[ThinLTO] Add per-module indexes to combined index consistently

[tejohnson]

Summary

Without this change we only add module paths to the combined index when
there is a module hash or at least one global value. Make this more
consistent by adding the module to the index whenever there is a summary
section, and it is a per-module summary (had a MODULE_CODE_SOURCE_FILENAME
record).

Since we will no longer add module paths lazily, add a new interface to get
the module info from the index that asserts it is already added.

Fixes PR37899.

[pcc]

lib/Bitcode/Reader/BitcodeReader.cpp

4812

Can we make this function return void now?

[tejohnson]

Address comment

include/llvm/IR/ModuleSummaryIndex.h

public:
 
   /// Add a new module with the given \p Hash, mapped to the given \p
   /// ModID, and return a reference to the module.
   ModuleInfo *addModule(StringRef ModPath, uint64_t ModId,
                         ModuleHash Hash = ModuleHash{{0}}) {
     return &*ModulePathStringTable.insert({ModPath, {ModId, Hash}}).first;
   }
 
+  /// Return module entry for module with the given \p ModPath.
+  ModuleInfo *getModule(StringRef ModPath) {
+    auto It = ModulePathStringTable.find(ModPath);
+    assert(It != ModulePathStringTable.end() && "Module not registered");
+    return &*It;
+  }
+
   /// 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 {

lib/Bitcode/Reader/BitcodeReader.cpp

std::vector<FunctionSummary::EdgeTy> makeCallList(ArrayRef<uint64_t> Record,
                                                     bool HasRelBF);
   Error parseEntireSummary(unsigned ID);
   Error parseModuleStringTable();
 
   std::pair<ValueInfo, GlobalValue::GUID>
   getValueInfoFromValueId(unsigned ValueId);
 
   ModuleSummaryIndex::ModuleInfo *addThisModule();
+  ModuleSummaryIndex::ModuleInfo *getThisModule();
 };
 
 } // end anonymous namespace
 
 std::error_code llvm::errorToErrorCodeAndEmitErrors(LLVMContext &Ctx,
                                                     Error Err) {
   if (Err) {
     std::error_code EC;

 
 ModuleSummaryIndexBitcodeReader::ModuleSummaryIndexBitcodeReader(
     BitstreamCursor Cursor, StringRef Strtab, ModuleSummaryIndex &TheIndex,
     StringRef ModulePath, unsigned ModuleId)
     : BitcodeReaderBase(std::move(Cursor), Strtab), TheIndex(TheIndex),
       ModulePath(ModulePath), ModuleId(ModuleId) {}
 
 ModuleSummaryIndex::ModuleInfo *
 ModuleSummaryIndexBitcodeReader::addThisModule() {
   return TheIndex.addModule(ModulePath, ModuleId);
 }
 
+ModuleSummaryIndex::ModuleInfo *
+ModuleSummaryIndexBitcodeReader::getThisModule() {
+  return TheIndex.getModule(ModulePath);
+}
+
 std::pair<ValueInfo, GlobalValue::GUID>
 ModuleSummaryIndexBitcodeReader::getValueInfoFromValueId(unsigned ValueId) {
   auto VGI = ValueIdToValueInfoMap[ValueId];
   assert(VGI.first);
   return VGI;
 }
 
