diff options
author | Dimitry Andric <dim@FreeBSD.org> | 2019-10-23 17:51:42 +0000 |
---|---|---|
committer | Dimitry Andric <dim@FreeBSD.org> | 2019-10-23 17:51:42 +0000 |
commit | 1d5ae1026e831016fc29fd927877c86af904481f (patch) | |
tree | 2cdfd12620fcfa5d9e4a0389f85368e8e36f63f9 /tools/llvm-objcopy | |
parent | e6d1592492a3a379186bfb02bd0f4eda0669c0d5 (diff) |
Notes
Diffstat (limited to 'tools/llvm-objcopy')
22 files changed, 1587 insertions, 906 deletions
diff --git a/tools/llvm-objcopy/COFF/COFFObjcopy.cpp b/tools/llvm-objcopy/COFF/COFFObjcopy.cpp index 4ae46851a66f..2a8d816e6f3c 100644 --- a/tools/llvm-objcopy/COFF/COFFObjcopy.cpp +++ b/tools/llvm-objcopy/COFF/COFFObjcopy.cpp @@ -16,8 +16,8 @@ #include "llvm/Object/Binary.h" #include "llvm/Object/COFF.h" +#include "llvm/Support/CRC.h" #include "llvm/Support/Errc.h" -#include "llvm/Support/JamCRC.h" #include "llvm/Support/Path.h" #include <cassert> @@ -40,22 +40,13 @@ static uint64_t getNextRVA(const Object &Obj) { Obj.IsPE ? Obj.PeHeader.SectionAlignment : 1); } -static uint32_t getCRC32(StringRef Data) { - JamCRC CRC; - CRC.update(ArrayRef<char>(Data.data(), Data.size())); - // The CRC32 value needs to be complemented because the JamCRC dosn't - // finalize the CRC32 value. It also dosn't negate the initial CRC32 value - // but it starts by default at 0xFFFFFFFF which is the complement of zero. - return ~CRC.getCRC(); -} - static std::vector<uint8_t> createGnuDebugLinkSectionContents(StringRef File) { ErrorOr<std::unique_ptr<MemoryBuffer>> LinkTargetOrErr = MemoryBuffer::getFile(File); if (!LinkTargetOrErr) error("'" + File + "': " + LinkTargetOrErr.getError().message()); auto LinkTarget = std::move(*LinkTargetOrErr); - uint32_t CRC32 = getCRC32(LinkTarget->getBuffer()); + uint32_t CRC32 = llvm::crc32(arrayRefFromStringRef(LinkTarget->getBuffer())); StringRef FileName = sys::path::filename(File); size_t CRCPos = alignTo(FileName.size() + 1, 4); @@ -65,26 +56,37 @@ static std::vector<uint8_t> createGnuDebugLinkSectionContents(StringRef File) { return Data; } -static void addGnuDebugLink(Object &Obj, StringRef DebugLinkFile) { - uint32_t StartRVA = getNextRVA(Obj); +// Adds named section with given contents to the object. +static void addSection(Object &Obj, StringRef Name, ArrayRef<uint8_t> Contents, + uint32_t Characteristics) { + bool NeedVA = Characteristics & (IMAGE_SCN_MEM_EXECUTE | IMAGE_SCN_MEM_READ | + IMAGE_SCN_MEM_WRITE); - std::vector<Section> Sections; Section Sec; - Sec.setOwnedContents(createGnuDebugLinkSectionContents(DebugLinkFile)); - Sec.Name = ".gnu_debuglink"; - Sec.Header.VirtualSize = Sec.getContents().size(); - Sec.Header.VirtualAddress = StartRVA; - Sec.Header.SizeOfRawData = alignTo(Sec.Header.VirtualSize, - Obj.IsPE ? Obj.PeHeader.FileAlignment : 1); + Sec.setOwnedContents(Contents); + Sec.Name = Name; + Sec.Header.VirtualSize = NeedVA ? Sec.getContents().size() : 0u; + Sec.Header.VirtualAddress = NeedVA ? getNextRVA(Obj) : 0u; + Sec.Header.SizeOfRawData = + NeedVA ? alignTo(Sec.Header.VirtualSize, + Obj.IsPE ? Obj.PeHeader.FileAlignment : 1) + : Sec.getContents().size(); // Sec.Header.PointerToRawData is filled in by the writer. Sec.Header.PointerToRelocations = 0; Sec.Header.PointerToLinenumbers = 0; // Sec.Header.NumberOfRelocations is filled in by the writer. Sec.Header.NumberOfLinenumbers = 0; - Sec.Header.Characteristics = IMAGE_SCN_CNT_INITIALIZED_DATA | - IMAGE_SCN_MEM_READ | IMAGE_SCN_MEM_DISCARDABLE; - Sections.push_back(Sec); - Obj.addSections(Sections); + Sec.Header.Characteristics = Characteristics; + + Obj.addSections(Sec); +} + +static void addGnuDebugLink(Object &Obj, StringRef DebugLinkFile) { + std::vector<uint8_t> Contents = + createGnuDebugLinkSectionContents(DebugLinkFile); + addSection(Obj, ".gnu_debuglink", Contents, + IMAGE_SCN_CNT_INITIALIZED_DATA | IMAGE_SCN_MEM_READ | + IMAGE_SCN_MEM_DISCARDABLE); } static Error handleArgs(const CopyConfig &Config, Object &Obj) { @@ -92,8 +94,7 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { Obj.removeSections([&Config](const Section &Sec) { // Contrary to --only-keep-debug, --only-section fully removes sections that // aren't mentioned. - if (!Config.OnlySection.empty() && - !is_contained(Config.OnlySection, Sec.Name)) + if (!Config.OnlySection.empty() && !Config.OnlySection.matches(Sec.Name)) return true; if (Config.StripDebug || Config.StripAll || Config.StripAllGNU || @@ -103,7 +104,7 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { return true; } - if (is_contained(Config.ToRemove, Sec.Name)) + if (Config.ToRemove.matches(Sec.Name)) return true; return false; @@ -137,7 +138,7 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { if (Config.StripAll || Config.StripAllGNU) return true; - if (is_contained(Config.SymbolsToRemove, Sym.Name)) { + if (Config.SymbolsToRemove.matches(Sym.Name)) { // Explicitly removing a referenced symbol is an error. if (Sym.Referenced) reportError(Config.OutputFilename, @@ -156,7 +157,7 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { if (Sym.Sym.StorageClass == IMAGE_SYM_CLASS_STATIC || Sym.Sym.SectionNumber == 0) if (Config.StripUnneeded || - is_contained(Config.UnneededSymbolsToRemove, Sym.Name)) + Config.UnneededSymbolsToRemove.matches(Sym.Name)) return true; // GNU objcopy keeps referenced local symbols and external symbols @@ -171,21 +172,38 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { return false; }); + for (const auto &Flag : Config.AddSection) { + StringRef SecName, FileName; + std::tie(SecName, FileName) = Flag.split("="); + + auto BufOrErr = MemoryBuffer::getFile(FileName); + if (!BufOrErr) + return createFileError(FileName, errorCodeToError(BufOrErr.getError())); + auto Buf = std::move(*BufOrErr); + + addSection( + Obj, SecName, + makeArrayRef(reinterpret_cast<const uint8_t *>(Buf->getBufferStart()), + Buf->getBufferSize()), + IMAGE_SCN_CNT_INITIALIZED_DATA | IMAGE_SCN_ALIGN_1BYTES); + } + if (!Config.AddGnuDebugLink.empty()) addGnuDebugLink(Obj, Config.AddGnuDebugLink); if (Config.AllowBrokenLinks || !Config.BuildIdLinkDir.empty() || Config.BuildIdLinkInput || Config.BuildIdLinkOutput || !Config.SplitDWO.empty() || !Config.SymbolsPrefix.empty() || - !Config.AllocSectionsPrefix.empty() || !Config.AddSection.empty() || - !Config.DumpSection.empty() || !Config.KeepSection.empty() || + !Config.AllocSectionsPrefix.empty() || !Config.DumpSection.empty() || + !Config.KeepSection.empty() || Config.NewSymbolVisibility || !Config.SymbolsToGlobalize.empty() || !Config.SymbolsToKeep.empty() || !Config.SymbolsToLocalize.empty() || !Config.SymbolsToWeaken.empty() || !Config.SymbolsToKeepGlobal.empty() || !Config.SectionsToRename.empty() || - !Config.SetSectionFlags.empty() || !Config.SymbolsToRename.empty() || - Config.ExtractDWO || Config.KeepFileSymbols || Config.LocalizeHidden || - Config.PreserveDates || Config.StripDWO || Config.StripNonAlloc || - Config.StripSections || Config.Weaken || Config.DecompressDebugSections || + !Config.SetSectionAlignment.empty() || !Config.SetSectionFlags.empty() || + !Config.SymbolsToRename.empty() || Config.ExtractDWO || + Config.KeepFileSymbols || Config.LocalizeHidden || Config.PreserveDates || + Config.StripDWO || Config.StripNonAlloc || Config.StripSections || + Config.Weaken || Config.DecompressDebugSections || Config.DiscardMode == DiscardType::Locals || !Config.SymbolsToAdd.empty() || Config.EntryExpr) { return createStringError(llvm::errc::invalid_argument, diff --git a/tools/llvm-objcopy/COFF/Reader.cpp b/tools/llvm-objcopy/COFF/Reader.cpp index 1f0ec9fa9691..2fcec0057c03 100644 --- a/tools/llvm-objcopy/COFF/Reader.cpp +++ b/tools/llvm-objcopy/COFF/Reader.cpp @@ -36,14 +36,9 @@ Error COFFReader::readExecutableHeaders(Object &Obj) const { DH->AddressOfNewExeHeader - sizeof(*DH)); if (COFFObj.is64()) { - const pe32plus_header *PE32Plus = nullptr; - if (auto EC = COFFObj.getPE32PlusHeader(PE32Plus)) - return errorCodeToError(EC); - Obj.PeHeader = *PE32Plus; + Obj.PeHeader = *COFFObj.getPE32PlusHeader(); } else { - const pe32_header *PE32 = nullptr; - if (auto EC = COFFObj.getPE32Header(PE32)) - return errorCodeToError(EC); + const pe32_header *PE32 = COFFObj.getPE32Header(); copyPeHeader(Obj.PeHeader, *PE32); // The pe32plus_header (stored in Object) lacks the BaseOfData field. Obj.BaseOfData = PE32->BaseOfData; @@ -196,16 +191,13 @@ Error COFFReader::setSymbolTargets(Object &Obj) const { } Expected<std::unique_ptr<Object>> COFFReader::create() const { - auto Obj = llvm::make_unique<Object>(); + auto Obj = std::make_unique<Object>(); - const coff_file_header *CFH = nullptr; - const coff_bigobj_file_header *CBFH = nullptr; - COFFObj.getCOFFHeader(CFH); - COFFObj.getCOFFBigObjHeader(CBFH); bool IsBigObj = false; - if (CFH) { + if (const coff_file_header *CFH = COFFObj.getCOFFHeader()) { Obj->CoffFileHeader = *CFH; } else { + const coff_bigobj_file_header *CBFH = COFFObj.getCOFFBigObjHeader(); if (!CBFH) return createStringError(object_error::parse_failed, "no COFF file header returned"); diff --git a/tools/llvm-objcopy/COFF/Writer.cpp b/tools/llvm-objcopy/COFF/Writer.cpp index f3bb1ce331f2..6db37435fd96 100644 --- a/tools/llvm-objcopy/COFF/Writer.cpp +++ b/tools/llvm-objcopy/COFF/Writer.cpp @@ -120,12 +120,12 @@ size_t COFFWriter::finalizeStringTable() { StrTabBuilder.finalize(); for (auto &S : Obj.getMutableSections()) { + memset(S.Header.Name, 0, sizeof(S.Header.Name)); if (S.Name.size() > COFF::NameSize) { - memset(S.Header.Name, 0, sizeof(S.Header.Name)); snprintf(S.Header.Name, sizeof(S.Header.Name), "/%d", (int)StrTabBuilder.getOffset(S.Name)); } else { - strncpy(S.Header.Name, S.Name.data(), COFF::NameSize); + memcpy(S.Header.Name, S.Name.data(), S.Name.size()); } } for (auto &S : Obj.getMutableSymbols()) { diff --git a/tools/llvm-objcopy/CommonOpts.td b/tools/llvm-objcopy/CommonOpts.td new file mode 100644 index 000000000000..e8c092b44431 --- /dev/null +++ b/tools/llvm-objcopy/CommonOpts.td @@ -0,0 +1,123 @@ +include "llvm/Option/OptParser.td" + +multiclass Eq<string name, string help> { + def NAME : Separate<["--"], name>; + def NAME #_eq : Joined<["--"], name #"=">, + Alias<!cast<Separate>(NAME)>, + HelpText<help>; +} + +def help : Flag<["--"], "help">; +def h : Flag<["-"], "h">, Alias<help>; + +def allow_broken_links + : Flag<["--"], "allow-broken-links">, + HelpText<"Allow the tool to remove sections even if it would leave " + "invalid section references. The appropriate sh_link fields " + "will be set to zero.">; + +def enable_deterministic_archives + : Flag<["--"], "enable-deterministic-archives">, + HelpText<"Enable deterministic mode when operating on archives (use " + "zero for UIDs, GIDs, and timestamps).">; +def D : Flag<["-"], "D">, + Alias<enable_deterministic_archives>, + HelpText<"Alias for --enable-deterministic-archives">; + +def disable_deterministic_archives + : Flag<["--"], "disable-deterministic-archives">, + HelpText<"Disable deterministic mode when operating on archives (use " + "real values for UIDs, GIDs, and timestamps).">; +def U : Flag<["-"], "U">, + Alias<disable_deterministic_archives>, + HelpText<"Alias for --disable-deterministic-archives">; + +def preserve_dates : Flag<["--"], "preserve-dates">, + HelpText<"Preserve access and modification timestamps">; +def p : Flag<["-"], "p">, + Alias<preserve_dates>, + HelpText<"Alias for --preserve-dates">; + +def strip_all : Flag<["--"], "strip-all">, + HelpText<"Remove non-allocated sections outside segments. " + ".gnu.warning* sections are not removed">; + +def strip_all_gnu + : Flag<["--"], "strip-all-gnu">, + HelpText<"Compatible with GNU's --strip-all">; + +def strip_debug : Flag<["--"], "strip-debug">, + HelpText<"Remove all debug sections">; +def g : Flag<["-"], "g">, + Alias<strip_debug>, + HelpText<"Alias for --strip-debug">; + +def strip_unneeded : Flag<["--"], "strip-unneeded">, + HelpText<"Remove all symbols not needed by relocations">; + +defm remove_section : Eq<"remove-section", "Remove <section>">, + MetaVarName<"section">; +def R : JoinedOrSeparate<["-"], "R">, + Alias<remove_section>, + HelpText<"Alias for --remove-section">; + +def strip_sections + : Flag<["--"], "strip-sections">, + HelpText<"Remove all section headers and all sections not in segments">; + +defm strip_symbol : Eq<"strip-symbol", "Strip <symbol>">, + MetaVarName<"symbol">; +def N : JoinedOrSeparate<["-"], "N">, + Alias<strip_symbol>, + HelpText<"Alias for --strip-symbol">; + +defm keep_section : Eq<"keep-section", "Keep <section>">, + MetaVarName<"section">; + +defm keep_symbol : Eq<"keep-symbol", "Do not remove symbol <symbol>">, + MetaVarName<"symbol">; +def K : JoinedOrSeparate<["-"], "K">, + Alias<keep_symbol>, + HelpText<"Alias for --keep-symbol">; + +def keep_file_symbols : Flag<["--"], "keep-file-symbols">, + HelpText<"Do not remove file symbols">; + +def only_keep_debug + : Flag<["--"], "only-keep-debug">, + HelpText<"Clear sections that would not be stripped by --strip-debug. " + "Currently only implemented for COFF.">; + +def discard_locals : Flag<["--"], "discard-locals">, + HelpText<"Remove compiler-generated local symbols, (e.g. " + "symbols starting with .L)">; +def X : Flag<["-"], "X">, + Alias<discard_locals>, + HelpText<"Alias for --discard-locals">; + +def discard_all + : Flag<["--"], "discard-all">, + HelpText<"Remove all local symbols except file and section symbols">; +def x : Flag<["-"], "x">, + Alias<discard_all>, + HelpText<"Alias for --discard-all">; + +def regex + : Flag<["--"], "regex">, + HelpText<"Permit regular expressions in name comparison">; + +def version : Flag<["--"], "version">, + HelpText<"Print the version and exit.">; +def V : Flag<["-"], "V">, + Alias<version>, + HelpText<"Alias for --version">; + +def wildcard + : Flag<["--"], "wildcard">, + HelpText<"Allow wildcard syntax for symbol-related flags. Incompatible " + "with --regex. Allows using '*' to match any number of " + "characters, '?' to match any single character, '\' to escape " + "special characters, and '[]' to define character classes. " + "Wildcards beginning with '!' will prevent a match, for example " + "\"-N '*' -N '!x'\" will strip all symbols except for \"x\".">; +def w : Flag<["-"], "w">, Alias<wildcard>, HelpText<"Alias for --wildcard">; diff --git a/tools/llvm-objcopy/CopyConfig.cpp b/tools/llvm-objcopy/CopyConfig.cpp index 8d6431b3044f..d707bec20c49 100644 --- a/tools/llvm-objcopy/CopyConfig.cpp +++ b/tools/llvm-objcopy/CopyConfig.cpp @@ -14,10 +14,10 @@ #include "llvm/ADT/StringSet.h" #include "llvm/Option/Arg.h" #include "llvm/Option/ArgList.h" +#include "llvm/Support/CRC.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Compression.h" #include "llvm/Support/Errc.h" -#include "llvm/Support/JamCRC.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/StringSaver.h" #include <memory> @@ -155,6 +155,25 @@ static Expected<SectionRename> parseRenameSectionValue(StringRef FlagValue) { return SR; } +static Expected<std::pair<StringRef, uint64_t>> +parseSetSectionAlignment(StringRef FlagValue) { + if (!FlagValue.contains('=')) + return createStringError( + errc::invalid_argument, + "bad format for --set-section-alignment: missing '='"); + auto Split = StringRef(FlagValue).split('='); + if (Split.first.empty()) + return createStringError( + errc::invalid_argument, + "bad format for --set-section-alignment: missing section name"); + uint64_t NewAlign; + if (Split.second.getAsInteger(0, NewAlign)) + return createStringError(errc::invalid_argument, + "invalid alignment for --set-section-alignment: '%s'", + Split.second.str().c_str()); + return std::make_pair(Split.first, NewAlign); +} + static Expected<SectionFlagsUpdate> parseSetSectionFlagValue(StringRef FlagValue) { if (!StringRef(FlagValue).contains('=')) @@ -177,106 +196,6 @@ parseSetSectionFlagValue(StringRef FlagValue) { return SFU; } -static Expected<NewSymbolInfo> parseNewSymbolInfo(StringRef FlagValue) { - // Parse value given with --add-symbol option and create the - // new symbol if possible. The value format for --add-symbol is: - // - // <name>=[<section>:]<value>[,<flags>] - // - // where: - // <name> - symbol name, can be empty string - // <section> - optional section name. If not given ABS symbol is created - // <value> - symbol value, can be decimal or hexadecimal number prefixed - // with 0x. - // <flags> - optional flags affecting symbol type, binding or visibility: - // The following are currently supported: - // - // global, local, weak, default, hidden, file, section, object, - // indirect-function. - // - // The following flags are ignored and provided for GNU - // compatibility only: - // - // warning, debug, constructor, indirect, synthetic, - // unique-object, before=<symbol>. - NewSymbolInfo SI; - StringRef Value; - std::tie(SI.SymbolName, Value) = FlagValue.split('='); - if (Value.empty()) - return createStringError( - errc::invalid_argument, - "bad format for --add-symbol, missing '=' after '%s'", - SI.SymbolName.str().c_str()); - - if (Value.contains(':')) { - std::tie(SI.SectionName, Value) = Value.split(':'); - if (SI.SectionName.empty() || Value.empty()) - return createStringError( - errc::invalid_argument, - "bad format for --add-symbol, missing section name or symbol value"); - } - - SmallVector<StringRef, 6> Flags; - Value.split(Flags, ','); - if (Flags[0].getAsInteger(0, SI.Value)) - return createStringError(errc::invalid_argument, "bad symbol value: '%s'", - Flags[0].str().c_str()); - - using Functor = std::function<void(void)>; - SmallVector<StringRef, 6> UnsupportedFlags; - for (size_t I = 1, NumFlags = Flags.size(); I < NumFlags; ++I) - static_cast<Functor>( - StringSwitch<Functor>(Flags[I]) - .CaseLower("global", [&SI] { SI.Bind = ELF::STB_GLOBAL; }) - .CaseLower("local", [&SI] { SI.Bind = ELF::STB_LOCAL; }) - .CaseLower("weak", [&SI] { SI.Bind = ELF::STB_WEAK; }) - .CaseLower("default", [&SI] { SI.Visibility = ELF::STV_DEFAULT; }) - .CaseLower("hidden", [&SI] { SI.Visibility = ELF::STV_HIDDEN; }) - .CaseLower("file", [&SI] { SI.Type = ELF::STT_FILE; }) - .CaseLower("section", [&SI] { SI.Type = ELF::STT_SECTION; }) - .CaseLower("object", [&SI] { SI.Type = ELF::STT_OBJECT; }) - .CaseLower("function", [&SI] { SI.Type = ELF::STT_FUNC; }) - .CaseLower("indirect-function", - [&SI] { SI.Type = ELF::STT_GNU_IFUNC; }) - .CaseLower("debug", [] {}) - .CaseLower("constructor", [] {}) - .CaseLower("warning", [] {}) - .CaseLower("indirect", [] {}) - .CaseLower("synthetic", [] {}) - .CaseLower("unique-object", [] {}) - .StartsWithLower("before", [] {}) - .Default([&] { UnsupportedFlags.push_back(Flags[I]); }))(); - if (!UnsupportedFlags.empty()) - return createStringError(errc::invalid_argument, - "unsupported flag%s for --add-symbol: '%s'", - UnsupportedFlags.size() > 1 ? "s" : "", - join(UnsupportedFlags, "', '").c_str()); - return SI; -} - -static const StringMap<MachineInfo> ArchMap{ - // Name, {EMachine, 64bit, LittleEndian} - {"aarch64", {ELF::EM_AARCH64, true, true}}, - {"arm", {ELF::EM_ARM, false, true}}, - {"i386", {ELF::EM_386, false, true}}, - {"i386:x86-64", {ELF::EM_X86_64, true, true}}, - {"mips", {ELF::EM_MIPS, false, false}}, - {"powerpc:common64", {ELF::EM_PPC64, true, true}}, - {"riscv:rv32", {ELF::EM_RISCV, false, true}}, - {"riscv:rv64", {ELF::EM_RISCV, true, true}}, - {"sparc", {ELF::EM_SPARC, false, false}}, - {"sparcel", {ELF::EM_SPARC, false, true}}, - {"x86-64", {ELF::EM_X86_64, true, true}}, -}; - -static Expected<const MachineInfo &> getMachineInfo(StringRef Arch) { - auto Iter = ArchMap.find(Arch); - if (Iter == std::end(ArchMap)) - return createStringError(errc::invalid_argument, - "invalid architecture: '%s'", Arch.str().c_str()); - return Iter->getValue(); -} - struct TargetInfo { FileFormat Format; MachineInfo Machine; @@ -341,9 +260,10 @@ getOutputTargetInfoByTargetName(StringRef TargetName) { return {TargetInfo{Format, MI}}; } -static Error addSymbolsFromFile(std::vector<NameOrRegex> &Symbols, - BumpPtrAllocator &Alloc, StringRef Filename, - bool UseRegex) { +static Error +addSymbolsFromFile(NameMatcher &Symbols, BumpPtrAllocator &Alloc, + StringRef Filename, MatchStyle MS, + llvm::function_ref<Error(Error)> ErrorCallback) { StringSaver Saver(Alloc); SmallVector<StringRef, 16> Lines; auto BufOrErr = MemoryBuffer::getFile(Filename); @@ -356,21 +276,47 @@ static Error addSymbolsFromFile(std::vector<NameOrRegex> &Symbols, // it's not empty. auto TrimmedLine = Line.split('#').first.trim(); if (!TrimmedLine.empty()) - Symbols.emplace_back(Saver.save(TrimmedLine), UseRegex); + if (Error E = Symbols.addMatcher(NameOrPattern::create( + Saver.save(TrimmedLine), MS, ErrorCallback))) + return E; } return Error::success(); } -NameOrRegex::NameOrRegex(StringRef Pattern, bool IsRegex) { - if (!IsRegex) { - Name = Pattern; - return; - } +Expected<NameOrPattern> +NameOrPattern::create(StringRef Pattern, MatchStyle MS, + llvm::function_ref<Error(Error)> ErrorCallback) { + switch (MS) { + case MatchStyle::Literal: + return NameOrPattern(Pattern); + case MatchStyle::Wildcard: { + SmallVector<char, 32> Data; + bool IsPositiveMatch = true; + if (Pattern[0] == '!') { + IsPositiveMatch = false; + Pattern = Pattern.drop_front(); + } + Expected<GlobPattern> GlobOrErr = GlobPattern::create(Pattern); + + // If we couldn't create it as a glob, report the error, but try again with + // a literal if the error reporting is non-fatal. + if (!GlobOrErr) { + if (Error E = ErrorCallback(GlobOrErr.takeError())) + return std::move(E); + return create(Pattern, MatchStyle::Literal, ErrorCallback); + } - SmallVector<char, 32> Data; - R = std::make_shared<Regex>( - ("^" + Pattern.ltrim('^').rtrim('$') + "$").toStringRef(Data)); + return NameOrPattern(std::make_shared<GlobPattern>(*GlobOrErr), + IsPositiveMatch); + } + case MatchStyle::Regex: { + SmallVector<char, 32> Data; + return NameOrPattern(std::make_shared<Regex>( + ("^" + Pattern.ltrim('^').rtrim('$') + "$").toStringRef(Data))); + } + } + llvm_unreachable("Unhandled llvm.objcopy.MatchStyle enum"); } static Error addSymbolsToRenameFromFile(StringMap<StringRef> &SymbolsToRename, @@ -407,10 +353,22 @@ template <class T> static ErrorOr<T> getAsInteger(StringRef Val) { return Result; } +static void printHelp(const opt::OptTable &OptTable, raw_ostream &OS, + StringRef ToolName) { + OptTable.PrintHelp(OS, (ToolName + " input [output]").str().c_str(), + (ToolName + " tool").str().c_str()); + // TODO: Replace this with libOption call once it adds extrahelp support. + // The CommandLine library has a cl::extrahelp class to support this, + // but libOption does not have that yet. + OS << "\nPass @FILE as argument to read options from FILE.\n"; +} + // ParseObjcopyOptions returns the config and sets the input arguments. If a // help flag is set then ParseObjcopyOptions will print the help messege and // exit. -Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { +Expected<DriverConfig> +parseObjcopyOptions(ArrayRef<const char *> ArgsArr, + llvm::function_ref<Error(Error)> ErrorCallback) { DriverConfig DC; ObjcopyOptTable T; unsigned MissingArgumentIndex, MissingArgumentCount; @@ -418,12 +376,12 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { T.ParseArgs(ArgsArr, MissingArgumentIndex, MissingArgumentCount); if (InputArgs.size() == 0) { - T.PrintHelp(errs(), "llvm-objcopy input [output]", "objcopy tool"); + printHelp(T, errs(), "llvm-objcopy"); exit(1); } if (InputArgs.hasArg(OBJCOPY_help)) { - T.PrintHelp(outs(), "llvm-objcopy input [output]", "objcopy tool"); + printHelp(T, outs(), "llvm-objcopy"); exit(0); } @@ -459,7 +417,18 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { errc::invalid_argument, "--target cannot be used with --input-target or --output-target"); - bool UseRegex = InputArgs.hasArg(OBJCOPY_regex); + if (InputArgs.hasArg(OBJCOPY_regex) && InputArgs.hasArg(OBJCOPY_wildcard)) + return createStringError(errc::invalid_argument, + "--regex and --wildcard are incompatible"); + + MatchStyle SectionMatchStyle = InputArgs.hasArg(OBJCOPY_regex) + ? MatchStyle::Regex + : MatchStyle::Wildcard; + MatchStyle SymbolMatchStyle = InputArgs.hasArg(OBJCOPY_regex) + ? MatchStyle::Regex + : InputArgs.hasArg(OBJCOPY_wildcard) + ? MatchStyle::Wildcard + : MatchStyle::Literal; StringRef InputFormat, OutputFormat; if (InputArgs.hasArg(OBJCOPY_target)) { InputFormat = InputArgs.getLastArgValue(OBJCOPY_target); @@ -476,28 +445,26 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { .Case("binary", FileFormat::Binary) .Case("ihex", FileFormat::IHex) .Default(FileFormat::Unspecified); - if (Config.InputFormat == FileFormat::Binary) { - auto BinaryArch = InputArgs.getLastArgValue(OBJCOPY_binary_architecture); - if (BinaryArch.empty()) - return createStringError( - errc::invalid_argument, - "specified binary input without specifiying an architecture"); - Expected<const MachineInfo &> MI = getMachineInfo(BinaryArch); - if (!MI) - return MI.takeError(); - Config.BinaryArch = *MI; - } + + if (InputArgs.hasArg(OBJCOPY_new_symbol_visibility)) + Config.NewSymbolVisibility = + InputArgs.getLastArgValue(OBJCOPY_new_symbol_visibility); Config.OutputFormat = StringSwitch<FileFormat>(OutputFormat) .Case("binary", FileFormat::Binary) .Case("ihex", FileFormat::IHex) .Default(FileFormat::Unspecified); - if (Config.OutputFormat == FileFormat::Unspecified && !OutputFormat.empty()) { - Expected<TargetInfo> Target = getOutputTargetInfoByTargetName(OutputFormat); - if (!Target) - return Target.takeError(); - Config.OutputFormat = Target->Format; - Config.OutputArch = Target->Machine; + if (Config.OutputFormat == FileFormat::Unspecified) { + if (OutputFormat.empty()) { + Config.OutputFormat = Config.InputFormat; + } else { + Expected<TargetInfo> Target = + getOutputTargetInfoByTargetName(OutputFormat); + if (!Target) + return Target.takeError(); + Config.OutputFormat = Target->Format; + Config.OutputArch = Target->Machine; + } } if (auto Arg = InputArgs.getLastArg(OBJCOPY_compress_debug_sections, @@ -535,12 +502,8 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { if (!DebugOrErr) return createFileError(Config.AddGnuDebugLink, DebugOrErr.getError()); auto Debug = std::move(*DebugOrErr); - JamCRC CRC; - CRC.update( - ArrayRef<char>(Debug->getBuffer().data(), Debug->getBuffer().size())); - // The CRC32 value needs to be complemented because the JamCRC doesn't - // finalize the CRC32 value. - Config.GnuDebugLinkCRC32 = ~CRC.getCRC(); + Config.GnuDebugLinkCRC32 = + llvm::crc32(arrayRefFromStringRef(Debug->getBuffer())); } Config.BuildIdLinkDir = InputArgs.getLastArgValue(OBJCOPY_build_id_link_dir); if (InputArgs.hasArg(OBJCOPY_build_id_link_input)) @@ -582,6 +545,13 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { "multiple renames of section '%s'", SR->OriginalName.str().c_str()); } + for (auto Arg : InputArgs.filtered(OBJCOPY_set_section_alignment)) { + Expected<std::pair<StringRef, uint64_t>> NameAndAlign = + parseSetSectionAlignment(Arg->getValue()); + if (!NameAndAlign) + return NameAndAlign.takeError(); + Config.SetSectionAlignment[NameAndAlign->first] = NameAndAlign->second; + } for (auto Arg : InputArgs.filtered(OBJCOPY_set_section_flags)) { Expected<SectionFlagsUpdate> SFU = parseSetSectionFlagValue(Arg->getValue()); @@ -612,13 +582,28 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { } for (auto Arg : InputArgs.filtered(OBJCOPY_remove_section)) - Config.ToRemove.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.ToRemove.addMatcher(NameOrPattern::create( + Arg->getValue(), SectionMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_keep_section)) - Config.KeepSection.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.KeepSection.addMatcher(NameOrPattern::create( + Arg->getValue(), SectionMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_only_section)) - Config.OnlySection.emplace_back(Arg->getValue(), UseRegex); - for (auto Arg : InputArgs.filtered(OBJCOPY_add_section)) - Config.AddSection.push_back(Arg->getValue()); + if (Error E = Config.OnlySection.addMatcher(NameOrPattern::create( + Arg->getValue(), SectionMatchStyle, ErrorCallback))) + return std::move(E); + for (auto Arg : InputArgs.filtered(OBJCOPY_add_section)) { + StringRef ArgValue(Arg->getValue()); + if (!ArgValue.contains('=')) + return createStringError(errc::invalid_argument, + "bad format for --add-section: missing '='"); + if (ArgValue.split("=").second.empty()) + return createStringError( + errc::invalid_argument, + "bad format for --add-section: missing file name"); + Config.AddSection.push_back(ArgValue); + } for (auto Arg : InputArgs.filtered(OBJCOPY_dump_section)) Config.DumpSection.push_back(Arg->getValue()); Config.StripAll = InputArgs.hasArg(OBJCOPY_strip_all); @@ -645,53 +630,71 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { if (Config.DiscardMode == DiscardType::All) Config.StripDebug = true; for (auto Arg : InputArgs.filtered(OBJCOPY_localize_symbol)) - Config.SymbolsToLocalize.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToLocalize.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_localize_symbols)) if (Error E = addSymbolsFromFile(Config.SymbolsToLocalize, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_keep_global_symbol)) - Config.SymbolsToKeepGlobal.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToKeepGlobal.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_keep_global_symbols)) if (Error E = addSymbolsFromFile(Config.SymbolsToKeepGlobal, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_globalize_symbol)) - Config.SymbolsToGlobalize.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToGlobalize.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_globalize_symbols)) if (Error E = addSymbolsFromFile(Config.SymbolsToGlobalize, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_weaken_symbol)) - Config.SymbolsToWeaken.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToWeaken.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_weaken_symbols)) if (Error E = addSymbolsFromFile(Config.SymbolsToWeaken, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_strip_symbol)) - Config.SymbolsToRemove.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToRemove.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_strip_symbols)) if (Error E = addSymbolsFromFile(Config.SymbolsToRemove, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_strip_unneeded_symbol)) - Config.UnneededSymbolsToRemove.emplace_back(Arg->getValue(), UseRegex); + if (Error E = + Config.UnneededSymbolsToRemove.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_strip_unneeded_symbols)) if (Error E = addSymbolsFromFile(Config.UnneededSymbolsToRemove, DC.Alloc, - Arg->getValue(), UseRegex)) + Arg->getValue(), SymbolMatchStyle, + ErrorCallback)) return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_keep_symbol)) - Config.SymbolsToKeep.emplace_back(Arg->getValue(), UseRegex); + if (Error E = Config.SymbolsToKeep.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(OBJCOPY_keep_symbols)) - if (Error E = addSymbolsFromFile(Config.SymbolsToKeep, DC.Alloc, - Arg->getValue(), UseRegex)) + if (Error E = + addSymbolsFromFile(Config.SymbolsToKeep, DC.Alloc, Arg->getValue(), + SymbolMatchStyle, ErrorCallback)) return std::move(E); - for (auto Arg : InputArgs.filtered(OBJCOPY_add_symbol)) { - Expected<NewSymbolInfo> NSI = parseNewSymbolInfo(Arg->getValue()); - if (!NSI) - return NSI.takeError(); - Config.SymbolsToAdd.push_back(*NSI); - } + for (auto Arg : InputArgs.filtered(OBJCOPY_add_symbol)) + Config.SymbolsToAdd.push_back(Arg->getValue()); Config.AllowBrokenLinks = InputArgs.hasArg(OBJCOPY_allow_broken_links); @@ -754,19 +757,19 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr) { // exit. Expected<DriverConfig> parseStripOptions(ArrayRef<const char *> ArgsArr, - std::function<Error(Error)> ErrorCallback) { + llvm::function_ref<Error(Error)> ErrorCallback) { StripOptTable T; unsigned MissingArgumentIndex, MissingArgumentCount; llvm::opt::InputArgList InputArgs = T.ParseArgs(ArgsArr, MissingArgumentIndex, MissingArgumentCount); if (InputArgs.size() == 0) { - T.PrintHelp(errs(), "llvm-strip [options] file...", "strip tool"); + printHelp(T, errs(), "llvm-strip"); exit(1); } if (InputArgs.hasArg(STRIP_help)) { - T.PrintHelp(outs(), "llvm-strip [options] file...", "strip tool"); + printHelp(T, outs(), "llvm-strip"); exit(0); } @@ -792,7 +795,17 @@ parseStripOptions(ArrayRef<const char *> ArgsArr, "multiple input files cannot be used in combination with -o"); CopyConfig Config; - bool UseRegexp = InputArgs.hasArg(STRIP_regex); + + if (InputArgs.hasArg(STRIP_regex) && InputArgs.hasArg(STRIP_wildcard)) + return createStringError(errc::invalid_argument, + "--regex and --wildcard are incompatible"); + MatchStyle SectionMatchStyle = + InputArgs.hasArg(STRIP_regex) ? MatchStyle::Regex : MatchStyle::Wildcard; + MatchStyle SymbolMatchStyle = InputArgs.hasArg(STRIP_regex) + ? MatchStyle::Regex + : InputArgs.hasArg(STRIP_wildcard) + ? MatchStyle::Wildcard + : MatchStyle::Literal; Config.AllowBrokenLinks = InputArgs.hasArg(STRIP_allow_broken_links); Config.StripDebug = InputArgs.hasArg(STRIP_strip_debug); @@ -801,6 +814,7 @@ parseStripOptions(ArrayRef<const char *> ArgsArr, InputArgs.hasFlag(STRIP_discard_all, STRIP_discard_locals) ? DiscardType::All : DiscardType::Locals; + Config.StripSections = InputArgs.hasArg(STRIP_strip_sections); Config.StripUnneeded = InputArgs.hasArg(STRIP_strip_unneeded); if (auto Arg = InputArgs.getLastArg(STRIP_strip_all, STRIP_no_strip_all)) Config.StripAll = Arg->getOption().getID() == STRIP_strip_all; @@ -809,16 +823,24 @@ parseStripOptions(ArrayRef<const char *> ArgsArr, Config.KeepFileSymbols = InputArgs.hasArg(STRIP_keep_file_symbols); for (auto Arg : InputArgs.filtered(STRIP_keep_section)) - Config.KeepSection.emplace_back(Arg->getValue(), UseRegexp); + if (Error E = Config.KeepSection.addMatcher(NameOrPattern::create( + Arg->getValue(), SectionMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(STRIP_remove_section)) - Config.ToRemove.emplace_back(Arg->getValue(), UseRegexp); + if (Error E = Config.ToRemove.addMatcher(NameOrPattern::create( + Arg->getValue(), SectionMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(STRIP_strip_symbol)) - Config.SymbolsToRemove.emplace_back(Arg->getValue(), UseRegexp); + if (Error E = Config.SymbolsToRemove.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); for (auto Arg : InputArgs.filtered(STRIP_keep_symbol)) - Config.SymbolsToKeep.emplace_back(Arg->getValue(), UseRegexp); + if (Error E = Config.SymbolsToKeep.addMatcher(NameOrPattern::create( + Arg->getValue(), SymbolMatchStyle, ErrorCallback))) + return std::move(E); if (!InputArgs.hasArg(STRIP_no_strip_all) && !Config.StripDebug && !Config.StripUnneeded && Config.DiscardMode == DiscardType::None && diff --git a/tools/llvm-objcopy/CopyConfig.h b/tools/llvm-objcopy/CopyConfig.h index aff3631a487c..55a55d3a2bc2 100644 --- a/tools/llvm-objcopy/CopyConfig.h +++ b/tools/llvm-objcopy/CopyConfig.h @@ -9,6 +9,7 @@ #ifndef LLVM_TOOLS_LLVM_OBJCOPY_COPY_CONFIG_H #define LLVM_TOOLS_LLVM_OBJCOPY_COPY_CONFIG_H +#include "ELF/ELFConfig.h" #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/BitmaskEnum.h" #include "llvm/ADT/Optional.h" @@ -18,6 +19,7 @@ #include "llvm/Object/ELFTypes.h" #include "llvm/Support/Allocator.h" #include "llvm/Support/Error.h" +#include "llvm/Support/GlobPattern.h" #include "llvm/Support/Regex.h" // Necessary for llvm::DebugCompressionType::None #include "llvm/Target/TargetOptions.h" @@ -87,36 +89,71 @@ enum class DiscardType { Locals, // --discard-locals (-X) }; -class NameOrRegex { +enum class MatchStyle { + Literal, // Default for symbols. + Wildcard, // Default for sections, or enabled with --wildcard (-w). + Regex, // Enabled with --regex. +}; + +class NameOrPattern { StringRef Name; // Regex is shared between multiple CopyConfig instances. std::shared_ptr<Regex> R; + std::shared_ptr<GlobPattern> G; + bool IsPositiveMatch = true; + + NameOrPattern(StringRef N) : Name(N) {} + NameOrPattern(std::shared_ptr<Regex> R) : R(R) {} + NameOrPattern(std::shared_ptr<GlobPattern> G, bool IsPositiveMatch) + : G(G), IsPositiveMatch(IsPositiveMatch) {} public: - NameOrRegex(StringRef Pattern, bool IsRegex); - bool operator==(StringRef S) const { return R ? R->match(S) : Name == S; } + // ErrorCallback is used to handle recoverable errors. An Error returned + // by the callback aborts the parsing and is then returned by this function. + static Expected<NameOrPattern> + create(StringRef Pattern, MatchStyle MS, + llvm::function_ref<Error(Error)> ErrorCallback); + + bool isPositiveMatch() const { return IsPositiveMatch; } + bool operator==(StringRef S) const { + return R ? R->match(S) : G ? G->match(S) : Name == S; + } bool operator!