Pull in r327101 from upstream llvm trunk (by Rafael Espindola):

Don't treat .symver as a regular alias definition.

  This patch starts simplifying the handling of .symver.

  For now it just moves the responsibility for creating an alias down to
  the streamer. With that the asm streamer can pass a .symver unchanged,
  which is nice since gas cannot parse "foo@bar = zed".

  In a followup I hope to move the handling down to the writer so that
  we don't need special hacks for avoiding breaking names with @@@ on
  windows.

Pull in r327160 from upstream llvm trunk (by Rafael Espindola):

  Delay creating an alias for @@@.

  With this we only create an alias for @@@ once we know if it should
  use @ or @@. This avoids last minutes renames and hacks to handle MS
  names.

  This only handles the ELF writer. LTO still has issues with @@@
  aliases.

Pull in r327928 from upstream llvm trunk (by Vitaly Buka):

  Object: Move attribute calculation into RecordStreamer. NFC

  Summary: Preparation for D44274

  Reviewers: pcc, espindola

  Subscribers: hiraditya

  Differential Revision: https://reviews.llvm.org/D44276

Pull in r327930 from upstream llvm trunk (by Vitaly Buka):

  Object: Fix handling of @@@ in .symver directive

  Summary:
  name@@@nodename is going to be replaced with name@@nodename if symbols is
  defined in the assembled file, or name@nodename if undefined.
  https://sourceware.org/binutils/docs/as/Symver.html

  Fixes PR36623

  Reviewers: pcc, espindola

  Subscribers: mehdi_amini, hiraditya

  Differential Revision: https://reviews.llvm.org/D44274

Together, these changes fix handling of @@@ in .symver directives when
doing Link Time Optimization.

Reported by:	Shawn Webb <shawn.webb@hardenedbsd.org>
MFC after:	3 months
X-MFC-With:	r327952

contrib/llvm/include/llvm/MC/MCAssembler.h

@@ -206,6 +206,8 @@ class MCAssembler {
   handleFixup(const MCAsmLayout &Layout, MCFragment &F, const MCFixup &Fixup);
 
 public:
+  std::vector<std::pair<StringRef, const MCSymbol *>> Symvers;
+
   /// Construct a new assembler instance.
   //
   // FIXME: How are we going to parameterize this? Two obvious options are stay

contrib/llvm/include/llvm/MC/MCELFStreamer.h

@@ -51,6 +51,8 @@ class MCELFStreamer : public MCObjectStreamer {
                         unsigned ByteAlignment) override;
 
   void emitELFSize(MCSymbol *Symbol, const MCExpr *Value) override;
+  void emitELFSymverDirective(StringRef AliasName,
+                              const MCSymbol *Aliasee) override;
 
   void EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size,
                              unsigned ByteAlignment) override;

contrib/llvm/include/llvm/MC/MCStreamer.h

@@ -519,9 +519,10 @@ class MCStreamer {
   ///
   /// This corresponds to an assembler statement such as:
   ///  .symver _start, foo@@SOME_VERSION
-  /// \param Alias - The versioned alias (i.e. "foo@@SOME_VERSION")
+  /// \param AliasName - The versioned alias (i.e. "foo@@SOME_VERSION")
   /// \param Aliasee - The aliased symbol (i.e. "_start")
-  virtual void emitELFSymverDirective(MCSymbol *Alias, const MCSymbol *Aliasee);
+  virtual void emitELFSymverDirective(StringRef AliasName,
+                                      const MCSymbol *Aliasee);
 
   /// \brief Emit a Linker Optimization Hint (LOH) directive.
   /// \param Args - Arguments of the LOH.

contrib/llvm/lib/MC/ELFObjectWriter.cpp

@@ -128,8 +128,6 @@ class ELFObjectWriter : public MCObjectWriter {
   /// @name Symbol Table Data
   /// @{
 
-  BumpPtrAllocator Alloc;
-  StringSaver VersionSymSaver{Alloc};
   StringTableBuilder StrTabBuilder{StringTableBuilder::ELF};
 
