//===----------------------------------------------------------------------===//
#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"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/Triple.h"
+#include "llvm/DebugInfo/DIContext.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCDisassembler.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCInstrAnalysis.h"
#include "llvm/MC/MCInstrDesc.h"
#include "llvm/MC/MCInstrInfo.h"
+#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/Object/MachO.h"
+#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/GraphWriter.h"
+#include "llvm/Support/MachO.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/TargetSelect.h"
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)"));
+ 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"));
-static const Target *GetTarget(const MachOObject *MachOObj) {
+static const Target *GetTarget(const MachOObjectFile *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;
+ if (TripleName.empty()) {
+ llvm::Triple TT("unknown-unknown-unknown");
+ TT.setArch(Triple::ArchType(MachOObj->getArch()));
+ TripleName = TT.str();
}
- TripleName = TT.str();
-
// Get the target specific parser.
std::string Error;
const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error);
return 0;
}
-struct Section {
- char Name[16];
- uint64_t Address;
- uint64_t Size;
- uint32_t Offset;
- uint32_t NumRelocs;
- uint64_t RelocTableOffset;
+struct SymbolSorter {
+ bool operator()(const SymbolRef &A, const SymbolRef &B) {
+ SymbolRef::Type AType, BType;
+ A.getType(AType);
+ B.getType(BType);
+
+ uint64_t AAddr, BAddr;
+ if (AType != SymbolRef::ST_Function)
+ AAddr = 0;
+ else
+ A.getAddress(AAddr);
+ if (BType != SymbolRef::ST_Function)
+ BAddr = 0;
+ else
+ B.getAddress(BAddr);
+ return AAddr < BAddr;
+ }
};
-struct Symbol {
+// Types for the storted data in code table that is built before disassembly
+// and the predicate function to sort them.
+typedef std::pair<uint64_t, DiceRef> DiceTableEntry;
+typedef std::vector<DiceTableEntry> DiceTable;
+typedef DiceTable::iterator dice_table_iterator;
+
+static bool
+compareDiceTableEntries(const DiceTableEntry i,
+ const DiceTableEntry j) {
+ return i.first == j.first;
+}
+
+static void DumpDataInCode(const char *bytes, uint64_t Size,
+ unsigned short Kind) {
uint64_t Value;
- uint32_t StringIndex;
- uint8_t SectionIndex;
- bool operator<(const Symbol &RHS) const { return Value < RHS.Value; }
-};
-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);
- if (!strcmp(Sections[i].Name, "__cstring"))
- OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"';
- if (!strcmp(Sections[i].Name, "__cfstring"))
- OS << "@\"" << bytes.substr(addr, bytes.find('\0', addr)) << '"';
+ switch (Kind) {
+ case MachO::DICE_KIND_DATA:
+ switch (Size) {
+ case 4:
+ Value = bytes[3] << 24 |
+ bytes[2] << 16 |
+ bytes[1] << 8 |
+ bytes[0];
+ outs() << "\t.long " << Value;
+ break;
+ case 2:
+ Value = bytes[1] << 8 |
+ bytes[0];
+ outs() << "\t.short " << Value;
+ break;
+ case 1:
+ Value = bytes[0];
+ outs() << "\t.byte " << Value;
+ break;
}
+ outs() << "\t@ KIND_DATA\n";
+ break;
+ case MachO::DICE_KIND_JUMP_TABLE8:
+ Value = bytes[0];
+ outs() << "\t.byte " << Value << "\t@ KIND_JUMP_TABLE8";
+ break;
+ case MachO::DICE_KIND_JUMP_TABLE16:
+ Value = bytes[1] << 8 |
+ bytes[0];
+ outs() << "\t.short " << Value << "\t@ KIND_JUMP_TABLE16";
+ break;
+ case MachO::DICE_KIND_JUMP_TABLE32:
+ Value = bytes[3] << 24 |
+ bytes[2] << 16 |
+ bytes[1] << 8 |
+ bytes[0];
+ outs() << "\t.long " << Value << "\t@ KIND_JUMP_TABLE32";
+ break;
+ default:
+ outs() << "\t@ data in code kind = " << Kind << "\n";
+ break;
}
}
-void llvm::DisassembleInputMachO(StringRef Filename) {
- OwningPtr<MemoryBuffer> Buff;
-
- if (error_code ec = MemoryBuffer::getFileOrSTDIN(Filename, Buff)) {
- errs() << "llvm-objdump: " << Filename << ": " << ec.message() << "\n";
- return;
+static void getSectionsAndSymbols(const MachO::mach_header Header,
+ MachOObjectFile *MachOObj,
+ std::vector<SectionRef> &Sections,
+ std::vector<SymbolRef> &Symbols,
+ SmallVectorImpl<uint64_t> &FoundFns,
+ uint64_t &BaseSegmentAddress) {
+ for (const SymbolRef &Symbol : MachOObj->symbols())
+ Symbols.push_back(Symbol);
+
+ for (const SectionRef &Section : MachOObj->sections()) {
+ StringRef SectName;
+ Section.getName(SectName);
+ Sections.push_back(Section);
}
- OwningPtr<MachOObject> MachOObj(MachOObject::LoadFromBuffer(Buff.take()));
+ MachOObjectFile::LoadCommandInfo Command =
+ MachOObj->getFirstLoadCommandInfo();
+ bool BaseSegmentAddressSet = false;
+ for (unsigned i = 0; ; ++i) {
+ if (Command.C.cmd == MachO::LC_FUNCTION_STARTS) {
+ // We found a function starts segment, parse the addresses for later
+ // consumption.
