1 files changed, 200 insertions, 101 deletions

diff --git a/llvm/tools/llvm-objcopy/MachO/MachOWriter.cpp b/llvm/tools/llvm-objcopy/MachO/MachOWriter.cpp
index 0d3d23567ab..74200c5aa62 100644
--- a/llvm/tools/llvm-objcopy/MachO/MachOWriter.cpp
+++ b/llvm/tools/llvm-objcopy/MachO/MachOWriter.cpp
@@ -7,7 +7,6 @@
 //===----------------------------------------------------------------------===//
 
 #include "MachOWriter.h"
-#include "MachOLayoutBuilder.h"
 #include "Object.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/BinaryFormat/MachO.h"
@@ -41,10 +40,16 @@ size_t MachOWriter::totalSize() const {
     const MachO::symtab_command &SymTabCommand =
         O.LoadCommands[*O.SymTabCommandIndex]
             .MachOLoadCommand.symtab_command_data;
-    if (SymTabCommand.symoff)
+    if (SymTabCommand.symoff) {
+      assert((SymTabCommand.nsyms == O.SymTable.Symbols.size()) &&
+             "Incorrect number of symbols");
       Ends.push_back(SymTabCommand.symoff + symTableSize());
-    if (SymTabCommand.stroff)
+    }
+    if (SymTabCommand.stroff) {
+      assert((SymTabCommand.strsize == StrTableBuilder.getSize()) &&
+             "Incorrect string table size");
       Ends.push_back(SymTabCommand.stroff + SymTabCommand.strsize);
+    }
   }
   if (O.DyLdInfoCommandIndex) {
     const MachO::dyld_info_command &DyLdInfoCommand =
@@ -79,36 +84,6 @@ size_t MachOWriter::totalSize() const {
     }
   }
 
-  if (O.DySymTabCommandIndex) {
-    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.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);
-  }
-
-  if (O.FunctionStartsCommandIndex) {
-    const MachO::linkedit_data_command &LinkEditDataCommand =
-        O.LoadCommands[*O.FunctionStartsCommandIndex]
-            .MachOLoadCommand.linkedit_data_command_data;
-
-    if (LinkEditDataCommand.dataoff)
-      Ends.push_back(LinkEditDataCommand.dataoff +
-                     LinkEditDataCommand.datasize);
-  }
-
   // Otherwise, use the last section / reloction.
   for (const auto &LC : O.LoadCommands)
     for (const auto &S : LC.Sections) {
@@ -145,6 +120,14 @@ void MachOWriter::writeHeader() {
   memcpy(B.getBufferStart(), &Header, HeaderSize);
 }
 
+void MachOWriter::updateSymbolIndexes() {
+  uint32_t Index = 0;
+  for (auto &Symbol : O.SymTable.Symbols) {
+    Symbol->Index = Index;
+    Index++;
+  }
+}
+
 void MachOWriter::writeLoadCommands() {
   uint8_t *Begin = B.getBufferStart() + headerSize();
   for (const auto &LC : O.LoadCommands) {
@@ -278,7 +261,7 @@ void MachOWriter::writeSymbolTable() {
           .MachOLoadCommand.symtab_command_data;
 
   uint8_t *StrTable = (uint8_t *)B.getBufferStart() + SymTabCommand.stroff;
-  LayoutBuilder.getStringTableBuilder().write(StrTable);
+  StrTableBuilder.write(StrTable);
 }
 
 void MachOWriter::writeStringTable() {
@@ -292,7 +275,7 @@ void MachOWriter::writeStringTable() {
   for (auto Iter = O.SymTable.Symbols.begin(), End = O.SymTable.Symbols.end();
        Iter != End; Iter++) {
     SymbolEntry *Sym = Iter->get();
-    uint32_t Nstrx = LayoutBuilder.getStringTableBuilder().getOffset(Sym->Name);
+    auto Nstrx = StrTableBuilder.getOffset(Sym->Name);
 
     if (Is64Bit)
       writeNListEntry<MachO::nlist_64>(*Sym, IsLittleEndian, SymTable, Nstrx);
@@ -361,45 +344,6 @@ void MachOWriter::writeExportInfo() {
   memcpy(Out, O.Exports.Trie.data(), O.Exports.Trie.size());
 }
 
