[LTO] Add option to enable LTOUnit splitting, and disable unless needed

Summary:
Adds a new -f[no]split-lto-unit flag that is disabled by default to
control module splitting during ThinLTO. It is automatically enabled
for -fsanitize=cfi and -fwhole-program-vtables.

The new EnableSplitLTOUnit codegen flag is passed down to llvm
via a new module flag of the same name.

Depends on D53890.

Reviewers: pcc

Subscribers: ormris, mehdi_amini, inglorion, eraman, steven_wu, dexonsmith, cfe-commits, llvm-commits

Differential Revision: https://reviews.llvm.org/D53891

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@350949 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/Basic/CodeGenOptions.def

@@ -116,6 +116,10 @@ CODEGENOPT(PrepareForThinLTO , 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).
+CODEGENOPT(EnableSplitLTOUnit, 1, 0) ///< Enable LTO unit splitting to support
+				     /// CFI and traditional whole program
+				     /// devirtualization that require whole
+				     /// program IR support.
 CODEGENOPT(IncrementalLinkerCompatible, 1, 0) ///< Emit an object file which can
                                               ///< be used with an incremental
                                               ///< linker.

include/clang/Driver/Options.td

@@ -1776,6 +1776,11 @@ def fwhole_program_vtables : Flag<["-"], "fwhole-program-vtables">, Group<f_Grou
   HelpText<"Enables whole-program vtable optimization. Requires -flto">;
 def fno_whole_program_vtables : Flag<["-"], "fno-whole-program-vtables">, Group<f_Group>,
   Flags<[CoreOption]>;
+def fsplit_lto_unit : Flag<["-"], "fsplit-lto-unit">, Group<f_Group>,
+  Flags<[CoreOption, CC1Option]>,
+  HelpText<"Enables splitting of the LTO unit.">;
+def fno_split_lto_unit : Flag<["-"], "fno-split-lto-unit">, Group<f_Group>,
+  Flags<[CoreOption]>;
 def fforce_emit_vtables : Flag<["-"], "fforce-emit-vtables">, Group<f_Group>,
     Flags<[CC1Option]>,
     HelpText<"Emits more virtual tables to improve devirtualization">;

include/clang/Driver/SanitizerArgs.h

@@ -81,6 +81,7 @@ class SanitizerArgs {
 
   bool requiresPIE() const;
   bool needsUnwindTables() const;
+  bool needsLTO() const;
   bool linkCXXRuntimes() const { return LinkCXXRuntimes; }
   bool hasCrossDsoCfi() const { return CfiCrossDso; }
   bool hasAnySanitizer() const { return !Sanitizers.empty(); }

lib/CodeGen/BackendUtil.cpp

@@ -814,6 +814,8 @@ void EmitAssemblyHelper::EmitAssembly(BackendAction Action,
         if (!ThinLinkOS)
           return;
       }
+      TheModule->addModuleFlag(Module::Error, "EnableSplitLTOUnit",
+                               CodeGenOpts.EnableSplitLTOUnit);
       PerModulePasses.add(createWriteThinLTOBitcodePass(
           *OS, ThinLinkOS ? &ThinLinkOS->os() : nullptr));
     } else {
@@ -824,12 +826,15 @@ void EmitAssemblyHelper::EmitAssembly(BackendAction Action,
            !CodeGenOpts.DisableLLVMPasses &&
            llvm::Triple(TheModule->getTargetTriple()).getVendor() !=
                llvm::Triple::Apple);
-      if (EmitLTOSummary && !TheModule->getModuleFlag("ThinLTO"))
-        TheModule->addModuleFlag(Module::Error, "ThinLTO", uint32_t(0));
+      if (EmitLTOSummary) {
+        if (!TheModule->getModuleFlag("ThinLTO"))
+          TheModule->addModuleFlag(Module::Error, "ThinLTO", uint32_t(0));
+        TheModule->addModuleFlag(Module::Error, "EnableSplitLTOUnit",
+                                 CodeGenOpts.EnableSplitLTOUnit);
+      }
 
