[lld] Initial commit for new Mach-O backend

Summary:
This is the first commit for the new Mach-O backend, designed to roughly
follow the architecture of the existing ELF and COFF backends, and
building off work that @RuiU and @pcc did in a branch a while back. Note
that this is a very stripped-down commit with the bare minimum of
functionality for ease of review. We'll be following up with more diffs
soon.

Currently, we're able to generate a simple "Hello World!" executable
that runs on OS X Catalina (and possibly on earlier OS X versions; I
haven't tested them). (This executable can be obtained by compiling
`test/MachO/relocations.s`.) We're mocking out a few load commands to
achieve this -- for example, we can't load dynamic libraries, but
Catalina requires binaries to be linked against `dyld`, so we hardcode
the emission of a `LC_LOAD_DYLIB` command. Other mocked out load
commands include LC_SYMTAB and LC_DYSYMTAB.

Differential Revision: https://reviews.llvm.org/D75382

lld/CMakeLists.txt

@@ -194,5 +194,6 @@ endif()
 add_subdirectory(docs)
 add_subdirectory(COFF)
 add_subdirectory(ELF)
+add_subdirectory(MachO)
 add_subdirectory(MinGW)
 add_subdirectory(wasm)

lld/MachO/Arch/X86_64.cpp

@@ -0,0 +1,60 @@
+//===- X86_64.cpp ---------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "Target.h"
+#include "lld/Common/ErrorHandler.h"
+#include "llvm/BinaryFormat/MachO.h"
+#include "llvm/Support/Endian.h"
+
+using namespace llvm::MachO;
+using namespace llvm::support::endian;
+using namespace lld;
+using namespace lld::macho;
+
+namespace {
+
+struct X86_64 : TargetInfo {
+  X86_64();
+  uint64_t getImplicitAddend(const uint8_t *loc, uint8_t type) const override;
+  void relocateOne(uint8_t *loc, uint8_t type, uint64_t val) const override;
+};
+
+X86_64::X86_64() {
+  cpuType = CPU_TYPE_X86_64;
+  cpuSubtype = CPU_SUBTYPE_X86_64_ALL;
+}
+
+uint64_t X86_64::getImplicitAddend(const uint8_t *loc, uint8_t type) const {
+  switch (type) {
+  case X86_64_RELOC_SIGNED:
+    return read32le(loc);
+  default:
+    error("TODO: Unhandled relocation type " + std::to_string(type));
+    return 0;
+  }
+}
+
+void X86_64::relocateOne(uint8_t *loc, uint8_t type, uint64_t val) const {
+  switch (type) {
+  case X86_64_RELOC_SIGNED:
+    // This type is only used for pc-relative relocations, so offset by 4 since
+    // the RIP has advanced by 4 at this point.
+    write32le(loc, val - 4);
+    break;
+  default:
+    llvm_unreachable(
+        "getImplicitAddend should have flagged all unhandled relocation types");
+  }
+}
+
+} // namespace
+
+TargetInfo *macho::createX86_64TargetInfo() {
+  static X86_64 t;
+  return &t;
+}

lld/MachO/CMakeLists.txt

@@ -0,0 +1,34 @@
+set(LLVM_TARGET_DEFINITIONS Options.td)
+tablegen(LLVM Options.inc -gen-opt-parser-defs)
+add_public_tablegen_target(MachOOptionsTableGen)
+
+add_lld_library(lldMachO2
+  Arch/X86_64.cpp
+  Driver.cpp
+  InputFiles.cpp
+  InputSection.cpp
+  OutputSegment.cpp
+  SymbolTable.cpp
+  Symbols.cpp
+  Target.cpp
+  Writer.cpp
+
+  LINK_COMPONENTS
+  ${LLVM_TARGETS_TO_BUILD}
+  BinaryFormat
+  Core
+  DebugInfoDWARF
+  LTO
+  MC
+  Object
+  Option
+  Support
+
+  LINK_LIBS
+  lldCommon
+  ${LLVM_PTHREAD_LIB}
+
+  DEPENDS
+  MachOOptionsTableGen
+  ${tablegen_deps}
+  )

lld/MachO/Config.h

@@ -0,0 +1,29 @@
+//===- Config.h -------------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLD_MACHO_CONFIG_H
+#define LLD_MACHO_CONFIG_H
+
+#include "llvm/ADT/StringRef.h"
+
+namespace lld {
+namespace macho {
+
+class Symbol;
+
+struct Configuration {
+  llvm::StringRef outputFile;
+  Symbol *entry;
+};
+
+extern Configuration *config;
+
+} // namespace macho
+} // namespace lld
+
+#endif

