[lld-macho] Add support for -mcpu, -mattr, -code-model in LTO

[int3]

Summary

-mcpu and -code-model tests were copied from similar ones in
LLD-ELF.

There doesn't seem to be an equivalent test for -mattr in LLD-ELF, so
I've verified our behavior by cribbing a test from
CodeGen/X86/recip-fastmath.ll.

[compnerd]

I wonder if there is a good way to enumerate the desired set of options (e.g. -O is currently missing), but I don't think that there have been too many attempts to flesh out the argument handling, so we can hold off on that until we find that we have had to do this a few times.

[MaskRay]

Maybe time to add lto/ or use the lto- prefix?

[int3]

Maybe time to add lto/ or use the lto- prefix?

I think the .ll extension is pretty much only used for LTO test cases, so it seems a bit redundant to add another prefix...

I wonder if there is a good way to enumerate the desired set of options

I don't understand what you mean by "enumerate" here... could you elaborate?

[int3]

merge other LTO diffs

[thakis]

Looks like this breaks tests on mac and windows: http://45.33.8.238/mac/25017/step_10.txt

[thakis]

Win log: http://45.33.8.238/win/29622/step_10.txt

[int3]

Looking

lld/MachO/Driver.cpp

static bool isPie(opt::InputArgList &args) {
 
   if (config->platform.kind == MachO::PlatformKind::macOS &&
       config->platform.minimum >= VersionTuple(10, 6))
     return true;
 
   return args.hasArg(OPT_pie);
 }
 
+static void parseClangOption(StringRef opt, const Twine &msg) {
+  std::string err;
+  raw_string_ostream os(err);
+
+  const char *argv[] = {"lld", opt.data()};
+  if (cl::ParseCommandLineOptions(2, argv, "", &os))
+    return;
+  os.flush();
+  error(msg + ": " + StringRef(err).trim());
+}
+
 bool macho::link(llvm::ArrayRef<const char *> argsArr, bool canExitEarly,
                  raw_ostream &stdoutOS, raw_ostream &stderrOS) {
   lld::stdoutOS = &stdoutOS;
   lld::stderrOS = &stderrOS;
 
   stderrOS.enable_colors(stderrOS.has_colors());
   // TODO: Set up error handler properly, e.g. the errorLimitExceededMsg
 
bool macho::link(llvm::ArrayRef<const char *> argsArr, bool canExitEarly,
   // re-exported.
   for (opt::Arg *arg : args.filtered(OPT_sub_library)) {
     config->hasReexports = true;
     StringRef searchName = arg->getValue();
     if (!markSubLibrary(searchName))
       error("-sub_library " + searchName + " does not match a supplied dylib");
   }
 
+  // Parse LTO options.
+  if (auto *arg = args.getLastArg(OPT_mcpu))
+    parseClangOption(saver.save("-mcpu=" + StringRef(arg->getValue())),
+                     arg->getSpelling());
+
+  for (auto *arg : args.filtered(OPT_mllvm))
+    parseClangOption(arg->getValue(), arg->getSpelling());
+
   initLLVM();
   compileBitcodeFiles();
   replaceCommonSymbols();
 
   StringRef orderFile = args.getLastArgValue(OPT_order_file);
   if (!orderFile.empty())
     parseOrderFile(orderFile);
 

lld/MachO/LTO.cpp

 using namespace lld;
 using namespace lld::macho;
 using namespace llvm;
 using namespace llvm::sys;
 
 static lto::Config createConfig() {
   lto::Config c;
   c.Options = initTargetOptionsFromCodeGenFlags();
+  c.CodeModel = getCodeModelFromCMModel();
+  c.CPU = getCPUStr();
+  c.MAttrs = getMAttrs();
   return c;
 }
 
 BitcodeCompiler::BitcodeCompiler() {
   auto backend =
       lto::createInProcessThinBackend(llvm::heavyweight_hardware_concurrency());
   ltoObj = std::make_unique<lto::LTO>(createConfig(), backend);
 }

lld/MachO/Options.td

def page_align_data_atoms : Flag<["-"], "page_align_data_atoms">,
      Flags<[HelpHidden]>,
      Group<grp_rare>;
 def not_for_dyld_shared_cache : Flag<["-"], "not_for_dyld_shared_cache">,
      HelpText<"Prevent system dylibs from being placed into the dylib shared cache">,
      Flags<[HelpHidden]>,
      Group<grp_rare>;
 def mllvm : Separate<["-"], "mllvm">,
      HelpText<"Options to pass to LLVM">,
-     Flags<[HelpHidden]>,
+     Group<grp_rare>;
+def mcpu : Separate<["-"], "mcpu">,
+     HelpText<"Processor family target for LTO code generation">,
      Group<grp_rare>;
 