-      PerModulePasses.add(
-          createBitcodeWriterPass(*OS, CodeGenOpts.EmitLLVMUseLists,
-                                  EmitLTOSummary));
+      PerModulePasses.add(createBitcodeWriterPass(
+          *OS, CodeGenOpts.EmitLLVMUseLists, EmitLTOSummary));
     }
     break;
 
@@ -1054,6 +1059,8 @@ void EmitAssemblyHelper::EmitAssemblyWithNewPassManager(
         if (!ThinLinkOS)
           return;
       }
+      TheModule->addModuleFlag(Module::Error, "EnableSplitLTOUnit",
+                               CodeGenOpts.EnableSplitLTOUnit);
       MPM.addPass(ThinLTOBitcodeWriterPass(*OS, ThinLinkOS ? &ThinLinkOS->os()
                                                            : nullptr));
     } else {
@@ -1064,11 +1071,14 @@ void EmitAssemblyHelper::EmitAssemblyWithNewPassManager(
            !CodeGenOpts.DisableLLVMPasses &&
            llvm::Triple(TheModule->getTargetTriple()).getVendor() !=
                llvm::Triple::Apple);
-      if (EmitLTOSummary && !TheModule->getModuleFlag("ThinLTO"))
-        TheModule->addModuleFlag(Module::Error, "ThinLTO", uint32_t(0));
-
-      MPM.addPass(BitcodeWriterPass(*OS, CodeGenOpts.EmitLLVMUseLists,
-                                    EmitLTOSummary));
+      if (EmitLTOSummary) {
+        if (!TheModule->getModuleFlag("ThinLTO"))
+          TheModule->addModuleFlag(Module::Error, "ThinLTO", uint32_t(0));
+        TheModule->addModuleFlag(Module::Error, "EnableSplitLTOUnit",
+                                 CodeGenOpts.EnableSplitLTOUnit);
+      }
+      MPM.addPass(
+          BitcodeWriterPass(*OS, CodeGenOpts.EmitLLVMUseLists, EmitLTOSummary));
     }
     break;
 

lib/Driver/SanitizerArgs.cpp

@@ -207,6 +207,8 @@ bool SanitizerArgs::needsUnwindTables() const {
   return Sanitizers.Mask & NeedsUnwindTables;
 }
 
+bool SanitizerArgs::needsLTO() const { return Sanitizers.Mask & NeedsLTO; }
+
 SanitizerArgs::SanitizerArgs(const ToolChain &TC,
                              const llvm::opt::ArgList &Args) {
   SanitizerMask AllRemove = 0;  // During the loop below, the accumulated set of

lib/Driver/ToolChains/Clang.cpp

@@ -5226,6 +5226,17 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back("-fwhole-program-vtables");
   }
 
+  bool RequiresSplitLTOUnit = WholeProgramVTables || Sanitize.needsLTO();
+  bool SplitLTOUnit =
+      Args.hasFlag(options::OPT_fsplit_lto_unit,
+                   options::OPT_fno_split_lto_unit, RequiresSplitLTOUnit);
+  if (RequiresSplitLTOUnit && !SplitLTOUnit)
+    D.Diag(diag::err_drv_argument_not_allowed_with)
+        << "-fno-split-lto-unit"
+        << (WholeProgramVTables ? "-fwhole-program-vtables" : "-fsanitize=cfi");
+  if (SplitLTOUnit)
+    CmdArgs.push_back("-fsplit-lto-unit");
+
   if (Arg *A = Args.getLastArg(options::OPT_fexperimental_isel,
                                options::OPT_fno_experimental_isel)) {
     CmdArgs.push_back("-mllvm");

lib/Frontend/CompilerInvocation.cpp

@@ -907,6 +907,7 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
       Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << S;
   }
   Opts.LTOUnit = Args.hasFlag(OPT_flto_unit, OPT_fno_lto_unit, false);
+  Opts.EnableSplitLTOUnit = Args.hasArg(OPT_fsplit_lto_unit);
   if (Arg *A = Args.getLastArg(OPT_fthinlto_index_EQ)) {
     if (IK.getLanguage() != InputKind::LLVM_IR)
       Diags.Report(diag::err_drv_argument_only_allowed_with)

test/CodeGen/thinlto-distributed-cfi-devirt.ll

@@ -4,7 +4,7 @@
 ; It additionally enables -fwhole-program-vtables to get more information in
 ; TYPE_IDs of GLOBALVAL_SUMMARY_BLOCK.
 
