Object: make the following changes into SymbolRef

- Add enum SymbolType and function getSymbolType()
- Add function isGlobal() - it's returns true for symbols that can be used in another objects, such as library functions.
- Rename function getAddress() to getOffset() and add new function getAddress(), because currently getAddress() returns section offset of symbol first byte. new getAddress() return symbol address.
- Change usage SymbolRef::getAddress() to getOffset() in tools/llvm-nm and tools/llvm-objdump.

Patch by Danil Malyshev!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139683 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Object/COFF.h

@@ -92,10 +92,13 @@ private:
 protected:
   virtual error_code getSymbolNext(DataRefImpl Symb, SymbolRef &Res) const;
   virtual error_code getSymbolName(DataRefImpl Symb, StringRef &Res) const;
+  virtual error_code getSymbolOffset(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolAddress(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolSize(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolNMTypeChar(DataRefImpl Symb, char &Res) const;
   virtual error_code isSymbolInternal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code isSymbolGlobal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code getSymbolType(DataRefImpl Symb, SymbolRef::SymbolType &Res) const;
 
   virtual error_code getSectionNext(DataRefImpl Sec, SectionRef &Res) const;
   virtual error_code getSectionName(DataRefImpl Sec, StringRef &Res) const;

include/llvm/Object/ObjectFile.h

@@ -51,6 +51,13 @@ public:
     std::memset(&SymbolPimpl, 0, sizeof(SymbolPimpl));
   }
 
+  enum SymbolType {
+    ST_Function,
+    ST_Data,
+    ST_External,    // Defined in another object file
+    ST_Other
+  };
+
   SymbolRef(DataRefImpl SymbolP, const ObjectFile *Owner);
 
   bool operator==(const SymbolRef &Other) const;
@@ -59,7 +66,9 @@ public:
 
   error_code getName(StringRef &Result) const;
   error_code getAddress(uint64_t &Result) const;
+  error_code getOffset(uint64_t &Result) const;
   error_code getSize(uint64_t &Result) const;
+  error_code getSymbolType(SymbolRef::SymbolType &Result) const;
 
   /// Returns the ascii char that should be displayed in a symbol table dump via
   /// nm for this symbol.
@@ -68,6 +77,10 @@ public:
   /// Returns true for symbols that are internal to the object file format such
   /// as section symbols.
   error_code isInternal(bool &Result) const;
+
+  /// Returns true for symbols that can be used in another objects,
+  /// such as library functions
+  error_code isGlobal(bool &Result) const;
 };
 
 /// RelocationRef - This is a value type class that represents a single
@@ -151,9 +164,12 @@ protected:
   virtual error_code getSymbolNext(DataRefImpl Symb, SymbolRef &Res) const = 0;
   virtual error_code getSymbolName(DataRefImpl Symb, StringRef &Res) const = 0;
   virtual error_code getSymbolAddress(DataRefImpl Symb, uint64_t &Res) const =0;
+  virtual error_code getSymbolOffset(DataRefImpl Symb, uint64_t &Res) const =0;
   virtual error_code getSymbolSize(DataRefImpl Symb, uint64_t &Res) const = 0;
   virtual error_code getSymbolNMTypeChar(DataRefImpl Symb, char &Res) const = 0;
   virtual error_code isSymbolInternal(DataRefImpl Symb, bool &Res) const = 0;
+  virtual error_code isSymbolGlobal(DataRefImpl Symb, bool &Res) const = 0;
+  virtual error_code getSymbolType(DataRefImpl Symb, SymbolRef::SymbolType &Res) const = 0;
 
   // Same as above for SectionRef.
   friend class SectionRef;
@@ -274,6 +290,10 @@ inline error_code SymbolRef::getAddress(uint64_t &Result) const {
   return OwningObject->getSymbolAddress(SymbolPimpl, Result);
 }
 
+inline error_code SymbolRef::getOffset(uint64_t &Result) const {
+  return OwningObject->getSymbolOffset(SymbolPimpl, Result);
+}
+
 inline error_code SymbolRef::getSize(uint64_t &Result) const {
   return OwningObject->getSymbolSize(SymbolPimpl, Result);
 }
@@ -286,6 +306,14 @@ inline error_code SymbolRef::isInternal(bool &Result) const {
   return OwningObject->isSymbolInternal(SymbolPimpl, Result);
 }
 