-void MachOWriter::writeIndirectSymbolTable() {
-  if (!O.DySymTabCommandIndex)
-    return;
-
-  const MachO::dysymtab_command &DySymTabCommand =
-      O.LoadCommands[*O.DySymTabCommandIndex]
-          .MachOLoadCommand.dysymtab_command_data;
-
-  char *Out = (char *)B.getBufferStart() + DySymTabCommand.indirectsymoff;
-  assert((DySymTabCommand.nindirectsyms == O.IndirectSymTable.Symbols.size()) &&
-         "Incorrect indirect symbol table size");
-  memcpy(Out, O.IndirectSymTable.Symbols.data(),
-         sizeof(uint32_t) * O.IndirectSymTable.Symbols.size());
-}
-
-void MachOWriter::writeDataInCodeData() {
-  if (!O.DataInCodeCommandIndex)
-    return;
-  const MachO::linkedit_data_command &LinkEditDataCommand =
-      O.LoadCommands[*O.DataInCodeCommandIndex]
-          .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());
-}
-
-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());
-}
-
 void MachOWriter::writeTail() {
   typedef void (MachOWriter::*WriteHandlerType)(void);
   typedef std::pair<uint64_t, WriteHandlerType> WriteOperation;
@@ -435,51 +379,206 @@ void MachOWriter::writeTail() {
           {DyLdInfoCommand.export_off, &MachOWriter::writeExportInfo});
   }
 
-  if (O.DySymTabCommandIndex) {
-    const MachO::dysymtab_command &DySymTabCommand =
-        O.LoadCommands[*O.DySymTabCommandIndex]
-            .MachOLoadCommand.dysymtab_command_data;
+  llvm::sort(Queue, [](const WriteOperation &LHS, const WriteOperation &RHS) {
+    return LHS.first < RHS.first;
+  });
+
+  for (auto WriteOp : Queue)
+    (this->*WriteOp.second)();
+}
+
+void MachOWriter::updateSizeOfCmds() {
+  auto Size = 0;
+  for (const auto &LC : O.LoadCommands) {
+    auto &MLC = LC.MachOLoadCommand;
+    auto cmd = MLC.load_command_data.cmd;
+
+    switch (cmd) {
+    case MachO::LC_SEGMENT:
+      Size += sizeof(MachO::segment_command) +
+              sizeof(MachO::section) * LC.Sections.size();
+      continue;
+    case MachO::LC_SEGMENT_64:
+      Size += sizeof(MachO::segment_command_64) +
+              sizeof(MachO::section_64) * LC.Sections.size();
+      continue;
+    }
+
+    switch (cmd) {
+#define HANDLE_LOAD_COMMAND(LCName, LCValue, LCStruct)                         \
+  case MachO::LCName:                                                          \
+    Size += sizeof(MachO::LCStruct);                                           \
+    break;
+#include "llvm/BinaryFormat/MachO.def"
+#undef HANDLE_LOAD_COMMAND
+    }
+  }
+
+  O.Header.SizeOfCmds = Size;
+}
+
+// Updates the index and the number of local/external/undefined symbols. Here we
+// assume that MLC is a LC_DYSYMTAB and the nlist entries in the symbol table
+// are already sorted by the those types.
+void MachOWriter::updateDySymTab(MachO::macho_load_command &MLC) {
+  uint32_t NumLocalSymbols = 0;
+  auto Iter = O.SymTable.Symbols.begin();
+  auto End = O.SymTable.Symbols.end();
+  for (; Iter != End; Iter++) {
+    if ((*Iter)->n_type & (MachO::N_EXT | MachO::N_PEXT))
+      break;
+
+    NumLocalSymbols++;
+  }
+
+  uint32_t NumExtDefSymbols = 0;
+  for (; Iter != End; Iter++) {
+    if (((*Iter)->n_type & MachO::N_TYPE) == MachO::N_UNDF)
+      break;
 
