[ThinLTO] Enable ThinLTO WholeProgramDevirt and LowerTypeTests in new PM

[tejohnson]

Summary

Enable these passes for CFI and WPD in ThinLTO and LTO with the new pass
manager. Add a couple of tests for both PMs based on the clang tests
tools/clang/test/CodeGen/thinlto-distributed-cfi*.ll, but just test
through llvm-lto2 and not with distributed ThinLTO.

[pcc]

LGTM

lib/Passes/PassBuilder.cpp

927 ↗

(On Diff #155903)

There's no need to pass ExportSummary into this function as it is unused (and logically can't be used because the ThinLTO phase should not be exporting anything). Similarly for ImportSummary into buildLTODefaultPipeline.

[tejohnson]

Address comment

llvm/trunk/include/llvm/Passes/PassBuilder.h

 #include "llvm/Transforms/Instrumentation.h"
 #include "llvm/Transforms/Scalar/LoopPassManager.h"
 #include <vector>
 
 namespace llvm {
 class StringRef;
 class AAManager;
 class TargetMachine;
+class ModuleSummaryIndex;
 
 /// A struct capturing PGO tunables.
 struct PGOOptions {
   PGOOptions(std::string ProfileGenFile = "", std::string ProfileUseFile = "",
              std::string SampleProfileFile = "", bool RunProfileGen = false,
              bool SamplePGOSupport = false)
       : ProfileGenFile(ProfileGenFile), ProfileUseFile(ProfileUseFile),
         SampleProfileFile(SampleProfileFile), RunProfileGen(RunProfileGen),
public:
   /// optimization and code generation. It is particularly tuned to fit well
   /// when IR coming into the LTO phase was first run through \c
   /// addPreLinkLTODefaultPipeline, and the two coordinate closely.
   ///
   /// Note that \p Level cannot be `O0` here. The pipelines produced are
   /// only intended for use when attempting to optimize code. If frontends
   /// require some transformations for semantic reasons, they should explicitly
   /// build them.
-  ModulePassManager buildThinLTODefaultPipeline(OptimizationLevel Level,
-                                                bool DebugLogging = false);
+  ModulePassManager
+  buildThinLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
+                              const ModuleSummaryIndex *ImportSummary);
 
   /// Build a pre-link, LTO-targeting default optimization pipeline to a pass
   /// manager.
   ///
   /// This adds the pre-link optimizations tuned to work well with a later LTO
   /// run. It works to minimize the IR which needs to be analyzed without
   /// making irreversible decisions which could be made better during the LTO
   /// run.
public:
   /// when IR coming into the LTO phase was first run through \c
   /// addPreLinkLTODefaultPipeline, and the two coordinate closely.
   ///
   /// Note that \p Level cannot be `O0` here. The pipelines produced are
   /// only intended for use when attempting to optimize code. If frontends
   /// require some transformations for semantic reasons, they should explicitly
   /// build them.
   ModulePassManager buildLTODefaultPipeline(OptimizationLevel Level,
-                                            bool DebugLogging = false);
+                                            bool DebugLogging,
+                                            ModuleSummaryIndex *ExportSummary);
 
   /// Build the default `AAManager` with the default alias analysis pipeline
   /// registered.
   AAManager buildDefaultAAPipeline();
 
   /// Parse a textual pass pipeline description into a \c
   /// ModulePassManager.
   ///

llvm/trunk/include/llvm/Transforms/IPO/LowerTypeTests.h

 #include <cstring>
 #include <limits>
 #include <set>
 #include <vector>
 
 namespace llvm {
 
 class Module;
+class ModuleSummaryIndex;
 class raw_ostream;
 
 namespace lowertypetests {
 
 struct BitSetInfo {
   // The indices of the set bits in the bitset.
   std::set<uint64_t> Bits;
 
struct ByteArrayBuilder {
   void allocate(const std::set<uint64_t> &Bits, uint64_t BitSize,
                 uint64_t &AllocByteOffset, uint8_t &AllocMask);
 };
 
 } // end namespace lowertypetests
 
 class LowerTypeTestsPass : public PassInfoMixin<LowerTypeTestsPass> {
 public:
+  ModuleSummaryIndex *ExportSummary;
+  const ModuleSummaryIndex *ImportSummary;
+  LowerTypeTestsPass(ModuleSummaryIndex *ExportSummary,
+                     const ModuleSummaryIndex *ImportSummary)
+      : ExportSummary(ExportSummary), ImportSummary(ImportSummary) {}
   PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
 };
 