+inline error_code SymbolRef::isGlobal(bool &Result) const {
+  return OwningObject->isSymbolGlobal(SymbolPimpl, Result);
+}
+
+inline error_code SymbolRef::getSymbolType(SymbolRef::SymbolType &Result) const {
+  return OwningObject->getSymbolType(SymbolPimpl, Result);
+}
+
 
 /// SectionRef
 inline SectionRef::SectionRef(DataRefImpl SectionP,

lib/Object/COFFObjectFile.cpp

@@ -114,7 +114,7 @@ error_code COFFObjectFile::getSymbolNext(DataRefImpl Symb,
   return object_error::success;
 }
 
-error_code COFFObjectFile::getSymbolAddress(DataRefImpl Symb,
+error_code COFFObjectFile::getSymbolOffset(DataRefImpl Symb,
                                             uint64_t &Result) const {
   const coff_symbol *symb = toSymb(Symb);
   const coff_section *Section = NULL;
@@ -132,6 +132,55 @@ error_code COFFObjectFile::getSymbolAddress(DataRefImpl Symb,
   return object_error::success;
 }
 
+error_code COFFObjectFile::getSymbolAddress(DataRefImpl Symb,
+                                            uint64_t &Result) const {
+  const coff_symbol *symb = toSymb(Symb);
+  const coff_section *Section = NULL;
+  if (error_code ec = getSection(symb->SectionNumber, Section))
+    return ec;
+  char Type;
+  if (error_code ec = getSymbolNMTypeChar(Symb, Type))
+    return ec;
+  if (Type == 'U' || Type == 'w')
+    Result = UnknownAddressOrSize;
+  else if (Section)
+    Result = reinterpret_cast<uintptr_t>(base() +
+                                         Section->PointerToRawData +
+                                         symb->Value);
+  else
+    Result = reinterpret_cast<uintptr_t>(base() + symb->Value);
+  return object_error::success;
+}
+
+error_code COFFObjectFile::getSymbolType(DataRefImpl Symb,
+                                         SymbolRef::SymbolType &Result) const {
+  const coff_symbol *symb = toSymb(Symb);
+  Result = SymbolRef::ST_Other;
+  if (symb->StorageClass == COFF::IMAGE_SYM_CLASS_EXTERNAL &&
+      symb->SectionNumber == COFF::IMAGE_SYM_UNDEFINED) {
+    Result = SymbolRef::ST_External;
+  } else {
+    if (symb->Type.ComplexType == COFF::IMAGE_SYM_DTYPE_FUNCTION) {
+      Result = SymbolRef::ST_Function;
+    } else {
+      char Type;
+      if (error_code ec = getSymbolNMTypeChar(Symb, Type))
+        return ec;
+      if (Type == 'r' || Type == 'R') {
+        Result = SymbolRef::ST_Data;
+      }
+    }
+  }
+  return object_error::success;
+}
+
+error_code COFFObjectFile::isSymbolGlobal(DataRefImpl Symb,
+                                          bool &Result) const {
+  const coff_symbol *symb = toSymb(Symb);
+  Result = (symb->StorageClass == COFF::IMAGE_SYM_CLASS_EXTERNAL);
+  return object_error::success;
+}
+
 error_code COFFObjectFile::getSymbolSize(DataRefImpl Symb,
                                          uint64_t &Result) const {
   // FIXME: Return the correct size. This requires looking at all the symbols

lib/Object/ELFObjectFile.cpp

@@ -310,10 +310,13 @@ class ELFObjectFile : public ObjectFile {
 protected:
   virtual error_code getSymbolNext(DataRefImpl Symb, SymbolRef &Res) const;
   virtual error_code getSymbolName(DataRefImpl Symb, StringRef &Res) const;
+  virtual error_code getSymbolOffset(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolAddress(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolSize(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolNMTypeChar(DataRefImpl Symb, char &Res) const;
   virtual error_code isSymbolInternal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code isSymbolGlobal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code getSymbolType(DataRefImpl Symb, SymbolRef::SymbolType &Res) const;
 
   virtual error_code getSectionNext(DataRefImpl Sec, SectionRef &Res) const;
   virtual error_code getSectionName(DataRefImpl Sec, StringRef &Res) const;
@@ -415,7 +418,7 @@ error_code ELFObjectFile<target_endianness, is64Bits>
 
 template<support::endianness target_endianness, bool is64Bits>
 error_code ELFObjectFile<target_endianness, is64Bits>
-                        ::getSymbolAddress(DataRefImpl Symb,
+                        ::getSymbolOffset(DataRefImpl Symb,
                                            uint64_t &Result) const {
   validateSymbol(Symb);
   const Elf_Sym  *symb = getSymbol(Symb);
@@ -447,6 +450,43 @@ error_code ELFObjectFile<target_endianness, is64Bits>
   }
 }
 