+ MachO::linkedit_data_command LLC =
+ MachOObj->getLinkeditDataLoadCommand(Command);
+
+ MachOObj->ReadULEB128s(LLC.dataoff, FoundFns);
+ }
+ else if (Command.C.cmd == MachO::LC_SEGMENT) {
+ MachO::segment_command SLC =
+ MachOObj->getSegmentLoadCommand(Command);
+ StringRef SegName = SLC.segname;
+ if(!BaseSegmentAddressSet && SegName != "__PAGEZERO") {
+ BaseSegmentAddressSet = true;
+ BaseSegmentAddress = SLC.vmaddr;
+ }
+ }
- const Target *TheTarget = GetTarget(MachOObj.get());
- if (!TheTarget) {
- // GetTarget prints out stuff.
- return;
+ if (i == Header.ncmds - 1)
+ break;
+ else
+ Command = MachOObj->getNextLoadCommandInfo(Command);
}
- const MCInstrInfo *InstrInfo = TheTarget->createMCInstrInfo();
- OwningPtr<MCInstrAnalysis>
- InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo));
+}
- // Set up disassembler.
- OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName));
+static void DisassembleInputMachO2(StringRef Filename,
+ MachOObjectFile *MachOOF);
- if (!AsmInfo) {
- errs() << "error: no assembly info for target " << TripleName << "\n";
+void llvm::DisassembleInputMachO(StringRef Filename) {
+ std::unique_ptr<MemoryBuffer> Buff;
+
+ if (error_code ec = MemoryBuffer::getFileOrSTDIN(Filename, Buff)) {
+ errs() << "llvm-objdump: " << Filename << ": " << ec.message() << "\n";
return;
}
- OwningPtr<const MCSubtargetInfo>
- STI(TheTarget->createMCSubtargetInfo(TripleName, "", ""));
+ std::unique_ptr<MachOObjectFile> MachOOF(static_cast<MachOObjectFile *>(
+ ObjectFile::createMachOObjectFile(Buff.release()).get()));
- if (!STI) {
- errs() << "error: no subtarget info for target " << TripleName << "\n";
- return;
- }
+ DisassembleInputMachO2(Filename, MachOOF.get());
+}
- OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI));
- if (!DisAsm) {
- errs() << "error: no disassembler for target " << TripleName << "\n";
+static void DisassembleInputMachO2(StringRef Filename,
+ MachOObjectFile *MachOOF) {
+ const Target *TheTarget = GetTarget(MachOOF);
+ if (!TheTarget) {
+ // GetTarget prints out stuff.
return;
}
+ std::unique_ptr<const MCInstrInfo> InstrInfo(TheTarget->createMCInstrInfo());
+ std::unique_ptr<MCInstrAnalysis> InstrAnalysis(
+ TheTarget->createMCInstrAnalysis(InstrInfo.get()));
+ // Set up disassembler.