 } // end namespace llvm
 
 #endif // LLVM_TRANSFORMS_IPO_LOWERTYPETESTS_H

llvm/trunk/include/llvm/Transforms/IPO/WholeProgramDevirt.h

 #include <vector>
 
 namespace llvm {
 
 template <typename T> class ArrayRef;
 template <typename T> class MutableArrayRef;
 class Function;
 class GlobalVariable;
+class ModuleSummaryIndex;
 
 namespace wholeprogramdevirt {
 
 // A bit vector that keeps track of which bits are used. We use this to
 // pack constant values compactly before and after each virtual table.
 struct AccumBitVector {
   std::vector<uint8_t> Bytes;
 

 // byte/bit offset to OffsetByte/OffsetBit.
 void setAfterReturnValues(MutableArrayRef<VirtualCallTarget> Targets,
                           uint64_t AllocAfter, unsigned BitWidth,
                           int64_t &OffsetByte, uint64_t &OffsetBit);
 
 } // end namespace wholeprogramdevirt
 
 struct WholeProgramDevirtPass : public PassInfoMixin<WholeProgramDevirtPass> {
+  ModuleSummaryIndex *ExportSummary;
+  const ModuleSummaryIndex *ImportSummary;
+  WholeProgramDevirtPass(ModuleSummaryIndex *ExportSummary,
+                         const ModuleSummaryIndex *ImportSummary)
+      : ExportSummary(ExportSummary), ImportSummary(ImportSummary) {
+    assert(!(ExportSummary && ImportSummary));
+  }
   PreservedAnalyses run(Module &M, ModuleAnalysisManager &);
 };
 
 } // end namespace llvm
 
 #endif // LLVM_TRANSFORMS_IPO_WHOLEPROGRAMDEVIRT_H

llvm/trunk/lib/LTO/LTOBackend.cpp

RelocModel =
         M.getPICLevel() == PICLevel::NotPIC ? Reloc::Static : Reloc::PIC_;
 
   return std::unique_ptr<TargetMachine>(TheTarget->createTargetMachine(
       TheTriple, Conf.CPU, Features.getString(), Conf.Options, RelocModel,
       Conf.CodeModel, Conf.CGOptLevel));
 }
 
 static void runNewPMPasses(Config &Conf, Module &Mod, TargetMachine *TM,
-                           unsigned OptLevel, bool IsThinLTO) {
+                           unsigned OptLevel, bool IsThinLTO,
+                           ModuleSummaryIndex *ExportSummary,
+                           const ModuleSummaryIndex *ImportSummary) {
   Optional<PGOOptions> PGOOpt;
   if (!Conf.SampleProfile.empty())
     PGOOpt = PGOOptions("", "", Conf.SampleProfile, false, true);
 
   PassBuilder PB(TM, PGOOpt);
   AAManager AA;
 
   // Parse a custom AA pipeline if asked to.
case 2:
     OL = PassBuilder::O2;
     break;
   case 3:
     OL = PassBuilder::O3;
     break;
   }
 
   if (IsThinLTO)
-    MPM = PB.buildThinLTODefaultPipeline(OL, Conf.DebugPassManager);
+    MPM = PB.buildThinLTODefaultPipeline(OL, Conf.DebugPassManager,
+                                         ImportSummary);
   else
-    MPM = PB.buildLTODefaultPipeline(OL, Conf.DebugPassManager);
+    MPM = PB.buildLTODefaultPipeline(OL, Conf.DebugPassManager, ExportSummary);
   MPM.run(Mod, MAM);
 
   // FIXME (davide): verify the output.
 }
 
 static void runNewPMCustomPasses(Module &Mod, TargetMachine *TM,
                                  std::string PipelineDesc,
                                  std::string AAPipelineDesc,

 bool opt(Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
          bool IsThinLTO, ModuleSummaryIndex *ExportSummary,
          const ModuleSummaryIndex *ImportSummary) {
   // FIXME: Plumb the combined index into the new pass manager.
   if (!Conf.OptPipeline.empty())
     runNewPMCustomPasses(Mod, TM, Conf.OptPipeline, Conf.AAPipeline,
                          Conf.DisableVerify);
   else if (Conf.UseNewPM)
-    runNewPMPasses(Conf, Mod, TM, Conf.OptLevel, IsThinLTO);
+    runNewPMPasses(Conf, Mod, TM, Conf.OptLevel, IsThinLTO, ExportSummary,
+                   ImportSummary);
   else
     runOldPMPasses(Conf, Mod, TM, IsThinLTO, ExportSummary, ImportSummary);
   return !Conf.PostOptModuleHook || Conf.PostOptModuleHook(Task, Mod);
 }
 
