C++ SymbolBody类代码示例

// Versions are usually assigned to symbols using version scripts,
// but there's another way to assign versions to symbols.
// If a symbol name contains '@', the string after it is not
// actually a part of the symbol name but specifies a version.
// This function takes care of it.
template <class ELFT> void SymbolTable<ELFT>::scanSymbolVersions() {
  if (Config->VersionDefinitions.empty())
    return;

  int MaxVersionLen = getMaxVersionLen();

  // Unfortunately there's no way other than iterating over all
  // symbols to look for '@' characters in symbol names.
  // So this is inherently slow. A good news is that we do this
  // only when versions have been defined.
  for (Symbol *Sym : SymVector) {
    // Symbol versions for exported symbols are by nature
    // only for defined global symbols.
    SymbolBody *B = Sym->body();
    if (!B->isDefined())
      continue;
    uint8_t Visibility = B->getVisibility();
    if (Visibility != STV_DEFAULT && Visibility != STV_PROTECTED)
      continue;

    // Look for '@' in the symbol name.
    StringRef Name;
    uint16_t Version;
    std::tie(Name, Version) = getSymbolVersion(B, MaxVersionLen);
    if (Name.empty())
      continue;

    B->setName(Name);
    Sym->VersionId = Version;
  }
}

Defined *Undefined::getWeakAlias() {
  // A weak alias may be a weak alias to another symbol, so check recursively.
  for (SymbolBody *A = WeakAlias; A; A = cast<Undefined>(A)->WeakAlias)
    if (auto *D = dyn_cast<Defined>(A->repl()))
      return D;
  return nullptr;
}

static typename ELFT::uint getSymVA(const SymbolBody &Body,
                                    typename ELFT::uint &Addend) {
  typedef typename ELFT::uint uintX_t;

  switch (Body.kind()) {
  case SymbolBody::DefinedSyntheticKind: {
    auto &D = cast<DefinedSynthetic<ELFT>>(Body);
    const OutputSectionBase<ELFT> *Sec = D.Section;
    if (!Sec)
      return D.Value;
    if (D.Value == DefinedSynthetic<ELFT>::SectionEnd)
      return Sec->getVA() + Sec->getSize();
    return Sec->getVA() + D.Value;
  }
  case SymbolBody::DefinedRegularKind: {
    auto &D = cast<DefinedRegular<ELFT>>(Body);
    InputSectionBase<ELFT> *SC = D.Section;

    // According to the ELF spec reference to a local symbol from outside
    // the group are not allowed. Unfortunately .eh_frame breaks that rule
    // and must be treated specially. For now we just replace the symbol with
    // 0.
    if (SC == &InputSection<ELFT>::Discarded)
      return 0;

    // This is an absolute symbol.
    if (!SC)
      return D.Value;

    uintX_t Offset = D.Value;
    if (D.isSection()) {
      Offset += Addend;
      Addend = 0;
    }
    uintX_t VA = SC->OutSec->getVA() + SC->getOffset(Offset);
    if (D.isTls())
      return VA - Out<ELFT>::TlsPhdr->p_vaddr;
    return VA;
  }
  case SymbolBody::DefinedCommonKind:
    return Out<ELFT>::Bss->getVA() + cast<DefinedCommon>(Body).OffsetInBss;
  case SymbolBody::SharedKind: {
    auto &SS = cast<SharedSymbol<ELFT>>(Body);
    if (!SS.NeedsCopyOrPltAddr)
      return 0;
    if (SS.isFunc())
      return Body.getPltVA<ELFT>();
    return Out<ELFT>::Bss->getVA() + SS.OffsetInBss;
  }
  case SymbolBody::UndefinedKind:
    return 0;
  case SymbolBody::LazyArchiveKind:
  case SymbolBody::LazyObjectKind:
    assert(Body.symbol()->IsUsedInRegularObj && "lazy symbol reached writer");
    return 0;
  case SymbolBody::DefinedBitcodeKind:
    llvm_unreachable("should have been replaced");
  }
  llvm_unreachable("invalid symbol kind");
}

std::map<std::string, SymbolBody *> SymbolTable<ELFT>::getDemangledSyms() {
  std::map<std::string, SymbolBody *> Result;
  for (Symbol *Sym : SymVector) {
    SymbolBody *B = Sym->body();
    Result[demangle(B->getName())] = B;
  }
  return Result;
}