+ std::unique_ptr<const MCRegisterInfo> MRI(
+ TheTarget->createMCRegInfo(TripleName));
+ std::unique_ptr<const MCAsmInfo> AsmInfo(
+ TheTarget->createMCAsmInfo(*MRI, TripleName));
+ std::unique_ptr<const MCSubtargetInfo> STI(
+ TheTarget->createMCSubtargetInfo(TripleName, "", ""));
+ std::unique_ptr<const MCDisassembler> DisAsm(
+ TheTarget->createMCDisassembler(*STI));
int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
- OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
- AsmPrinterVariant, *AsmInfo, *STI));
- if (!IP) {
- errs() << "error: no instruction printer for target " << TripleName << '\n';
+ std::unique_ptr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
+ AsmPrinterVariant, *AsmInfo, *InstrInfo, *MRI, *STI));
+
+ if (!InstrAnalysis || !AsmInfo || !STI || !DisAsm || !IP) {
+ errs() << "error: couldn't initialize disassembler for target "
+ << TripleName << '\n';
return;
}
- outs() << '\n';
- outs() << Filename << ":\n\n";
-
- const macho::Header &Header = MachOObj->getHeader();
-
- const MachOObject::LoadCommandInfo *SymtabLCI = 0;
- for (unsigned i = 0; i != Header.NumLoadCommands; ++i) {
- const MachOObject::LoadCommandInfo &LCI = MachOObj->getLoadCommandInfo(i);
- switch (LCI.Command.Type) {
- case macho::LCT_Symtab:
- SymtabLCI = &LCI;
- break;
- }
- }
+ outs() << '\n' << Filename << ":\n\n";
- // Read and register the symbol table data.
- InMemoryStruct<macho::SymtabLoadCommand> SymtabLC;
- MachOObj->ReadSymtabLoadCommand(*SymtabLCI, SymtabLC);
- MachOObj->RegisterStringTable(*SymtabLC);
+ MachO::mach_header Header = MachOOF->getHeader();
- std::vector<Section> Sections;
- std::vector<Symbol> Symbols;
- std::vector<Symbol> UnsortedSymbols; // FIXME: duplication
+ // FIXME: FoundFns isn't used anymore. Using symbols/LC_FUNCTION_STARTS to
+ // determine function locations will eventually go in MCObjectDisassembler.
+ // FIXME: Using the -cfg command line option, this code used to be able to
+ // annotate relocations with the referenced symbol's name, and if this was
+ // inside a __[cf]string section, the data it points to. This is now replaced
+ // by the upcoming MCSymbolizer, which needs the appropriate setup done above.
+ std::vector<SectionRef> Sections;
+ std::vector<SymbolRef> Symbols;
SmallVector<uint64_t, 8> FoundFns;
+ uint64_t BaseSegmentAddress;
- 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);
-
- for (unsigned SectNum = 0; SectNum != SegmentLC->NumSections; ++SectNum) {
- InMemoryStruct<macho::Section> Sect;
- MachOObj->ReadSection(LCI, SectNum, 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;
- Sections.push_back(S);
-
- for (unsigned i = 0; i != SymtabLC->NumSymbolTableEntries; ++i) {
- InMemoryStruct<macho::SymbolTableEntry> STE;
- MachOObj->ReadSymbolTableEntry(SymtabLC->SymbolTableOffset, i, STE);
-
- Symbol S;
- S.StringIndex = STE->StringIndex;
- S.SectionIndex = STE->SectionIndex;
- S.Value = STE->Value;
- Symbols.push_back(S);
- UnsortedSymbols.push_back(Symbols.back());
- }
- }
- } else if (LCI.Command.Type == macho::LCT_Segment64) {
- InMemoryStruct<macho::Segment64LoadCommand> Segment64LC;
- MachOObj->ReadSegment64LoadCommand(LCI, Segment64LC);
-
- for (unsigned SectNum = 0; SectNum != Segment64LC->NumSections; ++SectNum) {
- InMemoryStruct<macho::Section64> Sect64;
- MachOObj->ReadSection64(LCI, SectNum, Sect64);
-
- Section S;
- memcpy(S.Name, Sect64->Name, 16);
- S.Address = Sect64->Address;
- S.Size = Sect64->Size;
- S.Offset = Sect64->Offset;
- S.NumRelocs = Sect64->NumRelocationTableEntries;
- S.RelocTableOffset = Sect64->RelocationTableOffset;
- Sections.push_back(S);
-
- for (unsigned i = 0; i != SymtabLC->NumSymbolTableEntries; ++i) {
- InMemoryStruct<macho::Symbol64TableEntry> STE;
- MachOObj->ReadSymbol64TableEntry(SymtabLC->SymbolTableOffset, i, STE);
-
- Symbol S;
- S.StringIndex = STE->StringIndex;
- S.SectionIndex = STE->SectionIndex;
- S.Value = STE->Value;
- Symbols.push_back(S);
- UnsortedSymbols.push_back(Symbols.back());
- }
- }
- } else if (LCI.Command.Type == macho::LCT_FunctionStarts) {
- InMemoryStruct<macho::LinkeditDataLoadCommand> LLC;
- MachOObj->ReadLinkeditDataLoadCommand(LCI, LLC);
-
- MachOObj->ReadULEB128s(LLC->DataOffset, FoundFns);
- }
- }
-
- std::map<uint64_t, MCFunction*> FunctionMap;
+ getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns,
+ BaseSegmentAddress);
// Sort the symbols by address, just in case they didn't come in that way.
