//===- LinkerScript.cpp ---------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file contains the parser/evaluator of the linker script. // It parses a linker script and write the result to Config or ScriptConfig // objects. // // If SECTIONS command is used, a ScriptConfig contains an AST // of the command which will later be consumed by createSections() and // assignAddresses(). // //===----------------------------------------------------------------------===// #include "LinkerScript.h" #include "Config.h" #include "Driver.h" #include "InputSection.h" #include "OutputSections.h" #include "ScriptParser.h" #include "Strings.h" #include "Symbols.h" #include "SymbolTable.h" #include "Target.h" #include "Writer.h" #include "llvm/ADT/StringSwitch.h" #include "llvm/Support/ELF.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/Path.h" #include "llvm/Support/StringSaver.h" using namespace llvm; using namespace llvm::ELF; using namespace llvm::object; using namespace lld; using namespace lld::elf; ScriptConfiguration *elf::ScriptConfig; template static void addRegular(SymbolAssignment *Cmd) { Symbol *Sym = Symtab::X->addRegular(Cmd->Name, STB_GLOBAL, STV_DEFAULT); Sym->Visibility = Cmd->Hidden ? STV_HIDDEN : STV_DEFAULT; Cmd->Sym = Sym->body(); } template static void addSynthetic(SymbolAssignment *Cmd) { Symbol *Sym = Symtab::X->addSynthetic( Cmd->Name, nullptr, 0, Cmd->Hidden ? STV_HIDDEN : STV_DEFAULT); Cmd->Sym = Sym->body(); } // If a symbol was in PROVIDE(), we need to define it only when // it is an undefined symbol. template static bool shouldDefine(SymbolAssignment *Cmd) { if (Cmd->Name == ".") return false; if (!Cmd->Provide) return true; SymbolBody *B = Symtab::X->find(Cmd->Name); return B && B->isUndefined(); } bool SymbolAssignment::classof(const BaseCommand *C) { return C->Kind == AssignmentKind; } bool OutputSectionCommand::classof(const BaseCommand *C) { return C->Kind == OutputSectionKind; } bool InputSectionDescription::classof(const BaseCommand *C) { return C->Kind == InputSectionKind; } bool AssertCommand::classof(const BaseCommand *C) { return C->Kind == AssertKind; } template static bool isDiscarded(InputSectionBase *S) { return !S || !S->Live; } template LinkerScript::LinkerScript() {} template LinkerScript::~LinkerScript() {} template bool LinkerScript::shouldKeep(InputSectionBase *S) { for (StringRef Pat : Opt.KeptSections) if (globMatch(Pat, S->getSectionName())) return true; return false; } static bool match(ArrayRef Patterns, StringRef S) { for (StringRef Pat : Patterns) if (globMatch(Pat, S)) return true; return false; } static bool fileMatches(const InputSectionDescription *Desc, StringRef Filename) { if (!globMatch(Desc->FilePattern, Filename)) return false; return Desc->ExcludedFiles.empty() || !match(Desc->ExcludedFiles, Filename); } // Returns input sections filtered by given glob patterns. template std::vector *> LinkerScript::getInputSections(const InputSectionDescription *I) { ArrayRef Patterns = I->SectionPatterns; std::vector *> Ret; for (const std::unique_ptr> &F : Symtab::X->getObjectFiles()) { if (fileMatches(I, sys::path::filename(F->getName()))) for (InputSectionBase *S : F->getSections()) if (!isDiscarded(S) && !S->OutSec && match(Patterns, S->getSectionName())) Ret.push_back(S); } if (llvm::find(Patterns, "COMMON") != Patterns.end()) Ret.push_back(CommonInputSection::X); return Ret; } // You can define new symbols using linker scripts. For example, // ".text { abc.o(.text); foo = .; def.o(.text); }" defines symbol // foo just after abc.o's text section contents. This class is to // handle such symbol definitions. // // In order to handle scripts like the above one, we want to // keep symbol definitions in output sections. Because output sections // can contain only input sections, we wrap symbol definitions // with dummy input sections. This class serves that purpose. template class elf::LayoutInputSection : public InputSectionBase { public: explicit LayoutInputSection(SymbolAssignment *Cmd); static bool classof(const InputSectionBase *S); SymbolAssignment *Cmd; private: typename ELFT::Shdr Hdr; }; template static InputSectionBase * getNonLayoutSection(std::vector *> &Vec) { for (InputSectionBase *S : Vec) if (!isa>(S)) return S; return nullptr; } template static T *zero(T *Val) { memset(Val, 0, sizeof(*Val)); return Val; } template LayoutInputSection::LayoutInputSection(SymbolAssignment *Cmd) : InputSectionBase(nullptr, zero(&Hdr), InputSectionBase::Layout), Cmd(Cmd) { this->Live = true; Hdr.sh_type = SHT_NOBITS; } template bool