[llvm-objcopy][MachO] Add support for universal binaries

This diff adds support for universal binaries to llvm-objcopy.
This is a recommit of 32c8435 with the asan issue fixed.

Test plan: make check-all

Differential revision: https://reviews.llvm.org/D88400

llvm/include/llvm/Object/MachOUniversalWriter.h

@@ -43,6 +43,12 @@ class Slice {
 
   Slice(const MachOObjectFile &O, uint32_t Align);
 
+  /// This constructor takes prespecified \param CPUType, \param CPUSubType,
+  /// \param ArchName, \param Align instead of inferring them from the archive
+  /// memebers.
+  Slice(const Archive &A, uint32_t CPUType, uint32_t CPUSubType,
+        std::string ArchName, uint32_t Align);
+
   static Expected<Slice> create(const Archive &A,
                                 LLVMContext *LLVMCtx = nullptr);
 

llvm/lib/Object/MachOUniversalWriter.cpp

@@ -75,6 +75,11 @@ static uint32_t calculateAlignment(const MachOObjectFile &ObjectFile) {
   }
 }
 
+Slice::Slice(const Archive &A, uint32_t CPUType, uint32_t CPUSubType,
+             std::string ArchName, uint32_t Align)
+    : B(&A), CPUType(CPUType), CPUSubType(CPUSubType),
+      ArchName(std::move(ArchName)), P2Alignment(Align) {}
+
 Slice::Slice(const MachOObjectFile &O, uint32_t Align)
     : B(&O), CPUType(O.getHeader().cputype),
       CPUSubType(O.getHeader().cpusubtype),

llvm/test/tools/llvm-objcopy/MachO/strip-all.test

@@ -27,6 +27,11 @@
 # cmp %t4 %t.dwarf.stripped
 # cmp %t5 %t.dwarf.stripped
 
+# RUN: llvm-lipo %t.dwarf -create -output %t.dwarf.universal
+# RUN: llvm-strip %t.dwarf.universal -o %t.dwarf.universal.stripped
+# RUN: llvm-lipo %t.dwarf.universal.stripped -thin x86_64 -output %t6
+# RUN: cmp %t6 %t.dwarf.stripped
+
 ## Make sure that debug sections are removed.
 # DWARF:       Sections [
 # DWARF-NOT:     Name: __debug_str

llvm/test/tools/llvm-objcopy/MachO/universal-object.test

@@ -0,0 +1,42 @@
+# This test verifies that llvm-objcopy copies a univeral Mach-O object file properly.
+
+# RUN: yaml2obj %p/Inputs/i386.yaml -o %t.i386
+# RUN: yaml2obj %p/Inputs/x86_64.yaml -o %t.x86_64
+
+## Case 1: copy a universal object containing regular Mach-O objects.
+# RUN: llvm-lipo %t.i386 %t.x86_64 -create -output %t.universal
+# RUN: llvm-objcopy %t.universal %t.universal.copy
+# RUN: llvm-lipo %t.universal.copy -archs | FileCheck --check-prefix=VERIFY_ARCHS %s
+# RUN: llvm-lipo %t.universal.copy -thin i386 -output %t.i386.copy
+# RUN: llvm-lipo %t.universal.copy -thin x86_64 -output %t.x86_64.copy
+# RUN: cmp %t.i386 %t.i386.copy
+# RUN: cmp %t.x86_64 %t.x86_64.copy
+
+## Case 2: copy a universal object file containing an archive.
+# RUN: rm -f %t.archive.i386
+# RUN: llvm-ar cr %t.archive.i386 %t.i386
+# RUN: llvm-lipo %t.archive.i386 %t.x86_64 -create -output %t.universal.containing.archive
+# RUN: llvm-objcopy %t.universal.containing.archive %t.universal.containing.archive.copy
+# RUN: llvm-lipo %t.universal.containing.archive.copy -archs | FileCheck --check-prefix=VERIFY_ARCHS %s
+# RUN: llvm-lipo %t.universal.containing.archive.copy -thin i386 -output %t.archive.i386.copy
+# RUN: llvm-lipo %t.universal.containing.archive.copy -thin x86_64 -output %t.archive.x86_64.copy
+# RUN: cmp %t.archive.i386 %t.archive.i386.copy
+# RUN: cmp %t.x86_64 %t.archive.x86_64.copy
+
+## Case 3: copy an archive containing a universal object.
+# RUN: llvm-ar cr %t.archive.containing.universal %t.universal
+# RUN: llvm-objcopy %t.archive.containing.universal %t.archive.containing.universal.copy
+
+## Case 4: try to copy a universal object file contaning a bitcode slice.
+# RUN: echo 'target triple = "arm64-apple-ios8.0.0"' | llvm-as -o %t.bitcode
+# RUN: llvm-lipo %t.bitcode  %t.x86_64 -create -output %t.universal.containing.bitcode
+# RUN: not llvm-objcopy %t.universal.containing.bitcode %t.universal.containing.bitcode.copy 2>&1 \
+# RUN:  | FileCheck --check-prefix=UNSUPPORTED_UNIVERSAL_OBJECT %s
+
+## Case 5: try to copy an archive containing an unsupported universal object.
+# RUN: llvm-ar cr %t.archive.universal.bitcode %t.universal.containing.bitcode
+# RUN: not llvm-objcopy %t.archive.universal.bitcode %t.archive.universal.bitcode.copy 2>&1 \
+# RUN:  | FileCheck --check-prefix=UNSUPPORTED_UNIVERSAL_OBJECT %s
+
+# VERIFY_ARCHS: i386 x86_64
+# UNSUPPORTED_UNIVERSAL_OBJECT: slice for 'arm64' of the universal Mach-O binary {{.*}} is not a Mach-O object or an archive