-    if (DySymTabCommand.indirectsymoff)
-      Queue.emplace_back(DySymTabCommand.indirectsymoff,
-                         &MachOWriter::writeIndirectSymbolTable);
+    NumExtDefSymbols++;
   }
 
-  if (O.DataInCodeCommandIndex) {
-    const MachO::linkedit_data_command &LinkEditDataCommand =
-        O.LoadCommands[*O.DataInCodeCommandIndex]
-            .MachOLoadCommand.linkedit_data_command_data;
+  MLC.dysymtab_command_data.ilocalsym = 0;
+  MLC.dysymtab_command_data.nlocalsym = NumLocalSymbols;
+  MLC.dysymtab_command_data.iextdefsym = NumLocalSymbols;
+  MLC.dysymtab_command_data.nextdefsym = NumExtDefSymbols;
+  MLC.dysymtab_command_data.iundefsym = NumLocalSymbols + NumExtDefSymbols;
+  MLC.dysymtab_command_data.nundefsym =
+      O.SymTable.Symbols.size() - (NumLocalSymbols + NumExtDefSymbols);
+}
+
+// Recomputes and updates offset and size fields in load commands and sections
+// since they could be modified.
+Error MachOWriter::layout() {
+  auto SizeOfCmds = loadCommandsSize();
+  auto Offset = headerSize() + SizeOfCmds;
+  O.Header.NCmds = O.LoadCommands.size();
+  O.Header.SizeOfCmds = SizeOfCmds;
+
+  // Lay out sections.
+  for (auto &LC : O.LoadCommands) {
+    uint64_t FileOff = Offset;
+    uint64_t VMSize = 0;
+    uint64_t FileOffsetInSegment = 0;
+    for (auto &Sec : LC.Sections) {
+      if (!Sec.isVirtualSection()) {
+        auto FilePaddingSize =
+            OffsetToAlignment(FileOffsetInSegment, 1ull << Sec.Align);
+        Sec.Offset = Offset + FileOffsetInSegment + FilePaddingSize;
+        Sec.Size = Sec.Content.size();
+        FileOffsetInSegment += FilePaddingSize + Sec.Size;
+      }
+
+      VMSize = std::max(VMSize, Sec.Addr + Sec.Size);
+    }
+
+    // TODO: Handle the __PAGEZERO segment.
+    auto &MLC = LC.MachOLoadCommand;
+    switch (MLC.load_command_data.cmd) {
+    case MachO::LC_SEGMENT:
+      MLC.segment_command_data.cmdsize =
+          sizeof(MachO::segment_command) +
+          sizeof(MachO::section) * LC.Sections.size();
+      MLC.segment_command_data.nsects = LC.Sections.size();
+      MLC.segment_command_data.fileoff = FileOff;
+      MLC.segment_command_data.vmsize = VMSize;
+      MLC.segment_command_data.filesize = FileOffsetInSegment;
+      break;
+    case MachO::LC_SEGMENT_64:
+      MLC.segment_command_64_data.cmdsize =
+          sizeof(MachO::segment_command_64) +
+          sizeof(MachO::section_64) * LC.Sections.size();
+      MLC.segment_command_64_data.nsects = LC.Sections.size();
+      MLC.segment_command_64_data.fileoff = FileOff;
+      MLC.segment_command_64_data.vmsize = VMSize;
+      MLC.segment_command_64_data.filesize = FileOffsetInSegment;
+      break;
+    }
 
-    if (LinkEditDataCommand.dataoff)
-      Queue.emplace_back(LinkEditDataCommand.dataoff,
-                         &MachOWriter::writeDataInCodeData);
+    Offset += FileOffsetInSegment;
   }
 