LayoutInputSection::classof(const InputSectionBase *S) { return S->SectionKind == InputSectionBase::Layout; } template static bool compareName(InputSectionBase *A, InputSectionBase *B) { return A->getSectionName() < B->getSectionName(); } template static bool compareAlignment(InputSectionBase *A, InputSectionBase *B) { // ">" is not a mistake. Larger alignments are placed before smaller // alignments in order to reduce the amount of padding necessary. // This is compatible with GNU. return A->Alignment > B->Alignment; } template static std::function *, InputSectionBase *)> getComparator(SortKind K) { if (K == SortByName) return compareName; return compareAlignment; } template void LinkerScript::discard(OutputSectionCommand &Cmd) { for (const std::unique_ptr &Base : Cmd.Commands) { if (auto *Cmd = dyn_cast(Base.get())) { for (InputSectionBase *S : getInputSections(Cmd)) { S->Live = false; reportDiscarded(S); } } } } static bool checkConstraint(uint64_t Flags, ConstraintKind Kind) { bool RO = (Kind == ConstraintKind::ReadOnly); bool RW = (Kind == ConstraintKind::ReadWrite); bool Writable = Flags & SHF_WRITE; return !((RO && Writable) || (RW && !Writable)); } template static bool matchConstraints(ArrayRef *> Sections, ConstraintKind Kind) { if (Kind == ConstraintKind::NoConstraint) return true; return llvm::all_of(Sections, [=](InputSectionBase *Sec) { return checkConstraint(Sec->getSectionHdr()->sh_flags, Kind); }); } template std::vector *> LinkerScript::createInputSectionList(OutputSectionCommand &OutCmd) { std::vector *> Ret; for (const std::unique_ptr &Base : OutCmd.Commands) { if (auto *OutCmd = dyn_cast(Base.get())) { if (shouldDefine(OutCmd)) addSynthetic(OutCmd); Ret.push_back(new (LAlloc.Allocate()) LayoutInputSection(OutCmd)); continue; } auto *Cmd = cast(Base.get()); std::vector *> V = getInputSections(Cmd); if (!matchConstraints(V, OutCmd.Constraint)) continue; if (Cmd->SortInner) std::stable_sort(V.begin(), V.end(), getComparator(Cmd->SortInner)); if (Cmd->SortOuter) std::stable_sort(V.begin(), V.end(), getComparator(Cmd->SortOuter)); Ret.insert(Ret.end(), V.begin(), V.end()); } return Ret; } template void LinkerScript::createAssignments() { for (const std::unique_ptr &Cmd : Opt.Assignments) { if (shouldDefine(Cmd.get())) addRegular(Cmd.get()); if (Cmd->Sym) cast>(Cmd->Sym)->Value = Cmd->Expression(0); } } template void LinkerScript::createSections(OutputSectionFactory &Factory) { for (const std::unique_ptr &Base1 : Opt.Commands) { if (auto *Cmd = dyn_cast(Base1.get())) { if (shouldDefine(Cmd)) addRegular(Cmd); continue; } if (auto *Cmd = dyn_cast(Base1.get())) { if (Cmd->Name == "/DISCARD/") { discard(*Cmd); continue; } std::vector *> V = createInputSectionList(*Cmd); InputSectionBase *Head = getNonLayoutSection(V); if (!Head) continue; OutputSectionBase *OutSec; bool IsNew; std::tie(OutSec, IsNew) = Factory.create(Head, Cmd->Name); if (IsNew) OutputSections->push_back(OutSec); uint32_t Subalign = Cmd->SubalignExpr ? Cmd->SubalignExpr(0) : 0; for (InputSectionBase *Sec : V) { if (Subalign) Sec->Alignment = Subalign; if (!Sec->OutSec) OutSec->addSection(Sec); } } } // Add orphan sections. for (const std::unique_ptr> &F : Symtab::X->getObjectFiles()) { for (InputSectionBase *S : F->getSections()) { if (isDiscarded(S) || S->OutSec) continue; OutputSectionBase *OutSec; bool IsNew; std::tie(OutSec, IsNew) = Factory.create(S, getOutputSectionName(S)); if (IsNew) OutputSections->push_back(OutSec); OutSec->addSection(S); } } } // Linker script may define start and end symbols for special section types, // like .got, .eh_frame_hdr, .eh_frame and others. Those sections are not a list // of regular input input sections, therefore our way of defining symbols for // regular sections will not work. The approach we use for special section types // is not perfect - it handles only start and end symbols. template void addStartEndSymbols(OutputSectionCommand *Cmd, OutputSectionBase *Sec) { bool Start = true; BaseCommand *PrevCmd = nullptr; for (std::unique_ptr &Base : Cmd->Commands) { if (auto *AssignCmd = dyn_cast(Base.get())) { if (auto *Sym = cast_or_null>(AssignCmd->Sym)) { Sym->Section = Sec; Sym->Value = AssignCmd->Expression(Sec->getVA() + (Start ? 