[LTO][Legacy] Add new API to query Mach-O CPU (sub)type

[thegameg]

Summary

Tools working with object files on Darwin (e.g. lipo) may need to know properties like the CPU type and subtype of a bitcode file. The logic of converting a triple to a Mach-O CPU_(SUB_)TYPE should be provided by LLVM instead of relying on tools to re-implement it.

[dexonsmith]

@thegameg , tests are usually done through the llvm-lto or llvm-lto2 tools.

[thegameg]

Add test through llvm-lto. More extensive testing of the BinaryFormat logic was added in https://reviews.llvm.org/rG7b0a5683fa09be4e60bc93526aad7b63bbca687c.

llvm/docs/LinkTimeOptimization.rst

 .. code-block:: c
 
   lto_module_get_num_symbols(lto_module_t)
   lto_module_get_symbol_name(lto_module_t, unsigned int)
   lto_module_get_symbol_attribute(lto_module_t, unsigned int)
 
 The attributes of a symbol include the alignment, visibility, and kind.
 
+Tools working with object files on Darwin (e.g. lipo) may need to know properties like the CPU type:
+
+.. code-block:: c
+
+  lto_module_get_macho_cputype(lto_module_t mod, unsigned int *out_cputype, unsigned int *out_cpusubtype)
+
 ``lto_code_gen_t``
 ------------------
 
 Once the linker has loaded each non-native object files into an
 ``lto_module_t``, it can request ``libLTO`` to process them all and generate a
 native object file. This is done in a couple of steps. First, a code generator
 is created with:
 

llvm/include/llvm-c/lto.h

 
 /**
  * @defgroup LLVMCLTO LTO
  * @ingroup LLVMC
  *
  * @{
  */
 
-#define LTO_API_VERSION 26
+#define LTO_API_VERSION 27
 
 /**
  * \since prior to LTO_API_VERSION=3
  */
 typedef enum {
     LTO_SYMBOL_ALIGNMENT_MASK              = 0x0000001F, /* log2 of alignment */
     LTO_SYMBOL_PERMISSIONS_MASK            = 0x000000E0,
     LTO_SYMBOL_PERMISSIONS_CODE            = 0x000000A0,

  * responsibility to split the flags using a platform-specific mechanism.
  *
  * \since LTO_API_VERSION=16
  */
 extern const char*
 lto_module_get_linkeropts(lto_module_t mod);
 
 /**
+ * If targeting mach-o on darwin, this function gets the CPU type and subtype
+ * that will end up being encoded in the mach-o header. These are the values
+ * that can be found in mach/machine.h.
+ *
+ * \p out_cputype and \p out_cpusubtype must be non-NULL.
+ *
+ * Returns true on error (check lto_get_error_message() for details).
+ *
+ * \since LTO_API_VERSION=27
+ */
+extern lto_bool_t lto_module_get_macho_cputype(lto_module_t mod,
+                                               unsigned int *out_cputype,
+                                               unsigned int *out_cpusubtype);
+
+/**
  * Diagnostic severity.
  *
  * \since LTO_API_VERSION=7
  */
 typedef enum {
   LTO_DS_ERROR = 0,
   LTO_DS_WARNING = 1,
   LTO_DS_REMARK = 3, // Added in LTO_API_VERSION=10.

llvm/include/llvm/LTO/legacy/LTOModule.h

public:
 
   static lto::InputFile *createInputFile(const void *buffer, size_t buffer_size,
                                          const char *path, std::string &out_error);
 
   static size_t getDependentLibraryCount(lto::InputFile *input);
 
   static const char *getDependentLibrary(lto::InputFile *input, size_t index, size_t *size);
 
+  Expected<uint32_t> getMachOCPUType() const;
+
+  Expected<uint32_t> getMachOCPUSubType() const;
+
 private:
   /// Parse metadata from the module
   // FIXME: it only parses "llvm.linker.options" metadata at the moment
   // FIXME: can't access metadata in lazily loaded modules
   void parseMetadata();
 
   /// Parse the symbols from the module and model-level ASM and add them to
   /// either the defined or undefined lists.