 def grp_deprecated : OptionGroup<"deprecated">, HelpText<"DEPRECATED">;
 
 def lazy_framework : Separate<["-"], "lazy_framework">,
      MetaVarName<"<name>">,
      HelpText<"This option is deprecated and is now an alias for -framework.">,
      Flags<[HelpHidden]>,
def iosmac_version_min : Flag<["-"], "iosmac_version_min">,
      HelpText<"Alias for -maccatalyst_version_min">,
      Flags<[HelpHidden]>,
      Group<grp_undocumented>;
 def uikitformac_version_min : Flag<["-"], "uikitformac_version_min">,
      Alias<maccatalyst_version_min>,
      HelpText<"Alias for -maccatalyst_version_min">,
      Flags<[HelpHidden]>,
      Group<grp_undocumented>;
-def mcpu : Flag<["-"], "mcpu">,
-     HelpText<"This option is undocumented in ld64">,
-     Flags<[HelpHidden]>,
-     Group<grp_undocumented>;
 def no_compact_unwind : Flag<["-"], "no_compact_unwind">,
      HelpText<"This option is undocumented in ld64">,
      Flags<[HelpHidden]>,
      Group<grp_undocumented>;
 def no_dtrace_dof : Flag<["-"], "no_dtrace_dof">,
      HelpText<"This option is undocumented in ld64">,
      Flags<[HelpHidden]>,
      Group<grp_undocumented>;

lld/test/MachO/codemodel.ll

+; REQUIRES: x86
+; RUN: llvm-as %s -o %t.o
+; RUN: %lld -lSystem %t.o -o %ts -mllvm -code-model=small
+; RUN: %lld -lSystem %t.o -o %tl -mllvm -code-model=large
+; RUN: llvm-objdump -d %ts | FileCheck %s --check-prefix=CHECK-SMALL
+; RUN: llvm-objdump -d %tl | FileCheck %s --check-prefix=CHECK-LARGE
+
+target triple = "x86_64-apple-darwin"
+target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+
+@data = internal constant [0 x i32] []
+
+define i32* @main() nounwind readonly {
+entry:
+; CHECK-SMALL-LABEL: <_main>:
+; CHECK-SMALL:       leaq    [[#]](%rip), %rax
+; CHECK-LARGE-LABEL: <_main>:
+; CHECK-LARGE:       movabsq $[[#]], %rax
+  ret i32* getelementptr ([0 x i32], [0 x i32]* @data, i64 0, i64 0)
+}

lld/test/MachO/cpu-string.ll

+; REQUIRES: x86
+; RUN: llvm-as %s -o %t.o
+
+; RUN: %lld %t.o -o %t.dylib -dylib
+; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.dylib | FileCheck %s
+; CHECK: nop{{$}}
+
+; RUN: %lld -mcpu znver1 %t.o -o %t.znver1.dylib -dylib
+; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.znver1.dylib | FileCheck %s --check-prefix=ZNVER1
+
+; ZNVER1: nopw
+; ZNVER1-NOT: nop{{$}}
+
+target triple = "x86_64-apple-darwin"
+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() #0 {
+entry:
+  call void asm sideeffect ".p2align        4, 0x90", "~{dirflag},~{fpsr},~{flags}"()
+  ret void
+}
+
+attributes #0 = { "frame-pointer"="all" }

lld/test/MachO/mattrs.ll

+; REQUIRES: x86
+; RUN: llvm-as %s -o %t.o
+
+;; Verify that LTO behavior can be tweaked using -mattr.
+
+; RUN: %lld -mcpu haswell -mllvm -mattr=+fma %t.o -o %t.dylib -dylib
+; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.dylib | FileCheck %s --check-prefix=FMA
+
+; RUN: %lld -mcpu haswell -mllvm -mattr=-fma %t.o -o %t.dylib -dylib
+; RUN: llvm-objdump -d --section="__text" --no-leading-addr --no-show-raw-insn %t.dylib | FileCheck %s --check-prefix=NO-FMA
+
+; FMA:      <_foo>:
+; FMA-NEXT: vrcpss  %xmm0, %xmm0, %xmm1
+; FMA-NEXT: vfmsub213ss 7(%rip), %xmm1, %xmm0  # 2d4
+; FMA-NEXT: vfnmadd132ss  %xmm1, %xmm1, %xmm0
+; FMA-NEXT: retq
+
+; NO-FMA:      <_foo>:
+; NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1
+; NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0
+; NO-FMA-NEXT: vmovss 16(%rip), %xmm2  # 2e0
+; NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0
+; NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0
+; NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0
+; NO-FMA-NEXT: retq
+
+target triple = "x86_64-apple-darwin"
+target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+
+define float @foo(float %x) #0 {
+  %div = fdiv fast float 1.0, %x
+  ret float %div
+}
+
+attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }