ThinLTO: add early "dead-stripping" on the Index

Summary:
Using the linker-supplied list of "preserved" symbols, we can compute
the list of "dead" symbols, i.e. the one that are not reachable from
a "preserved" symbol transitively on the reference graph.
Right now we are using this information to mark these functions as
non-eligible for import.

The impact is two folds:
- Reduction of compile time: we don't import these functions anywhere
  or import the function these symbols are calling.
- The limited number of import/export leads to better internalization.

Patch originally by Mehdi Amini.

Reviewers: mehdi_amini, pcc

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D23488

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291177 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/IR/ModuleSummaryIndex.h

@@ -121,10 +121,16 @@ public:
     /// be renamed or references something that can't be renamed).
     unsigned NotEligibleToImport : 1;
 
+    /// Indicate that the global value must be considered a live root for
+    /// index-based liveness analysis. Used for special LLVM values such as
+    /// llvm.global_ctors that the linker does not know about.
+    unsigned LiveRoot : 1;
+
     /// Convenience Constructors
     explicit GVFlags(GlobalValue::LinkageTypes Linkage,
-                     bool NotEligibleToImport)
+                     bool NotEligibleToImport, bool LiveRoot)
-        : Linkage(Linkage), NotEligibleToImport(NotEligibleToImport) {}
+        : Linkage(Linkage), NotEligibleToImport(NotEligibleToImport),
+          LiveRoot(LiveRoot) {}
   };
 
 private:
@@ -195,6 +201,14 @@ public:
   /// Return true if this global value can't be imported.
   bool notEligibleToImport() const { return Flags.NotEligibleToImport; }
 
+  /// Return true if this global value must be considered a root for live
+  /// value analysis on the index.
+  bool liveRoot() const { return Flags.LiveRoot; }
+
+  /// Flag that this global value must be considered a root for live
+  /// value analysis on the index.
+  void setLiveRoot() { Flags.LiveRoot = true; }
+
   /// Flag that this global value cannot be imported.
   void setNotEligibleToImport() { Flags.NotEligibleToImport = true; }
 
@@ -366,6 +380,7 @@ public:
   const_gvsummary_iterator begin() const { return GlobalValueMap.begin(); }
   gvsummary_iterator end() { return GlobalValueMap.end(); }
   const_gvsummary_iterator end() const { return GlobalValueMap.end(); }
+  size_t size() const { return GlobalValueMap.size(); }
 
   /// Get the list of global value summary objects for a given value name.
   const GlobalValueSummaryList &getGlobalValueSummaryList(StringRef ValueName) {

include/llvm/IR/ModuleSummaryIndexYAML.h

@@ -78,7 +78,8 @@ template <> struct CustomMappingTraits<GlobalValueSummaryMapTy> {
     }
     auto &Elem = V[KeyInt];
     for (auto &FSum : FSums) {
-      GlobalValueSummary::GVFlags GVFlags(GlobalValue::ExternalLinkage, false);
+      GlobalValueSummary::GVFlags GVFlags(GlobalValue::ExternalLinkage, false,
+                                          false);
       Elem.push_back(llvm::make_unique<FunctionSummary>(
           GVFlags, 0, ArrayRef<ValueInfo>{},
           ArrayRef<FunctionSummary::EdgeTy>{}, std::move(FSum.TypeTests)));

include/llvm/LTO/LTO.h

@@ -382,6 +382,10 @@ private:
     /// The unmangled name of the global.
     std::string IRName;
 
+    /// Keep track if the symbol is visible outside of ThinLTO (i.e. in
+    /// either a regular object or the regular LTO partition).
+    bool VisibleOutsideThinLTO = false;
+
     bool UnnamedAddr = true;
 