llvm/lib/LTO/LTOModule.cpp

 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
 #include "llvm/MC/MCSection.h"
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/MC/SubtargetFeature.h"
 #include "llvm/Object/IRObjectFile.h"
+#include "llvm/Object/MachO.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Host.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/TargetSelect.h"

 }
 
 const char *LTOModule::getDependentLibrary(lto::InputFile *input, size_t index,
                                            size_t *size) {
   StringRef S = input->getDependentLibraries()[index];
   *size = S.size();
   return S.data();
 }
+
+Expected<uint32_t> LTOModule::getMachOCPUType() const {
+  return MachO::getCPUType(Triple(Mod->getTargetTriple()));
+}
+
+Expected<uint32_t> LTOModule::getMachOCPUSubType() const {
+  return MachO::getCPUSubType(Triple(Mod->getTargetTriple()));
+}

llvm/test/LTO/X86/print-macho-cpu.ll

+; RUN: rm -rf %t && mkdir -p %t
+; RUN: llvm-as -o %t/1.bc %s
+; RUN: llvm-lto -print-macho-cpu-only %t/1.bc | FileCheck %s
+
+target triple = "x86_64-apple-darwin"
+; CHECK: 1.bc:
+; CHECK-NEXT: cputype: 16777223
+; CHECK-NEXT: cpusubtype: 3

llvm/test/tools/llvm-lto/error.ll

 ; RUN: not llvm-lto foobar 2>&1 | FileCheck %s
 ; CHECK: llvm-lto: error loading file 'foobar': {{N|n}}o such file or directory
 
 ; RUN: not llvm-lto --list-symbols-only %S/Inputs/empty.bc 2>&1 | FileCheck %s --check-prefix=CHECK-LIST
 ; CHECK-LIST: llvm-lto: error loading file '{{.*}}/Inputs/empty.bc': The file was not recognized as a valid object file
 
 ; RUN: not llvm-lto --list-dependent-libraries-only %S/Inputs/empty.bc 2>&1 | FileCheck %s --check-prefix=CHECK-LIBS
 ; CHECK-LIBS: llvm-lto: {{.*}}/Inputs/empty.bc: Could not read LTO input file: The file was not recognized as a valid object file
 
+; RUN: not llvm-lto --print-macho-cpu-only %S/Inputs/empty.bc 2>&1 | FileCheck %s --check-prefix=CHECK-MACHO
+; CHECK-MACHO: llvm-lto: error: The file was not recognized as a valid object file
+
 ; RUN: not llvm-lto --thinlto %S/Inputs/empty.bc 2>&1 | FileCheck %s --check-prefix=CHECK-THIN
 ; CHECK-THIN: llvm-lto: error loading file '{{.*}}/Inputs/empty.bc': file too small to contain bitcode header

llvm/tools/llvm-lto/llvm-lto.cpp

 static cl::opt<bool> RestoreGlobalsLinkage(
     "restore-linkage", cl::init(false),
     cl::desc("Restore original linkage of globals prior to CodeGen"));
 
 static cl::opt<bool> CheckHasObjC(
     "check-for-objc", cl::init(false),
     cl::desc("Only check if the module has objective-C defined in it"));
 
+static cl::opt<bool> PrintMachOCPUOnly(
+    "print-macho-cpu-only", cl::init(false),
+    cl::desc("Instead of running LTO, print the mach-o cpu in each IR file"));
+
 namespace {
 
 struct ModuleInfo {
   std::vector<bool> CanBeHidden;
 };
 
 } // end anonymous namespace
 
for (size_t I = 0, C = LTOModule::getDependentLibraryCount(Input.get());
       size_t L = 0;
       const char *S = LTOModule::getDependentLibrary(Input.get(), I, &L);
       assert(S);
       outs() << StringRef(S, L) << "\n";
     }
   }
 }
 