   /// @}
@@ -391,27 +389,29 @@ void ELFObjectWriter::executePostLayoutBinding(MCAssembler &Asm,
                                                const MCAsmLayout &Layout) {
   // The presence of symbol versions causes undefined symbols and
   // versions declared with @@@ to be renamed.
-  for (const MCSymbol &A : Asm.symbols()) {
-    const auto &Alias = cast<MCSymbolELF>(A);
-    // Not an alias.
-    if (!Alias.isVariable())
-      continue;
-    auto *Ref = dyn_cast<MCSymbolRefExpr>(Alias.getVariableValue());
-    if (!Ref)
-      continue;
-    const auto &Symbol = cast<MCSymbolELF>(Ref->getSymbol());
-
-    StringRef AliasName = Alias.getName();
+  for (const std::pair<StringRef, const MCSymbol *> &P : Asm.Symvers) {
+    StringRef AliasName = P.first;
+    const auto &Symbol = cast<MCSymbolELF>(*P.second);
     size_t Pos = AliasName.find('@');
-    if (Pos == StringRef::npos)
-      continue;
+    assert(Pos != StringRef::npos);
+
+    StringRef Prefix = AliasName.substr(0, Pos);
+    StringRef Rest = AliasName.substr(Pos);
+    StringRef Tail = Rest;
+    if (Rest.startswith("@@@"))
+      Tail = Rest.substr(Symbol.isUndefined() ? 2 : 1);
+
+    auto *Alias =
+        cast<MCSymbolELF>(Asm.getContext().getOrCreateSymbol(Prefix + Tail));
+    Asm.registerSymbol(*Alias);
+    const MCExpr *Value = MCSymbolRefExpr::create(&Symbol, Asm.getContext());
+    Alias->setVariableValue(Value);
 
     // Aliases defined with .symvar copy the binding from the symbol they alias.
     // This is the first place we are able to copy this information.
-    Alias.setExternal(Symbol.isExternal());
-    Alias.setBinding(Symbol.getBinding());
+    Alias->setExternal(Symbol.isExternal());
+    Alias->setBinding(Symbol.getBinding());
 
-    StringRef Rest = AliasName.substr(Pos);
     if (!Symbol.isUndefined() && !Rest.startswith("@@@"))
       continue;
 
@@ -420,7 +420,7 @@ void ELFObjectWriter::executePostLayoutBinding(MCAssembler &Asm,
         !Rest.startswith("@@@"))
       report_fatal_error("A @@ version cannot be undefined");
 
-    Renames.insert(std::make_pair(&Symbol, &Alias));
+    Renames.insert(std::make_pair(&Symbol, Alias));
   }
 }
 
@@ -836,44 +836,7 @@ void ELFObjectWriter::computeSymbolTable(
         HasLargeSectionIndex = true;
     }
 
-    // The @@@ in symbol version is replaced with @ in undefined symbols and @@
-    // in defined ones.
-    //
-    // FIXME: All name handling should be done before we get to the writer,
-    // including dealing with GNU-style version suffixes.  Fixing this isn't
-    // trivial.
-    //
-    // We thus have to be careful to not perform the symbol version replacement
-    // blindly:
-    //
-    // The ELF format is used on Windows by the MCJIT engine.  Thus, on
-    // Windows, the ELFObjectWriter can encounter symbols mangled using the MS
-    // Visual Studio C++ name mangling scheme. Symbols mangled using the MSVC
-    // C++ name mangling can legally have "@@@" as a sub-string. In that case,
-    // the EFLObjectWriter should not interpret the "@@@" sub-string as
-    // specifying GNU-style symbol versioning. The ELFObjectWriter therefore
-    // checks for the MSVC C++ name mangling prefix which is either "?", "@?",
-    // "__imp_?" or "__imp_@?".
-    //
-    // It would have been interesting to perform the MS mangling prefix check
-    // only when the target triple is of the form *-pc-windows-elf. But, it
-    // seems that this information is not easily accessible from the
-    // ELFObjectWriter.
     StringRef Name = Symbol.getName();
-    SmallString<32> Buf;
-    if (!Name.startswith("?") && !Name.startswith("@?") &&
-        !Name.startswith("__imp_?") && !Name.startswith("__imp_@?")) {
-      // This symbol isn't following the MSVC C++ name mangling convention. We
-      // can thus safely interpret the @@@ in symbol names as specifying symbol
-      // versioning.
-      size_t Pos = Name.find("@@@");
-      if (Pos != StringRef::npos) {
-        Buf += Name.substr(0, Pos);
-        unsigned Skip = MSD.SectionIndex == ELF::SHN_UNDEF ? 2 : 1;
-        Buf += Name.substr(Pos + Skip);
-        Name = VersionSymSaver.save(Buf.c_str());
-      }
-    }
 
