Object, LTO: Add target triple to irsymtab and LTO API.

[pcc]

Summary

Start using it in LLD to avoid needing to read bitcode again just to get the
target triple, and in llvm-lto2 to avoid printing symbol table information
that is inappropriate for the target.

[pcc]

• Remove an unused field

[ruiu]

LGTM

lld/COFF/InputFiles.cpp

 #include "Error.h"
 #include "Memory.h"
 #include "SymbolTable.h"
 #include "Symbols.h"
 #include "llvm-c/lto.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/ADT/Twine.h"
-#include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/Object/Binary.h"
 #include "llvm/Object/COFF.h"
 #include "llvm/Support/COFF.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/ErrorOr.h"
 #include "llvm/Support/FileSystem.h"
if (ObjSym.isUndefined()) {
       Sym = Symtab->addRegular(this, SymName, IsCOMDAT);
     }
     SymbolBodies.push_back(Sym->body());
   }
   Directives = Obj->getCOFFLinkerOpts();
 }
 
 MachineTypes BitcodeFile::getMachineType() {
-  Expected<std::string> ET = getBitcodeTargetTriple(MB);
-  if (!ET)
-    return IMAGE_FILE_MACHINE_UNKNOWN;
-  switch (Triple(*ET).getArch()) {
+  switch (Triple(Obj->getTargetTriple()).getArch()) {
   case Triple::x86_64:
     return AMD64;
   case Triple::x86:
     return I386;
   case Triple::arm:
     return ARMNT;
   default:
     return IMAGE_FILE_MACHINE_UNKNOWN;

lld/ELF/InputFiles.h

 
 private:
   std::unique_ptr<Archive> File;
   llvm::DenseSet<uint64_t> Seen;
 };
 
 class BitcodeFile : public InputFile {
 public:
-  BitcodeFile(MemoryBufferRef M, uint64_t OffsetInArchive);
+  BitcodeFile(MemoryBufferRef M, StringRef ArchiveName,
+              uint64_t OffsetInArchive);
   static bool classof(const InputFile *F) { return F->kind() == BitcodeKind; }
   template <class ELFT>
   void parse(llvm::DenseSet<llvm::CachedHashStringRef> &ComdatGroups);
   ArrayRef<Symbol *> getSymbols() { return Symbols; }
   std::unique_ptr<llvm::lto::InputFile> Obj;
 
   // If this file is in an archive, the member contains the offset of
   // the file in the archive. Otherwise, it's just zero. We store this

lld/ELF/InputFiles.cpp

 #include "Error.h"
 #include "InputSection.h"
 #include "LinkerScript.h"
 #include "Memory.h"
 #include "SymbolTable.h"
 #include "Symbols.h"
 #include "SyntheticSections.h"
 #include "llvm/ADT/STLExtras.h"
-#include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/CodeGen/Analysis.h"
 #include "llvm/DebugInfo/DWARF/DWARFContext.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/MC/StringTableBuilder.h"
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/Support/Path.h"
for (const Elf_Sym &Sym : Syms) {
     if (V) {
       StringRef VerName = this->StringTable.data() + V->getAux()->vda_name;
       Name = Saver.save(Twine(Name) + "@" + VerName);
       elf::Symtab<ELFT>::X->addShared(this, Name, Sym, V);
     }
   }
 }
 
-static ELFKind getBitcodeELFKind(MemoryBufferRef MB) {
-  Triple T(check(getBitcodeTargetTriple(MB), MB.getBufferIdentifier()));
+static ELFKind getBitcodeELFKind(const Triple &T) {
   if (T.isLittleEndian())
     return T.isArch64Bit() ? ELF64LEKind : ELF32LEKind;
   return T.isArch64Bit() ? ELF64BEKind : ELF32BEKind;
 }
 