=(StringRef S) const { return !operator==(S); } }; -struct NewSymbolInfo { - StringRef SymbolName; - StringRef SectionName; - uint64_t Value = 0; - uint8_t Type = ELF::STT_NOTYPE; - uint8_t Bind = ELF::STB_GLOBAL; - uint8_t Visibility = ELF::STV_DEFAULT; +// Matcher that checks symbol or section names against the command line flags +// provided for that option. +class NameMatcher { + std::vector<NameOrPattern> PosMatchers; + std::vector<NameOrPattern> NegMatchers; + +public: + Error addMatcher(Expected<NameOrPattern> Matcher) { + if (!Matcher) + return Matcher.takeError(); + if (Matcher->isPositiveMatch()) + PosMatchers.push_back(std::move(*Matcher)); + else + NegMatchers.push_back(std::move(*Matcher)); + return Error::success(); + } + bool matches(StringRef S) const { + return is_contained(PosMatchers, S) && !is_contained(NegMatchers, S); + } + bool empty() const { return PosMatchers.empty() && NegMatchers.empty(); } }; // Configuration for copying/stripping a single file. struct CopyConfig { + // Format-specific options to be initialized lazily when needed. + Optional<elf::ELFCopyConfig> ELF; + // Main input/output options StringRef InputFilename; FileFormat InputFormat; StringRef OutputFilename; FileFormat OutputFormat; - // Only applicable for --input-format=binary - MachineInfo BinaryArch; // Only applicable when --output-format!=binary (e.g. elf64-x86-64). Optional<MachineInfo> OutputArch; @@ -132,24 +169,30 @@ struct CopyConfig { StringRef SymbolsPrefix; StringRef AllocSectionsPrefix; DiscardType DiscardMode = DiscardType::None; + Optional<StringRef> NewSymbolVisibility; // Repeated options std::vector<StringRef> AddSection; std::vector<StringRef> DumpSection; - std::vector<NewSymbolInfo> SymbolsToAdd; - std::vector<NameOrRegex> KeepSection; - std::vector<NameOrRegex> OnlySection; - std::vector<NameOrRegex> SymbolsToGlobalize; - std::vector<NameOrRegex> SymbolsToKeep; - std::vector<NameOrRegex> SymbolsToLocalize; - std::vector<NameOrRegex> SymbolsToRemove; - std::vector<NameOrRegex> UnneededSymbolsToRemove; - std::vector<NameOrRegex> SymbolsToWeaken; - std::vector<NameOrRegex> ToRemove; - std::vector<NameOrRegex> SymbolsToKeepGlobal; + std::vector<StringRef> SymbolsToAdd; + + // Section matchers + NameMatcher KeepSection; + NameMatcher OnlySection; + NameMatcher ToRemove; + + // Symbol matchers + NameMatcher SymbolsToGlobalize; + NameMatcher SymbolsToKeep; + NameMatcher SymbolsToLocalize; + NameMatcher SymbolsToRemove; + NameMatcher UnneededSymbolsToRemove; + NameMatcher SymbolsToWeaken; + NameMatcher SymbolsToKeepGlobal; // Map options StringMap<SectionRename> SectionsToRename; + StringMap<uint64_t> SetSectionAlignment; StringMap<SectionFlagsUpdate> SetSectionFlags; StringMap<StringRef> SymbolsToRename; @@ -178,6 +221,18 @@ struct CopyConfig { bool Weaken = false; bool DecompressDebugSections = false; DebugCompressionType CompressionType = DebugCompressionType::None; + + // parseELFConfig performs ELF-specific command-line parsing. Fills `ELF` on + // success or returns an Error otherwise. + Error parseELFConfig() { + if (!ELF) { + Expected<elf::ELFCopyConfig> ELFConfig = elf::parseConfig(*this); + if (!ELFConfig) + return ELFConfig.takeError(); + ELF = *ELFConfig; + } + return Error::success(); + } }; // Configuration for the overall invocation of this tool. When invoked as @@ -190,8 +245,11 @@ struct DriverConfig { // ParseObjcopyOptions returns the config and sets the input arguments. If a // help flag is set then ParseObjcopyOptions will print the help messege and -// exit. -Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr); +// exit. ErrorCallback is used to handle recoverable errors. An Error returned +// by the callback aborts the parsing and is then returned by this function. +Expected<DriverConfig> +parseObjcopyOptions(ArrayRef<const char *> ArgsArr, + llvm::function_ref<Error(Error)> ErrorCallback); // ParseStripOptions returns the config and sets the input arguments. If a // help flag is set then ParseStripOptions will print the help messege and @@ -199,7 +257,7 @@ Expected<DriverConfig> parseObjcopyOptions(ArrayRef<const char *> ArgsArr); // by the callback aborts the parsing and is then returned by this function. Expected<DriverConfig> parseStripOptions(ArrayRef<const char *> ArgsArr, - std::function<Error(Error)> ErrorCallback); + llvm::function_ref<Error(Error)> ErrorCallback); } // namespace objcopy } // namespace llvm diff --git a/tools/llvm-objcopy/ELF/ELFConfig.cpp b/tools/llvm-objcopy/ELF/ELFConfig.cpp new file mode 100644 index 000000000000..40993760add7 --- /dev/null +++ b/tools/llvm-objcopy/ELF/ELFConfig.cpp @@ -0,0 +1,133 @@ +//===- ELFConfig.cpp ------------------------------------------------------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#include "CopyConfig.h" +#include "llvm/ADT/Optional.h" +#include "llvm/ADT/StringSwitch.h" +#include "llvm/Support/Errc.h" +#include "llvm/Support/Error.h" + +namespace llvm { +namespace objcopy { +namespace elf { + +static Expected<NewSymbolInfo> parseNewSymbolInfo(StringRef FlagValue, + uint8_t DefaultVisibility) { + // Parse value given with --add-symbol option and create the + // new symbol if possible. The value format for --add-symbol is: + // + // <name>=[<section>:]<value>[,<flags>] + // + // where: + // <name> - symbol name, can be empty string + // <section> - optional section name. If not given ABS symbol is created + // <value> - symbol value, can be decimal or hexadecimal number prefixed + // with 0x. + // <flags> - optional flags affecting symbol type, binding or visibility: + // The following are currently supported: + // + // global, local, weak, default, hidden, file, section, object, + // indirect-function. + // + // The following flags are ignored and provided for GNU + // compatibility only: + // + // warning, debug, constructor, indirect, synthetic, + // unique-object, before=<symbol>. + NewSymbolInfo SI; + StringRef Value; + std::tie(SI.SymbolName, Value) = FlagValue.split('='); + if (Value.empty()) + return createStringError( + errc::invalid_argument, + "bad format for --add-symbol, missing '=' after '%s'", + SI.SymbolName.str().c_str()); + + if (Value.contains(':')) { + std::tie(SI.SectionName, Value) = Value.split(':'); + if (SI.SectionName.empty() || Value.empty()) + return createStringError( + errc::invalid_argument, + "bad format for --add-symbol, missing section name or symbol value"); + } + + SmallVector<StringRef, 6> Flags; + Value.split(Flags, ','); + if (Flags[0].getAsInteger(0, SI.Value)) + return createStringError(errc::invalid_argument, "bad symbol value: '%s'", + Flags[0].str().c_str()); + + SI.Visibility = DefaultVisibility; + + using Functor = std::function<void(void)>; + SmallVector<StringRef, 6> UnsupportedFlags; + for (size_t I = 1, NumFlags = Flags.size(); I < NumFlags; ++I) + static_cast<Functor>( + StringSwitch<Functor>(Flags[I]) + .CaseLower("global", [&SI] { SI.Bind = ELF::STB_GLOBAL; }) + .CaseLower("local", [&SI] { SI.Bind = ELF::STB_LOCAL; }) + .CaseLower("weak", [&SI] { SI.Bind = ELF::STB_WEAK; }) + .CaseLower("default", [&SI] { SI.Visibility = ELF::STV_DEFAULT; }) + .CaseLower("hidden", [&SI] { SI.Visibility = ELF::STV_HIDDEN; }) + .CaseLower("protected", + [&SI] { SI.Visibility = ELF::STV_PROTECTED; }) + .CaseLower("file", [&SI] { SI.Type = ELF::STT_FILE; }) + .CaseLower("section", [&SI] { SI.Type = ELF::STT_SECTION; }) + .CaseLower("object", [&SI] { SI.Type = ELF::STT_OBJECT; }) + .CaseLower("function", [&SI] { SI.Type = ELF::STT_FUNC; }) + .CaseLower("indirect-function", + [&SI] { SI.Type = ELF::STT_GNU_IFUNC; }) + .CaseLower("debug", [] {}) + .CaseLower("constructor", [] {}) + .CaseLower("warning", [] {}) + .CaseLower("indirect", [] {}) + .CaseLower("synthetic", [] {}) + .CaseLower("unique-object", [] {}) + .StartsWithLower("before", [] {}) + .Default([&] { UnsupportedFlags.push_back(Flags[I]); }))(); + if (!UnsupportedFlags.empty()) + return createStringError(errc::invalid_argument, + "unsupported flag%s for --add-symbol: '%s'", + UnsupportedFlags.size() > 1 ? "s" : "", + join(UnsupportedFlags, "', '").c_str()); + return SI; +} + +Expected<ELFCopyConfig> parseConfig(const CopyConfig &Config) { + ELFCopyConfig ELFConfig; + if (Config.NewSymbolVisibility) { + const uint8_t Invalid = 0xff; + ELFConfig.NewSymbolVisibility = + StringSwitch<uint8_t>(*Config.NewSymbolVisibility) + .Case("default", ELF::STV_DEFAULT) + .Case("hidden", ELF::STV_HIDDEN) + .Case("internal", ELF::STV_INTERNAL) + .Case("protected", ELF::STV_PROTECTED) + .Default(Invalid); + + if (ELFConfig.NewSymbolVisibility == Invalid) + return createStringError(errc::invalid_argument, + "'%s' is not a valid symbol visibility", + Config.NewSymbolVisibility->str().c_str()); + } + + for (StringRef Arg : Config.SymbolsToAdd) { + Expected<elf::NewSymbolInfo> NSI = parseNewSymbolInfo( + Arg, + ELFConfig.NewSymbolVisibility.getValueOr((uint8_t)ELF::STV_DEFAULT)); + if (!NSI) + return NSI.takeError(); + ELFConfig.SymbolsToAdd.push_back(*NSI); + } + + return ELFConfig; +} + +} // end namespace elf +} // end namespace objcopy +} // end namespace llvm diff --git a/tools/llvm-objcopy/ELF/ELFConfig.h b/tools/llvm-objcopy/ELF/ELFConfig.h new file mode 100644 index 000000000000..977efbc4166f --- /dev/null +++ b/tools/llvm-objcopy/ELF/ELFConfig.h @@ -0,0 +1,44 @@ +//===- ELFConfig.h ----------------------------------------------*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_TOOLS_OBJCOPY_ELFCONFIG_H +#define LLVM_TOOLS_OBJCOPY_ELFCONFIG_H + +#include "llvm/ADT/Optional.h" +#include "llvm/ADT/StringRef.h" +#include "llvm/Object/ELFTypes.h" +#include "llvm/Support/Error.h" +#include <vector> + +namespace llvm { +namespace objcopy { +struct CopyConfig; + +namespace elf { + +struct NewSymbolInfo { + StringRef SymbolName; + StringRef SectionName; + uint64_t Value = 0; + uint8_t Type = ELF::STT_NOTYPE; + uint8_t Bind = ELF::STB_GLOBAL; + uint8_t Visibility = ELF::STV_DEFAULT; +}; + +struct ELFCopyConfig { + Optional<uint8_t> NewSymbolVisibility; + std::vector<NewSymbolInfo> SymbolsToAdd; +}; + +Expected<ELFCopyConfig> parseConfig(const CopyConfig &Config); + +} // namespace elf +} // namespace objcopy +} // namespace llvm + +#endif diff --git a/tools/llvm-objcopy/ELF/ELFObjcopy.cpp b/tools/llvm-objcopy/ELF/ELFObjcopy.cpp index b366c6e55987..8bf7e0f88010 100644 --- a/tools/llvm-objcopy/ELF/ELFObjcopy.cpp +++ b/tools/llvm-objcopy/ELF/ELFObjcopy.cpp @@ -136,16 +136,16 @@ static std::unique_ptr<Writer> createELFWriter(const CopyConfig &Config, // Depending on the initial ELFT and OutputFormat we need a different Writer. switch (OutputElfType) { case ELFT_ELF32LE: - return llvm::make_unique<ELFWriter<ELF32LE>>(Obj, Buf, + return std::make_unique<ELFWriter<ELF32LE>>(Obj, Buf, !Config.StripSections); case ELFT_ELF64LE: - return llvm::make_unique<ELFWriter<ELF64LE>>(Obj, Buf, + return std::make_unique<ELFWriter<ELF64LE>>(Obj, Buf, !Config.StripSections); case ELFT_ELF32BE: - return llvm::make_unique<ELFWriter<ELF32BE>>(Obj, Buf, + return std::make_unique<ELFWriter<ELF32BE>>(Obj, Buf, !Config.StripSections); case ELFT_ELF64BE: - return llvm::make_unique<ELFWriter<ELF64BE>>(Obj, Buf, + return std::make_unique<ELFWriter<ELF64BE>>(Obj, Buf, !Config.StripSections); } llvm_unreachable("Invalid output format"); @@ -156,9 +156,9 @@ static std::unique_ptr<Writer> createWriter(const CopyConfig &Config, ElfType OutputElfType) { switch (Config.OutputFormat) { case FileFormat::Binary: - return llvm::make_unique<BinaryWriter>(Obj, Buf); + return std::make_unique<BinaryWriter>(Obj, Buf); case FileFormat::IHex: - return llvm::make_unique<IHexWriter>(Obj, Buf); + return std::make_unique<IHexWriter>(Obj, Buf); default: return createELFWriter(Config, Obj, Buf, OutputElfType); } @@ -263,7 +263,7 @@ static Error linkToBuildIdDir(const CopyConfig &Config, StringRef ToLink, static Error splitDWOToFile(const CopyConfig &Config, const Reader &Reader, StringRef File, ElfType OutputElfType) { - auto DWOFile = Reader.create(); + auto DWOFile = Reader.create(false); auto OnlyKeepDWOPred = [&DWOFile](const SectionBase &Sec) { return onlyKeepDWOPred(*DWOFile, Sec); }; @@ -305,9 +305,9 @@ static Error dumpSectionToFile(StringRef SecName, StringRef Filename, SecName.str().c_str()); } -static bool isCompressable(const SectionBase &Section) { - return !(Section.Flags & ELF::SHF_COMPRESSED) && - StringRef(Section.Name).startswith(".debug"); +static bool isCompressable(const SectionBase &Sec) { + return !(Sec.Flags & ELF::SHF_COMPRESSED) && + StringRef(Sec.Name).startswith(".debug"); } static void replaceDebugSections( @@ -356,7 +356,7 @@ static Error updateAndRemoveSymbols(const CopyConfig &Config, Object &Obj) { if (!Sym.isCommon() && Sym.getShndx() != SHN_UNDEF && ((Config.LocalizeHidden && (Sym.Visibility == STV_HIDDEN || Sym.Visibility == STV_INTERNAL)) || - is_contained(Config.SymbolsToLocalize, Sym.Name))) + Config.SymbolsToLocalize.matches(Sym.Name))) Sym.Binding = STB_LOCAL; // Note: these two globalize flags have very similar names but different @@ -370,16 +370,15 @@ static Error updateAndRemoveSymbols(const CopyConfig &Config, Object &Obj) { // --keep-global-symbol. Because of that, make sure to check // --globalize-symbol second. if (!Config.SymbolsToKeepGlobal.empty() && - !is_contained(Config.SymbolsToKeepGlobal, Sym.Name) && + !Config.SymbolsToKeepGlobal.matches(Sym.Name) && Sym.getShndx() != SHN_UNDEF) Sym.Binding = STB_LOCAL; - if (is_contained(Config.SymbolsToGlobalize, Sym.Name) && + if (Config.SymbolsToGlobalize.matches(Sym.Name) && Sym.getShndx() != SHN_UNDEF) Sym.Binding = STB_GLOBAL; - if (is_contained(Config.SymbolsToWeaken, Sym.Name) && - Sym.Binding == STB_GLOBAL) + if (Config.SymbolsToWeaken.matches(Sym.Name) && Sym.Binding == STB_GLOBAL) Sym.Binding = STB_WEAK; if (Config.Weaken && Sym.Binding == STB_GLOBAL && @@ -399,12 +398,12 @@ static Error updateAndRemoveSymbols(const CopyConfig &Config, Object &Obj) { // symbols are still 'needed' and which are not. if (Config.StripUnneeded || !Config.UnneededSymbolsToRemove.empty() || !Config.OnlySection.empty()) { - for (auto &Section : Obj.sections()) - Section.markSymbols(); + for (SectionBase &Sec : Obj.sections()) + Sec.markSymbols(); } auto RemoveSymbolsPred = [&](const Symbol &Sym) { - if (is_contained(Config.SymbolsToKeep, Sym.Name) || + if (Config.SymbolsToKeep.matches(Sym.Name) || (Config.KeepFileSymbols && Sym.Type == STT_FILE)) return false; @@ -418,12 +417,12 @@ static Error updateAndRemoveSymbols(const CopyConfig &Config, Object &Obj) { if (Config.StripAll || Config.StripAllGNU) return true; - if (is_contained(Config.SymbolsToRemove, Sym.Name)) + if (Config.SymbolsToRemove.matches(Sym.Name)) return true; if ((Config.StripUnneeded || - is_contained(Config.UnneededSymbolsToRemove, Sym.Name)) && - isUnneededSymbol(Sym)) + Config.UnneededSymbolsToRemove.matches(Sym.Name)) && + (!Obj.isRelocatable() || isUnneededSymbol(Sym))) return true; // We want to remove undefined symbols if all references have been stripped. @@ -443,7 +442,7 @@ static Error replaceAndRemoveSections(const CopyConfig &Config, Object &Obj) { // Removes: if (!Config.ToRemove.empty()) { RemovePred = [&Config](const SectionBase &Sec) { - return is_contained(Config.ToRemove, Sec.Name); + return Config.ToRemove.matches(Sec.Name); }; } @@ -481,7 +480,7 @@ static Error replaceAndRemoveSections(const CopyConfig &Config, Object &Obj) { }; } - if (Config.StripDebug) { + if (Config.StripDebug || Config.StripUnneeded) { RemovePred = [RemovePred](const SectionBase &Sec) { return RemovePred(Sec) || isDebugSection(Sec); }; @@ -523,7 +522,7 @@ static Error replaceAndRemoveSections(const CopyConfig &Config, Object &Obj) { if (!Config.OnlySection.empty()) { RemovePred = [&Config, RemovePred, &Obj](const SectionBase &Sec) { // Explicitly keep these sections regardless of previous removes. - if (is_contained(Config.OnlySection, Sec.Name)) + if (Config.OnlySection.matches(Sec.Name)) return false; // Allow all implicit removes. @@ -545,7 +544,7 @@ static Error replaceAndRemoveSections(const CopyConfig &Config, Object &Obj) { if (!Config.KeepSection.empty()) { RemovePred = [&Config, RemovePred](const SectionBase &Sec) { // Explicitly keep these sections regardless of previous removes. - if (is_contained(Config.KeepSection, Sec.Name)) + if (Config.KeepSection.matches(Sec.Name)) return false; // Otherwise defer to RemovePred. return RemovePred(Sec); @@ -614,9 +613,8 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj, if (Error E = updateAndRemoveSymbols(Config, Obj)) return