     /// This field keeps track of the partition number of this global. The
@@ -405,6 +409,9 @@ private:
       /// This global is either used by more than one partition or has an
       /// external reference, and therefore cannot be internalized.
       External = -2u,
+
+      /// The RegularLTO partition
+      RegularLTO = 0,
     };
   };
 

include/llvm/Transforms/IPO/FunctionImport.h

@@ -86,11 +86,15 @@ public:
 /// \p ExportLists contains for each Module the set of globals (GUID) that will
 /// be imported by another module, or referenced by such a function. I.e. this
 /// is the set of globals that need to be promoted/renamed appropriately.
+///
+/// \p DeadSymbols (optional) contains a list of GUID that are deemed "dead" and
+/// will be ignored for the purpose of importing.
 void ComputeCrossModuleImport(
     const ModuleSummaryIndex &Index,
     const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
     StringMap<FunctionImporter::ImportMapTy> &ImportLists,
-    StringMap<FunctionImporter::ExportSetTy> &ExportLists);
+    StringMap<FunctionImporter::ExportSetTy> &ExportLists,
+    const DenseSet<GlobalValue::GUID> *DeadSymbols = nullptr);
 
 /// Compute all the imports for the given module using the Index.
 ///
@@ -100,6 +104,13 @@ void ComputeCrossModuleImportForModule(
     StringRef ModulePath, const ModuleSummaryIndex &Index,
     FunctionImporter::ImportMapTy &ImportList);
 
+/// Compute all the symbols that are "dead": i.e these that can't be reached
+/// in the graph from any of the given symbols listed in
+/// \p GUIDPreservedSymbols.
+DenseSet<GlobalValue::GUID>
+computeDeadSymbols(const ModuleSummaryIndex &Index,
+                   const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols);
+
 /// Compute the set of summaries needed for a ThinLTO backend compilation of
 /// \p ModulePath.
 //

lib/Analysis/ModuleSummaryAnalysis.cpp

@@ -189,7 +189,8 @@ computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
       // Inliner doesn't handle variadic functions.
       // FIXME: refactor this to use the same code that inliner is using.
       F.isVarArg();
-  GlobalValueSummary::GVFlags Flags(F.getLinkage(), NotEligibleForImport);
+  GlobalValueSummary::GVFlags Flags(F.getLinkage(), NotEligibleForImport,
+                                    /* LiveRoot = */ false);
   auto FuncSummary = llvm::make_unique<FunctionSummary>(
       Flags, NumInsts, RefEdges.takeVector(), CallGraphEdges.takeVector(),
       TypeTests.takeVector());
@@ -205,7 +206,8 @@ computeVariableSummary(ModuleSummaryIndex &Index, const GlobalVariable &V,
   SmallPtrSet<const User *, 8> Visited;
   findRefEdges(&V, RefEdges, Visited);
   bool NonRenamableLocal = isNonRenamableLocal(V);
-  GlobalValueSummary::GVFlags Flags(V.getLinkage(), NonRenamableLocal);
+  GlobalValueSummary::GVFlags Flags(V.getLinkage(), NonRenamableLocal,
+                                    /* LiveRoot = */ false);
   auto GVarSummary =
       llvm::make_unique<GlobalVarSummary>(Flags, RefEdges.takeVector());
   if (NonRenamableLocal)
@@ -217,7 +219,8 @@ static void
 computeAliasSummary(ModuleSummaryIndex &Index, const GlobalAlias &A,
                     DenseSet<GlobalValue::GUID> &CantBePromoted) {
   bool NonRenamableLocal = isNonRenamableLocal(A);
-  GlobalValueSummary::GVFlags Flags(A.getLinkage(), NonRenamableLocal);
+  GlobalValueSummary::GVFlags Flags(A.getLinkage(), NonRenamableLocal,
+                                    /* LiveRoot = */ false);
   auto AS = llvm::make_unique<AliasSummary>(Flags, ArrayRef<ValueInfo>{});
   auto *Aliasee = A.getBaseObject();
   auto *AliaseeSummary = Index.getGlobalValueSummary(*Aliasee);
@@ -228,6 +231,16 @@ computeAliasSummary(ModuleSummaryIndex &Index, const GlobalAlias &A,
   Index.addGlobalValueSummary(A.getName(), std::move(AS));
 }
 
+// Set LiveRoot flag on entries matching the given value name.
+static void setLiveRoot(ModuleSummaryIndex &Index, StringRef Name) {
+  auto SummaryList =
+      Index.findGlobalValueSummaryList(GlobalValue::getGUID(Name));
+  if (SummaryList == Index.end())
+    return;
+  for (auto &Summary : SummaryList->second)
+    Summary->setLiveRoot();
+}
+
 ModuleSummaryIndex llvm::buildModuleSummaryIndex(
     const Module &M,
     std::function<BlockFrequencyInfo *(const Function &F)> GetBFICallback,
@@ -293,6 +306,15 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
     Summary->setNotEligibleToImport();
   }
 
