[C++20] [Modules] Introduce thin BMI

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -158,6 +158,8 @@ def err_drv_invalid_output_with_multiple_archs : Error<
 def err_drv_no_input_files : Error<"no input files">;
 def err_drv_output_argument_with_multiple_files : Error<
   "cannot specify -o when generating multiple output files">;
+def err_drv_thin_bmi_output_argument_with_multiple_files : Error <
+  "cannot specify -fthinBMI-output when generating multiple module files">;
 def err_drv_out_file_argument_with_multiple_sources : Error<
   "cannot specify '%0%1' when compiling multiple source files">;
 def err_no_external_assembler : Error<

clang/include/clang/Driver/Options.td

@@ -2915,6 +2915,11 @@ def fmodule_output : Flag<["-"], "fmodule-output">, Flags<[NoXarchOption]>,
   Visibility<[ClangOption, CC1Option]>,
   HelpText<"Save intermediate module file results when compiling a standard C++ module unit.">;
 
+def fthinBMI_output_EQ : Joined<["-"], "fthinBMI-output=">, Group<f_Group>,
+  HelpText<"Specify the output path for the thin BMI for C++20 Named modules">,
+  Visibility<[ClangOption, CC1Option, CLOption, DXCOption]>,
+  MarshallingInfoString<FrontendOpts<"ThinBMIPath">>;
+
 def fmodules_prune_interval : Joined<["-"], "fmodules-prune-interval=">, Group<i_Group>,
   Visibility<[ClangOption, CC1Option]>, MetaVarName<"<seconds>">,
   HelpText<"Specify the interval (in seconds) between attempts to prune the module cache">,
@@ -7223,7 +7228,9 @@ def ast_view : Flag<["-"], "ast-view">,
 def emit_module : Flag<["-"], "emit-module">,
   HelpText<"Generate pre-compiled module file from a module map">;
 def emit_module_interface : Flag<["-"], "emit-module-interface">,
-  HelpText<"Generate pre-compiled module file from a C++ module interface">;
+  HelpText<"Generate pre-compiled module file from a standard C++ module interface unit">;
+def emit_thin_module_interface : Flag<["-"], "emit-thin-module-interface">,
+  HelpText<"Generate reduced prebuilt module interface from a standard C++ module interface unit">;
 def emit_header_unit : Flag<["-"], "emit-header-unit">,
   HelpText<"Generate C++20 header units from header files">;
 def emit_pch : Flag<["-"], "emit-pch">,

clang/include/clang/Frontend/FrontendActions.h

@@ -118,6 +118,9 @@ class GenerateModuleAction : public ASTFrontendAction {
   CreateOutputFile(CompilerInstance &CI, StringRef InFile) = 0;
 
 protected:
+  std::vector<std::unique_ptr<ASTConsumer>>
+  CreateMultiplexConsumer(CompilerInstance &CI, StringRef InFile);
+
   std::unique_ptr<ASTConsumer> CreateASTConsumer(CompilerInstance &CI,
                                                  StringRef InFile) override;
 
@@ -147,14 +150,27 @@ class GenerateModuleFromModuleMapAction : public GenerateModuleAction {
   CreateOutputFile(CompilerInstance &CI, StringRef InFile) override;
 };
 
+/// Generates fatBMI (which contains full information to generate the object
+/// files) for C++20 Named Modules. Also generates the thin BMI (only contains
+/// necessary information for importers) if `-fthinBMI-output=`.
 class GenerateModuleInterfaceAction : public GenerateModuleAction {
-private:
+protected:
   bool BeginSourceFileAction(CompilerInstance &CI) override;
 
+  std::unique_ptr<ASTConsumer> CreateASTConsumer(CompilerInstance &CI,
+                                                 StringRef InFile) override;
+
   std::unique_ptr<raw_pwrite_stream>
   CreateOutputFile(CompilerInstance &CI, StringRef InFile) override;
 };
 