 void codegen(Config &Conf, TargetMachine *TM, AddStreamFn AddStream,
              unsigned Task, Module &Mod) {
   if (Conf.PreCodeGenModuleHook && !Conf.PreCodeGenModuleHook(Task, Mod))

llvm/trunk/lib/Passes/PassBuilder.cpp

if (RunPartialInlining)
     MPM.addPass(PartialInlinerPass());
 
   // Reduce the size of the IR as much as possible.
   MPM.addPass(GlobalOptPass());
 
   return MPM;
 }
 
-ModulePassManager
-PassBuilder::buildThinLTODefaultPipeline(OptimizationLevel Level,
-                                         bool DebugLogging) {
-  // FIXME: The summary index is not hooked in the new pass manager yet.
-  // When it's going to be hooked, enable WholeProgramDevirt and LowerTypeTest
-  // here.
-
+ModulePassManager PassBuilder::buildThinLTODefaultPipeline(
+    OptimizationLevel Level, bool DebugLogging,
+    const ModuleSummaryIndex *ImportSummary) {
   ModulePassManager MPM(DebugLogging);
 
+  if (ImportSummary) {
+    // These passes import type identifier resolutions for whole-program
+    // devirtualization and CFI. They must run early because other passes may
+    // disturb the specific instruction patterns that these passes look for,
+    // creating dependencies on resolutions that may not appear in the summary.
+    //
+    // For example, GVN may transform the pattern assume(type.test) appearing in
+    // two basic blocks into assume(phi(type.test, type.test)), which would
+    // transform a dependency on a WPD resolution into a dependency on a type
+    // identifier resolution for CFI.
+    //
+    // Also, WPD has access to more precise information than ICP and can
+    // devirtualize more effectively, so it should operate on the IR first.
+    MPM.addPass(WholeProgramDevirtPass(nullptr, ImportSummary));
+    MPM.addPass(LowerTypeTestsPass(nullptr, ImportSummary));
+  }
+
   // Force any function attributes we want the rest of the pipeline to observe.
   MPM.addPass(ForceFunctionAttrsPass());
 
   // During the ThinLTO backend phase we perform early indirect call promotion
   // here, before globalopt. Otherwise imported available_externally functions
   // look unreferenced and are removed.
   // FIXME: move this into buildModuleSimplificationPipeline to merge the logic
   //        with SamplePGO.

 ModulePassManager
 PassBuilder::buildLTOPreLinkDefaultPipeline(OptimizationLevel Level,
                                             bool DebugLogging) {
   assert(Level != O0 && "Must request optimizations for the default pipeline!");
   // FIXME: We should use a customized pre-link pipeline!
   return buildPerModuleDefaultPipeline(Level, DebugLogging);
 }
 
-ModulePassManager PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
-                                                       bool DebugLogging) {
+ModulePassManager
+PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
+                                     ModuleSummaryIndex *ExportSummary) {
   assert(Level != O0 && "Must request optimizations for the default pipeline!");
   ModulePassManager MPM(DebugLogging);
 
   // Remove unused virtual tables to improve the quality of code generated by
   // whole-program devirtualization and bitset lowering.
   MPM.addPass(GlobalDCEPass());
 
   // Force any function attributes we want the rest of the pipeline to observe.
PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level, bool DebugLogging,
   // FIXME: Is this really an optimization rather than a canonicalization?
   MPM.addPass(ReversePostOrderFunctionAttrsPass());
 
   // Use inragne annotations on GEP indices to split globals where beneficial.
   MPM.addPass(GlobalSplitPass());
 
   // Run whole program optimization of virtual call when the list of callees
   // is fixed.
-  MPM.addPass(WholeProgramDevirtPass());
+  MPM.addPass(WholeProgramDevirtPass(ExportSummary, nullptr));
 
   // Stop here at -O1.
-  if (Level == 1)
+  if (Level == 1) {
+    // The LowerTypeTestsPass needs to run to lower type metadata and the
+    // type.test intrinsics. The pass does nothing if CFI is disabled.
+    MPM.addPass(LowerTypeTestsPass(ExportSummary, nullptr));
     return MPM;
+  }
 
