[X86] Teach Clang about -mfentry flag

[niravd]

Summary

Replace mcount calls with calls to fentry.

[niravd]

Ping.

[mcrosier]

include/clang/Driver/Options.td

1731 ↗

(On Diff #82146)

Should this not be in the m_x86_Features_Group since this is an x86 specific flag?

test/CodeGen/fentry.c

1 ↗

(On Diff #82146)

I want to say this test should be in test/Frontend directory since you're testing a new CC1 option.

11 ↗

(On Diff #82146)

I'd prefer we stick with the default CHECK and CHECK-NOT prefixes.

[mcrosier]

test/CodeGen/fentry.c

11 ↗

(On Diff #82146)

Specifically, for the first two RUN commands please use CHECK and for the latter two use something like NOPG-NOT.

[niravd]

Address comments

[niravd]

include/clang/Driver/Options.td

1731 ↗

(On Diff #82146)

Done. -mfentry should eventually defined for at least aarch64 but until that point we should have the flag match clang's actual capabilities.

test/CodeGen/fentry.c

1 ↗

(On Diff #82146)

That seems reasonable, but I wanted to match with the mcount test.

[dberris]

LGTM

cfe/trunk/include/clang/Driver/Options.td

def mno_implicit_float : Flag<["-"], "mno-implicit-float">, Group<m_Group>,
   HelpText<"Don't generate implicit floating point instructions">;
 def mimplicit_float : Flag<["-"], "mimplicit-float">, Group<m_Group>;
 def mrecip : Flag<["-"], "mrecip">, Group<m_Group>;
 def mrecip_EQ : CommaJoined<["-"], "mrecip=">, Group<m_Group>, Flags<[CC1Option]>;
 def mpie_copy_relocations : Flag<["-"], "mpie-copy-relocations">, Group<m_Group>,
   Flags<[CC1Option]>,
   HelpText<"Use copy relocations support for PIE builds">;
 def mno_pie_copy_relocations : Flag<["-"], "mno-pie-copy-relocations">, Group<m_Group>;
+def mfentry : Flag<["-"], "mfentry">, HelpText<"insert calls to fentry at function entry (x86 only)">,
+  Flags<[CC1Option]>, Group<m_Group>;
 def mx87 : Flag<["-"], "mx87">, Group<m_x86_Features_Group>;
 def m80387 : Flag<["-"], "m80387">, Alias<mx87>;
 def msse2 : Flag<["-"], "msse2">, Group<m_x86_Features_Group>;
 def msse3 : Flag<["-"], "msse3">, Group<m_x86_Features_Group>;
 def msse4a : Flag<["-"], "msse4a">, Group<m_x86_Features_Group>;
 def msse4_1 : Flag<["-"], "msse4.1">, Group<m_x86_Features_Group>;
 def msse4_2 : Flag<["-"], "msse4.2">, Group<m_x86_Features_Group>;
 def msse4 : Flag<["-"], "msse4">, Alias<msse4_2>;

cfe/trunk/include/clang/Frontend/CodeGenOptions.def

 CODEGENOPT(XRayInstrumentFunctions , 1, 0) ///< Set when -fxray-instrument is
                                            ///< enabled.
 
 ///< Set the minimum number of instructions in a function to determine selective
 ///< XRay instrumentation.
 VALUE_CODEGENOPT(XRayInstructionThreshold , 32, 200)
 
 CODEGENOPT(InstrumentForProfiling , 1, 0) ///< Set when -pg is enabled.
+CODEGENOPT(CallFEntry , 1, 0) ///< Set when -mfentry is enabled.
 CODEGENOPT(LessPreciseFPMAD  , 1, 0) ///< Enable less precise MAD instructions to
                                      ///< be generated.
 CODEGENOPT(PrepareForLTO     , 1, 0) ///< Set when -flto is enabled on the
                                      ///< compile step.
 CODEGENOPT(EmitSummaryIndex, 1, 0)   ///< Set when -flto=thin is enabled on the
                                      ///< compile step.
 CODEGENOPT(LTOUnit, 1, 0) ///< Emit IR to support LTO unit features (CFI, whole
                           ///< program vtable opt).

