Rename embedded bitcode section in MachO

[steven_wu]

Summary

Rename the section embeds bitcode from ".llvmbc,.llvmbc" to "LLVM,bitcode".
The new name matches MachO section naming convention.

[• rafael]

Don't you also need to check the segment name on macho? Or it is just invalid to create a FOO, bitcode?

[davide]

lib/Object/FunctionIndexObjectFile.cpp

42 ↗

(On Diff #48343)

You can just inline the call here (also true in the other case), as there's only one use of this variable.

lib/Object/ObjectFile.cpp

119 ↗

(On Diff #48343)

this can be spelled in a more compact form.
return (Obj.isMachO()) ? "__bitcode" : ".llvmbc";

[steven_wu]

It will probably be better to check the segment name. I was hesitate to do
that because I couldn't figure out a way without adding more virtual method.
Here is a try to make it more robust. Note it does slightly change the
behavior because std::error not longer propagates through findBitcodeInObject.

[• rafael]

I think this is fine given that it just mean that a section with a corrupted name is not bitcode. That is the same answer you would get if the corruption had changed the name to __bitcodx.

pcc, what do you think?

[steven_wu]

Ping.

[pcc]

LGTM

llvm/trunk/docs/BitCodeFormat.rst

 encode the CPU of the target.
 
 .. _native object file:
 
 Native Object File Wrapper Format
 =================================
 
 Bitcode files for LLVM IR may also be wrapped in a native object file
-(i.e. ELF, COFF, Mach-O).  The bitcode must be stored in a section of the
-object file named ``.llvmbc``.  This wrapper format is useful for accommodating
-LTO in compilation pipelines where intermediate objects must be native object
-files which contain metadata in other sections.
+(i.e. ELF, COFF, Mach-O).  The bitcode must be stored in a section of the object
+file named ``__LLVM,__bitcode`` for MachO and ``.llvmbc`` for the other object
+formats.  This wrapper format is useful for accommodating LTO in compilation
+pipelines where intermediate objects must be native object files which contain
+metadata in other sections.
 
 Not all tools support this format.
 
 .. _encoding of LLVM IR:
 
 LLVM IR Encoding
 ================
 

llvm/trunk/include/llvm/Object/MachO.h

public:
   uint64_t getSectionSize(DataRefImpl Sec) const override;
   std::error_code getSectionContents(DataRefImpl Sec,
                                      StringRef &Res) const override;
   uint64_t getSectionAlignment(DataRefImpl Sec) const override;
   bool isSectionText(DataRefImpl Sec) const override;
   bool isSectionData(DataRefImpl Sec) const override;
   bool isSectionBSS(DataRefImpl Sec) const override;
   bool isSectionVirtual(DataRefImpl Sec) const override;
+  bool isSectionBitcode(DataRefImpl Sec) const override;
   relocation_iterator section_rel_begin(DataRefImpl Sec) const override;
   relocation_iterator section_rel_end(DataRefImpl Sec) const override;
 
   void moveRelocationNext(DataRefImpl &Rel) const override;
   uint64_t getRelocationOffset(DataRefImpl Rel) const override;
   symbol_iterator getRelocationSymbol(DataRefImpl Rel) const override;
   section_iterator getRelocationSection(DataRefImpl Rel) const;
   uint64_t getRelocationType(DataRefImpl Rel) const override;

llvm/trunk/include/llvm/Object/ObjectFile.h

public:
 
   /// @brief Get the alignment of this section as the actual value (not log 2).
   uint64_t getAlignment() const;
 
   bool isText() const;
   bool isData() const;
   bool isBSS() const;
   bool isVirtual() const;
+  bool isBitcode() const;
 
   bool containsSymbol(SymbolRef S) const;
 
   relocation_iterator relocation_begin() const;
   relocation_iterator relocation_end() const;
   iterator_range<relocation_iterator> relocations() const {
     return make_range(relocation_begin(), relocation_end());
   }
protected:
   virtual std::error_code getSectionContents(DataRefImpl Sec,
                                              StringRef &Res) const = 0;
   virtual uint64_t getSectionAlignment(DataRefImpl Sec) const = 0;
   virtual bool isSectionText(DataRefImpl Sec) const = 0;
   virtual bool isSectionData(DataRefImpl Sec) const = 0;
   virtual bool isSectionBSS(DataRefImpl Sec) const = 0;
   // A section is 'virtual' if its contents aren't present in the object image.
   virtual bool isSectionVirtual(DataRefImpl Sec) const = 0;
+  virtual bool isSectionBitcode(DataRefImpl Sec) const;
   virtual relocation_iterator section_rel_begin(DataRefImpl Sec) const = 0;
   virtual relocation_iterator section_rel_end(DataRefImpl Sec) const = 0;
   virtual section_iterator getRelocatedSection(DataRefImpl Sec) const;
 
   // Same as above for RelocationRef.
   friend class RelocationRef;
   virtual void moveRelocationNext(DataRefImpl &Rel) const = 0;
   virtual uint64_t getRelocationOffset(DataRefImpl Rel) const = 0;
public:
   static ErrorOr<std::unique_ptr<COFFObjectFile>>
   createCOFFObjectFile(MemoryBufferRef Object);
 
   static ErrorOr<std::unique_ptr<ObjectFile>>
   createELFObjectFile(MemoryBufferRef Object);
 
   static ErrorOr<std::unique_ptr<MachOObjectFile>>
   createMachOObjectFile(MemoryBufferRef Object);
+
 };
 