   // Optimize globals to try and fold them into constants.
   MPM.addPass(GlobalOptPass());
 
   // Promote any localized globals to SSA registers.
   MPM.addPass(createModuleToFunctionPassAdaptor(PromotePass()));
 
   // Linking modules together can lead to duplicate global constant, only
#endif
   // Create a function that performs CFI checks for cross-DSO calls with
   // targets in the current module.
   MPM.addPass(CrossDSOCFIPass());
 
   // Lower type metadata and the type.test intrinsic. This pass supports
   // clang's control flow integrity mechanisms (-fsanitize=cfi*) and needs
   // to be run at link time if CFI is enabled. This pass does nothing if
   // CFI is disabled.
-  // Enable once we add support for the summary in the new PM.
-#if 0
-  MPM.addPass(LowerTypeTestsPass(Summary ? PassSummaryAction::Export :
-                                           PassSummaryAction::None,
-                                Summary));
-#endif
+  MPM.addPass(LowerTypeTestsPass(ExportSummary, nullptr));
 
   // Add late LTO optimization passes.
   // Delete basic blocks, which optimization passes may have killed.
   MPM.addPass(createModuleToFunctionPassAdaptor(SimplifyCFGPass()));
 
   // Drop bodies of available eternally objects to improve GlobalDCE.
   MPM.addPass(EliminateAvailableExternallyPass());
 
if (L == O0)
       // At O0 we do nothing at all!
       return true;
 
     if (Matches[1] == "default") {
       MPM.addPass(buildPerModuleDefaultPipeline(L, DebugLogging));
     } else if (Matches[1] == "thinlto-pre-link") {
       MPM.addPass(buildThinLTOPreLinkDefaultPipeline(L, DebugLogging));
     } else if (Matches[1] == "thinlto") {
-      MPM.addPass(buildThinLTODefaultPipeline(L, DebugLogging));
+      MPM.addPass(buildThinLTODefaultPipeline(L, DebugLogging, nullptr));
     } else if (Matches[1] == "lto-pre-link") {
       MPM.addPass(buildLTOPreLinkDefaultPipeline(L, DebugLogging));
     } else {
       assert(Matches[1] == "lto" && "Not one of the matched options!");
-      MPM.addPass(buildLTODefaultPipeline(L, DebugLogging));
+      MPM.addPass(buildLTODefaultPipeline(L, DebugLogging, nullptr));
     }
     return true;
   }
 
   // Finally expand the basic registered passes from the .inc file.
 #define MODULE_PASS(NAME, CREATE_PASS)                                         \
   if (Name == NAME) {                                                          \
     MPM.addPass(CREATE_PASS);                                                  \

llvm/trunk/lib/Passes/PassRegistry.def

 MODULE_PASS("globalopt", GlobalOptPass())
 MODULE_PASS("globalsplit", GlobalSplitPass())
 MODULE_PASS("inferattrs", InferFunctionAttrsPass())
 MODULE_PASS("insert-gcov-profiling", GCOVProfilerPass())
 MODULE_PASS("instrprof", InstrProfiling())
 MODULE_PASS("internalize", InternalizePass())
 MODULE_PASS("invalidate<all>", InvalidateAllAnalysesPass())
 MODULE_PASS("ipsccp", IPSCCPPass())
-MODULE_PASS("lowertypetests", LowerTypeTestsPass())
+MODULE_PASS("lowertypetests", LowerTypeTestsPass(nullptr, nullptr))
 MODULE_PASS("name-anon-globals", NameAnonGlobalPass())
 MODULE_PASS("no-op-module", NoOpModulePass())
 MODULE_PASS("partial-inliner", PartialInlinerPass())
 MODULE_PASS("pgo-icall-prom", PGOIndirectCallPromotion())
 MODULE_PASS("pgo-instr-gen", PGOInstrumentationGen())
 MODULE_PASS("pgo-instr-use", PGOInstrumentationUse())
 MODULE_PASS("pre-isel-intrinsic-lowering", PreISelIntrinsicLoweringPass())
 MODULE_PASS("print-profile-summary", ProfileSummaryPrinterPass(dbgs()))
 MODULE_PASS("print-callgraph", CallGraphPrinterPass(dbgs()))
 MODULE_PASS("print", PrintModulePass(dbgs()))
 MODULE_PASS("print-lcg", LazyCallGraphPrinterPass(dbgs()))
 MODULE_PASS("print-lcg-dot", LazyCallGraphDOTPrinterPass(dbgs()))
 MODULE_PASS("rewrite-statepoints-for-gc", RewriteStatepointsForGC())
 MODULE_PASS("rewrite-symbols", RewriteSymbolPass())
 MODULE_PASS("rpo-functionattrs", ReversePostOrderFunctionAttrsPass())
 MODULE_PASS("sample-profile", SampleProfileLoaderPass())
 MODULE_PASS("strip-dead-prototypes", StripDeadPrototypesPass())
 MODULE_PASS("synthetic-counts-propagation", SyntheticCountsPropagation())
-MODULE_PASS("wholeprogramdevirt", WholeProgramDevirtPass())
+MODULE_PASS("wholeprogramdevirt", WholeProgramDevirtPass(nullptr, nullptr))
 MODULE_PASS("verify", VerifierPass())
 #undef MODULE_PASS
 