// We have a new defined symbol with the specified binding. Return 1 if the new
// symbol should win, -1 if the new symbol should lose, or 0 if both symbols are
// strong defined symbols.
static int compareDefined(Symbol *S, bool WasInserted, uint8_t Binding) {
  if (WasInserted)
    return 1;
  SymbolBody *Body = S->body();
  if (Body->isLazy() || Body->isUndefined() || Body->isShared())
    return 1;
  if (Binding == STB_WEAK)
    return -1;
  if (S->isWeak())
    return 1;
  return 0;
}

// Print out a log message for --trace-symbol.
void elf::printTraceSymbol(Symbol *Sym) {
  SymbolBody *B = Sym->body();
  outs() << getFilename(B->File);

  if (B->isUndefined())
    outs() << ": reference to ";
  else if (B->isCommon())
    outs() << ": common definition of ";
  else
    outs() << ": definition of ";
  outs() << B->getName() << "\n";
}

// Rename SYM as __wrap_SYM. The original symbol is preserved as __real_SYM.
// Used to implement --wrap.
template <class ELFT> void SymbolTable<ELFT>::wrap(StringRef Name) {
  SymbolBody *B = find(Name);
  if (!B)
    return;
  StringSaver Saver(Alloc);
  Symbol *Sym = B->symbol();
  Symbol *Real = addUndefined(Saver.save("__real_" + Name));
  Symbol *Wrap = addUndefined(Saver.save("__wrap_" + Name));
  // We rename symbols by replacing the old symbol's SymbolBody with the new
  // symbol's SymbolBody. This causes all SymbolBody pointers referring to the
  // old symbol to instead refer to the new symbol.
  memcpy(Real->Body.buffer, Sym->Body.buffer, sizeof(Sym->Body));
  memcpy(Sym->Body.buffer, Wrap->Body.buffer, sizeof(Wrap->Body));
}

// This is the main function of the garbage collector.
// Starting from GC-root sections, this function visits all reachable
// sections to set their "Live" bits.
template <class ELFT> void elf::markLive(SymbolTable<ELFT> *Symtab) {
  SmallVector<InputSection<ELFT> *, 256> Q;

  auto Enqueue = [&](InputSectionBase<ELFT> *Sec) {
    if (!Sec || Sec->Live)
      return;
    Sec->Live = true;
    if (InputSection<ELFT> *S = dyn_cast<InputSection<ELFT>>(Sec))
      Q.push_back(S);
  };

  auto MarkSymbol = [&](SymbolBody *Sym) {
    if (Sym)
      if (auto *D = dyn_cast<DefinedRegular<ELFT>>(&Sym->repl()))
        Enqueue(D->Section);
  };

  // Add GC root symbols.
  MarkSymbol(Config->EntrySym);
  MarkSymbol(Symtab->find(Config->Init));
  MarkSymbol(Symtab->find(Config->Fini));
  for (StringRef S : Config->Undefined)
    MarkSymbol(Symtab->find(S));

  // Preserve externally-visible symbols if the symbols defined by this
  // file can interrupt other ELF file's symbols at runtime.
  if (Config->Shared || Config->ExportDynamic) {
    for (const std::pair<StringRef, Symbol *> &P : Symtab->getSymbols()) {
      SymbolBody *B = P.second->Body;
      if (B->getVisibility() == STV_DEFAULT)
        MarkSymbol(B);
    }
  }

  // Preserve special sections and those which are specified in linker
  // script KEEP command.
  for (const std::unique_ptr<ObjectFile<ELFT>> &F : Symtab->getObjectFiles())
    for (InputSectionBase<ELFT> *Sec : F->getSections())
      if (Sec && Sec != &InputSection<ELFT>::Discarded)
        if (isReserved(Sec) || Script->shouldKeep<ELFT>(Sec))
          Enqueue(Sec);

  // Mark all reachable sections.
  while (!Q.empty())
    forEachSuccessor<ELFT>(Q.pop_back_val(), Enqueue);
}

