Object: Extract a ModuleSymbolTable class from IRObjectFile.

This class represents a symbol table built from in-memory IR. It provides
access to GlobalValues and should only be used if such access is required
(e.g. in the LTO implementation). We will eventually change IRObjectFile
to read from a bitcode symbol table rather than using ModuleSymbolTable,
so it would not be able to expose the module.

Differential Revision: https://reviews.llvm.org/D27073

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288319 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Object/IRObjectFile.h

@@ -15,6 +15,7 @@
 #define LLVM_OBJECT_IROBJECTFILE_H
 
 #include "llvm/ADT/PointerUnion.h"
+#include "llvm/Object/ModuleSymbolTable.h"
 #include "llvm/Object/SymbolicFile.h"
 
 namespace llvm {
@@ -28,15 +29,7 @@ class ObjectFile;
 
 class IRObjectFile : public SymbolicFile {
   std::unique_ptr<Module> M;
-  std::unique_ptr<Mangler> Mang;
-  typedef std::pair<std::string, uint32_t> AsmSymbol;
-  SpecificBumpPtrAllocator<AsmSymbol> AsmSymbols;
-
-  typedef PointerUnion<GlobalValue *, AsmSymbol *> Sym;
-  std::vector<Sym> SymTab;
-  static Sym getSym(DataRefImpl &Symb) {
-    return *reinterpret_cast<Sym *>(Symb.p);
-  }
+  ModuleSymbolTable SymTab;
 
 public:
   IRObjectFile(MemoryBufferRef Object, std::unique_ptr<Module> M);
@@ -70,15 +63,6 @@ class IRObjectFile : public SymbolicFile {
   /// error code if not found.
   static ErrorOr<MemoryBufferRef> findBitcodeInObject(const ObjectFile &Obj);
 
-  /// Parse inline ASM and collect the symbols that are not defined in
-  /// the current module.
-  ///
-  /// For each found symbol, call \p AsmUndefinedRefs with the name of the
-  /// symbol found and the associated flags.
-  static void CollectAsmUndefinedRefs(
-      const Triple &TheTriple, StringRef InlineAsm,
-      function_ref<void(StringRef, BasicSymbolRef::Flags)> AsmUndefinedRefs);
-
   /// \brief Finds and returns bitcode in the given memory buffer (which may
   /// be either a bitcode file or a native object file with embedded bitcode),
   /// or an error code if not found.

include/llvm/Object/ModuleSymbolTable.h

@@ -0,0 +1,61 @@
+//===- ModuleSymbolTable.h - symbol table for in-memory IR ----------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This class represents a symbol table built from in-memory IR. It provides
+// access to GlobalValues and should only be used if such access is required
+// (e.g. in the LTO implementation).
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_OBJECT_MODULESYMBOLTABLE_H
+#define LLVM_OBJECT_MODULESYMBOLTABLE_H
+
+#include "llvm/ADT/PointerUnion.h"
+#include "llvm/ADT/Triple.h"
+#include "llvm/IR/Mangler.h"
+#include "llvm/Object/SymbolicFile.h"
+#include <string>
+#include <utility>
+
+namespace llvm {
+
+class GlobalValue;
+
+class ModuleSymbolTable {
+public:
+  typedef std::pair<std::string, uint32_t> AsmSymbol;
+  typedef PointerUnion<GlobalValue *, AsmSymbol *> Symbol;
+
+private:
+  Module *FirstMod = nullptr;
+
+  SpecificBumpPtrAllocator<AsmSymbol> AsmSymbols;
+  std::vector<Symbol> SymTab;
+  Mangler Mang;
+
+public:
+  ArrayRef<Symbol> symbols() const { return SymTab; }
+  void addModule(Module *M);
+
+  void printSymbolName(raw_ostream &OS, Symbol S) const;
+  uint32_t getSymbolFlags(Symbol S) const;
+
+  /// Parse inline ASM and collect the symbols that are defined or referenced in
+  /// the current module.
+  ///
+  /// For each found symbol, call \p AsmSymbol with the name of the symbol found
+  /// and the associated flags.
+  static void CollectAsmSymbols(
+      const Triple &TheTriple, StringRef InlineAsm,
+      function_ref<void(StringRef, object::BasicSymbolRef::Flags)> AsmSymbol);
+};
+
+}
+
+#endif

lib/Analysis/ModuleSummaryAnalysis.cpp

@@ -269,9 +269,7 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
     // Also, any values used but not defined within module level asm should
     // be listed on the llvm.used or llvm.compiler.used global and marked as
     // referenced from there.
-    // FIXME: Rename CollectAsmUndefinedRefs to something more general, as we
-    // are also using it to find the file-scope locals defined in module asm.
-    object::IRObjectFile::CollectAsmUndefinedRefs(
+    ModuleSymbolTable::CollectAsmSymbols(
         Triple(M.getTargetTriple()), M.getModuleInlineAsm(),
         [&M, &Index](StringRef Name, object::BasicSymbolRef::Flags Flags) {
           // Symbols not marked as Weak or Global are local definitions.