lld/MachO/Driver.cpp

@@ -0,0 +1,150 @@
+//===- Driver.cpp ---------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "Driver.h"
+#include "Config.h"
+#include "InputFiles.h"
+#include "OutputSegment.h"
+#include "SymbolTable.h"
+#include "Symbols.h"
+#include "Target.h"
+#include "Writer.h"
+
+#include "lld/Common/Args.h"
+#include "lld/Common/Driver.h"
+#include "lld/Common/ErrorHandler.h"
+#include "lld/Common/LLVM.h"
+#include "lld/Common/Memory.h"
+#include "lld/Common/Version.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/BinaryFormat/MachO.h"
+#include "llvm/BinaryFormat/Magic.h"
+#include "llvm/Option/ArgList.h"
+#include "llvm/Option/Option.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+using namespace llvm;
+using namespace llvm::MachO;
+using namespace llvm::sys;
+using namespace lld;
+using namespace lld::macho;
+
+Configuration *lld::macho::config;
+
+// Create prefix string literals used in Options.td
+#define PREFIX(NAME, VALUE) const char *NAME[] = VALUE;
+#include "Options.inc"
+#undef PREFIX
+
+// Create table mapping all options defined in Options.td
+static const opt::OptTable::Info optInfo[] = {
+#define OPTION(X1, X2, ID, KIND, GROUP, ALIAS, X7, X8, X9, X10, X11, X12)      \
+  {X1, X2, X10,         X11,         OPT_##ID, opt::Option::KIND##Class,       \
+   X9, X8, OPT_##GROUP, OPT_##ALIAS, X7,       X12},
+#include "Options.inc"
+#undef OPTION
+};
+
+MachOOptTable::MachOOptTable() : OptTable(optInfo) {}
+
+opt::InputArgList MachOOptTable::parse(ArrayRef<const char *> argv) {
+  // Make InputArgList from string vectors.
+  unsigned missingIndex;
+  unsigned missingCount;
+  SmallVector<const char *, 256> vec(argv.data(), argv.data() + argv.size());
+
+  opt::InputArgList args = ParseArgs(vec, missingIndex, missingCount);
+
+  if (missingCount)
+    error(Twine(args.getArgString(missingIndex)) + ": missing argument");
+
+  for (opt::Arg *arg : args.filtered(OPT_UNKNOWN))
+    error("unknown argument: " + arg->getSpelling());
+  return args;
+}
+
+static TargetInfo *createTargetInfo(opt::InputArgList &args) {
+  StringRef s = args.getLastArgValue(OPT_arch, "x86_64");
+  if (s != "x86_64")
+    error("missing or unsupported -arch " + s);
+  return createX86_64TargetInfo();
+}
+
+static void addFile(StringRef path) {
+  Optional<MemoryBufferRef> buffer = readFile(path);
+  if (!buffer)
+    return;
+  MemoryBufferRef mbref = *buffer;
+
+  switch (identify_magic(mbref.getBuffer())) {
+  case file_magic::macho_object:
+    inputFiles.push_back(make<ObjFile>(mbref));
+    break;
+  default:
+    error(path + ": unhandled file type");
+  }
+}
+
+bool macho::link(llvm::ArrayRef<const char *> argsArr, bool canExitEarly,
+                 raw_ostream &stdoutOS, raw_ostream &stderrOS) {
+  lld::stdoutOS = &stdoutOS;
+  lld::stderrOS = &stderrOS;
+
+  MachOOptTable parser;
+  opt::InputArgList args = parser.parse(argsArr.slice(1));
+
+  if (args.hasArg(OPT_v)) {
+    message(getLLDVersion());
+    freeArena();
+    return !errorCount();
+  }
+
+  config = make<Configuration>();
+  symtab = make<SymbolTable>();
+  target = createTargetInfo(args);
+
+  config->entry = symtab->addUndefined(args.getLastArgValue(OPT_e, "_main"));
+  config->outputFile = args.getLastArgValue(OPT_o, "a.out");
+
+  getOrCreateOutputSegment("__TEXT", VM_PROT_READ | VM_PROT_EXECUTE);
+  getOrCreateOutputSegment("__DATA", VM_PROT_READ | VM_PROT_WRITE);
+
+  for (opt::Arg *arg : args) {
+    switch (arg->getOption().getID()) {
+    case OPT_INPUT:
+      addFile(arg->getValue());
+      break;
+    }
+  }
+
+  if (!isa<Defined>(config->entry)) {
+    error("undefined symbol: " + config->entry->getName());
+    return false;
+  }
+
+  // Initialize InputSections.
+  for (InputFile *file : inputFiles)
+    for (InputSection *sec : file->sections)
+      inputSections.push_back(sec);
+
+  // Add input sections to output segments.
+  for (InputSection *isec : inputSections) {
+    OutputSegment *os =
+        getOrCreateOutputSegment(isec->segname, VM_PROT_READ | VM_PROT_WRITE);
+    os->sections[isec->name].push_back(isec);
+  }
+
+  // Write to an output file.
+  writeResult();
+
+  if (canExitEarly)
+    exitLld(errorCount() ? 1 : 0);
+
+  freeArena();
+  return !errorCount();
+}

lld/MachO/Driver.h

@@ -0,0 +1,35 @@
+//===- Driver.h -------------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLD_MACHO_DRIVER_H
+#define LLD_MACHO_DRIVER_H
+
+#include "lld/Common/LLVM.h"
+#include "llvm/Option/OptTable.h"
+
+namespace lld {
+namespace macho {
+
+class MachOOptTable : public llvm::opt::OptTable {
+public:
+  MachOOptTable();
+  llvm::opt::InputArgList parse(ArrayRef<const char *> argv);
+};
+
+// Create enum with OPT_xxx values for each option in Options.td
+enum {
+  OPT_INVALID = 0,
+#define OPTION(_1, _2, ID, _4, _5, _6, _7, _8, _9, _10, _11, _12) OPT_##ID,
+#include "Options.inc"
+#undef OPTION
+};
+
+} // namespace macho
+} // namespace lld
+
+#endif