-; RUN: opt -thinlto-bc -o %t.o %s
+; RUN: opt -thinlto-bc -thinlto-split-lto-unit -o %t.o %s
 
 ; FIXME: Fix machine verifier issues and remove -verify-machineinstrs=0. PR39436.
 ; RUN: llvm-lto2 run -thinlto-distributed-indexes %t.o \

test/CodeGen/thinlto-distributed-cfi.ll

@@ -2,7 +2,7 @@
 
 ; Backend test for distribute ThinLTO with CFI.
 
-; RUN: opt -thinlto-bc -o %t.o %s
+; RUN: opt -thinlto-bc -thinlto-split-lto-unit -o %t.o %s
 
 ; RUN: llvm-lto2 run -thinlto-distributed-indexes %t.o \
 ; RUN:   -o %t2.index \

test/CodeGenCXX/no-lto-unit.cpp

@@ -2,6 +2,8 @@
 // RUN: llvm-dis -o - %t | FileCheck %s
 // RUN: %clang_cc1 -flto=thin -flto-unit -fno-lto-unit -triple x86_64-unknown-linux -fvisibility hidden -emit-llvm-bc -o %t %s
 // RUN: llvm-dis -o - %t | FileCheck %s
+// RUN: llvm-bcanalyzer -dump %t | FileCheck %s --check-prefix=NOLTOUNIT
+// NOLTOUNIT: <FLAGS op0=0/>
 
 // CHECK-NOT: !type
 class A {

test/CodeGenCXX/type-metadata-thinlto.cpp

@@ -1,5 +1,7 @@
-// RUN: %clang_cc1 -flto=thin -flto-unit -triple x86_64-unknown-linux -fvisibility hidden -emit-llvm-bc -o %t %s
+// RUN: %clang_cc1 -flto=thin -flto-unit -fsplit-lto-unit -triple x86_64-unknown-linux -fvisibility hidden -emit-llvm-bc -o %t %s
 // RUN: llvm-modextract -o - -n 1 %t | llvm-dis | FileCheck %s
+// RUN: llvm-modextract -b -o - -n 1 %t | llvm-bcanalyzer -dump | FileCheck %s --check-prefix=LTOUNIT
+// LTOUNIT: <FLAGS op0=8/>
 
 // CHECK: @_ZTV1A = linkonce_odr
 class A {

test/Driver/split-lto-unit.c

@@ -0,0 +1,10 @@
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin 2>&1 | FileCheck --check-prefix=NOUNIT %s
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin -fsplit-lto-unit 2>&1 | FileCheck --check-prefix=UNIT %s
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin -fno-split-lto-unit 2>&1 | FileCheck --check-prefix=NOUNIT %s
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin -fno-split-lto-unit -fwhole-program-vtables 2>&1 | FileCheck --check-prefix=ERROR1 %s
+// RUN: %clang -target x86_64-unknown-linux -### %s -flto=thin -fno-split-lto-unit -fsanitize=cfi 2>&1 | FileCheck --check-prefix=ERROR2 %s
+
+// UNIT: "-fsplit-lto-unit"
+// NOUNIT-NOT: "-fsplit-lto-unit"
+// ERROR1: error: invalid argument '-fno-split-lto-unit' not allowed with '-fwhole-program-vtables'
+// ERROR2: error: invalid argument '-fno-split-lto-unit' not allowed with '-fsanitize=cfi'