-static uint8_t getBitcodeMachineKind(MemoryBufferRef MB) {
-  Triple T(check(getBitcodeTargetTriple(MB), MB.getBufferIdentifier()));
+static uint8_t getBitcodeMachineKind(StringRef Path, const Triple &T) {
   switch (T.getArch()) {
   case Triple::aarch64:
     return EM_AARCH64;
   case Triple::arm:
   case Triple::thumb:
     return EM_ARM;
   case Triple::mips:
   case Triple::mipsel:
   case Triple::mips64:
   case Triple::mips64el:
     return EM_MIPS;
   case Triple::ppc:
     return EM_PPC;
   case Triple::ppc64:
     return EM_PPC64;
   case Triple::x86:
     return T.isOSIAMCU() ? EM_IAMCU : EM_386;
   case Triple::x86_64:
     return EM_X86_64;
   default:
-    fatal(MB.getBufferIdentifier() +
-          ": could not infer e_machine from bitcode target triple " + T.str());
+    fatal(Path + ": could not infer e_machine from bitcode target triple " +
+          T.str());
   }
 }
 
-BitcodeFile::BitcodeFile(MemoryBufferRef MB, uint64_t OffsetInArchive)
+BitcodeFile::BitcodeFile(MemoryBufferRef MB, StringRef ArchiveName,
+                         uint64_t OffsetInArchive)
     : InputFile(BitcodeKind, MB), OffsetInArchive(OffsetInArchive) {
-  EKind = getBitcodeELFKind(MB);
-  EMachine = getBitcodeMachineKind(MB);
+  this->ArchiveName = ArchiveName;
+
+  // Here we pass a new MemoryBufferRef which is identified by ArchiveName
+  // (the fully resolved path of the archive) + member name + offset of the
+  // member in the archive.
+  // ThinLTO uses the MemoryBufferRef identifier to access its internal
+  // data structures and if two archives define two members with the same name,
+  // this causes a collision which result in only one of the objects being
+  // taken into consideration at LTO time (which very likely causes undefined
+  // symbols later in the link stage).
+  MemoryBufferRef MBRef(MB.getBuffer(),
+                        Saver.save(ArchiveName + MB.getBufferIdentifier() +
+                                   utostr(OffsetInArchive)));
+  Obj = check(lto::InputFile::create(MBRef), toString(this));
+
+  Triple T(Obj->getTargetTriple());
+  EKind = getBitcodeELFKind(T);
+  EMachine = getBitcodeMachineKind(MB.getBufferIdentifier(), T);
 }
 
 static uint8_t mapVisibility(GlobalValue::VisibilityTypes GvVisibility) {
   switch (GvVisibility) {
   case GlobalValue::DefaultVisibility:
     return STV_DEFAULT;
   case GlobalValue::HiddenVisibility:
     return STV_HIDDEN;
static Symbol *createBitcodeSymbol(const std::vector<bool> &KeptComdats,
 
   return Symtab<ELFT>::X->addBitcode(NameRef, Binding, Visibility, Type,
                                      CanOmitFromDynSym, F);
 }
 
 template <class ELFT>
 void BitcodeFile::parse(DenseSet<CachedHashStringRef> &ComdatGroups) {
 
-  // Here we pass a new MemoryBufferRef which is identified by ArchiveName
-  // (the fully resolved path of the archive) + member name + offset of the
-  // member in the archive.
-  // ThinLTO uses the MemoryBufferRef identifier to access its internal
-  // data structures and if two archives define two members with the same name,
-  // this causes a collision which result in only one of the objects being
-  // taken into consideration at LTO time (which very likely causes undefined
-  // symbols later in the link stage).
-  MemoryBufferRef MBRef(MB.getBuffer(),
-                        Saver.save(ArchiveName + MB.getBufferIdentifier() +
-                                   utostr(OffsetInArchive)));
-  Obj = check(lto::InputFile::create(MBRef), toString(this));
-
   std::vector<bool> KeptComdats;
   for (StringRef S : Obj->getComdatTable())
     KeptComdats.push_back(ComdatGroups.insert(CachedHashStringRef(S)).second);
 
   for (const lto::InputFile::Symbol &ObjSym : Obj->symbols())
     Symbols.push_back(createBitcodeSymbol<ELFT>(KeptComdats, ObjSym, this));
 }
 

 
 static bool isBitcode(MemoryBufferRef MB) {
   using namespace sys::fs;
   return identify_magic(MB.getBuffer()) == file_magic::bitcode;
 }
 
