[lld-macho] Allow linking with ABI compatible architectures

[thevinster]

Summary

Linking fails when targeting x86_64-apple-darwin for runtimes. The issue
is that LLD strictly assumes the target architecture be present in the tbd
files (which isn't always true). For example, when targeting x86_64h, it should
work with x86_64 because they are ABI compatible. This is also inline with what
ld64 does.

An environment variable (which ld64 also supports) is also added to preserve the
existing behavior of strict architecture matching.

[thevinster]

clang-format

[int3]

lgtm

lld/MachO/InputFiles.cpp

1876–1880

1895–1896

we can move this to line 1888 I think? doesn't seem like computing archSet is necessary if forceExactCpuSubtypeMatch == true

lld/MachO/Config.h

struct Configuration {
   bool emitDataInCodeInfo = false;
   bool emitEncryptionInfo = false;
   bool timeTraceEnabled = false;
   bool dataConst = false;
   bool dedupLiterals = true;
   bool omitDebugInfo = false;
   bool warnDylibInstallName = false;
   bool ignoreOptimizationHints = false;
+  bool forceExactCpuSubtypeMatch = false;
   uint32_t headerPad;
   uint32_t dylibCompatibilityVersion = 0;
   uint32_t dylibCurrentVersion = 0;
   uint32_t timeTraceGranularity = 500;
   unsigned optimize;
   std::string progName;
 
   // For `clang -arch arm64 -arch x86_64`, clang will:

lld/MachO/Driver.cpp

config->dedupLiterals =
       args.hasFlag(OPT_deduplicate_literals, OPT_icf_eq, false) ||
       config->icfLevel != ICFLevel::none;
   config->warnDylibInstallName = args.hasFlag(
       OPT_warn_dylib_install_name, OPT_no_warn_dylib_install_name, false);
   config->ignoreOptimizationHints = args.hasArg(OPT_ignore_optimization_hints);
   config->callGraphProfileSort = args.hasFlag(
       OPT_call_graph_profile_sort, OPT_no_call_graph_profile_sort, true);
   config->printSymbolOrder = args.getLastArgValue(OPT_print_symbol_order);
+  config->forceExactCpuSubtypeMatch = getenv("LD_DYLIB_CPU_SUBTYPES_MUST_MATCH");
 
   for (const Arg *arg : args.filtered(OPT_alias)) {
     config->aliasedSymbols.push_back(
         std::make_pair(arg->getValue(0), arg->getValue(1)));
   }
 
   // FIXME: Add a commandline flag for this too.
   config->zeroModTime = getenv("ZERO_AR_DATE");

lld/MachO/InputFiles.cpp

template <class LP> void ObjFile::parse() {
   using Header = typename LP::mach_header;
   using SegmentCommand = typename LP::segment_command;
   using SectionHeader = typename LP::section;
   using NList = typename LP::nlist;
 
   auto *buf = reinterpret_cast<const uint8_t *>(mb.getBufferStart());
   auto *hdr = reinterpret_cast<const Header *>(mb.getBufferStart());
 
+  uint32_t cpuType;
+  std::tie(cpuType, std::ignore) = getCPUTypeFromArchitecture(config->arch());
+  if (hdr->cputype != cpuType) {
     Architecture arch = getArchitectureFromCpuType(hdr->cputype, hdr->cpusubtype);
-  if (arch != config->arch()) {
     auto msg = config->errorForArchMismatch
                    ? static_cast<void (*)(const Twine &)>(error)
                    : warn;
     msg(toString(this) + " has architecture " + getArchitectureName(arch) +
         " which is incompatible with target architecture " +
         getArchitectureName(config->arch()));
     return;
   }
static bool skipPlatformCheckForCatalyst(const InterfaceFile &interface,
                                          bool explicitlyLinked) {
   // Catalyst outputs can link against implicitly linked macOS-only libraries.
   if (config->platform() != PLATFORM_MACCATALYST || explicitlyLinked)
     return false;
   return is_contained(interface.targets(),
                       MachO::Target(config->arch(), PLATFORM_MACOS));
 }
 
+static bool isArchABICompatible(ArchitectureSet archSet, Architecture targetArch) {
+  uint32_t cpuType;
+  uint32_t targetCpuType;
+  std::tie(targetCpuType, std::ignore) = getCPUTypeFromArchitecture(targetArch);
+
+  auto it = llvm::find_if(archSet, [&](const auto &p) {
+    std::tie(cpuType, std::ignore) = getCPUTypeFromArchitecture(p);
+    return cpuType == targetCpuType;
+  });
+  return it != archSet.end();
+}
+
+static bool isTargetPlatformArchCompatible(InterfaceFile::const_target_range interfaceTargets, Target target) {
+  if (is_contained(interfaceTargets, target))
+    return true;
+
+  ArchitectureSet archSet;
+  for (const auto &p : interfaceTargets)
+    if (p.Platform == target.Platform)
+      archSet.set(p.Arch);
+  if (archSet.empty())
+    return false;
+
+  if (config->forceExactCpuSubtypeMatch)
+    return false;
+
+  return isArchABICompatible(archSet, target.Arch);
+}
+
 DylibFile::DylibFile(const InterfaceFile &interface, DylibFile *umbrella,
                      bool isBundleLoader, bool explicitlyLinked)
     : InputFile(DylibKind, interface), refState(RefState::Unreferenced),
       explicitlyLinked(explicitlyLinked), isBundleLoader(isBundleLoader) {
   // FIXME: Add test for the missing TBD code path.
 
