[lld-macho] Check for arch compatibility when loading ObjFiles and TBDs

[int3]

Summary

The silent failures had confused me a few times.

I haven't added a similar check for platform yet as we don't yet have logic to
infer the platform automatically, and so adding that check would require
updating dozens of test files.

[int3]

update test

[thakis]

ELF and COFF do this a bit earlier, COFF in SymbolTable::addFile() which has the nicer diag I suggest below -- but otherwise I don't like the COFF approach much, since it parses the whole InputFile, which adds its symbols, and only after that it checks the arch. Checking the arch first and returning early if it doens't match, like this does, seems better. ELF does it in doParseFile(), with a similar timing to this patch. Maybe we could make it look a bit more like the ELF port, to keep the different lld ports consistent in parts where they don't need to be different?

lld/MachO/InputFiles.cpp

481

should the diag mention the arch of the source file too? "file has architecture x86 which is incompatible with output architecture x64" or similar?

[int3]

Maybe we could make it look a bit more like the ELF port, to keep the different lld ports consistent in parts where they don't need to be different?

Yup, that's the plan :) I'll tackle that when I add support for arch inference: https://bugs.llvm.org/show_bug.cgi?id=49277

[int3]

print file arch in error message

[DavidSpickett]

Hi. (in case you didn't know already) This is failing on one of our bots:
http://lab.llvm.org:8011/#/builders/53/builds/1386

This bot only enables ARM and AArch64 targets so I think you need a "REQUIRES" line for the new tests, like lld/test/MachO/header.s has.

[int3]

Thanks for the heads up, just pushed rG9ced8b3b614c.

lld/MachO/InputFiles.cpp

 #include "lld/Common/Reproduce.h"
 #include "llvm/ADT/iterator.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/TarWriter.h"
+#include "llvm/TextAPI/MachO/Architecture.h"
 
 using namespace llvm;
 using namespace llvm::MachO;
 using namespace llvm::support::endian;
 using namespace llvm::sys;
 using namespace lld;
 using namespace lld::macho;
 

 
 ObjFile::ObjFile(MemoryBufferRef mb, uint32_t modTime, StringRef archiveName)
     : InputFile(ObjKind, mb), modTime(modTime) {
   this->archiveName = std::string(archiveName);
 
   auto *buf = reinterpret_cast<const uint8_t *>(mb.getBufferStart());
   auto *hdr = reinterpret_cast<const mach_header_64 *>(mb.getBufferStart());
 
+  MachO::Architecture arch =
+      MachO::getArchitectureFromCpuType(hdr->cputype, hdr->cpusubtype);
+  if (arch != config->arch) {
+    error(toString(this) + " has architecture " + getArchitectureName(arch) +
+          " which is incompatible with target architecture " +
+          getArchitectureName(config->arch));
+    return;
+  }
+
   if (const load_command *cmd = findCommand(hdr, LC_LINKER_OPTION)) {
     auto *c = reinterpret_cast<const linker_option_command *>(cmd);
     StringRef data{reinterpret_cast<const char *>(c + 1),
                    c->cmdsize - sizeof(linker_option_command)};
     parseLCLinkerOption(this, c->count, data);
   }
 
   if (const load_command *cmd = findCommand(hdr, LC_SEGMENT_64)) {
DylibFile::DylibFile(const InterfaceFile &interface, DylibFile *umbrella,
                      bool isBundleLoader)
     : InputFile(DylibKind, interface), refState(RefState::Unreferenced),
       isBundleLoader(isBundleLoader) {
   // FIXME: Add test for the missing TBD code path.
 
   if (umbrella == nullptr)
     umbrella = this;
 
