[Object, MachO] Cache parsed MachO header in MachOObjectFile. NFC.

[samsonov]

Summary

Avoid parsing object file each time MachOObjectFile::getHeader() is
called. Instead, cache the header in MachOObjectFile constructor, where
it's parsed anyway. In future, we must avoid constructing the object
at all if the header can't be parsed.

[filcab]

LGTM.

I'd probably like a comment pointing out that it works because all the (used) members of mach_header and mach_header64 match in size and location.
For people reading the code who aren't familiar with how those headers look, the MachOObjectFile constructor might look weird. (Not a strong want, but I think it might help readability)

Thanks

[samsonov]

We may get rid of Header pointer completely, and instead put this logic (with an appropriate comment) in getHeader() method. Let me know what you prefer.

[samsonov]

Submitted in r239075 (messed with branches, so Phabricator didn't close it for some reason).

include/llvm/Object/MachO.h

public:
   getRoutinesCommand(const LoadCommandInfo &L) const;
   MachO::routines_command_64
   getRoutinesCommand64(const LoadCommandInfo &L) const;
   MachO::thread_command
   getThreadCommand(const LoadCommandInfo &L) const;
 
   MachO::any_relocation_info getRelocation(DataRefImpl Rel) const;
   MachO::data_in_code_entry getDice(DataRefImpl Rel) const;
-  MachO::mach_header getHeader() const;
-  MachO::mach_header_64 getHeader64() const;
+  const MachO::mach_header &getHeader() const;
+  const MachO::mach_header_64 &getHeader64() const;
   uint32_t
   getIndirectSymbolTableEntry(const MachO::dysymtab_command &DLC,
                               unsigned Index) const;
   MachO::data_in_code_entry getDataInCodeTableEntry(uint32_t DataOffset,
                                                     unsigned Index) const;
   MachO::symtab_command getSymtabLoadCommand() const;
   MachO::dysymtab_command getDysymtabLoadCommand() const;
   MachO::linkedit_data_command getDataInCodeLoadCommand() const;
static bool classof(const Binary *v) {
     return v->isMachO();
   }
 
 private:
   // Walk load commands.
   LoadCommandInfo getFirstLoadCommandInfo() const;
   LoadCommandInfo getNextLoadCommandInfo(const LoadCommandInfo &L) const;
 
+  MachO::mach_header_64 Header64;
+  MachO::mach_header *Header;  // Points inside Header64.
   typedef SmallVector<const char*, 1> SectionList;
   SectionList Sections;
   typedef SmallVector<const char*, 1> LibraryList;
   LibraryList Libraries;
   LoadCommandList LoadCommands;
   typedef SmallVector<StringRef, 1> LibraryShortName;
   mutable LibraryShortName LibrariesShortNames;
   const char *SymtabLoadCmd;

lib/Object/MachOObjectFile.cpp

static uint32_t getSectionFlags(const MachOObjectFile *O,
   }
   MachO::section Sect = O->getSection(Sec);
   return Sect.flags;
 }
 
 MachOObjectFile::MachOObjectFile(MemoryBufferRef Object, bool IsLittleEndian,
                                  bool Is64bits, std::error_code &EC)
     : ObjectFile(getMachOType(IsLittleEndian, Is64bits), Object),
+      Header(reinterpret_cast<MachO::mach_header*>(&this->Header64)),
       SymtabLoadCmd(nullptr), DysymtabLoadCmd(nullptr),
       DataInCodeLoadCmd(nullptr), LinkOptHintsLoadCmd(nullptr),
       DyldInfoLoadCmd(nullptr), UuidLoadCmd(nullptr),
       HasPageZeroSegment(false) {
-  uint32_t LoadCommandCount = this->getHeader().ncmds;
+  // Parse header.
+  if (is64Bit())
+    Header64 = getStruct<MachO::mach_header_64>(this, getPtr(this, 0));
+  else
+    *Header = getStruct<MachO::mach_header>(this, getPtr(this, 0));
+
+  uint32_t LoadCommandCount = Header->ncmds;
   if (LoadCommandCount == 0)
     return;
 
   MachO::LoadCommandType SegmentLoadType = is64Bit() ?
     MachO::LC_SEGMENT_64 : MachO::LC_SEGMENT;
 
   LoadCommandInfo Load = getFirstLoadCommandInfo();
   for (unsigned I = 0; I < LoadCommandCount; ++I) {

 }
 
 unsigned MachOObjectFile::getArch() const {
   return getArch(getCPUType(this));
 }
 
 Triple MachOObjectFile::getArch(const char **McpuDefault,
                                 Triple *ThumbTriple) const {
-  Triple T;
-  if (is64Bit()) {
-    MachO::mach_header_64 H_64;
-    H_64 = getHeader64();
-    T = MachOObjectFile::getArch(H_64.cputype, H_64.cpusubtype, McpuDefault);
-    *ThumbTriple = MachOObjectFile::getThumbArch(H_64.cputype, H_64.cpusubtype,
-                                                 McpuDefault);
-  } else {
-    MachO::mach_header H;
-    H = getHeader();
-    T = MachOObjectFile::getArch(H.cputype, H.cpusubtype, McpuDefault);
-    *ThumbTriple = MachOObjectFile::getThumbArch(H.cputype, H.cpusubtype,
-                                                 McpuDefault);
-  }
-  return T;
+  *ThumbTriple = getThumbArch(Header->cputype, Header->cpusubtype, McpuDefault);
+  return getArch(Header->cputype, Header->cpusubtype, McpuDefault);
 }
 
 relocation_iterator MachOObjectFile::section_rel_begin(unsigned Index) const {
   DataRefImpl DRI;
   DRI.d.a = Index;
   return section_rel_begin(DRI);
 }
 

 }
 
 MachO::data_in_code_entry
 MachOObjectFile::getDice(DataRefImpl Rel) const {
   const char *P = reinterpret_cast<const char *>(Rel.p);
   return getStruct<MachO::data_in_code_entry>(this, P);
 }
 
-MachO::mach_header MachOObjectFile::getHeader() const {
-  return getStruct<MachO::mach_header>(this, getPtr(this, 0));
+const MachO::mach_header &MachOObjectFile::getHeader() const {
+  return *Header;
 }
 
-MachO::mach_header_64 MachOObjectFile::getHeader64() const {
-  return getStruct<MachO::mach_header_64>(this, getPtr(this, 0));
+const MachO::mach_header_64 &MachOObjectFile::getHeader64() const {
+  assert(is64Bit());
+  return Header64;
 }
 
 uint32_t MachOObjectFile::getIndirectSymbolTableEntry(
                                              const MachO::dysymtab_command &DLC,
                                              unsigned Index) const {
   uint64_t Offset = DLC.indirectsymoff + Index * sizeof(uint32_t);
   return getStruct<uint32_t>(this, getPtr(this, Offset));
 }