cfe/trunk/lib/CodeGen/CodeGenFunction.cpp

void CodeGenFunction::StartFunction(GlobalDecl GD,
 
   if (ShouldInstrumentFunction())
     EmitFunctionInstrumentation("__cyg_profile_func_enter");
 
   // Since emitting the mcount call here impacts optimizations such as function
   // inlining, we just add an attribute to insert a mcount call in backend.
   // The attribute "counting-function" is set to mcount function name which is
   // architecture dependent.
-  if (CGM.getCodeGenOpts().InstrumentForProfiling)
+  if (CGM.getCodeGenOpts().InstrumentForProfiling) {
+    if (CGM.getCodeGenOpts().CallFEntry)
+      Fn->addFnAttr("fentry-call", "true");
+    else
       Fn->addFnAttr("counting-function", getTarget().getMCountName());
+  }
 
   if (RetTy->isVoidType()) {
     // Void type; nothing to return.
     ReturnValue = Address::invalid();
 
     // Count the implicit return.
     if (!endsWithReturn(D))
       ++NumReturnExprs;

cfe/trunk/lib/Driver/Tools.cpp

   if (Arg *A = Args.getLastArg(options::OPT_fzvector))
     if (Args.hasArg(options::OPT_faltivec))
       D.Diag(diag::err_drv_argument_not_allowed_with) << A->getAsString(Args)
                                                       << "-faltivec";
 
   if (getToolChain().SupportsProfiling())
     Args.AddLastArg(CmdArgs, options::OPT_pg);
 
+  if (getToolChain().SupportsProfiling())
+    Args.AddLastArg(CmdArgs, options::OPT_mfentry);
+
   // -flax-vector-conversions is default.
   if (!Args.hasFlag(options::OPT_flax_vector_conversions,
                     options::OPT_fno_lax_vector_conversions))
     CmdArgs.push_back("-fno-lax-vector-conversions");
 
   if (Args.getLastArg(options::OPT_fapple_kext) ||
       (Args.hasArg(options::OPT_mkernel) && types::isCXX(InputType)))
     CmdArgs.push_back("-fapple-kext");

cfe/trunk/lib/Frontend/CompilerInvocation.cpp

if (Opts.getEmbedBitcode() == CodeGenOptions::Embed_All) {
     }
   }
 
   Opts.InstrumentFunctions = Args.hasArg(OPT_finstrument_functions);
   Opts.XRayInstrumentFunctions = Args.hasArg(OPT_fxray_instrument);
   Opts.XRayInstructionThreshold =
       getLastArgIntValue(Args, OPT_fxray_instruction_threshold_, 200, Diags);
   Opts.InstrumentForProfiling = Args.hasArg(OPT_pg);
+  Opts.CallFEntry = Args.hasArg(OPT_mfentry);
   Opts.EmitOpenCLArgMetadata = Args.hasArg(OPT_cl_kernel_arg_info);
   Opts.CompressDebugSections = Args.hasArg(OPT_compress_debug_sections);
   Opts.RelaxELFRelocations = Args.hasArg(OPT_mrelax_relocations);
   Opts.DebugCompilationDir = Args.getLastArgValue(OPT_fdebug_compilation_dir);
   for (auto A : Args.filtered(OPT_mlink_bitcode_file, OPT_mlink_cuda_bitcode)) {
     CodeGenOptions::BitcodeFileToLink F;
     F.Filename = A->getValue();
     if (A->getOption().matches(OPT_mlink_cuda_bitcode)) {

cfe/trunk/test/CodeGen/fentry.c

+// RUN: %clang_cc1 -pg -mfentry -triple i386-unknown-unknown -emit-llvm -o - %s | FileCheck  %s
+// RUN: %clang_cc1 -pg -mfentry -triple x86_64-unknown-linux-gnu -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -mfentry -triple i386-unknown-unknown -emit-llvm -o - %s | FileCheck -check-prefix=NOPG %s
+// RUN: %clang_cc1 -mfentry -triple x86_64-unknown-linux-gnu -emit-llvm -o - %s | FileCheck -check-prefix=NOPG %s
+
+int foo(void) {
+  return 0;
+}
+
+//CHECK: attributes #{{[0-9]+}} = { {{.*}}"fentry-call"="true"{{.*}} }
+//NOPG-NOT: attributes #{{[0-9]+}} = { {{.*}}"fentry-call"{{.*}} }