[llvm-objcopy][MachO] Add support for LC_CODE_SIGNATURE

[alexander-shaposhnikov]

Summary

This diff adds support for copying binaries containing a LC_CODE_SIGNATURE load command .

Test plan: make check-all

[alexander-shaposhnikov]

Fix typo.

[hiraditya]

Not sure if this will also fix: "llvm-objcopy: error: unsupported load command (cmd=0x1d)" error. https://bugs.llvm.org/show_bug.cgi?id=46306

[alexander-shaposhnikov]

@hiraditya , if I'm not mistaken, yes, it will. https://github.com/llvm-mirror/llvm/blob/master/include/llvm/BinaryFormat/MachO.def#L53

[hiraditya]

Thanks a lot for fixing this, this was blocking me earlier yesterday and @smeenai asked me to reach out to you.

[MaskRay]

llvm/test/tools/llvm-objcopy/MachO/code_signature_lc.test

5

Does this test need CHECK lines?

[jhenderson]

Looks reasonable on the surface, but I don't have the Mach-O knowledge to confirm it, so best get someone else to give the LGTM.

llvm/test/tools/llvm-objcopy/MachO/code_signature_lc.test

5

I don't think so, strictly? cmp does the job fine, since we know the load command is in the input (citation: presumably some yaml2obj test), and it does a binary diff.

That being said, a check line might be helpful to prevent user error in the input.

[smeenai]

LGTM from the Mach-O side.

llvm/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp

222

Typo: covention -> convention

IIRC the reason for this convention is that dyld3 assumes the text segment starts at file offset 0, so the Mach-O header is counted as part of the text segment. See the comment about dyld3 in Writer.cpp in D75382.

234

Does this comment need updating? It appears the code signature is at the end.

llvm/tools/llvm-objcopy/MachO/Object.h

309

Typo: comamnd -> command

[alexander-shaposhnikov]

llvm/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp

234

yeah, thanks, I'll update the comment

[alexander-shaposhnikov]

Fix typos

llvm/test/tools/llvm-objcopy/MachO/code_signature_lc.test

+# RUN: yaml2obj %s -o %t
+# RUN: llvm-objcopy %t %t.copy
+# RUN: cmp %t %t.copy
+
+--- !mach-o
+FileHeader:
+  magic:           0xFEEDFACF
+  cputype:         0x01000007
+  cpusubtype:      0x80000003
+  filetype:        0x00000002
+  ncmds:           2
+  sizeofcmds:      88
+  flags:           0x00218085
+  reserved:        0x00000000
+LoadCommands:
+  - cmd:             LC_SEGMENT_64
+    cmdsize:         72
+    segname:         __LINKEDIT
+    vmaddr:          4294979584
+    vmsize:          4096
+    fileoff:         120
+    filesize:        20
+    maxprot:         7
+    initprot:        1
+    nsects:          0
+    flags:           0
+  - cmd:             LC_CODE_SIGNATURE
+    cmdsize:         16
+    dataoff:         124
+    datasize:        16
+...

llvm/tools/llvm-objcopy/MachO/MachOLayoutBuilder.cpp

for (std::unique_ptr<Section> &Sec : LC.Sections) {
       Sec->NReloc = Sec->Relocations.size();
       Offset += sizeof(MachO::any_relocation_info) * Sec->NReloc;
     }
 
   return Offset;
 }
 
 Error MachOLayoutBuilder::layoutTail(uint64_t Offset) {
+  // If we are building the layout of an executable or dynamic library
+  // which does not have any segments other than __LINKEDIT,
+  // the Offset can be equal to zero by this time. It happens because of the
+  // covention that in such cases the file offsets specified by LC_SEGMENT start
+  // with zero (unlike the case of a relocatable object file).
+  const bool IsObject = O.Header.FileType == MachO::HeaderFileType::MH_OBJECT;
+  const uint64_t HeaderSize =
+      Is64Bit ? sizeof(MachO::mach_header_64) : sizeof(MachO::mach_header);
+  assert((!IsObject || Offset >= HeaderSize + O.Header.SizeOfCmds) &&
+         "Incorrect tail offset");
+  Offset = std::max(Offset, HeaderSize + O.Header.SizeOfCmds);
+
   // The order of LINKEDIT elements is as follows:
   // rebase info, binding info, weak binding info, lazy binding info, export
   // trie, data-in-code, symbol table, indirect symbol table, symbol table
   // strings.
   uint64_t NListSize = Is64Bit ? sizeof(MachO::nlist_64) : sizeof(MachO::nlist);
   uint64_t StartOfLinkEdit = Offset;
   uint64_t StartOfRebaseInfo = StartOfLinkEdit;
   uint64_t StartOfBindingInfo = StartOfRebaseInfo + O.Rebases.Opcodes.size();
   uint64_t StartOfWeakBindingInfo = StartOfBindingInfo + O.Binds.Opcodes.size();
   uint64_t StartOfLazyBindingInfo =
       StartOfWeakBindingInfo + O.WeakBinds.Opcodes.size();
   uint64_t StartOfExportTrie =
       StartOfLazyBindingInfo + O.LazyBinds.Opcodes.size();
   uint64_t StartOfFunctionStarts = StartOfExportTrie + O.Exports.Trie.size();
   uint64_t StartOfDataInCode =
       StartOfFunctionStarts + O.FunctionStarts.Data.size();
   uint64_t StartOfSymbols = StartOfDataInCode + O.DataInCode.Data.size();
   uint64_t StartOfIndirectSymbols =
       StartOfSymbols + NListSize * O.SymTable.Symbols.size();
   uint64_t StartOfSymbolStrings =
       StartOfIndirectSymbols +
       sizeof(uint32_t) * O.IndirectSymTable.Symbols.size();
+  uint64_t StartOfCodeSignature =
+      StartOfSymbolStrings + StrTableBuilder.getSize();
   uint64_t LinkEditSize =
-      (StartOfSymbolStrings + StrTableBuilder.getSize()) - StartOfLinkEdit;
+      (StartOfCodeSignature + O.CodeSignature.Data.size()) - StartOfLinkEdit;
 
   // Now we have determined the layout of the contents of the __LINKEDIT
   // segment. Update its load command.
   if (LinkEditLoadCommand) {
     MachO::macho_load_command *MLC = LinkEditLoadCommand;
     switch (LinkEditLoadCommand->load_command_data.cmd) {
     case MachO::LC_SEGMENT:
       MLC->segment_command_data.cmdsize = sizeof(MachO::segment_command);
case MachO::LC_SEGMENT_64:
       break;
     }
   }
 
   for (LoadCommand &LC : O.LoadCommands) {
     auto &MLC = LC.MachOLoadCommand;
     auto cmd = MLC.load_command_data.cmd;
     switch (cmd) {
+    case MachO::LC_CODE_SIGNATURE:
+      MLC.linkedit_data_command_data.dataoff = StartOfCodeSignature;
+      MLC.linkedit_data_command_data.datasize = O.CodeSignature.Data.size();
+      break;
     case MachO::LC_SYMTAB:
       MLC.symtab_command_data.symoff = StartOfSymbols;
       MLC.symtab_command_data.nsyms = O.SymTable.Symbols.size();
       MLC.symtab_command_data.stroff = StartOfSymbolStrings;
       MLC.symtab_command_data.strsize = StrTableBuilder.getSize();
       break;
     case MachO::LC_DYSYMTAB: {
       if (MLC.dysymtab_command_data.ntoc != 0 ||

llvm/tools/llvm-objcopy/MachO/MachOReader.h

class MachOReader : public Reader {
   void readLoadCommands(Object &O) const;
   void readSymbolTable(Object &O) const;
   void setSymbolInRelocationInfo(Object &O) const;
   void readRebaseInfo(Object &O) const;
   void readBindInfo(Object &O) const;
   void readWeakBindInfo(Object &O) const;
   void readLazyBindInfo(Object &O) const;
   void readExportInfo(Object &O) const;
+  void readLinkData(Object &O, Optional<size_t> LCIndex, LinkData &LD) const;
+  void readCodeSignature(Object &O) const;
   void readDataInCodeData(Object &O) const;
   void readFunctionStartsData(Object &O) const;
   void readIndirectSymbolTable(Object &O) const;
   void readSwiftVersion(Object &O) const;
 
 public:
   explicit MachOReader(const object::MachOObjectFile &Obj) : MachOObj(Obj) {}
 
   std::unique_ptr<Object> create() const override;
 };
 
 } // end namespace macho
 } // end namespace objcopy
 } // end namespace llvm

llvm/tools/llvm-objcopy/MachO/MachOReader.cpp

 }
 
 void MachOReader::readLoadCommands(Object &O) const {
   // For MachO sections indices start from 1.
   uint32_t NextSectionIndex = 1;
   for (auto LoadCmd : MachOObj.load_commands()) {
     LoadCommand LC;
     switch (LoadCmd.C.cmd) {
+    case MachO::LC_CODE_SIGNATURE:
+      O.CodeSignatureCommandIndex = O.LoadCommands.size();
+      break;
     case MachO::LC_SEGMENT:
       LC.Sections = extractSections<MachO::section, MachO::segment_command>(
           LoadCmd, MachOObj, NextSectionIndex);
       break;
     case MachO::LC_SEGMENT_64:
       LC.Sections =
           extractSections<MachO::section_64, MachO::segment_command_64>(
               LoadCmd, MachOObj, NextSectionIndex);

 void MachOReader::readLazyBindInfo(Object &O) const {
   O.LazyBinds.Opcodes = MachOObj.getDyldInfoLazyBindOpcodes();
 }
 
 void MachOReader::readExportInfo(Object &O) const {
   O.Exports.Trie = MachOObj.getDyldInfoExportsTrie();
 }
 
-void MachOReader::readDataInCodeData(Object &O) const {
-  if (!O.DataInCodeCommandIndex)
+void MachOReader::readLinkData(Object &O, Optional<size_t> LCIndex,
+                               LinkData &LD) const {
+  if (!LCIndex)
     return;
-  const MachO::linkedit_data_command &LDC =
-      O.LoadCommands[*O.DataInCodeCommandIndex]
-          .MachOLoadCommand.linkedit_data_command_data;
+  const MachO::linkedit_data_command &LC =
+      O.LoadCommands[*LCIndex].MachOLoadCommand.linkedit_data_command_data;
+  LD.Data =
+      arrayRefFromStringRef(MachOObj.getData().substr(LC.dataoff, LC.datasize));
+}
 
-  O.DataInCode.Data = arrayRefFromStringRef(
-      MachOObj.getData().substr(LDC.dataoff, LDC.datasize));
+void MachOReader::readCodeSignature(Object &O) const {
+  return readLinkData(O, O.CodeSignatureCommandIndex, O.CodeSignature);
 }
 
-void MachOReader::readFunctionStartsData(Object &O) const {
-  if (!O.FunctionStartsCommandIndex)
-    return;
-  const MachO::linkedit_data_command &LDC =
-      O.LoadCommands[*O.FunctionStartsCommandIndex]
-          .MachOLoadCommand.linkedit_data_command_data;
+void MachOReader::readDataInCodeData(Object &O) const {
+  return readLinkData(O, O.DataInCodeCommandIndex, O.DataInCode);
+}
 
-  O.FunctionStarts.Data = arrayRefFromStringRef(
-      MachOObj.getData().substr(LDC.dataoff, LDC.datasize));
+void MachOReader::readFunctionStartsData(Object &O) const {
+  return readLinkData(O, O.FunctionStartsCommandIndex, O.FunctionStarts);
 }
 