+  // The linker doesn't know about these LLVM produced values, so we need
+  // to flag them as live in the index to ensure index-based dead value
+  // analysis treats them as live roots of the analysis.
+  setLiveRoot(Index, "llvm.used");
+  setLiveRoot(Index, "llvm.compiler.used");
+  setLiveRoot(Index, "llvm.global_ctors");
+  setLiveRoot(Index, "llvm.global_dtors");
+  setLiveRoot(Index, "llvm.global.annotations");
+
   if (!M.getModuleInlineAsm().empty()) {
     // Collect the local values defined by module level asm, and set up
     // summaries for these symbols so that they can be marked as NoRename,
@@ -316,7 +338,8 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
             return;
           assert(GV->isDeclaration() && "Def in module asm already has definition");
           GlobalValueSummary::GVFlags GVFlags(GlobalValue::InternalLinkage,
-                                              /* NotEligibleToImport */ true);
+                                              /* NotEligibleToImport */ true,
+                                              /* LiveRoot */ true);
           CantBePromoted.insert(GlobalValue::getGUID(Name));
           // Create the appropriate summary type.
           if (isa<Function>(GV)) {

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -802,7 +802,11 @@ static GlobalValueSummary::GVFlags getDecodedGVSummaryFlags(uint64_t RawFlags,
   auto Linkage = GlobalValue::LinkageTypes(RawFlags & 0xF); // 4 bits
   RawFlags = RawFlags >> 4;
   bool NotEligibleToImport = (RawFlags & 0x1) || Version < 3;
-  return GlobalValueSummary::GVFlags(Linkage, NotEligibleToImport);
+  // The LiveRoot flag wasn't introduced until version 3. For dead stripping
+  // to work correctly on earlier versions, we must conservatively treat all
+  // values as live.
+  bool LiveRoot = (RawFlags & 0x2) || Version < 3;
+  return GlobalValueSummary::GVFlags(Linkage, NotEligibleToImport, LiveRoot);
 }
 
 static GlobalValue::VisibilityTypes getDecodedVisibility(unsigned Val) {

lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -972,6 +972,7 @@ static uint64_t getEncodedGVSummaryFlags(GlobalValueSummary::GVFlags Flags) {
   uint64_t RawFlags = 0;
 
   RawFlags |= Flags.NotEligibleToImport; // bool
+  RawFlags |= (Flags.LiveRoot << 1);
   // Linkage don't need to be remapped at that time for the summary. Any future
   // change to the getEncodedLinkage() function will need to be taken into
   // account here as well.

lib/LTO/LTO.cpp

@@ -337,12 +337,21 @@ void LTO::addSymbolToGlobalRes(SmallPtrSet<GlobalValue *, 8> &Used,
     if (Res.Prevailing)
       GlobalRes.IRName = GV->getName();
   }
+  // Set the partition to external if we know it is used elsewhere, e.g.
+  // it is visible to a regular object, is referenced from llvm.compiler_used,
+  // or was already recorded as being referenced from a different partition.
   if (Res.VisibleToRegularObj || (GV && Used.count(GV)) ||
       (GlobalRes.Partition != GlobalResolution::Unknown &&
-       GlobalRes.Partition != Partition))
+       GlobalRes.Partition != Partition)) {
     GlobalRes.Partition = GlobalResolution::External;
-  else
+  } else
+    // First recorded reference, save the current partition.
     GlobalRes.Partition = Partition;
+
+  // Flag as visible outside of ThinLTO if visible from a regular object or
+  // if this is a reference in the regular LTO partition.
+  GlobalRes.VisibleOutsideThinLTO |=
+      (Res.VisibleToRegularObj || (Partition == GlobalResolution::RegularLTO));
 }
 
 static void writeToResolutionFile(raw_ostream &OS, InputFile *Input,
@@ -848,6 +857,19 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
     if (!ModuleToDefinedGVSummaries.count(Mod.first))
       ModuleToDefinedGVSummaries.try_emplace(Mod.first);
 
