diff options
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/COFFDump.cpp | 4 | ||||
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/ELFDump.cpp | 91 | ||||
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/MachODump.cpp | 407 | ||||
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/WasmDump.cpp | 2 | ||||
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp | 1073 | ||||
| -rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.h | 7 |
6 files changed, 974 insertions, 610 deletions
diff --git a/contrib/llvm/tools/llvm-objdump/COFFDump.cpp b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp index 780d1e9e6111..7ca5d04593ff 100644 --- a/contrib/llvm/tools/llvm-objdump/COFFDump.cpp +++ b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp @@ -8,7 +8,7 @@ //===----------------------------------------------------------------------===// /// /// \file -/// \brief This file implements the COFF-specific dumper for llvm-objdump. +/// 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 described in MSDN: /// http://msdn.microsoft.com/en-us/library/ck9asaa9.aspx @@ -453,7 +453,7 @@ static bool getPDataSection(const COFFObjectFile *Obj, Rels.push_back(Reloc); // Sort relocations by address. - std::sort(Rels.begin(), Rels.end(), RelocAddressLess); + llvm::sort(Rels.begin(), Rels.end(), RelocAddressLess); ArrayRef<uint8_t> Contents; error(Obj->getSectionContents(Pdata, Contents)); diff --git a/contrib/llvm/tools/llvm-objdump/ELFDump.cpp b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp index 7f5fe5a9d3b8..f4d36656a6c4 100644 --- a/contrib/llvm/tools/llvm-objdump/ELFDump.cpp +++ b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp @@ -8,7 +8,7 @@ //===----------------------------------------------------------------------===// /// /// \file -/// \brief This file implements the ELF-specific dumper for llvm-objdump. +/// This file implements the ELF-specific dumper for llvm-objdump. /// //===----------------------------------------------------------------------===// @@ -21,6 +21,77 @@ using namespace llvm; using namespace llvm::object; +template <class ELFT> +Expected<StringRef> getDynamicStrTab(const ELFFile<ELFT> *Elf) { + typedef ELFFile<ELFT> ELFO; + + auto DynamicEntriesOrError = Elf->dynamicEntries(); + if (!DynamicEntriesOrError) + return DynamicEntriesOrError.takeError(); + + for (const typename ELFO::Elf_Dyn &Dyn : *DynamicEntriesOrError) { + if (Dyn.d_tag == ELF::DT_STRTAB) { + auto MappedAddrOrError = Elf->toMappedAddr(Dyn.getPtr()); + if (!MappedAddrOrError) + consumeError(MappedAddrOrError.takeError()); + return StringRef(reinterpret_cast<const char *>(*MappedAddrOrError)); + } + } + + // If the dynamic segment is not present, we fall back on the sections. + auto SectionsOrError = Elf->sections(); + if (!SectionsOrError) + return SectionsOrError.takeError(); + + for (const typename ELFO::Elf_Shdr &Sec : *SectionsOrError) { + if (Sec.sh_type == ELF::SHT_DYNSYM) + return Elf->getStringTableForSymtab(Sec); + } + + return createError("dynamic string table not found"); +} + +template <class ELFT> +void printDynamicSection(const ELFFile<ELFT> *Elf, StringRef Filename) { + auto ProgramHeaderOrError = Elf->program_headers(); + if (!ProgramHeaderOrError) + report_error(Filename, ProgramHeaderOrError.takeError()); + + auto DynamicEntriesOrError = Elf->dynamicEntries(); + if (!DynamicEntriesOrError) + report_error(Filename, DynamicEntriesOrError.takeError()); + + outs() << "Dynamic Section:\n"; + for (const auto &Dyn : *DynamicEntriesOrError) { + if (Dyn.d_tag == ELF::DT_NULL) + continue; + + StringRef Str = StringRef(Elf->getDynamicTagAsString(Dyn.d_tag)); + + if (Str.empty()) { + std::string HexStr = utohexstr(static_cast<uint64_t>(Dyn.d_tag), true); + outs() << format(" 0x%-19s", HexStr.c_str()); + } else { + // We use "-21" in order to match GNU objdump's output. + outs() << format(" %-21s", Str.data()); + } + + const char *Fmt = + ELFT::Is64Bits ? "0x%016" PRIx64 "\n" : "0x%08" PRIx64 "\n"; + if (Dyn.d_tag == ELF::DT_NEEDED) { + Expected<StringRef> StrTabOrErr = getDynamicStrTab(Elf); + if (StrTabOrErr) { + const char *Data = StrTabOrErr.get().data(); + outs() << (Data + Dyn.d_un.d_val) << "\n"; + continue; + } + warn(errorToErrorCode(StrTabOrErr.takeError()).message()); + consumeError(StrTabOrErr.takeError()); + } + outs() << format(Fmt, (uint64_t)Dyn.d_un.d_val); + } +} + template <class ELFT> void printProgramHeaders(const ELFFile<ELFT> *o) { typedef ELFFile<ELFT> ELFO; outs() << "Program Header:\n"; @@ -103,3 +174,21 @@ void llvm::printELFFileHeader(const object::ObjectFile *Obj) { if (const ELF64BEObjectFile *ELFObj = dyn_cast<ELF64BEObjectFile>(Obj)) printProgramHeaders(ELFObj->getELFFile()); } + +void llvm::printELFDynamicSection(const object::ObjectFile *Obj) { + // Little-endian 32-bit + if (const ELF32LEObjectFile *ELFObj = dyn_cast<ELF32LEObjectFile>(Obj)) + printDynamicSection(ELFObj->getELFFile(), Obj->getFileName()); + + // Big-endian 32-bit + if (const ELF32BEObjectFile *ELFObj = dyn_cast<ELF32BEObjectFile>(Obj)) + printDynamicSection(ELFObj->getELFFile(), Obj->getFileName()); + + // Little-endian 64-bit + if (const ELF64LEObjectFile *ELFObj = dyn_cast<ELF64LEObjectFile>(Obj)) + printDynamicSection(ELFObj->getELFFile(), Obj->getFileName()); + + // Big-endian 64-bit + if (const ELF64BEObjectFile *ELFObj = dyn_cast<ELF64BEObjectFile>(Obj)) + printDynamicSection(ELFObj->getELFFile(), Obj->getFileName()); +} diff --git a/contrib/llvm/tools/llvm-objdump/MachODump.cpp b/contrib/llvm/tools/llvm-objdump/MachODump.cpp index 9908c2f2d016..bdf80c73b999 100644 --- a/contrib/llvm/tools/llvm-objdump/MachODump.cpp +++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp @@ -76,11 +76,6 @@ cl::opt<bool> llvm::UniversalHeaders("universal-headers", "(requires -macho)")); cl::opt<bool> - llvm::ArchiveHeaders("archive-headers", - cl::desc("Print archive headers for Mach-O archives " - "(requires -macho)")); - -cl::opt<bool> ArchiveMemberOffsets("archive-member-offsets", cl::desc("Print the offset to each archive member for " "Mach-O archives (requires -macho and " @@ -1284,14 +1279,35 @@ static void DumpLiteralPointerSection(MachOObjectFile *O, } } -static void DumpInitTermPointerSection(MachOObjectFile *O, const char *sect, +static void DumpInitTermPointerSection(MachOObjectFile *O, + const SectionRef &Section, + const char *sect, uint32_t sect_size, uint64_t sect_addr, SymbolAddressMap *AddrMap, bool verbose) { uint32_t stride; stride = (O->is64Bit()) ? sizeof(uint64_t) : sizeof(uint32_t); + + // Collect the external relocation symbols for the pointers. + std::vector<std::pair<uint64_t, SymbolRef>> Relocs; + for (const RelocationRef &Reloc : Section.relocations()) { + DataRefImpl Rel; + MachO::any_relocation_info RE; + bool isExtern = false; + Rel = Reloc.getRawDataRefImpl(); + RE = O->getRelocation(Rel); + isExtern = O->getPlainRelocationExternal(RE); + if (isExtern) { + uint64_t RelocOffset = Reloc.getOffset(); + symbol_iterator RelocSym = Reloc.getSymbol(); + Relocs.push_back(std::make_pair(RelocOffset, *RelocSym)); + } + } + array_pod_sort(Relocs.begin(), Relocs.end()); + for (uint32_t i = 0; i < sect_size; i += stride) { const char *SymbolName = nullptr; + uint64_t p; if (O->is64Bit()) { outs() << format("0x%016" PRIx64, sect_addr + i * stride) << " "; uint64_t pointer_value; @@ -1299,8 +1315,7 @@ static void DumpInitTermPointerSection(MachOObjectFile *O, const char *sect, if (O->isLittleEndian() != sys::IsLittleEndianHost) sys::swapByteOrder(pointer_value); outs() << format("0x%016" PRIx64, pointer_value); - if (verbose) - SymbolName = GuessSymbolName(pointer_value, AddrMap); + p = pointer_value; } else { outs() << format("0x%08" PRIx64, sect_addr + i * stride) << " "; uint32_t pointer_value; @@ -1308,11 +1323,25 @@ static void DumpInitTermPointerSection(MachOObjectFile *O, const char *sect, if (O->isLittleEndian() != sys::IsLittleEndianHost) sys::swapByteOrder(pointer_value); outs() << format("0x%08" PRIx32, pointer_value); - if (verbose) - SymbolName = GuessSymbolName(pointer_value, AddrMap); + p = pointer_value; + } + if (verbose) { + // First look for an external relocation entry for this pointer. + auto Reloc = find_if(Relocs, [&](const std::pair<uint64_t, SymbolRef> &P) { + return P.first == i; + }); + if (Reloc != Relocs.end()) { + symbol_iterator RelocSym = Reloc->second; + Expected<StringRef> SymName = RelocSym->getName(); + if (!SymName) + report_error(O->getFileName(), SymName.takeError()); + outs() << " " << *SymName; + } else { + SymbolName = GuessSymbolName(p, AddrMap); + if (SymbolName) + outs() << " " << SymbolName; + } } - if (SymbolName) - outs() << " " << SymbolName; outs() << "\n"; } } @@ -1463,8 +1492,8 @@ static void DumpSectionContents(StringRef Filename, MachOObjectFile *O, break; case MachO::S_MOD_INIT_FUNC_POINTERS: case MachO::S_MOD_TERM_FUNC_POINTERS: - DumpInitTermPointerSection(O, sect, sect_size, sect_addr, &AddrMap, - verbose); + DumpInitTermPointerSection(O, Section, sect, sect_size, sect_addr, + &AddrMap, verbose); break; default: outs() << "Unknown section type (" @@ -2149,19 +2178,22 @@ void llvm::ParseInputMachO(StringRef Filename) { // The block of info used by the Symbolizer call backs. struct DisassembleInfo { + DisassembleInfo(MachOObjectFile *O, SymbolAddressMap *AddrMap, + std::vector<SectionRef> *Sections, bool verbose) + : verbose(verbose), O(O), AddrMap(AddrMap), Sections(Sections) {} bool verbose; MachOObjectFile *O; SectionRef S; SymbolAddressMap *AddrMap; std::vector<SectionRef> *Sections; - const char *class_name; - const char *selector_name; - char *method; - char *demangled_name; - uint64_t adrp_addr; - uint32_t adrp_inst; + const char *class_name = nullptr; + const char *selector_name = nullptr; + std::unique_ptr<char[]> method = nullptr; + char *demangled_name = nullptr; + uint64_t adrp_addr = 0; + uint32_t adrp_inst = 