+/// Only generates the thin BMI. This action is mainly used by tests.
+class GenerateThinModuleInterfaceAction : public GenerateModuleInterfaceAction {
+private:
+  std::unique_ptr<ASTConsumer> CreateASTConsumer(CompilerInstance &CI,
+                                                 StringRef InFile) override;
+};
+
 class GenerateHeaderUnitAction : public GenerateModuleAction {
 
 private:

clang/include/clang/Frontend/FrontendOptions.h

@@ -85,9 +85,13 @@ enum ActionKind {
   /// Generate pre-compiled module from a module map.
   GenerateModule,
 
-  /// Generate pre-compiled module from a C++ module interface file.
+  /// Generate pre-compiled module from a standard C++ module interface unit.
   GenerateModuleInterface,
 
+  /// Generate reduced module interface for a standard C++ module interface
+  /// unit.
+  GenerateThinModuleInterface,
+
   /// Generate a C++20 header unit module from a header file.
   GenerateHeaderUnit,
 
@@ -549,6 +553,9 @@ class FrontendOptions {
   /// Path which stores the output files for -ftime-trace
   std::string TimeTracePath;
 
+  /// Path to the thin BMI for -fthinbmi-output=
+  std::string ThinBMIPath;
+
 public:
   FrontendOptions()
       : DisableFree(false), RelocatablePCH(false), ShowHelp(false),

clang/include/clang/Serialization/ASTWriter.h

@@ -166,6 +166,10 @@ class ASTWriter : public ASTDeserializationListener,
   /// Indicates that the AST contained compiler errors.
   bool ASTHasCompilerErrors = false;
 
+  /// Indicates that we're going to generate the reduced BMI for C++20
+  /// named modules.
+  bool GeneratingThinBMI = false;
+
   /// Mapping from input file entries to the index into the
   /// offset table where information about that input file is stored.
   llvm::DenseMap<const FileEntry *, uint32_t> InputFileIDs;
@@ -582,7 +586,8 @@ class ASTWriter : public ASTDeserializationListener,
   ASTWriter(llvm::BitstreamWriter &Stream, SmallVectorImpl<char> &Buffer,
             InMemoryModuleCache &ModuleCache,
             ArrayRef<std::shared_ptr<ModuleFileExtension>> Extensions,
-            bool IncludeTimestamps = true, bool BuildingImplicitModule = false);
+            bool IncludeTimestamps = true, bool BuildingImplicitModule = false,
+            bool GeneratingThinBMI = false);
   ~ASTWriter() override;
 
   ASTContext &getASTContext() const {
@@ -813,14 +818,22 @@ class PCHGenerator : public SemaConsumer {
   const ASTWriter &getWriter() const { return Writer; }
   SmallVectorImpl<char> &getPCH() const { return Buffer->Data; }
 
+  bool isComplete() const { return Buffer->IsComplete; }
+  PCHBuffer *getBufferPtr() { return Buffer.get(); }
+  StringRef getOutputFile() const { return OutputFile; }
+  DiagnosticsEngine &getDiagnostics() const {
+    return SemaPtr->getDiagnostics();
+  }
+
 public:
   PCHGenerator(const Preprocessor &PP, InMemoryModuleCache &ModuleCache,
                StringRef OutputFile, StringRef isysroot,
                std::shared_ptr<PCHBuffer> Buffer,
                ArrayRef<std::shared_ptr<ModuleFileExtension>> Extensions,
                bool AllowASTWithErrors = false, bool IncludeTimestamps = true,
                bool BuildingImplicitModule = false,
-               bool ShouldCacheASTInMemory = false);
+               bool ShouldCacheASTInMemory = false,
+               bool GeneratingThinBMI = false);
   ~PCHGenerator() override;
 
   void InitializeSema(Sema &S) override { SemaPtr = &S; }
@@ -830,6 +843,19 @@ class PCHGenerator : public SemaConsumer {
   bool hasEmittedPCH() const { return Buffer->IsComplete; }
 };
 