E; - if (!Config.SectionsToRename.empty() || !Config.AllocSectionsPrefix.empty()) { - DenseSet<SectionBase *> PrefixedSections; - for (auto &Sec : Obj.sections()) { + if (!Config.SectionsToRename.empty()) { + for (SectionBase &Sec : Obj.sections()) { const auto Iter = Config.SectionsToRename.find(Sec.Name); if (Iter != Config.SectionsToRename.end()) { const SectionRename &SR = Iter->second; @@ -624,63 +622,62 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj, if (SR.NewFlags.hasValue()) setSectionFlagsAndType(Sec, SR.NewFlags.getValue()); } + } + } - // Add a prefix to allocated sections and their relocation sections. This - // should be done after renaming the section by Config.SectionToRename to - // imitate the GNU objcopy behavior. - if (!Config.AllocSectionsPrefix.empty()) { - if (Sec.Flags & SHF_ALLOC) { - Sec.Name = (Config.AllocSectionsPrefix + Sec.Name).str(); - PrefixedSections.insert(&Sec); - - // Rename relocation sections associated to the allocated sections. - // For example, if we rename .text to .prefix.text, we also rename - // .rel.text to .rel.prefix.text. - // - // Dynamic relocation sections (SHT_REL[A] with SHF_ALLOC) are handled - // above, e.g., .rela.plt is renamed to .prefix.rela.plt, not - // .rela.prefix.plt since GNU objcopy does so. - } else if (auto *RelocSec = dyn_cast<RelocationSectionBase>(&Sec)) { - auto *TargetSec = RelocSec->getSection(); - if (TargetSec && (TargetSec->Flags & SHF_ALLOC)) { - StringRef prefix; - switch (Sec.Type) { - case SHT_REL: - prefix = ".rel"; - break; - case SHT_RELA: - prefix = ".rela"; - break; - default: - continue; - } - - // If the relocation section comes *after* the target section, we - // don't add Config.AllocSectionsPrefix because we've already added - // the prefix to TargetSec->Name. Otherwise, if the relocation - // section comes *before* the target section, we add the prefix. - if (PrefixedSections.count(TargetSec)) { - Sec.Name = (prefix + TargetSec->Name).str(); - } else { - const auto Iter = Config.SectionsToRename.find(TargetSec->Name); - if (Iter != Config.SectionsToRename.end()) { - // Both `--rename-section` and `--prefix-alloc-sections` are - // given but the target section is not yet renamed. - Sec.Name = - (prefix + Config.AllocSectionsPrefix + Iter->second.NewName) - .str(); - } else { - Sec.Name = - (prefix + Config.AllocSectionsPrefix + TargetSec->Name) - .str(); - } - } + // Add a prefix to allocated sections and their relocation sections. This + // should be done after renaming the section by Config.SectionToRename to + // imitate the GNU objcopy behavior. + if (!Config.AllocSectionsPrefix.empty()) { + DenseSet<SectionBase *> PrefixedSections; + for (SectionBase &Sec : Obj.sections()) { + if (Sec.Flags & SHF_ALLOC) { + Sec.Name = (Config.AllocSectionsPrefix + Sec.Name).str(); + PrefixedSections.insert(&Sec); + } else if (auto *RelocSec = dyn_cast<RelocationSectionBase>(&Sec)) { + // Rename relocation sections associated to the allocated sections. + // For example, if we rename .text to .prefix.text, we also rename + // .rel.text to .rel.prefix.text. + // + // Dynamic relocation sections (SHT_REL[A] with SHF_ALLOC) are handled + // above, e.g., .rela.plt is renamed to .prefix.rela.plt, not + // .rela.prefix.plt since GNU objcopy does so. + const SectionBase *TargetSec = RelocSec->getSection(); + if (TargetSec && (TargetSec->Flags & SHF_ALLOC)) { + StringRef prefix; + switch (Sec.Type) { + case SHT_REL: + prefix = ".rel"; + break; + case SHT_RELA: + prefix = ".rela"; + break; + default: + llvm_unreachable("not a relocation section"); } + + // If the relocation section comes *after* the target section, we + // don't add Config.AllocSectionsPrefix because we've already added + // the prefix to TargetSec->Name. Otherwise, if the relocation + // section comes *before* the target section, we add the prefix. + if (PrefixedSections.count(TargetSec)) + Sec.Name = (prefix + TargetSec->Name).str(); + else + Sec.Name = + (prefix + Config.AllocSectionsPrefix + TargetSec->Name).str(); } } } } + if (!Config.SetSectionAlignment.empty()) { + for (SectionBase &Sec : Obj.sections()) { + auto I = Config.SetSectionAlignment.find(Sec.Name); + if (I != Config.SetSectionAlignment.end()) + Sec.Align = I->second; + } + } + if (!Config.SetSectionFlags.empty()) { for (auto &Sec : Obj.sections()) { const auto Iter = Config.SetSectionFlags.find(Sec.Name); @@ -721,7 +718,7 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj, Obj.addSection<GnuDebugLinkSection>(Config.AddGnuDebugLink, Config.GnuDebugLinkCRC32); - for (const NewSymbolInfo &SI : Config.SymbolsToAdd) { + for (const NewSymbolInfo &SI : Config.ELF->SymbolsToAdd) { SectionBase *Sec = Obj.findSection(SI.SectionName); uint64_t Value = Sec ? Sec->Addr + SI.Value : SI.Value; Obj.SymbolTable->addSymbol( @@ -746,9 +743,9 @@ static Error writeOutput(const CopyConfig &Config, Object &Obj, Buffer &Out, Error executeObjcopyOnIHex(const CopyConfig &Config, MemoryBuffer &In, Buffer &Out) { IHexReader Reader(&In); - std::unique_ptr<Object> Obj = Reader.create(); + std::unique_ptr<Object> Obj = Reader.create(true); const ElfType OutputElfType = - getOutputElfType(Config.OutputArch.getValueOr(Config.BinaryArch)); + getOutputElfType(Config.OutputArch.getValueOr(MachineInfo())); if (Error E = handleArgs(Config, *Obj, Reader, OutputElfType)) return E; return writeOutput(Config, *Obj, Out, OutputElfType); @@ -756,13 +753,15 @@ Error executeObjcopyOnIHex(const CopyConfig &Config, MemoryBuffer &In, Error executeObjcopyOnRawBinary(const CopyConfig &Config, MemoryBuffer &In, Buffer &Out) { - BinaryReader Reader(Config.BinaryArch, &In); - std::unique_ptr<Object> Obj = Reader.create(); + uint8_t NewSymbolVisibility = + Config.ELF->NewSymbolVisibility.getValueOr((uint8_t)ELF::STV_DEFAULT); + BinaryReader Reader(&In, NewSymbolVisibility); + std::unique_ptr<Object> Obj = Reader.create(true); // Prefer OutputArch (-O<format>) if set, otherwise fallback to BinaryArch // (-B<arch>). const ElfType OutputElfType = - getOutputElfType(Config.OutputArch.getValueOr(Config.BinaryArch)); + getOutputElfType(Config.OutputArch.getValueOr(MachineInfo())); if (Error E = handleArgs(Config, *Obj, Reader, OutputElfType)) return E; return writeOutput(Config, *Obj, Out, OutputElfType); @@ -771,7 +770,7 @@ Error executeObjcopyOnRawBinary(const CopyConfig &Config, MemoryBuffer &In, Error executeObjcopyOnBinary(const CopyConfig &Config, object::ELFObjectFileBase &In, Buffer &Out) { ELFReader Reader(&In, Config.ExtractPartition); - std::unique_ptr<Object> Obj = Reader.create(); + std::unique_ptr<Object> Obj = Reader.create(!Config.SymbolsToAdd.empty()); // Prefer OutputArch (-O<format>) if set, otherwise infer it from the input. const ElfType OutputElfType = Config.OutputArch ? getOutputElfType(Config.OutputArch.getValue()) diff --git a/tools/llvm-objcopy/ELF/Object.cpp b/tools/llvm-objcopy/ELF/Object.cpp index fa696380e17c..74145dad6e6b 100644 --- a/tools/llvm-objcopy/ELF/Object.cpp +++ b/tools/llvm-objcopy/ELF/Object.cpp @@ -397,7 +397,7 @@ void SectionWriter::visit(const OwnedDataSection &Sec) { llvm::copy(Sec.Data, Out.getBufferStart() + Sec.Offset); } -static const std::vector<uint8_t> ZlibGnuMagic = {'Z', 'L', 'I', 'B'}; +static constexpr std::array<uint8_t, 4> ZlibGnuMagic = {{'Z', 'L', 'I', 'B'}}; static bool isDataGnuCompressed(ArrayRef<uint8_t> Data) { return Data.size() > ZlibGnuMagic.size() && @@ -665,7 +665,7 @@ void SymbolTableSection::addSymbol(Twine Name, uint8_t Bind, uint8_t Type, Sym.Visibility = Visibility; Sym.Size = SymbolSize; Sym.Index = Symbols.size(); - Symbols.emplace_back(llvm::make_unique<Symbol>(Sym)); + Symbols.emplace_back(std::make_unique<Symbol>(Sym)); Size += this->EntrySize; } @@ -1055,29 +1055,28 @@ void GroupSection::accept(MutableSectionVisitor &Visitor) { } // Returns true IFF a section is wholly inside the range of a segment -static bool sectionWithinSegment(const SectionBase &Section, - const Segment &Segment) { +static bool sectionWithinSegment(const SectionBase &Sec, const Segment &Seg) { // If a section is empty it should be treated like it has a size of 1. This is // to clarify the case when an empty section lies on a boundary between two // segments and ensures that the section "belongs" to the second segment and // not the first. - uint64_t SecSize = Section.Size ? Section.Size : 1; + uint64_t SecSize = Sec.Size ? Sec.Size : 1; - if (Section.Type == SHT_NOBITS) { - if (!(Section.Flags & SHF_ALLOC)) + if (Sec.Type == SHT_NOBITS) { + if (!(Sec.Flags & SHF_ALLOC)) return false; - bool SectionIsTLS = Section.Flags & SHF_TLS; - bool SegmentIsTLS = Segment.Type == PT_TLS; + bool SectionIsTLS = Sec.Flags & SHF_TLS; + bool SegmentIsTLS = Seg.Type == PT_TLS; if (SectionIsTLS != SegmentIsTLS) return false; - return Segment.VAddr <= Section.Addr && - Segment.VAddr + Segment.MemSize >= Section.Addr + SecSize; + return Seg.VAddr <= Sec.Addr && + Seg.VAddr + Seg.MemSize >= Sec.Addr + SecSize; } - return Segment.Offset <= Section.OriginalOffset && - Segment.Offset + Segment.FileSize >= Section.OriginalOffset + SecSize; + return Seg.Offset <= Sec.OriginalOffset && + Seg.Offset + Seg.FileSize >= Sec.OriginalOffset + SecSize; } // Returns true IFF a segment's original offset is inside of another segment's @@ -1113,7 +1112,7 @@ void BasicELFBuilder::initFileHeader() { Obj->OSABI = ELFOSABI_NONE; Obj->ABIVersion = 0; Obj->Entry = 0x0; - Obj->Machine = EMachine; + Obj->Machine = EM_NONE; Obj->Version = 1; } @@ -1141,8 +1140,8 @@ SymbolTableSection *BasicELFBuilder::addSymTab(StringTableSection *StrTab) { } void BasicELFBuilder::initSections() { - for (auto &Section : Obj->sections()) - Section.initialize(Obj->sections()); + for (SectionBase &Sec : Obj->sections()) + Sec.initialize(Obj->sections()); } void BinaryELFBuilder::addData(SymbolTableSection *SymTab) { @@ -1161,11 +1160,12 @@ void BinaryELFBuilder::addData(SymbolTableSection *SymTab) { Twine Prefix = Twine("_binary_") + SanitizedFilename; SymTab->addSymbol(Prefix + "_start", STB_GLOBAL, STT_NOTYPE, &DataSection, - /*Value=*/0, STV_DEFAULT, 0, 0); + /*Value=*/0, NewSymbolVisibility, 0, 0); SymTab->addSymbol(Prefix + "_end", STB_GLOBAL, STT_NOTYPE, &DataSection, - /*Value=*/DataSection.Size, STV_DEFAULT, 0, 0); + /*Value=*/DataSection.Size, NewSymbolVisibility, 0, 0); SymTab->addSymbol(Prefix + "_size", STB_GLOBAL, STT_NOTYPE, nullptr, - /*Value=*/DataSection.Size, STV_DEFAULT, SHN_ABS, 0); + /*Value=*/DataSection.Size, NewSymbolVisibility, SHN_ABS, + 0); } std::unique_ptr<Object> BinaryELFBuilder::build() { @@ -1255,10 +1255,9 @@ template <class ELFT> void ELFBuilder<ELFT>::findEhdrOffset() { if (!ExtractPartition) return; - for (const SectionBase &Section : Obj.sections()) { - if (Section.Type == SHT_LLVM_PART_EHDR && - Section.Name == *ExtractPartition) { - EhdrOffset = Section.Offset; + for (const SectionBase &Sec : Obj.sections()) { + if (Sec.Type == SHT_LLVM_PART_EHDR && Sec.Name == *ExtractPartition) { + EhdrOffset = Sec.Offset; return; } } @@ -1287,15 +1286,12 @@ void ELFBuilder<ELFT>::readProgramHeaders(const ELFFile<ELFT> &HeadersFile) { Seg.MemSize = Phdr.p_memsz; Seg.Align = Phdr.p_align; Seg.Index = Index++; - for (SectionBase &Section : Obj.sections()) { - if (sectionWithinSegment(Section, Seg)) { - Seg.addSection(&Section); - if (!Section.ParentSegment || - Section.ParentSegment->Offset > Seg.Offset) { - Section.ParentSegment = &Seg; - } + for (SectionBase &Sec : Obj.sections()) + if (sectionWithinSegment(Sec, Seg)) { + Seg.addSection(&Sec); + if (!Sec.ParentSegment || Sec.ParentSegment->Offset > Seg.Offset) + Sec.ParentSegment = &Seg; } - } } auto &ElfHdr = Obj.ElfHdrSegment; @@ -1531,7 +1527,7 @@ template <class ELFT> void ELFBuilder<ELFT>::readSectionHeaders() { } } -template <class ELFT> void ELFBuilder<ELFT>::readSections() { +template <class ELFT> void ELFBuilder<ELFT>::readSections(bool EnsureSymtab) { // If a section index table exists we'll need to initialize it before we // initialize the symbol table because the symbol table might need to // reference it. @@ -1544,16 +1540,37 @@ template <class ELFT> void ELFBuilder<ELFT>::readSections() { if (Obj.SymbolTable) { Obj.SymbolTable->initialize(Obj.sections()); initSymbolTable(Obj.SymbolTable); + } else if (EnsureSymtab) { + // Reuse the existing SHT_STRTAB section if exists. + StringTableSection *StrTab = nullptr; + for (auto &Sec : Obj.sections()) { + if (Sec.Type == ELF::SHT_STRTAB && !(Sec.Flags & SHF_ALLOC)) { + StrTab = static_cast<StringTableSection *>(&Sec); + + // Prefer .strtab to .shstrtab. + if (Obj.SectionNames != &Sec) + break; + } + } + if (!StrTab) + StrTab = &Obj.addSection<StringTableSection>(); + + SymbolTableSection &SymTab = Obj.addSection<SymbolTableSection>(); + SymTab.Name = ".symtab"; + SymTab.Link = StrTab->Index; + SymTab.initialize(Obj.sections()); + SymTab.addSymbol("", 0, 0, nullptr, 0, 0, 0, 0); + Obj.SymbolTable = &SymTab; } // Now that all sections and symbols have been added we can add // relocations that reference symbols and set the link and info fields for // relocation sections. - for (auto &Section : Obj.sections()) { - if (&Section == Obj.SymbolTable) + for (auto &Sec : Obj.sections()) { + if (&Sec == Obj.SymbolTable) continue; - Section.initialize(Obj.sections()); - if (auto RelSec = dyn_cast<RelocationSection>(&Section)) { + Sec.initialize(Obj.sections()); + if (auto RelSec = dyn_cast<RelocationSection>(&Sec)) { auto Shdr = unwrapOrError(ElfFile.sections()).begin() + RelSec->Index; if (RelSec->Type == SHT_REL) initRelocations(RelSec, Obj.SymbolTable, @@ -1561,7 +1578,7 @@ template <class ELFT> void ELFBuilder<ELFT>::readSections() { else initRelocations(RelSec, Obj.SymbolTable, unwrapOrError(ElfFile.relas(Shdr))); - } else if (auto GroupSec = dyn_cast<GroupSection>(&Section)) { + } else if (auto GroupSec = dyn_cast<GroupSection>(&Sec)) { initGroupSection(GroupSec); } } @@ -1582,7 +1599,7 @@ template <class ELFT> void ELFBuilder<ELFT>::readSections() { " is not a string table"); } -template <class ELFT> void ELFBuilder<ELFT>::build() { +template <class ELFT> void ELFBuilder<ELFT>::build(bool EnsureSymtab) { readSectionHeaders(); findEhdrOffset(); @@ -1601,7 +1618,7 @@ template <class ELFT> void ELFBuilder<ELFT>::build() { Obj.Entry = Ehdr.e_entry; Obj.Flags = Ehdr.e_flags; - readSections(); + readSections(EnsureSymtab); readProgramHeaders(HeadersFile); } @@ -1609,8 +1626,8 @@ Writer::~Writer() {} Reader::~Reader() {} -std::unique_ptr<Object> BinaryReader::create() const { - return BinaryELFBuilder(MInfo.EMachine, MemBuf).build(); +std::unique_ptr<Object> BinaryReader::create(bool /*EnsureSymtab*/) const { + return BinaryELFBuilder(MemBuf, NewSymbolVisibility).build(); } Expected<std::vector<IHexRecord>> IHexReader::parse() const { @@ -1639,28 +1656,28 @@ Expected<std::vector<IHexRecord>> IHexReader::parse() const { return std::move(Records); } -std::unique_ptr<Object> IHexReader::create() const { +std::unique_ptr<Object> IHexReader::create(bool /*EnsureSymtab*/) const { std::vector<IHexRecord> Records = unwrapOrError(parse()); return IHexELFBuilder(Records).build(); } -std::unique_ptr<Object> ELFReader::create() const { - auto Obj = llvm::make_unique<Object>(); +std::unique_ptr<Object> ELFReader::create(bool EnsureSymtab) const { + auto Obj = std::make_unique<Object>(); if (auto *O = dyn_cast<ELFObjectFile<ELF32LE>>(Bin)) { ELFBuilder<ELF32LE> Builder(*O, *Obj, ExtractPartition); - Builder.build(); + Builder.build(EnsureSymtab); return Obj; } else if (auto *O = dyn_cast<ELFObjectFile<ELF64LE>>(Bin)) { ELFBuilder<ELF64LE> Builder(*O, *Obj, ExtractPartition); - Builder.build(); + Builder.build(EnsureSymtab); return Obj; } else if (auto *O = dyn_cast<ELFObjectFile<ELF32BE>>(Bin)) { ELFBuilder<ELF32BE> Builder(*O, *Obj, ExtractPartition); - Builder.build(); + Builder.build(EnsureSymtab); return Obj; } else if (auto *O = dyn_cast<ELFObjectFile<ELF64BE>>(Bin)) { ELFBuilder<ELF64BE> Builder(*O, *Obj, ExtractPartition); - Builder.build(); + Builder.build(EnsureSymtab); return Obj; } error("invalid file type"); @@ -1693,7 +1710,7 @@ template <class ELFT> void ELFWriter<ELFT>::writeEhdr() { Ehdr.e_ehsize = sizeof(Elf_Ehdr); if (WriteSectionHeaders && Obj.sections().size() != 0) { Ehdr.e_shentsize = sizeof(Elf_Shdr); - Ehdr.e_shoff = Obj.SHOffset; + Ehdr.e_shoff = Obj.SHOff; // """ // If the number of sections is greater than or equal to // SHN_LORESERVE (0xff00), this member has the value zero and the actual @@ -1732,7 +1749,7 @@ template <class ELFT> void ELFWriter<ELFT>::writeShdrs() { // This reference serves to write the dummy section header at the begining // of the file. It is not used for anything else Elf_Shdr &Shdr = - *reinterpret_cast<Elf_Shdr *>(Buf.getBufferStart() + Obj.SHOffset); + *reinterpret_cast<Elf_Shdr *>(Buf.getBufferStart() + Obj.SHOff); Shdr.sh_name = 0; Shdr.sh_type = SHT_NULL; Shdr.sh_flags = 0; @@ -1862,26 +1879,13 @@ void Object::sortSections() { }); } -static uint64_t alignToAddr(uint64_t Offset, uint64_t Addr, uint64_t Align) { - // Calculate Diff such that (Offset + Diff) & -Align == Addr & -Align. - if (Align == 0) - Align = 1; - auto Diff = - static_cast<int64_t>(Addr % Align) - static_cast<int64_t>(Offset % Align); - // We only want to add to Offset, however, so if Diff < 0 we can add Align and - // (Offset + Diff) & -Align == Addr & -Align will still hold. - if (Diff < 0) - Diff += Align; - return Offset + Diff; -} - // Orders segments such that if x = y->ParentSegment then y comes before x. static void orderSegments(std::vector<Segment *> &Segments) { llvm::stable_sort(Segments, compareSegmentsByOffset); } // This function finds a consistent layout for a list of segments starting from -// an Offset. It assumes that Segments have been sorted by OrderSegments and +// an Offset. It assumes that Segments have been sorted by orderSegments and // returns an Offset one past the end of the last segment. static uint64_t layoutSegments(std::vector<Segment *> &Segments, uint64_t Offset) { @@ -1902,8 +1906,8 @@ static uint64_t layoutSegments(std::vector<Segment *> &Segments, Seg->Offset = Parent->Offset + Seg->OriginalOffset - Parent->OriginalOffset; } else { - Offset = alignToAddr(Offset, Seg->VAddr, Seg->Align); - Seg->Offset = Offset; + Seg->Offset = + alignTo(Offset, std::max<uint64_t>(Seg->Align, 1), Seg->VAddr); } Offset = std::max(Offset, Seg->Offset + Seg->FileSize); } @@ -1925,17 +1929,17 @@ static uint64_t layoutSections(Range Sections, uint64_t Offset) { // of the segment we can assign a new offset to the section. For sections not // covered by segments we can just bump Offset to the next valid location. uint32_t Index = 1; - for (auto &Section : Sections) { - Section.Index = Index++; - if (Section.ParentSegment != nullptr) { - auto Segment = *Section.ParentSegment; - Section.Offset = - Segment.Offset + (Section.OriginalOffset - Segment.OriginalOffset); + for (auto &Sec : Sections) { + Sec.Index = Index++; + if (Sec.ParentSegment != nullptr) { + auto Segment = *Sec.ParentSegment; + Sec.Offset = + Segment.Offset + (Sec.OriginalOffset - Segment.OriginalOffset); } else { - Offset = alignTo(Offset, Section.Align == 0 ? 