 #ifndef CGSCC_ANALYSIS
 #define CGSCC_ANALYSIS(NAME, CREATE_PASS)
 #endif
 CGSCC_ANALYSIS("no-op-cgscc", NoOpCGSCCAnalysis())
 CGSCC_ANALYSIS("fam-proxy", FunctionAnalysisManagerCGSCCProxy())

llvm/trunk/lib/Transforms/IPO/LowerTypeTests.cpp

if (ExportSummary) {
     }
   }
 
   return true;
 }
 
 PreservedAnalyses LowerTypeTestsPass::run(Module &M,
                                           ModuleAnalysisManager &AM) {
-  bool Changed = LowerTypeTestsModule(M, /*ExportSummary=*/nullptr,
-                                      /*ImportSummary=*/nullptr)
-                     .lower();
+  bool Changed = LowerTypeTestsModule(M, ExportSummary, ImportSummary).lower();
   if (!Changed)
     return PreservedAnalyses::all();
   return PreservedAnalyses::none();
 }

llvm/trunk/lib/Transforms/IPO/WholeProgramDevirt.cpp

PreservedAnalyses WholeProgramDevirtPass::run(Module &M,
                                               ModuleAnalysisManager &AM) {
   auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
   auto AARGetter = [&](Function &F) -> AAResults & {
     return FAM.getResult<AAManager>(F);
   };
   auto OREGetter = [&](Function *F) -> OptimizationRemarkEmitter & {
     return FAM.getResult<OptimizationRemarkEmitterAnalysis>(*F);
   };
-  if (!DevirtModule(M, AARGetter, OREGetter, nullptr, nullptr).run())
+  if (!DevirtModule(M, AARGetter, OREGetter, ExportSummary, ImportSummary)
+           .run())
     return PreservedAnalyses::all();
   return PreservedAnalyses::none();
 }
 
 bool DevirtModule::runForTesting(
     Module &M, function_ref<AAResults &(Function &)> AARGetter,
     function_ref<OptimizationRemarkEmitter &(Function *)> OREGetter) {
   ModuleSummaryIndex Summary(/*HaveGVs=*/false);

llvm/trunk/test/Other/new-pm-lto-defaults.ll

 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph{{.*}}>
 ; CHECK-O-NEXT: Running analysis: AAManager
 ; CHECK-O1-NEXT: Running analysis: TargetLibraryAnalysis
 ; CHECK-O-NEXT: Running pass: ReversePostOrderFunctionAttrsPass
 ; CHECK-O-NEXT: Running analysis: CallGraphAnalysis
 ; CHECK-O-NEXT: Running pass: GlobalSplitPass
 ; CHECK-O-NEXT: Running pass: WholeProgramDevirtPass
+; CHECK-O1-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O2-NEXT: Running pass: GlobalOptPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PromotePass>
 ; CHECK-O2-NEXT: Running analysis: DominatorTreeAnalysis
 ; CHECK-O2-NEXT: Running analysis: AssumptionAnalysis
 ; CHECK-O2-NEXT: Running pass: ConstantMergePass
 ; CHECK-O2-NEXT: Running pass: DeadArgumentEliminationPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PassManager{{.*}}>
 ; CHECK-O2-NEXT: Starting llvm::Function pass manager run.