     // Sections have their own string table
     if (Symbol.getType() != ELF::STT_SECTION) {

contrib/llvm/lib/MC/MCAsmStreamer.cpp

@@ -129,6 +129,9 @@ class MCAsmStreamer final : public MCStreamer {
 
   void ChangeSection(MCSection *Section, const MCExpr *Subsection) override;
 
+  void emitELFSymverDirective(StringRef AliasName,
+                              const MCSymbol *Aliasee) override;
+
   void EmitLOHDirective(MCLOHType Kind, const MCLOHArgs &Args) override;
   void EmitLabel(MCSymbol *Symbol, SMLoc Loc = SMLoc()) override;
 
@@ -411,6 +414,14 @@ void MCAsmStreamer::ChangeSection(MCSection *Section,
   }
 }
 
+void MCAsmStreamer::emitELFSymverDirective(StringRef AliasName,
+                                           const MCSymbol *Aliasee) {
+  OS << ".symver ";
+  Aliasee->print(OS, MAI);
+  OS << ", " << AliasName;
+  EmitEOL();
+}
+
 void MCAsmStreamer::EmitLabel(MCSymbol *Symbol, SMLoc Loc) {
   MCStreamer::EmitLabel(Symbol, Loc);
 

contrib/llvm/lib/MC/MCELFStreamer.cpp

@@ -337,6 +337,11 @@ void MCELFStreamer::emitELFSize(MCSymbol *Symbol, const MCExpr *Value) {
   cast<MCSymbolELF>(Symbol)->setSize(Value);
 }
 
+void MCELFStreamer::emitELFSymverDirective(StringRef AliasName,
+                                           const MCSymbol *Aliasee) {
+  getAssembler().Symvers.push_back({AliasName, Aliasee});
+}
+
 void MCELFStreamer::EmitLocalCommonSymbol(MCSymbol *S, uint64_t Size,
                                           unsigned ByteAlignment) {
   auto *Symbol = cast<MCSymbolELF>(S);

contrib/llvm/lib/MC/MCParser/ELFAsmParser.cpp

@@ -767,12 +767,8 @@ bool ELFAsmParser::ParseDirectiveSymver(StringRef, SMLoc) {
   if (AliasName.find('@') == StringRef::npos)
     return TokError("expected a '@' in the name");
 
-  MCSymbol *Alias = getContext().getOrCreateSymbol(AliasName);
   MCSymbol *Sym = getContext().getOrCreateSymbol(Name);
-  const MCExpr *Value = MCSymbolRefExpr::create(Sym, getContext());
-
-  getStreamer().EmitAssignment(Alias, Value);
-  getStreamer().emitELFSymverDirective(Alias, Sym);
+  getStreamer().emitELFSymverDirective(AliasName, Sym);
   return false;
 }
 

contrib/llvm/lib/MC/MCStreamer.cpp

@@ -925,7 +925,7 @@ void MCStreamer::EmitCOFFSymbolType(int Type) {
   llvm_unreachable("this directive only supported on COFF targets");
 }
 void MCStreamer::emitELFSize(MCSymbol *Symbol, const MCExpr *Value) {}
-void MCStreamer::emitELFSymverDirective(MCSymbol *Alias,
+void MCStreamer::emitELFSymverDirective(StringRef AliasName,
                                         const MCSymbol *Aliasee) {}
 void MCStreamer::EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size,
                                        unsigned ByteAlignment) {}

contrib/llvm/lib/Object/ModuleSymbolTable.cpp

@@ -24,7 +24,6 @@
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/IR/GlobalVariable.h"
-#include "llvm/IR/Mangler.h"
 #include "llvm/IR/Module.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
@@ -69,81 +68,6 @@ void ModuleSymbolTable::addModule(Module *M) {
   });
 }
 