0; std::unique_ptr<SymbolAddressMap> bindtable; - uint32_t depth; + uint32_t depth = 0; }; // SymbolizerGetOpInfo() is the operand information call back function. @@ -2756,32 +2788,33 @@ static void method_reference(struct DisassembleInfo *info, if (*ReferenceName != nullptr) { if (strcmp(*ReferenceName, "_objc_msgSend") == 0) { if (info->selector_name != nullptr) { - if (info->method != nullptr) - free(info->method); if (info->class_name != nullptr) { - info->method = (char *)malloc(5 + strlen(info->class_name) + - strlen(info->selector_name)); - if (info->method != nullptr) { - strcpy(info->method, "+["); - strcat(info->method, info->class_name); - strcat(info->method, " "); - strcat(info->method, info->selector_name); - strcat(info->method, "]"); - *ReferenceName = info->method; + info->method = llvm::make_unique<char[]>( + 5 + strlen(info->class_name) + strlen(info->selector_name)); + char *method = info->method.get(); + if (method != nullptr) { + strcpy(method, "+["); + strcat(method, info->class_name); + strcat(method, " "); + strcat(method, info->selector_name); + strcat(method, "]"); + *ReferenceName = method; *ReferenceType = LLVMDisassembler_ReferenceType_Out_Objc_Message; } } else { - info->method = (char *)malloc(9 + strlen(info->selector_name)); - if (info->method != nullptr) { + info->method = + llvm::make_unique<char[]>(9 + strlen(info->selector_name)); + char *method = info->method.get(); + if (method != nullptr) { if (Arch == Triple::x86_64) - strcpy(info->method, "-[%rdi "); + strcpy(method, "-[%rdi "); else if (Arch == Triple::aarch64) - strcpy(info->method, "-[x0 "); + strcpy(method, "-[x0 "); else - strcpy(info->method, "-[r? "); - strcat(info->method, info->selector_name); - strcat(info->method, "]"); - *ReferenceName = info->method; + strcpy(method, "-[r? "); + strcat(method, info->selector_name); + strcat(method, "]"); + *ReferenceName = method; *ReferenceType = LLVMDisassembler_ReferenceType_Out_Objc_Message; } } @@ -2789,19 +2822,19 @@ static void method_reference(struct DisassembleInfo *info, } } else if (strcmp(*ReferenceName, "_objc_msgSendSuper2") == 0) { if (info->selector_name != nullptr) { - if (info->method != nullptr) - free(info->method); - info->method = (char *)malloc(17 + strlen(info->selector_name)); - if (info->method != nullptr) { + info->method = + llvm::make_unique<char[]>(17 + strlen(info->selector_name)); + char *method = info->method.get(); + if (method != nullptr) { if (Arch == Triple::x86_64) - strcpy(info->method, "-[[%rdi super] "); + strcpy(method, "-[[%rdi super] "); else if (Arch == Triple::aarch64) - strcpy(info->method, "-[[x0 super] "); + strcpy(method, "-[[x0 super] "); else - strcpy(info->method, "-[[r? super] "); - strcat(info->method, info->selector_name); - strcat(info->method, "]"); - *ReferenceName = info->method; + strcpy(method, "-[[r? super] "); + strcat(method, info->selector_name); + strcat(method, "]"); + *ReferenceName = method; *ReferenceType = LLVMDisassembler_ReferenceType_Out_Objc_Message; } info->class_name = nullptr; @@ -3196,6 +3229,8 @@ struct imageInfo_t { /* masks for objc_image_info.flags */ #define OBJC_IMAGE_IS_REPLACEMENT (1 << 0) #define OBJC_IMAGE_SUPPORTS_GC (1 << 1) +#define OBJC_IMAGE_IS_SIMULATED (1 << 5) +#define OBJC_IMAGE_HAS_CATEGORY_CLASS_PROPERTIES (1 << 6) struct message_ref64 { uint64_t imp; /* IMP (64-bit pointer) */ @@ -5557,12 +5592,24 @@ static void print_image_info64(SectionRef S, struct DisassembleInfo *info) { outs() << " OBJC_IMAGE_IS_REPLACEMENT"; if (o.flags & OBJC_IMAGE_SUPPORTS_GC) outs() << " OBJC_IMAGE_SUPPORTS_GC"; + if (o.flags & OBJC_IMAGE_IS_SIMULATED) + outs() << " OBJC_IMAGE_IS_SIMULATED"; + if (o.flags & OBJC_IMAGE_HAS_CATEGORY_CLASS_PROPERTIES) + outs() << " OBJC_IMAGE_HAS_CATEGORY_CLASS_PROPERTIES"; swift_version = (o.flags >> 8) & 0xff; if (swift_version != 0) { if (swift_version == 1) outs() << " Swift 1.0"; else if (swift_version == 2) outs() << " Swift 1.1"; + else if(swift_version == 3) + outs() << " Swift 2.0"; + else if(swift_version == 4) + outs() << " Swift 3.0"; + else if(swift_version == 5) + outs() << " Swift 4.0"; + else if(swift_version == 6) + outs() << " Swift 4.1"; else outs() << " unknown future Swift version (" << swift_version << ")"; } @@ -5606,6 +5653,14 @@ static void print_image_info32(SectionRef S, struct DisassembleInfo *info) { outs() << " Swift 1.0"; else if (swift_version == 2) outs() << " Swift 1.1"; + else if(swift_version == 3) + outs() << " Swift 2.0"; + else if(swift_version == 4) + outs() << " Swift 3.0"; + else if(swift_version == 5) + outs() << " Swift 4.0"; + else if(swift_version == 6) + outs() << " Swift 4.1"; else outs() << " unknown future Swift version (" << swift_version << ")"; } @@ -5659,21 +5714,8 @@ static void printObjc2_64bit_MetaData(MachOObjectFile *O, bool verbose) { Sections.push_back(Section); } - struct DisassembleInfo info; - // Set up the block of info used by the Symbolizer call backs. - info.verbose = verbose; - info.O = O; - info.AddrMap = &AddrMap; - info.Sections = &Sections; - info.class_name = nullptr; - info.selector_name = nullptr; - info.method = nullptr; - info.demangled_name = nullptr; - info.bindtable = nullptr; - info.adrp_addr = 0; - info.adrp_inst = 0; - - info.depth = 0; + struct DisassembleInfo info(O, &AddrMap, &Sections, verbose); + SectionRef CL = get_section(O, "__OBJC2", "__class_list"); if (CL == SectionRef()) CL = get_section(O, "__DATA", "__objc_classlist"); @@ -5757,19 +5799,7 @@ static void printObjc2_32bit_MetaData(MachOObjectFile *O, bool verbose) { Sections.push_back(Section); } - struct DisassembleInfo info; - // Set up the block of info used by the Symbolizer call backs. - info.verbose = verbose; - info.O = O; - info.AddrMap = &AddrMap; - info.Sections = &Sections; - info.class_name = nullptr; - info.selector_name = nullptr; - info.method = nullptr; - info.demangled_name = nullptr; - info.bindtable = nullptr; - info.adrp_addr = 0; - info.adrp_inst = 0; + struct DisassembleInfo info(O, &AddrMap, &Sections, verbose); SectionRef CL = get_section(O, "__OBJC2", "__class_list"); if (CL == SectionRef()) @@ -5867,19 +5897,7 @@ static bool printObjc1_32bit_MetaData(MachOObjectFile *O, bool verbose) { Sections.push_back(Section); } - struct DisassembleInfo info; - // Set up the block of info used by the Symbolizer call backs. - info.verbose = verbose; - info.O = O; - info.AddrMap = &AddrMap; - info.Sections = &Sections; - info.class_name = nullptr; - info.selector_name = nullptr; - info.method = nullptr; - info.demangled_name = nullptr; - info.bindtable = nullptr; - info.adrp_addr = 0; - info.adrp_inst = 0; + struct DisassembleInfo info(O, &AddrMap, &Sections, verbose); for (i = 0; i < S.getSize(); i += sizeof(struct objc_module_t)) { p = S.getAddress() + i; @@ -6040,19 +6058,7 @@ static void DumpProtocolSection(MachOObjectFile *O, const char *sect, Sections.push_back(Section); } - struct DisassembleInfo info; - // Set up the block of info used by the Symbolizer call backs. - info.verbose = true; - info.O = O; - info.AddrMap = &AddrMap; - info.Sections = &Sections; - info.class_name = nullptr; - info.selector_name = nullptr; - info.method = nullptr; - info.demangled_name = nullptr; - info.bindtable = nullptr; - info.adrp_addr = 0; - info.adrp_inst = 0; + struct DisassembleInfo info(O, &AddrMap, &Sections, true); const char *p; struct objc_protocol_t protocol; @@ -6748,7 +6754,7 @@ static const char *SymbolizerSymbolLookUp(void *DisInfo, return SymbolName; } -/// \brief Emits the comments that are stored in the CommentStream. +/// Emits the comments that are stored in the CommentStream. /// Each comment in the CommentStream must end with a newline. static void emitComments(raw_svector_ostream &CommentStream, SmallString<128> &CommentsToEmit, @@ -6817,7 +6823,7 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, std::unique_ptr<MCDisassembler> DisAsm( TheTarget->createMCDisassembler(*STI, Ctx)); std::unique_ptr<MCSymbolizer> Symbolizer; - struct DisassembleInfo SymbolizerInfo; + struct DisassembleInfo SymbolizerInfo(nullptr, nullptr, nullptr, false); std::unique_ptr<MCRelocationInfo> RelInfo( TheTarget->createMCRelocationInfo(TripleName, Ctx)); if (RelInfo) { @@ -6855,7 +6861,7 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, std::unique_ptr<MCInstPrinter> ThumbIP; std::unique_ptr<MCContext> ThumbCtx; std::unique_ptr<MCSymbolizer> ThumbSymbolizer; - struct DisassembleInfo ThumbSymbolizerInfo; + struct DisassembleInfo ThumbSymbolizerInfo(nullptr, nullptr, nullptr, false); std::unique_ptr<MCRelocationInfo> ThumbRelInfo; if (ThumbTarget) { ThumbMRI.reset(ThumbTarget->createMCRegInfo(ThumbTripleName)); @@ -6904,7 +6910,7 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, BaseSegmentAddress); // Sort the symbols by address, just in case they didn't come in that way. - std::sort(Symbols.begin(), Symbols.end(), SymbolSorter()); + llvm::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; @@ -6940,10 +6946,12 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, errs() << "llvm-objdump: " << Filename << ": " << EC.message() << '\n'; return; } - DbgObj = - ObjectFile::createMachOObjectFile(BufOrErr.get()->getMemBufferRef()) - .get() - .release(); + Expected<std::unique_ptr<MachOObjectFile>> DbgObjCheck = + ObjectFile::createMachOObjectFile(BufOrErr.get()->getMemBufferRef()); + + if (DbgObjCheck.takeError()) + report_error(MachOOF->getFileName(), DbgObjCheck.takeError()); + DbgObj = DbgObjCheck.get().release(); } // Setup the DIContext @@ -7003,26 +7011,12 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, SymbolizerInfo.S = Sections[SectIdx]; SymbolizerInfo.AddrMap = &AddrMap; SymbolizerInfo.Sections = &Sections; - SymbolizerInfo.class_name = nullptr; - SymbolizerInfo.selector_name = nullptr; - SymbolizerInfo.method = nullptr; - SymbolizerInfo.demangled_name = nullptr; - SymbolizerInfo.bindtable = nullptr; - SymbolizerInfo.adrp_addr = 