RelExpr MIPS<ELFT>::getRelExpr(uint32_t Type, const SymbolBody &S,
                               const uint8_t *Loc) const {
  // See comment in the calculateMipsRelChain.
  if (ELFT::Is64Bits || Config->MipsN32Abi)
    Type &= 0xff;
  switch (Type) {
  default:
    return R_ABS;
  case R_MIPS_JALR:
    return R_HINT;
  case R_MIPS_GPREL16:
  case R_MIPS_GPREL32:
    return R_MIPS_GOTREL;
  case R_MIPS_26:
    return R_PLT;
  case R_MIPS_HI16:
  case R_MIPS_LO16:
    // R_MIPS_HI16/R_MIPS_LO16 relocations against _gp_disp calculate
    // offset between start of function and 'gp' value which by default
    // equal to the start of .got section. In that case we consider these
    // relocations as relative.
    if (&S == ElfSym::MipsGpDisp)
      return R_MIPS_GOT_GP_PC;
    if (&S == ElfSym::MipsLocalGp)
      return R_MIPS_GOT_GP;
    LLVM_FALLTHROUGH;
  case R_MIPS_GOT_OFST:
    return R_ABS;
  case R_MIPS_PC32:
  case R_MIPS_PC16:
  case R_MIPS_PC19_S2:
  case R_MIPS_PC21_S2:
  case R_MIPS_PC26_S2:
  case R_MIPS_PCHI16:
  case R_MIPS_PCLO16:
    return R_PC;
  case R_MIPS_GOT16:
    if (S.isLocal())
      return R_MIPS_GOT_LOCAL_PAGE;
    LLVM_FALLTHROUGH;
  case R_MIPS_CALL16:
  case R_MIPS_GOT_DISP:
  case R_MIPS_TLS_GOTTPREL:
    return R_MIPS_GOT_OFF;
  case R_MIPS_CALL_HI16:
  case R_MIPS_CALL_LO16:
  case R_MIPS_GOT_HI16:
  case R_MIPS_GOT_LO16:
    return R_MIPS_GOT_OFF32;
  case R_MIPS_GOT_PAGE:
    return R_MIPS_GOT_LOCAL_PAGE;
  case R_MIPS_TLS_GD:
    return R_MIPS_TLSGD;
  case R_MIPS_TLS_LDM:
    return R_MIPS_TLSLD;
  }
}

template <class ELFT> void LinkerScript<ELFT>::addScriptedSymbols() {
  for (const std::unique_ptr<BaseCommand> &Base : Opt.Commands) {
    auto *Cmd = dyn_cast<SymbolAssignment>(Base.get());
    if (!Cmd || Cmd->Name == ".")
      continue;

    SymbolBody *B = Symtab<ELFT>::X->find(Cmd->Name);
    // The semantic of PROVIDE is that of introducing a symbol only if
    // it's not defined and there's at least a reference to it.
    if ((!B && !Cmd->Provide) || (B && B->isUndefined()))
      Symtab<ELFT>::X->addAbsolute(Cmd->Name,
                                   Cmd->Hidden ? STV_HIDDEN : STV_DEFAULT);
    else
      // Symbol already exists in symbol table. If it is provided
      // then we can't override its value.
      Cmd->Ignore = Cmd->Provide;
  }
}

static void reportUndefined(const SymbolTable<ELFT> &S, const SymbolBody &Sym) {
  typedef typename ELFFile<ELFT>::Elf_Sym Elf_Sym;
  typedef typename ELFFile<ELFT>::Elf_Sym_Range Elf_Sym_Range;

  if (Config->Shared && !Config->NoUndefined)
    return;

  const Elf_Sym &SymE = cast<ELFSymbolBody<ELFT>>(Sym).Sym;
  ELFFileBase<ELFT> *SymFile = nullptr;

  for (const std::unique_ptr<ObjectFile<ELFT>> &File : S.getObjectFiles()) {
    Elf_Sym_Range Syms = File->getObj().symbols(File->getSymbolTable());
    if (&SymE > Syms.begin() && &SymE < Syms.end())
      SymFile = File.get();
  }

  std::string Message = "undefined symbol: " + Sym.getName().str();
  if (SymFile)
    Message += " in " + SymFile->getName().str();
  if (Config->NoInhibitExec)
    warning(Message);
  else
    error(Message);
}

void Writer<ELFT>::scanRelocs(
    InputSectionBase<ELFT> &C,
    iterator_range<const Elf_Rel_Impl<ELFT, isRela> *> Rels) {
  typedef Elf_Rel_Impl<ELFT, isRela> RelType;
  const ObjectFile<ELFT> &File = *C.getFile();
  for (const RelType &RI : Rels) {
    uint32_t SymIndex = RI.getSymbol(Config->Mips64EL);
    SymbolBody *Body = File.getSymbolBody(SymIndex);
    uint32_t Type = RI.getType(Config->Mips64EL);