lib/LTO/LTOBackend.cpp

@@ -280,7 +280,7 @@ static void handleAsmUndefinedRefs(Module &Mod, TargetMachine &TM) {
   // Collect the list of undefined symbols used in asm and update
   // llvm.compiler.used to prevent optimization to drop these from the output.
   StringSet<> AsmUndefinedRefs;
-  object::IRObjectFile::CollectAsmUndefinedRefs(
+  ModuleSymbolTable::CollectAsmSymbols(
       Triple(Mod.getTargetTriple()), Mod.getModuleInlineAsm(),
       [&AsmUndefinedRefs](StringRef Name, object::BasicSymbolRef::Flags Flags) {
         if (Flags & object::BasicSymbolRef::SF_Undefined)

lib/Object/CMakeLists.txt

@@ -10,6 +10,7 @@ add_llvm_library(LLVMObject
   MachOObjectFile.cpp
   MachOUniversal.cpp
   ModuleSummaryIndexObjectFile.cpp
+  ModuleSymbolTable.cpp
   Object.cpp
   ObjectFile.cpp
   RecordStreamer.cpp

lib/Object/IRObjectFile.cpp

@@ -37,162 +37,27 @@ using namespace object;
 
 IRObjectFile::IRObjectFile(MemoryBufferRef Object, std::unique_ptr<Module> Mod)
     : SymbolicFile(Binary::ID_IR, Object), M(std::move(Mod)) {
-  Mang.reset(new Mangler());
-
-  for (Function &F : *M)
-    SymTab.push_back(&F);
-  for (GlobalVariable &GV : M->globals())
-    SymTab.push_back(&GV);
-  for (GlobalAlias &GA : M->aliases())
-    SymTab.push_back(&GA);
-
-  CollectAsmUndefinedRefs(Triple(M->getTargetTriple()), M->getModuleInlineAsm(),
-                          [this](StringRef Name, BasicSymbolRef::Flags Flags) {
-                            SymTab.push_back(new (AsmSymbols.Allocate())
-                                                 AsmSymbol(Name, Flags));
-                          });
+  SymTab.addModule(M.get());
 }
 
-// Parse inline ASM and collect the list of symbols that are not defined in
-// the current module. This is inspired from IRObjectFile.
-void IRObjectFile::CollectAsmUndefinedRefs(
-    const Triple &TT, StringRef InlineAsm,
-    function_ref<void(StringRef, BasicSymbolRef::Flags)> AsmUndefinedRefs) {
-  if (InlineAsm.empty())
-    return;
-
-  std::string Err;
-  const Target *T = TargetRegistry::lookupTarget(TT.str(), Err);
-  assert(T && T->hasMCAsmParser());
-
-  std::unique_ptr<MCRegisterInfo> MRI(T->createMCRegInfo(TT.str()));
-  if (!MRI)
-    return;
-
-  std::unique_ptr<MCAsmInfo> MAI(T->createMCAsmInfo(*MRI, TT.str()));
-  if (!MAI)
-    return;
-
-  std::unique_ptr<MCSubtargetInfo> STI(
-      T->createMCSubtargetInfo(TT.str(), "", ""));
-  if (!STI)
-    return;
-
-  std::unique_ptr<MCInstrInfo> MCII(T->createMCInstrInfo());
-  if (!MCII)
-    return;
-
-  MCObjectFileInfo MOFI;
-  MCContext MCCtx(MAI.get(), MRI.get(), &MOFI);
-  MOFI.InitMCObjectFileInfo(TT, /*PIC*/ false, CodeModel::Default, MCCtx);
-  RecordStreamer Streamer(MCCtx);
-  T->createNullTargetStreamer(Streamer);
-
-  std::unique_ptr<MemoryBuffer> Buffer(MemoryBuffer::getMemBuffer(InlineAsm));
-  SourceMgr SrcMgr;
-  SrcMgr.AddNewSourceBuffer(std::move(Buffer), SMLoc());
-  std::unique_ptr<MCAsmParser> Parser(
-      createMCAsmParser(SrcMgr, MCCtx, Streamer, *MAI));
-
-  MCTargetOptions MCOptions;
-  std::unique_ptr<MCTargetAsmParser> TAP(
-      T->createMCAsmParser(*STI, *Parser, *MCII, MCOptions));
-  if (!TAP)
-    return;
-
-  Parser->setTargetParser(*TAP);
-  if (Parser->Run(false))
-    return;
+IRObjectFile::~IRObjectFile() {}
 