   if (umbrella == nullptr)
     umbrella = this;
   this->umbrella = umbrella;
 
   installName = saver().save(interface.getInstallName());
   compatibilityVersion = interface.getCompatibilityVersion().rawValue();
   currentVersion = interface.getCurrentVersion().rawValue();
 
   if (config->printEachFile)
     message(toString(this));
   inputFiles.insert(this);
 
   if (!is_contained(skipPlatformChecks, installName) &&
-      !is_contained(interface.targets(), config->platformInfo.target) &&
+      !isTargetPlatformArchCompatible(interface.targets(), config->platformInfo.target) &&
       !skipPlatformCheckForCatalyst(interface, explicitlyLinked)) {
     error(toString(this) + " is incompatible with " +
           std::string(config->platformInfo.target));
     return;
   }
 
   checkAppExtensionSafety(interface.isApplicationExtensionSafe());
 
   exportingFile = isImplicitlyLinked(installName) ? this : umbrella;
   auto addSymbol = [&](const Twine &name) -> void {
     StringRef savedName = saver().save(name);
     if (exportingFile->hiddenSymbols.contains(CachedHashStringRef(savedName)))
       return;
 
     symbols.push_back(symtab->addDylib(savedName, exportingFile,
                                        /*isWeakDef=*/false,
                                        /*isTlv=*/false));
   };
 
   std::vector<const llvm::MachO::Symbol *> normalSymbols;
   normalSymbols.reserve(interface.symbolsCount());
   for (const auto *symbol : interface.symbols()) {
-    if (!symbol->getArchitectures().has(config->arch()))
+    if (!isArchABICompatible(symbol->getArchitectures(), config->arch()))
        continue;
     if (handleLDSymbol(symbol->getName()))
       continue;
 
     switch (symbol->getKind()) {
     case SymbolKind::GlobalSymbol:               // Fallthrough
     case SymbolKind::ObjectiveCClass:            // Fallthrough
     case SymbolKind::ObjectiveCClassEHType:      // Fallthrough
     case SymbolKind::ObjectiveCInstanceVariable: // Fallthrough

 }
 
 void DylibFile::parseReexports(const InterfaceFile &interface) {
   const InterfaceFile *topLevel =
       interface.getParent() == nullptr ? &interface : interface.getParent();
   for (const InterfaceFileRef &intfRef : interface.reexportedLibraries()) {
     InterfaceFile::const_target_range targets = intfRef.targets();
     if (is_contained(skipPlatformChecks, intfRef.getInstallName()) ||
-        is_contained(targets, config->platformInfo.target))
+        isTargetPlatformArchCompatible(targets, config->platformInfo.target))
       loadReexport(intfRef.getInstallName(), exportingFile, topLevel);
   }
 }
 
 // $ld$ symbols modify the properties/behavior of the library (e.g. its install
 // name, compatibility version or hide/add symbols) for specific target
 // versions.
 bool DylibFile::handleLDSymbol(StringRef originalName) {

lld/test/MachO/tapi-link.s

 # REQUIRES: x86
 
 # RUN: split-file %s %t --no-leading-lines
 
 # RUN: llvm-mc -filetype obj -triple x86_64-apple-darwin %t/test.s -o %t/test.o
 
 # RUN: %lld -o %t/test -lSystem -lc++ -framework CoreFoundation %t/libNested.tbd %t/test.o
 # RUN: llvm-objdump --bind --no-show-raw-insn -d -r %t/test | FileCheck %s
 
+## Targeting an arch not listed in the tbd should fallback to an ABI compatible arch
+# RUN: %lld -arch x86_64h -o %t/test-compat -lSystem -lc++ -framework CoreFoundation %t/libNested.tbd %t/test.o
+# RUN: llvm-objdump --bind --no-show-raw-insn -d -r %t/test-compat | FileCheck %s
+
+## Setting LD_DYLIB_CPU_SUBTYPES_MUST_MATCH forces exact target arch match.
+# RUN: env LD_DYLIB_CPU_SUBTYPES_MUST_MATCH=1 not %lld -arch x86_64h -o /dev/null -lSystem -lc++ -framework \
+# RUN:   CoreFoundation %t/libNested.tbd %t/test.o 2>&1 | FileCheck %s -check-prefix=INCOMPATIBLE
+
+# INCOMPATIBLE:      error: {{.*}}libSystem.tbd(/usr/lib/libSystem.dylib) is incompatible with x86_64h (macOS)
+# INCOMPATIBLE-NEXT: error: {{.*}}libc++.tbd(/usr/lib/libc++.dylib) is incompatible with x86_64h (macOS)
+# INCOMPATIBLE-NEXT: error: {{.*}}CoreFoundation.tbd(/System/Library/Frameworks/CoreFoundation.framework/CoreFoundation) is incompatible with x86_64h (macOS)
+
 ## libReexportSystem.tbd tests that we can reference symbols from a 2nd-level
 ## tapi document, re-exported by a top-level tapi document, which itself is
 ## re-exported by another top-level tapi document.
 # RUN: %lld -o %t/with-reexport -lSystem -L%t %t/libReexportNested.tbd -lc++ -framework CoreFoundation %t/test.o
 # RUN: llvm-objdump --bind --no-show-raw-insn -d -r %t/with-reexport | FileCheck %s
 
 # CHECK: Bind table:
 # CHECK-DAG: __DATA __data {{.*}} pointer 0 CoreFoundation _OBJC_CLASS_$_NSObject