0; - SymbolizerInfo.adrp_inst = 0; // Same for the ThumbSymbolizer ThumbSymbolizerInfo.verbose = !NoSymbolicOperands; ThumbSymbolizerInfo.O = MachOOF; ThumbSymbolizerInfo.S = Sections[SectIdx]; ThumbSymbolizerInfo.AddrMap = &AddrMap; ThumbSymbolizerInfo.Sections = &Sections; - ThumbSymbolizerInfo.class_name = nullptr; - ThumbSymbolizerInfo.selector_name = nullptr; - ThumbSymbolizerInfo.method = nullptr; - ThumbSymbolizerInfo.demangled_name = nullptr; - ThumbSymbolizerInfo.bindtable = nullptr; - ThumbSymbolizerInfo.adrp_addr = 0; - ThumbSymbolizerInfo.adrp_inst = 0; unsigned int Arch = MachOOF->getArch(); @@ -7293,12 +7287,8 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, TripleName = ""; ThumbTripleName = ""; - if (SymbolizerInfo.method != nullptr) - free(SymbolizerInfo.method); if (SymbolizerInfo.demangled_name != nullptr) free(SymbolizerInfo.demangled_name); - if (ThumbSymbolizerInfo.method != nullptr) - free(ThumbSymbolizerInfo.method); if (ThumbSymbolizerInfo.demangled_name != nullptr) free(ThumbSymbolizerInfo.demangled_name); } @@ -7310,12 +7300,25 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, namespace { -template <typename T> static uint64_t readNext(const char *&Buf) { +template <typename T> +static uint64_t read(StringRef Contents, ptrdiff_t Offset) { using llvm::support::little; using llvm::support::unaligned; - uint64_t Val = support::endian::read<T, little, unaligned>(Buf); - Buf += sizeof(T); + if (Offset + sizeof(T) > Contents.size()) { + outs() << "warning: attempt to read past end of buffer\n"; + return T(); + } + + uint64_t Val = + support::endian::read<T, little, unaligned>(Contents.data() + Offset); + return Val; +} + +template <typename T> +static uint64_t readNext(StringRef Contents, ptrdiff_t &Offset) { + T Val = read<T>(Contents, Offset); + Offset += sizeof(T); return Val; } @@ -7335,18 +7338,18 @@ struct CompactUnwindEntry { CompactUnwindEntry(StringRef Contents, unsigned Offset, bool Is64) : OffsetInSection(Offset) { if (Is64) - read<uint64_t>(Contents.data() + Offset); + read<uint64_t>(Contents, Offset); else - read<uint32_t>(Contents.data() + Offset); + read<uint32_t>(Contents, Offset); } private: - template <typename UIntPtr> void read(const char *Buf) { - FunctionAddr = readNext<UIntPtr>(Buf); - Length = readNext<uint32_t>(Buf); - CompactEncoding = readNext<uint32_t>(Buf); - PersonalityAddr = readNext<UIntPtr>(Buf); - LSDAAddr = readNext<UIntPtr>(Buf); + template <typename UIntPtr> void read(StringRef Contents, ptrdiff_t Offset) { + FunctionAddr = readNext<UIntPtr>(Contents, Offset); + Length = readNext<uint32_t>(Contents, Offset); + CompactEncoding = readNext<uint32_t>(Contents, Offset); + PersonalityAddr = readNext<UIntPtr>(Contents, Offset); + LSDAAddr = readNext<UIntPtr>(Contents, Offset); } }; } @@ -7448,7 +7451,7 @@ printMachOCompactUnwindSection(const MachOObjectFile *Obj, // First populate the initial raw offsets, encodings and so on from the entry. for (unsigned Offset = 0; Offset < Contents.size(); Offset += EntrySize) { - CompactUnwindEntry Entry(Contents.data(), Offset, Is64); + CompactUnwindEntry Entry(Contents, Offset, Is64); CompactUnwinds.push_back(Entry); } @@ -7515,19 +7518,19 @@ printMachOCompactUnwindSection(const MachOObjectFile *Obj, // __unwind_info section dumping //===----------------------------------------------------------------------===// -static void printRegularSecondLevelUnwindPage(const char *PageStart) { - const char *Pos = PageStart; - uint32_t Kind = readNext<uint32_t>(Pos); +static void printRegularSecondLevelUnwindPage(StringRef PageData) { + ptrdiff_t Pos = 0; + uint32_t Kind = readNext<uint32_t>(PageData, Pos); (void)Kind; assert(Kind == 2 && "kind for a regular 2nd level index should be 2"); - uint16_t EntriesStart = readNext<uint16_t>(Pos); - uint16_t NumEntries = readNext<uint16_t>(Pos); + uint16_t EntriesStart = readNext<uint16_t>(PageData, Pos); + uint16_t NumEntries = readNext<uint16_t>(PageData, Pos); - Pos = PageStart + EntriesStart; + Pos = EntriesStart; for (unsigned i = 0; i < NumEntries; ++i) { - uint32_t FunctionOffset = readNext<uint32_t>(Pos); - uint32_t Encoding = readNext<uint32_t>(Pos); + uint32_t FunctionOffset = readNext<uint32_t>(PageData, Pos); + uint32_t Encoding = readNext<uint32_t>(PageData, Pos); outs() << " [" << i << "]: " << "function offset=" << format("0x%08" PRIx32, FunctionOffset) @@ -7537,24 +7540,23 @@ static void printRegularSecondLevelUnwindPage(const char *PageStart) { } static void printCompressedSecondLevelUnwindPage( - const char *PageStart, uint32_t FunctionBase, + StringRef PageData, uint32_t FunctionBase, const SmallVectorImpl<uint32_t> &CommonEncodings) { - const char *Pos = PageStart; - uint32_t Kind = readNext<uint32_t>(Pos); + ptrdiff_t Pos = 0; + uint32_t Kind = readNext<uint32_t>(PageData, Pos); (void)Kind; assert(Kind == 3 && "kind for a compressed 2nd level index should be 3"); - uint16_t EntriesStart = readNext<uint16_t>(Pos); - uint16_t NumEntries = readNext<uint16_t>(Pos); + uint16_t EntriesStart = readNext<uint16_t>(PageData, Pos); + uint16_t NumEntries = readNext<uint16_t>(PageData, Pos); - uint16_t EncodingsStart = readNext<uint16_t>(Pos); - readNext<uint16_t>(Pos); - const auto *PageEncodings = reinterpret_cast<const support::ulittle32_t *>( - PageStart + EncodingsStart); + uint16_t EncodingsStart = readNext<uint16_t>(PageData, Pos); + readNext<uint16_t>(PageData, Pos); + StringRef PageEncodings = PageData.substr(EncodingsStart, StringRef::npos); - Pos = PageStart + EntriesStart; + Pos = EntriesStart; for (unsigned i = 0; i < NumEntries; ++i) { - uint32_t Entry = readNext<uint32_t>(Pos); + uint32_t Entry = readNext<uint32_t>(PageData, Pos); uint32_t FunctionOffset = FunctionBase + (Entry & 0xffffff); uint32_t EncodingIdx = Entry >> 24; @@ -7562,7 +7564,9 @@ static void printCompressedSecondLevelUnwindPage( if (EncodingIdx < CommonEncodings.size()) Encoding = CommonEncodings[EncodingIdx]; else - Encoding = PageEncodings[EncodingIdx - CommonEncodings.size()]; + Encoding = read<uint32_t>(PageEncodings, + sizeof(uint32_t) * + (EncodingIdx - CommonEncodings.size())); outs() << " [" << i << "]: " << "function offset=" << format("0x%08" PRIx32, FunctionOffset) @@ -7585,13 +7589,13 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, StringRef Contents; UnwindInfo.getContents(Contents); - const char *Pos = Contents.data(); + ptrdiff_t Pos = 0; //===---------------------------------- // Section header //===---------------------------------- - uint32_t Version = readNext<uint32_t>(Pos); + uint32_t Version = readNext<uint32_t>(Contents, Pos); outs() << " Version: " << format("0x%" PRIx32, Version) << '\n'; if (Version != 1) { @@ -7599,24 +7603,24 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, return; } - uint32_t CommonEncodingsStart = readNext<uint32_t>(Pos); + uint32_t CommonEncodingsStart = readNext<uint32_t>(Contents, Pos); outs() << " Common encodings array section offset: " << format("0x%" PRIx32, CommonEncodingsStart) << '\n'; - uint32_t NumCommonEncodings = readNext<uint32_t>(Pos); + uint32_t NumCommonEncodings = readNext<uint32_t>(Contents, Pos); outs() << " Number of common encodings in array: " << format("0x%" PRIx32, NumCommonEncodings) << '\n'; - uint32_t PersonalitiesStart = readNext<uint32_t>(Pos); + uint32_t PersonalitiesStart = readNext<uint32_t>(Contents, Pos); outs() << " Personality function array section offset: " << format("0x%" PRIx32, PersonalitiesStart) << '\n'; - uint32_t NumPersonalities = readNext<uint32_t>(Pos); + uint32_t NumPersonalities = readNext<uint32_t>(Contents, Pos); outs() << " Number of personality functions in array: " << format("0x%" PRIx32, NumPersonalities) << '\n'; - uint32_t IndicesStart = readNext<uint32_t>(Pos); + uint32_t IndicesStart = readNext<uint32_t>(Contents, Pos); outs() << " Index array section offset: " << format("0x%" PRIx32, IndicesStart) << '\n'; - uint32_t NumIndices = readNext<uint32_t>(Pos); + uint32_t NumIndices = readNext<uint32_t>(Contents, Pos); outs() << " Number of indices in array: " << format("0x%" PRIx32, NumIndices) << '\n'; @@ -7631,9 +7635,9 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, SmallVector<uint32_t, 64> CommonEncodings; outs() << " Common encodings: (count = " << NumCommonEncodings << ")\n"; - Pos = Contents.data() + CommonEncodingsStart; + Pos = CommonEncodingsStart; for (unsigned i = 0; i < NumCommonEncodings; ++i) { - uint32_t Encoding = readNext<uint32_t>(Pos); + uint32_t Encoding = readNext<uint32_t>(Contents, Pos); CommonEncodings.push_back(Encoding); outs() << " encoding[" << i << "]: " << format("0x%08" PRIx32, Encoding) @@ -7648,9 +7652,9 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, // roughly). Particularly since they only get 2 bits in the compact encoding. outs() << " Personality functions: (count = " << NumPersonalities << ")\n"; - Pos = Contents.data() + PersonalitiesStart; + Pos = PersonalitiesStart; for (unsigned i = 0; i < NumPersonalities; ++i) { - uint32_t PersonalityFn = readNext<uint32_t>(Pos); + uint32_t PersonalityFn = readNext<uint32_t>(Contents, Pos); outs() << " personality[" << i + 1 << "]: " << format("0x%08" PRIx32, PersonalityFn) << '\n'; } @@ -7671,13 +7675,13 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, SmallVector<IndexEntry, 4> IndexEntries; outs() << " Top level indices: (count = " << NumIndices << ")\n"; - Pos = Contents.data() + IndicesStart; + Pos = IndicesStart; for (unsigned i = 0; i < NumIndices; ++i) { IndexEntry Entry; - Entry.FunctionOffset = readNext<uint32_t>(Pos); - Entry.SecondLevelPageStart = readNext<uint32_t>(Pos); - Entry.LSDAStart = readNext<uint32_t>(Pos); + Entry.FunctionOffset = readNext<uint32_t>(Contents, Pos); + Entry.SecondLevelPageStart = readNext<uint32_t>(Contents, Pos); + Entry.LSDAStart = readNext<uint32_t>(Contents, Pos); IndexEntries.push_back(Entry); outs() << " [" << i << "]: " @@ -7696,12 +7700,14 