0 : Sec->getSize())) - Sec->getVA(); } } else { if (!Start && isa(PrevCmd)) error("section '" + Sec->getName() + "' supports only start and end symbols"); Start = false; } PrevCmd = Base.get(); } } template void assignOffsets(OutputSectionCommand *Cmd, OutputSectionBase *Sec) { auto *OutSec = dyn_cast>(Sec); if (!OutSec) { Sec->assignOffsets(); // This section is not regular output section. However linker script may // have defined start/end symbols for it. This case is handled below. addStartEndSymbols(Cmd, Sec); return; } typedef typename ELFT::uint uintX_t; uintX_t Off = 0; for (InputSection *I : OutSec->Sections) { if (auto *L = dyn_cast>(I)) { uintX_t Value = L->Cmd->Expression(Sec->getVA() + Off) - Sec->getVA(); if (L->Cmd->Name == ".") { Off = Value; } else if (auto *Sym = cast_or_null>(L->Cmd->Sym)) { // shouldDefine could have returned false, so we need to check Sym, // for non-null value. Sym->Section = OutSec; Sym->Value = Value; } } else { Off = alignTo(Off, I->Alignment); I->OutSecOff = Off; Off += I->getSize(); } // Update section size inside for-loop, so that SIZEOF // works correctly in the case below: // .foo { *(.aaa) a = SIZEOF(.foo); *(.bbb) } Sec->setSize(Off); } } template static OutputSectionBase * findSection(OutputSectionCommand &Cmd, ArrayRef *> Sections) { for (OutputSectionBase *Sec : Sections) { if (Sec->getName() != Cmd.Name) continue; if (checkConstraint(Sec->getFlags(), Cmd.Constraint)) return Sec; } return nullptr; } template void LinkerScript::assignAddresses() { // Orphan sections are sections present in the input files which // are not explicitly placed into the output file by the linker script. // We place orphan sections at end of file. // Other linkers places them using some heuristics as described in // https://sourceware.org/binutils/docs/ld/Orphan-Sections.html#Orphan-Sections. for (OutputSectionBase *Sec : *OutputSections) { StringRef Name = Sec->getName(); if (getSectionIndex(Name) == INT_MAX) Opt.Commands.push_back(llvm::make_unique(Name)); } // Assign addresses as instructed by linker script SECTIONS sub-commands. Dot = getHeaderSize(); uintX_t MinVA = std::numeric_limits::max(); uintX_t ThreadBssOffset = 0; for (const std::unique_ptr &Base : Opt.Commands) { if (auto *Cmd = dyn_cast(Base.get())) { if (Cmd->Name == ".") { Dot = Cmd->Expression(Dot); } else if (Cmd->Sym) { cast>(Cmd->Sym)->Value = Cmd->Expression(Dot); } continue; } if (auto *Cmd = dyn_cast(Base.get())) { Cmd->Expression(Dot); continue; } auto *Cmd = cast(Base.get()); OutputSectionBase *Sec = findSection(*Cmd, *OutputSections); if (!Sec) continue; if (Cmd->AddrExpr) Dot = Cmd->AddrExpr(Dot); if (Cmd->AlignExpr) Sec->updateAlignment(Cmd->AlignExpr(Dot)); if ((Sec->getFlags() & SHF_TLS) && Sec->getType() == SHT_NOBITS) { uintX_t TVA = Dot + ThreadBssOffset; TVA = alignTo(TVA, Sec->getAlignment()); Sec->setVA(TVA); assignOffsets(Cmd, Sec); ThreadBssOffset = TVA - Dot + Sec->getSize(); continue; } if (!(Sec->getFlags() & SHF_ALLOC)) { assignOffsets(Cmd, Sec); continue; } Dot = alignTo(Dot, Sec->getAlignment()); Sec->setVA(Dot); assignOffsets(Cmd, Sec); MinVA = std::min(MinVA, Dot); Dot += Sec->getSize(); } // ELF and Program headers need to be right before the first section in // memory. Set their addresses accordingly. MinVA = alignDown(MinVA - Out::ElfHeader->getSize() - Out::ProgramHeaders->getSize(), Target->PageSize); Out::ElfHeader->setVA(MinVA); Out::ProgramHeaders->setVA(Out::ElfHeader->getSize() + MinVA); } // Creates program headers as instructed by PHDRS linker script command. template std::vector> LinkerScript::createPhdrs() { std::vector> Ret; // Process PHDRS and FILEHDR keywords because they are not // real output sections and cannot be added in the following loop. for (const PhdrsCommand &Cmd : Opt.PhdrsCommands) { Ret.emplace_back(Cmd.Type, Cmd.Flags == UINT_MAX ? PF_R : Cmd.Flags); PhdrEntry &Phdr = Ret.back(); if (Cmd.HasFilehdr) Phdr.add(Out::ElfHeader); if (Cmd.HasPhdrs) Phdr.add(Out::ProgramHeaders); } // Add output sections to program headers. PhdrEntry *Load = nullptr; uintX_t Flags = PF_R; for (OutputSectionBase *Sec : *OutputSections) { if (!(Sec->getFlags() & SHF_ALLOC)) break; std::vector PhdrIds = getPhdrIndices(Sec->getName()); if (!PhdrIds.empty()) { // Assign headers specified by linker script for (size_t Id : PhdrIds) { Ret[Id].add(Sec); if (Opt.PhdrsCommands[Id].Flags == UINT_MAX) Ret[Id].H.p_flags |= Sec->getPhdrFlags(); } } else { // If we have no load segment or flags've changed then we want new load // segment. uintX_t NewFlags = Sec->getPhdrFlags(); if (Load == nullptr || Flags != NewFlags) { Load = &*Ret.emplace(Ret.end(), PT_LOAD, NewFlags); Flags = NewFlags; } Load->add(Sec); } } return Ret; } template bool LinkerScript::ignoreInterpSection() { // Ignore .interp section in case we have PHDRS specification // and PT_INTERP isn't listed. return !Opt.PhdrsCommands.empty() && llvm::find_if(Opt.PhdrsCommands, [](const PhdrsCommand &Cmd) { return Cmd.Type == PT_INTERP; }) == Opt.PhdrsCommands.end(); } template ArrayRef LinkerScript::getFiller(StringRef Name) { for (const std::unique_ptr &Base : Opt.Commands) if (auto *Cmd = dyn_cast(Base.get())) if (Cmd->Name == Name) return Cmd->Filler; return {}; } template Expr LinkerScript::getLma(StringRef Name) { for (const std::unique_ptr &Base : Opt.Commands) if (auto *Cmd = dyn_cast(Base.get())) if (Cmd->LmaExpr && Cmd->Name == Name) return Cmd->LmaExpr; return {}; } // Returns the index of the given section name in linker script // SECTIONS commands. Sections are laid out as the same order as they // were in the script. If a given name did not appear in the script, // it returns INT_MAX, so that it will be laid out at end of file. template int LinkerScript::getSectionIndex(StringRef Name) { int I = 0; for (std::unique_ptr &Base : Opt.Commands) { if (auto *Cmd = dyn_cast(Base.get())) if (Cmd->Name == Name) return I; ++I; } return INT_MAX; } // A compartor to sort output sections. Returns -1 or 1 if // A or B are mentioned in linker script. Otherwise, returns 0. template int LinkerScript::compareSections(StringRef A, StringRef B) { int I = getSectionIndex(A); int J = getSectionIndex(B); if (I == INT_MAX && J == INT_MAX) return 0; return I < J ? -1 : 1; } template bool LinkerScript::hasPhdrsCommands() { return !Opt.PhdrsCommands.empty(); } template typename ELFT::uint LinkerScript::getOutputSectionAddress(StringRef Name) { for (OutputSectionBase *Sec : *OutputSections) if (Sec->getName() == Name) return Sec->getVA(); error("undefined section " + Name); return 0; } template typename ELFT::uint LinkerScript::getOutputSectionSize(StringRef Name) { for (OutputSectionBase *Sec : *OutputSections) if (Sec->getName() == Name) return Sec->getSize(); error("undefined section " + Name); return 0; } template typename ELFT::uint LinkerScript::getHeaderSize() { return Out::ElfHeader->getSize() + Out::ProgramHeaders->getSize(); } // Returns indices of ELF headers containing specific section, identified // by Name. Each index is a zero based number of ELF header listed within // PHDRS {} script block. template std::vector LinkerScript::getPhdrIndices(StringRef SectionName) { for (const std::unique_ptr &Base : Opt.Commands) { auto *Cmd = dyn_cast(Base.get()); if (!Cmd || Cmd->Name != SectionName) continue; std::vector Ret; for (StringRef PhdrName : Cmd->Phdrs) Ret.push_back(getPhdrIndex(PhdrName)); return Ret; } return {}; } template size_t LinkerScript::getPhdrIndex(StringRef PhdrName) { size_t I = 0; for (PhdrsCommand &Cmd : Opt.PhdrsCommands) { if (Cmd.Name == PhdrName) return I; ++I; } error("section header '" + PhdrName + "' is not listed in PHDRS"); return 0; } class elf::ScriptParser : public ScriptParserBase { typedef void (ScriptParser::*Handler)(); public: ScriptParser(StringRef S, bool B) : ScriptParserBase(S), IsUnderSysroot(B) {} void readLinkerScript(); void readVersionScript(); private: void addFile(StringRef Path); void readAsNeeded(); void readEntry(); void readExtern(); void readGroup(); void readInclude(); void readNothing() {} void readOutput(); void readOutputArch(); void readOutputFormat(); void readPhdrs(); void readSearchDir(); void readSections(); void readVersion(); void readVersionScriptCommand(); SymbolAssignment *readAssignment(StringRef Name); OutputSectionCommand *readOutputSectionDescription(StringRef OutSec); std::vector readOutputSectionFiller(); std::vector readOutputSectionPhdrs(); InputSectionDescription *readInputSectionDescription(StringRef Tok); std::vector readInputFilePatterns(); InputSectionDescription *readInputSectionRules(StringRef FilePattern); unsigned readPhdrType(); SortKind readSortKind(); SymbolAssignment *readProvideHidden(bool Provide, bool Hidden); SymbolAssignment *readProvideOrAssignment(StringRef Tok); void readSort(); Expr readAssert(); Expr readExpr(); Expr readExpr1(Expr Lhs, int MinPrec); Expr readPrimary(); Expr readTernary(Expr Cond); Expr readParenExpr(); // For parsing version script. void readExtern(std::vector *Globals); void readVersionDeclaration(StringRef VerStr); void readGlobal(StringRef VerStr); void readLocal(); const static StringMap Cmd; ScriptConfiguration &Opt = *ScriptConfig; StringSaver Saver = {ScriptConfig->Alloc}; bool IsUnderSysroot; }; const StringMap elf::ScriptParser::Cmd = { {"ENTRY", &ScriptParser::readEntry}, {"EXTERN", &ScriptParser::readExtern}, {"GROUP", &ScriptParser::readGroup}, {"INCLUDE", &ScriptParser::readInclude}, {"INPUT", &ScriptParser::readGroup}, {"OUTPUT", &ScriptParser::readOutput}, {"OUTPUT_ARCH", &ScriptParser::readOutputArch}, {"OUTPUT_FORMAT", &ScriptParser::readOutputFormat}, {"PHDRS", &ScriptParser::readPhdrs}, {"SEARCH_DIR", &ScriptParser::readSearchDir}, {"SECTIONS", &ScriptParser::readSections}, {"VERSION", &ScriptParser::readVersion}, {";", &ScriptParser::readNothing}}; void ScriptParser::readVersionScript() { readVersionScriptCommand(); if (!atEOF()) setError("EOF expected, but got " + next()); } void ScriptParser::readVersionScriptCommand() { if (skip("{")) { readVersionDeclaration(""); return; } while (!atEOF() && !Error && peek() != "}") { StringRef VerStr = next(); if (VerStr == "{") { setError("anonymous version definition is used in " "combination with other version definitions"); return; } expect("{"); readVersionDeclaration(VerStr); } } void ScriptParser::readVersion() { expect("{"); readVersionScriptCommand(); expect("}"); } void ScriptParser::readLinkerScript() { while (!atEOF()) { StringRef Tok = next(); if (Handler Fn = Cmd.lookup(Tok)) { (this->*Fn)(); } else if (SymbolAssignment *Cmd = readProvideOrAssignment(Tok)) { if (Opt.HasContents) Opt.Commands.emplace_back(Cmd); else Opt.Assignments.emplace_back(Cmd); } else { setError("unknown directive: " + Tok); } } } void ScriptParser::addFile(StringRef S) { if (IsUnderSysroot && S.startswith("/")) { SmallString<128> Path; (Config->Sysroot + S).toStringRef(Path); if (sys::fs::exists(Path)) { Driver->addFile(Saver.save(Path.str())); return; } } if (sys::path::is_absolute(S)) { Driver->addFile(S); } else if (S.startswith("=")) { if (Config->Sysroot.empty()) Driver->addFile(S.substr(1)); else Driver->addFile(Saver.save(Config->Sysroot + "/" + S.substr(1))); } else if (S.startswith("-l")) { Driver->addLibrary(S.substr(2)); } else if (sys::fs::exists(S)) { Driver->addFile(S); } else { std::string Path = findFromSearchPaths(S); if (Path.empty()) setError("unable to find " + S); else Driver->addFile(Saver.save(Path)); } } void ScriptParser::readAsNeeded() { expect("("); bool Orig = Config->AsNeeded; Config->AsNeeded = true; while (!Error && !skip(")")) addFile(next()); Config->AsNeeded = Orig; } void ScriptParser::readEntry() { // -e takes predecence over ENTRY(). expect("("); StringRef Tok = next(); if (Config->Entry.empty()) Config->Entry = Tok; expect(")"); } void ScriptParser::readExtern() { expect("("); while (!Error && !skip(")")) Config->Undefined.push_back(next()); } void ScriptParser::readGroup() { expect("("); while (!Error && !skip(")")) { StringRef Tok = next(); if (Tok == "AS_NEEDED") readAsNeeded(); else addFile(Tok); } } void ScriptParser::readInclude() { StringRef Tok = next(); auto MBOrErr = MemoryBuffer::getFile(Tok); if (!MBOrErr) { setError("cannot open " + Tok); return; } std::unique_ptr &MB = *MBOrErr; StringRef S = Saver.save(MB->getMemBufferRef().getBuffer()); std::vector V = tokenize(S); Tokens.insert(Tokens.begin() + Pos, V.begin(), V.end()); } void ScriptParser::readOutput() { // -o takes predecence over OUTPUT(). expect("("); StringRef Tok = next(); if (Config->OutputFile.empty()) Config->OutputFile = Tok; expect(")"); } void ScriptParser::readOutputArch() { // Error checking only for now. expect("("); next(); expect(")"); } void ScriptParser::readOutputFormat() { // Error checking only for now. expect("("); next(); StringRef Tok = next(); if (Tok == ")") return; if (Tok != ",") { setError("unexpected token: " + Tok); return; } next(); expect(","); next(); expect(")"); } void ScriptParser::readPhdrs() { expect("{"); while (!Error && !skip("}")) { StringRef Tok = next(); Opt.PhdrsCommands.push_back({Tok, PT_NULL, false, false, UINT_MAX}); PhdrsCommand &PhdrCmd = Opt.PhdrsCommands.back(); PhdrCmd.Type = readPhdrType(); do { Tok = next(); if (Tok == ";") break; if (Tok == "FILEHDR") PhdrCmd.HasFilehdr = true; else if (Tok == "PHDRS") PhdrCmd.HasPhdrs = true; else if (Tok == "FLAGS") { expect("("); // Passing 0 for the value of dot is a bit of a hack. It means that // we accept expressions like ".|1". PhdrCmd.Flags = readExpr()(0); expect(")"); } else setError("unexpected header attribute: " + Tok); } while (!Error); } } void ScriptParser::readSearchDir() { expect("("); Config->SearchPaths.push_back(next()); expect(")"); } void ScriptParser::readSections() { Opt.HasContents = true; expect("{"); while (!Error && !skip("}")) { StringRef Tok = next(); BaseCommand *Cmd = readProvideOrAssignment(Tok); if (!Cmd) { if (Tok == "ASSERT") Cmd = new AssertCommand(readAssert()); else Cmd = readOutputSectionDescription(Tok); } Opt.Commands.emplace_back(Cmd); } } static int precedence(StringRef Op) { return StringSwitch(Op) .Case("*", 4) .Case("/", 4) .Case("+", 3) .Case("-", 3) .Case("<", 2) .Case(">", 2) .Case(">=", 2) .Case("<=", 2) .Case("==", 2) .Case("!