LTO: Hash type identifier resolutions for LowerTypeTests.

[tejohnson]

LGTM, with one comment request

llvm/lib/LTO/LTO.cpp

56 ↗

(On Diff #90396)

Document, specifically so that it is clear what the std::string here is.

llvm/trunk/include/llvm/IR/ModuleSummaryIndex.h

public:
 
   /// Check if the given Module has any functions available for exporting
   /// in the index. We consider any module present in the ModulePathStringTable
   /// to have exported functions.
   bool hasExportedFunctions(const Module &M) const {
     return ModulePathStringTable.count(M.getModuleIdentifier());
   }
 
+  const std::map<std::string, TypeIdSummary> &typeIds() const {
+    return TypeIdMap;
+  }
+
   TypeIdSummary &getTypeIdSummary(StringRef TypeId) {
     return TypeIdMap[TypeId];
   }
 
   /// Remove entries in the GlobalValueMap that have empty summaries due to the
   /// eager nature of map entry creation during VST parsing. These would
   /// also be suppressed during combined index generation in mergeFrom(),
   /// but if there was only one module or this was the first module we might

llvm/trunk/lib/LTO/LTO.cpp

 #include <set>
 
 using namespace llvm;
 using namespace lto;
 using namespace object;
 
 #define DEBUG_TYPE "lto"
 
+// The values are (type identifier, summary) pairs.
+typedef DenseMap<
+    GlobalValue::GUID,
+    TinyPtrVector<const std::pair<const std::string, TypeIdSummary> *>>
+    TypeIdSummariesByGuidTy;
+
 // Returns a unique hash for the Module considering the current list of
 // export/import and other global analysis results.
 // The hash is produced in \p Key.
 static void computeCacheKey(
     SmallString<40> &Key, const Config &Conf, const ModuleSummaryIndex &Index,
     StringRef ModuleID, const FunctionImporter::ImportMapTy &ImportList,
     const FunctionImporter::ExportSetTy &ExportList,
     const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
-    const GVSummaryMapTy &DefinedGlobals) {
+    const GVSummaryMapTy &DefinedGlobals,
+    const TypeIdSummariesByGuidTy &TypeIdSummariesByGuid) {
   // Compute the unique hash for this entry.
   // This is based on the current compiler version, the module itself, the
   // export list, the hash for every single module in the import list, the
   // list of ResolvedODR for the module, and the list of preserved symbols.
   SHA1 Hasher;
 
   // Start with the compiler revision
   Hasher.update(LLVM_VERSION_STRING);
#endif
   // Include the hash for the resolved ODR.
   for (auto &Entry : ResolvedODR) {
     Hasher.update(ArrayRef<uint8_t>((const uint8_t *)&Entry.first,
                                     sizeof(GlobalValue::GUID)));
     Hasher.update(ArrayRef<uint8_t>((const uint8_t *)&Entry.second,
                                     sizeof(GlobalValue::LinkageTypes)));
   }
 
+  std::set<GlobalValue::GUID> UsedTypeIds;
+
+  auto AddUsedTypeIds = [&](GlobalValueSummary *GS) {
+    auto *FS = dyn_cast_or_null<FunctionSummary>(GS);
+    if (!FS)
+      return;
+    for (auto &TT : FS->type_tests())
+      UsedTypeIds.insert(TT);
+    for (auto &TT : FS->type_test_assume_vcalls())
+      UsedTypeIds.insert(TT.GUID);
+    for (auto &TT : FS->type_checked_load_vcalls())
+      UsedTypeIds.insert(TT.GUID);
+    for (auto &TT : FS->type_test_assume_const_vcalls())
+      UsedTypeIds.insert(TT.VFunc.GUID);
+    for (auto &TT : FS->type_checked_load_const_vcalls())
+      UsedTypeIds.insert(TT.VFunc.GUID);
+  };
+
   // Include the hash for the linkage type to reflect internalization and weak
-  // resolution.
+  // resolution, and collect any used type identifier resolutions.
   for (auto &GS : DefinedGlobals) {
     GlobalValue::LinkageTypes Linkage = GS.second->linkage();
     Hasher.update(
         ArrayRef<uint8_t>((const uint8_t *)&Linkage, sizeof(Linkage)));
+    AddUsedTypeIds(GS.second);
+  }
+
+  // Imported functions may introduce new uses of type identifier resolutions,
+  // so we need to collect their used resolutions as well.
+  for (auto &ImpM : ImportList)
+    for (auto &ImpF : ImpM.second)
+      AddUsedTypeIds(Index.findSummaryInModule(ImpF.first, ImpM.first()));
+
+  auto AddTypeIdSummary = [&](StringRef TId, const TypeIdSummary &S) {
+    AddString(TId);
+
+    AddUnsigned(S.TTRes.TheKind);
+    AddUnsigned(S.TTRes.SizeM1BitWidth);
+  };
+
+  // Include the hash for all type identifiers used by this module.
+  for (GlobalValue::GUID TId : UsedTypeIds) {
+    auto SummariesI = TypeIdSummariesByGuid.find(TId);
+    if (SummariesI != TypeIdSummariesByGuid.end())
+      for (auto *Summary : SummariesI->second)
+        AddTypeIdSummary(Summary->first, Summary->second);
   }
 