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, // the first top-level index's LSDAOffset to the last (sentinel). outs() << " LSDA descriptors:\n"; - Pos = Contents.data() + IndexEntries[0].LSDAStart; - int NumLSDAs = (IndexEntries.back().LSDAStart - IndexEntries[0].LSDAStart) / - (2 * sizeof(uint32_t)); + Pos = IndexEntries[0].LSDAStart; + const uint32_t LSDASize = 2 * sizeof(uint32_t); + int NumLSDAs = + (IndexEntries.back().LSDAStart - IndexEntries[0].LSDAStart) / LSDASize; + for (int i = 0; i < NumLSDAs; ++i) { - uint32_t FunctionOffset = readNext<uint32_t>(Pos); - uint32_t LSDAOffset = readNext<uint32_t>(Pos); + uint32_t FunctionOffset = readNext<uint32_t>(Contents, Pos); + uint32_t LSDAOffset = readNext<uint32_t>(Contents, Pos); outs() << " [" << i << "]: " << "function offset=" << format("0x%08" PRIx32, FunctionOffset) << ", " @@ -7729,12 +7735,19 @@ static void printMachOUnwindInfoSection(const MachOObjectFile *Obj, << "base function offset=" << format("0x%08" PRIx32, IndexEntries[i].FunctionOffset) << '\n'; - Pos = Contents.data() + IndexEntries[i].SecondLevelPageStart; - uint32_t Kind = *reinterpret_cast<const support::ulittle32_t *>(Pos); + Pos = IndexEntries[i].SecondLevelPageStart; + if (Pos + sizeof(uint32_t) > Contents.size()) { + outs() << "warning: invalid offset for second level page: " << Pos << '\n'; + continue; + } + + uint32_t Kind = + *reinterpret_cast<const support::ulittle32_t *>(Contents.data() + Pos); if (Kind == 2) - printRegularSecondLevelUnwindPage(Pos); + printRegularSecondLevelUnwindPage(Contents.substr(Pos, 4096)); else if (Kind == 3) - printCompressedSecondLevelUnwindPage(Pos, IndexEntries[i].FunctionOffset, + printCompressedSecondLevelUnwindPage(Contents.substr(Pos, 4096), + IndexEntries[i].FunctionOffset, CommonEncodings); else outs() << " Skipping 2nd level page with unknown kind " << Kind @@ -9352,6 +9365,26 @@ static void PrintThreadCommand(MachO::thread_command t, const char *Ptr, outs() << "\t esh.flavor " << es.esh.flavor << " esh.count " << es.esh.count << "\n"; } + } else if (flavor == MachO::x86_EXCEPTION_STATE64) { + outs() << " flavor x86_EXCEPTION_STATE64\n"; + if (count == MachO::x86_EXCEPTION_STATE64_COUNT) + outs() << " count x86_EXCEPTION_STATE64_COUNT\n"; + else + outs() << " count " << count + << " (not x86_EXCEPTION_STATE64_COUNT)\n"; + struct MachO::x86_exception_state64_t es64; + left = end - begin; + if (left >= sizeof(MachO::x86_exception_state64_t)) { + memcpy(&es64, begin, sizeof(MachO::x86_exception_state64_t)); + begin += sizeof(MachO::x86_exception_state64_t); + } else { + memset(&es64, '\0', sizeof(MachO::x86_exception_state64_t)); + memcpy(&es64, begin, left); + begin += left; + } + if (isLittleEndian != sys::IsLittleEndianHost) + swapStruct(es64); + Print_x86_exception_state_t(es64); } else { outs() << " flavor " << flavor << " (unknown)\n"; outs() << " count " << count << "\n"; diff --git a/contrib/llvm/tools/llvm-objdump/WasmDump.cpp b/contrib/llvm/tools/llvm-objdump/WasmDump.cpp index 0d8ffba6ba45..045002cd4b34 100644 --- a/contrib/llvm/tools/llvm-objdump/WasmDump.cpp +++ b/contrib/llvm/tools/llvm-objdump/WasmDump.cpp @@ -8,7 +8,7 @@ //===----------------------------------------------------------------------===// /// /// \file -/// \brief This file implements the wasm-specific dumper for llvm-objdump. +/// This file implements the wasm-specific dumper for llvm-objdump. /// //===----------------------------------------------------------------------===// diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp index 3a9112423cff..8041e6f59940 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -20,10 +20,12 @@ #include "llvm/ADT/Optional.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/StringSet.h" #include "llvm/ADT/Triple.h" #include "llvm/CodeGen/FaultMaps.h" #include "llvm/DebugInfo/DWARF/DWARFContext.h" #include "llvm/DebugInfo/Symbolize/Symbolize.h" +#include "llvm/Demangle/Demangle.h" #include "llvm/MC/MCAsmInfo.h" #include "llvm/MC/MCContext.h" #include "llvm/MC/MCDisassembler/MCDisassembler.h" @@ -50,10 +52,8 @@ #include "llvm/Support/Format.h" #include "llvm/Support/GraphWriter.h" #include "llvm/Support/Host.h" -#include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/InitLLVM.h" #include "llvm/Support/MemoryBuffer.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" @@ -68,6 +68,12 @@ using namespace llvm; using namespace object; +cl::opt<bool> + llvm::AllHeaders("all-headers", + cl::desc("Display all available header information")); +static cl::alias AllHeadersShort("x", cl::desc("Alias for --all-headers"), + cl::aliasopt(AllHeaders)); + static cl::list<std::string> InputFilenames(cl::Positional, cl::desc("<input object files>"),cl::ZeroOrMore); @@ -85,10 +91,30 @@ static cl::alias DisassembleAlld("D", cl::desc("Alias for --disassemble-all"), cl::aliasopt(DisassembleAll)); +cl::opt<std::string> llvm::Demangle("demangle", + cl::desc("Demangle symbols names"), + cl::ValueOptional, cl::init("none")); + +static cl::alias DemangleShort("C", cl::desc("Alias for --demangle"), + cl::aliasopt(Demangle)); + +static cl::list<std::string> +DisassembleFunctions("df", + cl::CommaSeparated, + cl::desc("List of functions to disassemble")); +static StringSet<> DisasmFuncsSet; + cl::opt<bool> llvm::Relocations("r", cl::desc("Display the relocation entries in the file")); cl::opt<bool> +llvm::DynamicRelocations("dynamic-reloc", + cl::desc("Display the dynamic relocation entries in the file")); +static cl::alias +DynamicRelocationsd("R", cl::desc("Alias for --dynamic-reloc"), + cl::aliasopt(DynamicRelocations)); + +cl::opt<bool> llvm::SectionContents("s", cl::desc("Display the content of each section")); cl::opt<bool> @@ -182,6 +208,21 @@ static cl::alias PrivateHeadersShort("p", cl::desc("Alias for --private-headers"), cl::aliasopt(PrivateHeaders)); +cl::opt<bool> llvm::FileHeaders( + "file-headers", + cl::desc("Display the contents of the overall file header")); + +static cl::alias FileHeadersShort("f", cl::desc("Alias for --file-headers"), + cl::aliasopt(FileHeaders)); + +cl::opt<bool> + llvm::ArchiveHeaders("archive-headers", + cl::desc("Display archive header information")); + +cl::alias +ArchiveHeadersShort("a", cl::desc("Alias for --archive-headers"), + cl::aliasopt(ArchiveHeaders)); + cl::opt<bool> llvm::PrintImmHex("print-imm-hex", cl::desc("Use hex format for immediate values")); @@ -196,7 +237,7 @@ cl::opt<DIDumpType> llvm::DwarfDumpType( cl::opt<bool> PrintSource( "source", cl::desc( - "Display source inlined with disassembly. Implies disassmble object")); + "Display source inlined with disassembly. Implies disassemble object")); cl::alias PrintSourceShort("S", cl::desc("Alias for -source"), cl::aliasopt(PrintSource)); @@ -297,6 +338,11 @@ LLVM_ATTRIBUTE_NORETURN void llvm::error(Twine Message) { exit(1); } +void llvm::warn(StringRef Message) { + errs() << ToolName << ": warning: " << Message << ".\n"; + errs().flush(); +} + LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef File, Twine Message) { errs() << ToolName << ": '" << File << "': " << Message << ".\n"; @@ -396,252 +442,6 @@ bool llvm::RelocAddressLess(RelocationRef a, RelocationRef b) { return a.getOffset() < b.getOffset(); } -namespace { -class SourcePrinter { -protected: - DILineInfo OldLineInfo; - const ObjectFile *Obj = nullptr; - std::unique_ptr<symbolize::LLVMSymbolizer> Symbolizer; - // File name to file contents of source - std::unordered_map<std::string, std::unique_ptr<MemoryBuffer>> SourceCache; - // Mark the line endings of the cached source - std::unordered_map<std::string, std::vector<StringRef>> LineCache; - -private: - bool cacheSource(const std::string& File); - -public: - SourcePrinter() = default; - SourcePrinter(const ObjectFile *Obj, StringRef DefaultArch) : Obj(Obj) { - symbolize::LLVMSymbolizer::Options SymbolizerOpts( - DILineInfoSpecifier::FunctionNameKind::None, true, false, false, - DefaultArch); - Symbolizer.reset(new symbolize::LLVMSymbolizer(SymbolizerOpts)); - } - virtual ~SourcePrinter() = default; - virtual void printSourceLine(raw_ostream &OS, uint64_t Address, - StringRef Delimiter = "; "); -}; - -bool SourcePrinter::cacheSource(const std::string& File) { - auto BufferOrError = MemoryBuffer::getFile(File); - if (!BufferOrError) - return false; - // Chomp the file to get lines - size_t BufferSize = (*BufferOrError)->getBufferSize(); - const char *BufferStart = (*BufferOrError)->getBufferStart(); - for (const char *Start = BufferStart, *End = BufferStart; - End < BufferStart + BufferSize; End++) - if (*End == '\n' || End == BufferStart + BufferSize - 1 || - (*End == '\r' && *(End + 1) == '\n')) { - LineCache[File].push_back(StringRef(Start, End - Start)); - if (*End == '\r') - End++; - Start = End + 1; - } - SourceCache[File] = std::move(*BufferOrError); - return true; -} - -void SourcePrinter::printSourceLine(raw_ostream &OS, uint64_t Address, - StringRef Delimiter) { - if (!Symbolizer) - return; - DILineInfo LineInfo = DILineInfo(); - auto ExpectecLineInfo = - Symbolizer->symbolizeCode(Obj->getFileName(), Address); - if (!ExpectecLineInfo) - consumeError(ExpectecLineInfo.takeError()); - else - LineInfo = *ExpectecLineInfo; - - if ((LineInfo.FileName == "<invalid>") || OldLineInfo.Line == LineInfo.Line || - LineInfo.Line == 0) - return; - - if (PrintLines) - OS << Delimiter << LineInfo.FileName << ":" << LineInfo.Line << "\n"; - if (PrintSource) { - if (SourceCache.find(LineInfo.FileName) == SourceCache.end()) - if (!cacheSource(LineInfo.FileName)) - return; - auto FileBuffer = SourceCache.find(LineInfo.FileName); - if (FileBuffer != SourceCache.end()) { - auto LineBuffer = LineCache.find(LineInfo.FileName); - if (LineBuffer != LineCache.end()) { - if (LineInfo.Line > LineBuffer->second.size()) - return; - // Vector begins at 0, line numbers are non-zero - OS << Delimiter << LineBuffer->second[LineInfo.Line - 1].ltrim() - << "\n"; - } - } - } - OldLineInfo = LineInfo; -} - -static bool isArmElf(const ObjectFile *Obj) { - return (Obj->isELF() && - (Obj->getArch() == Triple::aarch64 || - Obj->getArch() == Triple::aarch64_be || - Obj->getArch() == Triple::arm || Obj->getArch() == Triple::armeb || - Obj->getArch() == Triple::thumb || - Obj->getArch() == Triple::thumbeb)); -} - -class PrettyPrinter { -public: - virtual ~PrettyPrinter() = default; - virtual void printInst(MCInstPrinter &IP, const MCInst *MI, - ArrayRef<uint8_t> Bytes, uint64_t Address, - raw_ostream &OS, StringRef Annot, - MCSubtargetInfo const &STI, SourcePrinter *SP) { - if (SP && (PrintSource || PrintLines)) - SP->printSourceLine(OS, Address); - if (!NoLeadingAddr) - OS << format("%8" PRIx64 ":", Address); - if (!NoShowRawInsn) { - OS << "\t"; - dumpBytes(Bytes, OS); - } - if (MI) - IP.printInst(MI, OS, "", STI); - else - OS << " <unknown>"; - } -}; -PrettyPrinter PrettyPrinterInst; -class HexagonPrettyPrinter : public PrettyPrinter { -public: - void printLead(ArrayRef<uint8_t> Bytes, uint64_t Address, - raw_ostream &OS) { - uint32_t opcode = - (Bytes[3] << 24) | (Bytes[2] << 16) | (Bytes[1] << 8) | Bytes[0]; - if (!NoLeadingAddr) - OS << format("%8" PRIx64 ":", Address); - if (!NoShowRawInsn) { - OS << "\t"; - dumpBytes(Bytes.slice(0, 4), OS); - OS << format("%08" PRIx32, opcode); - } - } - void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, - uint64_t Address, raw_ostream &OS, StringRef Annot, - MCSubtargetInfo const &STI, SourcePrinter *SP) override { - if (SP && (PrintSource || PrintLines)) - SP->printSourceLine(OS, Address, ""); - if (!MI) { - printLead(Bytes, Address, OS); - OS << " <unknown>"; - return; - } - std::string Buffer; - { - raw_string_ostream TempStream(Buffer); - IP.printInst(MI, TempStream, "", STI); - } - StringRef Contents(Buffer); - // Split off bundle attributes - auto PacketBundle = Contents.rsplit('\n'); - // Split off first instruction from the rest - auto HeadTail = PacketBundle.first.split('\n'); - auto Preamble = " { "; - auto Separator = ""; - while(!HeadTail.first.empty()) { - OS << Separator; - Separator = "\n"; - if (SP && (PrintSource || PrintLines)) - SP->printSourceLine(OS, Address, ""); - printLead(Bytes, Address, OS); - OS << Preamble; - Preamble = " "; - StringRef Inst; - auto Duplex = HeadTail.first.split('\v'); - if(!Duplex.second.empty()){ - OS << Duplex.first; - OS << "; "; - Inst = Duplex.second; - } - else - Inst = HeadTail.first; - OS << Inst; - Bytes = Bytes.slice(4); - Address += 4; - HeadTail = HeadTail.second.split('\n'); - } - OS << " } " << PacketBundle.second; - } -}; -HexagonPrettyPrinter HexagonPrettyPrinterInst; - -class AMDGCNPrettyPrinter : public PrettyPrinter { -public: - void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, - uint64_t Address, raw_ostream &OS, StringRef Annot, - MCSubtargetInfo const &STI, SourcePrinter *SP) override { - if (SP && (PrintSource || PrintLines)) - SP->printSourceLine(OS, Address); - - if (!MI) { - OS << " <unknown>"; - return; - } - - SmallString<40> InstStr; - raw_svector_ostream IS(InstStr); - - IP.printInst(MI, IS, "", STI); - - OS << left_justify(IS.str(), 60) << format("// %012" PRIX64 ": ", Address); - typedef support::ulittle32_t U32; - for (auto D : makeArrayRef(reinterpret_cast<const U32*>(Bytes.data()), - Bytes.size() / sizeof(U32))) - // D should be explicitly casted to uint32_t here as it is passed - // by format to snprintf as vararg. - OS << format("%08" PRIX32 " ", static_cast<uint32_t>(D)); - - if (!Annot.empty()) - OS << "// " << Annot; - } -}; -AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst; - -class BPFPrettyPrinter : public PrettyPrinter { -public: - void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, - uint64_t Address, raw_ostream &OS, StringRef Annot, - MCSubtargetInfo const &STI, SourcePrinter *SP) override { - if (SP && (PrintSource || PrintLines)) - SP->printSourceLine(OS, Address); - if (!NoLeadingAddr) - OS << format("%8" PRId64 ":", Address / 8); - if (!NoShowRawInsn) { - OS << "\t"; - dumpBytes(Bytes, OS); - } - if (MI) - IP.printInst(MI, OS, "", STI); - else - OS << " <unknown>"; - } -}; -BPFPrettyPrinter BPFPrettyPrinterInst; - -PrettyPrinter &selectPrettyPrinter(Triple const &Triple) { - switch(Triple.getArch()) { - default: - return PrettyPrinterInst; - case Triple::hexagon: - return HexagonPrettyPrinterInst; - case Triple::amdgcn: - return AMDGCNPrettyPrinterInst; - case Triple::bpfel: - case Triple::bpfeb: - return BPFPrettyPrinterInst; - } -} -} - template <class ELFT> static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj, const RelocationRef &RelRef, @@ -671,9 +471,11 @@ static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj, if (!StrTabOrErr) return errorToErrorCode(StrTabOrErr.takeError()); StringRef StrTab = *StrTabOrErr; - uint8_t type = RelRef.getType(); - StringRef res; int64_t addend = 0; + // If there is no Symbol associated with the relocation, we set the undef + // boolean value to 'true'. This will prevent us from calling functions that + // requires the relocation to be associated with a symbol. + bool undef = false; switch (Sec->sh_type) { default: return object_error::parse_failed; @@ -684,97 +486,41 @@ static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj, case ELF::SHT_RELA: { const Elf_Rela *ERela = Obj->getRela(Rel); addend = ERela->r_addend; + undef = ERela->getSymbol(false) == 0; break; } } - symbol_iterator SI = RelRef.getSymbol(); - const Elf_Sym *symb = Obj->getSymbol(SI->getRawDataRefImpl()); StringRef Target; - if (symb->getType() == ELF::STT_SECTION) { - Expected<section_iterator> SymSI = SI->getSection(); - if (!SymSI) - return errorToErrorCode(SymSI.takeError()); - const Elf_Shdr *SymSec = Obj->getSection((*SymSI)->getRawDataRefImpl()); - auto SecName = EF.getSectionName(SymSec); - if (!SecName) - return errorToErrorCode(SecName.takeError()); - Target = *SecName; - } else { - Expected<StringRef> SymName = symb->getName(StrTab); - if (!SymName) - return errorToErrorCode(SymName.takeError()); - Target = *SymName; - } - switch (EF.getHeader()->e_machine) { - case ELF::EM_X86_64: - switch (type) { - case ELF::R_X86_64_PC8: - case ELF::R_X86_64_PC16: - case ELF::R_X86_64_PC32: { - std::string fmtbuf; - raw_string_ostream fmt(fmtbuf); - fmt << Target << (addend < 0 ? "" : "+") << addend << "-P"; - fmt.flush(); - Result.append(fmtbuf.begin(), fmtbuf.end()); - } break; - case ELF::R_X86_64_8: - case ELF::R_X86_64_16: - case ELF::R_X86_64_32: - case ELF::R_X86_64_32S: - case ELF::R_X86_64_64: { - std::string fmtbuf; - raw_string_ostream fmt(fmtbuf); - fmt << Target << (addend < 0 ? "" : "+") << addend; - fmt.flush(); - Result.append(fmtbuf.begin(), fmtbuf.end()); - } break; - default: - res = "Unknown"; - } - break; - case ELF::EM_LANAI: - case ELF::EM_AVR: - case ELF::EM_AARCH64: { - std::string fmtbuf; - raw_string_ostream fmt(fmtbuf); - fmt << Target; - if (addend != 0) - fmt << (addend < 0 ? "" : "+") << addend; - fmt.flush(); - Result.append(fmtbuf.begin(), fmtbuf.end()); - break; - } - case ELF::EM_386: - case ELF::EM_IAMCU: - case ELF::EM_ARM: - case ELF::EM_HEXAGON: - case ELF::EM_MIPS: - case ELF::EM_BPF: - case ELF::EM_RISCV: - res = Target; - break; - case ELF::EM_WEBASSEMBLY: - switch (type) { - case ELF::R_WEBASSEMBLY_DATA: { - std::string fmtbuf; - raw_string_ostream fmt(fmtbuf); - fmt << Target << (addend < 0 ? "" : "+") << addend; - fmt.flush(); - Result.append(fmtbuf.begin(), fmtbuf.end()); - break; - } - case ELF::R_WEBASSEMBLY_FUNCTION: - res = Target; - break; - default: - res = "Unknown"; + if (!undef) { + symbol_iterator SI = RelRef.getSymbol(); + const Elf_Sym *symb = Obj->getSymbol(SI->getRawDataRefImpl()); + if (symb->getType() == ELF::STT_SECTION) { + Expected<section_iterator> SymSI = SI->getSection(); + if (!SymSI) + return errorToErrorCode(SymSI.takeError()); + const Elf_Shdr *SymSec = Obj->getSection((*SymSI)->getRawDataRefImpl()); + auto SecName = EF.getSectionName(SymSec); + if (!SecName) + return errorToErrorCode(SecName.takeError()); + Target = *SecName; + } else { + Expected<StringRef> SymName = symb->getName(StrTab); + if (!SymName) + return errorToErrorCode(SymName.takeError()); + Target = *SymName; } - break; - default: - res = "Unknown"; - } - if (Result.empty()) - Result.append(res.begin(), res.end()); + } else + Target = "*ABS*"; + + // Default scheme is to print Target, as well as "+ <addend>" for nonzero + // addend. Should be acceptable for all normal purposes. + std::string fmtbuf; + raw_string_ostream fmt(fmtbuf); + fmt << Target; + if (addend != 0) + fmt << (addend < 0 ? "" : "+") << addend; + fmt.flush(); + Result.append(fmtbuf.begin(), fmtbuf.end()); return std::error_code(); } @@ -887,9 +633,21 @@ static std::error_code getRelocationValueString(const WasmObjectFile *Obj, const RelocationRef &RelRef, SmallVectorImpl<char> &Result) { const wasm::WasmRelocation& Rel = Obj->getWasmRelocation(RelRef); + symbol_iterator SI = RelRef.getSymbol(); std::string fmtbuf; raw_string_ostream fmt(fmtbuf); - fmt << Rel.Index << (Rel.Addend < 0 ? "" : "+") << Rel.Addend; + if (SI == Obj->symbol_end()) { + // Not all wasm relocations have symbols associated with them. + // In particular R_WEBASSEMBLY_TYPE_INDEX_LEB. + fmt << Rel.Index; + } else { + Expected<StringRef> SymNameOrErr = SI->getName(); + if (!SymNameOrErr) + return errorToErrorCode(SymNameOrErr.takeError()); + StringRef SymName = *SymNameOrErr; + Result.append(SymName.begin(), SymName.end()); + } + fmt << (Rel.Addend < 0 ? "" : "+") << Rel.Addend; fmt.flush(); Result.append(fmtbuf.begin(), fmtbuf.end()); return std::error_code(); @@ -1087,7 +845,7 @@ static std::error_code getRelocationValueString(const RelocationRef &Rel, llvm_unreachable("unknown object file format"); } -/// @brief Indicates whether this relocation should hidden when listing +/// Indicates whether this relocation should hidden when listing /// relocations, usually