1 : Section.Align); - Section.Offset = Offset; - if (Section.Type != SHT_NOBITS) - Offset += Section.Size; + Offset = alignTo(Offset, Sec.Align == 0 ? 1 : Sec.Align); + Sec.Offset = Offset; + if (Sec.Type != SHT_NOBITS) + Offset += Sec.Size; } } return Offset; @@ -1971,16 +1975,16 @@ template <class ELFT> void ELFWriter<ELFT>::assignOffsets() { // Offset so that SHOffset is valid. if (WriteSectionHeaders) Offset = alignTo(Offset, sizeof(Elf_Addr)); - Obj.SHOffset = Offset; + Obj.SHOff = Offset; } template <class ELFT> size_t ELFWriter<ELFT>::totalSize() const { // We already have the section header offset so we can calculate the total // size by just adding up the size of each section header. if (!WriteSectionHeaders) - return Obj.SHOffset; + return Obj.SHOff; size_t ShdrCount = Obj.sections().size() + 1; // Includes null shdr. - return Obj.SHOffset + ShdrCount * sizeof(Elf_Shdr); + return Obj.SHOff + ShdrCount * sizeof(Elf_Shdr); } template <class ELFT> Error ELFWriter<ELFT>::write() { @@ -1995,6 +1999,25 @@ template <class ELFT> Error ELFWriter<ELFT>::write() { return Buf.commit(); } +static Error removeUnneededSections(Object &Obj) { + // We can remove an empty symbol table from non-relocatable objects. + // Relocatable objects typically have relocation sections whose + // sh_link field points to .symtab, so we can't remove .symtab + // even if it is empty. + if (Obj.isRelocatable() || Obj.SymbolTable == nullptr || + !Obj.SymbolTable->empty()) + return Error::success(); + + // .strtab can be used for section names. In such a case we shouldn't + // remove it. + auto *StrTab = Obj.SymbolTable->getStrTab() == Obj.SectionNames + ? nullptr + : Obj.SymbolTable->getStrTab(); + return Obj.removeSections(false, [&](const SectionBase &Sec) { + return &Sec == Obj.SymbolTable || &Sec == StrTab; + }); +} + template <class ELFT> Error ELFWriter<ELFT>::finalize() { // It could happen that SectionNames has been removed and yet the user wants // a section header table output. We need to throw an error if a user tries @@ -2004,6 +2027,8 @@ template <class ELFT> Error ELFWriter<ELFT>::finalize() { "cannot write section header table because " "section header string table was removed"); + if (Error E = removeUnneededSections(Obj)) + return E; Obj.sortSections(); // We need to assign indexes before we perform layout because we need to know @@ -2045,9 +2070,8 @@ template <class ELFT> Error ELFWriter<ELFT>::finalize() { // Make sure we add the names of all the sections. Importantly this must be // done after we decide to add or remove SectionIndexes. if (Obj.SectionNames != nullptr) - for (const auto &Section : Obj.sections()) { - Obj.SectionNames->addString(Section.Name); - } + for (const SectionBase &Sec : Obj.sections()) + Obj.SectionNames->addString(Sec.Name); initEhdrSegment(); @@ -2055,8 +2079,8 @@ template <class ELFT> Error ELFWriter<ELFT>::finalize() { // Also, the output arch may not be the same as the input arch, so fix up // size-related fields before doing layout calculations. uint64_t Index = 0; - auto SecSizer = llvm::make_unique<ELFSectionSizer<ELFT>>(); - for (auto &Sec : Obj.sections()) { + auto SecSizer = std::make_unique<ELFSectionSizer<ELFT>>(); + for (SectionBase &Sec : Obj.sections()) { Sec.Index = Index++; Sec.accept(*SecSizer); } @@ -2082,40 +2106,36 @@ template <class ELFT> Error ELFWriter<ELFT>::finalize() { // Finally now that all offsets and indexes have been set we can finalize any // remaining issues. - uint64_t Offset = Obj.SHOffset + sizeof(Elf_Shdr); - for (SectionBase &Section : Obj.sections()) { - Section.HeaderOffset = Offset; + uint64_t Offset = Obj.SHOff + sizeof(Elf_Shdr); + for (SectionBase &Sec : Obj.sections()) { + Sec.HeaderOffset = Offset; Offset += sizeof(Elf_Shdr); if (WriteSectionHeaders) - Section.NameIndex = Obj.SectionNames->findIndex(Section.Name); - Section.finalize(); + Sec.NameIndex = Obj.SectionNames->findIndex(Sec.Name); + Sec.finalize(); } if (Error E = Buf.allocate(totalSize())) return E; - SecWriter = llvm::make_unique<ELFSectionWriter<ELFT>>(Buf); + SecWriter = std::make_unique<ELFSectionWriter<ELFT>>(Buf); return Error::success(); } Error BinaryWriter::write() { - for (auto &Section : Obj.sections()) - if (Section.Flags & SHF_ALLOC) - Section.accept(*SecWriter); + for (const SectionBase &Sec : Obj.allocSections()) + Sec.accept(*SecWriter); return Buf.commit(); } Error BinaryWriter::finalize() { - // TODO: Create a filter range to construct OrderedSegments from so that this - // code can be deduped with assignOffsets above. This should also solve the - // todo below for LayoutSections. // We need a temporary list of segments that has a special order to it // so that we know that anytime ->ParentSegment is set that segment has // already had it's offset properly set. We only want to consider the segments // that will affect layout of allocated sections so we only add those. std::vector<Segment *> OrderedSegments; - for (SectionBase &Section : Obj.sections()) - if ((Section.Flags & SHF_ALLOC) != 0 && Section.ParentSegment != nullptr) - OrderedSegments.push_back(Section.ParentSegment); + for (const SectionBase &Sec : Obj.allocSections()) + if (Sec.ParentSegment != nullptr) + OrderedSegments.push_back(Sec.ParentSegment); // For binary output, we're going to use physical addresses instead of // virtual addresses, since a binary output is used for cases like ROM @@ -2130,7 +2150,7 @@ Error BinaryWriter::finalize() { llvm::stable_sort(OrderedSegments, compareSegmentsByPAddr); // Because we add a ParentSegment for each section we might have duplicate - // segments in OrderedSegments. If there were duplicates then LayoutSegments + // segments in OrderedSegments. If there were duplicates then layoutSegments // would do very strange things. auto End = std::unique(std::begin(OrderedSegments), std::end(OrderedSegments)); @@ -2158,28 +2178,20 @@ Error BinaryWriter::finalize() { } } - // TODO: generalize LayoutSections to take a range. Pass a special range - // constructed from an iterator that skips values for which a predicate does - // not hold. Then pass such a range to LayoutSections instead of constructing - // AllocatedSections here. - std::vector<SectionBase *> AllocatedSections; - for (SectionBase &Section : Obj.sections()) - if (Section.Flags & SHF_ALLOC) - AllocatedSections.push_back(&Section); - layoutSections(make_pointee_range(AllocatedSections), Offset); + layoutSections(Obj.allocSections(), Offset); // Now that every section has been laid out we just need to compute the total // file size. This might not be the same as the offset returned by - // LayoutSections, because we want to truncate the last segment to the end of + // layoutSections, because we want to truncate the last segment to the end of // its last section, to match GNU objcopy's behaviour. TotalSize = 0; - for (SectionBase *Section : AllocatedSections) - if (Section->Type != SHT_NOBITS) - TotalSize = std::max(TotalSize, Section->Offset + Section->Size); + for (const SectionBase &Sec : Obj.allocSections()) + if (Sec.Type != SHT_NOBITS) + TotalSize = std::max(TotalSize, Sec.Offset + Sec.Size); if (Error E = Buf.allocate(TotalSize)) return E; - SecWriter = llvm::make_unique<BinarySectionWriter>(Buf); + SecWriter = std::make_unique<BinarySectionWriter>(Buf); return Error::success(); } @@ -2259,17 +2271,17 @@ Error IHexWriter::finalize() { // If any section we're to write has segment then we // switch to using physical addresses. Otherwise we // use section virtual address. - for (auto &Section : Obj.sections()) - if (ShouldWrite(Section) && IsInPtLoad(Section)) { + for (const SectionBase &Sec : Obj.sections()) + if (ShouldWrite(Sec) && IsInPtLoad(Sec)) { UseSegments = true; break; } - for (auto &Section : Obj.sections()) - if (ShouldWrite(Section) && (!UseSegments || IsInPtLoad(Section))) { - if (Error E = checkSection(Section)) + for (const SectionBase &Sec : Obj.sections()) + if (ShouldWrite(Sec) && (!UseSegments || IsInPtLoad(Sec))) { + if (Error E = checkSection(Sec)) return E; - Sections.insert(&Section); + Sections.insert(&Sec); } IHexSectionWriterBase LengthCalc(Buf); diff --git a/tools/llvm-objcopy/ELF/Object.h b/tools/llvm-objcopy/ELF/Object.h index f3df93b9662f..eeacb014e4dc 100644 --- a/tools/llvm-objcopy/ELF/Object.h +++ b/tools/llvm-objcopy/ELF/Object.h @@ -57,8 +57,8 @@ public: : Sections(Secs) {} SectionTableRef(const SectionTableRef &) = default; - iterator begin() { return iterator(Sections.data()); } - iterator end() { return iterator(Sections.data() + Sections.size()); } + iterator begin() const { return iterator(Sections.data()); } + iterator end() const { return iterator(Sections.data() + Sections.size()); } size_t size() const { return Sections.size(); } SectionBase *getSection(uint32_t Index, Twine ErrMsg); @@ -863,7 +863,7 @@ public: class Reader { public: virtual ~Reader(); - virtual std::unique_ptr<Object> create() const = 0; + virtual std::unique_ptr<Object> create(bool EnsureSymtab) const = 0; }; using object::Binary; @@ -873,7 +873,6 @@ using object::OwningBinary; class BasicELFBuilder { protected: - uint16_t EMachine; std::unique_ptr<Object> Obj; void initFileHeader(); @@ -883,17 +882,18 @@ protected: void initSections(); public: - BasicELFBuilder(uint16_t EM) - : EMachine(EM), Obj(llvm::make_unique<Object>()) {} + BasicELFBuilder() : Obj(std::make_unique<Object>()) {} }; class BinaryELFBuilder : public BasicELFBuilder { MemoryBuffer *MemBuf; + uint8_t NewSymbolVisibility; void addData(SymbolTableSection *SymTab); public: - BinaryELFBuilder(uint16_t EM, MemoryBuffer *MB) - : BasicELFBuilder(EM), MemBuf(MB) {} + BinaryELFBuilder(MemoryBuffer *MB, uint8_t NewSymbolVisibility) + : BasicELFBuilder(), MemBuf(MB), + NewSymbolVisibility(NewSymbolVisibility) {} std::unique_ptr<Object> build(); }; @@ -905,7 +905,7 @@ class IHexELFBuilder : public BasicELFBuilder { public: IHexELFBuilder(const std::vector<IHexRecord> &Records) - : BasicELFBuilder(ELF::EM_386), Records(Records) {} + : BasicELFBuilder(), Records(Records) {} std::unique_ptr<Object> build(); }; @@ -926,7 +926,7 @@ private: void initGroupSection(GroupSection *GroupSec); void initSymbolTable(SymbolTableSection *SymTab); void readSectionHeaders(); - void readSections(); + void readSections(bool EnsureSymtab); void findEhdrOffset(); SectionBase &makeSection(const Elf_Shdr &Shdr); @@ -936,17 +936,17 @@ public: : ElfFile(*ElfObj.getELFFile()), Obj(Obj), ExtractPartition(ExtractPartition) {} - void build(); + void build(bool EnsureSymtab); }; class BinaryReader : public Reader { - const MachineInfo &MInfo; MemoryBuffer *MemBuf; + uint8_t NewSymbolVisibility; public: - BinaryReader(const MachineInfo &MI, MemoryBuffer *MB) - : MInfo(MI), MemBuf(MB) {} - std::unique_ptr<Object> create() const override; + BinaryReader(MemoryBuffer *MB, const uint8_t NewSymbolVisibility) + : MemBuf(MB), NewSymbolVisibility(NewSymbolVisibility) {} + std::unique_ptr<Object> create(bool EnsureSymtab) const override; }; class IHexReader : public Reader { @@ -968,7 +968,7 @@ class IHexReader : public Reader { public: IHexReader(MemoryBuffer *MB) : MemBuf(MB) {} - std::unique_ptr<Object> create() const override; + std::unique_ptr<Object> create(bool EnsureSymtab) const override; }; class ELFReader : public Reader { @@ -976,7 +976,7 @@ class ELFReader : public Reader { Optional<StringRef> ExtractPartition; public: - std::unique_ptr<Object> create() const override; + std::unique_ptr<Object> create(bool EnsureSymtab) const override; explicit ELFReader(Binary *B, Optional<StringRef> ExtractPartition) : Bin(B), ExtractPartition(ExtractPartition) {} }; @@ -990,6 +990,10 @@ private: std::vector<SegPtr> Segments; std::vector<SecPtr> RemovedSections; + static bool sectionIsAlloc(const SectionBase &Sec) { + return Sec.Flags & ELF::SHF_ALLOC; + }; + public: template <class T> using Range = iterator_range< @@ -1011,13 +1015,14 @@ public: uint8_t OSABI; uint8_t ABIVersion; uint64_t Entry; - uint64_t SHOffset; + uint64_t SHOff; uint32_t Type; uint32_t Machine; uint32_t Version; uint32_t Flags; bool HadShdrs = true; + bool MustBeRelocatable = false; StringTableSection *SectionNames = nullptr; SymbolTableSection *SymbolTable = nullptr; SectionIndexSection *SectionIndexTable = nullptr; @@ -1027,6 +1032,13 @@ public: ConstRange<SectionBase> sections() const { return make_pointee_range(Sections); } + iterator_range< + filter_iterator<pointee_iterator<std::vector<SecPtr>::const_iterator>, + decltype(§ionIsAlloc)>> + allocSections() const { + return make_filter_range(make_pointee_range(Sections), sectionIsAlloc); + } + SectionBase *findSection(StringRef Name) { auto SecIt = find_if(Sections, [&](const SecPtr &Sec) { return Sec->Name == Name; }); @@ -1041,16 +1053,20 @@ public: std::function<bool(const SectionBase &)> ToRemove); Error removeSymbols(function_ref<bool(const Symbol &)> ToRemove); template <class T, class... Ts> T &addSection(Ts &&... Args) { - auto Sec = llvm::make_unique<T>(std::forward<Ts>(Args)...); + auto Sec = std::make_unique<T>(std::forward<Ts>(Args)...); auto Ptr = Sec.get(); + MustBeRelocatable |= isa<RelocationSection>(*Ptr); Sections.emplace_back(std::move(Sec)); Ptr->Index = Sections.size(); return *Ptr; } Segment &addSegment(ArrayRef<uint8_t> Data) { - Segments.emplace_back(llvm::make_unique<Segment>(Data)); + Segments.emplace_back(std::make_unique<Segment>(Data)); return *Segments.back(); } + bool isRelocatable() const { + return (Type != ELF::ET_DYN && Type != ELF::ET_EXEC) || MustBeRelocatable; + } }; } // end namespace elf diff --git a/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp b/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp new file mode 100644 index 000000000000..f621f3aa09cf --- /dev/null +++ b/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp @@ -0,0 +1,350 @@ +//===- MachOLayoutBuilder.cpp -----------------------------------*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#include "MachOLayoutBuilder.h" +#include "llvm/Support/Alignment.h" +#include "llvm/Support/Errc.h" +#include "llvm/Support/ErrorHandling.h" + +namespace llvm { +namespace objcopy { +namespace macho { + +uint32_t MachOLayoutBuilder::computeSizeOfCmds() const { + uint32_t Size = 0; + for (const auto &LC : O.LoadCommands) { + const MachO::macho_load_command &MLC = LC.MachOLoadCommand; + auto cmd = MLC.load_command_data.cmd; + switch (cmd) { + case MachO::LC_SEGMENT: + Size += sizeof(MachO::segment_command) + + sizeof(MachO::section) * LC.Sections.size(); + continue; + case MachO::LC_SEGMENT_64: + Size += sizeof(MachO::segment_command_64) + + sizeof(MachO::section_64) * LC.Sections.size(); + continue; + } + + switch (cmd) { +#define HANDLE_LOAD_COMMAND(LCName, LCValue, LCStruct) \ + case MachO::LCName: \ + Size += sizeof(MachO::LCStruct) + LC.Payload.size(); \ + break; +#include "llvm/BinaryFormat/MachO.def" +#undef HANDLE_LOAD_COMMAND + } + } + + return Size; +} + +void MachOLayoutBuilder::constructStringTable() { + for (std::unique_ptr<SymbolEntry> &Sym : O.SymTable.Symbols) + StrTableBuilder.add(Sym->Name); + StrTableBuilder.finalize(); +} + +void MachOLayoutBuilder::updateSymbolIndexes() { + uint32_t Index = 0; + for (auto &Symbol : O.SymTable.Symbols) + Symbol->Index = Index++; +} + +// Updates the index and the number of local/external/undefined symbols. +void MachOLayoutBuilder::updateDySymTab(MachO::macho_load_command &MLC) { + assert(MLC.load_command_data.cmd == MachO::LC_DYSYMTAB); + // Make sure that nlist entries in the symbol table are sorted by the those + // types. The order is: local < defined external < undefined external. + assert(std::is_sorted(O.SymTable.Symbols.begin(), O.SymTable.Symbols.end(), + [](const std::unique_ptr<SymbolEntry> &A, + const std::unique_ptr<SymbolEntry> &B) { + return (A->isLocalSymbol() && !B->isLocalSymbol()) || + (!A->isUndefinedSymbol() && + B->isUndefinedSymbol()); + }) && + "Symbols are not sorted by their types."); + + uint32_t NumLocalSymbols = 0; + auto Iter = O.SymTable.Symbols.begin(); + auto End = O.SymTable.Symbols.end(); + for (; Iter != End; ++Iter) { + if ((*Iter)->isExternalSymbol()) + break; + + ++NumLocalSymbols; + } + + uint32_t NumExtDefSymbols = 0; + for (; Iter != End; ++Iter) { + if ((*Iter)->isUndefinedSymbol()) + break; + + ++NumExtDefSymbols; + } + + MLC.dysymtab_command_data.ilocalsym = 0; + MLC.dysymtab_command_data.nlocalsym = NumLocalSymbols; + MLC.dysymtab_command_data.iextdefsym = NumLocalSymbols; + MLC.dysymtab_command_data.nextdefsym = NumExtDefSymbols; + MLC.dysymtab_command_data.iundefsym = NumLocalSymbols + NumExtDefSymbols; + MLC.dysymtab_command_data.nundefsym = + O.SymTable.Symbols.size() - (NumLocalSymbols + NumExtDefSymbols); +} + +// Recomputes and updates offset and size fields in load commands and sections +// since they could be modified. +uint64_t MachOLayoutBuilder::layoutSegments() { + auto HeaderSize = + Is64Bit ? sizeof(MachO::mach_header_64) : sizeof(MachO::mach_header); + const bool IsObjectFile = + O.Header.FileType == MachO::HeaderFileType::MH_OBJECT; + uint64_t Offset = IsObjectFile ? (HeaderSize + O.Header.SizeOfCmds) : 0; + for (auto &LC : O.LoadCommands) { + auto &MLC = LC.MachOLoadCommand; + StringRef Segname; + uint64_t SegmentVmAddr; + uint64_t SegmentVmSize; + switch (MLC.load_command_data.cmd) { + case MachO::LC_SEGMENT: + SegmentVmAddr = MLC.segment_command_data.vmaddr; + SegmentVmSize = MLC.segment_command_data.vmsize; + Segname = StringRef(MLC.segment_command_data.segname, + strnlen(MLC.segment_command_data.segname, + sizeof(MLC.segment_command_data.segname))); + break; + case MachO::LC_SEGMENT_64: + SegmentVmAddr = MLC.segment_command_64_data.vmaddr; + SegmentVmSize = MLC.segment_command_64_data.vmsize; + Segname = StringRef(MLC.segment_command_64_data.segname, + strnlen(MLC.segment_command_64_data.segname, + sizeof(MLC.segment_command_64_data.segname))); + break; + default: + continue; + } + + if (Segname == "__LINKEDIT") { + // We update the __LINKEDIT segment later (in layoutTail). + assert(LC.Sections.empty() && "__LINKEDIT segment has sections"); + LinkEditLoadCommand = &MLC; + continue; + } + + // Update file offsets and sizes of sections. + uint64_t SegOffset = Offset; + uint64_t SegFileSize = 0; + uint64_t VMSize = 0; + for (auto &Sec : LC.Sections) { + if (IsObjectFile) { + if (Sec.isVirtualSection()) { + Sec.Offset = 0; + } else { + uint64_t PaddingSize = + offsetToAlignment(SegFileSize, Align(1ull << Sec.Align)); + Sec.Offset = SegOffset + SegFileSize + PaddingSize; + Sec.Size = Sec.Content.size(); + SegFileSize += PaddingSize + Sec.Size; + } + VMSize = std::max(VMSize, Sec.Addr + Sec.Size); + } else { + if (Sec.isVirtualSection()) { + Sec.Offset = 0; + VMSize += Sec.Size; + } else { + uint32_t SectOffset = Sec.Addr - SegmentVmAddr; + Sec.Offset = SegOffset + SectOffset; + Sec.Size = Sec.Content.size(); + SegFileSize = std::max(SegFileSize, SectOffset + Sec.Size); + VMSize = std::max(VMSize, SegFileSize); + } + } + } + + if (IsObjectFile) { + Offset += SegFileSize; + } else { + Offset = alignTo(Offset + SegFileSize, PageSize); + SegFileSize = alignTo(SegFileSize, PageSize); + // Use the original vmsize if the segment is __PAGEZERO. + VMSize = + Segname == "__PAGEZERO" ? SegmentVmSize : alignTo(VMSize, PageSize); + } + + switch (MLC.load_command_data.cmd) { + case MachO::LC_SEGMENT: + MLC.segment_command_data.cmdsize = + sizeof(MachO::segment_command) + + sizeof(MachO::section) * LC.Sections.size(); + MLC.segment_command_data.nsects = LC.Sections.size(); + MLC.segment_command_data.fileoff = SegOffset; + MLC.segment_command_data.vmsize = VMSize; + MLC.segment_command_data.filesize = SegFileSize; + break; + case MachO::LC_SEGMENT_64: + MLC.segment_command_64_data.cmdsize = + sizeof(MachO::segment_command_64) + + sizeof(MachO::section_64) * LC.Sections.size(); + MLC.segment_command_64_data.nsects = LC.Sections.size(); + MLC.segment_command_64_data.fileoff = SegOffset; + MLC.segment_command_64_data.vmsize = VMSize; + MLC.segment_command_64_data.filesize = SegFileSize; + break; + } + } + + return Offset; +} + +uint64_t MachOLayoutBuilder::layoutRelocations(uint64_t Offset) { + for (auto &LC : O.LoadCommands) + for (auto &Sec : LC.Sections) { + Sec.RelOff = Sec.Relocations.empty() ? 0 : Offset; + Sec.NReloc = Sec.Relocations.size(); + Offset += sizeof(MachO::any_relocation_info) * Sec.NReloc; + } + + return Offset; +} + +Error MachOLayoutBuilder::layoutTail(uint64_t Offset) { + // The order of LINKEDIT elements is as follows: + // rebase info, binding info, weak binding info, lazy binding info, export + // trie, data-in-code, symbol table, indirect symbol table, symbol table + // strings. + uint64_t NListSize = Is64Bit ? sizeof(MachO::nlist_64) : sizeof(MachO::nlist); + uint64_t StartOfLinkEdit = Offset; + uint64_t StartOfRebaseInfo = StartOfLinkEdit; + uint64_t StartOfBindingInfo = StartOfRebaseInfo + O.Rebases.Opcodes.size(); + uint64_t StartOfWeakBindingInfo = StartOfBindingInfo + O.Binds.Opcodes.size(); + uint64_t StartOfLazyBindingInfo = + StartOfWeakBindingInfo + O.WeakBinds.Opcodes.size(); + uint64_t StartOfExportTrie = + StartOfLazyBindingInfo + O.LazyBinds.Opcodes.size(); + uint64_t StartOfFunctionStarts = StartOfExportTrie + O.Exports.Trie.size(); + uint64_t StartOfDataInCode = + StartOfFunctionStarts + O.FunctionStarts.Data.size(); + uint64_t StartOfSymbols = StartOfDataInCode + O.DataInCode.Data.size(); + uint64_t StartOfIndirectSymbols = + StartOfSymbols + NListSize * O.SymTable.Symbols.size(); + uint64_t StartOfSymbolStrings = + StartOfIndirectSymbols + + sizeof(uint32_t) * O.IndirectSymTable.Symbols.size(); + uint64_t LinkEditSize = + (StartOfSymbolStrings + StrTableBuilder.getSize()) - StartOfLinkEdit; + + // Now we have determined the layout of the contents of the __LINKEDIT + // segment. Update its load command. + if (LinkEditLoadCommand) { + MachO::macho_load_command *MLC = LinkEditLoadCommand; + switch (LinkEditLoadCommand->load_command_data.cmd) { + case MachO::LC_SEGMENT: + MLC->segment_command_data.cmdsize = sizeof(MachO::segment_command); + MLC->segment_command_data.fileoff = StartOfLinkEdit; + MLC->segment_command_data.vmsize = alignTo(LinkEditSize, PageSize); + MLC->segment_command_data.filesize = LinkEditSize; + break; + case MachO::LC_SEGMENT_64: + MLC->segment_command_64_data.cmdsize = sizeof(MachO::segment_command_64); + MLC->segment_command_64_data.fileoff = StartOfLinkEdit; + MLC->segment_command_64_data.vmsize = alignTo(LinkEditSize, PageSize); + MLC->segment_command_64_data.filesize = LinkEditSize; + break; + } + } + + for (auto &LC : O.LoadCommands) { + auto &MLC = LC.MachOLoadCommand; + auto cmd = MLC.load_command_data.cmd; + switch (cmd) { + case MachO::LC_SYMTAB: + MLC.symtab_command_data.symoff = StartOfSymbols; + MLC.symtab_command_data.nsyms = O.SymTable.Symbols.size(); + MLC.symtab_command_data.stroff = StartOfSymbolStrings; + MLC.symtab_command_data.strsize = StrTableBuilder.getSize(); + break; + case MachO::LC_DYSYMTAB: { + if (MLC.dysymtab_command_data.ntoc != 0 || + MLC.dysymtab_command_data.nmodtab != 0 || + MLC.dysymtab_command_data.nextrefsyms != 0 || + MLC.dysymtab_command_data.nlocrel != 0 || + MLC.dysymtab_command_data.nextrel != 0) + return createStringError(llvm::errc::not_supported, + "shared library is not yet supported"); + + if (!O.IndirectSymTable.Symbols.empty()) { + MLC.dysymtab_command_data.indirectsymoff = StartOfIndirectSymbols; + MLC.dysymtab_command_data.nindirectsyms = + O.IndirectSymTable.Symbols.size(); + } + + updateDySymTab(MLC); + break; + } + case MachO::LC_DATA_IN_CODE: + MLC.linkedit_data_command_data.dataoff = StartOfDataInCode; + MLC.linkedit_data_command_data.datasize = O.DataInCode.Data.size(); + break; + case MachO::LC_FUNCTION_STARTS: + MLC.linkedit_data_command_data.dataoff = StartOfFunctionStarts; + MLC.linkedit_data_command_data.datasize = O.FunctionStarts.Data.size(); + break; + case MachO::LC_DYLD_INFO: + case MachO::LC_DYLD_INFO_ONLY: + MLC.dyld_info_command_data.rebase_off = + O.Rebases.Opcodes.empty() ? 0 : StartOfRebaseInfo; + MLC.dyld_info_command_data.rebase_size = O.Rebases.Opcodes.size(); + MLC.dyld_info_command_data.bind_off = + O.Binds.Opcodes.empty() ? 0 : StartOfBindingInfo; + MLC.dyld_info_command_data.bind_size = O.Binds.Opcodes.size(); + MLC.dyld_info_command_data.weak_bind_off = + O.WeakBinds.Opcodes.empty() ? 0 : StartOfWeakBindingInfo; + MLC.dyld_info_command_data.weak_bind_size = O.WeakBinds.Opcodes.size(); + MLC.dyld_info_command_data.lazy_bind_off = + O.LazyBinds.Opcodes.empty() ? 0 : StartOfLazyBindingInfo; + MLC.dyld_info_command_data.lazy_bind_size = O.LazyBinds.Opcodes.size(); + MLC.dyld_info_command_data.export_off = + O.Exports.Trie.empty() ? 0 : StartOfExportTrie; + MLC.dyld_info_command_data.export_size = O.Exports.Trie.size(); + break; + case MachO::LC_LOAD_DYLINKER: + case MachO::LC_MAIN: + case MachO::LC_RPATH: + case MachO::LC_SEGMENT: + case MachO::LC_SEGMENT_64: + case MachO::LC_VERSION_MIN_MACOSX: + case MachO::LC_BUILD_VERSION: + case MachO::LC_ID_DYLIB: + case MachO::LC_LOAD_DYLIB: + case MachO::LC_UUID: + case MachO::LC_SOURCE_VERSION: + // Nothing to update. + break; + default: + // Abort if it's unsupported in order to prevent corrupting the object. + return createStringError(llvm::errc::not_supported, + "unsupported load command (cmd=0x%x)", cmd); + } + } + + return Error::success(); +} + +Error MachOLayoutBuilder::layout() { + O.Header.NCmds = O.LoadCommands.size(); + O.Header.SizeOfCmds = computeSizeOfCmds(); + constructStringTable(); + updateSymbolIndexes(); + uint64_t Offset = layoutSegments(); + Offset = layoutRelocations(Offset); + return layoutTail(Offset); +} + +} // end namespace macho +} // end namespace objcopy +} // end namespace llvm diff --git a/tools/llvm-objcopy/MachO/MachOLayoutBuilder.h b/tools/llvm-objcopy/MachO/MachOLayoutBuilder.h new file mode 100644 index 000000000000..21cbe56605de --- /dev/null +++ b/tools/llvm-objcopy/MachO/MachOLayoutBuilder.h @@ -0,0 +1,50 @@ +//===- MachOLayoutBuilder.h -------------------------------------*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_OBJCOPY_MACHO_MACHOLAYOUTBUILDER_H +#define LLVM_OBJCOPY_MACHO_MACHOLAYOUTBUILDER_H + +#include "MachOObjcopy.h" +#include "Object.h" + +namespace llvm { +namespace objcopy { +namespace macho { + +class MachOLayoutBuilder { + Object &O; + bool Is64Bit; + uint64_t PageSize; + + // Points to the __LINKEDIT segment if it exists. + MachO::macho_load_command *LinkEditLoadCommand = nullptr; + StringTableBuilder StrTableBuilder{StringTableBuilder::MachO}; + + uint32_t computeSizeOfCmds() const; + void constructStringTable(); + void updateSymbolIndexes(); + void updateDySymTab(MachO::macho_load_command &MLC); + uint64_t layoutSegments(); + uint64_t layoutRelocations(uint64_t Offset); + Error layoutTail(uint64_t Offset); + +public: + MachOLayoutBuilder(Object &O, bool Is64Bit, uint64_t PageSize) + : O(O), Is64Bit(Is64Bit), PageSize(PageSize) {} + + // Recomputes and updates fields in the given object such as file offsets. + Error layout(); + + StringTableBuilder &getStringTableBuilder() { return StrTableBuilder; } +}; + +} // end namespace macho +} // end namespace objcopy +} // end namespace llvm + +#endif // LLVM_OBJCOPY_MACHO_MACHOLAYOUTBUILDER_H diff --git a/tools/llvm-objcopy/MachO/MachOObjcopy.cpp b/tools/llvm-objcopy/MachO/MachOObjcopy.cpp index 19343b65dd1e..6d586e7d73f1 100644 --- a/tools/llvm-objcopy/MachO/MachOObjcopy.cpp +++ b/tools/llvm-objcopy/MachO/MachOObjcopy.cpp @@ -25,18 +25,20 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) { !Config.SplitDWO.empty() || !Config.SymbolsPrefix.empty() || !Config.AllocSectionsPrefix.empty() || !Config.AddSection.empty() || !Config.DumpSection.empty() || !Config.KeepSection.empty() || - !Config.OnlySection.empty() || !Config.SymbolsToGlobalize.empty() || - !Config.SymbolsToKeep.empty() || !Config.SymbolsToLocalize.empty() || - !Config.SymbolsToWeaken.empty() || !Config.SymbolsToKeepGlobal.empty() || - !Config.SectionsToRename.empty() || !Config.SymbolsToRename.empty() || + Config.NewSymbolVisibility || !Config.OnlySection.empty() || + !Config.SymbolsToGlobalize.empty() || !Config.SymbolsToKeep.empty() || + !Config.SymbolsToLocalize.empty() || !Config.SymbolsToWeaken.empty() || + !Config.SymbolsToKeepGlobal.empty() || !Config.SectionsToRename.empty() || + !Config.SymbolsToRename.empty() || !Config.UnneededSymbolsToRemove.empty() || - !Config.SetSectionFlags.empty() || !Config.ToRemove.empty() || - Config.ExtractDWO || Config.KeepFileSymbols || Config.LocalizeHidden || - Config.PreserveDates || Config.StripDWO || Config.StripNonAlloc || - Config.StripSections || Config.Weaken || Config.DecompressDebugSections || - Config.StripDebug || Config.StripNonAlloc || Config.StripSections || - Config.StripUnneeded || Config.DiscardMode != DiscardType::None || - !Config.SymbolsToAdd.empty() || Config.EntryExpr) { + !Config.SetSectionAlignment.empty() || !Config.SetSectionFlags.empty() || + !Config.ToRemove.empty() || Config.ExtractDWO || Config.KeepFileSymbols || + Config.LocalizeHidden || Config.PreserveDates || Config.StripDWO || + Config.StripNonAlloc || Config.StripSections || Config.Weaken || + Config.DecompressDebugSections || Config.StripDebug || + Config.StripNonAlloc || Config.StripSections || Config.StripUnneeded || + Config.DiscardMode != DiscardType::None || !Config.SymbolsToAdd.empty() || + Config.EntryExpr) { return createStringError(llvm::errc::invalid_argument, "option not supported by llvm-objcopy for MachO"); } @@ -57,7 +59,11 @@ Error executeObjcopyOnBinary(const CopyConfig &Config, if (Error E = handleArgs(Config, *O)) return createFileError(Config.InputFilename, std::move(E)); - MachOWriter Writer(*O, In.is64Bit(), In.isLittleEndian(), Out); + // TODO: Support 16KB pages which are employed in iOS arm64 binaries: + // https://github.com/llvm/llvm-project/commit/1bebb2832ee312d3b0316dacff457a7a29435edb + const uint64_t PageSize = 4096; + + MachOWriter Writer(*O, In.is64Bit(), In.isLittleEndian(), PageSize, Out); if (auto E = Writer.finalize()) return E; return Writer.write(); diff --git a/tools/llvm-objcopy/MachO/MachOReader.cpp b/tools/llvm-objcopy/MachO/MachOReader.cpp index d31293034608..b48a0d8952d0 100644 --- a/tools/llvm-objcopy/MachO/MachOReader.cpp +++ b/tools/llvm-objcopy/MachO/MachOReader.cpp @@ -129,10 +129,19 @@ void MachOReader::readLoadCommands(Object &O) const { case MachO::LC_SYMTAB: O.SymTabCommandIndex = O.LoadCommands.size(); break; + case MachO::LC_DYSYMTAB: + O.DySymTabCommandIndex = O.LoadCommands.size(); + break; case MachO::LC_DYLD_INFO: case MachO::LC_DYLD_INFO_ONLY: O.DyLdInfoCommandIndex = O.LoadCommands.size(); break; + case MachO::LC_DATA_IN_CODE: + O.DataInCodeCommandIndex = O.LoadCommands.size(); + break; + case MachO::LC_FUNCTION_STARTS: + O.FunctionStartsCommandIndex = O.LoadCommands.size(); + break; } #define HANDLE_LOAD_COMMAND(LCName, LCValue, LCStruct) \ case MachO::LCName: \ @@ -188,7 +197,7 @@ void MachOReader::readSymbolTable(Object &O) const { StrTable, MachOObj.getSymbolTableEntry(Symbol.getRawDataRefImpl()))); - O.SymTable.Symbols.push_back(llvm::make_unique<SymbolEntry>(SE)); + O.SymTable.Symbols.push_back(std::make_unique<SymbolEntry>(SE)); } } @@ -222,8 +231,37 @@ void MachOReader::readExportInfo(Object &O) const { O.Exports.Trie = MachOObj.getDyldInfoExportsTrie(); } +void MachOReader::readDataInCodeData(Object &O) const { + if (!O.DataInCodeCommandIndex) + return; + const MachO::linkedit_data_command &LDC = + O.LoadCommands[*O.DataInCodeCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + + O.DataInCode.Data = arrayRefFromStringRef( + MachOObj.getData().substr(LDC.dataoff, LDC.datasize)); +} + +void MachOReader::readFunctionStartsData(Object &O) const { + if (!O.FunctionStartsCommandIndex) + return; + const MachO::linkedit_data_command &LDC = + O.LoadCommands[*O.FunctionStartsCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + + O.FunctionStarts.Data = arrayRefFromStringRef( + MachOObj.getData().substr(LDC.dataoff, LDC.datasize)); +} + +void MachOReader::readIndirectSymbolTable(Object &O) const { + MachO::dysymtab_command DySymTab = MachOObj.getDysymtabLoadCommand(); + for (uint32_t i = 0; i < DySymTab.nindirectsyms; ++i) + O.IndirectSymTable.Symbols.push_back( + MachOObj.getIndirectSymbolTableEntry(DySymTab, i)); +} + std::unique_ptr<Object> MachOReader::create() const { - auto Obj = llvm::make_unique<Object>(); + auto Obj = std::make_unique<Object>(); readHeader(*Obj); readLoadCommands(*Obj); readSymbolTable(*Obj); @@ -233,6 +271,9 @@ std::unique_ptr<Object> MachOReader::create() const { readWeakBindInfo(*Obj); readLazyBindInfo(*Obj); readExportInfo(*Obj); + readDataInCodeData(*Obj); + readFunctionStartsData(*Obj); + readIndirectSymbolTable(*Obj); return Obj; } diff --git a/tools/llvm-objcopy/MachO/MachOReader.h b/tools/llvm-objcopy/MachO/MachOReader.h index 795e5cc2363d..00c8f0d55f61 100644 --- a/tools/llvm-objcopy/MachO/MachOReader.h +++ b/tools/llvm-objcopy/MachO/MachOReader.h @@ -36,6 +36,9 @@ class MachOReader : public Reader { void readWeakBindInfo(Object &O) const; void readLazyBindInfo(Object &O) const; void readExportInfo(Object &O) const; + void readDataInCodeData(Object &O) const; + void readFunctionStartsData(Object &O) const; + void readIndirectSymbolTable(Object &O) const; public: explicit MachOReader(const object::MachOObjectFile &Obj) : MachOObj(Obj) {} diff --git a/tools/llvm-objcopy/MachO/MachOWriter.cpp b/tools/llvm-objcopy/MachO/MachOWriter.cpp index 74200c5aa62a..4ec91cc9eb7a 100644 --- a/tools/llvm-objcopy/MachO/MachOWriter.cpp +++ b/tools/llvm-objcopy/MachO/MachOWriter.cpp @@ -7,6 +7,7 @@ //===----------------------------------------------------------------------===// #include "MachOWriter.h" +#include "MachOLayoutBuilder.h" #include "Object.h" #include "llvm/ADT/STLExtras.h" #include "llvm/BinaryFormat/MachO.h" @@ -40,16 +41,10 @@ size_t MachOWriter::totalSize() const { const MachO::symtab_command &SymTabCommand = O.LoadCommands[*O.SymTabCommandIndex] .MachOLoadCommand.symtab_command_data; - if (SymTabCommand.symoff) { - assert((SymTabCommand.nsyms == O.SymTable.Symbols.size()) && - "Incorrect number of symbols"); + if (SymTabCommand.symoff) Ends.push_back(SymTabCommand.symoff + symTableSize()); - } - if (SymTabCommand.stroff) { - assert((SymTabCommand.strsize == StrTableBuilder.getSize()) && - "Incorrect string table size"); + if (SymTabCommand.stroff) Ends.push_back(SymTabCommand.stroff + SymTabCommand.strsize); - } } if (O.DyLdInfoCommandIndex) { const MachO::dyld_info_command &DyLdInfoCommand = @@ -84,6 +79,36 @@ size_t MachOWriter::totalSize() const { } } + if (O.DySymTabCommandIndex) { + const MachO::dysymtab_command &DySymTabCommand = + O.LoadCommands[*O.DySymTabCommandIndex] + .MachOLoadCommand.dysymtab_command_data; + + if (DySymTabCommand.indirectsymoff) + Ends.push_back(DySymTabCommand.indirectsymoff + + sizeof(uint32_t) * O.IndirectSymTable.Symbols.size()); + } + + if (O.DataInCodeCommandIndex) { + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.DataInCodeCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + + if (LinkEditDataCommand.dataoff) + Ends.push_back(LinkEditDataCommand.dataoff + + LinkEditDataCommand.datasize); + } + + if (O.FunctionStartsCommandIndex) { + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.FunctionStartsCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + + if (LinkEditDataCommand.dataoff) + Ends.push_back(LinkEditDataCommand.dataoff + + LinkEditDataCommand.datasize); + } + // Otherwise, use the last section / reloction. for (const auto &LC : O.LoadCommands) for (const auto &S : LC.Sections) { @@ -120,14 +145,6 @@ void MachOWriter::writeHeader() { memcpy(B.getBufferStart(), &Header, HeaderSize); } -void MachOWriter::updateSymbolIndexes() { - uint32_t Index = 0; - for (auto &Symbol : O.SymTable.Symbols) { - Symbol->Index = Index; - Index++; - } -} - void MachOWriter::writeLoadCommands() { uint8_t *Begin = B.getBufferStart() + headerSize(); for (const auto &LC : O.LoadCommands) { @@ -253,7 +270,7 @@ void writeNListEntry(const SymbolEntry &SE, bool IsLittleEndian, char *&Out, Out += sizeof(NListType); } -void MachOWriter::writeSymbolTable() { +void MachOWriter::writeStringTable() { if (!O.SymTabCommandIndex) return; const MachO::symtab_command &SymTabCommand = @@ -261,10 +278,10 @@ void MachOWriter::writeSymbolTable() { .MachOLoadCommand.symtab_command_data; uint8_t *StrTable = (uint8_t *)B.getBufferStart() + SymTabCommand.stroff; - StrTableBuilder.write(StrTable); + LayoutBuilder.getStringTableBuilder().write(StrTable); } -void MachOWriter::writeStringTable() { +void MachOWriter::writeSymbolTable() { if (!O.SymTabCommandIndex) return; const MachO::symtab_command &SymTabCommand = @@ -275,7 +292,7 @@ void MachOWriter::writeStringTable() { for (auto Iter = O.SymTable.Symbols.begin(), End = O.SymTable.Symbols.end(); Iter != End; Iter++) { SymbolEntry *Sym = Iter->get(); - auto Nstrx = StrTableBuilder.getOffset(Sym->Name); + uint32_t Nstrx = LayoutBuilder.getStringTableBuilder().getOffset(Sym->Name); if (Is64Bit) writeNListEntry<MachO::nlist_64>(*Sym, IsLittleEndian, SymTable, Nstrx); @@ -344,6 +361,45 @@ void MachOWriter::writeExportInfo() { memcpy(Out, O.Exports.Trie.data(), O.Exports.Trie.size()); } +void MachOWriter::writeIndirectSymbolTable() { + if (!O.DySymTabCommandIndex) + return; + + const MachO::dysymtab_command &DySymTabCommand = + O.LoadCommands[*O.DySymTabCommandIndex] + .MachOLoadCommand.dysymtab_command_data; + + char *Out = (char *)B.getBufferStart() + DySymTabCommand.indirectsymoff; + assert((DySymTabCommand.nindirectsyms == O.IndirectSymTable.Symbols.size()) && + "Incorrect indirect symbol table size"); + memcpy(Out, O.IndirectSymTable.Symbols.data(), + sizeof(uint32_t) * O.IndirectSymTable.Symbols.size()); +} + +void MachOWriter::writeDataInCodeData() { + if (!O.DataInCodeCommandIndex) + return; + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.DataInCodeCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + char *Out = (char *)B.getBufferStart() + LinkEditDataCommand.dataoff; + assert((LinkEditDataCommand.datasize == O.DataInCode.Data.size()) && + "Incorrect data in code data size"); + memcpy(Out, O.DataInCode.Data.data(), O.DataInCode.Data.size()); +} + +void MachOWriter::writeFunctionStartsData() { + if (!O.FunctionStartsCommandIndex) + return; + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.FunctionStartsCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; + char *Out = (char *)B.getBufferStart() + LinkEditDataCommand.dataoff; + assert((LinkEditDataCommand.datasize == O.FunctionStarts.Data.size()) && + "Incorrect function starts data size"); + memcpy(Out, O.FunctionStarts.Data.data(), O.FunctionStarts.Data.size()); +} + void MachOWriter::writeTail() { typedef void (MachOWriter::*WriteHandlerType)(void); typedef std::pair<uint64_t, WriteHandlerType> WriteOperation; @@ -379,206 +435,51 @@ void MachOWriter::writeTail() { {DyLdInfoCommand.export_off, &MachOWriter::writeExportInfo}); } - llvm::sort(Queue, [](const WriteOperation &LHS, const WriteOperation &RHS) { - return LHS.first < RHS.first; - }); - - for (auto WriteOp : Queue) - (this->*WriteOp.second)(); -} - -void MachOWriter::updateSizeOfCmds() { - auto Size = 0; - for (const auto &LC : O.LoadCommands) { - auto &MLC = LC.MachOLoadCommand; - auto cmd = MLC.load_command_data.cmd; - - switch (cmd) { - case MachO::LC_SEGMENT: - Size += sizeof(MachO::segment_command) + - sizeof(MachO::section) * LC.Sections.size(); - continue; - case MachO::LC_SEGMENT_64: - Size += sizeof(MachO::segment_command_64) + - sizeof(MachO::section_64) * LC.Sections.size(); - continue; - } - - switch (cmd) { -#define HANDLE_LOAD_COMMAND(LCName, LCValue, LCStruct) \ - case MachO::LCName: \ - Size += sizeof(MachO::LCStruct); \ - break; -#include "llvm/BinaryFormat/MachO.def" -#undef HANDLE_LOAD_COMMAND - } - } - - O.Header.SizeOfCmds = Size; -} - -// Updates the index and the number of local/external/undefined symbols. Here we -// assume that MLC is a LC_DYSYMTAB and the nlist entries in the symbol table -// are already sorted by the those types. -void MachOWriter::updateDySymTab(MachO::macho_load_command &MLC) { - uint32_t NumLocalSymbols = 0; - auto Iter = O.SymTable.Symbols.begin(); - auto End = O.SymTable.Symbols.end(); - for (; Iter != End; Iter++) { - if ((*Iter)->n_type & (MachO::N_EXT | MachO::N_PEXT)) - break; + if (O.DySymTabCommandIndex) { + const MachO::dysymtab_command &DySymTabCommand = + O.LoadCommands[*O.DySymTabCommandIndex] + .MachOLoadCommand.dysymtab_command_data; - NumLocalSymbols++; + if (DySymTabCommand.indirectsymoff) + Queue.emplace_back(DySymTabCommand.indirectsymoff, + &MachOWriter::writeIndirectSymbolTable); } - uint32_t NumExtDefSymbols = 0; - for (; Iter != End; Iter++) { - if (((*Iter)->n_type & MachO::N_TYPE) == MachO::N_UNDF) - break; - - NumExtDefSymbols++; - } - - MLC.dysymtab_command_data.ilocalsym = 0; - MLC.dysymtab_command_data.nlocalsym = NumLocalSymbols; - MLC.dysymtab_command_data.iextdefsym = NumLocalSymbols; - MLC.dysymtab_command_data.nextdefsym = NumExtDefSymbols; - MLC.dysymtab_command_data.iundefsym = NumLocalSymbols + NumExtDefSymbols; - MLC.dysymtab_command_data.nundefsym = - O.SymTable.Symbols.size() - (NumLocalSymbols + NumExtDefSymbols); -} - -// Recomputes and updates offset and size fields in load commands and sections -// since they could be modified. -Error MachOWriter::layout() { - auto SizeOfCmds = loadCommandsSize(); - auto Offset = headerSize() + SizeOfCmds; - O.Header.NCmds = O.LoadCommands.size(); - O.Header.SizeOfCmds = SizeOfCmds; - - // Lay out sections. - for (auto &LC : O.LoadCommands) { - uint64_t FileOff = Offset; - uint64_t VMSize = 0; - uint64_t FileOffsetInSegment = 0; - for (auto &Sec : LC.Sections) { - if (!Sec.isVirtualSection()) { - auto FilePaddingSize = - OffsetToAlignment(FileOffsetInSegment, 1ull << Sec.Align); - Sec.Offset = Offset + FileOffsetInSegment + FilePaddingSize; - Sec.Size = Sec.Content.size(); - FileOffsetInSegment += FilePaddingSize + Sec.Size; - } - - VMSize = std::max(VMSize, Sec.Addr + Sec.Size); - } - - // TODO: Handle the __PAGEZERO segment. - auto &MLC = LC.MachOLoadCommand; - switch (MLC.load_command_data.cmd) { - case MachO::LC_SEGMENT: - MLC.segment_command_data.cmdsize = - sizeof(MachO::segment_command) + - sizeof(MachO::section) * LC.Sections.size(); - MLC.segment_command_data.nsects = LC.Sections.size(); - MLC.segment_command_data.fileoff = FileOff; - MLC.segment_command_data.vmsize = VMSize; - MLC.segment_command_data.filesize = FileOffsetInSegment; - break; - case MachO::LC_SEGMENT_64: - MLC.segment_command_64_data.cmdsize = - sizeof(MachO::segment_command_64) + - sizeof(MachO::section_64) * LC.Sections.size(); - MLC.segment_command_64_data.nsects = LC.Sections.size(); - MLC.segment_command_64_data.fileoff = FileOff; - MLC.segment_command_64_data.vmsize = VMSize; - MLC.segment_command_64_data.filesize = FileOffsetInSegment; - break; - } + if (O.DataInCodeCommandIndex) { + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.DataInCodeCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; - Offset += FileOffsetInSegment; + if (LinkEditDataCommand.dataoff) + Queue.emplace_back(LinkEditDataCommand.dataoff, + &MachOWriter::writeDataInCodeData); } - // Lay out relocations. - for (auto &LC : O.LoadCommands) - for (auto &Sec : LC.Sections) { - Sec.RelOff = Sec.Relocations.empty() ? 0 : Offset; - Sec.NReloc = Sec.Relocations.size(); - Offset += sizeof(MachO::any_relocation_info) * Sec.NReloc; - } + if (O.FunctionStartsCommandIndex) { + const MachO::linkedit_data_command &LinkEditDataCommand = + O.LoadCommands[*O.FunctionStartsCommandIndex] + .MachOLoadCommand.linkedit_data_command_data; - // Lay out tail stuff. - auto NListSize = Is64Bit ? sizeof(MachO::nlist_64) : sizeof(MachO::nlist); - for (auto &LC : O.LoadCommands) { - auto &MLC = LC.MachOLoadCommand; - auto cmd = MLC.load_command_data.cmd; - switch (cmd) { - case MachO::LC_SYMTAB: - MLC.symtab_command_data.nsyms = O.SymTable.Symbols.size(); - MLC.symtab_command_data.strsize = StrTableBuilder.getSize(); - MLC.symtab_command_data.symoff = Offset; - Offset += NListSize * MLC.symtab_command_data.nsyms; - MLC.symtab_command_data.stroff = Offset; - Offset += MLC.symtab_command_data.strsize; - break; - case MachO::LC_DYSYMTAB: { - if (MLC.dysymtab_command_data.ntoc != 0 || - MLC.dysymtab_command_data.nmodtab != 0 || - MLC.dysymtab_command_data.nextrefsyms != 0 || - MLC.dysymtab_command_data.nlocrel != 0 || - MLC.dysymtab_command_data.nextrel != 0) - return createStringError(llvm::errc::not_supported, - "shared library is not yet supported"); - - if (MLC.dysymtab_command_data.nindirectsyms != 0) - return createStringError(llvm::errc::not_supported, - "indirect symbol table is not yet supported"); - - updateDySymTab(MLC); - break; - } - case MachO::LC_SEGMENT: - case MachO::LC_SEGMENT_64: - case MachO::LC_VERSION_MIN_MACOSX: - case MachO::LC_BUILD_VERSION: - case MachO::LC_ID_DYLIB: - case MachO::LC_LOAD_DYLIB: - case MachO::LC_UUID: - case MachO::LC_SOURCE_VERSION: - // Nothing to update. - break; - default: - // Abort if it's unsupported in order to prevent corrupting the object. - return createStringError(llvm::errc::not_supported, - "unsupported load command (cmd=0x%x)", cmd); - } + if (LinkEditDataCommand.dataoff) + Queue.emplace_back(LinkEditDataCommand.dataoff, + &MachOWriter::writeFunctionStartsData); } - return Error::success(); -} + llvm::sort(Queue, [](const WriteOperation &LHS, const WriteOperation &RHS) { + return LHS.first < RHS.first; + }); -void MachOWriter::constructStringTable() { - for (std::unique_ptr<SymbolEntry> &Sym : O.SymTable.Symbols) - StrTableBuilder.add(Sym->Name); - StrTableBuilder.finalize(); + for (auto WriteOp : Queue) + (this->*WriteOp.second)(); } -Error MachOWriter::finalize() { - updateSizeOfCmds(); - constructStringTable(); - - if (auto E = layout()) - return E; - - return Error::success(); -} +Error MachOWriter::finalize() { return LayoutBuilder.layout(); } Error MachOWriter::write() { if (Error E = B.allocate(totalSize())) return E; memset(B.getBufferStart(), 0, totalSize()); writeHeader(); - updateSymbolIndexes(); writeLoadCommands(); writeSections(); writeTail(); diff --git a/tools/llvm-objcopy/MachO/MachOWriter.h b/tools/llvm-objcopy/MachO/MachOWriter.h index ecf12d62de2c..22abbad56f41 100644 --- a/tools/llvm-objcopy/MachO/MachOWriter.h +++ b/tools/llvm-objcopy/MachO/MachOWriter.h @@ -7,6 +7,7 @@ //===----------------------------------------------------------------------===// #include "../Buffer.h" +#include "MachOLayoutBuilder.h" #include "MachOObjcopy.h" #include "Object.h" #include "llvm/BinaryFormat/MachO.h" @@ -22,20 +23,15 @@ class MachOWriter { Object &O; bool Is64Bit; bool IsLittleEndian; + uint64_t PageSize; Buffer &B; - StringTableBuilder StrTableBuilder{StringTableBuilder::MachO}; + MachOLayoutBuilder LayoutBuilder; size_t headerSize() const; size_t loadCommandsSize() const; size_t symTableSize() const; size_t strTableSize() const; - void updateDySymTab(MachO::macho_load_command &MLC); - void updateSizeOfCmds(); - void updateSymbolIndexes(); - void constructStringTable(); - Error layout(); - void writeHeader(); void writeLoadCommands(); template <typename StructType> @@ -48,11 +44,16 @@ class MachOWriter { void writeWeakBindInfo(); void writeLazyBindInfo(); void writeExportInfo(); + void writeIndirectSymbolTable(); + void writeDataInCodeData(); + void writeFunctionStartsData(); void writeTail(); public: - MachOWriter(Object &O, bool Is64Bit, bool IsLittleEndian, Buffer &B) - : O(O), Is64Bit(Is64Bit), IsLittleEndian(IsLittleEndian), B(B) {} + MachOWriter(Object &O, bool Is64Bit, bool IsLittleEndian, uint64_t PageSize, + Buffer &B) + : O(O), Is64Bit(Is64Bit), IsLittleEndian(IsLittleEndian), + PageSize(PageSize), B(B), LayoutBuilder(O, Is64Bit, PageSize) {} size_t totalSize() const; Error finalize(); diff --git a/tools/llvm-objcopy/MachO/Object.h b/tools/llvm-objcopy/MachO/Object.h index ed85fcbc47f7..1cebf8253d19 100644 --- a/tools/llvm-objcopy/MachO/Object.h +++ b/tools/llvm-objcopy/MachO/Object.h @@ -90,6 +90,16 @@ struct SymbolEntry { uint8_t n_sect; uint16_t n_desc; uint64_t n_value; + + bool isExternalSymbol() const { + return n_type & ((MachO::N_EXT | MachO::N_PEXT)); + } + + bool isLocalSymbol() const { return !isExternalSymbol(); } + + bool isUndefinedSymbol() const { + return (n_type & MachO::N_TYPE) == MachO::N_UNDF; + } }; /// The location of the symbol table inside the binary is described by LC_SYMTAB @@ -100,6 +110,10 @@ struct SymbolTable { const SymbolEntry *getSymbolByIndex(uint32_t Index) const; }; +struct IndirectSymbolTable { + std::vector<uint32_t> Symbols; +}; + /// The location of the string table inside the binary is described by LC_SYMTAB /// load command. struct StringTable { @@ -206,6 +220,10 @@ struct ExportInfo { ArrayRef<uint8_t> Trie; }; +struct LinkData { + ArrayRef<uint8_t> Data; +}; + struct Object { MachHeader Header; std::vector<LoadCommand> LoadCommands; @@ -218,11 +236,20 @@ struct Object { WeakBindInfo WeakBinds; LazyBindInfo LazyBinds; ExportInfo Exports; + IndirectSymbolTable IndirectSymTable; + LinkData DataInCode; + LinkData FunctionStarts; /// The index of LC_SYMTAB load command if present. Optional<size_t> SymTabCommandIndex; /// The index of LC_DYLD_INFO or LC_DYLD_INFO_ONLY load command if present. Optional<size_t> DyLdInfoCommandIndex; + /// The index LC_DYSYMTAB load comamnd if present. + Optional<size_t> DySymTabCommandIndex; + /// The index LC_DATA_IN_CODE load comamnd if present. + Optional<size_t> DataInCodeCommandIndex; + /// The index LC_FUNCTION_STARTS load comamnd if present. + Optional<size_t> FunctionStartsCommandIndex; }; } // end namespace macho diff --git a/tools/llvm-objcopy/ObjcopyOpts.td b/tools/llvm-objcopy/ObjcopyOpts.td index 5fce4fbde539..9e6b6f0005cd 100644 --- a/tools/llvm-objcopy/ObjcopyOpts.td +++ b/tools/llvm-objcopy/ObjcopyOpts.td @@ -1,37 +1,33 @@ -include "llvm/Option/OptParser.td" - -multiclass Eq<string name, string help> { - def NAME : Separate<["--"], name>; - def NAME #_eq : Joined<["--"], name #"=">, - Alias<!cast<Separate>(NAME)>, - HelpText<help>; -} - -def help : Flag<["--"], "help">; -def h : Flag<["-"], "h">, Alias<help>; - -def allow_broken_links - : Flag<["--"], "allow-broken-links">, - HelpText<"Allow llvm-objcopy to remove sections even if it would leave " - "invalid section references. The appropriate sh_link fields " - "will be set to zero.">; +include "CommonOpts.td" defm binary_architecture - : Eq<"binary-architecture", "Used when transforming an architecture-less " - "format (such as binary) to another format">; -def B : JoinedOrSeparate<["-"], "B">, Alias<binary_architecture>; + : Eq<"binary-architecture", "Ignored for compatibility">; +def B : JoinedOrSeparate<["-"], "B">, + Alias<binary_architecture>, + HelpText<"Alias for --binary-architecture">; defm target : Eq<"target", "Format of the input and output file">, Values<"binary">; -def F : JoinedOrSeparate<["-"], "F">, Alias<target>; +def F : JoinedOrSeparate<["-"], "F">, + Alias<target>, + HelpText<"Alias for --target">; defm input_target : Eq<"input-target", "Format of the input file">, Values<"binary">; -def I : JoinedOrSeparate<["-"], "I">, Alias<input_target>; +def I : JoinedOrSeparate<["-"], "I">, + Alias<input_target>, + HelpText<"Alias for --input-target">; defm output_target : Eq<"output-target", "Format of the output file">, Values<"binary">; -def O : JoinedOrSeparate<["-"], "O">, Alias<output_target>; +def O : JoinedOrSeparate<["-"], "O">, + Alias<output_target>, + HelpText<"Alias for --output-target">; + +defm new_symbol_visibility : Eq<"new-symbol-visibility", "Visibility of " + "symbols generated for binary