Object: Add SF_Text symbol flag.

[pcc]

Summary

This allows us to remove a few uses of IRObjectFile::getSymbolGV() in
llvm-nm.

While here change host-dependent logic in llvm-nm to target-dependent
logic.

Depends on D27074

[mehdi_amini]

llvm/lib/Object/ModuleSymbolTable.cpp

166

Why the test on the presence of a section? Do we have a test that exercise this?

[pcc]

llvm/lib/Object/ModuleSymbolTable.cpp

166

It's a rough approximation for "is this function in the .text section or not". I don't think there's a test, I'll add one.

[pcc]

• Rename SF_Text -> SF_Executable; remove hasSection check

[mehdi_amini]

LGTM.

llvm/include/llvm/Object/SymbolicFile.h

 
 /// This is a value type class that represents a single symbol in the list of
 /// symbols in the object file.
 class BasicSymbolRef {
   DataRefImpl SymbolPimpl;
   const SymbolicFile *OwningObject;
 
 public:
-  // FIXME: should we add a SF_Text?
   enum Flags : unsigned {
     SF_None = 0,
     SF_Undefined = 1U << 0,      // Symbol is defined in another object file
     SF_Global = 1U << 1,         // Global symbol
     SF_Weak = 1U << 2,           // Weak symbol
     SF_Absolute = 1U << 3,       // Absolute symbol
     SF_Common = 1U << 4,         // Symbol has common linkage
     SF_Indirect = 1U << 5,       // Symbol is an alias to another symbol
     SF_Exported = 1U << 6,       // Symbol is visible to other DSOs
     SF_FormatSpecific = 1U << 7, // Specific to the object file format
                                  // (e.g. section symbols)
     SF_Thumb = 1U << 8,          // Thumb symbol in a 32-bit ARM binary
     SF_Hidden = 1U << 9,         // Symbol has hidden visibility
     SF_Const = 1U << 10,         // Symbol value is constant
+    SF_Text = 1U << 11,          // Symbol points to the text section (IR only)
   };
 
   BasicSymbolRef() : OwningObject(nullptr) { }
   BasicSymbolRef(DataRefImpl SymbolP, const SymbolicFile *Owner);
 
   bool operator==(const BasicSymbolRef &Other) const;
   bool operator<(const BasicSymbolRef &Other) const;
 

llvm/lib/Object/ModuleSymbolTable.cpp

void ModuleSymbolTable::CollectAsmSymbols(
 
   Parser->setTargetParser(*TAP);
   if (Parser->Run(false))
     return;
 
   for (auto &KV : Streamer) {
     StringRef Key = KV.first();
     RecordStreamer::State Value = KV.second;
-    uint32_t Res = BasicSymbolRef::SF_None;
+    // FIXME: For now we just assume that all asm symbols are text.
+    uint32_t Res = BasicSymbolRef::SF_Text;
     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;
uint32_t ModuleSymbolTable::getSymbolFlags(Symbol S) const {
   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 (auto *GO = GV->getBaseObject())
+    if (isa<Function>(GO) && !GO->hasSection())
+      Res |= BasicSymbolRef::SF_Text;
   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())

llvm/tools/llvm-nm/llvm-nm.cpp

if (SymFlags & SymbolRef::SF_Undefined)
       NType |= MachO::N_EXT | MachO::N_UNDF;
     else {
       // Here we have a symbol definition.  So to fake out a section name we
       // use 1, 2 and 3 for section numbers.  See below where they are used to
       // print out fake section names.
       NType |= MachO::N_SECT;
       if (SymFlags & SymbolRef::SF_Const)
         NSect = 3;
-      else {
-        IRObjectFile *IRobj = dyn_cast<IRObjectFile>(&Obj);
-        NSect = (getSymbolNMTypeChar(*IRobj, I->Sym) == 't') ? 1 : 2;
-      }
+      else if (SymFlags & SymbolRef::SF_Text)
+        NSect = 1;
+      else
+        NSect = 2;
     }
     if (SymFlags & SymbolRef::SF_Weak)
       NDesc |= MachO::N_WEAK_DEF;
   } else {
     DataRefImpl SymDRI = I->Sym.getRawDataRefImpl();
     if (MachO->is64Bit()) {
       H_64 = MachO->MachOObjectFile::getHeader64();
       Filetype = H_64.filetype;
if (SegmentName == "__DATA" && SectionName == "__bss")
       return 'b';
     return 's';
   }
   }
 
   return '?';
 }
 
-static char getSymbolNMTypeChar(const GlobalValue &GV) {
+static char getSymbolNMTypeChar(IRObjectFile &Obj, basic_symbol_iterator I) {
+  uint32_t Flags = I->getFlags();
   // FIXME: should we print 'b'? At the IR level we cannot be sure if this
   // will be in bss or not, but we could approximate.
-  return GV.getValueType()->isFunctionTy() ? 't' : 'd';
-}
-
-static char getSymbolNMTypeChar(IRObjectFile &Obj, basic_symbol_iterator I) {
-  const GlobalValue *GV = Obj.getSymbolGV(I->getRawDataRefImpl());
-  return !GV ? 't' : getSymbolNMTypeChar(*GV);
+  if (Flags & SymbolRef::SF_Text)
+    return 't';
+  else if (Triple(Obj.getTargetTriple()).isOSDarwin() &&
+           (Flags & SymbolRef::SF_Const))
+    return 's';
+  else
+    return 'd';
 }
 
 static bool isObject(SymbolicFile &Obj, basic_symbol_iterator I) {
   return !dyn_cast<ELFObjectFileBase>(&Obj)
              ? false
              : elf_symbol_iterator(I)->getELFType() == ELF::STT_OBJECT;
 }
 
 static char getNMTypeChar(SymbolicFile &Obj, basic_symbol_iterator I) {
   uint32_t Symflags = I->getFlags();
   if ((Symflags & object::SymbolRef::SF_Weak) && !isa<MachOObjectFile>(Obj)) {
     char Ret = isObject(Obj, I) ? 'v' : 'w';
     return (!(Symflags & object::SymbolRef::SF_Undefined)) ? toupper(Ret) : Ret;
   }
 
   if (Symflags & object::SymbolRef::SF_Undefined)
     return 'U';
 
   if (Symflags & object::SymbolRef::SF_Common)
     return 'C';
 
   char Ret = '?';
   if (Symflags & object::SymbolRef::SF_Absolute)
     Ret = 'a';
-  else if (IRObjectFile *IR = dyn_cast<IRObjectFile>(&Obj)) {
+  else if (IRObjectFile *IR = dyn_cast<IRObjectFile>(&Obj))
     Ret = getSymbolNMTypeChar(*IR, I);
-    Triple Host(sys::getDefaultTargetTriple());
-    if (Ret == 'd' && Host.isOSDarwin() && Symflags & SymbolRef::SF_Const)
-      Ret = 's';
-  }
   else if (COFFObjectFile *COFF = dyn_cast<COFFObjectFile>(&Obj))
     Ret = getSymbolNMTypeChar(*COFF, I);
   else if (MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(&Obj))
     Ret = getSymbolNMTypeChar(*MachO, I);
   else
     Ret = getSymbolNMTypeChar(cast<ELFObjectFileBase>(Obj), I);
 
   if (Symflags & object::SymbolRef::SF_Global)