-  for (auto &KV : Streamer) {
-    StringRef Key = KV.first();
-    RecordStreamer::State Value = KV.second;
-    uint32_t Res = BasicSymbolRef::SF_None;
-    switch (Value) {
-    case RecordStreamer::NeverSeen:
-      llvm_unreachable("NeverSeen should have been replaced earlier");
-    case RecordStreamer::DefinedGlobal:
-      Res |= BasicSymbolRef::SF_Global;
-      break;
-    case RecordStreamer::Defined:
-      break;
-    case RecordStreamer::Global:
-    case RecordStreamer::Used:
-      Res |= BasicSymbolRef::SF_Undefined;
-      Res |= BasicSymbolRef::SF_Global;
-      break;
-    case RecordStreamer::DefinedWeak:
-      Res |= BasicSymbolRef::SF_Weak;
-      Res |= BasicSymbolRef::SF_Global;
-      break;
-    case RecordStreamer::UndefinedWeak:
-      Res |= BasicSymbolRef::SF_Weak;
-      Res |= BasicSymbolRef::SF_Undefined;
-    }
-    AsmUndefinedRefs(Key, BasicSymbolRef::Flags(Res));
-  }
+static ModuleSymbolTable::Symbol getSym(DataRefImpl &Symb) {
+  return *reinterpret_cast<ModuleSymbolTable::Symbol *>(Symb.p);
 }
 
-IRObjectFile::~IRObjectFile() {}
-
 void IRObjectFile::moveSymbolNext(DataRefImpl &Symb) const {
-  Symb.p += sizeof(Sym);
+  Symb.p += sizeof(ModuleSymbolTable::Symbol);
 }
 
 std::error_code IRObjectFile::printSymbolName(raw_ostream &OS,
                                               DataRefImpl Symb) const {
-  Sym S = getSym(Symb);
-  if (S.is<AsmSymbol *>()) {
-    OS << S.get<AsmSymbol *>()->first;
-    return std::error_code();
-  }
-
-  auto *GV = S.get<GlobalValue *>();
-  if (GV->hasDLLImportStorageClass())
-    OS << "__imp_";
-
-  if (Mang)
-    Mang->getNameWithPrefix(OS, GV, false);
-  else
-    OS << GV->getName();
-
+  SymTab.printSymbolName(OS, getSym(Symb));
   return std::error_code();
 }
 
 uint32_t IRObjectFile::getSymbolFlags(DataRefImpl Symb) const {
-  Sym S = getSym(Symb);
-  if (S.is<AsmSymbol *>())
-    return S.get<AsmSymbol *>()->second;
-
-  auto *GV = S.get<GlobalValue *>();
-
-  uint32_t Res = BasicSymbolRef::SF_None;
-  if (GV->isDeclarationForLinker())
-    Res |= BasicSymbolRef::SF_Undefined;
-  else if (GV->hasHiddenVisibility() && !GV->hasLocalLinkage())
-    Res |= BasicSymbolRef::SF_Hidden;
-  if (const GlobalVariable *GVar = dyn_cast<GlobalVariable>(GV)) {
-    if (GVar->isConstant())
-      Res |= BasicSymbolRef::SF_Const;
-  }
-  if (GV->hasPrivateLinkage())
-    Res |= BasicSymbolRef::SF_FormatSpecific;
-  if (!GV->hasLocalLinkage())
-    Res |= BasicSymbolRef::SF_Global;
-  if (GV->hasCommonLinkage())
-    Res |= BasicSymbolRef::SF_Common;
-  if (GV->hasLinkOnceLinkage() || GV->hasWeakLinkage() ||
-      GV->hasExternalWeakLinkage())
-    Res |= BasicSymbolRef::SF_Weak;
-
-  if (GV->getName().startswith("llvm."))
-    Res |= BasicSymbolRef::SF_FormatSpecific;
-  else if (auto *Var = dyn_cast<GlobalVariable>(GV)) {
-    if (Var->getSection() == "llvm.metadata")
-      Res |= BasicSymbolRef::SF_FormatSpecific;
-  }
-
-  return Res;
+  return SymTab.getSymbolFlags(getSym(Symb));
 }
 
 GlobalValue *IRObjectFile::getSymbolGV(DataRefImpl Symb) {
@@ -203,13 +68,14 @@ std::unique_ptr<Module> IRObjectFile::takeModule() { return std::move(M); }
 
 basic_symbol_iterator IRObjectFile::symbol_begin() const {
   DataRefImpl Ret;
-  Ret.p = reinterpret_cast<uintptr_t>(SymTab.data());
+  Ret.p = reinterpret_cast<uintptr_t>(SymTab.symbols().data());
   return basic_symbol_iterator(BasicSymbolRef(Ret, this));
 }
 
 basic_symbol_iterator IRObjectFile::symbol_end() const {
   DataRefImpl Ret;
-  Ret.p = reinterpret_cast<uintptr_t>(SymTab.data() + SymTab.size());
+  Ret.p = reinterpret_cast<uintptr_t>(SymTab.symbols().data() +
+                                      SymTab.symbols().size());
   return basic_symbol_iterator(BasicSymbolRef(Ret, this));
 }