+template<support::endianness target_endianness, bool is64Bits>
+error_code ELFObjectFile<target_endianness, is64Bits>
+                        ::getSymbolAddress(DataRefImpl Symb,
+                                           uint64_t &Result) const {
+  validateSymbol(Symb);
+  const Elf_Sym  *symb = getSymbol(Symb);
+  const Elf_Shdr *Section;
+  switch (symb->st_shndx) {
+  case ELF::SHN_COMMON: // Fall through.
+   // Undefined symbols have no address yet.
+  case ELF::SHN_UNDEF:
+    Result = UnknownAddressOrSize;
+    return object_error::success;
+  case ELF::SHN_ABS:
+    Result = reinterpret_cast<uintptr_t>(base()+symb->st_value);
+    return object_error::success;
+  default: Section = getSection(symb->st_shndx);
+  }
+  const uint8_t* addr = base();
+  if (Section)
+    addr += Section->sh_offset;
+  switch (symb->getType()) {
+  case ELF::STT_SECTION:
+    Result = reinterpret_cast<uintptr_t>(addr);
+    return object_error::success;
+  case ELF::STT_FUNC: // Fall through.
+  case ELF::STT_OBJECT: // Fall through.
+  case ELF::STT_NOTYPE:
+    addr += symb->st_value;
+    Result = reinterpret_cast<uintptr_t>(addr);
+    return object_error::success;
+  default:
+    Result = UnknownAddressOrSize;
+    return object_error::success;
+  }
+}
+
 template<support::endianness target_endianness, bool is64Bits>
 error_code ELFObjectFile<target_endianness, is64Bits>
                         ::getSymbolSize(DataRefImpl Symb,
@@ -524,6 +564,43 @@ error_code ELFObjectFile<target_endianness, is64Bits>
   return object_error::success;
 }
 
+template<support::endianness target_endianness, bool is64Bits>
+error_code ELFObjectFile<target_endianness, is64Bits>
+                        ::getSymbolType(DataRefImpl Symb,
+                                        SymbolRef::SymbolType &Result) const {
+  validateSymbol(Symb);
+  const Elf_Sym  *symb = getSymbol(Symb);
+
+  if (symb->st_shndx == ELF::SHN_UNDEF) {
+    Result = SymbolRef::ST_External;
+    return object_error::success;
+  }
+
+  switch (symb->getType()) {
+  case ELF::STT_FUNC:
+    Result = SymbolRef::ST_Function;
+    break;
+  case ELF::STT_OBJECT:
+    Result = SymbolRef::ST_Data;
+    break;
+  default:
+    Result = SymbolRef::ST_Other;
+    break;
+  }
+  return object_error::success;
+}
+
+template<support::endianness target_endianness, bool is64Bits>
+error_code ELFObjectFile<target_endianness, is64Bits>
+                        ::isSymbolGlobal(DataRefImpl Symb,
+                                        bool &Result) const {
+  validateSymbol(Symb);
+  const Elf_Sym  *symb = getSymbol(Symb);
+
+  Result = symb->getBinding() == ELF::STB_GLOBAL;
+  return object_error::success;
+}
+
 template<support::endianness target_endianness, bool is64Bits>
 error_code ELFObjectFile<target_endianness, is64Bits>
                         ::isSymbolInternal(DataRefImpl Symb,

lib/Object/MachOObjectFile.cpp

@@ -49,10 +49,13 @@ public:
 protected:
   virtual error_code getSymbolNext(DataRefImpl Symb, SymbolRef &Res) const;
   virtual error_code getSymbolName(DataRefImpl Symb, StringRef &Res) const;
+  virtual error_code getSymbolOffset(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolAddress(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolSize(DataRefImpl Symb, uint64_t &Res) const;
   virtual error_code getSymbolNMTypeChar(DataRefImpl Symb, char &Res) const;
   virtual error_code isSymbolInternal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code isSymbolGlobal(DataRefImpl Symb, bool &Res) const;
+  virtual error_code getSymbolType(DataRefImpl Symb, SymbolRef::SymbolType &Res) const;
 
   virtual error_code getSectionNext(DataRefImpl Sec, SectionRef &Res) const;
   virtual error_code getSectionName(DataRefImpl Sec, StringRef &Res) const;
@@ -190,7 +193,7 @@ error_code MachOObjectFile::getSymbolName(DataRefImpl DRI,
   return object_error::success;
 }
 