-  if (O.FunctionStartsCommandIndex) {
-    const MachO::linkedit_data_command &LinkEditDataCommand =
-        O.LoadCommands[*O.FunctionStartsCommandIndex]
-            .MachOLoadCommand.linkedit_data_command_data;
+  // Lay out relocations.
+  for (auto &LC : O.LoadCommands)
+    for (auto &Sec : LC.Sections) {
+      Sec.RelOff = Sec.Relocations.empty() ? 0 : Offset;
+      Sec.NReloc = Sec.Relocations.size();
+      Offset += sizeof(MachO::any_relocation_info) * Sec.NReloc;
+    }
 
-    if (LinkEditDataCommand.dataoff)
-      Queue.emplace_back(LinkEditDataCommand.dataoff,
-                         &MachOWriter::writeFunctionStartsData);
+  // Lay out tail stuff.
+  auto NListSize = Is64Bit ? sizeof(MachO::nlist_64) : sizeof(MachO::nlist);
+  for (auto &LC : O.LoadCommands) {
+    auto &MLC = LC.MachOLoadCommand;
+    auto cmd = MLC.load_command_data.cmd;
+    switch (cmd) {
+    case MachO::LC_SYMTAB:
+      MLC.symtab_command_data.nsyms = O.SymTable.Symbols.size();
+      MLC.symtab_command_data.strsize = StrTableBuilder.getSize();
+      MLC.symtab_command_data.symoff = Offset;
+      Offset += NListSize * MLC.symtab_command_data.nsyms;
+      MLC.symtab_command_data.stroff = Offset;
+      Offset += MLC.symtab_command_data.strsize;
+      break;
+    case MachO::LC_DYSYMTAB: {
+      if (MLC.dysymtab_command_data.ntoc != 0 ||
+          MLC.dysymtab_command_data.nmodtab != 0 ||
+          MLC.dysymtab_command_data.nextrefsyms != 0 ||
+          MLC.dysymtab_command_data.nlocrel != 0 ||
+          MLC.dysymtab_command_data.nextrel != 0)
+        return createStringError(llvm::errc::not_supported,
+                                 "shared library is not yet supported");
+
+      if (MLC.dysymtab_command_data.nindirectsyms != 0)
+        return createStringError(llvm::errc::not_supported,
+                                 "indirect symbol table is not yet supported");
+
+      updateDySymTab(MLC);
+      break;
+    }
+    case MachO::LC_SEGMENT:
+    case MachO::LC_SEGMENT_64:
+    case MachO::LC_VERSION_MIN_MACOSX:
+    case MachO::LC_BUILD_VERSION:
+    case MachO::LC_ID_DYLIB:
+    case MachO::LC_LOAD_DYLIB:
+    case MachO::LC_UUID:
+    case MachO::LC_SOURCE_VERSION:
+      // Nothing to update.
+      break;
+    default:
+      // Abort if it's unsupported in order to prevent corrupting the object.
+      return createStringError(llvm::errc::not_supported,
+                               "unsupported load command (cmd=0x%x)", cmd);
+    }
   }
 
-  llvm::sort(Queue, [](const WriteOperation &LHS, const WriteOperation &RHS) {
-    return LHS.first < RHS.first;
-  });
+  return Error::success();
+}
 
-  for (auto WriteOp : Queue)
-    (this->*WriteOp.second)();
+void MachOWriter::constructStringTable() {
+  for (std::unique_ptr<SymbolEntry> &Sym : O.SymTable.Symbols)
+    StrTableBuilder.add(Sym->Name);
+  StrTableBuilder.finalize();
 }
 
-Error MachOWriter::finalize() { return LayoutBuilder.layout(); }
+Error MachOWriter::finalize() {
+  updateSizeOfCmds();
+  constructStringTable();
+
+  if (auto E = layout())
+    return E;
+
+  return Error::success();
+}
 
 Error MachOWriter::write() {
   if (Error E = B.allocate(totalSize()))
     return E;
   memset(B.getBufferStart(), 0, totalSize());
   writeHeader();
+  updateSymbolIndexes();
   writeLoadCommands();
   writeSections();
   writeTail();