From 78976bf3dae2a4fac3b7fb2ab1a8d8e986ea36ff Mon Sep 17 00:00:00 2001
From: Jez Ng <jezng@fb.com>
Date: Wed, 2 Dec 2020 14:12:51 -0800
Subject: [PATCH] [lld-macho] Support parsing of bitcode within archives

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.

Reviewed By: thakis

Differential Revision: https://reviews.llvm.org/D92539
---
 lld/MachO/InputFiles.cpp                    | 21 ++++++++++++++++-----
 lld/test/MachO/bitcode-nodatalayout.ll      | 13 +++++++++++++
 lld/test/MachO/invalid/bad-archive-member.s | 20 ++++++++++++++++++++
 lld/test/MachO/lto-archive.ll               | 28 ++++++++++++++++++++++++++++
 4 files changed, 77 insertions(+), 5 deletions(-)
 create mode 100644 lld/test/MachO/bitcode-nodatalayout.ll
 create mode 100644 lld/test/MachO/invalid/bad-archive-member.s
 create mode 100644 lld/test/MachO/lto-archive.ll

diff --git a/lld/MachO/InputFiles.cpp b/lld/MachO/InputFiles.cpp
index 2460009..c452648 100644
--- a/lld/MachO/InputFiles.cpp
+++ b/lld/MachO/InputFiles.cpp
@@ -631,15 +631,26 @@ void ArchiveFile::fetch(const object::Archive::Symbol &sym) {
   // 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)
diff --git a/lld/test/MachO/bitcode-nodatalayout.ll b/lld/test/MachO/bitcode-nodatalayout.ll
new file mode 100644
index 0000000..5e1c43c
--- /dev/null
+++ b/lld/test/MachO/bitcode-nodatalayout.ll
@@ -0,0 +1,13 @@
+; 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
+}
diff --git a/lld/test/MachO/invalid/bad-archive-member.s b/lld/test/MachO/invalid/bad-archive-member.s
new file mode 100644
index 0000000..15ab524
--- /dev/null
+++ b/lld/test/MachO/invalid/bad-archive-member.s
@@ -0,0 +1,20 @@
+# 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
diff --git a/lld/test/MachO/lto-archive.ll b/lld/test/MachO/lto-archive.ll
new file mode 100644
index 0000000..42b2c0f
--- /dev/null
+++ b/lld/test/MachO/lto-archive.ll
@@ -0,0 +1,28 @@
+; 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
-- 
2.7.4