- array_pod_sort(Symbols.begin(), Symbols.end());
+ std::sort(Symbols.begin(), Symbols.end(), SymbolSorter());
+
+ // Build a data in code table that is sorted on by the address of each entry.
+ uint64_t BaseAddress = 0;
+ if (Header.filetype == MachO::MH_OBJECT)
+ Sections[0].getAddress(BaseAddress);
+ else
+ BaseAddress = BaseSegmentAddress;
+ DiceTable Dices;
+ for (dice_iterator DI = MachOOF->begin_dices(), DE = MachOOF->end_dices();
+ DI != DE; ++DI) {
+ uint32_t Offset;
+ DI->getOffset(Offset);
+ Dices.push_back(std::make_pair(BaseAddress + Offset, *DI));
+ }
+ array_pod_sort(Dices.begin(), Dices.end());
#ifndef NDEBUG
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
raw_ostream &DebugOut = nulls();
#endif
- SmallVector<MCFunction, 16> Functions;
+ std::unique_ptr<DIContext> diContext;
+ ObjectFile *DbgObj = MachOOF;
+ // Try to find debug info and set up the DIContext for it.
+ if (UseDbg) {
+ // A separate DSym file path was specified, parse it as a macho file,
+ // get the sections and supply it to the section name parsing machinery.
+ if (!DSYMFile.empty()) {
+ std::unique_ptr<MemoryBuffer> Buf;
+ if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile, Buf)) {
+ errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n';
+ return;
+ }
+ DbgObj = ObjectFile::createMachOObjectFile(Buf.release()).get();
+ }
+
+ // Setup the DIContext
+ diContext.reset(DIContext::getDWARFContext(DbgObj));
+ }
for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) {
- if (strcmp(Sections[SectIdx].Name, "__text"))
+
+ bool SectIsText = false;
+ Sections[SectIdx].isText(SectIsText);
+ if (SectIsText == false)
continue;
- uint64_t VMAddr = Sections[SectIdx].Address - Sections[SectIdx].Offset;
- for (unsigned i = 0, e = FoundFns.size(); i != e; ++i)
- FunctionMap.insert(std::pair<uint64_t,MCFunction*>(FoundFns[i]+VMAddr,0));
+ StringRef SectName;
+ if (Sections[SectIdx].getName(SectName) ||
+ SectName != "__text")
+ continue; // Skip non-text sections
+
+ DataRefImpl DR = Sections[SectIdx].getRawDataRefImpl();
- StringRef Bytes = MachOObj->getData(Sections[SectIdx].Offset,
- Sections[SectIdx].Size);
+ StringRef SegmentName = MachOOF->getSectionFinalSegmentName(DR);
+ if (SegmentName != "__TEXT")
+ continue;
+
+ StringRef Bytes;
+ Sections[SectIdx].getContents(Bytes);
StringRefMemoryObject memoryObject(Bytes);
bool symbolTableWorked = false;
- 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));
+ // Parse relocations.
+ std::vector<std::pair<uint64_t, SymbolRef>> Relocs;
+ for (const RelocationRef &Reloc : Sections[SectIdx].relocations()) {
+ uint64_t RelocOffset, SectionAddress;
+ Reloc.getOffset(RelocOffset);
+ Sections[SectIdx].getAddress(SectionAddress);
+ RelocOffset -= SectionAddress;
+
+ symbol_iterator RelocSym = Reloc.getSymbol();
+
+ Relocs.push_back(std::make_pair(RelocOffset, *RelocSym));
}
array_pod_sort(Relocs.begin(), Relocs.end());
+ // Disassemble symbol by symbol.
for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) {
- if ((unsigned)Symbols[SymIdx].SectionIndex - 1 != SectIdx)
- continue;
-
- uint64_t Start = Symbols[SymIdx].Value - Sections[SectIdx].Address;
- 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;
+ StringRef SymName;
+ Symbols[SymIdx].getName(SymName);
- if (Start >= End)
+ SymbolRef::Type ST;
+ Symbols[SymIdx].getType(ST);
+ if (ST != SymbolRef::ST_Function)
continue;
- symbolTableWorked = true;
+ // Make sure the symbol is defined in this section.