+  // Compute "dead" symbols, we don't want to import/export these!
+  DenseSet<GlobalValue::GUID> GUIDPreservedSymbols;
+  for (auto &Res : GlobalResolutions) {
+    if (Res.second.VisibleOutsideThinLTO &&
+        // IRName will be defined if we have seen the prevailing copy of
+        // this value. If not, no need to preserve any ThinLTO copies.
+        !Res.second.IRName.empty())
+      GUIDPreservedSymbols.insert(GlobalValue::getGUID(Res.second.IRName));
+  }
+
+  auto DeadSymbols =
+      computeDeadSymbols(ThinLTO.CombinedIndex, GUIDPreservedSymbols);
+
   StringMap<FunctionImporter::ImportMapTy> ImportLists(
       ThinLTO.ModuleMap.size());
   StringMap<FunctionImporter::ExportSetTy> ExportLists(
@@ -856,12 +878,21 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
 
   if (Conf.OptLevel > 0) {
     ComputeCrossModuleImport(ThinLTO.CombinedIndex, ModuleToDefinedGVSummaries,
-                             ImportLists, ExportLists);
+                             ImportLists, ExportLists, &DeadSymbols);
 
     std::set<GlobalValue::GUID> ExportedGUIDs;
     for (auto &Res : GlobalResolutions) {
-      if (!Res.second.IRName.empty() &&
+      // First check if the symbol was flagged as having external references.
-          Res.second.Partition == GlobalResolution::External)
+      if (Res.second.Partition != GlobalResolution::External)
+        continue;
+      // IRName will be defined if we have seen the prevailing copy of
+      // this value. If not, no need to mark as exported from a ThinLTO
+      // partition (and we can't get the GUID).
+      if (Res.second.IRName.empty())
+        continue;
+      auto GUID = GlobalValue::getGUID(Res.second.IRName);
+      // Mark exported unless index-based analysis determined it to be dead.
+      if (!DeadSymbols.count(GUID))
         ExportedGUIDs.insert(GlobalValue::getGUID(Res.second.IRName));
     }
 

lib/LTO/ThinLTOCodeGenerator.cpp

@@ -581,11 +581,18 @@ void ThinLTOCodeGenerator::promote(Module &TheModule,
   StringMap<GVSummaryMapTy> ModuleToDefinedGVSummaries;
   Index.collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
 
+  // Convert the preserved symbols set from string to GUID
+  auto GUIDPreservedSymbols = computeGUIDPreservedSymbols(
+      PreservedSymbols, Triple(TheModule.getTargetTriple()));
+
+  // Compute "dead" symbols, we don't want to import/export these!
+  auto DeadSymbols = computeDeadSymbols(Index, GUIDPreservedSymbols);
+
   // Generate import/export list
   StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
   StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
   ComputeCrossModuleImport(Index, ModuleToDefinedGVSummaries, ImportLists,
-                           ExportLists);
+                           ExportLists, &DeadSymbols);
 
   // Resolve LinkOnce/Weak symbols.
   StringMap<std::map<GlobalValue::GUID, GlobalValue::LinkageTypes>> ResolvedODR;
@@ -594,10 +601,6 @@ void ThinLTOCodeGenerator::promote(Module &TheModule,
   thinLTOResolveWeakForLinkerModule(
       TheModule, ModuleToDefinedGVSummaries[ModuleIdentifier]);
 
-  // Convert the preserved symbols set from string to GUID
-  auto GUIDPreservedSymbols = computeGUIDPreservedSymbols(
-      PreservedSymbols, Triple(TheModule.getTargetTriple()));
-
   // Promote the exported values in the index, so that they are promoted
   // in the module.
   auto isExported = [&](StringRef ModuleIdentifier, GlobalValue::GUID GUID) {
@@ -623,11 +626,18 @@ void ThinLTOCodeGenerator::crossModuleImport(Module &TheModule,
   StringMap<GVSummaryMapTy> ModuleToDefinedGVSummaries(ModuleCount);
   Index.collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
 