 void ModuleSummaryIndexBitcodeReader::setValueGUID(
case BitstreamEntry::SubBlock:
         assert(((SeenValueSymbolTable && VSTOffset > 0) ||
                 !SeenGlobalValSummary) &&
                "Expected early VST parse via VSTOffset record");
         if (Stream.SkipBlock())
           return error("Invalid record");
         break;
       case bitc::GLOBALVAL_SUMMARY_BLOCK_ID:
       case bitc::FULL_LTO_GLOBALVAL_SUMMARY_BLOCK_ID:
+        // Add the module if it is a per-module index (has a source file name).
+        if (!SourceFileName.empty())
+          addThisModule();
         assert(!SeenValueSymbolTable &&
                "Already read VST when parsing summary block?");
         // We might not have a VST if there were no values in the
         // summary. An empty summary block generated when we are
         // performing ThinLTO compiles so we don't later invoke
         // the regular LTO process on them.
         if (VSTOffset > 0) {
           if (Error Err = parseValueSymbolTable(VSTOffset, ValueIdToLinkageMap))
case BitstreamEntry::Record: {
             return error("Invalid record");
           SourceFileName = ValueName.c_str();
           break;
         }
         /// MODULE_CODE_HASH: [5*i32]
         case bitc::MODULE_CODE_HASH: {
           if (Record.size() != 5)
             return error("Invalid hash length " + Twine(Record.size()).str());
-          auto &Hash = addThisModule()->second.second;
+          auto &Hash = getThisModule()->second.second;
           int Pos = 0;
           for (auto &Val : Record) {
             assert(!(Val >> 32) && "Unexpected high bits set");
             Hash[Pos++] = Val;
           }
           break;
         }
         /// MODULE_CODE_VSTOFFSET: [offset]
case bitc::FS_PERMODULE_PROFILE: {
           std::move(PendingTypeTestAssumeConstVCalls),
           std::move(PendingTypeCheckedLoadConstVCalls));
       PendingTypeTests.clear();
       PendingTypeTestAssumeVCalls.clear();
       PendingTypeCheckedLoadVCalls.clear();
       PendingTypeTestAssumeConstVCalls.clear();
       PendingTypeCheckedLoadConstVCalls.clear();
       auto VIAndOriginalGUID = getValueInfoFromValueId(ValueID);
-      FS->setModulePath(addThisModule()->first());
+      FS->setModulePath(getThisModule()->first());
       FS->setOriginalName(VIAndOriginalGUID.second);
       TheIndex.addGlobalValueSummary(VIAndOriginalGUID.first, std::move(FS));
       break;
     }
     // FS_ALIAS: [valueid, flags, valueid]
     // Aliases must be emitted (and parsed) after all FS_PERMODULE entries, as
     // they expect all aliasee summaries to be available.
     case bitc::FS_ALIAS: {
       unsigned ValueID = Record[0];
       uint64_t RawFlags = Record[1];
       unsigned AliaseeID = Record[2];
       auto Flags = getDecodedGVSummaryFlags(RawFlags, Version);
       auto AS = llvm::make_unique<AliasSummary>(Flags);
       // The module path string ref set in the summary must be owned by the
       // index's module string table. Since we don't have a module path
       // string table section in the per-module index, we create a single
       // module path string table entry with an empty (0) ID to take
       // ownership.
-      AS->setModulePath(addThisModule()->first());
+      AS->setModulePath(getThisModule()->first());
 
       GlobalValue::GUID AliaseeGUID =
           getValueInfoFromValueId(AliaseeID).first.getGUID();
       auto AliaseeInModule =
           TheIndex.findSummaryInModule(AliaseeGUID, ModulePath);
       if (!AliaseeInModule)
         return error("Alias expects aliasee summary to be parsed");
       AS->setAliasee(AliaseeInModule);
       AS->setAliaseeGUID(AliaseeGUID);
 
       auto GUID = getValueInfoFromValueId(ValueID);
       AS->setOriginalName(GUID.second);
       TheIndex.addGlobalValueSummary(GUID.first, std::move(AS));
       break;
     }
     // FS_PERMODULE_GLOBALVAR_INIT_REFS: [valueid, flags, n x valueid]
     case bitc::FS_PERMODULE_GLOBALVAR_INIT_REFS: {
       unsigned ValueID = Record[0];
       uint64_t RawFlags = Record[1];
       auto Flags = getDecodedGVSummaryFlags(RawFlags, Version);
       std::vector<ValueInfo> Refs =
           makeRefList(ArrayRef<uint64_t>(Record).slice(2));
       auto FS = llvm::make_unique<GlobalVarSummary>(Flags, std::move(Refs));
-      FS->setModulePath(addThisModule()->first());
+      FS->setModulePath(getThisModule()->first());
       auto GUID = getValueInfoFromValueId(ValueID);
       FS->setOriginalName(GUID.second);
       TheIndex.addGlobalValueSummary(GUID.first, std::move(FS));
       break;
     }
     // FS_COMBINED: [valueid, modid, flags, instcount, fflags, numrefs,
     //               numrefs x valueid, n x (valueid)]
     // FS_COMBINED_PROFILE: [valueid, modid, flags, instcount, fflags, numrefs,

test/LTO/Resolution/X86/mod-asm-used.ll

 ; RUN: opt -module-summary -o %t.bc %s
 ; RUN: opt -module-summary -o %t2.bc %S/Inputs/mod-asm-used.ll
-; RUN: llvm-lto2 run %t.bc -r %t.bc,foo,l %t2.bc -r %t2.bc,foo,pl -o %t3
-; RUN: llvm-nm %t3.* | FileCheck %s
+; RUN: llvm-lto2 run %t.bc -r %t.bc,foo,l %t2.bc -r %t2.bc,foo,pl -o %t3 -save-temps
+; RUN: llvm-nm %t3.? | FileCheck %s
+
+; RUN: llvm-dis %t3.index.bc -o - | FileCheck %s --check-prefix=INDEX
+; INDEX: ^0 = module: (path: "{{.*}}mod-asm-used.ll.tmp.bc"
+; INDEX: ^1 = module: (path: "{{.*}}mod-asm-used.ll.tmp2.bc"
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; CHECK: D foo
 module asm ".quad foo"