    if (Target->isTlsLocalDynamicReloc(Type)) {
      if (Target->isTlsOptimized(Type, nullptr))
        continue;
      if (Out<ELFT>::LocalModuleTlsIndexOffset == uint32_t(-1)) {
        Out<ELFT>::LocalModuleTlsIndexOffset =
            Out<ELFT>::Got->addLocalModuleTlsIndex();
        Out<ELFT>::RelaDyn->addReloc({&C, &RI});
      }
      continue;
    }

    // Set "used" bit for --as-needed.
    if (Body && Body->isUndefined() && !Body->isWeak())
      if (auto *S = dyn_cast<SharedSymbol<ELFT>>(Body->repl()))
        S->File->IsUsed = true;

    if (Body)
      Body = Body->repl();

    if (Body && Body->isTLS() && Target->isTlsGlobalDynamicReloc(Type)) {
      if (Target->isTlsOptimized(Type, Body))
        continue;
      if (Body->isInGot())
        continue;
      Out<ELFT>::Got->addDynTlsEntry(Body);
      Out<ELFT>::RelaDyn->addReloc({&C, &RI});
      Out<ELFT>::RelaDyn->addReloc({nullptr, nullptr});
      Body->setUsedInDynamicReloc();
      continue;
    }

    if (Body && Body->isTLS() && !Target->isTlsDynReloc(Type))
      continue;

    bool NeedsGot = false;
    bool NeedsPlt = false;
    if (Body) {
      if (auto *E = dyn_cast<SharedSymbol<ELFT>>(Body)) {
        if (E->needsCopy())
          continue;
        if (Target->relocNeedsCopy(Type, *Body))
          E->OffsetInBSS = 0;
      }
      NeedsPlt = Target->relocNeedsPlt(Type, *Body);
      if (NeedsPlt) {
        if (Body->isInPlt())
          continue;
        Out<ELFT>::Plt->addEntry(Body);
      }
      NeedsGot = Target->relocNeedsGot(Type, *Body);
      if (NeedsGot) {
        if (NeedsPlt && Target->supportsLazyRelocations()) {
          Out<ELFT>::GotPlt->addEntry(Body);
        } else {
          if (Body->isInGot())
            continue;
          Out<ELFT>::Got->addEntry(Body);
        }
      }
    }

    if (Config->EMachine == EM_MIPS && NeedsGot) {
      // MIPS ABI has special rules to process GOT entries
      // and doesn't require relocation entries for them.
      // See "Global Offset Table" in Chapter 5 in the following document
      // for detailed description:
      // ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
      Body->setUsedInDynamicReloc();
      continue;
    }
    bool CBP = canBePreempted(Body, NeedsGot);
    if (!CBP && (!Config->Shared || Target->isRelRelative(Type)))
      continue;
    if (CBP)
      Body->setUsedInDynamicReloc();
    if (NeedsPlt && Target->supportsLazyRelocations())
      Out<ELFT>::RelaPlt->addReloc({&C, &RI});
    else
      Out<ELFT>::RelaDyn->addReloc({&C, &RI});
  }
}

// Returns a symbol for an error message.
std::string lld::toString(const SymbolBody &B) {
  if (Config->Demangle)
    if (Optional<std::string> S = demangle(B.getName()))
      return *S;
  return B.getName();
}

void BitcodeCompiler::add(BitcodeFile &F) {
  std::unique_ptr<IRObjectFile> Obj =
      check(IRObjectFile::create(F.MB, Context));
  std::vector<GlobalValue *> Keep;
  unsigned BodyIndex = 0;
  ArrayRef<SymbolBody *> Bodies = F.getSymbols();

  Module &M = Obj->getModule();
  if (M.getDataLayoutStr().empty())
    fatal("invalid bitcode file: " + F.getName() + " has no datalayout");