+  // Convert the preserved symbols set from string to GUID
+  auto GUIDPreservedSymbols = computeGUIDPreservedSymbols(
+      PreservedSymbols, Triple(TheModule.getTargetTriple()));
+
+  // Compute "dead" symbols, we don't want to import/export these!
+  auto DeadSymbols = computeDeadSymbols(Index, GUIDPreservedSymbols);
+
   // Generate import/export list
   StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
   StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
   ComputeCrossModuleImport(Index, ModuleToDefinedGVSummaries, ImportLists,
-                           ExportLists);
+                           ExportLists, &DeadSymbols);
   auto &ImportList = ImportLists[TheModule.getModuleIdentifier()];
 
   crossImportIntoModule(TheModule, Index, ModuleMap, ImportList);
@@ -697,11 +707,14 @@ void ThinLTOCodeGenerator::internalize(Module &TheModule,
   StringMap<GVSummaryMapTy> ModuleToDefinedGVSummaries(ModuleCount);
   Index.collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
 
+  // Compute "dead" symbols, we don't want to import/export these!
+  auto DeadSymbols = computeDeadSymbols(Index, GUIDPreservedSymbols);
+
   // Generate import/export list
   StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
   StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
   ComputeCrossModuleImport(Index, ModuleToDefinedGVSummaries, ImportLists,
-                           ExportLists);
+                           ExportLists, &DeadSymbols);
   auto &ExportList = ExportLists[ModuleIdentifier];
 
   // Be friendly and don't nuke totally the module when the client didn't
@@ -836,17 +849,20 @@ void ThinLTOCodeGenerator::run() {
   StringMap<GVSummaryMapTy> ModuleToDefinedGVSummaries(ModuleCount);
   Index->collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
 
+  // Convert the preserved symbols set from string to GUID, this is needed for
+  // computing the caching hash and the internalization.
+  auto GUIDPreservedSymbols =
+      computeGUIDPreservedSymbols(PreservedSymbols, TMBuilder.TheTriple);
+
+  // Compute "dead" symbols, we don't want to import/export these!
+  auto DeadSymbols = computeDeadSymbols(*Index, GUIDPreservedSymbols);
+
   // Collect the import/export lists for all modules from the call-graph in the
   // combined index.
   StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
   StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
   ComputeCrossModuleImport(*Index, ModuleToDefinedGVSummaries, ImportLists,
-                           ExportLists);
+                           ExportLists, &DeadSymbols);
-
-  // Convert the preserved symbols set from string to GUID, this is needed for
-  // computing the caching hash and the internalization.
-  auto GUIDPreservedSymbols =
-      computeGUIDPreservedSymbols(PreservedSymbols, TMBuilder.TheTriple);
 
   // We use a std::map here to be able to have a defined ordering when
   // producing a hash for the cache entry.

lib/Transforms/IPO/FunctionImport.cpp

@@ -36,7 +36,10 @@
 
 using namespace llvm;
 
-STATISTIC(NumImported, "Number of functions imported");
+STATISTIC(NumImportedFunctions, "Number of functions imported");
+STATISTIC(NumImportedModules, "Number of modules imported from");
+STATISTIC(NumDeadSymbols, "Number of dead stripped symbols in index");
+STATISTIC(NumLiveSymbols, "Number of live symbols in index");
 
 /// Limit on instruction count of imported functions.
 static cl::opt<unsigned> ImportInstrLimit(
@@ -69,6 +72,9 @@ static cl::opt<float> ImportColdMultiplier(
 static cl::opt<bool> PrintImports("print-imports", cl::init(false), cl::Hidden,
                                   cl::desc("Print imported functions"));
 