input or added" + " with --add-symbol unless otherwise" + " specified. The default value is 'default'.">; def compress_debug_sections : Flag<["--"], "compress-debug-sections">; def compress_debug_sections_eq @@ -46,34 +42,10 @@ defm split_dwo "<dwo-file>, then strip-dwo on the input file">, MetaVarName<"dwo-file">; -def enable_deterministic_archives - : Flag<["--"], "enable-deterministic-archives">, - HelpText<"Enable deterministic mode when copying archives (use zero for " - "UIDs, GIDs, and timestamps).">; -def D : Flag<["-"], "D">, - Alias<enable_deterministic_archives>, - HelpText<"Alias for --enable-deterministic-archives">; - -def disable_deterministic_archives - : Flag<["--"], "disable-deterministic-archives">, - HelpText<"Disable deterministic mode when copying archives (use real " - "values for UIDs, GIDs, and timestamps).">; -def U : Flag<["-"], "U">, - Alias<disable_deterministic_archives>, - HelpText<"Alias for --disable-deterministic-archives">; - -def preserve_dates : Flag<["--"], "preserve-dates">, - HelpText<"Preserve access and modification timestamps">; -def p : Flag<["-"], "p">, Alias<preserve_dates>; - defm add_gnu_debuglink : Eq<"add-gnu-debuglink", "Add a .gnu_debuglink for <debug-file>">, MetaVarName<"debug-file">; -defm remove_section : Eq<"remove-section", "Remove <section>">, - MetaVarName<"section">; -def R : JoinedOrSeparate<["-"], "R">, Alias<remove_section>; - defm rename_section : Eq<"rename-section", "Renames a section from old to new, optionally with specified flags. " @@ -93,16 +65,20 @@ defm redefine_symbols "symbols from many files.">, MetaVarName<"filename">; -defm keep_section : Eq<"keep-section", "Keep <section>">, - MetaVarName<"section">; defm only_section : Eq<"only-section", "Remove all but <section>">, MetaVarName<"section">; -def j : JoinedOrSeparate<["-"], "j">, Alias<only_section>; +def j : JoinedOrSeparate<["-"], "j">, + Alias<only_section>, + HelpText<"Alias for --only-section">; defm add_section : Eq<"add-section", "Make a section named <section> with the contents of <file>.">, MetaVarName<"section=file">; +defm set_section_alignment + : Eq<"set-section-alignment", "Set alignment for a given section.">, + MetaVarName<"section=align">; + defm set_section_flags : Eq<"set-section-flags", "Set section flags for a given section. Flags supported for GNU " @@ -110,26 +86,14 @@ defm set_section_flags "rom, share, contents, merge, strings.">, MetaVarName<"section=flag1[,flag2,...]">; -def strip_all : Flag<["--"], "strip-all">, - HelpText<"Remove non-allocated sections outside segments. " - ".gnu.warning* sections are not removed">; -def S : Flag<["-"], "S">, Alias<strip_all>; -def strip_all_gnu : Flag<["--"], "strip-all-gnu">, - HelpText<"Compatible with GNU objcopy's --strip-all">; -def strip_debug : Flag<["--"], "strip-debug">, - HelpText<"Remove all debug information">; -def g : Flag<["-"], "g">, Alias<strip_debug>, - HelpText<"Alias for --strip-debug">; +def S : Flag<["-"], "S">, + Alias<strip_all>, + HelpText<"Alias for --strip-all">; def strip_dwo : Flag<["--"], "strip-dwo">, HelpText<"Remove all DWARF .dwo sections from file">; -def strip_sections - : Flag<["--"], "strip-sections">, - HelpText<"Remove all section headers and all sections not in segments">; def strip_non_alloc : Flag<["--"], "strip-non-alloc">, HelpText<"Remove all non-allocated sections outside segments">; -def strip_unneeded : Flag<["--"], "strip-unneeded">, - HelpText<"Remove all symbols not needed by relocations">; defm strip_unneeded_symbol : Eq<"strip-unneeded-symbol", "Remove symbol <symbol> if it is not needed by relocations">, @@ -163,7 +127,9 @@ defm localize_symbols "Reads a list of symbols from <filename> and marks them local.">, MetaVarName<"filename">; -def L : JoinedOrSeparate<["-"], "L">, Alias<localize_symbol>; +def L : JoinedOrSeparate<["-"], "L">, + Alias<localize_symbol>, + HelpText<"Alias for --localize-symbol">; defm globalize_symbol : Eq<"globalize-symbol", "Mark <symbol> as global">, MetaVarName<"symbol">; @@ -178,7 +144,9 @@ defm keep_global_symbol "Convert all symbols except <symbol> to local. May be repeated to " "convert all except a set of symbols to local.">, MetaVarName<"symbol">; -def G : JoinedOrSeparate<["-"], "G">, Alias<keep_global_symbol>; +def G : JoinedOrSeparate<["-"], "G">, + Alias<keep_global_symbol>, + HelpText<"Alias for --keep-global-symbol">; defm keep_global_symbols : Eq<"keep-global-symbols", @@ -196,31 +164,17 @@ defm weaken_symbols "Reads a list of symbols from <filename> and marks them weak.">, MetaVarName<"filename">; -def W : JoinedOrSeparate<["-"], "W">, Alias<weaken_symbol>; +def W : JoinedOrSeparate<["-"], "W">, + Alias<weaken_symbol>, + HelpText<"Alias for --weaken-symbol">; def weaken : Flag<["--"], "weaken">, HelpText<"Mark all global symbols as weak">; -def discard_locals : Flag<["--"], "discard-locals">, - HelpText<"Remove compiler-generated local symbols, (e.g. " - "symbols starting with .L)">; -def X : Flag<["-"], "X">, Alias<discard_locals>; - -def discard_all - : Flag<["--"], "discard-all">, - HelpText<"Remove all local symbols except file and section symbols">; -def x : Flag<["-"], "x">, Alias<discard_all>; -defm strip_symbol : Eq<"strip-symbol", "Remove symbol <symbol>">, - MetaVarName<"symbol">; defm strip_symbols : Eq<"strip-symbols", "Reads a list of symbols from <filename> and removes them.">, MetaVarName<"filename">; -def N : JoinedOrSeparate<["-"], "N">, Alias<strip_symbol>; -defm keep_symbol : Eq<"keep-symbol", "Do not remove symbol <symbol>">, - MetaVarName<"symbol">; -def K : JoinedOrSeparate<["-"], "K">, Alias<keep_symbol>; - defm keep_symbols : Eq<"keep-symbols", "Reads a list of symbols from <filename> and runs as if " @@ -230,13 +184,6 @@ defm keep_symbols "be repeated to read symbols from many files.">, MetaVarName<"filename">; -def only_keep_debug - : Flag<["--"], "only-keep-debug">, - HelpText<"Clear sections that would not be stripped by --strip-debug. " - "Currently only implemented for COFF.">; - -def keep_file_symbols : Flag<["--"], "keep-file-symbols">, - HelpText<"Do not remove file symbols">; defm dump_section : Eq<"dump-section", "Dump contents of section named <section> into file <file>">, @@ -249,9 +196,6 @@ defm prefix_alloc_sections : Eq<"prefix-alloc-sections", "Add <prefix> to the start of every allocated section name">, MetaVarName<"prefix">; -def version : Flag<["--"], "version">, - HelpText<"Print the version and exit.">; -def V : Flag<["-"], "V">, Alias<version>; defm build_id_link_dir : Eq<"build-id-link-dir", "Set directory for --build-id-link-input and " "--build-id-link-output to <dir>">, @@ -265,10 +209,6 @@ defm build_id_link_output "name derived from hex build ID">, MetaVarName<"suffix">; -def regex - : Flag<["--"], "regex">, - HelpText<"Permit regular expressions in name comparison">; - defm set_start : Eq<"set-start", "Set the start address to <addr>. Overrides " "any previous --change-start or --adjust-start values.">, MetaVarName<"addr">; @@ -277,11 +217,12 @@ defm change_start : Eq<"change-start", "Add <incr> to the start address. Can be "cumulatively.">, MetaVarName<"incr">; def adjust_start : JoinedOrSeparate<["--"], "adjust-start">, - Alias<change_start>; + Alias<change_start>, + HelpText<"Alias for --change-start">; defm add_symbol : Eq<"add-symbol", "Add new symbol <name> to .symtab. Accepted flags: " - "global, local, weak, default, hidden, file, section, object, " + "global, local, weak, default, hidden, protected, file, section, object, " "function, indirect-function. Accepted but ignored for " "compatibility: debug, constructor, warning, indirect, synthetic, " "unique-object, before.">, diff --git a/tools/llvm-objcopy/StripOpts.td b/tools/llvm-objcopy/StripOpts.td index 1d06bb3dfb38..cd02cffae673 100644 --- a/tools/llvm-objcopy/StripOpts.td +++ b/tools/llvm-objcopy/StripOpts.td @@ -1,96 +1,17 @@ -include "llvm/Option/OptParser.td" +include "CommonOpts.td" -multiclass Eq<string name, string help> { - def NAME : Separate<["--"], name>; - def NAME #_eq : Joined<["--"], name #"=">, - Alias<!cast<Separate>(NAME)>, - HelpText<help>; -} +def output : JoinedOrSeparate<["-"], "o">, HelpText<"Write output to <file>">, + MetaVarName<"<file>">; -def help : Flag<["--"], "help">; -def h : Flag<["-"], "h">, Alias<help>; - -def allow_broken_links - : Flag<["--"], "allow-broken-links">, - HelpText<"Allow llvm-strip to remove sections even if it would leave " - "invalid section references. The appropriate sh_link fields " - "will be set to zero.">; - -def enable_deterministic_archives - : Flag<["--"], "enable-deterministic-archives">, - HelpText<"Enable deterministic mode when stripping archives (use zero " - "for UIDs, GIDs, and timestamps).">; -def D : Flag<["-"], "D">, - Alias<enable_deterministic_archives>, - HelpText<"Alias for --enable-deterministic-archives">; - -def disable_deterministic_archives - : Flag<["--"], "disable-deterministic-archives">, - HelpText<"Disable deterministic mode when stripping archives (use real " - "values for UIDs, GIDs, and timestamps).">; -def U : Flag<["-"], "U">, - Alias<disable_deterministic_archives>, - HelpText<"Alias for --disable-deterministic-archives">; - -def output : JoinedOrSeparate<["-"], "o">, HelpText<"Write output to <file>">; - -def preserve_dates : Flag<["--"], "preserve-dates">, - HelpText<"Preserve access and modification timestamps">; -def p : Flag<["-"], "p">, Alias<preserve_dates>; - -def strip_all : Flag<["--"], "strip-all">, - HelpText<"Remove non-allocated sections outside segments. " - ".gnu.warning* sections are not removed">; -def s : Flag<["-"], "s">, Alias<strip_all>; +def s : Flag<["-"], "s">, + Alias<strip_all>, + HelpText<"Alias for --strip-all">; def no_strip_all : Flag<["--"], "no-strip-all">, HelpText<"Disable --strip-all">; -def strip_all_gnu : Flag<["--"], "strip-all-gnu">, - HelpText<"Compatible with GNU strip's --strip-all">; -def strip_debug : Flag<["--"], "strip-debug">, - HelpText<"Remove debugging symbols only">; -def d : Flag<["-"], "d">, Alias<strip_debug>; -def g : Flag<["-"], "g">, Alias<strip_debug>; -def S : Flag<["-"], "S">, Alias<strip_debug>; -def strip_unneeded : Flag<["--"], "strip-unneeded">, - HelpText<"Remove all symbols not needed by relocations">; - -defm remove_section : Eq<"remove-section", "Remove <section>">, - MetaVarName<"section">; -def R : JoinedOrSeparate<["-"], "R">, Alias<remove_section>; - -defm strip_symbol : Eq<"strip-symbol", "Strip <symbol>">, - MetaVarName<"symbol">; -def N : JoinedOrSeparate<["-"], "N">, Alias<strip_symbol>; - -defm keep_section : Eq<"keep-section", "Keep <section>">, - MetaVarName<"section">; -defm keep_symbol : Eq<"keep-symbol", "Do not remove symbol <symbol>">, - MetaVarName<"symbol">; -def keep_file_symbols : Flag<["--"], "keep-file-symbols">, - HelpText<"Do not remove file symbols">; - -def K : JoinedOrSeparate<["-"], "K">, Alias<keep_symbol>; - -def only_keep_debug - : Flag<["--"], "only-keep-debug">, - HelpText<"Clear sections that would not be stripped by --strip-debug. " - "Currently only implemented for COFF.">; - -def discard_locals : Flag<["--"], "discard-locals">, - HelpText<"Remove compiler-generated local symbols, (e.g. " - "symbols starting with .L)">; -def X : Flag<["-"], "X">, Alias<discard_locals>; - -def discard_all - : Flag<["--"], "discard-all">, - HelpText<"Remove all local symbols except file and section symbols">; -def x : Flag<["-"], "x">, Alias<discard_all>; - -def regex - : Flag<["--"], "regex">, - HelpText<"Permit regular expressions in name comparison">; - -def version : Flag<["--"], "version">, - HelpText<"Print the version and exit.">; -def V : Flag<["-"], "V">, Alias<version>; +def d : Flag<["-"], "d">, + Alias<strip_debug>, + HelpText<"Alias for --strip-debug">; +def S : Flag<["-"], "S">, + Alias<strip_debug>, + HelpText<"Alias for --strip-debug">; diff --git a/tools/llvm-objcopy/llvm-objcopy.cpp b/tools/llvm-objcopy/llvm-objcopy.cpp index e9372176e43b..a68210f3fdd3 100644 --- a/tools/llvm-objcopy/llvm-objcopy.cpp +++ b/tools/llvm-objcopy/llvm-objcopy.cpp @@ -29,6 +29,7 @@ #include "llvm/Option/ArgList.h" #include "llvm/Option/Option.h" #include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" #include "llvm/Support/Error.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/ErrorOr.h" @@ -36,6 +37,7 @@ #include "llvm/Support/Memory.h" #include "llvm/Support/Path.h" #include "llvm/Support/Process.h" +#include "llvm/Support/StringSaver.h" #include "llvm/Support/WithColor.h" #include "llvm/Support/raw_ostream.h" #include <algorithm> @@ -84,7 +86,7 @@ LLVM_ATTRIBUTE_NORETURN void reportError(StringRef File, Error E) { ErrorSuccess reportWarning(Error E) { assert(E); - WithColor::warning(errs(), ToolName) << toString(std::move(E)); + WithColor::warning(errs(), ToolName) << toString(std::move(E)) << '\n'; return Error::success(); } @@ -130,16 +132,18 @@ static Error deepWriteArchive(StringRef ArcName, /// The function executeObjcopyOnIHex does the dispatch based on the format /// of the output specified by the command line options. -static Error executeObjcopyOnIHex(const CopyConfig &Config, MemoryBuffer &In, +static Error executeObjcopyOnIHex(CopyConfig &Config, MemoryBuffer &In, Buffer &Out) { // TODO: support output formats other than ELF. + if (Error E = Config.parseELFConfig()) + return E; return elf::executeObjcopyOnIHex(Config, In, Out); } /// The function executeObjcopyOnRawBinary does the dispatch based on the format /// of the output specified by the command line options. -static Error executeObjcopyOnRawBinary(const CopyConfig &Config, - MemoryBuffer &In, Buffer &Out) { +static Error executeObjcopyOnRawBinary(CopyConfig &Config, MemoryBuffer &In, + Buffer &Out) { switch (Config.OutputFormat) { case FileFormat::ELF: // FIXME: Currently, we call elf::executeObjcopyOnRawBinary even if the @@ -148,6 +152,8 @@ static Error executeObjcopyOnRawBinary(const CopyConfig &Config, case FileFormat::Binary: case FileFormat::IHex: case FileFormat::Unspecified: + if (Error E = Config.parseELFConfig()) + return E; return elf::executeObjcopyOnRawBinary(Config, In, Out); } @@ -156,11 +162,13 @@ static Error executeObjcopyOnRawBinary(const CopyConfig &Config, /// The function executeObjcopyOnBinary does the dispatch based on the format /// of the input binary (ELF, MachO or COFF). -static Error executeObjcopyOnBinary(const CopyConfig &Config, - object::Binary &In, Buffer &Out) { - if (auto *ELFBinary = dyn_cast<object::ELFObjectFileBase>(&In)) +static Error executeObjcopyOnBinary(CopyConfig &Config, object::Binary &In, + Buffer &Out) { + if (auto *ELFBinary = dyn_cast<object::ELFObjectFileBase>(&In)) { + if (Error E = Config.parseELFConfig()) + return E; return elf::executeObjcopyOnBinary(Config, *ELFBinary, Out); - else if (auto *COFFBinary = dyn_cast<object::COFFObjectFile>(&In)) + } else if (auto *COFFBinary = dyn_cast<object::COFFObjectFile>(&In)) return coff::executeObjcopyOnBinary(Config, *COFFBinary, Out); else if (auto *MachOBinary = dyn_cast<object::MachOObjectFile>(&In)) return macho::executeObjcopyOnBinary(Config, *MachOBinary, Out); @@ -169,8 +177,7 @@ static Error executeObjcopyOnBinary(const CopyConfig &Config, "unsupported object file format"); } -static Error executeObjcopyOnArchive(const CopyConfig &Config, - const Archive &Ar) { +static Error executeObjcopyOnArchive(CopyConfig &Config, const Archive &Ar) { std::vector<NewArchiveMember> NewArchiveMembers; Error Err = Error::success(); for (const Archive::Child &Child : Ar.children(Err)) { @@ -246,7 +253,7 @@ static Error restoreStatOnFile(StringRef Filename, /// The function executeObjcopy does the higher level dispatch based on the type /// of input (raw binary, archive or single object file) and takes care of the /// format-agnostic modifications, i.e. preserving dates. -static Error executeObjcopy(const CopyConfig &Config) { +static Error executeObjcopy(CopyConfig &Config) { sys::fs::file_status Stat; if (Config.InputFilename != "-") { if (auto EC = sys::fs::status(Config.InputFilename, Stat)) @@ -255,7 +262,7 @@ static Error executeObjcopy(const CopyConfig &Config) { Stat.permissions(static_cast<sys::fs::perms>(0777)); } - typedef Error (*ProcessRawFn)(const CopyConfig &, MemoryBuffer &, Buffer &); + using ProcessRawFn = Error (*)(CopyConfig &, MemoryBuffer &, Buffer &); ProcessRawFn ProcessRaw; switch (Config.InputFormat) { case FileFormat::Binary: @@ -310,15 +317,31 @@ int main(int argc, char **argv) { InitLLVM X(argc, argv); ToolName = argv[0]; bool IsStrip = sys::path::stem(ToolName).contains("strip"); + + // Expand response files. + // TODO: Move these lines, which are copied from lib/Support/CommandLine.cpp, + // into a separate function in the CommandLine library and call that function + // here. This is duplicated code. + SmallVector<const char *, 20> NewArgv(argv, argv + argc); + BumpPtrAllocator A; + StringSaver Saver(A); + cl::ExpandResponseFiles(Saver, + Triple(sys::getProcessTriple()).isOSWindows() + ? cl::TokenizeWindowsCommandLine + : cl::TokenizeGNUCommandLine, + NewArgv); + + auto Args = makeArrayRef(NewArgv).drop_front(); + Expected<DriverConfig> DriverConfig = - IsStrip ? parseStripOptions(makeArrayRef(argv + 1, argc), reportWarning) - : parseObjcopyOptions(makeArrayRef(argv + 1, argc)); + IsStrip ? parseStripOptions(Args, reportWarning) + : parseObjcopyOptions(Args, reportWarning); if (!DriverConfig) { logAllUnhandledErrors(DriverConfig.takeError(), WithColor::error(errs(), ToolName)); return 1; } - for (const CopyConfig &CopyConfig : DriverConfig->CopyConfigs) { + for (CopyConfig &CopyConfig : DriverConfig->CopyConfigs) { if (Error E = executeObjcopy(CopyConfig)) { logAllUnhandledErrors(std::move(E), WithColor::error(errs(), ToolName)); return 1; |