
|
|
|
|
if (Relocs[j].first >= Sections[SectIdx].Address + Inst.Address &&
|
|
|
|
Relocs[j].first < Sections[SectIdx].Address + Inst.Address +
|
|
|
|
Inst.Size) {
|
|
|
|
outs() << "\t# "
|
|
|
|
<< MachOObj->getStringAtIndex(
|
|
|
|
UnsortedSymbols[Relocs[j].second].StringIndex)
|
|
|
|
<< ' ';
|
|
|
|
DumpAddress(UnsortedSymbols[Relocs[j].second].Value, Sections,
|
|
|
|
MachOObj.get(), outs());
|
|
|
|
}
|
2011-09-20 17:53:01 +00:00
|
|
|
|
|
|
|
// If this instructions contains an address, see if we can evaluate
|
|
|
|
// it and print additional information.
|
2011-09-19 17:56:04 +00:00
|
|
|
uint64_t targ = InstrAnalysis->evaluateBranch(Inst.Inst,
|
|
|
|
Inst.Address,
|
|
|
|
Inst.Size);
|
|
|
|
if (targ != -1ULL)
|
|
|
|
DumpAddress(targ, Sections, MachOObj.get(), outs());
|
|
|
|
|
2011-09-21 01:13:19 +00:00
|
|
|
// Print debug info.
|
|
|
|
if (diContext) {
|
|
|
|
DILineInfo dli =
|
|
|
|
diContext->getLineInfoForAddress(Sections[SectIdx].Address +
|
|
|
|
Inst.Address);
|
|
|
|
// Print valid line info if it changed.
|
|
|
|
if (dli != lastLine && dli.getLine() != 0)
|
|
|
|
outs() << "\t## " << dli.getFileName() << ':'
|
|
|
|
<< dli.getLine() << ':' << dli.getColumn();
|
|
|
|
lastLine = dli;
|
|
|
|
}
|
|
|
|
|
2011-09-19 17:56:04 +00:00
|
|
|
outs() << '\n';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-09-20 17:53:01 +00:00
|
|
|
emitDOTFile((f.getName().str() + ".dot").c_str(), f, IP.get());
|
2011-09-19 17:56:04 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|