+static cl::opt<bool> ComputeDead("compute-dead", cl::init(true), cl::Hidden,
+                                 cl::desc("Compute dead symbols"));
+
 // Temporary allows the function import pass to disable always linking
 // referenced discardable symbols.
 static cl::opt<bool>
@@ -274,7 +280,8 @@ static void computeImportForFunction(
 static void ComputeImportForModule(
     const GVSummaryMapTy &DefinedGVSummaries, const ModuleSummaryIndex &Index,
     FunctionImporter::ImportMapTy &ImportList,
-    StringMap<FunctionImporter::ExportSetTy> *ExportLists = nullptr) {
+    StringMap<FunctionImporter::ExportSetTy> *ExportLists = nullptr,
+    const DenseSet<GlobalValue::GUID> *DeadSymbols = nullptr) {
   // Worklist contains the list of function imported in this module, for which
   // we will analyse the callees and may import further down the callgraph.
   SmallVector<EdgeInfo, 128> Worklist;
@@ -282,6 +289,10 @@ static void ComputeImportForModule(
   // Populate the worklist with the import for the functions in the current
   // module
   for (auto &GVSummary : DefinedGVSummaries) {
+    if (DeadSymbols && DeadSymbols->count(GVSummary.first)) {
+      DEBUG(dbgs() << "Ignores Dead GUID: " << GVSummary.first << "\n");
+      continue;
+    }
     auto *Summary = GVSummary.second;
     if (auto *AS = dyn_cast<AliasSummary>(Summary))
       Summary = &AS->getAliasee();
@@ -321,14 +332,15 @@ void llvm::ComputeCrossModuleImport(
     const ModuleSummaryIndex &Index,
     const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
     StringMap<FunctionImporter::ImportMapTy> &ImportLists,
-    StringMap<FunctionImporter::ExportSetTy> &ExportLists) {
+    StringMap<FunctionImporter::ExportSetTy> &ExportLists,
+    const DenseSet<GlobalValue::GUID> *DeadSymbols) {
   // For each module that has function defined, compute the import/export lists.
   for (auto &DefinedGVSummaries : ModuleToDefinedGVSummaries) {
     auto &ImportList = ImportLists[DefinedGVSummaries.first()];
     DEBUG(dbgs() << "Computing import for Module '"
                  << DefinedGVSummaries.first() << "'\n");
     ComputeImportForModule(DefinedGVSummaries.second, Index, ImportList,
-                           &ExportLists);
+                           &ExportLists, DeadSymbols);
   }
 
   // When computing imports we added all GUIDs referenced by anything
@@ -390,6 +402,86 @@ void llvm::ComputeCrossModuleImportForModule(
 #endif
 }
 
+DenseSet<GlobalValue::GUID> llvm::computeDeadSymbols(
+    const ModuleSummaryIndex &Index,
+    const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) {
+  if (!ComputeDead)
+    return DenseSet<GlobalValue::GUID>();
+  if (GUIDPreservedSymbols.empty())
+    // Don't do anything when nothing is live, this is friendly with tests.
+    return DenseSet<GlobalValue::GUID>();