   if (!Conf.SampleProfile.empty()) {
     auto FileOrErr = MemoryBuffer::getFile(Conf.SampleProfile);
     if (FileOrErr)
       Hasher.update(FileOrErr.get()->getBuffer());
   }
 
public:
   virtual Error wait() = 0;
 };
 
 namespace {
 class InProcessThinBackend : public ThinBackendProc {
   ThreadPool BackendThreadPool;
   AddStreamFn AddStream;
   NativeObjectCache Cache;
+  TypeIdSummariesByGuidTy TypeIdSummariesByGuid;
 
   Optional<Error> Err;
   std::mutex ErrMu;
 
 public:
   InProcessThinBackend(
       Config &Conf, ModuleSummaryIndex &CombinedIndex,
       unsigned ThinLTOParallelismLevel,
       const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
       AddStreamFn AddStream, NativeObjectCache Cache)
       : ThinBackendProc(Conf, CombinedIndex, ModuleToDefinedGVSummaries),
         BackendThreadPool(ThinLTOParallelismLevel),
-        AddStream(std::move(AddStream)), Cache(std::move(Cache)) {}
+        AddStream(std::move(AddStream)), Cache(std::move(Cache)) {
+    // Create a mapping from type identifier GUIDs to type identifier summaries.
+    // This allows backends to use the type identifier GUIDs stored in the
+    // function summaries to determine which type identifier summaries affect
+    // each function without needing to compute GUIDs in each backend.
+    for (auto &TId : CombinedIndex.typeIds())
+      TypeIdSummariesByGuid[GlobalValue::getGUID(TId.first)].push_back(&TId);
+  }
 
   Error runThinLTOBackendThread(
       AddStreamFn AddStream, NativeObjectCache Cache, unsigned Task,
       BitcodeModule BM, ModuleSummaryIndex &CombinedIndex,
       const FunctionImporter::ImportMapTy &ImportList,
       const FunctionImporter::ExportSetTy &ExportList,
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       const GVSummaryMapTy &DefinedGlobals,
-      MapVector<StringRef, BitcodeModule> &ModuleMap) {
+      MapVector<StringRef, BitcodeModule> &ModuleMap,
+      const TypeIdSummariesByGuidTy &TypeIdSummariesByGuid) {
     auto RunThinBackend = [&](AddStreamFn AddStream) {
       LTOLLVMContext BackendContext(Conf);
       Expected<std::unique_ptr<Module>> MOrErr = BM.parseModule(BackendContext);
       if (!MOrErr)
         return MOrErr.takeError();
 
       return thinBackend(Conf, Task, AddStream, **MOrErr, CombinedIndex,
                          ImportList, DefinedGlobals, ModuleMap);
     };
 
     auto ModuleID = BM.getModuleIdentifier();
 
     if (!Cache || !CombinedIndex.modulePaths().count(ModuleID) ||
         all_of(CombinedIndex.getModuleHash(ModuleID),
                [](uint32_t V) { return V == 0; }))
       // Cache disabled or no entry for this module in the combined index or
       // no module hash.
       return RunThinBackend(AddStream);
 
     SmallString<40> Key;
     // The module may be cached, this helps handling it.
     computeCacheKey(Key, Conf, CombinedIndex, ModuleID, ImportList, ExportList,
-                    ResolvedODR, DefinedGlobals);
+                    ResolvedODR, DefinedGlobals, TypeIdSummariesByGuid);
     if (AddStreamFn CacheAddStream = Cache(Task, Key))
       return RunThinBackend(CacheAddStream);
 
     return Error::success();
   }
 
   Error start(
       unsigned Task, BitcodeModule BM,
       const FunctionImporter::ImportMapTy &ImportList,
       const FunctionImporter::ExportSetTy &ExportList,
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       MapVector<StringRef, BitcodeModule> &ModuleMap) override {
     StringRef ModulePath = BM.getModuleIdentifier();
     assert(ModuleToDefinedGVSummaries.count(ModulePath));
     const GVSummaryMapTy &DefinedGlobals =
         ModuleToDefinedGVSummaries.find(ModulePath)->second;
     BackendThreadPool.async(
         [=](BitcodeModule BM, ModuleSummaryIndex &CombinedIndex,
             const FunctionImporter::ImportMapTy &ImportList,
             const FunctionImporter::ExportSetTy &ExportList,
             const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes>
                 &ResolvedODR,
             const GVSummaryMapTy &DefinedGlobals,
-            MapVector<StringRef, BitcodeModule> &ModuleMap) {
+            MapVector<StringRef, BitcodeModule> &ModuleMap,
+            const TypeIdSummariesByGuidTy &TypeIdSummariesByGuid) {
           Error E = runThinLTOBackendThread(
-              AddStream, Cache, Task, BM, CombinedIndex, ImportList,
-              ExportList, ResolvedODR, DefinedGlobals, ModuleMap);
+              AddStream, Cache, Task, BM, CombinedIndex, ImportList, ExportList,
+              ResolvedODR, DefinedGlobals, ModuleMap, TypeIdSummariesByGuid);
           if (E) {
             std::unique_lock<std::mutex> L(ErrMu);
             if (Err)
               Err = joinErrors(std::move(*Err), std::move(E));
             else
               Err = std::move(E);
           }
         },
-        BM, std::ref(CombinedIndex), std::ref(ImportList),
-        std::ref(ExportList), std::ref(ResolvedODR), std::ref(DefinedGlobals),
-        std::ref(ModuleMap));
+        BM, std::ref(CombinedIndex), std::ref(ImportList), std::ref(ExportList),
+        std::ref(ResolvedODR), std::ref(DefinedGlobals), std::ref(ModuleMap),
+        std::ref(TypeIdSummariesByGuid));
     return Error::success();
   }
 
   Error wait() override {
     BackendThreadPool.wait();
     if (Err)
       return std::move(*Err);
     else

llvm/trunk/test/ThinLTO/X86/Inputs/cache-typeid-resolutions-import.ll

+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i1 @importf1(i8* %p) {
+  %x = call i1 @f1(i8* %p)
+  ret i1 %x
+}
+
+declare i1 @f1(i8* %p)

llvm/trunk/test/ThinLTO/X86/Inputs/cache-typeid-resolutions1.ll

+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@vt1 = constant i32 0, !type !0
+
+!0 = !{i32 0, !"typeid1"}

llvm/trunk/test/ThinLTO/X86/cache-typeid-resolutions.ll

+; RUN: opt -module-hash -module-summary %s -o %t.bc
+; RUN: opt -module-hash -module-summary %S/Inputs/cache-typeid-resolutions-import.ll -o %t-import.bc
+
+; RUN: llvm-as -o %t1.bc %S/Inputs/cache-typeid-resolutions1.ll
+
+; Two resolutions for typeid1: Unsat, Single
+; where both t and t-import are sensitive to typeid1's resolution
+; so 4 distinct objects in total.
+; RUN: rm -rf %t.cache
+; RUN: llvm-lto2 -o %t.o %t.bc %t-import.bc -cache-dir %t.cache -r=%t.bc,f1,plx -r=%t-import.bc,importf1,plx -r=%t-import.bc,f1,lx
+; RUN: llvm-lto2 -o %t.o %t.bc %t-import.bc %t1.bc -cache-dir %t.cache -r=%t.bc,f1,plx -r=%t-import.bc,importf1,plx -r=%t-import.bc,f1,lx -r=%t1.bc,vt1,plx
+; RUN: ls %t.cache | count 4
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i1 @f1(i8* %p) {
+  %x = call i1 @llvm.type.test(i8* %p, metadata !"typeid1")
+  ret i1 %x
+}
+
+declare i1 @llvm.type.test(i8*, metadata)