 ; CHECK-O2-NEXT: Running analysis: LazyValueAnalysis
 ; CHECK-O2-NEXT: Running pass: SROA on foo
 ; CHECK-O2-NEXT: Finished llvm::Function pass manager run.
 ; CHECK-O2-NEXT: Running pass: ModuleToPostOrderCGSCCPassAdaptor<{{.*}}PostOrderFunctionAttrsPass>
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}PassManager{{.*}}>
 ; CHECK-O2-NEXT: Running analysis: MemoryDependenceAnalysis
 ; CHECK-O2-NEXT: Running analysis: DemandedBitsAnalysis
 ; CHECK-O2-NEXT: Running pass: CrossDSOCFIPass
+; CHECK-O2-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O2-NEXT: Running pass: ModuleToFunctionPassAdaptor<{{.*}}SimplifyCFGPass>
 ; CHECK-O2-NEXT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-O2-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O-NEXT: Finished llvm::Module pass manager run.
 ; CHECK-O-NEXT: Running pass: PrintModulePass
 
 ; Make sure we get the IR back out without changes when we print the module.
 ; CHECK-O-LABEL: define void @foo(i32 %n) local_unnamed_addr {

llvm/trunk/test/ThinLTO/X86/cfi-devirt.ll

+; REQUIRES: x86-registered-target
+
+; Test CFI devirtualization through the thin link and backend.
+
+; RUN: opt -thinlto-bc -o %t.o %s
+
+; Legacy PM
+; RUN: llvm-lto2 run %t.o -save-temps \
+; RUN:   -o %t3 \
+; RUN:   -r=%t.o,test,px \
+; RUN:   -r=%t.o,_ZN1A1nEi,p \
+; RUN:   -r=%t.o,_ZN1B1fEi,p \
+; RUN:   -r=%t.o,_ZN1C1fEi,p \
+; RUN:   -r=%t.o,_ZTV1B, \
+; RUN:   -r=%t.o,_ZTV1C, \
+; RUN:   -r=%t.o,_ZN1A1nEi, \
+; RUN:   -r=%t.o,_ZN1B1fEi, \
+; RUN:   -r=%t.o,_ZN1C1fEi, \
+; RUN:   -r=%t.o,_ZTV1B,px \
+; RUN:   -r=%t.o,_ZTV1C,px
+; RUN: llvm-dis %t3.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
+
+; New PM
+; RUN: llvm-lto2 run %t.o -save-temps -use-new-pm \
+; RUN:   -o %t3 \
+; RUN:   -r=%t.o,test,px \
+; RUN:   -r=%t.o,_ZN1A1nEi,p \
+; RUN:   -r=%t.o,_ZN1B1fEi,p \
+; RUN:   -r=%t.o,_ZN1C1fEi,p \
+; RUN:   -r=%t.o,_ZTV1B, \
+; RUN:   -r=%t.o,_ZTV1C, \
+; RUN:   -r=%t.o,_ZN1A1nEi, \
+; RUN:   -r=%t.o,_ZN1B1fEi, \
+; RUN:   -r=%t.o,_ZN1C1fEi, \
+; RUN:   -r=%t.o,_ZTV1B,px \
+; RUN:   -r=%t.o,_ZTV1C,px
+; RUN: llvm-dis %t3.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-grtev4-linux-gnu"
+
+%struct.A = type { i32 (...)** }
+%struct.B = type { %struct.A }
+%struct.C = type { %struct.A }
+
+@_ZTV1B = constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* undef, i8* bitcast (i32 (%struct.B*, i32)* @_ZN1B1fEi to i8*), i8* bitcast (i32 (%struct.A*, i32)* @_ZN1A1nEi to i8*)] }, !type !0, !type !1
+@_ZTV1C = constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* undef, i8* bitcast (i32 (%struct.C*, i32)* @_ZN1C1fEi to i8*), i8* bitcast (i32 (%struct.A*, i32)* @_ZN1A1nEi to i8*)] }, !type !0, !type !2
+
+; CHECK-IR-LABEL: define i32 @test
+define i32 @test(%struct.A* %obj, i32 %a) {
+entry:
+  %0 = bitcast %struct.A* %obj to i8**
+  %vtable5 = load i8*, i8** %0
+
+  %1 = tail call { i8*, i1 } @llvm.type.checked.load(i8* %vtable5, i32 8, metadata !"_ZTS1A")
+  %2 = extractvalue { i8*, i1 } %1, 1
+  br i1 %2, label %cont, label %trap
+
+trap:
+  tail call void @llvm.trap()
+  unreachable
+
+cont:
+  %3 = extractvalue { i8*, i1 } %1, 0
+  %4 = bitcast i8* %3 to i32 (%struct.A*, i32)*
+
+  ; Check that the call was devirtualized.
+  ; CHECK-IR: %call = tail call i32 @_ZN1A1nEi
+  %call = tail call i32 %4(%struct.A* nonnull %obj, i32 %a)
+  %vtable16 = load i8*, i8** %0
+  %5 = tail call { i8*, i1 } @llvm.type.checked.load(i8* %vtable16, i32 0, metadata !"_ZTS1A")
+  %6 = extractvalue { i8*, i1 } %5, 1
+  br i1 %6, label %cont2, label %trap
+
+cont2:
+  %7 = extractvalue { i8*, i1 } %5, 0
+  %8 = bitcast i8* %7 to i32 (%struct.A*, i32)*
+
+  ; Check that traps are conditional. Invalid TYPE_ID can cause
+  ; unconditional traps.
+  ; CHECK-IR: br i1 {{.*}}, label %trap
+
+  ; We still have to call it as virtual.
+  ; CHECK-IR: %call3 = tail call i32 %8
+  %call3 = tail call i32 %8(%struct.A* nonnull %obj, i32 %call)
+  ret i32 %call3
+}
+; CHECK-IR-LABEL: ret i32
+; CHECK-IR-LABEL: }
+
+declare { i8*, i1 } @llvm.type.checked.load(i8*, i32, metadata)
+declare void @llvm.trap()
+
+declare i32 @_ZN1B1fEi(%struct.B* %this, i32 %a)
+declare i32 @_ZN1A1nEi(%struct.A* %this, i32 %a)
+declare i32 @_ZN1C1fEi(%struct.C* %this, i32 %a)
+
+!0 = !{i64 16, !"_ZTS1A"}
+!1 = !{i64 16, !"_ZTS1B"}
+!2 = !{i64 16, !"_ZTS1C"}