+  DenseSet<GlobalValue::GUID> LiveSymbols = GUIDPreservedSymbols;
+  SmallVector<GlobalValue::GUID, 128> Worklist;
+  Worklist.reserve(LiveSymbols.size() * 2);
+  for (auto GUID : LiveSymbols) {
+    DEBUG(dbgs() << "Live root: " << GUID << "\n");
+    Worklist.push_back(GUID);
+  }
+  // Add values flagged in the index as live roots to the worklist.
+  for (const auto &Entry : Index) {
+    bool IsLiveRoot = llvm::any_of(
+        Entry.second,
+        [&](const std::unique_ptr<llvm::GlobalValueSummary> &Summary) {
+          return Summary->liveRoot();
+        });
+    if (!IsLiveRoot)
+      continue;
+    DEBUG(dbgs() << "Live root (summary): " << Entry.first << "\n");
+    Worklist.push_back(Entry.first);
+  }
+
+  while (!Worklist.empty()) {
+    auto GUID = Worklist.pop_back_val();
+    auto It = Index.findGlobalValueSummaryList(GUID);
+    if (It == Index.end()) {
+      DEBUG(dbgs() << "Not in index: " << GUID << "\n");
+      continue;
+    }
+
+    // FIXME: we should only make the prevailing copy live here
+    for (auto &Summary : It->second) {
+      for (auto Ref : Summary->refs()) {
+        auto RefGUID = Ref.getGUID();
+        if (LiveSymbols.insert(RefGUID).second) {
+          DEBUG(dbgs() << "Marking live (ref): " << RefGUID << "\n");
+          Worklist.push_back(RefGUID);
+        }
+      }
+      if (auto *FS = dyn_cast<FunctionSummary>(Summary.get())) {
+        for (auto Call : FS->calls()) {
+          auto CallGUID = Call.first.getGUID();
+          if (LiveSymbols.insert(CallGUID).second) {
+            DEBUG(dbgs() << "Marking live (call): " << CallGUID << "\n");
+            Worklist.push_back(CallGUID);
+          }
+        }
+      }
+      if (auto *AS = dyn_cast<AliasSummary>(Summary.get())) {
+        auto AliaseeGUID = AS->getAliasee().getOriginalName();
+        if (LiveSymbols.insert(AliaseeGUID).second) {
+          DEBUG(dbgs() << "Marking live (alias): " << AliaseeGUID << "\n");
+          Worklist.push_back(AliaseeGUID);
+        }
+      }
+    }
+  }
+  DenseSet<GlobalValue::GUID> DeadSymbols;
+  DeadSymbols.reserve(
+      std::min(Index.size(), Index.size() - LiveSymbols.size()));
+  for (auto &Entry : Index) {
+    auto GUID = Entry.first;
+    if (!LiveSymbols.count(GUID)) {
+      DEBUG(dbgs() << "Marking dead: " << GUID << "\n");
+      DeadSymbols.insert(GUID);
+    }
+  }
+  DEBUG(dbgs() << LiveSymbols.size() << " symbols Live, and "
+               << DeadSymbols.size() << " symbols Dead \n");
+  NumDeadSymbols += DeadSymbols.size();
+  NumLiveSymbols += LiveSymbols.size();
+  return DeadSymbols;
+}
+
 /// Compute the set of summaries needed for a ThinLTO backend compilation of
 /// \p ModulePath.
 void llvm::gatherImportedSummariesForModule(
@@ -648,9 +740,10 @@ Expected<bool> FunctionImporter::importFunctions(
       report_fatal_error("Function Import: link error");
 