 InputFile *elf::createObjectFile(MemoryBufferRef MB, StringRef ArchiveName,
                                  uint64_t OffsetInArchive) {
-  InputFile *F = isBitcode(MB) ? make<BitcodeFile>(MB, OffsetInArchive)
-                               : createELFFile<ObjectFile>(MB);
+  InputFile *F = isBitcode(MB)
+                     ? make<BitcodeFile>(MB, ArchiveName, OffsetInArchive)
   F->ArchiveName = ArchiveName;
   return F;
 }
 
 InputFile *elf::createSharedFile(MemoryBufferRef MB) {
   return createELFFile<SharedFile>(MB);
 }
 

llvm/include/llvm/LTO/LTO.h

private:
 
   std::vector<BitcodeModule> Mods;
   SmallVector<char, 0> Strtab;
   std::vector<Symbol> Symbols;
 
   // [begin, end) for each module
   std::vector<std::pair<size_t, size_t>> ModuleSymIndices;
 
-  StringRef SourceFileName, COFFLinkerOpts;
+  StringRef TargetTriple, SourceFileName, COFFLinkerOpts;
   std::vector<StringRef> ComdatTable;
 
 public:
   ~InputFile();
 
   /// Create an InputFile.
   static Expected<std::unique_ptr<InputFile>> create(MemoryBufferRef Object);
 
public:
   ArrayRef<Symbol> symbols() const { return Symbols; }
 
   /// Returns linker options specified in the input file.
   StringRef getCOFFLinkerOpts() const { return COFFLinkerOpts; }
 
   /// Returns the path to the InputFile.
   StringRef getName() const;
 
+  /// Returns the input file's target triple.
+  StringRef getTargetTriple() const { return TargetTriple; }
+
   /// Returns the source file path specified at compile time.
   StringRef getSourceFileName() const { return SourceFileName; }
 
   // Returns a table with all the comdats used by this file.
   ArrayRef<StringRef> getComdatTable() const { return ComdatTable; }
 
 private:
   ArrayRef<Symbol> module_symbols(unsigned I) const {

llvm/include/llvm/Object/IRSymtab.h

 };
 
 struct Header {
   Range<Module> Modules;
   Range<Comdat> Comdats;
   Range<Symbol> Symbols;
   Range<Uncommon> Uncommons;
 
-  Str SourceFileName;
+  Str TargetTriple, SourceFileName;
 
   /// COFF-specific: linker directives.
   Str COFFLinkerOpts;
 };
 
 }
 
 /// Fills in Symtab and Strtab with a valid symbol and string table for Mods.
public:
   /// copied into an irsymtab::Symbol object.
   symbol_range symbols() const;
 
   /// Returns a slice of the symbol table for the I'th module in the file.
   /// The symbols enumerated by this method are ephemeral, but they can be
   /// copied into an irsymtab::Symbol object.
   symbol_range module_symbols(unsigned I) const;
 
+  StringRef getTargetTriple() const { return str(header().TargetTriple); }
+
   /// Returns the source file path specified at compile time.
   StringRef getSourceFileName() const { return str(header().SourceFileName); }
 
   /// Returns a table with all the comdats used by this file.
   std::vector<StringRef> getComdatTable() const {
     std::vector<StringRef> ComdatTable;
     ComdatTable.reserve(Comdats.size());
     for (auto C : Comdats)

llvm/lib/LTO/LTO.cpp

Expected<std::unique_ptr<InputFile>> InputFile::create(MemoryBufferRef Object) {
   }
 
   SmallVector<char, 0> Symtab;
   if (Error E = irsymtab::build(Mods, Symtab, File->Strtab))
     return std::move(E);
 
   irsymtab::Reader R({Symtab.data(), Symtab.size()},
                      {File->Strtab.data(), File->Strtab.size()});
+  File->TargetTriple = R.getTargetTriple();
   File->SourceFileName = R.getSourceFileName();
   File->COFFLinkerOpts = R.getCOFFLinkerOpts();
   File->ComdatTable = R.getComdatTable();
 
   for (unsigned I = 0; I != Mods.size(); ++I) {
     size_t Begin = File->Symbols.size();
     for (const irsymtab::Reader::SymbolRef &Sym : R.module_symbols(I))
       // Skip symbols that are irrelevant to LTO. Note that this condition needs

