diff options
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/COFFDump.cpp | 401 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/ELFDump.cpp | 94 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MachODump.cpp | 467 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp | 889 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.h | 41 |
5 files changed, 1892 insertions, 0 deletions
diff --git a/contrib/llvm/tools/llvm-objdump/COFFDump.cpp b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp new file mode 100644 index 0000000..5f0bcbb --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp @@ -0,0 +1,401 @@ +//===-- COFFDump.cpp - COFF-specific dumper ---------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements the COFF-specific dumper for llvm-objdump. +/// It outputs the Win64 EH data structures as plain text. +/// The encoding of the unwind codes is decribed in MSDN: +/// http://msdn.microsoft.com/en-us/library/ck9asaa9.aspx +/// +//===----------------------------------------------------------------------===// + +#include "llvm-objdump.h" +#include "llvm/Object/COFF.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/SourceMgr.h" +#include "llvm/Support/Win64EH.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/system_error.h" +#include <algorithm> +#include <cstring> + +using namespace llvm; +using namespace object; +using namespace llvm::Win64EH; + +// Returns the name of the unwind code. +static StringRef getUnwindCodeTypeName(uint8_t Code) { + switch(Code) { + default: llvm_unreachable("Invalid unwind code"); + case UOP_PushNonVol: return "UOP_PushNonVol"; + case UOP_AllocLarge: return "UOP_AllocLarge"; + case UOP_AllocSmall: return "UOP_AllocSmall"; + case UOP_SetFPReg: return "UOP_SetFPReg"; + case UOP_SaveNonVol: return "UOP_SaveNonVol"; + case UOP_SaveNonVolBig: return "UOP_SaveNonVolBig"; + case UOP_SaveXMM128: return "UOP_SaveXMM128"; + case UOP_SaveXMM128Big: return "UOP_SaveXMM128Big"; + case UOP_PushMachFrame: return "UOP_PushMachFrame"; + } +} + +// Returns the name of a referenced register. +static StringRef getUnwindRegisterName(uint8_t Reg) { + switch(Reg) { + default: llvm_unreachable("Invalid register"); + case 0: return "RAX"; + case 1: return "RCX"; + case 2: return "RDX"; + case 3: return "RBX"; + case 4: return "RSP"; + case 5: return "RBP"; + case 6: return "RSI"; + case 7: return "RDI"; + case 8: return "R8"; + case 9: return "R9"; + case 10: return "R10"; + case 11: return "R11"; + case 12: return "R12"; + case 13: return "R13"; + case 14: return "R14"; + case 15: return "R15"; + } +} + +// Calculates the number of array slots required for the unwind code. +static unsigned getNumUsedSlots(const UnwindCode &UnwindCode) { + switch (UnwindCode.getUnwindOp()) { + default: llvm_unreachable("Invalid unwind code"); + case UOP_PushNonVol: + case UOP_AllocSmall: + case UOP_SetFPReg: + case UOP_PushMachFrame: + return 1; + case UOP_SaveNonVol: + case UOP_SaveXMM128: + return 2; + case UOP_SaveNonVolBig: + case UOP_SaveXMM128Big: + return 3; + case UOP_AllocLarge: + return (UnwindCode.getOpInfo() == 0) ? 2 : 3; + } +} + +// Prints one unwind code. Because an unwind code can occupy up to 3 slots in +// the unwind codes array, this function requires that the correct number of +// slots is provided. +static void printUnwindCode(ArrayRef<UnwindCode> UCs) { + assert(UCs.size() >= getNumUsedSlots(UCs[0])); + outs() << format(" 0x%02x: ", unsigned(UCs[0].u.CodeOffset)) + << getUnwindCodeTypeName(UCs[0].getUnwindOp()); + switch (UCs[0].getUnwindOp()) { + case UOP_PushNonVol: + outs() << " " << getUnwindRegisterName(UCs[0].getOpInfo()); + break; + case UOP_AllocLarge: + if (UCs[0].getOpInfo() == 0) { + outs() << " " << UCs[1].FrameOffset; + } else { + outs() << " " << UCs[1].FrameOffset + + (static_cast<uint32_t>(UCs[2].FrameOffset) << 16); + } + break; + case UOP_AllocSmall: + outs() << " " << ((UCs[0].getOpInfo() + 1) * 8); + break; + case UOP_SetFPReg: + outs() << " "; + break; + case UOP_SaveNonVol: + outs() << " " << getUnwindRegisterName(UCs[0].getOpInfo()) + << format(" [0x%04x]", 8 * UCs[1].FrameOffset); + break; + case UOP_SaveNonVolBig: + outs() << " " << getUnwindRegisterName(UCs[0].getOpInfo()) + << format(" [0x%08x]", UCs[1].FrameOffset + + (static_cast<uint32_t>(UCs[2].FrameOffset) << 16)); + break; + case UOP_SaveXMM128: + outs() << " XMM" << static_cast<uint32_t>(UCs[0].getOpInfo()) + << format(" [0x%04x]", 16 * UCs[1].FrameOffset); + break; + case UOP_SaveXMM128Big: + outs() << " XMM" << UCs[0].getOpInfo() + << format(" [0x%08x]", UCs[1].FrameOffset + + (static_cast<uint32_t>(UCs[2].FrameOffset) << 16)); + break; + case UOP_PushMachFrame: + outs() << " " << (UCs[0].getOpInfo() ? "w/o" : "w") + << " error code"; + break; + } + outs() << "\n"; +} + +static void printAllUnwindCodes(ArrayRef<UnwindCode> UCs) { + for (const UnwindCode *I = UCs.begin(), *E = UCs.end(); I < E; ) { + unsigned UsedSlots = getNumUsedSlots(*I); + if (UsedSlots > UCs.size()) { + outs() << "Unwind data corrupted: Encountered unwind op " + << getUnwindCodeTypeName((*I).getUnwindOp()) + << " which requires " << UsedSlots + << " slots, but only " << UCs.size() + << " remaining in buffer"; + return ; + } + printUnwindCode(ArrayRef<UnwindCode>(I, E)); + I += UsedSlots; + } +} + +// Given a symbol sym this functions returns the address and section of it. +static error_code resolveSectionAndAddress(const COFFObjectFile *Obj, + const SymbolRef &Sym, + const coff_section *&ResolvedSection, + uint64_t &ResolvedAddr) { + if (error_code ec = Sym.getAddress(ResolvedAddr)) return ec; + section_iterator iter(Obj->begin_sections()); + if (error_code ec = Sym.getSection(iter)) return ec; + ResolvedSection = Obj->getCOFFSection(iter); + return object_error::success; +} + +// Given a vector of relocations for a section and an offset into this section +// the function returns the symbol used for the relocation at the offset. +static error_code resolveSymbol(const std::vector<RelocationRef> &Rels, + uint64_t Offset, SymbolRef &Sym) { + for (std::vector<RelocationRef>::const_iterator I = Rels.begin(), + E = Rels.end(); + I != E; ++I) { + uint64_t Ofs; + if (error_code ec = I->getOffset(Ofs)) return ec; + if (Ofs == Offset) { + Sym = *I->getSymbol(); + break; + } + } + return object_error::success; +} + +// Given a vector of relocations for a section and an offset into this section +// the function resolves the symbol used for the relocation at the offset and +// returns the section content and the address inside the content pointed to +// by the symbol. +static error_code getSectionContents(const COFFObjectFile *Obj, + const std::vector<RelocationRef> &Rels, + uint64_t Offset, + ArrayRef<uint8_t> &Contents, + uint64_t &Addr) { + SymbolRef Sym; + if (error_code ec = resolveSymbol(Rels, Offset, Sym)) return ec; + const coff_section *Section; + if (error_code ec = resolveSectionAndAddress(Obj, Sym, Section, Addr)) + return ec; + if (error_code ec = Obj->getSectionContents(Section, Contents)) return ec; + return object_error::success; +} + +// Given a vector of relocations for a section and an offset into this section +// the function returns the name of the symbol used for the relocation at the +// offset. +static error_code resolveSymbolName(const std::vector<RelocationRef> &Rels, + uint64_t Offset, StringRef &Name) { + SymbolRef Sym; + if (error_code ec = resolveSymbol(Rels, Offset, Sym)) return ec; + if (error_code ec = Sym.getName(Name)) return ec; + return object_error::success; +} + +static void printCOFFSymbolAddress(llvm::raw_ostream &Out, + const std::vector<RelocationRef> &Rels, + uint64_t Offset, uint32_t Disp) { + StringRef Sym; + if (error_code ec = resolveSymbolName(Rels, Offset, Sym)) { + error(ec); + return ; + } + Out << Sym; + if (Disp > 0) + Out << format(" + 0x%04x", Disp); +} + +// Prints import tables. The import table is a table containing the list of +// DLL name and symbol names which will be linked by the loader. +static void printImportTables(const COFFObjectFile *Obj) { + outs() << "The Import Tables:\n"; + error_code ec; + for (import_directory_iterator i = Obj->import_directory_begin(), + e = Obj->import_directory_end(); + i != e; i = i.increment(ec)) { + if (ec) + return; + + const import_directory_table_entry *Dir; + StringRef Name; + if (i->getImportTableEntry(Dir)) return; + if (i->getName(Name)) return; + + outs() << format(" lookup %08x time %08x fwd %08x name %08x addr %08x\n\n", + static_cast<uint32_t>(Dir->ImportLookupTableRVA), + static_cast<uint32_t>(Dir->TimeDateStamp), + static_cast<uint32_t>(Dir->ForwarderChain), + static_cast<uint32_t>(Dir->NameRVA), + static_cast<uint32_t>(Dir->ImportAddressTableRVA)); + outs() << " DLL Name: " << Name << "\n"; + outs() << " Hint/Ord Name\n"; + const import_lookup_table_entry32 *entry; + if (i->getImportLookupEntry(entry)) + return; + for (; entry->data; ++entry) { + if (entry->isOrdinal()) { + outs() << format(" % 6d\n", entry->getOrdinal()); + continue; + } + uint16_t Hint; + StringRef Name; + if (Obj->getHintName(entry->getHintNameRVA(), Hint, Name)) + return; + outs() << format(" % 6d ", Hint) << Name << "\n"; + } + outs() << "\n"; + } +} + +void llvm::printCOFFUnwindInfo(const COFFObjectFile *Obj) { + const coff_file_header *Header; + if (error(Obj->getCOFFHeader(Header))) return; + + if (Header->Machine != COFF::IMAGE_FILE_MACHINE_AMD64) { + errs() << "Unsupported image machine type " + "(currently only AMD64 is supported).\n"; + return; + } + + const coff_section *Pdata = 0; + + error_code ec; + for (section_iterator SI = Obj->begin_sections(), + SE = Obj->end_sections(); + SI != SE; SI.increment(ec)) { + if (error(ec)) return; + + StringRef Name; + if (error(SI->getName(Name))) continue; + + if (Name != ".pdata") continue; + + Pdata = Obj->getCOFFSection(SI); + std::vector<RelocationRef> Rels; + for (relocation_iterator RI = SI->begin_relocations(), + RE = SI->end_relocations(); + RI != RE; RI.increment(ec)) { + if (error(ec)) break; + Rels.push_back(*RI); + } + + // Sort relocations by address. + std::sort(Rels.begin(), Rels.end(), RelocAddressLess); + + ArrayRef<uint8_t> Contents; + if (error(Obj->getSectionContents(Pdata, Contents))) continue; + if (Contents.empty()) continue; + + ArrayRef<RuntimeFunction> RFs( + reinterpret_cast<const RuntimeFunction *>(Contents.data()), + Contents.size() / sizeof(RuntimeFunction)); + for (const RuntimeFunction *I = RFs.begin(), *E = RFs.end(); I < E; ++I) { + const uint64_t SectionOffset = std::distance(RFs.begin(), I) + * sizeof(RuntimeFunction); + + outs() << "Function Table:\n"; + + outs() << " Start Address: "; + printCOFFSymbolAddress(outs(), Rels, SectionOffset + + /*offsetof(RuntimeFunction, StartAddress)*/ 0, + I->StartAddress); + outs() << "\n"; + + outs() << " End Address: "; + printCOFFSymbolAddress(outs(), Rels, SectionOffset + + /*offsetof(RuntimeFunction, EndAddress)*/ 4, + I->EndAddress); + outs() << "\n"; + + outs() << " Unwind Info Address: "; + printCOFFSymbolAddress(outs(), Rels, SectionOffset + + /*offsetof(RuntimeFunction, UnwindInfoOffset)*/ 8, + I->UnwindInfoOffset); + outs() << "\n"; + + ArrayRef<uint8_t> XContents; + uint64_t UnwindInfoOffset = 0; + if (error(getSectionContents(Obj, Rels, SectionOffset + + /*offsetof(RuntimeFunction, UnwindInfoOffset)*/ 8, + XContents, UnwindInfoOffset))) continue; + if (XContents.empty()) continue; + + UnwindInfoOffset += I->UnwindInfoOffset; + if (UnwindInfoOffset > XContents.size()) continue; + + const Win64EH::UnwindInfo *UI = + reinterpret_cast<const Win64EH::UnwindInfo *> + (XContents.data() + UnwindInfoOffset); + + // The casts to int are required in order to output the value as number. + // Without the casts the value would be interpreted as char data (which + // results in garbage output). + outs() << " Version: " << static_cast<int>(UI->getVersion()) << "\n"; + outs() << " Flags: " << static_cast<int>(UI->getFlags()); + if (UI->getFlags()) { + if (UI->getFlags() & UNW_ExceptionHandler) + outs() << " UNW_ExceptionHandler"; + if (UI->getFlags() & UNW_TerminateHandler) + outs() << " UNW_TerminateHandler"; + if (UI->getFlags() & UNW_ChainInfo) + outs() << " UNW_ChainInfo"; + } + outs() << "\n"; + outs() << " Size of prolog: " + << static_cast<int>(UI->PrologSize) << "\n"; + outs() << " Number of Codes: " + << static_cast<int>(UI->NumCodes) << "\n"; + // Maybe this should move to output of UOP_SetFPReg? + if (UI->getFrameRegister()) { + outs() << " Frame register: " + << getUnwindRegisterName(UI->getFrameRegister()) + << "\n"; + outs() << " Frame offset: " + << 16 * UI->getFrameOffset() + << "\n"; + } else { + outs() << " No frame pointer used\n"; + } + if (UI->getFlags() & (UNW_ExceptionHandler | UNW_TerminateHandler)) { + // FIXME: Output exception handler data + } else if (UI->getFlags() & UNW_ChainInfo) { + // FIXME: Output chained unwind info + } + + if (UI->NumCodes) + outs() << " Unwind Codes:\n"; + + printAllUnwindCodes(ArrayRef<UnwindCode>(&UI->UnwindCodes[0], + UI->NumCodes)); + + outs() << "\n\n"; + outs().flush(); + } + } +} + +void llvm::printCOFFFileHeader(const object::ObjectFile *Obj) { + printImportTables(dyn_cast<const COFFObjectFile>(Obj)); +} diff --git a/contrib/llvm/tools/llvm-objdump/ELFDump.cpp b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp new file mode 100644 index 0000000..9c091a4 --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp @@ -0,0 +1,94 @@ +//===-- ELFDump.cpp - ELF-specific dumper -----------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements the ELF-specific dumper for llvm-objdump. +/// +//===----------------------------------------------------------------------===// + +#include "llvm-objdump.h" +#include "llvm/Object/ELFObjectFile.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/MathExtras.h" +#include "llvm/Support/raw_ostream.h" + +using namespace llvm; +using namespace llvm::object; + +template <class ELFT> void printProgramHeaders(const ELFFile<ELFT> *o) { + typedef ELFFile<ELFT> ELFO; + outs() << "Program Header:\n"; + for (typename ELFO::Elf_Phdr_Iter pi = o->begin_program_headers(), + pe = o->end_program_headers(); + pi != pe; ++pi) { + switch (pi->p_type) { + case ELF::PT_LOAD: + outs() << " LOAD "; + break; + case ELF::PT_GNU_STACK: + outs() << " STACK "; + break; + case ELF::PT_GNU_EH_FRAME: + outs() << "EH_FRAME "; + break; + case ELF::PT_INTERP: + outs() << " INTERP "; + break; + case ELF::PT_DYNAMIC: + outs() << " DYNAMIC "; + break; + case ELF::PT_PHDR: + outs() << " PHDR "; + break; + case ELF::PT_TLS: + outs() << " TLS "; + break; + default: + outs() << " UNKNOWN "; + } + + const char *Fmt = ELFT::Is64Bits ? "0x%016" PRIx64 " " : "0x%08" PRIx64 " "; + + outs() << "off " + << format(Fmt, (uint64_t)pi->p_offset) + << "vaddr " + << format(Fmt, (uint64_t)pi->p_vaddr) + << "paddr " + << format(Fmt, (uint64_t)pi->p_paddr) + << format("align 2**%u\n", countTrailingZeros<uint64_t>(pi->p_align)) + << " filesz " + << format(Fmt, (uint64_t)pi->p_filesz) + << "memsz " + << format(Fmt, (uint64_t)pi->p_memsz) + << "flags " + << ((pi->p_flags & ELF::PF_R) ? "r" : "-") + << ((pi->p_flags & ELF::PF_W) ? "w" : "-") + << ((pi->p_flags & ELF::PF_X) ? "x" : "-") + << "\n"; + } + outs() << "\n"; +} + +void llvm::printELFFileHeader(const object::ObjectFile *Obj) { + // Little-endian 32-bit + if (const ELF32LEObjectFile *ELFObj = dyn_cast<ELF32LEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); + + // Big-endian 32-bit + if (const ELF32BEObjectFile *ELFObj = dyn_cast<ELF32BEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); + + // Little-endian 64-bit + if (const ELF64LEObjectFile *ELFObj = dyn_cast<ELF64LEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); + + // Big-endian 64-bit + if (const ELF64BEObjectFile *ELFObj = dyn_cast<ELF64BEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); +} diff --git a/contrib/llvm/tools/llvm-objdump/MachODump.cpp b/contrib/llvm/tools/llvm-objdump/MachODump.cpp new file mode 100644 index 0000000..86923fd --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp @@ -0,0 +1,467 @@ +//===-- 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 "llvm/ADT/OwningPtr.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/Triple.h" +#include "llvm/DebugInfo/DIContext.h" +#include "llvm/MC/MCAsmInfo.h" +#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/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" +#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> + 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 MachOObjectFile *MachOObj) { + // Figure out the target triple. + if (TripleName.empty()) { + llvm::Triple TT("unknown-unknown-unknown"); + TT.setArch(Triple::ArchType(MachOObj->getArch())); + 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 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; + } +}; + +// 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; + + 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; + } +} + +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) { + error_code ec; + for (symbol_iterator SI = MachOObj->begin_symbols(), + SE = MachOObj->end_symbols(); SI != SE; SI.increment(ec)) + Symbols.push_back(*SI); + + for (section_iterator SI = MachOObj->begin_sections(), + SE = MachOObj->end_sections(); SI != SE; SI.increment(ec)) { + SectionRef SR = *SI; + StringRef SectName; + SR.getName(SectName); + Sections.push_back(*SI); + } + + 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; + } + } + + if (i == Header.ncmds - 1) + break; + else + Command = MachOObj->getNextLoadCommandInfo(Command); + } +} + +static void DisassembleInputMachO2(StringRef Filename, + MachOObjectFile *MachOOF); + +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<MachOObjectFile> MachOOF(static_cast<MachOObjectFile*>( + ObjectFile::createMachOObjectFile(Buff.take()))); + + DisassembleInputMachO2(Filename, MachOOF.get()); +} + +static void DisassembleInputMachO2(StringRef Filename, + MachOObjectFile *MachOOF) { + const Target *TheTarget = GetTarget(MachOOF); + if (!TheTarget) { + // GetTarget prints out stuff. + return; + } + OwningPtr<const MCInstrInfo> InstrInfo(TheTarget->createMCInstrInfo()); + OwningPtr<MCInstrAnalysis> + InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo.get())); + + // Set up disassembler. + OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); + OwningPtr<const MCAsmInfo> AsmInfo( + TheTarget->createMCAsmInfo(*MRI, TripleName)); + OwningPtr<const MCSubtargetInfo> + STI(TheTarget->createMCSubtargetInfo(TripleName, "", "")); + OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI)); + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + OwningPtr<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' << Filename << ":\n\n"; + + MachO::mach_header Header = MachOOF->getHeader(); + + // FIXME: FoundFns isn't used anymore. Using symbols/LC_FUNCTION_STARTS to + // determine function locations will eventually go in MCObjectDisassembler. + // FIXME: Using the -cfg command line option, this code used to be able to + // annotate relocations with the referenced symbol's name, and if this was + // inside a __[cf]string section, the data it points to. This is now replaced + // by the upcoming MCSymbolizer, which needs the appropriate setup done above. + std::vector<SectionRef> Sections; + std::vector<SymbolRef> Symbols; + SmallVector<uint64_t, 8> FoundFns; + uint64_t BaseSegmentAddress; + + getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns, + BaseSegmentAddress); + + // Sort the symbols by address, just in case they didn't come in that way. + std::sort(Symbols.begin(), Symbols.end(), SymbolSorter()); + + // Build a data in code table that is sorted on by the address of each entry. + uint64_t BaseAddress = 0; + if (Header.filetype == MachO::MH_OBJECT) + Sections[0].getAddress(BaseAddress); + else + BaseAddress = BaseSegmentAddress; + DiceTable Dices; + error_code ec; + for (dice_iterator DI = MachOOF->begin_dices(), DE = MachOOF->end_dices(); + DI != DE; DI.increment(ec)){ + uint32_t Offset; + DI->getOffset(Offset); + Dices.push_back(std::make_pair(BaseAddress + Offset, *DI)); + } + array_pod_sort(Dices.begin(), Dices.end()); + +#ifndef NDEBUG + raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); +#else + raw_ostream &DebugOut = nulls(); +#endif + + OwningPtr<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()) { + OwningPtr<MemoryBuffer> Buf; + if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile, Buf)) { + errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n'; + return; + } + DbgObj = ObjectFile::createMachOObjectFile(Buf.take()); + } + + // Setup the DIContext + diContext.reset(DIContext::getDWARFContext(DbgObj)); + } + + for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) { + + bool SectIsText = false; + Sections[SectIdx].isText(SectIsText); + if (SectIsText == false) + continue; + + StringRef SectName; + if (Sections[SectIdx].getName(SectName) || + SectName != "__text") + continue; // Skip non-text sections + + DataRefImpl DR = Sections[SectIdx].getRawDataRefImpl(); + + StringRef SegmentName = MachOOF->getSectionFinalSegmentName(DR); + if (SegmentName != "__TEXT") + continue; + + StringRef Bytes; + Sections[SectIdx].getContents(Bytes); + StringRefMemoryObject memoryObject(Bytes); + bool symbolTableWorked = false; + + // Parse relocations. + std::vector<std::pair<uint64_t, SymbolRef> > Relocs; + error_code ec; + for (relocation_iterator RI = Sections[SectIdx].begin_relocations(), + RE = Sections[SectIdx].end_relocations(); RI != RE; RI.increment(ec)) { + uint64_t RelocOffset, SectionAddress; + RI->getOffset(RelocOffset); + Sections[SectIdx].getAddress(SectionAddress); + RelocOffset -= SectionAddress; + + symbol_iterator RelocSym = RI->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++) { + StringRef SymName; + Symbols[SymIdx].getName(SymName); + + SymbolRef::Type ST; + Symbols[SymIdx].getType(ST); + if (ST != SymbolRef::ST_Function) + continue; + + // Make sure the symbol is defined in this section. + bool containsSym = false; + Sections[SectIdx].containsSymbol(Symbols[SymIdx], containsSym); + if (!containsSym) + continue; + + // 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; + } + ++NextSymIdx; + } + + uint64_t SectSize; + Sections[SectIdx].getSize(SectSize); + uint64_t End = containsNextSym ? NextSym : SectSize; + uint64_t Size; + + symbolTableWorked = true; + + outs() << SymName << ":\n"; + DILineInfo lastLine; + for (uint64_t Index = Start; Index < End; Index += Size) { + MCInst Inst; + + uint64_t SectAddress = 0; + Sections[SectIdx].getAddress(SectAddress); + outs() << format("%8" PRIx64 ":\t", SectAddress + Index); + + // Check the data in code table here to see if this is data not an + // instruction to be disassembled. + DiceTable Dice; + Dice.push_back(std::make_pair(SectAddress + Index, DiceRef())); + dice_table_iterator DTI = std::search(Dices.begin(), Dices.end(), + Dice.begin(), Dice.end(), + compareDiceTableEntries); + if (DTI != Dices.end()){ + uint16_t Length; + DTI->second.getLength(Length); + DumpBytes(StringRef(Bytes.data() + Index, Length)); + uint16_t Kind; + DTI->second.getKind(Kind); + DumpDataInCode(Bytes.data() + Index, Length, Kind); + continue; + } + + if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, + DebugOut, nulls())) { + DumpBytes(StringRef(Bytes.data() + Index, Size)); + IP->printInst(&Inst, outs(), ""); + + // Print debug info. + if (diContext) { + DILineInfo dli = + diContext->getLineInfoForAddress(SectAddress + Index); + // Print valid line info if it changed. + if (dli != lastLine && dli.getLine() != 0) + outs() << "\t## " << dli.getFileName() << ':' + << dli.getLine() << ':' << dli.getColumn(); + lastLine = dli; + } + outs() << "\n"; + } else { + errs() << "llvm-objdump: warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes + } + } + } + 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 + } + } + } + } +} diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp new file mode 100644 index 0000000..9bc092e --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -0,0 +1,889 @@ +//===-- llvm-objdump.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 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/OwningPtr.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/Triple.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCAtom.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCFunction.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCModule.h" +#include "llvm/MC/MCModuleYAML.h" +#include "llvm/MC/MCObjectDisassembler.h" +#include "llvm/MC/MCObjectFileInfo.h" +#include "llvm/MC/MCObjectSymbolizer.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCRelocationInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Object/Archive.h" +#include "llvm/Object/COFF.h" +#include "llvm/Object/MachO.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/GraphWriter.h" +#include "llvm/Support/Host.h" +#include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/MemoryObject.h" +#include "llvm/Support/PrettyStackTrace.h" +#include "llvm/Support/Signals.h" +#include "llvm/Support/SourceMgr.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 <cctype> +#include <cstring> + +using namespace llvm; +using namespace object; + +static cl::list<std::string> +InputFilenames(cl::Positional, cl::desc("<input object files>"),cl::ZeroOrMore); + +static cl::opt<bool> +Disassemble("disassemble", + cl::desc("Display assembler mnemonics for the machine instructions")); +static cl::alias +Disassembled("d", cl::desc("Alias for --disassemble"), + cl::aliasopt(Disassemble)); + +static cl::opt<bool> +Relocations("r", cl::desc("Display the relocation entries in the file")); + +static cl::opt<bool> +SectionContents("s", cl::desc("Display the content of each section")); + +static cl::opt<bool> +SymbolTable("t", cl::desc("Display the symbol table")); + +static cl::opt<bool> +MachOOpt("macho", cl::desc("Use MachO specific object file parser")); +static cl::alias +MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachOOpt)); + +cl::opt<std::string> +llvm::TripleName("triple", cl::desc("Target triple to disassemble for, " + "see -version for available targets")); + +cl::opt<std::string> +llvm::ArchName("arch", cl::desc("Target arch to disassemble for, " + "see -version for available targets")); + +static cl::opt<bool> +SectionHeaders("section-headers", cl::desc("Display summaries of the headers " + "for each section.")); +static cl::alias +SectionHeadersShort("headers", cl::desc("Alias for --section-headers"), + cl::aliasopt(SectionHeaders)); +static cl::alias +SectionHeadersShorter("h", cl::desc("Alias for --section-headers"), + cl::aliasopt(SectionHeaders)); + +static cl::list<std::string> +MAttrs("mattr", + cl::CommaSeparated, + cl::desc("Target specific attributes"), + cl::value_desc("a1,+a2,-a3,...")); + +static cl::opt<bool> +NoShowRawInsn("no-show-raw-insn", cl::desc("When disassembling instructions, " + "do not print the instruction bytes.")); + +static cl::opt<bool> +UnwindInfo("unwind-info", cl::desc("Display unwind information")); + +static cl::alias +UnwindInfoShort("u", cl::desc("Alias for --unwind-info"), + cl::aliasopt(UnwindInfo)); + +static cl::opt<bool> +PrivateHeaders("private-headers", + cl::desc("Display format specific file headers")); + +static cl::alias +PrivateHeadersShort("p", cl::desc("Alias for --private-headers"), + cl::aliasopt(PrivateHeaders)); + +static cl::opt<bool> +Symbolize("symbolize", cl::desc("When disassembling instructions, " + "try to symbolize operands.")); + +static cl::opt<bool> +CFG("cfg", cl::desc("Create a CFG for every function found in the object" + " and write it to a graphviz file")); + +// FIXME: Does it make sense to have a dedicated tool for yaml cfg output? +static cl::opt<std::string> +YAMLCFG("yaml-cfg", + cl::desc("Create a CFG and write it as a YAML MCModule."), + cl::value_desc("yaml output file")); + +static StringRef ToolName; + +bool llvm::error(error_code ec) { + if (!ec) return false; + + outs() << ToolName << ": error reading file: " << ec.message() << ".\n"; + outs().flush(); + return true; +} + +static const Target *getTarget(const ObjectFile *Obj = NULL) { + // Figure out the target triple. + llvm::Triple TheTriple("unknown-unknown-unknown"); + if (TripleName.empty()) { + if (Obj) { + TheTriple.setArch(Triple::ArchType(Obj->getArch())); + // TheTriple defaults to ELF, and COFF doesn't have an environment: + // the best we can do here is indicate that it is mach-o. + if (Obj->isMachO()) + TheTriple.setEnvironment(Triple::MachO); + } + } else + TheTriple.setTriple(Triple::normalize(TripleName)); + + // Get the target specific parser. + std::string Error; + const Target *TheTarget = TargetRegistry::lookupTarget(ArchName, TheTriple, + Error); + if (!TheTarget) { + errs() << ToolName << ": " << Error; + return 0; + } + + // Update the triple name and return the found target. + TripleName = TheTriple.getTriple(); + return TheTarget; +} + +// Write a graphviz file for the CFG inside an MCFunction. +// FIXME: Use GraphWriter +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::const_iterator i = f.begin(), e = f.end(); i != e; ++i) { + // Only print blocks that have predecessors. + bool hasPreds = (*i)->pred_begin() != (*i)->pred_end(); + + if (!hasPreds && i != f.begin()) + continue; + + Out << '"' << (*i)->getInsts()->getBeginAddr() << "\" [ label=\"<a>"; + // Print instructions. + for (unsigned ii = 0, ie = (*i)->getInsts()->size(); ii != ie; + ++ii) { + if (ii != 0) // Not the first line, start a new row. + Out << '|'; + if (ii + 1 == ie) // Last line, add an end id. + Out << "<o>"; + + // Escape special chars and print the instruction in mnemonic form. + std::string Str; + raw_string_ostream OS(Str); + IP->printInst(&(*i)->getInsts()->at(ii).Inst, OS, ""); + Out << DOT::EscapeString(OS.str()); + } + Out << "\" shape=\"record\" ];\n"; + + // Add edges. + for (MCBasicBlock::succ_const_iterator si = (*i)->succ_begin(), + se = (*i)->succ_end(); si != se; ++si) + Out << (*i)->getInsts()->getBeginAddr() << ":o -> " + << (*si)->getInsts()->getBeginAddr() << ":a\n"; + } + Out << "}\n"; +} + +void llvm::DumpBytes(StringRef bytes) { + static const char hex_rep[] = "0123456789abcdef"; + // FIXME: The real way to do this is to figure out the longest instruction + // and align to that size before printing. I'll fix this when I get + // around to outputting relocations. + // 15 is the longest x86 instruction + // 3 is for the hex rep of a byte + a space. + // 1 is for the null terminator. + enum { OutputSize = (15 * 3) + 1 }; + char output[OutputSize]; + + assert(bytes.size() <= 15 + && "DumpBytes only supports instructions of up to 15 bytes"); + memset(output, ' ', sizeof(output)); + unsigned index = 0; + for (StringRef::iterator i = bytes.begin(), + e = bytes.end(); i != e; ++i) { + output[index] = hex_rep[(*i & 0xF0) >> 4]; + output[index + 1] = hex_rep[*i & 0xF]; + index += 3; + } + + output[sizeof(output) - 1] = 0; + outs() << output; +} + +bool llvm::RelocAddressLess(RelocationRef a, RelocationRef b) { + uint64_t a_addr, b_addr; + if (error(a.getOffset(a_addr))) return false; + if (error(b.getOffset(b_addr))) return false; + return a_addr < b_addr; +} + +static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { + const Target *TheTarget = getTarget(Obj); + // getTarget() will have already issued a diagnostic if necessary, so + // just bail here if it failed. + if (!TheTarget) + return; + + // Package up features to be passed to target/subtarget + std::string FeaturesStr; + if (MAttrs.size()) { + SubtargetFeatures Features; + for (unsigned i = 0; i != MAttrs.size(); ++i) + Features.AddFeature(MAttrs[i]); + FeaturesStr = Features.getString(); + } + + OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); + if (!MRI) { + errs() << "error: no register info for target " << TripleName << "\n"; + return; + } + + // Set up disassembler. + OwningPtr<const MCAsmInfo> AsmInfo( + TheTarget->createMCAsmInfo(*MRI, TripleName)); + if (!AsmInfo) { + errs() << "error: no assembly info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCSubtargetInfo> STI( + TheTarget->createMCSubtargetInfo(TripleName, "", FeaturesStr)); + if (!STI) { + errs() << "error: no subtarget info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo()); + if (!MII) { + errs() << "error: no instruction info for target " << TripleName << "\n"; + return; + } + + OwningPtr<MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI)); + if (!DisAsm) { + errs() << "error: no disassembler for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCObjectFileInfo> MOFI; + OwningPtr<MCContext> Ctx; + + if (Symbolize) { + MOFI.reset(new MCObjectFileInfo); + Ctx.reset(new MCContext(AsmInfo.get(), MRI.get(), MOFI.get())); + OwningPtr<MCRelocationInfo> RelInfo( + TheTarget->createMCRelocationInfo(TripleName, *Ctx.get())); + if (RelInfo) { + OwningPtr<MCSymbolizer> Symzer( + MCObjectSymbolizer::createObjectSymbolizer(*Ctx.get(), RelInfo, Obj)); + if (Symzer) + DisAsm->setSymbolizer(Symzer); + } + } + + OwningPtr<const MCInstrAnalysis> + MIA(TheTarget->createMCInstrAnalysis(MII.get())); + + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( + AsmPrinterVariant, *AsmInfo, *MII, *MRI, *STI)); + if (!IP) { + errs() << "error: no instruction printer for target " << TripleName + << '\n'; + return; + } + + if (CFG || !YAMLCFG.empty()) { + OwningPtr<MCObjectDisassembler> OD( + new MCObjectDisassembler(*Obj, *DisAsm, *MIA)); + OwningPtr<MCModule> Mod(OD->buildModule(/* withCFG */ true)); + for (MCModule::const_atom_iterator AI = Mod->atom_begin(), + AE = Mod->atom_end(); + AI != AE; ++AI) { + outs() << "Atom " << (*AI)->getName() << ": \n"; + if (const MCTextAtom *TA = dyn_cast<MCTextAtom>(*AI)) { + for (MCTextAtom::const_iterator II = TA->begin(), IE = TA->end(); + II != IE; + ++II) { + IP->printInst(&II->Inst, outs(), ""); + outs() << "\n"; + } + } + } + if (CFG) { + for (MCModule::const_func_iterator FI = Mod->func_begin(), + FE = Mod->func_end(); + FI != FE; ++FI) { + static int filenum = 0; + emitDOTFile((Twine((*FI)->getName()) + "_" + + utostr(filenum) + ".dot").str().c_str(), + **FI, IP.get()); + ++filenum; + } + } + if (!YAMLCFG.empty()) { + std::string Error; + raw_fd_ostream YAMLOut(YAMLCFG.c_str(), Error); + if (!Error.empty()) { + errs() << ToolName << ": warning: " << Error << '\n'; + return; + } + mcmodule2yaml(YAMLOut, *Mod, *MII, *MRI); + } + } + + + error_code ec; + for (section_iterator i = Obj->begin_sections(), + e = Obj->end_sections(); + i != e; i.increment(ec)) { + if (error(ec)) break; + bool text; + if (error(i->isText(text))) break; + if (!text) continue; + + uint64_t SectionAddr; + if (error(i->getAddress(SectionAddr))) break; + + // Make a list of all the symbols in this section. + std::vector<std::pair<uint64_t, StringRef> > Symbols; + for (symbol_iterator si = Obj->begin_symbols(), + se = Obj->end_symbols(); + si != se; si.increment(ec)) { + bool contains; + if (!error(i->containsSymbol(*si, contains)) && contains) { + uint64_t Address; + if (error(si->getAddress(Address))) break; + if (Address == UnknownAddressOrSize) continue; + Address -= SectionAddr; + + StringRef Name; + if (error(si->getName(Name))) break; + Symbols.push_back(std::make_pair(Address, Name)); + } + } + + // Sort the symbols by address, just in case they didn't come in that way. + array_pod_sort(Symbols.begin(), Symbols.end()); + + // Make a list of all the relocations for this section. + std::vector<RelocationRef> Rels; + if (InlineRelocs) { + for (relocation_iterator ri = i->begin_relocations(), + re = i->end_relocations(); + ri != re; ri.increment(ec)) { + if (error(ec)) break; + Rels.push_back(*ri); + } + } + + // Sort relocations by address. + std::sort(Rels.begin(), Rels.end(), RelocAddressLess); + + StringRef SegmentName = ""; + if (const MachOObjectFile *MachO = + dyn_cast<const MachOObjectFile>(Obj)) { + DataRefImpl DR = i->getRawDataRefImpl(); + SegmentName = MachO->getSectionFinalSegmentName(DR); + } + StringRef name; + if (error(i->getName(name))) break; + outs() << "Disassembly of section "; + if (!SegmentName.empty()) + outs() << SegmentName << ","; + outs() << name << ':'; + + // If the section has no symbols just insert a dummy one and disassemble + // the whole section. + if (Symbols.empty()) + Symbols.push_back(std::make_pair(0, name)); + + + SmallString<40> Comments; + raw_svector_ostream CommentStream(Comments); + + StringRef Bytes; + if (error(i->getContents(Bytes))) break; + StringRefMemoryObject memoryObject(Bytes, SectionAddr); + uint64_t Size; + uint64_t Index; + uint64_t SectSize; + if (error(i->getSize(SectSize))) break; + + std::vector<RelocationRef>::const_iterator rel_cur = Rels.begin(); + std::vector<RelocationRef>::const_iterator rel_end = Rels.end(); + // Disassemble symbol by symbol. + for (unsigned si = 0, se = Symbols.size(); si != se; ++si) { + uint64_t Start = Symbols[si].first; + uint64_t End; + // The end is either the size of the section or the beginning of the next + // symbol. + if (si == se - 1) + End = SectSize; + // Make sure this symbol takes up space. + else if (Symbols[si + 1].first != Start) + End = Symbols[si + 1].first - 1; + else + // This symbol has the same address as the next symbol. Skip it. + continue; + + outs() << '\n' << Symbols[si].second << ":\n"; + +#ifndef NDEBUG + raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); +#else + raw_ostream &DebugOut = nulls(); +#endif + + for (Index = Start; Index < End; Index += Size) { + MCInst Inst; + + if (DisAsm->getInstruction(Inst, Size, memoryObject, + SectionAddr + Index, + DebugOut, CommentStream)) { + outs() << format("%8" PRIx64 ":", SectionAddr + Index); + if (!NoShowRawInsn) { + outs() << "\t"; + DumpBytes(StringRef(Bytes.data() + Index, Size)); + } + IP->printInst(&Inst, outs(), ""); + outs() << CommentStream.str(); + Comments.clear(); + outs() << "\n"; + } else { + errs() << ToolName << ": warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes + } + + // Print relocation for instruction. + while (rel_cur != rel_end) { + bool hidden = false; + uint64_t addr; + SmallString<16> name; + SmallString<32> val; + + // If this relocation is hidden, skip it. + if (error(rel_cur->getHidden(hidden))) goto skip_print_rel; + if (hidden) goto skip_print_rel; + + if (error(rel_cur->getOffset(addr))) goto skip_print_rel; + // Stop when rel_cur's address is past the current instruction. + if (addr >= Index + Size) break; + if (error(rel_cur->getTypeName(name))) goto skip_print_rel; + if (error(rel_cur->getValueString(val))) goto skip_print_rel; + + outs() << format("\t\t\t%8" PRIx64 ": ", SectionAddr + addr) << name + << "\t" << val << "\n"; + + skip_print_rel: + ++rel_cur; + } + } + } + } +} + +static void PrintRelocations(const ObjectFile *o) { + error_code ec; + for (section_iterator si = o->begin_sections(), se = o->end_sections(); + si != se; si.increment(ec)){ + if (error(ec)) return; + if (si->begin_relocations() == si->end_relocations()) + continue; + StringRef secname; + if (error(si->getName(secname))) continue; + outs() << "RELOCATION RECORDS FOR [" << secname << "]:\n"; + for (relocation_iterator ri = si->begin_relocations(), + re = si->end_relocations(); + ri != re; ri.increment(ec)) { + if (error(ec)) return; + + bool hidden; + uint64_t address; + SmallString<32> relocname; + SmallString<32> valuestr; + if (error(ri->getHidden(hidden))) continue; + if (hidden) continue; + if (error(ri->getTypeName(relocname))) continue; + if (error(ri->getOffset(address))) continue; + if (error(ri->getValueString(valuestr))) continue; + outs() << address << " " << relocname << " " << valuestr << "\n"; + } + outs() << "\n"; + } +} + +static void PrintSectionHeaders(const ObjectFile *o) { + outs() << "Sections:\n" + "Idx Name Size Address Type\n"; + error_code ec; + unsigned i = 0; + for (section_iterator si = o->begin_sections(), se = o->end_sections(); + si != se; si.increment(ec)) { + if (error(ec)) return; + StringRef Name; + if (error(si->getName(Name))) return; + uint64_t Address; + if (error(si->getAddress(Address))) return; + uint64_t Size; + if (error(si->getSize(Size))) return; + bool Text, Data, BSS; + if (error(si->isText(Text))) return; + if (error(si->isData(Data))) return; + if (error(si->isBSS(BSS))) return; + std::string Type = (std::string(Text ? "TEXT " : "") + + (Data ? "DATA " : "") + (BSS ? "BSS" : "")); + outs() << format("%3d %-13s %08" PRIx64 " %016" PRIx64 " %s\n", + i, Name.str().c_str(), Size, Address, Type.c_str()); + ++i; + } +} + +static void PrintSectionContents(const ObjectFile *o) { + error_code ec; + for (section_iterator si = o->begin_sections(), + se = o->end_sections(); + si != se; si.increment(ec)) { + if (error(ec)) return; + StringRef Name; + StringRef Contents; + uint64_t BaseAddr; + bool BSS; + if (error(si->getName(Name))) continue; + if (error(si->getContents(Contents))) continue; + if (error(si->getAddress(BaseAddr))) continue; + if (error(si->isBSS(BSS))) continue; + + outs() << "Contents of section " << Name << ":\n"; + if (BSS) { + outs() << format("<skipping contents of bss section at [%04" PRIx64 + ", %04" PRIx64 ")>\n", BaseAddr, + BaseAddr + Contents.size()); + continue; + } + + // 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 (std::isprint(static_cast<unsigned char>(Contents[addr + i]) & 0xFF)) + outs() << Contents[addr + i]; + else + outs() << "."; + } + outs() << "\n"; + } + } +} + +static void PrintCOFFSymbolTable(const COFFObjectFile *coff) { + const coff_file_header *header; + if (error(coff->getHeader(header))) return; + int aux_count = 0; + const coff_symbol *symbol = 0; + for (int i = 0, e = header->NumberOfSymbols; i != e; ++i) { + if (aux_count--) { + // Figure out which type of aux this is. + if (symbol->StorageClass == COFF::IMAGE_SYM_CLASS_STATIC + && symbol->Value == 0) { // Section definition. + const coff_aux_section_definition *asd; + if (error(coff->getAuxSymbol<coff_aux_section_definition>(i, asd))) + return; + outs() << "AUX " + << format("scnlen 0x%x nreloc %d nlnno %d checksum 0x%x " + , unsigned(asd->Length) + , unsigned(asd->NumberOfRelocations) + , unsigned(asd->NumberOfLinenumbers) + , unsigned(asd->CheckSum)) + << format("assoc %d comdat %d\n" + , unsigned(asd->Number) + , unsigned(asd->Selection)); + } else + outs() << "AUX Unknown\n"; + } else { + StringRef name; + if (error(coff->getSymbol(i, symbol))) return; + if (error(coff->getSymbolName(symbol, name))) return; + outs() << "[" << format("%2d", i) << "]" + << "(sec " << format("%2d", int(symbol->SectionNumber)) << ")" + << "(fl 0x00)" // Flag bits, which COFF doesn't have. + << "(ty " << format("%3x", unsigned(symbol->Type)) << ")" + << "(scl " << format("%3x", unsigned(symbol->StorageClass)) << ") " + << "(nx " << unsigned(symbol->NumberOfAuxSymbols) << ") " + << "0x" << format("%08x", unsigned(symbol->Value)) << " " + << name << "\n"; + aux_count = symbol->NumberOfAuxSymbols; + } + } +} + +static void PrintSymbolTable(const ObjectFile *o) { + outs() << "SYMBOL TABLE:\n"; + + if (const COFFObjectFile *coff = dyn_cast<const COFFObjectFile>(o)) + PrintCOFFSymbolTable(coff); + else { + error_code ec; + for (symbol_iterator si = o->begin_symbols(), + se = o->end_symbols(); si != se; si.increment(ec)) { + if (error(ec)) return; + StringRef Name; + uint64_t Address; + SymbolRef::Type Type; + uint64_t Size; + uint32_t Flags; + section_iterator Section = o->end_sections(); + if (error(si->getName(Name))) continue; + if (error(si->getAddress(Address))) continue; + if (error(si->getFlags(Flags))) continue; + if (error(si->getType(Type))) continue; + if (error(si->getSize(Size))) continue; + if (error(si->getSection(Section))) continue; + + bool Global = Flags & SymbolRef::SF_Global; + bool Weak = Flags & SymbolRef::SF_Weak; + bool Absolute = Flags & SymbolRef::SF_Absolute; + + if (Address == UnknownAddressOrSize) + Address = 0; + if (Size == UnknownAddressOrSize) + Size = 0; + 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'; + + 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 (Section == o->end_sections()) + 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; + if (error(Section->getName(SectionName))) + SectionName = ""; + outs() << SectionName; + } + outs() << '\t' + << format("%08" PRIx64 " ", Size) + << Name + << '\n'; + } + } +} + +static void PrintUnwindInfo(const ObjectFile *o) { + outs() << "Unwind info:\n\n"; + + if (const COFFObjectFile *coff = dyn_cast<COFFObjectFile>(o)) { + printCOFFUnwindInfo(coff); + } else { + // TODO: Extract DWARF dump tool to objdump. + errs() << "This operation is only currently supported " + "for COFF object files.\n"; + return; + } +} + +static void printPrivateFileHeader(const ObjectFile *o) { + if (o->isELF()) { + printELFFileHeader(o); + } else if (o->isCOFF()) { + printCOFFFileHeader(o); + } +} + +static void DumpObject(const ObjectFile *o) { + outs() << '\n'; + outs() << o->getFileName() + << ":\tfile format " << o->getFileFormatName() << "\n\n"; + + if (Disassemble) + DisassembleObject(o, Relocations); + if (Relocations && !Disassemble) + PrintRelocations(o); + if (SectionHeaders) + PrintSectionHeaders(o); + if (SectionContents) + PrintSectionContents(o); + if (SymbolTable) + PrintSymbolTable(o); + if (UnwindInfo) + PrintUnwindInfo(o); + if (PrivateHeaders) + printPrivateFileHeader(o); +} + +/// @brief Dump each object file in \a a; +static void DumpArchive(const Archive *a) { + for (Archive::child_iterator i = a->begin_children(), + e = a->end_children(); i != e; ++i) { + OwningPtr<Binary> child; + if (error_code ec = i->getAsBinary(child)) { + // Ignore non-object files. + if (ec != object_error::invalid_file_type) + errs() << ToolName << ": '" << a->getFileName() << "': " << ec.message() + << ".\n"; + continue; + } + if (ObjectFile *o = dyn_cast<ObjectFile>(child.get())) + DumpObject(o); + else + errs() << ToolName << ": '" << a->getFileName() << "': " + << "Unrecognized file type.\n"; + } +} + +/// @brief Open file and figure out how to dump it. +static void DumpInput(StringRef file) { + // If file isn't stdin, check that it exists. + if (file != "-" && !sys::fs::exists(file)) { + errs() << ToolName << ": '" << file << "': " << "No such file\n"; + return; + } + + if (MachOOpt && Disassemble) { + DisassembleInputMachO(file); + return; + } + + // Attempt to open the binary. + OwningPtr<Binary> binary; + if (error_code ec = createBinary(file, binary)) { + errs() << ToolName << ": '" << file << "': " << ec.message() << ".\n"; + return; + } + + if (Archive *a = dyn_cast<Archive>(binary.get())) + DumpArchive(a); + else if (ObjectFile *o = dyn_cast<ObjectFile>(binary.get())) + DumpObject(o); + else + errs() << ToolName << ": '" << file << "': " << "Unrecognized file type.\n"; +} + +int main(int argc, char **argv) { + // Print a stack trace if we signal out. + sys::PrintStackTraceOnErrorSignal(); + PrettyStackTraceProgram X(argc, argv); + llvm_shutdown_obj Y; // Call llvm_shutdown() on exit. + + // Initialize targets and assembly printers/parsers. + llvm::InitializeAllTargetInfos(); + llvm::InitializeAllTargetMCs(); + llvm::InitializeAllAsmParsers(); + llvm::InitializeAllDisassemblers(); + + // Register the target printer for --version. + cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion); + + cl::ParseCommandLineOptions(argc, argv, "llvm object file dumper\n"); + TripleName = Triple::normalize(TripleName); + + ToolName = argv[0]; + + // Defaults to a.out if no filenames specified. + if (InputFilenames.size() == 0) + InputFilenames.push_back("a.out"); + + if (!Disassemble + && !Relocations + && !SectionHeaders + && !SectionContents + && !SymbolTable + && !UnwindInfo + && !PrivateHeaders) { + cl::PrintHelpMessage(); + return 2; + } + + std::for_each(InputFilenames.begin(), InputFilenames.end(), + DumpInput); + + return 0; +} diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h new file mode 100644 index 0000000..b716a26 --- /dev/null +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h @@ -0,0 +1,41 @@ +//===-- llvm-objdump.h ----------------------------------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_OBJDUMP_H +#define LLVM_OBJDUMP_H + +#include "llvm/ADT/StringRef.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/DataTypes.h" +#include "llvm/Support/StringRefMemoryObject.h" + +namespace llvm { + +namespace object { + class COFFObjectFile; + class ObjectFile; + class RelocationRef; +} +class error_code; + +extern cl::opt<std::string> TripleName; +extern cl::opt<std::string> ArchName; + +// Various helper functions. +bool error(error_code ec); +bool RelocAddressLess(object::RelocationRef a, object::RelocationRef b); +void DumpBytes(StringRef bytes); +void DisassembleInputMachO(StringRef Filename); +void printCOFFUnwindInfo(const object::COFFObjectFile* o); +void printELFFileHeader(const object::ObjectFile *o); +void printCOFFFileHeader(const object::ObjectFile *o); + +} // end namespace llvm + +#endif |