=", 2) .Case("&", 1) .Case("|", 1) .Default(-1); } std::vector ScriptParser::readInputFilePatterns() { std::vector V; while (!Error && !skip(")")) V.push_back(next()); return V; } SortKind ScriptParser::readSortKind() { if (skip("SORT") || skip("SORT_BY_NAME")) return SortByName; if (skip("SORT_BY_ALIGNMENT")) return SortByAlignment; return SortNone; } InputSectionDescription * ScriptParser::readInputSectionRules(StringRef FilePattern) { auto *Cmd = new InputSectionDescription; Cmd->FilePattern = FilePattern; expect("("); // Read EXCLUDE_FILE(). if (skip("EXCLUDE_FILE")) { expect("("); while (!Error && !skip(")")) Cmd->ExcludedFiles.push_back(next()); } // Read SORT(). if (SortKind K1 = readSortKind()) { Cmd->SortOuter = K1; expect("("); if (SortKind K2 = readSortKind()) { Cmd->SortInner = K2; expect("("); Cmd->SectionPatterns = readInputFilePatterns(); expect(")"); } else { Cmd->SectionPatterns = readInputFilePatterns(); } expect(")"); return Cmd; } Cmd->SectionPatterns = readInputFilePatterns(); return Cmd; } InputSectionDescription * ScriptParser::readInputSectionDescription(StringRef Tok) { // Input section wildcard can be surrounded by KEEP. // https://sourceware.org/binutils/docs/ld/Input-Section-Keep.html#Input-Section-Keep if (Tok == "KEEP") { expect("("); StringRef FilePattern = next(); InputSectionDescription *Cmd = readInputSectionRules(FilePattern); expect(")"); Opt.KeptSections.insert(Opt.KeptSections.end(), Cmd->SectionPatterns.begin(), Cmd->SectionPatterns.end()); return Cmd; } return readInputSectionRules(Tok); } void ScriptParser::readSort() { expect("("); expect("CONSTRUCTORS"); expect(")"); } Expr ScriptParser::readAssert() { expect("("); Expr E = readExpr(); expect(","); StringRef Msg = next(); expect(")"); return [=](uint64_t Dot) { uint64_t V = E(Dot); if (!V) error(Msg); return V; }; } OutputSectionCommand * ScriptParser::readOutputSectionDescription(StringRef OutSec) { OutputSectionCommand *Cmd = new OutputSectionCommand(OutSec); // Read an address expression. // https://sourceware.org/binutils/docs/ld/Output-Section-Address.html#Output-Section-Address if (peek() != ":") Cmd->AddrExpr = readExpr(); expect(":"); if (skip("AT")) Cmd->LmaExpr = readParenExpr(); if (skip("ALIGN")) Cmd->AlignExpr = readParenExpr(); if (skip("SUBALIGN")) Cmd->SubalignExpr = readParenExpr(); // Parse constraints. if (skip("ONLY_IF_RO")) Cmd->Constraint = ConstraintKind::ReadOnly; if (skip("ONLY_IF_RW")) Cmd->Constraint = ConstraintKind::ReadWrite; expect("{"); while (!Error && !skip("}")) { StringRef Tok = next(); if (SymbolAssignment *Assignment = readProvideOrAssignment(Tok)) Cmd->Commands.emplace_back(Assignment); else if (Tok == "SORT") readSort(); else if (peek() == "(") Cmd->Commands.emplace_back(readInputSectionDescription(Tok)); else setError("unknown command " + Tok); } Cmd->Phdrs = readOutputSectionPhdrs(); Cmd->Filler = readOutputSectionFiller(); return Cmd; } // Read "=" where is an octal/decimal/hexadecimal number. // https://sourceware.org/binutils/docs/ld/Output-Section-Fill.html // // ld.gold is not fully compatible with ld.bfd. ld.bfd handles // hexstrings as blobs of arbitrary sizes, while ld.gold handles them // as 32-bit big-endian values. We will do the same as ld.gold does // because it's simpler than what ld.bfd does. std::vector ScriptParser::readOutputSectionFiller() { if (!peek().startswith("=")) return {}; StringRef Tok = next(); uint32_t V; if (Tok.substr(1).getAsInteger(0, V)) { setError("invalid filler expression: " + Tok); return {}; } return {uint8_t(V >> 24), uint8_t(V >> 16), uint8_t(V >> 8), uint8_t(V)}; } SymbolAssignment *ScriptParser::readProvideHidden(bool Provide, bool Hidden) { expect("("); SymbolAssignment *Cmd = readAssignment(next()); Cmd->Provide = Provide; Cmd->Hidden = Hidden; expect(")"); expect(";"); return Cmd; } SymbolAssignment *ScriptParser::readProvideOrAssignment(StringRef Tok) { SymbolAssignment *Cmd = nullptr; if (peek() == "=" || peek() == "+=") { Cmd = readAssignment(Tok); expect(";"); } else if (Tok == "PROVIDE") { Cmd = readProvideHidden(true, false); } else if (Tok == "HIDDEN") { Cmd = readProvideHidden(false, true); } else if (Tok == "PROVIDE_HIDDEN") { Cmd = readProvideHidden(true, true); } return Cmd; } static uint64_t getSymbolValue(StringRef S, uint64_t Dot) { if (S == ".") return