-// Ensure ELF .symver aliases get the same binding as the defined symbol
-// they alias with.
-static void handleSymverAliases(const Module &M, RecordStreamer &Streamer) {
-  if (Streamer.symverAliases().empty())
-    return;
-
-  // The name in the assembler will be mangled, but the name in the IR
-  // might not, so we first compute a mapping from mangled name to GV.
-  Mangler Mang;
-  SmallString<64> MangledName;
-  StringMap<const GlobalValue *> MangledNameMap;
-  auto GetMangledName = [&](const GlobalValue &GV) {
-    if (!GV.hasName())
-      return;
-
-    MangledName.clear();
-    MangledName.reserve(GV.getName().size() + 1);
-    Mang.getNameWithPrefix(MangledName, &GV, /*CannotUsePrivateLabel=*/false);
-    MangledNameMap[MangledName] = &GV;
-  };
-  for (const Function &F : M)
-    GetMangledName(F);
-  for (const GlobalVariable &GV : M.globals())
-    GetMangledName(GV);
-  for (const GlobalAlias &GA : M.aliases())
-    GetMangledName(GA);
-
-  // Walk all the recorded .symver aliases, and set up the binding
-  // for each alias.
-  for (auto &Symver : Streamer.symverAliases()) {
-    const MCSymbol *Aliasee = Symver.first;
-    MCSymbolAttr Attr = MCSA_Invalid;
-
-    // First check if the aliasee binding was recorded in the asm.
-    RecordStreamer::State state = Streamer.getSymbolState(Aliasee);
-    switch (state) {
-    case RecordStreamer::Global:
-    case RecordStreamer::DefinedGlobal:
-      Attr = MCSA_Global;
-      break;
-    case RecordStreamer::UndefinedWeak:
-    case RecordStreamer::DefinedWeak:
-      Attr = MCSA_Weak;
-      break;
-    default:
-      break;
-    }
-
-    // If we don't have a symbol attribute from assembly, then check if
-    // the aliasee was defined in the IR.
-    if (Attr == MCSA_Invalid) {
-      const auto *GV = M.getNamedValue(Aliasee->getName());
-      if (!GV) {
-        auto MI = MangledNameMap.find(Aliasee->getName());
-        if (MI != MangledNameMap.end())
-          GV = MI->second;
-        else
-          continue;
-      }
-      if (GV->hasExternalLinkage())
-        Attr = MCSA_Global;
-      else if (GV->hasLocalLinkage())
-        Attr = MCSA_Local;
-      else if (GV->isWeakForLinker())
-        Attr = MCSA_Weak;
-    }
-    if (Attr == MCSA_Invalid)
-      continue;
-
-    // Set the detected binding on each alias with this aliasee.
-    for (auto &Alias : Symver.second)
-      Streamer.EmitSymbolAttribute(Alias, Attr);
-  }
-}
-
 void ModuleSymbolTable::CollectAsmSymbols(
     const Module &M,
     function_ref<void(StringRef, BasicSymbolRef::Flags)> AsmSymbol) {
@@ -176,7 +100,7 @@ void ModuleSymbolTable::CollectAsmSymbols(
   MCObjectFileInfo MOFI;
   MCContext MCCtx(MAI.get(), MRI.get(), &MOFI);
   MOFI.InitMCObjectFileInfo(TT, /*PIC*/ false, MCCtx);
-  RecordStreamer Streamer(MCCtx);
+  RecordStreamer Streamer(MCCtx, M);
   T->createNullTargetStreamer(Streamer);
 
   std::unique_ptr<MemoryBuffer> Buffer(MemoryBuffer::getMemBuffer(InlineAsm));
@@ -195,7 +119,7 @@ void ModuleSymbolTable::CollectAsmSymbols(
   if (Parser->Run(false))
     return;
 
