Move SymbolTable::addFile to InputFiles.cpp.

[ruiu]

Summary

The symbol table used to be a container of vectors of input files,
but that's no longer the case because the vectors are moved out of
SymbolTable and are now global variables.

Therefore, addFile doesn't have to belong to any class. This patch
moves the function out of the class.

This patch is a preparation for my RFC [1].

[1] http://lists.llvm.org/pipermail/llvm-dev/2019-April/131902.html

[grimar]

LGTM

lld/ELF/Driver.cpp

template <class ELFT> void LinkerDriver::link(opt::InputArgList &Args) {
 
   // Handle --trace-symbol.
   for (auto *Arg : Args.filtered(OPT_trace_symbol))
     Symtab->trace(Arg->getValue());
 
   // Add all files to the symbol table. This will add almost all
   // symbols that we need to the symbol table.
   for (InputFile *F : Files)
-    Symtab->addFile<ELFT>(F);
+    parseFile<ELFT>(F);
 
   // Now that we have every file, we can decide if we will need a
   // dynamic symbol table.
   // We need one if we were asked to export dynamic symbols or if we are
   // producing a shared library.
   // We also need one if any shared libraries are used and for pie executables
   // (probably because the dynamic linker needs it).
   Config->HasDynSymTab =

lld/ELF/InputFiles.h

 
 // If -reproduce option is given, all input files are written
 // to this tar archive.
 extern std::unique_ptr<llvm::TarWriter> Tar;
 
 // Opens a given file.
 llvm::Optional<MemoryBufferRef> readFile(StringRef Path);
 
+// Add symbols in File to the symbol table.
+template <class ELFT> void parseFile(InputFile *File);
+
 // The root class of input files.
 class InputFile {
 public:
   enum Kind {
     ObjKind,
     SharedKind,
     LazyObjKind,
     ArchiveKind,

lld/ELF/InputFiles.cpp

Optional<MemoryBufferRef> elf::readFile(StringRef Path) {
   MemoryBufferRef MBRef = MB->getMemBufferRef();
   make<std::unique_ptr<MemoryBuffer>>(std::move(MB)); // take MB ownership
 
   if (Tar)
     Tar->append(relativeToRoot(Path), MBRef.getBuffer());
   return MBRef;
 }
 
+// All input object files must be for the same architecture
+// (e.g. it does not make sense to link x86 object files with
+// MIPS object files.) This function checks for that error.
+static bool isCompatible(InputFile *File) {
+  if (!File->isElf() && !isa<BitcodeFile>(File))
+    return true;
+
+  if (File->EKind == Config->EKind && File->EMachine == Config->EMachine) {
+    if (Config->EMachine != EM_MIPS)
+      return true;
+    if (isMipsN32Abi(File) == Config->MipsN32Abi)
+      return true;
+  }
+
+  if (!Config->Emulation.empty()) {
+    error(toString(File) + " is incompatible with " + Config->Emulation);
+  } else {
+    InputFile *Existing;
+    if (!ObjectFiles.empty())
+      Existing = ObjectFiles[0];
+    else if (!SharedFiles.empty())
+      Existing = SharedFiles[0];
+    else
+      Existing = BitcodeFiles[0];
+
+    error(toString(File) + " is incompatible with " + toString(Existing));
+  }
+
+  return false;
+}
+
+// Add symbols in File to the symbol table.
+template <class ELFT> void elf::parseFile(InputFile *File) {
+  // Comdat groups define "link once" sections. If two comdat groups have the
+  // same name, only one of them is linked, and the other is ignored. This set
+  // is used to uniquify them.
+  static llvm::DenseSet<llvm::CachedHashStringRef> ComdatGroups;
+
+  if (!isCompatible(File))
+    return;
+
+  // Binary file
+  if (auto *F = dyn_cast<BinaryFile>(File)) {
+    BinaryFiles.push_back(F);
+    F->parse();
+    return;
+  }
+
+  // .a file
+  if (auto *F = dyn_cast<ArchiveFile>(File)) {
+    F->parse<ELFT>();
+    return;
+  }
+
+  // Lazy object file
+  if (auto *F = dyn_cast<LazyObjFile>(File)) {
+    LazyObjFiles.push_back(F);
+    F->parse<ELFT>();
+    return;
+  }
+
+  if (Config->Trace)
+    message(toString(File));
+
+  // .so file
+  if (auto *F = dyn_cast<SharedFile>(File)) {
+    F->parse<ELFT>();
+    return;
+  }
+
+  // LLVM bitcode file
+  if (auto *F = dyn_cast<BitcodeFile>(File)) {
+    BitcodeFiles.push_back(F);
+    F->parse<ELFT>(ComdatGroups);
+    return;
+  }
+
+  // Regular object file
+  ObjectFiles.push_back(File);
+  cast<ObjFile<ELFT>>(File)->parse(ComdatGroups);
+}
+
 // Concatenates arguments to construct a string representing an error location.
 static std::string createFileLineMsg(StringRef Path, unsigned Line) {
   std::string Filename = path::filename(Path);
   std::string Lineno = ":" + std::to_string(Line);
   if (Filename == Path)
     return Filename + Lineno;
   return Filename + Lineno + " (" + Path.str() + Lineno + ")";
 }
std::string elf::replaceThinLTOSuffix(StringRef Path) {
   StringRef Suffix = Config->ThinLTOObjectSuffixReplace.first;
   StringRef Repl = Config->ThinLTOObjectSuffixReplace.second;
 
   if (Path.consume_back(Suffix))
     return (Path + Repl).str();
   return Path;
 }
 
+template void elf::parseFile<ELF32LE>(InputFile *);
+template void elf::parseFile<ELF32BE>(InputFile *);
+template void elf::parseFile<ELF64LE>(InputFile *);
+template void elf::parseFile<ELF64BE>(InputFile *);
+
 template void ArchiveFile::parse<ELF32LE>();
 template void ArchiveFile::parse<ELF32BE>();
 template void ArchiveFile::parse<ELF64LE>();
 template void ArchiveFile::parse<ELF64BE>();
 
 template void BitcodeFile::parse<ELF32LE>(DenseSet<CachedHashStringRef> &);
 template void BitcodeFile::parse<ELF32BE>(DenseSet<CachedHashStringRef> &);
 template void BitcodeFile::parse<ELF64LE>(DenseSet<CachedHashStringRef> &);

lld/ELF/SymbolTable.h

 // conflicts. For example, obviously, a defined symbol is better than
 // an undefined symbol. Or, if there's a conflict between a lazy and a
 // undefined, it'll read an archive member to read a real definition
 // to replace the lazy symbol. The logic is implemented in the
 // add*() functions, which are called by input files as they are parsed. There
 // is one add* function per symbol type.
 class SymbolTable {
 public:
-  template <class ELFT> void addFile(InputFile *File);
   template <class ELFT> void addCombinedLTOObject();
   void wrap(Symbol *Sym, Symbol *Real, Symbol *Wrap);
 
   ArrayRef<Symbol *> getSymbols() const { return SymVector; }
 
   template <class ELFT>
   Symbol *addUndefined(StringRef Name, uint8_t Binding, uint8_t StOther,
                        uint8_t Type, bool CanOmitFromDynSym, InputFile *File);

lld/ELF/SymbolTable.cpp

 using namespace llvm::object;
 using namespace llvm::ELF;
 
 using namespace lld;
 using namespace lld::elf;
 
 SymbolTable *elf::Symtab;
 
-static InputFile *getFirstElf() {
-  if (!ObjectFiles.empty())
-    return ObjectFiles[0];
-  if (!SharedFiles.empty())
-    return SharedFiles[0];
-  return BitcodeFiles[0];
-}
-
-// All input object files must be for the same architecture
-// (e.g. it does not make sense to link x86 object files with
-// MIPS object files.) This function checks for that error.
-static bool isCompatible(InputFile *F) {
-  if (!F->isElf() && !isa<BitcodeFile>(F))
-    return true;
-
-  if (F->EKind == Config->EKind && F->EMachine == Config->EMachine) {
-    if (Config->EMachine != EM_MIPS)
-      return true;
-    if (isMipsN32Abi(F) == Config->MipsN32Abi)
-      return true;
-  }
-
-  if (!Config->Emulation.empty())
-    error(toString(F) + " is incompatible with " + Config->Emulation);
-  else
-    error(toString(F) + " is incompatible with " + toString(getFirstElf()));
-  return false;
-}
-
-// Add symbols in File to the symbol table.
-template <class ELFT> void SymbolTable::addFile(InputFile *File) {
-  if (!isCompatible(File))
-    return;
-
-  // Binary file
-  if (auto *F = dyn_cast<BinaryFile>(File)) {
-    BinaryFiles.push_back(F);
-    F->parse();
-    return;
-  }
-
-  // .a file
-  if (auto *F = dyn_cast<ArchiveFile>(File)) {
-    F->parse<ELFT>();
-    return;
-  }
-
-  // Lazy object file
-  if (auto *F = dyn_cast<LazyObjFile>(File)) {
-    LazyObjFiles.push_back(F);
-    F->parse<ELFT>();
-    return;
-  }
-
-  if (Config->Trace)
-    message(toString(File));
-
-  // .so file
-  if (auto *F = dyn_cast<SharedFile>(File)) {
-    F->parse<ELFT>();
-    return;
-  }
-
-  // LLVM bitcode file
-  if (auto *F = dyn_cast<BitcodeFile>(File)) {
-    BitcodeFiles.push_back(F);
-    F->parse<ELFT>(ComdatGroups);
-    return;
-  }
-
-  // Regular object file
-  ObjectFiles.push_back(File);
-  cast<ObjFile<ELFT>>(File)->parse(ComdatGroups);
-}
-
 // This function is where all the optimizations of link-time
 // optimization happens. When LTO is in use, some input files are
 // not in native object file format but in the LLVM bitcode format.
 // This function compiles bitcode files into a few big native files
 // using LLVM functions and replaces bitcode symbols with the results.
 // Because all bitcode files that the program consists of are passed
 // to the compiler at once, it can do whole-program optimization.
 template <class ELFT> void SymbolTable::addCombinedLTOObject() {
void SymbolTable::addLazyArchive(StringRef Name, ArchiveFile &File,
   // Symbols.h for the details.
   if (S->isWeak()) {
     replaceSymbol<LazyArchive>(S, File, S->Type, Sym);
     S->Binding = STB_WEAK;
     return;
   }
 