 void MachOReader::readIndirectSymbolTable(Object &O) const {
   MachO::dysymtab_command DySymTab = MachOObj.getDysymtabLoadCommand();
   constexpr uint32_t AbsOrLocalMask =
       MachO::INDIRECT_SYMBOL_LOCAL | MachO::INDIRECT_SYMBOL_ABS;
   for (uint32_t i = 0; i < DySymTab.nindirectsyms; ++i) {
     uint32_t Index = MachOObj.getIndirectSymbolTableEntry(DySymTab, i);
std::unique_ptr<Object> MachOReader::create() const {
   readLoadCommands(*Obj);
   readSymbolTable(*Obj);
   setSymbolInRelocationInfo(*Obj);
   readRebaseInfo(*Obj);
   readBindInfo(*Obj);
   readWeakBindInfo(*Obj);
   readLazyBindInfo(*Obj);
   readExportInfo(*Obj);
+  readCodeSignature(*Obj);
   readDataInCodeData(*Obj);
   readFunctionStartsData(*Obj);
   readIndirectSymbolTable(*Obj);
   readSwiftVersion(*Obj);
   return Obj;
 }
 
 } // end namespace macho
 } // end namespace objcopy
 } // end namespace llvm

llvm/tools/llvm-objcopy/MachO/MachOWriter.h

class MachOWriter {
   void writeSymbolTable();
   void writeStringTable();
   void writeRebaseInfo();
   void writeBindInfo();
   void writeWeakBindInfo();
   void writeLazyBindInfo();
   void writeExportInfo();
   void writeIndirectSymbolTable();
+  void writeLinkData(Optional<size_t> LCIndex, const LinkData &LD);
+  void writeCodeSignatureData();
   void writeDataInCodeData();
   void writeFunctionStartsData();
   void writeTail();
 
 public:
   MachOWriter(Object &O, bool Is64Bit, bool IsLittleEndian, uint64_t PageSize,
               Buffer &B)
       : O(O), Is64Bit(Is64Bit), IsLittleEndian(IsLittleEndian),

llvm/tools/llvm-objcopy/MachO/MachOWriter.cpp

const MachO::dysymtab_command &DySymTabCommand =
         O.LoadCommands[*O.DySymTabCommandIndex]
             .MachOLoadCommand.dysymtab_command_data;
 
     if (DySymTabCommand.indirectsymoff)
       Ends.push_back(DySymTabCommand.indirectsymoff +
                      sizeof(uint32_t) * O.IndirectSymTable.Symbols.size());
   }
 
+  if (O.CodeSignatureCommandIndex) {
+    const MachO::linkedit_data_command &LinkEditDataCommand =
+        O.LoadCommands[*O.CodeSignatureCommandIndex]
+            .MachOLoadCommand.linkedit_data_command_data;
+    if (LinkEditDataCommand.dataoff)
+      Ends.push_back(LinkEditDataCommand.dataoff +
+                     LinkEditDataCommand.datasize);
+  }
+
   if (O.DataInCodeCommandIndex) {
     const MachO::linkedit_data_command &LinkEditDataCommand =
         O.LoadCommands[*O.DataInCodeCommandIndex]
             .MachOLoadCommand.linkedit_data_command_data;
 
     if (LinkEditDataCommand.dataoff)
       Ends.push_back(LinkEditDataCommand.dataoff +
                      LinkEditDataCommand.datasize);
void MachOWriter::writeIndirectSymbolTable() {
   for (const IndirectSymbolEntry &Sym : O.IndirectSymTable.Symbols) {
     uint32_t Entry = (Sym.Symbol) ? (*Sym.Symbol)->Index : Sym.OriginalIndex;
     if (IsLittleEndian != sys::IsLittleEndianHost)
       sys::swapByteOrder(Entry);
     *Out++ = Entry;
   }
 }
 
-void MachOWriter::writeDataInCodeData() {
-  if (!O.DataInCodeCommandIndex)
+void MachOWriter::writeLinkData(Optional<size_t> LCIndex, const LinkData &LD) {
+  if (!LCIndex)
     return;
   const MachO::linkedit_data_command &LinkEditDataCommand =
-      O.LoadCommands[*O.DataInCodeCommandIndex]
-          .MachOLoadCommand.linkedit_data_command_data;
+      O.LoadCommands[*LCIndex].MachOLoadCommand.linkedit_data_command_data;
   char *Out = (char *)B.getBufferStart() + LinkEditDataCommand.dataoff;
-  assert((LinkEditDataCommand.datasize == O.DataInCode.Data.size()) &&
-         "Incorrect data in code data size");
-  memcpy(Out, O.DataInCode.Data.data(), O.DataInCode.Data.size());
+  assert((LinkEditDataCommand.datasize == LD.Data.size()) &&
+         "Incorrect data size");
+  memcpy(Out, LD.Data.data(), LD.Data.size());
+}
+
+void MachOWriter::writeCodeSignatureData() {
+  return writeLinkData(O.CodeSignatureCommandIndex, O.CodeSignature);
+}
+
+void MachOWriter::writeDataInCodeData() {
+  return writeLinkData(O.DataInCodeCommandIndex, O.DataInCode);
 }
 
 void MachOWriter::writeFunctionStartsData() {
-  if (!O.FunctionStartsCommandIndex)
-    return;
-  const MachO::linkedit_data_command &LinkEditDataCommand =
-      O.LoadCommands[*O.FunctionStartsCommandIndex]
-          .MachOLoadCommand.linkedit_data_command_data;
-  char *Out = (char *)B.getBufferStart() + LinkEditDataCommand.dataoff;
-  assert((LinkEditDataCommand.datasize == O.FunctionStarts.Data.size()) &&
-         "Incorrect function starts data size");
-  memcpy(Out, O.FunctionStarts.Data.data(), O.FunctionStarts.Data.size());
+  return writeLinkData(O.FunctionStartsCommandIndex, O.FunctionStarts);
 }
 
 void MachOWriter::writeTail() {
   typedef void (MachOWriter::*WriteHandlerType)(void);
   typedef std::pair<uint64_t, WriteHandlerType> WriteOperation;
   SmallVector<WriteOperation, 7> Queue;
 
   if (O.SymTabCommandIndex) {
const MachO::dysymtab_command &DySymTabCommand =
         O.LoadCommands[*O.DySymTabCommandIndex]
             .MachOLoadCommand.dysymtab_command_data;
 
     if (DySymTabCommand.indirectsymoff)
       Queue.emplace_back(DySymTabCommand.indirectsymoff,
                          &MachOWriter::writeIndirectSymbolTable);
   }
 
+  if (O.CodeSignatureCommandIndex) {
+    const MachO::linkedit_data_command &LinkEditDataCommand =
+        O.LoadCommands[*O.CodeSignatureCommandIndex]
+            .MachOLoadCommand.linkedit_data_command_data;
+
+    if (LinkEditDataCommand.dataoff)
+      Queue.emplace_back(LinkEditDataCommand.dataoff,
+                         &MachOWriter::writeCodeSignatureData);
+  }
+
   if (O.DataInCodeCommandIndex) {
     const MachO::linkedit_data_command &LinkEditDataCommand =
         O.LoadCommands[*O.DataInCodeCommandIndex]
             .MachOLoadCommand.linkedit_data_command_data;
 
     if (LinkEditDataCommand.dataoff)
       Queue.emplace_back(LinkEditDataCommand.dataoff,
                          &MachOWriter::writeDataInCodeData);

llvm/tools/llvm-objcopy/MachO/Object.h

struct Object {
   RebaseInfo Rebases;
   BindInfo Binds;
   WeakBindInfo WeakBinds;
   LazyBindInfo LazyBinds;
   ExportInfo Exports;
   IndirectSymbolTable IndirectSymTable;
   LinkData DataInCode;
   LinkData FunctionStarts;
+  LinkData CodeSignature;
 
   Optional<uint32_t> SwiftVersion;
 
+  /// The index LC_CODE_SIGNATURE load comamnd if present.
+  Optional<size_t> CodeSignatureCommandIndex;
   /// The index of LC_SYMTAB load command if present.
   Optional<size_t> SymTabCommandIndex;
   /// The index of LC_DYLD_INFO or LC_DYLD_INFO_ONLY load command if present.
   Optional<size_t> DyLdInfoCommandIndex;
   /// The index LC_DYSYMTAB load comamnd if present.
   Optional<size_t> DySymTabCommandIndex;
   /// The index LC_DATA_IN_CODE load comamnd if present.
   Optional<size_t> DataInCodeCommandIndex;