-  handleSymverAliases(M, Streamer);
+  Streamer.flushSymverDirectives();
 
   for (auto &KV : Streamer) {
     StringRef Key = KV.first();

contrib/llvm/lib/Object/RecordStreamer.cpp

@@ -8,6 +8,9 @@
 //===----------------------------------------------------------------------===//
 
 #include "RecordStreamer.h"
+#include "llvm/IR/Mangler.h"
+#include "llvm/IR/Module.h"
+#include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCSymbol.h"
 
 using namespace llvm;
@@ -70,7 +73,8 @@ void RecordStreamer::markUsed(const MCSymbol &Symbol) {
 
 void RecordStreamer::visitUsedSymbol(const MCSymbol &Sym) { markUsed(Sym); }
 
-RecordStreamer::RecordStreamer(MCContext &Context) : MCStreamer(Context) {}
+RecordStreamer::RecordStreamer(MCContext &Context, const Module &M)
+    : MCStreamer(Context), M(M) {}
 
 RecordStreamer::const_iterator RecordStreamer::begin() {
   return Symbols.begin();
@@ -112,7 +116,109 @@ void RecordStreamer::EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
   markDefined(*Symbol);
 }
 
-void RecordStreamer::emitELFSymverDirective(MCSymbol *Alias,
-                                            const MCSymbol *Aliasee) {
-  SymverAliasMap[Aliasee].push_back(Alias);
+RecordStreamer::State RecordStreamer::getSymbolState(const MCSymbol *Sym) {
+  auto SI = Symbols.find(Sym->getName());
+  if (SI == Symbols.end())
+    return NeverSeen;
+  return SI->second;
+}
+
+void RecordStreamer::emitELFSymverDirective(StringRef AliasName,
+                                            const MCSymbol *Aliasee) {
+  SymverAliasMap[Aliasee].push_back(AliasName);
+}
+
+void RecordStreamer::flushSymverDirectives() {
+  // Mapping from mangled name to GV.
+  StringMap<const GlobalValue *> MangledNameMap;
+  // The name in the assembler will be mangled, but the name in the IR
+  // might not, so we first compute a mapping from mangled name to GV.
+  Mangler Mang;
+  SmallString<64> MangledName;
+  for (const GlobalValue &GV : M.global_values()) {
+    if (!GV.hasName())
+      continue;
+    MangledName.clear();
+    MangledName.reserve(GV.getName().size() + 1);
+    Mang.getNameWithPrefix(MangledName, &GV, /*CannotUsePrivateLabel=*/false);
+    MangledNameMap[MangledName] = &GV;
+  }
+
+  // Walk all the recorded .symver aliases, and set up the binding
+  // for each alias.
+  for (auto &Symver : SymverAliasMap) {
+    const MCSymbol *Aliasee = Symver.first;
+    MCSymbolAttr Attr = MCSA_Invalid;
+    bool IsDefined = false;
+
+    // First check if the aliasee binding was recorded in the asm.
+    RecordStreamer::State state = getSymbolState(Aliasee);
+    switch (state) {
+    case RecordStreamer::Global:
+    case RecordStreamer::DefinedGlobal:
+      Attr = MCSA_Global;
+      break;
+    case RecordStreamer::UndefinedWeak:
+    case RecordStreamer::DefinedWeak:
+      Attr = MCSA_Weak;
+      break;
+    default:
+      break;
+    }
+
+    switch (state) {
+    case RecordStreamer::Defined:
+    case RecordStreamer::DefinedGlobal:
+    case RecordStreamer::DefinedWeak:
+      IsDefined = true;
+      break;
+    case RecordStreamer::NeverSeen:
+    case RecordStreamer::Global:
+    case RecordStreamer::Used:
+    case RecordStreamer::UndefinedWeak:
+      break;
+    }
+
+    if (Attr == MCSA_Invalid || !IsDefined) {
+      const GlobalValue *GV = M.getNamedValue(Aliasee->getName());
+      if (!GV) {
+        auto MI = MangledNameMap.find(Aliasee->getName());
+        if (MI != MangledNameMap.end())
+          GV = MI->second;
+      }
+      if (GV) {
+        // If we don't have a symbol attribute from assembly, then check if
+        // the aliasee was defined in the IR.
+        if (Attr == MCSA_Invalid) {
+          if (GV->hasExternalLinkage())
+            Attr = MCSA_Global;
+          else if (GV->hasLocalLinkage())
+            Attr = MCSA_Local;
+          else if (GV->isWeakForLinker())
+            Attr = MCSA_Weak;
+        }
+        IsDefined = IsDefined || !GV->isDeclarationForLinker();
+      }
+    }
+
+    // Set the detected binding on each alias with this aliasee.
+    for (auto AliasName : Symver.second) {
+      std::pair<StringRef, StringRef> Split = AliasName.split("@@@");
+      SmallString<128> NewName;
+      if (!Split.second.empty() && !Split.second.startswith("@")) {
+        // Special processing for "@@@" according
+        // https://sourceware.org/binutils/docs/as/Symver.html
+        const char *Separator = IsDefined ? "@@" : "@";
+        AliasName =
+            (Split.first + Separator + Split.second).toStringRef(NewName);
+      }
+      MCSymbol *Alias = getContext().getOrCreateSymbol(AliasName);
+      // TODO: Handle "@@@". Depending on SymbolAttribute value it needs to be
+      // converted into @ or @@.
+      const MCExpr *Value = MCSymbolRefExpr::create(Aliasee, getContext());
+      EmitAssignment(Alias, Value);
+      if (Attr != MCSA_Invalid)
+        EmitSymbolAttribute(Alias, Attr);
+    }
+  }
 }