+class ThinBMIGenerator : public PCHGenerator {
+public:
+  ThinBMIGenerator(const Preprocessor &PP, InMemoryModuleCache &ModuleCache,
+                   StringRef OutputFile, std::shared_ptr<PCHBuffer> Buffer,
+                   bool IncludeTimestamps);
+
+  void HandleTranslationUnit(ASTContext &Ctx) override;
+};
+
+/// If the definition may impact the ABI. If yes, we're allowed to eliminate
+/// the definition of D in thin BMI.
+bool MayDefAffectABI(const Decl *D);
+
 /// A simple helper class to pack several bits in order into (a) 32 bit
 /// integer(s).
 class BitsPacker {

clang/lib/Driver/Driver.cpp

@@ -4086,6 +4086,13 @@ void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
     }
   }
 
+  // Diagnose misuse of -fthinBMI-output. It should be an error if we specify
+  // -fthinBMI-output with multiple precompilation jobs. Here we didn't check if
+  // there are multiple module units in the inputs.
+  if (C.getArgs().getLastArg(options::OPT_fthinBMI_output_EQ) &&
+      Inputs.size() > 1)
+    Diag(clang::diag::err_drv_thin_bmi_output_argument_with_multiple_files);
+
   handleArguments(C, Args, Inputs, Actions);
 
   bool UseNewOffloadingDriver =

clang/lib/Driver/ToolChains/Clang.cpp

@@ -3940,6 +3940,8 @@ static bool RenderModulesOptions(Compilation &C, const Driver &D,
   Args.ClaimAllArgs(options::OPT_fmodule_output);
   Args.ClaimAllArgs(options::OPT_fmodule_output_EQ);
 
+  Args.AddLastArg(CmdArgs, options::OPT_fthinBMI_output_EQ);
+
   return HaveModules;
 }
 

clang/lib/Frontend/CompilerInvocation.cpp

@@ -2554,6 +2554,7 @@ static const auto &getFrontendActionTable() {
 
       {frontend::GenerateModule, OPT_emit_module},
       {frontend::GenerateModuleInterface, OPT_emit_module_interface},
+      {frontend::GenerateThinModuleInterface, OPT_emit_thin_module_interface},
       {frontend::GenerateHeaderUnit, OPT_emit_header_unit},
       {frontend::GeneratePCH, OPT_emit_pch},
       {frontend::GenerateInterfaceStubs, OPT_emit_interface_stubs},
@@ -4236,6 +4237,7 @@ static bool isStrictlyPreprocessorAction(frontend::ActionKind Action) {
   case frontend::FixIt:
   case frontend::GenerateModule:
   case frontend::GenerateModuleInterface:
+  case frontend::GenerateThinModuleInterface:
   case frontend::GenerateHeaderUnit:
   case frontend::GeneratePCH:
   case frontend::GenerateInterfaceStubs:

clang/lib/Frontend/FrontendActions.cpp

@@ -184,12 +184,12 @@ bool GeneratePCHAction::BeginSourceFileAction(CompilerInstance &CI) {
   return true;
 }
 
-std::unique_ptr<ASTConsumer>
-GenerateModuleAction::CreateASTConsumer(CompilerInstance &CI,
-                                        StringRef InFile) {
+std::vector<std::unique_ptr<ASTConsumer>>
+GenerateModuleAction::CreateMultiplexConsumer(CompilerInstance &CI,
+                                              StringRef InFile) {
   std::unique_ptr<raw_pwrite_stream> OS = CreateOutputFile(CI, InFile);
   if (!OS)
-    return nullptr;
+    return {};
 