-error_code MachOObjectFile::getSymbolAddress(DataRefImpl DRI,
+error_code MachOObjectFile::getSymbolOffset(DataRefImpl DRI,
                                              uint64_t &Result) const {
   if (MachOObj->is64Bit()) {
     InMemoryStruct<macho::Symbol64TableEntry> Entry;
@@ -204,6 +207,27 @@ error_code MachOObjectFile::getSymbolAddress(DataRefImpl DRI,
   return object_error::success;
 }
 
+error_code MachOObjectFile::getSymbolAddress(DataRefImpl DRI,
+                                             uint64_t &Result) const {
+  uint64_t SymbolOffset;
+  uint8_t SectionIndex;
+  if (MachOObj->is64Bit()) {
+    InMemoryStruct<macho::Symbol64TableEntry> Entry;
+    getSymbol64TableEntry(DRI, Entry);
+    SymbolOffset = Entry->Value;
+    SectionIndex = Entry->SectionIndex;
+  } else {
+    InMemoryStruct<macho::SymbolTableEntry> Entry;
+    getSymbolTableEntry(DRI, Entry);
+    SymbolOffset = Entry->Value;
+    SectionIndex = Entry->SectionIndex;
+  }
+  getSectionAddress(Sections[SectionIndex], Result);
+  Result += SymbolOffset;
+
+  return object_error::success;
+}
+
 error_code MachOObjectFile::getSymbolSize(DataRefImpl DRI,
                                           uint64_t &Result) const {
   Result = UnknownAddressOrSize;
@@ -259,6 +283,45 @@ error_code MachOObjectFile::isSymbolInternal(DataRefImpl DRI,
   return object_error::success;
 }
 
+error_code MachOObjectFile::isSymbolGlobal(DataRefImpl Symb, bool &Res) const {
+
+  if (MachOObj->is64Bit()) {
+    InMemoryStruct<macho::Symbol64TableEntry> Entry;
+    getSymbol64TableEntry(Symb, Entry);
+    Res = Entry->Type & MachO::NlistMaskExternal;
+  } else {
+    InMemoryStruct<macho::SymbolTableEntry> Entry;
+    getSymbolTableEntry(Symb, Entry);
+    Res = Entry->Type & MachO::NlistMaskExternal;
+  }
+  return object_error::success;
+}
+
+error_code MachOObjectFile::getSymbolType(DataRefImpl Symb,
+                                          SymbolRef::SymbolType &Res) const {
+  uint8_t n_type;
+  if (MachOObj->is64Bit()) {
+    InMemoryStruct<macho::Symbol64TableEntry> Entry;
+    getSymbol64TableEntry(Symb, Entry);
+    n_type = Entry->Type;
+  } else {
+    InMemoryStruct<macho::SymbolTableEntry> Entry;
+    getSymbolTableEntry(Symb, Entry);
+    n_type = Entry->Type;
+  }
+  Res = SymbolRef::ST_Other;
+  switch (n_type & MachO::NlistMaskType) {
+    case MachO::NListTypeUndefined :
+      Res = SymbolRef::ST_External;
+      break;
+    case MachO::NListTypeSection :
+      Res = SymbolRef::ST_Function;
+      break;
+  }
+  return object_error::success;
+}
+
+
 ObjectFile::symbol_iterator MachOObjectFile::begin_symbols() const {
   // DRI.d.a = segment number; DRI.d.b = symbol index.
   DataRefImpl DRI;

tools/llvm-nm/llvm-nm.cpp

@@ -285,7 +285,7 @@ static void DumpSymbolNamesFromObject(ObjectFile *obj) {
       if (error(i->getSize(s.Size))) break;
     }
     if (PrintAddress)
-      if (error(i->getAddress(s.Address))) break;
+      if (error(i->getOffset(s.Address))) break;
     if (error(i->getNMTypeChar(s.TypeChar))) break;
     if (error(i->getName(s.Name))) break;
     SymbolList.push_back(s);

tools/llvm-objdump/llvm-objdump.cpp

@@ -191,7 +191,7 @@ static void DisassembleInput(const StringRef &Filename) {
       bool contains;
       if (!error(i->containsSymbol(*si, contains)) && contains) {
         uint64_t Address;
-        if (error(si->getAddress(Address))) break;
+        if (error(si->getOffset(Address))) break;
         StringRef Name;
         if (error(si->getName(Name))) break;
         Symbols.push_back(std::make_pair(Address, Name));