  // If a symbol appears in @llvm.used, the linker is required
  // to treat the symbol as there is a reference to the symbol
  // that it cannot see. Therefore, we can't internalize.
  SmallPtrSet<GlobalValue *, 8> Used;
  collectUsedGlobalVariables(M, Used, /* CompilerUsed */ false);

  for (const BasicSymbolRef &Sym : Obj->symbols()) {
    GlobalValue *GV = Obj->getSymbolGV(Sym.getRawDataRefImpl());
    // Ignore module asm symbols.
    if (!GV)
      continue;
    if (GV->hasAppendingLinkage()) {
      Keep.push_back(GV);
      continue;
    }
    if (BitcodeFile::shouldSkip(Sym))
      continue;
    SymbolBody *B = Bodies[BodyIndex++];
    if (!B || &B->repl() != B || !isa<DefinedBitcode>(B))
      continue;
    switch (GV->getLinkage()) {
    default:
      break;
    case llvm::GlobalValue::LinkOnceAnyLinkage:
      GV->setLinkage(GlobalValue::WeakAnyLinkage);
      break;
    case llvm::GlobalValue::LinkOnceODRLinkage:
      GV->setLinkage(GlobalValue::WeakODRLinkage);
      break;
    }

    // We collect the set of symbols we want to internalize here
    // and change the linkage after the IRMover executed, i.e. after
    // we imported the symbols and satisfied undefined references
    // to it. We can't just change linkage here because otherwise
    // the IRMover will just rename the symbol.
    // Shared libraries need to be handled slightly differently.
    // For now, let's be conservative and just never internalize
    // symbols when creating a shared library.
    if (!Config->Shared && !Config->ExportDynamic && !B->isUsedInRegularObj() &&
        !B->MustBeInDynSym)
      if (!Used.count(GV))
        InternalizedSyms.insert(GV->getName());

    Keep.push_back(GV);
  }

  Mover.move(Obj->takeModule(), Keep,
             [](GlobalValue &, IRMover::ValueAdder) {});
}

static typename ELFT::uint getSymVA(const SymbolBody &Body,
                                    typename ELFT::uint &Addend) {
  typedef typename ELFT::uint uintX_t;

  switch (Body.kind()) {
  case SymbolBody::DefinedSyntheticKind: {
    auto &D = cast<DefinedSynthetic>(Body);
    const OutputSectionBase *Sec = D.Section;
    if (!Sec)
      return D.Value;
    if (D.Value == uintX_t(-1))
      return Sec->Addr + Sec->Size;
    return Sec->Addr + D.Value;
  }
  case SymbolBody::DefinedRegularKind: {
    auto &D = cast<DefinedRegular<ELFT>>(Body);
    InputSectionBase<ELFT> *IS = D.Section;

    // According to the ELF spec reference to a local symbol from outside
    // the group are not allowed. Unfortunately .eh_frame breaks that rule
    // and must be treated specially. For now we just replace the symbol with
    // 0.
    if (IS == &InputSection<ELFT>::Discarded)
      return 0;

    // This is an absolute symbol.
    if (!IS)
      return D.Value;

    uintX_t Offset = D.Value;
    if (D.isSection()) {
      Offset += Addend;
      Addend = 0;
    }
    uintX_t VA = (IS->OutSec ? IS->OutSec->Addr : 0) + IS->getOffset(Offset);
    if (D.isTls() && !Config->Relocatable) {
      if (!Out<ELFT>::TlsPhdr)
        fatal(toString(D.File) +
              " has a STT_TLS symbol but doesn't have a PT_TLS section");
      return VA - Out<ELFT>::TlsPhdr->p_vaddr;
    }
    return VA;
  }
  case SymbolBody::DefinedCommonKind:
    if (!Config->DefineCommon)
      return 0;
    return In<ELFT>::Common->OutSec->Addr + In<ELFT>::Common->OutSecOff +
           cast<DefinedCommon>(Body).Offset;
  case SymbolBody::SharedKind: {
    auto &SS = cast<SharedSymbol<ELFT>>(Body);
    if (!SS.NeedsCopyOrPltAddr)
      return 0;
    if (SS.isFunc())
      return Body.getPltVA<ELFT>();
    return SS.getBssSectionForCopy()->Addr + SS.CopyOffset;
  }
  case SymbolBody::UndefinedKind:
    return 0;
  case SymbolBody::LazyArchiveKind:
  case SymbolBody::LazyObjectKind:
    assert(Body.symbol()->IsUsedInRegularObj && "lazy symbol reached writer");
    return 0;
  }
  llvm_unreachable("invalid symbol kind");
}