+  if (!interface.getArchitectures().has(config->arch)) {
+    error(toString(this) + " is incompatible with " +
+          getArchitectureName(config->arch));
+    return;
+  }
+
   dylibName = saver.save(interface.getInstallName());
   compatibilityVersion = interface.getCompatibilityVersion().rawValue();
   currentVersion = interface.getCurrentVersion().rawValue();
   DylibFile *exportingFile = isImplicitlyLinked(dylibName) ? this : umbrella;
   auto addSymbol = [&](const Twine &name) -> void {
     symbols.push_back(symtab->addDylib(saver.save(name), exportingFile,
                                        /*isWeakDef=*/false,
                                        /*isTlv=*/false));

lld/test/MachO/Inputs/MacOSX.sdk/usr/lib/libc++.tbd

 --- !tapi-tbd-v3
-archs:            [ i386, x86_64 ]
+archs:            [ i386, x86_64, arm64 ]
 uuids:            [ 'i386: 00000000-0000-0000-0000-000000000000', 'x86_64: 00000000-0000-0000-0000-000000000001', 'arm64: 00000000-0000-0000-0000-000000000002' ]
 platform:         macosx
 install-name:     '/usr/lib/libc++.dylib'
 current-version:  1281
 exports:
   - archs:        [ i386, x86_64, arm64 ]
     re-exports:   [ '/usr/lib/libc++abi.dylib' ]
 ...

lld/test/MachO/header.s

 # REQUIRES: x86, arm
 # RUN: rm -rf %t && mkdir -p %t
-# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t/test.o
-# RUN: %lld -arch x86_64 -platform_version macos 10.5.0 11.0 -o %t/x86-64-executable %t/test.o
-# RUN: %lld -arch arm64 -o %t/arm64-executable %t/test.o
-# RUN: %lld -arch x86_64 -dylib -o %t/x86-64-dylib %t/test.o
-# RUN: %lld -arch arm64  -dylib -o %t/arm64-dylib %t/test.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t/x86_64-test.o
+# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t/arm64-test.o
+# RUN: %lld -arch x86_64 -platform_version macos 10.5.0 11.0 -o %t/x86-64-executable %t/x86_64-test.o
+# RUN: %lld -arch arm64 -o %t/arm64-executable %t/arm64-test.o
+# RUN: %lld -arch x86_64 -dylib -o %t/x86-64-dylib %t/x86_64-test.o
+# RUN: %lld -arch arm64  -dylib -o %t/arm64-dylib %t/arm64-test.o
 
 # RUN: llvm-objdump --macho --all-headers %t/x86-64-executable | FileCheck %s -DCAPS=LIB64
 # RUN: llvm-objdump --macho --all-headers %t/arm64-executable | FileCheck %s -DCAPS=0x00
 # RUN: llvm-objdump --macho --all-headers %t/x86-64-dylib | FileCheck %s -DCAPS=0x00
 # RUN: llvm-objdump --macho --all-headers %t/arm64-dylib | FileCheck %s -DCAPS=0x00
 
 # CHECK:      magic        cputype cpusubtype  caps    filetype
 # CHECK-NEXT: MH_MAGIC_64  {{.*}}         ALL  [[CAPS]]   {{.*}}
 
 .globl _main
 _main:
   ret

lld/test/MachO/invalid/Inputs/libincompatible.tbd

+--- !tapi-tbd-v3
+archs:            [ arm64 ]
+uuids:            [ 'arm64: 00000000-0000-0000-0000-000000000000' ]
+platform:         macosx
+install-name:     '/usr/lib/libincompatible.dylib'
+current-version:  0001.001.1
+exports:
+  - archs:        [ 'x86_64', 'arm64' ]
+    symbols:      [ ]

lld/test/MachO/invalid/incompatible-arch-tapi.s

+# RUN: rm -rf %t; split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-macosx %t/main.s -o %t/main.o
+# RUN: not %lld -arch x86_64 -lSystem %S/Inputs/libincompatible.tbd %t/main.o -o /dev/null 2>&1 | FileCheck %s --check-prefix=ARCH
+# ARCH: error: {{.*}}libincompatible.tbd is incompatible with x86_64
+
+#--- main.s
+.globl _main
+_main:
+  ret

lld/test/MachO/invalid/incompatible-arch.s

+# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t.o
+# RUN: not %lld -arch x86_64 -lSystem %t.o -o /dev/null 2>&1 | FileCheck %s -DFILE=%t.o
+# CHECK: error: {{.*}}[[FILE]] has architecture arm64 which is incompatible with target architecture x86_64
+
+.globl _main
+_main:
+  ret