   if (InputFile *F = File.fetch(Sym))
-    addFile<ELFT>(F);
+    parseFile<ELFT>(F);
 }
 
 template <class ELFT>
 void SymbolTable::addLazyObject(StringRef Name, LazyObjFile &File) {
   Symbol *S;
   bool WasInserted;
   std::tie(S, WasInserted) = insertName(Name);
   if (WasInserted) {
     replaceSymbol<LazyObject>(S, File, STT_NOTYPE, Name);
     return;
   }
   if (!S->isUndefined())
     return;
 
   // An undefined weak will not fetch archive members. See comment on Lazy in
   // Symbols.h for the details.
   if (S->isWeak()) {
     replaceSymbol<LazyObject>(S, File, S->Type, Name);
     S->Binding = STB_WEAK;
     return;
   }
 
   if (InputFile *F = File.fetch())
-    addFile<ELFT>(F);
+    parseFile<ELFT>(F);
 }
 
 template <class ELFT> void SymbolTable::fetchLazy(Symbol *Sym) {
   if (auto *S = dyn_cast<LazyArchive>(Sym)) {
     if (InputFile *File = S->fetch())
-      addFile<ELFT>(File);
+      parseFile<ELFT>(File);
     return;
   }
 
   auto *S = cast<LazyObject>(Sym);
   if (InputFile *File = cast<LazyObjFile>(S->File)->fetch())
-    addFile<ELFT>(File);
+    parseFile<ELFT>(File);
 }
 
 // Initialize DemangledSyms with a map from demangled symbols to symbol
 // objects. Used to handle "extern C++" directive in version scripts.
 //
 // The map will contain all demangled symbols. That can be very large,
 // and in LLD we generally want to avoid do anything for each symbol.
 // Then, why are we doing this? Here's why.
void SymbolTable::scanVersionScript() {
 
   // Symbol themselves might know their versions because symbols
   // can contain versions in the form of <name>@<version>.
   // Let them parse and update their names to exclude version suffix.
   for (Symbol *Sym : SymVector)
     Sym->parseSymbolVersion();
 }
 
-template void SymbolTable::addFile<ELF32LE>(InputFile *);
-template void SymbolTable::addFile<ELF32BE>(InputFile *);
-template void SymbolTable::addFile<ELF64LE>(InputFile *);
-template void SymbolTable::addFile<ELF64BE>(InputFile *);
-
 template Symbol *SymbolTable::addUndefined<ELF32LE>(StringRef, uint8_t, uint8_t,
                                                     uint8_t, bool, InputFile *);
 template Symbol *SymbolTable::addUndefined<ELF32BE>(StringRef, uint8_t, uint8_t,
                                                     uint8_t, bool, InputFile *);
 template Symbol *SymbolTable::addUndefined<ELF64LE>(StringRef, uint8_t, uint8_t,
                                                     uint8_t, bool, InputFile *);
 template Symbol *SymbolTable::addUndefined<ELF64BE>(StringRef, uint8_t, uint8_t,
                                                     uint8_t, bool, InputFile *);