+ bool containsSym = false;
+ Sections[SectIdx].containsSymbol(Symbols[SymIdx], containsSym);
+ if (!containsSym)
+ continue;
- if (!CFG) {
- outs() << MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex)
- << ":\n";
- 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(), "");
- outs() << "\n";
- } else {
- errs() << "llvm-objdump: warning: invalid instruction encoding\n";
- if (Size == 0)
- Size = 1; // skip illegible bytes
- }
+ // Start at the address of the symbol relative to the section's address.
+ uint64_t SectionAddress = 0;
+ uint64_t Start = 0;
+ Sections[SectIdx].getAddress(SectionAddress);
+ Symbols[SymIdx].getAddress(Start);
+ Start -= SectionAddress;
+
+ // Stop disassembling either at the beginning of the next symbol or at
+ // the end of the section.
+ bool containsNextSym = false;
+ uint64_t NextSym = 0;
+ uint64_t NextSymIdx = SymIdx+1;
+ while (Symbols.size() > NextSymIdx) {
+ SymbolRef::Type NextSymType;
+ Symbols[NextSymIdx].getType(NextSymType);
+ if (NextSymType == SymbolRef::ST_Function) {
+ Sections[SectIdx].containsSymbol(Symbols[NextSymIdx],
+ containsNextSym);
+ Symbols[NextSymIdx].getAddress(NextSym);
+ NextSym -= SectionAddress;
+ break;
}
- } else {
- // Create CFG and use it for disassembly.
- SmallVector<uint64_t, 16> Calls;
- MCFunction f =
- MCFunction::createFunctionFromMC(
- MachOObj->getStringAtIndex(Symbols[SymIdx].StringIndex),
- DisAsm.get(),
- memoryObject, Start, End,
- InstrAnalysis.get(), DebugOut,
- Calls);
-
- Functions.push_back(f);
- FunctionMap[Start] = &Functions.back();
-
- for (unsigned i = 0, e = Calls.size(); i != e; ++i)
- FunctionMap.insert(std::pair<uint64_t, MCFunction*>(Calls[i], 0));
+ ++NextSymIdx;
}
- }
- if (CFG) {
- if (!symbolTableWorked) {
- // Create CFG and use it for disassembly.
- SmallVector<uint64_t, 16> Calls;
- MCFunction f =
- MCFunction::createFunctionFromMC("__TEXT", DisAsm.get(),
- memoryObject, 0, Sections[SectIdx].Size,
- InstrAnalysis.get(), DebugOut,
- Calls);
-
- Functions.push_back(f);
- FunctionMap[Sections[SectIdx].Offset] = &Functions.back();
-
- for (unsigned i = 0, e = Calls.size(); i != e; ++i)
- FunctionMap.insert(std::pair<uint64_t, MCFunction*>(Calls[i], 0));
- }
- for (std::map<uint64_t, MCFunction*>::iterator mi = FunctionMap.begin(),
- me = FunctionMap.end(); mi != me; ++mi)
- if (mi->second == 0) {
- 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();
- for (unsigned i = 0, e = Calls.size(); i != e; ++i)
- if (FunctionMap.insert(std::pair<uint64_t, MCFunction*>(Calls[i],0))
- .second)
- mi = FunctionMap.begin();
- }
-
- DenseSet<uint64_t> PrintedBlocks;
- for (unsigned ffi = 0, ffe = Functions.size(); ffi != ffe; ++ffi) {
- MCFunction &f = Functions[ffi];
- for (MCFunction::iterator fi = f.begin(), fe = f.end(); fi != fe; ++fi){
- if (!PrintedBlocks.insert(fi->first).second)
- continue;
- bool hasPreds = FunctionMap.find(fi->first) != FunctionMap.end();
-
- // Only print blocks that have predecessors.
- // FIXME: Slow.
- for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe;
- ++pi)
- if (pi->second.contains(fi->first)) {
- hasPreds = true;
- break;
- }
-
- // Data block.
