[clang] Adjust -mlarge-data-threshold handling (#77958)

Make it apply to x86-64 medium and large code models since that's what
the backend does.

Limit logic to exclude x86-32.

Default to 0, let the driver set it to 65536 for the medium code model
if one is not passed. Set it to 0 for the large code model by default to
match gcc and since some users make assumptions about the large code
model that any small data will break.

Author: aeubanks

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -472,7 +472,7 @@ def warn_unsupported_branch_protection: Warning <
 def err_sls_hardening_arm_not_supported : Error<
   "-mharden-sls is only supported on armv7-a or later">;
 def warn_drv_large_data_threshold_invalid_code_model: Warning<
-  "'%0' only applies to medium code model">,
+  "'%0' only applies to medium and large code models">,
   InGroup<UnusedCommandLineArgument>;
 
 def note_drv_command_failed_diag_msg : Note<

clang/include/clang/Driver/Options.td

@@ -4392,8 +4392,8 @@ def mcmodel_EQ : Joined<["-"], "mcmodel=">, Group<m_Group>,
   Visibility<[ClangOption, CC1Option]>,
   MarshallingInfoString<TargetOpts<"CodeModel">, [{"default"}]>;
 def mlarge_data_threshold_EQ : Joined<["-"], "mlarge-data-threshold=">, Group<m_Group>,
-  Visibility<[ClangOption, CC1Option]>,
-  MarshallingInfoInt<TargetOpts<"LargeDataThreshold">, "65535">;
+  Flags<[TargetSpecific]>, Visibility<[ClangOption, CC1Option]>,
+  MarshallingInfoInt<TargetOpts<"LargeDataThreshold">, "0">;
 def mtls_size_EQ : Joined<["-"], "mtls-size=">, Group<m_Group>,
   Visibility<[ClangOption, CC1Option]>,
   HelpText<"Specify bit size of immediate TLS offsets (AArch64 ELF only): "

clang/lib/CodeGen/CodeGenModule.cpp

@@ -1201,7 +1201,7 @@ void CodeGenModule::Release() {
       llvm::CodeModel::Model codeModel = static_cast<llvm::CodeModel::Model>(CM);
       getModule().setCodeModel(codeModel);
 
-      if (CM == llvm::CodeModel::Medium &&
+      if ((CM == llvm::CodeModel::Medium || CM == llvm::CodeModel::Large) &&
           Context.getTargetInfo().getTriple().getArch() ==
               llvm::Triple::x86_64) {
         getModule().setLargeDataThreshold(getCodeGenOpts().LargeDataThreshold);

clang/lib/Driver/ToolChains/Clang.cpp

@@ -5752,20 +5752,24 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     }
   }
 
-  if (Arg *A = Args.getLastArg(options::OPT_mlarge_data_threshold_EQ)) {
-    if (!Triple.isX86()) {
-      D.Diag(diag::err_drv_unsupported_opt_for_target)
-          << A->getOption().getName() << TripleStr;
-    } else {
-      bool IsMediumCM = false;
-      if (Arg *A = Args.getLastArg(options::OPT_mcmodel_EQ))
-        IsMediumCM = StringRef(A->getValue()) == "medium";
-      if (!IsMediumCM) {
+  if (Triple.getArch() == llvm::Triple::x86_64) {
+    bool IsMediumCM = false;
+    bool IsLargeCM = false;
+    if (Arg *A = Args.getLastArg(options::OPT_mcmodel_EQ)) {
+      IsMediumCM = StringRef(A->getValue()) == "medium";
+      IsLargeCM = StringRef(A->getValue()) == "large";
+    }
+    if (Arg *A = Args.getLastArg(options::OPT_mlarge_data_threshold_EQ)) {
+      if (!IsMediumCM && !IsLargeCM) {
         D.Diag(diag::warn_drv_large_data_threshold_invalid_code_model)
             << A->getOption().getRenderName();
       } else {
         A->render(Args, CmdArgs);
       }
+    } else if (IsMediumCM) {
+      CmdArgs.push_back("-mlarge-data-threshold=65536");
+    } else if (IsLargeCM) {
+      CmdArgs.push_back("-mlarge-data-threshold=0");
     }
   }
 

clang/test/CodeGen/large-data-threshold.c

@@ -2,11 +2,14 @@
 
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm %s -o - -mcmodel=medium | FileCheck %s --check-prefix=IR-DEFAULT
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm %s -o - -mcmodel=medium -mlarge-data-threshold=200 | FileCheck %s --check-prefix=IR-CUSTOM
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm %s -o - -mcmodel=large -mlarge-data-threshold=200 | FileCheck %s --check-prefix=IR-CUSTOM
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm %s -o - -mcmodel=small -mlarge-data-threshold=200 | FileCheck %s --check-prefix=IR-SMALL
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -S %s -o - -mcmodel=medium -mlarge-data-threshold=200 | FileCheck %s --check-prefix=ASM-SMALL
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -S %s -o - -mcmodel=medium -mlarge-data-threshold=2 | FileCheck %s --check-prefix=ASM-LARGE
 
-// IR-DEFAULT: !{i32 1, !"Large Data Threshold", i64 65535}
+// IR-DEFAULT: !{i32 1, !"Large Data Threshold", i64 0}
 // IR-CUSTOM: !{i32 1, !"Large Data Threshold", i64 200}
+// IR-SMALL-NOT: !"Large Data Threshold"
 
 // ASM-SMALL-NOT: movabsq
 // ASM-LARGE: movabsq

clang/test/Driver/large-data-threshold.c

@@ -1,8 +1,13 @@
+// RUN: %clang --target=x86_64 -### -c -mcmodel=large -mlarge-data-threshold=200 %s 2>&1 | FileCheck --check-prefix=ARG %s
 // RUN: %clang --target=x86_64 -### -c -mcmodel=medium -mlarge-data-threshold=200 %s 2>&1 | FileCheck --check-prefix=ARG %s
-// RUN: %clang --target=x86_64 -### -c -mcmodel=small -mlarge-data-threshold=200 %s 2>&1 | FileCheck --check-prefix=SMALL %s
+// RUN: %clang --target=x86_64 -### -c -mcmodel=large %s 2>&1 | FileCheck --check-prefix=ARG-LARGE-DEFAULT %s
+// RUN: %clang --target=x86_64 -### -c -mcmodel=medium %s 2>&1 | FileCheck --check-prefix=ARG-MEDIUM-DEFAULT %s
+// RUN: %clang --target=x86_64 -### -c -mcmodel=small -mlarge-data-threshold=200 %s 2>&1 | FileCheck --check-prefix=SMALL --implicit-check-not=mlarge-data-threshold %s
 // RUN: not %clang --target=riscv32 -### -c -mcmodel=medium -mlarge-data-threshold=200 %s 2>&1 | FileCheck --check-prefix=ARCH %s
 
 // ARG: "-mlarge-data-threshold=200"
+// ARG-MEDIUM-DEFAULT: "-mlarge-data-threshold=65536"
+// ARG-LARGE-DEFAULT: "-mlarge-data-threshold=0"
 
-// SMALL: 'mlarge-data-threshold=' only applies to medium code model
-// ARCH: unsupported option 'mlarge-data-threshold=' for target 'riscv32'
+// SMALL: 'mlarge-data-threshold=' only applies to medium and large code models
+// ARCH: unsupported option '-mlarge-data-threshold=' for target