because it is the trailing part of a multipart /// relocation that will be printed as part of the leading relocation. static bool getHidden(RelocationRef RelRef) { @@ -1120,6 +878,304 @@ static bool getHidden(RelocationRef RelRef) { return false; } +namespace { +class SourcePrinter { +protected: + DILineInfo OldLineInfo; + const ObjectFile *Obj = nullptr; + std::unique_ptr<symbolize::LLVMSymbolizer> Symbolizer; + // File name to file contents of source + std::unordered_map<std::string, std::unique_ptr<MemoryBuffer>> SourceCache; + // Mark the line endings of the cached source + std::unordered_map<std::string, std::vector<StringRef>> LineCache; + +private: + bool cacheSource(const DILineInfo& LineInfoFile); + +public: + SourcePrinter() = default; + SourcePrinter(const ObjectFile *Obj, StringRef DefaultArch) : Obj(Obj) { + symbolize::LLVMSymbolizer::Options SymbolizerOpts( + DILineInfoSpecifier::FunctionNameKind::None, true, false, false, + DefaultArch); + Symbolizer.reset(new symbolize::LLVMSymbolizer(SymbolizerOpts)); + } + virtual ~SourcePrinter() = default; + virtual void printSourceLine(raw_ostream &OS, uint64_t Address, + StringRef Delimiter = "; "); +}; + +bool SourcePrinter::cacheSource(const DILineInfo &LineInfo) { + std::unique_ptr<MemoryBuffer> Buffer; + if (LineInfo.Source) { + Buffer = MemoryBuffer::getMemBuffer(*LineInfo.Source); + } else { + auto BufferOrError = MemoryBuffer::getFile(LineInfo.FileName); + if (!BufferOrError) + return false; + Buffer = std::move(*BufferOrError); + } + // Chomp the file to get lines + size_t BufferSize = Buffer->getBufferSize(); + const char *BufferStart = Buffer->getBufferStart(); + for (const char *Start = BufferStart, *End = BufferStart; + End < BufferStart + BufferSize; End++) + if (*End == '\n' || End == BufferStart + BufferSize - 1 || + (*End == '\r' && *(End + 1) == '\n')) { + LineCache[LineInfo.FileName].push_back(StringRef(Start, End - Start)); + if (*End == '\r') + End++; + Start = End + 1; + } + SourceCache[LineInfo.FileName] = std::move(Buffer); + return true; +} + +void SourcePrinter::printSourceLine(raw_ostream &OS, uint64_t Address, + StringRef Delimiter) { + if (!Symbolizer) + return; + DILineInfo LineInfo = DILineInfo(); + auto ExpectecLineInfo = + Symbolizer->symbolizeCode(Obj->getFileName(), Address); + if (!ExpectecLineInfo) + consumeError(ExpectecLineInfo.takeError()); + else + LineInfo = *ExpectecLineInfo; + + if ((LineInfo.FileName == "<invalid>") || OldLineInfo.Line == LineInfo.Line || + LineInfo.Line == 0) + return; + + if (PrintLines) + OS << Delimiter << LineInfo.FileName << ":" << LineInfo.Line << "\n"; + if (PrintSource) { + if (SourceCache.find(LineInfo.FileName) == SourceCache.end()) + if (!cacheSource(LineInfo)) + return; + auto FileBuffer = SourceCache.find(LineInfo.FileName); + if (FileBuffer != SourceCache.end()) { + auto LineBuffer = LineCache.find(LineInfo.FileName); + if (LineBuffer != LineCache.end()) { + if (LineInfo.Line > LineBuffer->second.size()) + return; + // Vector begins at 0, line numbers are non-zero + OS << Delimiter << LineBuffer->second[LineInfo.Line - 1].ltrim() + << "\n"; + } + } + } + OldLineInfo = LineInfo; +} + +static bool isArmElf(const ObjectFile *Obj) { + return (Obj->isELF() && + (Obj->getArch() == Triple::aarch64 || + Obj->getArch() == Triple::aarch64_be || + Obj->getArch() == Triple::arm || Obj->getArch() == Triple::armeb || + Obj->getArch() == Triple::thumb || + Obj->getArch() == Triple::thumbeb)); +} + +class PrettyPrinter { +public: + virtual ~PrettyPrinter() = default; + virtual void printInst(MCInstPrinter &IP, const MCInst *MI, + ArrayRef<uint8_t> Bytes, uint64_t Address, + raw_ostream &OS, StringRef Annot, + MCSubtargetInfo const &STI, SourcePrinter *SP, + std::vector<RelocationRef> *Rels = nullptr) { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address); + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address); + if (!NoShowRawInsn) { + OS << "\t"; + dumpBytes(Bytes, OS); + } + if (MI) + IP.printInst(MI, OS, "", STI); + else + OS << " <unknown>"; + } +}; +PrettyPrinter PrettyPrinterInst; +class HexagonPrettyPrinter : public PrettyPrinter { +public: + void printLead(ArrayRef<uint8_t> Bytes, uint64_t Address, + raw_ostream &OS) { + uint32_t opcode = + (Bytes[3] << 24) | (Bytes[2] << 16) | (Bytes[1] << 8) | Bytes[0]; + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address); + if (!NoShowRawInsn) { + OS << "\t"; + dumpBytes(Bytes.slice(0, 4), OS); + OS << format("%08" PRIx32, opcode); + } + } + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + uint64_t Address, raw_ostream &OS, StringRef Annot, + MCSubtargetInfo const &STI, SourcePrinter *SP, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ""); + if (!MI) { + printLead(Bytes, Address, OS); + OS << " <unknown>"; + return; + } + std::string Buffer; + { + raw_string_ostream TempStream(Buffer); + IP.printInst(MI, TempStream, "", STI); + } + StringRef Contents(Buffer); + // Split off bundle attributes + auto PacketBundle = Contents.rsplit('\n'); + // Split off first instruction from the rest + auto HeadTail = PacketBundle.first.split('\n'); + auto Preamble = " { "; + auto Separator = ""; + StringRef Fmt = "\t\t\t%08" PRIx64 ": "; + std::vector<RelocationRef>::const_iterator rel_cur = Rels->begin(); + std::vector<RelocationRef>::const_iterator rel_end = Rels->end(); + + // Hexagon's packets require relocations to be inline rather than + // clustered at the end of the packet. + auto PrintReloc = [&]() -> void { + while ((rel_cur != rel_end) && (rel_cur->getOffset() <= Address)) { + if (rel_cur->getOffset() == Address) { + SmallString<16> name; + SmallString<32> val; + rel_cur->getTypeName(name); + error(getRelocationValueString(*rel_cur, val)); + OS << Separator << format(Fmt.data(), Address) << name << "\t" << val + << "\n"; + return; + } + rel_cur++; + } + }; + + while(!HeadTail.first.empty()) { + OS << Separator; + Separator = "\n"; + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address, ""); + printLead(Bytes, Address, OS); + OS << Preamble; + Preamble = " "; + StringRef Inst; + auto Duplex = HeadTail.first.split('\v'); + if(!Duplex.second.empty()){ + OS << Duplex.first; + OS << "; "; + Inst = Duplex.second; + } + else + Inst = HeadTail.first; + OS << Inst; + HeadTail = HeadTail.second.split('\n'); + if (HeadTail.first.empty()) + OS << " } " << PacketBundle.second; + PrintReloc(); + Bytes = Bytes.slice(4); + Address += 4; + } + } +}; +HexagonPrettyPrinter HexagonPrettyPrinterInst; + +class AMDGCNPrettyPrinter : public PrettyPrinter { +public: + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + uint64_t Address, raw_ostream &OS, StringRef Annot, + MCSubtargetInfo const &STI, SourcePrinter *SP, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address); + + typedef support::ulittle32_t U32; + + if (MI) { + SmallString<40> InstStr; + raw_svector_ostream IS(InstStr); + + IP.printInst(MI, IS, "", STI); + + OS << left_justify(IS.str(), 60); + } else { + // an unrecognized encoding - this is probably data so represent it + // using the .long directive, or .byte directive if fewer than 4 bytes + // remaining + if (Bytes.size() >= 4) { + OS << format("\t.long 0x%08" PRIx32 " ", + static_cast<uint32_t>(*reinterpret_cast<const U32*>(Bytes.data()))); + OS.indent(42); + } else { + OS << format("\t.byte 0x%02" PRIx8, Bytes[0]); + for (unsigned int i = 1; i < Bytes.size(); i++) + OS << format(", 0x%02" PRIx8, Bytes[i]); + OS.indent(55 - (6 * Bytes.size())); + } + } + + OS << format("// %012" PRIX64 ": ", Address); + if (Bytes.size() >=4) { + for (auto D : makeArrayRef(reinterpret_cast<const U32*>(Bytes.data()), + Bytes.size() / sizeof(U32))) + // D should be explicitly casted to uint32_t here as it is passed + // by format to snprintf as vararg. + OS << format("%08" PRIX32 " ", static_cast<uint32_t>(D)); + } else { + for (unsigned int i = 0; i < Bytes.size(); i++) + OS << format("%02" PRIX8 " ", Bytes[i]); + } + + if (!Annot.empty()) + OS << "// " << Annot; + } +}; +AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst; + +class BPFPrettyPrinter : public PrettyPrinter { +public: + void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, + uint64_t Address, raw_ostream &OS, StringRef Annot, + MCSubtargetInfo const &STI, SourcePrinter *SP, + std::vector<RelocationRef> *Rels) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address); + if (!NoLeadingAddr) + OS << format("%8" PRId64 ":", Address / 8); + if (!NoShowRawInsn) { + OS << "\t"; + dumpBytes(Bytes, OS); + } + if (MI) + IP.printInst(MI, OS, "", STI); + else + OS << " <unknown>"; + } +}; +BPFPrettyPrinter BPFPrettyPrinterInst; + +PrettyPrinter &selectPrettyPrinter(Triple const &Triple) { + switch(Triple.getArch()) { + default: + return PrettyPrinterInst; + case Triple::hexagon: + return HexagonPrettyPrinterInst; + case Triple::amdgcn: + return AMDGCNPrettyPrinterInst; + case Triple::bpfel: + case Triple::bpfeb: + return BPFPrettyPrinterInst; + } +} +} + static uint8_t getElfSymbolType(const ObjectFile *Obj, const SymbolRef &Sym) { assert(Obj->isELF()); if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj)) @@ -1254,6 +1310,7 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { // Create a mapping from virtual address to symbol name. This is used to // pretty print the symbols while disassembling. std::map<SectionRef, SectionSymbolsTy> AllSymbols; + SectionSymbolsTy AbsoluteSymbols; for (const SymbolRef &Symbol : Obj->symbols()) { Expected<uint64_t> AddressOrErr = Symbol.getAddress(); if (!AddressOrErr) @@ -1269,15 +1326,17 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { Expected<section_iterator> SectionOrErr = Symbol.getSection(); if (!SectionOrErr) report_error(Obj->getFileName(), SectionOrErr.takeError()); - section_iterator SecI = *SectionOrErr; - if (SecI == Obj->section_end()) - continue; uint8_t SymbolType = ELF::STT_NOTYPE; if (Obj->isELF()) SymbolType = getElfSymbolType(Obj, Symbol); - AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType); + section_iterator SecI = *SectionOrErr; + if (SecI != Obj->section_end()) + AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType); + else + AbsoluteSymbols.emplace_back(Address, *Name, SymbolType); + } if (AllSymbols.empty() && Obj->isELF()) @@ -1313,6 +1372,8 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { if (Sec != SectionAddresses.end()) AllSymbols[Sec->second].emplace_back(VA, Name, ELF::STT_NOTYPE); + else + AbsoluteSymbols.emplace_back(VA, Name, ELF::STT_NOTYPE); } } @@ -1320,6 +1381,7 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { // a symbol near an address. for (std::pair<const SectionRef, SectionSymbolsTy> &SecSyms : AllSymbols) array_pod_sort(SecSyms.second.begin(), SecSyms.second.end()); + array_pod_sort(AbsoluteSymbols.begin(), AbsoluteSymbols.end()); for (const SectionRef &Section : ToolSectionFilter(*Obj)) { if (!DisassembleAll && (!Section.isText() || Section.isVirtual())) @@ -1349,8 +1411,8 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { } } - std::sort(DataMappingSymsAddr.begin(), DataMappingSymsAddr.end()); - std::sort(TextMappingSymsAddr.begin(), TextMappingSymsAddr.end()); + llvm::sort(DataMappingSymsAddr.begin(), DataMappingSymsAddr.end()); + llvm::sort(TextMappingSymsAddr.begin(), TextMappingSymsAddr.end()); if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) { // AMDGPU disassembler uses symbolizer for printing labels @@ -1375,30 +1437,22 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { } // Sort relocations by address. - std::sort(Rels.begin(), Rels.end(), RelocAddressLess); + llvm::sort(Rels.begin(), Rels.end(), RelocAddressLess); StringRef SegmentName = ""; if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj)) { DataRefImpl DR = Section.getRawDataRefImpl(); SegmentName = MachO->getSectionFinalSegmentName(DR); } - StringRef name; - error(Section.getName(name)); - - if ((SectionAddr <= StopAddress) && - (SectionAddr + SectSize) >= StartAddress) { - outs() << "Disassembly of section "; - if (!SegmentName.empty()) - outs() << SegmentName << ","; - outs() << name << ':'; - } + StringRef SectionName; + error(Section.getName(SectionName)); // If the section has no symbol at the start, just insert a dummy one. if (Symbols.empty() || std::get<0>(Symbols[0]) != 0) { - Symbols.insert(Symbols.begin(), - std::make_tuple(SectionAddr, name, Section.isText() - ? ELF::STT_FUNC - : ELF::STT_OBJECT)); + Symbols.insert( + Symbols.begin(), + std::make_tuple(SectionAddr, SectionName, + Section.isText() ? ELF::STT_FUNC : ELF::STT_OBJECT)); } SmallString<40> Comments; @@ -1411,6 +1465,7 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { uint64_t Size; uint64_t Index; + bool PrintedSection = false; std::vector<RelocationRef>::const_iterator rel_cur = Rels.begin(); std::vector<RelocationRef>::const_iterator rel_end = Rels.end(); @@ -1435,13 +1490,24 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { continue; } + /// Skip if user requested specific symbols and this is not in the list + if (!DisasmFuncsSet.empty() && + !DisasmFuncsSet.count(std::get<1>(Symbols[si]))) + continue; + + if (!PrintedSection) { + PrintedSection = true; + outs() << "Disassembly of section "; + if (!SegmentName.empty()) + outs() << SegmentName << ","; + outs() << SectionName << ':'; + } + // Stop disassembly at the stop address specified if (End + SectionAddr > StopAddress) End = StopAddress - SectionAddr; if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) { - // make size 4 bytes folded - End = Start + ((End - Start) & ~0x3ull); if (std::get<2>(Symbols[si]) == ELF::STT_AMDGPU_HSA_KERNEL) { // skip amd_kernel_code_t at the begining of kernel symbol (256 bytes) Start += 256; @@ -1458,7 +1524,32 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { } } - outs() << '\n' << std::get<1>(Symbols[si]) << ":\n"; + auto PrintSymbol = [](StringRef Name) { + outs() << '\n' << Name << ":\n"; + }; + StringRef SymbolName = std::get<1>(Symbols[si]); + if (Demangle.getValue() == "" || Demangle.getValue() == "itanium") { + char *DemangledSymbol = nullptr; + size_t Size = 0; + int Status; + DemangledSymbol = + itaniumDemangle(SymbolName.data(), DemangledSymbol, &Size, &Status); + if (Status == 0) + PrintSymbol(StringRef(DemangledSymbol)); + else + PrintSymbol(SymbolName); + + if (Size != 0) + free(DemangledSymbol); + } else + PrintSymbol(SymbolName); + + // Don't print raw contents of a virtual section. A virtual section + // doesn't have any contents in the file. + if (Section.isVirtual()) { + outs() << "...\n"; + continue; + } #ifndef NDEBUG raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); @@ -1560,7 +1651,7 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { } Byte = Bytes.slice(Index)[0]; outs() << format(" %02x", Byte); - AsciiData[NumBytes] = isprint(Byte) ? Byte : '.'; + AsciiData[NumBytes] = isPrint(Byte) ? Byte : '.'; uint8_t IndentOffset = 0; NumBytes++; @@ -1594,7 +1685,7 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { PIP.printInst(*IP, Disassembled ? &Inst : nullptr, Bytes.slice(Index, Size), SectionAddr + Index, outs(), "", - *STI, &SP); + *STI, &SP, &Rels); outs() << CommentStream.str(); Comments.clear(); @@ -1623,55 +1714,65 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { --SectionAddress; TargetSectionSymbols = &AllSymbols[SectionAddress->second]; } else { - TargetSectionSymbols = nullptr; + TargetSectionSymbols = &AbsoluteSymbols; } } // Find the first symbol in the section whose offset is less than - // or equal to the target. - if (TargetSectionSymbols) { - auto TargetSym = std::upper_bound( - TargetSectionSymbols->begin(), TargetSectionSymbols->end(), + // or equal to the target. If there isn't a section that contains + // the target, find the nearest preceding absolute symbol. + auto TargetSym = std::upper_bound( + TargetSectionSymbols->begin(), TargetSectionSymbols->end(), + Target, [](uint64_t LHS, + const std::tuple<uint64_t, StringRef, uint8_t> &RHS) { + return LHS < std::get<0>(RHS); + }); + if (TargetSym == TargetSectionSymbols->begin()) { + TargetSectionSymbols = &AbsoluteSymbols; + TargetSym = std::upper_bound( + AbsoluteSymbols.begin(), AbsoluteSymbols.end(), Target, [](uint64_t LHS, const std::tuple<uint64_t, StringRef, uint8_t> &RHS) { - return LHS < std::get<0>(RHS); - }); - if (TargetSym != TargetSectionSymbols->begin()) { - --TargetSym; - uint64_t TargetAddress = std::get<0>(*TargetSym); - StringRef TargetName = std::get<1>(*TargetSym); - outs() << " <" << TargetName; - uint64_t Disp = Target - TargetAddress; - if (Disp) - outs() << "+0x" << Twine::utohexstr(Disp); - outs() << '>'; - } + return LHS < std::get<0>(RHS); + }); + } + if (TargetSym != TargetSectionSymbols->begin()) { + --TargetSym; + uint64_t TargetAddress = std::get<0>(*TargetSym); + StringRef TargetName = std::get<1>(*TargetSym); + outs() << " <" << TargetName; + uint64_t Disp = Target - TargetAddress; + if (Disp) + outs() << "+0x" << Twine::utohexstr(Disp); + outs() << '>'; } } } outs() << "\n"; - // Print relocation for instruction. - while (rel_cur != rel_end) { - bool hidden = getHidden(*rel_cur); - uint64_t addr = rel_cur->getOffset(); - SmallString<16> name; - SmallString<32> val; + // Hexagon does this in pretty printer + if (Obj->getArch() != Triple::hexagon) + // Print relocation for instruction. + while (rel_cur != rel_end) { + bool hidden = getHidden(*rel_cur); + uint64_t addr = rel_cur->getOffset(); + SmallString<16> name; + SmallString<32> val; + + // If this relocation is hidden, skip it. + if (hidden || ((SectionAddr + addr) < StartAddress)) { + ++rel_cur; + continue; + } - // If this relocation is hidden, skip it. - if (hidden || ((SectionAddr + addr) < StartAddress)) { + // Stop when rel_cur's address is past the current instruction. + if (addr >= Index + Size) break; + rel_cur->getTypeName(name); + error(getRelocationValueString(*rel_cur, val)); + outs() << format(Fmt.data(), SectionAddr + addr) << name + << "\t" << val << "\n"; ++rel_cur; - continue; } - - // Stop when rel_cur's address is past the current instruction. - if (addr >= Index + Size) break; - rel_cur->getTypeName(name); - error(getRelocationValueString(*rel_cur, val)); - outs() << format(Fmt.data(), SectionAddr + addr) << name - << "\t" << val << "\n"; - ++rel_cur; - } } } } @@ -1707,10 +1808,44 @@ void llvm::PrintRelocations(const ObjectFile *Obj) { } } +void llvm::PrintDynamicRelocations(const ObjectFile *Obj) { + + // For the moment, this option is for ELF only + if (!Obj->isELF()) + return; + + const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj); + + if (!Elf || Elf->getEType() != ELF::ET_DYN) { + error("not a dynamic object"); + return; + } + + StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 : "%08" PRIx64; + + std::vector<SectionRef> DynRelSec = Obj->dynamic_relocation_sections(); + if (DynRelSec.empty()) + return; + + outs() << "DYNAMIC RELOCATION RECORDS\n"; + for (const SectionRef &Section : DynRelSec) { + if (Section.relocation_begin() == Section.relocation_end()) + continue; + for (const RelocationRef &Reloc : Section.relocations()) { + uint64_t address = Reloc.getOffset(); + SmallString<32> relocname; + SmallString<32> valuestr; + Reloc.getTypeName(relocname); + error(getRelocationValueString(Reloc, valuestr)); + outs() << format(Fmt.data(), address) << " " << relocname << " " + << valuestr << "\n"; + } + } +} + void llvm::PrintSectionHeaders(const ObjectFile *Obj) { outs() << "Sections:\n" "Idx Name Size Address Type\n"; - unsigned i = 0; for (const SectionRef &Section : ToolSectionFilter(*Obj)) { StringRef Name; error(Section.getName(Name)); @@ -1721,9 +1856,9 @@ void llvm::PrintSectionHeaders(const ObjectFile *Obj) { bool BSS = Section.isBSS(); 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; + outs() << format("%3d %-13s %08" PRIx64 " %016" PRIx64 " %s\n", + (unsigned)Section.getIndex(), Name.str().c_str(), Size, + Address, Type.c_str()); } } @@ -1764,7 +1899,7 @@ void llvm::PrintSectionContents(const ObjectFile *Obj) { // 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)) + if (isPrint(static_cast<unsigned char>(Contents[addr + i]) & 0xFF)) outs() << Contents[addr + i]; else outs() << "."; @@ -2018,8 +2153,10 @@ static void printFaultMaps(const ObjectFile *Obj) { } static void printPrivateFileHeaders(const ObjectFile *o, bool onlyFirst) { - if (o->isELF()) - return printELFFileHeader(o); + if (o->isELF()) { + printELFFileHeader(o); + return printELFDynamicSection(o); + } if (o->isCOFF()) return printCOFFFileHeader(o); if (o->isWasm()) @@ -2033,7 +2170,86 @@ static void printPrivateFileHeaders(const ObjectFile *o, bool onlyFirst) { report_error(o->getFileName(), "Invalid/Unsupported object file format"); } -static void DumpObject(ObjectFile *o, const Archive *a = nullptr) { +static void printFileHeaders(const ObjectFile *o) { + if (!o->isELF() && !o->isCOFF()) + report_error(o->getFileName(), "Invalid/Unsupported object file format"); + + Triple::ArchType AT = o->getArch(); + outs() << "architecture: " << Triple::getArchTypeName(AT) << "\n"; + Expected<uint64_t> StartAddrOrErr = o->getStartAddress(); + if (!StartAddrOrErr) + report_error(o->getFileName(), StartAddrOrErr.takeError()); + outs() << "start address: " + << format("0x%0*x", o->getBytesInAddress(), StartAddrOrErr.get()) + << "\n"; +} + +static void printArchiveChild(StringRef Filename, const Archive::Child &C) { + Expected<sys::fs::perms> ModeOrErr = C.getAccessMode(); + if (!ModeOrErr) { + errs() << "ill-formed archive entry.\n"; + consumeError(ModeOrErr.takeError()); + return; + } + sys::fs::perms Mode = ModeOrErr.get(); + outs() << ((Mode & sys::fs::owner_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::owner_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::owner_exe) ? "x" : "-"); + outs() << ((Mode & sys::fs::group_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::group_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::group_exe) ? "x" : "-"); + outs() << ((Mode & sys::fs::others_read) ? "r" : "-"); + outs() << ((Mode & sys::fs::others_write) ? "w" : "-"); + outs() << ((Mode & sys::fs::others_exe) ? "x" : "-"); + + outs() << " "; + + Expected<unsigned> UIDOrErr = C.getUID(); + if (!UIDOrErr) + report_error(Filename, UIDOrErr.takeError()); + unsigned UID = UIDOrErr.get(); + outs() << format("%d/", UID); + + Expected<unsigned> GIDOrErr = C.getGID(); + if (!GIDOrErr) + report_error(Filename, GIDOrErr.takeError()); + unsigned GID = GIDOrErr.get(); + outs() << format("%-d ", GID); + + Expected<uint64_t> Size = C.getRawSize(); + if (!Size) + report_error(Filename, Size.takeError()); + outs() << format("%6" PRId64, Size.get()) << " "; + + StringRef RawLastModified = C.getRawLastModified(); + unsigned Seconds; + if (RawLastModified.getAsInteger(10, Seconds)) + outs() << "(date: \"" << RawLastModified + << "\" contains non-decimal chars) "; + else { + // Since ctime(3) returns a 26 character string of the form: + // "Sun Sep 16 01:03:52 1973\n\0" + // just print 24 characters. + time_t t = Seconds; + outs() << format("%.24s ", ctime(&t)); + } + + StringRef Name = ""; + Expected<StringRef> NameOrErr = C.getName(); + if (!NameOrErr) { + consumeError(NameOrErr.takeError()); + Expected<StringRef> RawNameOrErr = C.getRawName(); + if (!RawNameOrErr) + report_error(Filename, NameOrErr.takeError()); + Name = RawNameOrErr.get(); + } else { + Name = NameOrErr.get(); + } + outs() << Name << "\n"; +} + +static void DumpObject(ObjectFile *o, const Archive *a = nullptr, + const Archive::Child *c = nullptr) { StringRef ArchiveName = a != nullptr ? a->getFileName() : ""; // Avoid other output when using a raw option. if (!RawClangAST) { @@ -2045,10 +2261,14 @@ static void DumpObject(ObjectFile *o, const Archive *a = nullptr) { outs() << ":\tfile format " << o->getFileFormatName() << "\n\n"; } + if (ArchiveHeaders && !MachOOpt) + printArchiveChild(a->getFileName(), *c); if (Disassemble) DisassembleObject(o, Relocations); if (Relocations && !Disassemble) PrintRelocations(o); + if (DynamicRelocations) + PrintDynamicRelocations(o); if (SectionHeaders) PrintSectionHeaders(o); if (SectionContents) @@ -2059,6 +2279,8 @@ static void DumpObject(ObjectFile *o, const Archive *a = nullptr) { PrintUnwindInfo(o); if (PrivateHeaders || FirstPrivateHeader) printPrivateFileHeaders(o, FirstPrivateHeader); + if (FileHeaders) + printFileHeaders(o); if (ExportsTrie) printExportsTrie(o); if (Rebase) @@ -2082,7 +2304,8 @@ static void DumpObject(ObjectFile *o, const Archive *a = nullptr) { } } -static void DumpObject(const COFFImportFile *I, const Archive *A) { +static void DumpObject(const COFFImportFile *I, const Archive *A, + const Archive::Child *C = nullptr) { StringRef ArchiveName = A ? A->getFileName() : ""; // Avoid other output when using a raw option. @@ -2092,11 +2315,13 @@ static void DumpObject(const COFFImportFile *I, const Archive *A) { << ":\tfile format COFF-import-file" << "\n\n"; + if (ArchiveHeaders && !MachOOpt) + printArchiveChild(A->getFileName(), *C); if (SymbolTable) printCOFFSymbolTable(I); } -/// @brief Dump each object file in \a a; +/// Dump each object file in \a a; static void DumpArchive(const Archive *a) { Error Err = Error::success(); for (auto &C : a->children(Err)) { @@ -2107,9 +2332,9 @@ static void DumpArchive(const Archive *a) { continue; } if (ObjectFile *o = dyn_cast<ObjectFile>(&*ChildOrErr.get())) - DumpObject(o, a); + DumpObject(o, a, &C); else if (COFFImportFile *I = dyn_cast<COFFImportFile>(&*ChildOrErr.get())) - DumpObject(I, a); + DumpObject(I, a, &C); else report_error(a->getFileName(), object_error::invalid_file_type); } @@ -2117,7 +2342,7 @@ static void DumpArchive(const Archive *a) { report_error(a->getFileName(), std::move(Err)); } -/// @brief Open file and figure out how to dump it. +/// Open file and figure out how to dump it. static void DumpInput(StringRef file) { // If we are using the Mach-O specific object file parser, then let it parse @@ -2143,10 +2368,7 @@ static void DumpInput(StringRef file) { } int main(int argc, char **argv) { - // Print a stack trace if we signal out. - sys::PrintStackTraceOnErrorSignal(argv[0]); - PrettyStackTraceProgram X(argc, argv); - llvm_shutdown_obj Y; // Call llvm_shutdown() on exit. + InitLLVM X(argc, argv); // Initialize targets and assembly printers/parsers. llvm::InitializeAllTargetInfos(); @@ -2165,15 +2387,25 @@ int main(int argc, char **argv) { if (InputFilenames.size() == 0) InputFilenames.push_back("a.out"); + if (AllHeaders) + PrivateHeaders = Relocations = SectionHeaders = SymbolTable = true; + if (DisassembleAll || PrintSource || PrintLines) Disassemble = true; + + if (Demangle.getValue() != "none" && Demangle.getValue() != "" && + Demangle.getValue() != "itanium") + warn("Unsupported demangling style"); + if (!Disassemble && !Relocations + && !DynamicRelocations && !SectionHeaders && !SectionContents && !SymbolTable && !UnwindInfo && !PrivateHeaders + && !FileHeaders && !FirstPrivateHeader && !ExportsTrie && !Rebase @@ -2182,7 +2414,7 @@ int main(int argc, char **argv) { && !WeakBind && !RawClangAST && !(UniversalHeaders && MachOOpt) - && !(ArchiveHeaders && MachOOpt) + && !ArchiveHeaders && !(IndirectSymbols && MachOOpt) && !(DataInCode && MachOOpt) && !(LinkOptHints && MachOOpt) @@ -2197,6 +2429,9 @@ int main(int argc, char **argv) { return 2; } + DisasmFuncsSet.insert(DisassembleFunctions.begin(), + DisassembleFunctions.end()); + llvm::for_each(InputFilenames, DumpInput); return EXIT_SUCCESS; diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h index 2fcd506884b1..b2eb6e9d7771 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h @@ -30,13 +30,16 @@ namespace object { extern cl::opt<std::string> TripleName; extern cl::opt<std::string> ArchName; extern cl::opt<std::string> MCPU; +extern cl::opt<std::string> Demangle; extern cl::list<std::string> MAttrs; extern cl::list<std::string> FilterSections; +extern cl::opt<bool> AllHeaders; extern cl::opt<bool> Disassemble; extern cl::opt<bool> DisassembleAll; extern cl::opt<bool> NoShowRawInsn; extern cl::opt<bool> NoLeadingAddr; extern cl::opt<bool> PrivateHeaders; +extern cl::opt<bool> FileHeaders; extern cl::opt<bool> FirstPrivateHeader; extern cl::opt<bool> ExportsTrie; extern cl::opt<bool> Rebase; @@ -56,6 +59,7 @@ extern cl::opt<bool> ObjcMetaData; extern cl::opt<std::string> DisSymName; extern cl::opt<bool> NonVerbose; extern cl::opt<bool> Relocations; +extern cl::opt<bool> DynamicRelocations; extern cl::opt<bool> SectionHeaders; extern cl::opt<bool> SectionContents; extern cl::opt<bool> SymbolTable; @@ -75,6 +79,7 @@ void printMachOBindTable(object::MachOObjectFile* o); void printMachOLazyBindTable(object::MachOObjectFile* o); void printMachOWeakBindTable(object::MachOObjectFile* o); void printELFFileHeader(const object::ObjectFile *o); +void printELFDynamicSection(const object::ObjectFile *Obj); void printCOFFFileHeader(const object::ObjectFile *o); void printCOFFSymbolTable(const object::COFFImportFile *i); void printCOFFSymbolTable(const object::COFFObjectFile *o); @@ -88,10 +93,12 @@ void printLazyBindTable(object::ObjectFile *o); void printWeakBindTable(object::ObjectFile *o); void printRawClangAST(const object::ObjectFile *o); void PrintRelocations(const object::ObjectFile *o); +void PrintDynamicRelocations(const object::ObjectFile *o); void PrintSectionHeaders(const object::ObjectFile *o); void PrintSectionContents(const object::ObjectFile *o); void PrintSymbolTable(const object::ObjectFile *o, StringRef ArchiveName, StringRef ArchitectureName = StringRef()); +void warn(StringRef Message); LLVM_ATTRIBUTE_NORETURN void error(Twine Message); LLVM_ATTRIBUTE_NORETURN void report_error(StringRef File, Twine Message); LLVM_ATTRIBUTE_NORETURN void report_error(StringRef File, std::error_code EC); |