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

@@ -8,9 +8,13 @@
 
 #include "MachOObjcopy.h"
 #include "../CopyConfig.h"
+#include "../llvm-objcopy.h"
 #include "MachOReader.h"
 #include "MachOWriter.h"
 #include "llvm/ADT/DenseSet.h"
+#include "llvm/Object/ArchiveWriter.h"
+#include "llvm/Object/MachOUniversal.h"
+#include "llvm/Object/MachOUniversalWriter.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/Error.h"
 
@@ -386,6 +390,75 @@ Error executeObjcopyOnBinary(const CopyConfig &Config,
   return Writer.write();
 }
 
+Error executeObjcopyOnMachOUniversalBinary(CopyConfig &Config,
+                                           const MachOUniversalBinary &In,
+                                           Buffer &Out) {
+  SmallVector<OwningBinary<Binary>, 2> Binaries;
+  SmallVector<Slice, 2> Slices;
+  for (const auto &O : In.objects()) {
+    Expected<std::unique_ptr<Archive>> ArOrErr = O.getAsArchive();
+    if (ArOrErr) {
+      Expected<std::vector<NewArchiveMember>> NewArchiveMembersOrErr =
+          createNewArchiveMembers(Config, **ArOrErr);
+      if (!NewArchiveMembersOrErr)
+        return NewArchiveMembersOrErr.takeError();
+      Expected<std::unique_ptr<MemoryBuffer>> OutputBufferOrErr =
+          writeArchiveToBuffer(*NewArchiveMembersOrErr,
+                               (*ArOrErr)->hasSymbolTable(), (*ArOrErr)->kind(),
+                               Config.DeterministicArchives,
+                               (*ArOrErr)->isThin());
+      if (!OutputBufferOrErr)
+        return OutputBufferOrErr.takeError();
+      Expected<std::unique_ptr<Binary>> BinaryOrErr =
+          object::createBinary(**OutputBufferOrErr);
+      if (!BinaryOrErr)
+        return BinaryOrErr.takeError();
+      Binaries.emplace_back(std::move(*BinaryOrErr),
+                            std::move(*OutputBufferOrErr));
+      Slices.emplace_back(*cast<Archive>(Binaries.back().getBinary()),
+                          O.getCPUType(), O.getCPUSubType(),
+                          O.getArchFlagName(), O.getAlign());
+      continue;
+    }
+    // The methods getAsArchive, getAsObjectFile, getAsIRObject of the class
+    // ObjectForArch return an Error in case of the type mismatch. We need to
+    // check each in turn to see what kind of slice this is, so ignore errors
+    // produced along the way.
+    consumeError(ArOrErr.takeError());
+
+    Expected<std::unique_ptr<MachOObjectFile>> ObjOrErr = O.getAsObjectFile();
+    if (!ObjOrErr) {
+      consumeError(ObjOrErr.takeError());
+      return createStringError(std::errc::invalid_argument,
+                               "slice for '%s' of the universal Mach-O binary "
+                               "'%s' is not a Mach-O object or an archive",
+                               O.getArchFlagName().c_str(),
+                               Config.InputFilename.str().c_str());
+    }
+    std::string ArchFlagName = O.getArchFlagName();
+    MemBuffer MB(ArchFlagName);
+    if (Error E = executeObjcopyOnBinary(Config, **ObjOrErr, MB))
+      return E;
+    std::unique_ptr<WritableMemoryBuffer> OutputBuffer =
+        MB.releaseMemoryBuffer();
+    Expected<std::unique_ptr<Binary>> BinaryOrErr =
+        object::createBinary(*OutputBuffer);
+    if (!BinaryOrErr)
+      return BinaryOrErr.takeError();
+    Binaries.emplace_back(std::move(*BinaryOrErr), std::move(OutputBuffer));
+    Slices.emplace_back(*cast<MachOObjectFile>(Binaries.back().getBinary()),
+                        O.getAlign());
+  }
+  Expected<std::unique_ptr<MemoryBuffer>> B =
+      writeUniversalBinaryToBuffer(Slices);
+  if (!B)
+    return B.takeError();
+  if (Error E = Out.allocate((*B)->getBufferSize()))
+    return E;
+  memcpy(Out.getBufferStart(), (*B)->getBufferStart(), (*B)->getBufferSize());
+  return Out.commit();
+}
+
 } // end namespace macho
 } // end namespace objcopy
 } // end namespace llvm