     ImportedCount += GlobalsToImport.size();
+    NumImportedModules++;
   }
 
-  NumImported += ImportedCount;
+  NumImportedFunctions += ImportedCount;
 
   DEBUG(dbgs() << "Imported " << ImportedCount << " functions for Module "
                << DestModule.getModuleIdentifier() << "\n");

test/ThinLTO/X86/Inputs/deadstrip.ll

@@ -0,0 +1,22 @@
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.11.0"
+
+declare void @dead_func()
+
+; Called from a @dead_func() in the other file, should not be imported there
+; Ensure the cycle formed by calling @dead_func doesn't prevent stripping.
+define void @baz() {
+    call void @dead_func()
+    ret void
+}
+
+; Called via llvm.global_ctors, should be detected as live via the
+; marking of llvm.global_ctors as a live root in the index.
+define void @boo() {
+  ret void
+}
+
+define void @another_dead_func() {
+    call void @dead_func()
+    ret void
+}

test/ThinLTO/X86/deadstrip.ll

@@ -0,0 +1,109 @@
+; RUN: opt -module-summary %s -o %t1.bc
+; RUN: opt -module-summary %p/Inputs/deadstrip.ll -o %t2.bc
+; RUN: llvm-lto -thinlto-action=thinlink -o %t.index.bc %t1.bc %t2.bc
+
+; RUN: llvm-lto -exported-symbol=_main -thinlto-action=promote %t1.bc -thinlto-index=%t.index.bc -o - | llvm-lto -exported-symbol=_main -thinlto-action=internalize -thinlto-index %t.index.bc -thinlto-module-id=%t1.bc - -o - | llvm-dis -o - | FileCheck %s
+; RUN: llvm-lto -exported-symbol=_main -thinlto-action=promote %t2.bc -thinlto-index=%t.index.bc -o - | llvm-lto -exported-symbol=_main -thinlto-action=internalize -thinlto-index %t.index.bc -thinlto-module-id=%t2.bc - -o - | llvm-dis -o - | FileCheck %s --check-prefix=CHECK2
+
+; RUN: llvm-lto -exported-symbol=_main -thinlto-action=run %t1.bc %t2.bc
+; RUN: llvm-nm %t1.bc.thinlto.o | FileCheck %s --check-prefix=CHECK-NM
+
+; RUN: llvm-lto2 %t1.bc %t2.bc -o %t.out -save-temps \
+; RUN:   -r %t1.bc,_main,plx \
+; RUN:   -r %t1.bc,_bar,pl \
+; RUN:   -r %t1.bc,_dead_func,pl \
+; RUN:   -r %t1.bc,_baz,l \
+; RUN:   -r %t1.bc,_boo,l \
+; RUN:   -r %t2.bc,_baz,pl \
+; RUN:   -r %t2.bc,_boo,pl \
+; RUN:   -r %t2.bc,_dead_func,pl \
+; RUN:   -r %t2.bc,_another_dead_func,pl
+; RUN: llvm-dis < %t.out.0.3.import.bc | FileCheck %s
+; RUN: llvm-dis < %t.out.1.3.import.bc | FileCheck %s --check-prefix=CHECK2
+; RUN: llvm-nm %t.out.1 | FileCheck %s --check-prefix=CHECK2-NM
+
+; Dead-stripping on the index allows to internalize these,
+; and limit the import of @baz thanks to early pruning.
+; CHECK-NOT: available_externally {{.*}} @baz()
+; CHECK: @llvm.global_ctors =
+; CHECK: define internal void @_GLOBAL__I_a()
+; CHECK: define internal void @bar() {
+; CHECK: define internal void @bar_internal()
+; CHECK: define internal void @dead_func() {
+; CHECK-NOT: available_externally {{.*}} @baz()
+
+; Make sure we didn't internalize @boo, which is reachable via
+; llvm.global_ctors
+; CHECK2: define void @boo()
+; We should have eventually revoved @baz since it was internalized and unused
+; CHECK2-NM-NOT: _baz
+
+; The final binary should not contain any of the dead functions,
+; only main is expected because bar is expected to be inlined and stripped out.
+; CHECK-NM-NOT: bar
+; CHECK-NM-NOT: dead
+; CHECK-NM: T _main
+; CHECK-NM-NOT: bar
+; CHECK-NM-NOT: dead
+
+; Next test the case where Inputs/deadstrip.ll does not get a module index,
+; which will cause it to be handled by regular LTO in the new LTO API.
+; In that case there are uses of @dead_func in the regular LTO partition
+; and it shouldn't be internalized.
+; RUN: opt %p/Inputs/deadstrip.ll -o %t3.bc
+; RUN: llvm-lto2 %t1.bc %t3.bc -o %t4.out -save-temps \
+; RUN:   -r %t1.bc,_main,plx \
+; RUN:   -r %t1.bc,_bar,pl \
+; RUN:   -r %t1.bc,_dead_func,pl \
+; RUN:   -r %t1.bc,_baz,l \
+; RUN:   -r %t1.bc,_boo,l \
+; RUN:   -r %t3.bc,_baz,pl \
+; RUN:   -r %t3.bc,_boo,pl \
+; RUN:   -r %t3.bc,_dead_func,pl \
+; RUN:   -r %t3.bc,_another_dead_func,pl
+; RUN: llvm-dis < %t4.out.1.3.import.bc | FileCheck %s --check-prefix=CHECK-NOTDEAD
+; RUN: llvm-nm %t4.out.0 | FileCheck %s --check-prefix=CHECK-NM-NOTDEAD
+
+; We can't internalize @dead_func because of the use in the regular LTO
+; partition.
+; CHECK-NOTDEAD: define void @dead_func()
+; We also can't eliminate @baz because it is in the regular LTO partition
+; and called from @dead_func.
+; CHECK-NM-NOTDEAD: T _baz
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.11.0"
+
+
+@llvm.global_ctors = appending global [1 x { i32, void ()* }] [{ i32, void ()* } { i32 65535, void ()* @_GLOBAL__I_a }]
+
+declare void @baz()
+
+declare void @boo()
+
+define internal void @_GLOBAL__I_a() #1 section "__TEXT,__StaticInit,regular,pure_instructions" {
+entry:
+    call void @boo()
+    ret void
+}
+
+define void @bar() {
+    ret void
+}
+
+define internal void @bar_internal() {
+    ret void
+}
+
+define void @dead_func() {
+    call void @bar()
+    call void @baz()
+    call void @bar_internal()
+    ret void
+}
+
+define void @main() {
+    call void @bar()
+    call void @bar_internal()
+    ret void
+}