+static void printMachOCPUOnly() {
+  LLVMContext Context;
+  Context.setDiagnosticHandler(std::make_unique<LLVMLTODiagnosticHandler>(),
+                               true);
+  TargetOptions Options = InitTargetOptionsFromCodeGenFlags();
+  for (auto &Filename : InputFilenames) {
+    ErrorOr<std::unique_ptr<LTOModule>> ModuleOrErr =
+        LTOModule::createFromFile(Context, Filename, Options);
+    if (!ModuleOrErr)
+      error(ModuleOrErr, "llvm-lto: ");
+
+    Expected<uint32_t> CPUType = (*ModuleOrErr)->getMachOCPUType();
+    Expected<uint32_t> CPUSubType = (*ModuleOrErr)->getMachOCPUSubType();
+    if (!CPUType)
+      error("Error while printing mach-o cputype: " +
+            toString(CPUType.takeError()));
+    if (!CPUSubType)
+      error("Error while printing mach-o cpusubtype: " +
+            toString(CPUSubType.takeError()));
+    outs() << llvm::format("%s:\ncputype: %u\ncpusubtype: %u\n",
+                           Filename.c_str(), *CPUType, *CPUSubType);
+  }
+}
+
 /// Create a combined index file from the input IR files and write it.
 ///
 /// This is meant to enable testing of ThinLTO combined index generation,
 /// currently available via the gold plugin via -thinlto.
 static void createCombinedModuleSummaryIndex() {
   ModuleSummaryIndex CombinedIndex(/*HaveGVs=*/false);
   uint64_t NextModuleId = 0;
   for (auto &Filename : InputFilenames) {
for (auto &Filename : InputFilenames) {
       if (ExitOnErr(isBitcodeContainingObjCCategory(*Buffer)))
         outs() << "Bitcode " << Filename << " contains ObjC\n";
       else
         outs() << "Bitcode " << Filename << " does not contain ObjC\n";
     }
     return 0;
   }
 
+  if (PrintMachOCPUOnly) {
+    printMachOCPUOnly();
+    return 0;
+  }
+
   if (ThinLTOMode.getNumOccurrences()) {
     if (ThinLTOMode.getNumOccurrences() > 1)
       report_fatal_error("You can't specify more than one -thinlto-action");
     thinlto::ThinLTOProcessing ThinLTOProcessor(Options);
     ThinLTOProcessor.run();
     return 0;
   }
 

llvm/tools/lto/lto.cpp

lto_symbol_attributes lto_module_get_symbol_attribute(lto_module_t mod,
                                                       unsigned int index) {
   return unwrap(mod)->getSymbolAttributes(index);
 }
 
 const char* lto_module_get_linkeropts(lto_module_t mod) {
   return unwrap(mod)->getLinkerOpts().data();
 }
 
+lto_bool_t lto_module_get_macho_cputype(lto_module_t mod,
+                                        unsigned int *out_cputype,
+                                        unsigned int *out_cpusubtype) {
+  LTOModule *M = unwrap(mod);
+  Expected<uint32_t> CPUType = M->getMachOCPUType();
+  if (!CPUType) {
+    sLastErrorString = toString(CPUType.takeError());
+    return true;
+  }
+  *out_cputype = *CPUType;
+
+  Expected<uint32_t> CPUSubType = M->getMachOCPUSubType();
+  if (!CPUSubType) {
+    sLastErrorString = toString(CPUSubType.takeError());
+    return true;
+  }
+  *out_cpusubtype = *CPUSubType;
+
+  return false;
+}
+
 void lto_codegen_set_diagnostic_handler(lto_code_gen_t cg,
                                         lto_diagnostic_handler_t diag_handler,
                                         void *ctxt) {
   unwrap(cg)->setDiagnosticHandler(diag_handler, ctxt);
 }
 
 static lto_code_gen_t createCodeGen(bool InLocalContext) {
   lto_initialize();

llvm/tools/lto/lto.exports

 lto_get_error_message
 lto_get_version
 lto_initialize_disassembler
 lto_module_create
 lto_module_create_from_fd
 lto_module_create_from_fd_at_offset
 lto_module_create_from_memory
 lto_module_create_from_memory_with_path
 lto_module_create_in_local_context
 lto_module_create_in_codegen_context
 lto_module_get_linkeropts
+lto_module_get_macho_cputype
 lto_module_get_num_symbols
 lto_module_get_symbol_attribute
 lto_module_get_symbol_name
 lto_module_get_target_triple
 lto_module_set_target_triple
 lto_module_is_object_file
 lto_module_is_object_file_for_target
 lto_module_is_object_file_in_memory