 // Inline function definitions.
 inline SymbolRef::SymbolRef(DataRefImpl SymbolP, const ObjectFile *Owner)
     : BasicSymbolRef(SymbolP, Owner) {}
 
 inline ErrorOr<StringRef> SymbolRef::getName() const {
   return getObject()->getSymbolName(getRawDataRefImpl());

 inline bool SectionRef::isBSS() const {
   return OwningObject->isSectionBSS(SectionPimpl);
 }
 
 inline bool SectionRef::isVirtual() const {
   return OwningObject->isSectionVirtual(SectionPimpl);
 }
 
+inline bool SectionRef::isBitcode() const {
+  return OwningObject->isSectionBitcode(SectionPimpl);
+}
+
 inline relocation_iterator SectionRef::relocation_begin() const {
   return OwningObject->section_rel_begin(SectionPimpl);
 }
 
 inline relocation_iterator SectionRef::relocation_end() const {
   return OwningObject->section_rel_end(SectionPimpl);
 }
 

llvm/trunk/lib/Object/FunctionIndexObjectFile.cpp

 
 std::unique_ptr<FunctionInfoIndex> FunctionIndexObjectFile::takeIndex() {
   return std::move(Index);
 }
 
 ErrorOr<MemoryBufferRef>
 FunctionIndexObjectFile::findBitcodeInObject(const ObjectFile &Obj) {
   for (const SectionRef &Sec : Obj.sections()) {
-    StringRef SecName;
-    if (std::error_code EC = Sec.getName(SecName))
-      return EC;
-    if (SecName == ".llvmbc") {
+    if (Sec.isBitcode()) {
       StringRef SecContents;
       if (std::error_code EC = Sec.getContents(SecContents))
         return EC;
       return MemoryBufferRef(SecContents, Obj.getFileName());
     }
   }
 
   return object_error::bitcode_section_not_found;

llvm/trunk/lib/Object/IRObjectFile.cpp

basic_symbol_iterator IRObjectFile::symbol_end_impl() const {
   uint64_t NumAsm = AsmSymbols.size();
   NumAsm <<= 2;
   Ret.p = 3 | NumAsm;
   return basic_symbol_iterator(BasicSymbolRef(Ret, this));
 }
 
 ErrorOr<MemoryBufferRef> IRObjectFile::findBitcodeInObject(const ObjectFile &Obj) {
   for (const SectionRef &Sec : Obj.sections()) {
-    StringRef SecName;
-    if (std::error_code EC = Sec.getName(SecName))
-      return EC;
-    if (SecName == ".llvmbc") {
+    if (Sec.isBitcode()) {
       StringRef SecContents;
       if (std::error_code EC = Sec.getContents(SecContents))
         return EC;
       return MemoryBufferRef(SecContents, Obj.getFileName());
     }
   }
 
   return object_error::bitcode_section_not_found;

llvm/trunk/lib/Object/MachOObjectFile.cpp

unsigned MachOObjectFile::getSectionID(SectionRef Sec) const {
   return Sec.getRawDataRefImpl().d.a;
 }
 
 bool MachOObjectFile::isSectionVirtual(DataRefImpl Sec) const {
   // FIXME: Unimplemented.
   return false;
 }
 
+bool MachOObjectFile::isSectionBitcode(DataRefImpl Sec) const {
+  StringRef SegmentName = getSectionFinalSegmentName(Sec);
+  StringRef SectName;
+  if (!getSectionName(Sec, SectName))
+    return (SegmentName == "__LLVM" && SectName == "__bitcode");
+  return false;
+}
+
 relocation_iterator MachOObjectFile::section_rel_begin(DataRefImpl Sec) const {
   DataRefImpl Ret;
   Ret.d.a = Sec.d.a;
   Ret.d.b = 0;
   return relocation_iterator(RelocationRef(Ret, this));
 }
 
 relocation_iterator

llvm/trunk/lib/Object/ObjectFile.cpp

std::error_code ObjectFile::printSymbolName(raw_ostream &OS,
   if (std::error_code EC = Name.getError())
     return EC;
   OS << *Name;
   return std::error_code();
 }
 
 uint32_t ObjectFile::getSymbolAlignment(DataRefImpl DRI) const { return 0; }
 
+bool ObjectFile::isSectionBitcode(DataRefImpl Sec) const {
+  StringRef SectName;
+  if (!getSectionName(Sec, SectName))
+    return SectName == ".llvmbc";
+  return false;
+}
+
 section_iterator ObjectFile::getRelocatedSection(DataRefImpl Sec) const {
   return section_iterator(SectionRef(Sec, this));
 }
 
 ErrorOr<std::unique_ptr<ObjectFile>>
 ObjectFile::createObjectFile(MemoryBufferRef Object, sys::fs::file_magic Type) {
   StringRef Data = Object.getBuffer();
   if (Type == sys::fs::file_magic::unknown)

llvm/trunk/test/LTO/X86/Inputs/bcsection.macho.s

-.section .llvmbc,.llvmbc
+.section __FOO,__bitcode
+.asciz "Wrong Section"
+
+.section __LLVM,__bitcode
 .incbin "bcsection.bc"