- if (!hasPreds && fi != f.begin()) {
- 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;
- }
+ uint64_t SectSize;
+ Sections[SectIdx].getSize(SectSize);
+ uint64_t End = containsNextSym ? NextSym : SectSize;
+ uint64_t Size;
- if (fi->second.contains(fi->first))
- outs() << "# Loop begin:\n";
-
- for (unsigned ii = 0, ie = fi->second.getInsts().size(); ii != ie;
- ++ii) {
- const MCDecodedInst &Inst = fi->second.getInsts()[ii];
- if (FunctionMap.find(Sections[SectIdx].Address + Inst.Address) !=
- FunctionMap.end())
- outs() << FunctionMap[Sections[SectIdx].Address + Inst.Address]->
- getName() << ":\n";
- outs() << format("%8llx:\t", Sections[SectIdx].Address +
- Inst.Address);
- DumpBytes(StringRef(Bytes.data() + Inst.Address, Inst.Size));
- // Simple loops.
- if (fi->second.contains(fi->first))
- outs() << '\t';
- IP->printInst(&Inst.Inst, outs(), "");
- 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());
- }
- uint64_t targ = InstrAnalysis->evaluateBranch(Inst.Inst,
- Inst.Address,
- Inst.Size);
- if (targ != -1ULL)
- DumpAddress(targ, Sections, MachOObj.get(), outs());
-
- outs() << '\n';
- }
- }
+ symbolTableWorked = true;
- // Start a new dot file.
- std::string Error;
- raw_fd_ostream Out((f.getName().str() + ".dot").c_str(), Error);
- if (!Error.empty()) {
- errs() << "llvm-objdump: warning: " << Error << '\n';
+ outs() << SymName << ":\n";
+ DILineInfo lastLine;
+ for (uint64_t Index = Start; Index < End; Index += Size) {
+ MCInst Inst;
+
+ uint64_t SectAddress = 0;
+ Sections[SectIdx].getAddress(SectAddress);
+ outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
+
+ // Check the data in code table here to see if this is data not an
+ // instruction to be disassembled.
+ DiceTable Dice;
+ Dice.push_back(std::make_pair(SectAddress + Index, DiceRef()));
+ dice_table_iterator DTI = std::search(Dices.begin(), Dices.end(),
+ Dice.begin(), Dice.end(),
+ compareDiceTableEntries);
+ if (DTI != Dices.end()){
+ uint16_t Length;
+ DTI->second.getLength(Length);
+ DumpBytes(StringRef(Bytes.data() + Index, Length));
+ uint16_t Kind;
+ DTI->second.getKind(Kind);
+ DumpDataInCode(Bytes.data() + Index, Length, Kind);
continue;
}
- 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()) << '|';
+ if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
+ DebugOut, nulls())) {
+ DumpBytes(StringRef(Bytes.data() + Index, Size));
+ IP->printInst(&Inst, outs(), "");
+
+ // Print debug info.
+ if (diContext) {
+ DILineInfo dli =
+ diContext->getLineInfoForAddress(SectAddress + Index);
+ // Print valid line info if it changed.
+ if (dli != lastLine && dli.getLine() != 0)
+ outs() << "\t## " << dli.getFileName() << ':'
+ << dli.getLine() << ':' << dli.getColumn();
+ lastLine = dli;
}
- Out << "<o>\" shape=\"record\" ];\n";
-
- // Add edges.
- for (MCBasicBlock::succ_iterator si = i->second.succ_begin(),
- se = i->second.succ_end(); si != se; ++si)
- Out << i->first << ":o -> " << *si <<":a\n";
+ outs() << "\n";
+ } else {
+ errs() << "llvm-objdump: warning: invalid instruction encoding\n";
+ if (Size == 0)
+ Size = 1; // skip illegible bytes
+ }
+ }
+ }
+ if (!symbolTableWorked) {
+ // Reading the symbol table didn't work, disassemble the whole section.
+ uint64_t SectAddress;
+ Sections[SectIdx].getAddress(SectAddress);
+ uint64_t SectSize;
+ Sections[SectIdx].getSize(SectSize);
+ uint64_t InstSize;
+ for (uint64_t Index = 0; Index < SectSize; Index += InstSize) {
+ MCInst Inst;
+
+ if (DisAsm->getInstruction(Inst, InstSize, memoryObject, Index,
+ DebugOut, nulls())) {
+ outs() << format("%8" PRIx64 ":\t", SectAddress + Index);
+ DumpBytes(StringRef(Bytes.data() + Index, InstSize));
+ IP->printInst(&Inst, outs(), "");
+ outs() << "\n";
+ } else {
+ errs() << "llvm-objdump: warning: invalid instruction encoding\n";
+ if (InstSize == 0)
+ InstSize = 1; // skip illegible bytes
}
- Out << "}\n";
}
}
}