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

@@ -24,6 +24,10 @@ class Buffer;
 namespace macho {
 Error executeObjcopyOnBinary(const CopyConfig &Config,
                              object::MachOObjectFile &In, Buffer &Out);
+
+Error executeObjcopyOnMachOUniversalBinary(
+    CopyConfig &Config, const object::MachOUniversalBinary &In, Buffer &Out);
+
 } // end namespace macho
 } // end namespace objcopy
 } // end namespace llvm

llvm/tools/llvm-objcopy/llvm-objcopy.cpp

@@ -25,6 +25,7 @@
 #include "llvm/Object/ELFTypes.h"
 #include "llvm/Object/Error.h"
 #include "llvm/Object/MachO.h"
+#include "llvm/Object/MachOUniversal.h"
 #include "llvm/Object/Wasm.h"
 #include "llvm/Option/Arg.h"
 #include "llvm/Option/ArgList.h"
@@ -144,14 +145,22 @@ static Error executeObjcopyOnBinary(CopyConfig &Config, object::Binary &In,
     return coff::executeObjcopyOnBinary(Config, *COFFBinary, Out);
   else if (auto *MachOBinary = dyn_cast<object::MachOObjectFile>(&In))
     return macho::executeObjcopyOnBinary(Config, *MachOBinary, Out);
+  else if (auto *MachOUniversalBinary =
+               dyn_cast<object::MachOUniversalBinary>(&In))
+    return macho::executeObjcopyOnMachOUniversalBinary(
+        Config, *MachOUniversalBinary, Out);
   else if (auto *WasmBinary = dyn_cast<object::WasmObjectFile>(&In))
     return objcopy::wasm::executeObjcopyOnBinary(Config, *WasmBinary, Out);
   else
     return createStringError(object_error::invalid_file_type,
                              "unsupported object file format");
 }
 
-static Error executeObjcopyOnArchive(CopyConfig &Config, const Archive &Ar) {
+namespace llvm {
+namespace objcopy {
+
+Expected<std::vector<NewArchiveMember>>
+createNewArchiveMembers(CopyConfig &Config, const Archive &Ar) {
   std::vector<NewArchiveMember> NewArchiveMembers;
   Error Err = Error::success();
   for (const Archive::Child &Child : Ar.children(Err)) {
@@ -166,7 +175,7 @@ static Error executeObjcopyOnArchive(CopyConfig &Config, const Archive &Ar) {
 
     MemBuffer MB(ChildNameOrErr.get());
     if (Error E = executeObjcopyOnBinary(Config, *ChildOrErr->get(), MB))
-      return E;
+      return std::move(E);
 
     Expected<NewArchiveMember> Member =
         NewArchiveMember::getOldMember(Child, Config.DeterministicArchives);
@@ -178,8 +187,19 @@ static Error executeObjcopyOnArchive(CopyConfig &Config, const Archive &Ar) {
   }
   if (Err)
     return createFileError(Config.InputFilename, std::move(Err));
+  return std::move(NewArchiveMembers);
+}
+
+} // end namespace objcopy
+} // end namespace llvm
 
-  return deepWriteArchive(Config.OutputFilename, NewArchiveMembers,
+static Error executeObjcopyOnArchive(CopyConfig &Config,
+                                     const object::Archive &Ar) {
+  Expected<std::vector<NewArchiveMember>> NewArchiveMembersOrErr =
+      createNewArchiveMembers(Config, Ar);
+  if (!NewArchiveMembersOrErr)
+    return NewArchiveMembersOrErr.takeError();
+  return deepWriteArchive(Config.OutputFilename, *NewArchiveMembersOrErr,
                           Ar.hasSymbolTable(), Ar.kind(),
                           Config.DeterministicArchives, Ar.isThin());
 }

llvm/tools/llvm-objcopy/llvm-objcopy.h

@@ -0,0 +1,32 @@
+//===- llvm-objcopy.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 LLVM_TOOLS_OBJCOPY_OBJCOPY_H
+#define LLVM_TOOLS_OBJCOPY_OBJCOPY_H
+
+#include "llvm/Support/Error.h"
+
+namespace llvm {
+
+struct NewArchiveMember;
+
+namespace object {
+
+class Archive;
+
+} // end namespace object
+
+namespace objcopy {
+struct CopyConfig;
+Expected<std::vector<NewArchiveMember>>
+createNewArchiveMembers(CopyConfig &Config, const object::Archive &Ar);
+
+} // end namespace objcopy
+} // end namespace llvm
+
+#endif // LLVM_TOOLS_OBJCOPY_OBJCOPY_H