contrib/llvm/lib/Object/RecordStreamer.h

@@ -20,17 +20,24 @@
 
 namespace llvm {
 
+class GlobalValue;
+class Module;
+
 class RecordStreamer : public MCStreamer {
 public:
   enum State { NeverSeen, Global, Defined, DefinedGlobal, DefinedWeak, Used,
                UndefinedWeak};
 
 private:
+  const Module &M;
   StringMap<State> Symbols;
   // Map of aliases created by .symver directives, saved so we can update
   // their symbol binding after parsing complete. This maps from each
   // aliasee to its list of aliases.
-  DenseMap<const MCSymbol *, std::vector<MCSymbol *>> SymverAliasMap;
+  DenseMap<const MCSymbol *, std::vector<StringRef>> SymverAliasMap;
+
+  /// Get the state recorded for the given symbol.
+  State getSymbolState(const MCSymbol *Sym);
 
   void markDefined(const MCSymbol &Symbol);
   void markGlobal(const MCSymbol &Symbol, MCSymbolAttr Attribute);
@@ -38,7 +45,7 @@ class RecordStreamer : public MCStreamer {
   void visitUsedSymbol(const MCSymbol &Sym) override;
 
 public:
-  RecordStreamer(MCContext &Context);
+  RecordStreamer(MCContext &Context, const Module &M);
 
   using const_iterator = StringMap<State>::const_iterator;
 
@@ -54,20 +61,11 @@ class RecordStreamer : public MCStreamer {
   void EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
                         unsigned ByteAlignment) override;
   /// Record .symver aliases for later processing.
-  void emitELFSymverDirective(MCSymbol *Alias,
+  void emitELFSymverDirective(StringRef AliasName,
                               const MCSymbol *Aliasee) override;
-  /// Return the map of .symver aliasee to associated aliases.
-  DenseMap<const MCSymbol *, std::vector<MCSymbol *>> &symverAliases() {
-    return SymverAliasMap;
-  }
-
-  /// Get the state recorded for the given symbol.
-  State getSymbolState(const MCSymbol *Sym) {
-    auto SI = Symbols.find(Sym->getName());
-    if (SI == Symbols.end())
-      return NeverSeen;
-    return SI->second;
-  }
+  // Emit ELF .symver aliases and ensure they have the same binding as the
+  // defined symbol they alias with.
+  void flushSymverDirectives();
 };
 
 } // end namespace llvm