llvm/lib/Object/IRSymtab.cpp

Error Builder::addSymbol(ModuleSymbolTable::Symbol Msym) {
 
   return Error::success();
 }
 
 Error Builder::build(ArrayRef<Module *> IRMods) {
   storage::Header Hdr;
 
   assert(!IRMods.empty());
+  setStr(Hdr.TargetTriple, IRMods[0]->getTargetTriple());
   setStr(Hdr.SourceFileName, IRMods[0]->getSourceFileName());
   TT = Triple(IRMods[0]->getTargetTriple());
 
   // This adds the symbols for each module to Msymtab.
   for (auto *M : IRMods)
     if (Error Err = addModule(M))
       return Err;
 

llvm/test/LTO/Resolution/X86/symtab-elf.ll

+; RUN: llvm-as -o %t %s
+; RUN: llvm-lto2 dump-symtab %t | FileCheck %s
+
+; CHECK: target triple: x86_64-unknown-linux-gnu
+target triple = "x86_64-unknown-linux-gnu"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+; CHECK-NOT: linker opts:
+!0 = !{i32 6, !"Linker Options", !{!{!"/include:foo"}}}
+!llvm.module.flags = !{ !0 }
+
+@g1 = global i32 0
+
+; CHECK-NOT: fallback g1
+@g2 = weak alias i32, i32* @g1

llvm/test/LTO/Resolution/X86/symtab.ll

 ; RUN: llvm-as -o %t %s
 ; RUN: llvm-lto2 dump-symtab %t | FileCheck %s
 
+; CHECK: target triple: i686-pc-windows-msvc18.0.0
 target triple = "i686-pc-windows-msvc18.0.0"
 target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
 
 ; CHECK: source filename: src.c
 source_filename = "src.c"
 
-; CHECK: linker opts (COFF only): /include:foo
+; CHECK: linker opts: /include:foo
 !0 = !{i32 6, !"Linker Options", !{!{!"/include:foo"}}}
 !llvm.module.flags = !{ !0 }
 
 ; CHECK: H------ _g1
 @g1 = hidden global i32 0
 
 ; CHECK: P------ _g2
 @g2 = protected global i32 0

llvm/tools/llvm-lto2/llvm-lto2.cpp

 }
 
 static int dumpSymtab(int argc, char **argv) {
   for (StringRef F : make_range(argv + 1, argv + argc)) {
     std::unique_ptr<MemoryBuffer> MB = check(MemoryBuffer::getFile(F), F);
     std::unique_ptr<InputFile> Input =
         check(InputFile::create(MB->getMemBufferRef()), F);
 
+    outs() << "target triple: " << Input->getTargetTriple() << '\n';
+    Triple TT(Input->getTargetTriple());
+
     outs() << "source filename: " << Input->getSourceFileName() << '\n';
-    outs() << "linker opts (COFF only): " << Input->getCOFFLinkerOpts() << '\n';
+
+    if (TT.isOSBinFormatCOFF())
+      outs() << "linker opts: " << Input->getCOFFLinkerOpts() << '\n';
 
     std::vector<StringRef> ComdatTable = Input->getComdatTable();
     for (const InputFile::Symbol &Sym : Input->symbols()) {
       switch (Sym.getVisibility()) {
       case GlobalValue::HiddenVisibility:
         outs() << 'H';
         break;
       case GlobalValue::ProtectedVisibility:
for (const InputFile::Symbol &Sym : Input->symbols()) {
       if (Sym.isCommon())
         outs() << "        size " << Sym.getCommonSize() << " align "
                << Sym.getCommonAlignment() << '\n';
 
       int Comdat = Sym.getComdatIndex();
       if (Comdat != -1)
         outs() << "        comdat " << ComdatTable[Comdat] << '\n';
 
-      if (Sym.isWeak() && Sym.isIndirect())
+      if (TT.isOSBinFormatCOFF() && Sym.isWeak() && Sym.isIndirect())
         outs() << "        fallback " << Sym.getCOFFWeakExternalFallback() << '\n';
     }
 
     outs() << '\n';
   }
 
   return 0;
 }