[lld-macho] Support parsing of bitcode within archives

[int3]

Summary

Also error out if we find anything other than an object or bitcode file
in the archive.

Note that we were previously inserting the symbols and sections of the
unpacked ObjFile into the containing ArchiveFile. This was actually
unnecessary -- we can just insert the ObjectFile (or BitcodeFile) into
the inputFiles vector. This is the approach taken by LLD-ELF.

[int3]

update

[thakis]

Conceptually lg, but I think it'd be good if we try to keep the various ports looking alike (in this case, probably like COFF/InputFiles.cpp).

lld/MachO/InputFiles.cpp

654

nit: other ports have a isBitcode() in InputFiles.h instead and call that here and assume obj if that returns false

[int3]

lld/MachO/InputFiles.cpp

654

Isn't it better to have more precise error handling though?

lld/MachO/InputFiles.cpp

uint32_t modTime = toTimeT(
                                      "for the member defining symbol " +
                                      toMachOString(sym)));
 
   // `sym` is owned by a LazySym, which will be replace<>() by make<ObjFile>
   // and become invalid after that call. Copy it to the stack so we can refer
   // to it later.
   const object::Archive::Symbol sym_copy = sym;
 
-  auto file = make<ObjFile>(mb, modTime, getName());
+  InputFile *file;
+  switch (identify_magic(mb.getBuffer())) {
+  case file_magic::macho_object:
+    file = make<ObjFile>(mb, modTime, getName());
+    break;
+  case file_magic::bitcode:
+    file = make<BitcodeFile>(mb);
+    break;
+  default:
+    StringRef bufname =
+        CHECK(c.getName(), toString(this) + ": could not get buffer name");
+    error(toString(this) + ": archive member " + bufname +
+          " has unhandled file type");
+    return;
+  }
+  inputFiles.push_back(file);
 
   // ld64 doesn't demangle sym here even with -demangle. Match that, so
   // intentionally no call to toMachOString() here.
   printArchiveMemberLoad(sym_copy.getName(), file);
-
-  symbols.insert(symbols.end(), file->symbols.begin(), file->symbols.end());
-  subsections.insert(subsections.end(), file->subsections.begin(),
-                     file->subsections.end());
 }
 
 BitcodeFile::BitcodeFile(MemoryBufferRef mbref)
     : InputFile(BitcodeKind, mbref) {
   obj = check(lto::InputFile::create(mbref));
 }

lld/test/MachO/bitcode-nodatalayout.ll

+; REQUIRES: x86
+; RUN: llvm-as %s -o %t.o
+; RUN: not %lld %t.o -o /dev/null 2>&1 | FileCheck %s
+
+; CHECK: error: input module has no datalayout
+
+; This bitcode file has no datalayout.
+; Check that we error out producing a reasonable diagnostic.
+target triple = "x86_64-apple-macosx10.15.0"
+
+define void @_start() {
+  ret void
+}

lld/test/MachO/invalid/bad-archive-member.s

+# REQUIRES: x86
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/foo.s -o %t/foo.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/test.s -o %t/test.o
+# RUN: %lld -dylib -lSystem %t/foo.o -o %t/foo.dylib
+# RUN: rm -f %t/foo.a
+# RUN: llvm-ar rcs %t/foo.a %t/foo.dylib
+# RUN: not %lld %t/test.o %t/foo.a -o /dev/null 2>&1 | FileCheck %s -DFILE=%t/foo.a
+# CHECK: error: [[FILE]]: archive member foo.dylib has unhandled file type
+
+#--- foo.s
+.globl _foo
+_foo:
+  ret
+
+#--- test.s
+.globl _main
+_main:
+  callq _foo
+  ret

lld/test/MachO/lto-archive.ll

+; REQUIRES: x86
+; RUN: split-file %s %t
+; RUN: llvm-as %t/foo.ll -o %t/foo.o
+; RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/test.s -o %t/test.o
+; RUN: rm -f %t/foo.a
+; RUN: llvm-ar rcs %t/foo.a %t/foo.o
+; RUN: %lld -save-temps -lSystem %t/test.o %t/foo.a -o %t/test
+; RUN: llvm-objdump -d --macho --no-show-raw-insn %t/test | FileCheck %s
+
+; CHECK:      _main:
+; CHECK-NEXT: callq _foo
+; CHECK-NEXT: retq
+
+;--- foo.ll
+
+target triple = "x86_64-apple-macosx10.15.0"
+target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @foo() {
+  ret void
+}
+
+;--- test.s
+
+.globl _main
+_main:
+  callq _foo
+  ret