llvm/trunk/test/ThinLTO/X86/cfi.ll

+; REQUIRES: x86-registered-target
+
+; Test CFI through the thin link and backend.
+
+; RUN: opt -thinlto-bc -o %t.o %s
+
+; Legacy PM
+; RUN: llvm-lto2 run -save-temps %t.o \
+; RUN:   -o %t3 \
+; RUN:   -r=%t.o,test,px \
+; RUN:   -r=%t.o,_ZTV1B, \
+; RUN:   -r=%t.o,_ZN1B1fEi, \
+; RUN:   -r=%t.o,_ZTV1B,px
+; RUN: llvm-dis %t3.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
+
+; New PM
+; RUN: llvm-lto2 run -save-temps %t.o -use-new-pm \
+; RUN:   -o %t3 \
+; RUN:   -r=%t.o,test,px \
+; RUN:   -r=%t.o,_ZTV1B, \
+; RUN:   -r=%t.o,_ZN1B1fEi, \
+; RUN:   -r=%t.o,_ZTV1B,px
+; RUN: llvm-dis %t3.1.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-grtev4-linux-gnu"
+
+%struct.B = type { %struct.A }
+%struct.A = type { i32 (...)** }
+
+@_ZTV1B = constant { [3 x i8*] } { [3 x i8*] [i8* undef, i8* undef, i8* undef] }, !type !0
+
+; CHECK-IR-LABEL: define void @test
+define void @test(i8* %b) {
+entry:
+  ; Ensure that traps are conditional. Invalid TYPE_ID can cause
+  ; unconditional traps.
+  ; CHECK-IR: br i1 {{.*}}, label %trap
+  %0 = bitcast i8* %b to i8**
+  %vtable2 = load i8*, i8** %0
+  %1 = tail call i1 @llvm.type.test(i8* %vtable2, metadata !"_ZTS1A")
+  br i1 %1, label %cont, label %trap
+
+trap:
+  tail call void @llvm.trap()
+  unreachable
+
+cont:
+  ; CHECK-IR-LABEL: ret void
+  ret void
+}
+; CHECK-IR-LABEL: }
+
+declare i1 @llvm.type.test(i8*, metadata)
+declare void @llvm.trap()
+
+declare i32 @_ZN1B1fEi(%struct.B* %this, i32 %a)
+
+!0 = !{i64 16, !"_ZTS1A"}
+!1 = !{i64 16, !"_ZTS1B"}