Dot; switch (Config->EKind) { case ELF32LEKind: if (SymbolBody *B = Symtab::X->find(S)) return B->getVA(); break; case ELF32BEKind: if (SymbolBody *B = Symtab::X->find(S)) return B->getVA(); break; case ELF64LEKind: if (SymbolBody *B = Symtab::X->find(S)) return B->getVA(); break; case ELF64BEKind: if (SymbolBody *B = Symtab::X->find(S)) return B->getVA(); break; default: llvm_unreachable("unsupported target"); } error("symbol not found: " + S); return 0; } static uint64_t getSectionSize(StringRef Name) { switch (Config->EKind) { case ELF32LEKind: return Script::X->getOutputSectionSize(Name); case ELF32BEKind: return Script::X->getOutputSectionSize(Name); case ELF64LEKind: return Script::X->getOutputSectionSize(Name); case ELF64BEKind: return Script::X->getOutputSectionSize(Name); default: llvm_unreachable("unsupported target"); } } static uint64_t getSectionAddress(StringRef Name) { switch (Config->EKind) { case ELF32LEKind: return Script::X->getOutputSectionAddress(Name); case ELF32BEKind: return Script::X->getOutputSectionAddress(Name); case ELF64LEKind: return Script::X->getOutputSectionAddress(Name); case ELF64BEKind: return Script::X->getOutputSectionAddress(Name); default: llvm_unreachable("unsupported target"); } } static uint64_t getHeaderSize() { switch (Config->EKind) { case ELF32LEKind: return Script::X->getHeaderSize(); case ELF32BEKind: return Script::X->getHeaderSize(); case ELF64LEKind: return Script::X->getHeaderSize(); case ELF64BEKind: return Script::X->getHeaderSize(); default: llvm_unreachable("unsupported target"); } } SymbolAssignment *ScriptParser::readAssignment(StringRef Name) { StringRef Op = next(); assert(Op == "=" || Op == "+="); Expr E = readExpr(); if (Op == "+=") E = [=](uint64_t Dot) { return getSymbolValue(Name, Dot) + E(Dot); }; return new SymbolAssignment(Name, E); } // This is an operator-precedence parser to parse a linker // script expression. Expr ScriptParser::readExpr() { return readExpr1(readPrimary(), 0); } static Expr combine(StringRef Op, Expr L, Expr R) { if (Op == "*") return [=](uint64_t Dot) { return L(Dot) * R(Dot); }; if (Op == "/") { return [=](uint64_t Dot) -> uint64_t { uint64_t RHS = R(Dot); if (RHS == 0) { error("division by zero"); return 0; } return L(Dot) / RHS; }; } if (Op == "+") return [=](uint64_t Dot) { return L(Dot) + R(Dot); }; if (Op == "-") return [=](uint64_t Dot) { return L(Dot) - R(Dot); }; if (Op == "<") return [=](uint64_t Dot) { return L(Dot) < R(Dot); }; if (Op == ">") return [=](uint64_t Dot) { return L(Dot) > R(Dot); }; if (Op == ">=") return [=](uint64_t Dot) { return L(Dot) >= R(Dot); }; if (Op == "<=") return [=](uint64_t Dot) { return L(Dot) <= R(Dot); }; if (Op == "==") return [=](uint64_t Dot) { return L(Dot) == R(Dot); }; if (Op == "!=") return [=](uint64_t Dot) { return L(Dot) != R(Dot); }; if (Op == "&") return [=](uint64_t Dot) { return L(Dot) & R(Dot); }; if (Op == "|") return [=](uint64_t Dot) { return L(Dot) | R(Dot); }; llvm_unreachable("invalid operator"); } // This is a part of the operator-precedence parser. This function // assumes that the remaining token stream starts with an operator. Expr ScriptParser::readExpr1(Expr Lhs, int MinPrec) { while (!atEOF() && !Error) { // Read an operator and an expression. StringRef Op1 = peek(); if (Op1 == "?") return readTernary(Lhs); if (precedence(Op1) < MinPrec) break; next(); Expr Rhs = readPrimary(); // Evaluate the remaining part of the expression first if the // next operator has greater precedence than the previous one. // For example, if we have read "+" and "3", and if the next // operator is "*", then we'll evaluate 3 * ... part first. while (!atEOF()) { StringRef Op2 = peek(); if (precedence(Op2) <= precedence(Op1)) break; Rhs = readExpr1(Rhs, precedence(Op2)); } Lhs = combine(Op1, Lhs, Rhs); } return Lhs; } uint64_t static getConstant(StringRef S) { if (S == "COMMONPAGESIZE") return Target->PageSize; if (S == "MAXPAGESIZE") return Target->MaxPageSize; error("unknown constant: " + S); return 0; } Expr ScriptParser::readPrimary() { if (peek() == "(") return readParenExpr(); StringRef Tok = next(); // Built-in functions are parsed here. // https://sourceware.org/binutils/docs/ld/Builtin-Functions.html. if (Tok == "ADDR") { expect("("); StringRef Name = next(); expect(")"); return [=](uint64_t Dot) { return getSectionAddress(Name); }; } if (Tok == "ASSERT") return readAssert(); if (Tok == "ALIGN") { Expr E = readParenExpr(); return [=](uint64_t Dot) { return alignTo(Dot, E(Dot)); }; } if (Tok == "CONSTANT") { expect("("); StringRef Tok = next(); expect(")"); return [=](uint64_t Dot) { return getConstant(Tok); }; } if (Tok == "SEGMENT_START") { expect("("); next(); expect(","); uint64_t Val; next().getAsInteger(0, Val); expect(")"); return [=](uint64_t Dot) { return Val; }; } if (Tok == "DATA_SEGMENT_ALIGN") { expect("("); Expr E = readExpr(); expect(","); readExpr(); expect(")"); return [=](uint64_t Dot) { return alignTo(Dot, E(Dot)); }; } if (Tok == "DATA_SEGMENT_END") { expect("("); expect("."); expect(")"); return [](uint64_t Dot) { return Dot; }; } // GNU linkers implements more complicated logic to handle // DATA_SEGMENT_RELRO_END. We instead ignore the arguments and just align to // the next page boundary for simplicity. if (Tok == "DATA_SEGMENT_RELRO_END") { expect("("); next(); expect(","); readExpr(); expect(")"); return [](uint64_t Dot) { return alignTo(Dot, Target->PageSize); }; } if (Tok == "SIZEOF") { expect("("); StringRef Name = next(); expect(")"); return [=](uint64_t Dot) { return getSectionSize(Name); }; } if (Tok == "SIZEOF_HEADERS") return [=](uint64_t Dot) { return getHeaderSize(); }; // Parse a symbol name or a number literal. uint64_t V = 0; if (Tok.getAsInteger(0, V)) { if (Tok != "." && !isValidCIdentifier(Tok)) setError("malformed number: " + Tok); return [=](uint64_t Dot) { return getSymbolValue(Tok, Dot); }; } return [=](uint64_t Dot) { return V; }; } Expr ScriptParser::readTernary(Expr Cond) { next(); Expr L = readExpr(); expect(":"); Expr R = readExpr(); return [=](uint64_t Dot) { return Cond(Dot) ? L(Dot) : R(Dot); }; } Expr ScriptParser::readParenExpr() { expect("("); Expr E = readExpr(); expect(")"); return E; } std::vector ScriptParser::readOutputSectionPhdrs() { std::vector Phdrs; while (!Error && peek().startswith(":")) { StringRef Tok = next(); Tok = (Tok.size() == 1) ? next() : Tok.substr(1); if (Tok.empty()) { setError("section header name is empty"); break; } Phdrs.push_back(Tok); } return Phdrs; } unsigned ScriptParser::readPhdrType() { StringRef Tok = next(); unsigned Ret = StringSwitch(Tok) .Case("PT_NULL", PT_NULL) .Case("PT_LOAD", PT_LOAD) .Case("PT_DYNAMIC", PT_DYNAMIC) .Case("PT_INTERP", PT_INTERP) .Case("PT_NOTE", PT_NOTE) .Case("PT_SHLIB", PT_SHLIB) .Case("PT_PHDR", PT_PHDR) .Case("PT_TLS", PT_TLS) .Case("PT_GNU_EH_FRAME", PT_GNU_EH_FRAME) .Case("PT_GNU_STACK", PT_GNU_STACK) .Case("PT_GNU_RELRO", PT_GNU_RELRO) .Default(-1); if (Ret == (unsigned)-1) { setError("invalid program header type: " + Tok); return PT_NULL; } return Ret; } void ScriptParser::readVersionDeclaration(StringRef VerStr) { // Identifiers start at 2 because 0 and 1 are reserved // for VER_NDX_LOCAL and VER_NDX_GLOBAL constants. size_t VersionId = Config->VersionDefinitions.size() + 2; Config->VersionDefinitions.push_back({VerStr, VersionId}); if (skip("global:") || peek() != "local:") readGlobal(VerStr); if (skip("local:")) readLocal(); expect("}"); // Each version may have a parent version. For example, "Ver2" defined as // "Ver2 { global: foo; local: *; } Ver1;" has "Ver1" as a parent. This // version hierarchy is, probably against your instinct, purely for human; the // runtime doesn't care about them at all. In LLD, we simply skip the token. if (!VerStr.empty() && peek() != ";") next(); expect(";"); } void ScriptParser::readLocal() { Config->DefaultSymbolVersion = VER_NDX_LOCAL; expect("*"); expect(";"); } void ScriptParser::readExtern(std::vector *Globals) { expect("C++"); expect("{"); for (;;) { if (peek() == "}" || Error) break; Globals->push_back({next(), true}); expect(";"); } expect("}"); expect(";"); } void ScriptParser::readGlobal(StringRef VerStr) { std::vector *Globals; if (VerStr.empty()) Globals = &Config->VersionScriptGlobals; else Globals = &Config->VersionDefinitions.back().Globals; for (;;) { if (skip("extern")) readExtern(Globals); StringRef Cur = peek(); if (Cur == "}" || Cur == "local:" || Error) return; next(); Globals->push_back({Cur, false}); expect(";"); } } static bool isUnderSysroot(StringRef Path) { if (Config->Sysroot == "") return false; for (; !Path.empty(); Path = sys::path::parent_path(Path)) if (sys::fs::equivalent(Config->Sysroot, Path)) return true; return false; } void elf::readLinkerScript(MemoryBufferRef MB) { StringRef Path = MB.getBufferIdentifier(); ScriptParser(MB.getBuffer(), isUnderSysroot(Path)).readLinkerScript(); } void elf::readVersionScript(MemoryBufferRef MB) { ScriptParser(MB.getBuffer(), false).readVersionScript(); } template class elf::LinkerScript; template class elf::LinkerScript; template class elf::LinkerScript; template class elf::LinkerScript;