   std::string OutputFile = CI.getFrontendOpts().OutputFile;
   std::string Sysroot;
@@ -210,6 +210,17 @@ GenerateModuleAction::CreateASTConsumer(CompilerInstance &CI,
       +CI.getFrontendOpts().BuildingImplicitModule));
   Consumers.push_back(CI.getPCHContainerWriter().CreatePCHContainerGenerator(
       CI, std::string(InFile), OutputFile, std::move(OS), Buffer));
+  return std::move(Consumers);
+}
+
+std::unique_ptr<ASTConsumer>
+GenerateModuleAction::CreateASTConsumer(CompilerInstance &CI,
+                                        StringRef InFile) {
+  std::vector<std::unique_ptr<ASTConsumer>> Consumers =
+      CreateMultiplexConsumer(CI, InFile);
+  if (Consumers.empty())
+    return nullptr;
+
   return std::make_unique<MultiplexConsumer>(std::move(Consumers));
 }
 
@@ -264,6 +275,35 @@ GenerateModuleInterfaceAction::CreateOutputFile(CompilerInstance &CI,
   return CI.createDefaultOutputFile(/*Binary=*/true, InFile, "pcm");
 }
 
+static std::unique_ptr<ASTConsumer>
+CreateThinBMIGenerator(CompilerInstance &CI, StringRef OutputFile) {
+  auto Buffer = std::make_shared<PCHBuffer>();
+  return std::make_unique<ThinBMIGenerator>(
+      CI.getPreprocessor(), CI.getModuleCache(), OutputFile, Buffer,
+      /*IncludeTimestamps=*/+CI.getFrontendOpts().IncludeTimestamps);
+}
+
+std::unique_ptr<ASTConsumer>
+GenerateModuleInterfaceAction::CreateASTConsumer(CompilerInstance &CI,
+                                                 StringRef InFile) {
+  std::vector<std::unique_ptr<ASTConsumer>> Consumers =
+      CreateMultiplexConsumer(CI, InFile);
+  if (Consumers.empty())
+    return nullptr;
+
+  if (!CI.getFrontendOpts().ThinBMIPath.empty())
+    Consumers.push_back(
+        CreateThinBMIGenerator(CI, CI.getFrontendOpts().ThinBMIPath));
+
+  return std::make_unique<MultiplexConsumer>(std::move(Consumers));
+}
+
+std::unique_ptr<ASTConsumer>
+GenerateThinModuleInterfaceAction::CreateASTConsumer(CompilerInstance &CI,
+                                                     StringRef InFile) {
+  return CreateThinBMIGenerator(CI, CI.getFrontendOpts().OutputFile);
+}
+
 bool GenerateHeaderUnitAction::BeginSourceFileAction(CompilerInstance &CI) {
   if (!CI.getLangOpts().CPlusPlusModules) {
     CI.getDiagnostics().Report(diag::err_module_interface_requires_cpp_modules);
@@ -830,7 +870,6 @@ void DumpModuleInfoAction::ExecuteAction() {
 
   const LangOptions &LO = getCurrentASTUnit().getLangOpts();
   if (LO.CPlusPlusModules && !LO.CurrentModule.empty()) {
-
     ASTReader *R = getCurrentASTUnit().getASTReader().get();
     unsigned SubModuleCount = R->getTotalNumSubmodules();
     serialization::ModuleFile &MF = R->getModuleManager().getPrimaryModule();

clang/lib/FrontendTool/ExecuteCompilerInvocation.cpp

@@ -65,6 +65,8 @@ CreateFrontendBaseAction(CompilerInstance &CI) {
     return std::make_unique<GenerateModuleFromModuleMapAction>();
   case GenerateModuleInterface:
     return std::make_unique<GenerateModuleInterfaceAction>();
+  case GenerateThinModuleInterface:
+    return std::make_unique<GenerateThinModuleInterfaceAction>();
   case GenerateHeaderUnit:
     return std::make_unique<GenerateHeaderUnitAction>();
   case GeneratePCH:            return std::make_unique<GeneratePCHAction>();

clang/lib/Serialization/ASTWriter.cpp

@@ -4593,10 +4593,12 @@ ASTWriter::ASTWriter(llvm::BitstreamWriter &Stream,
                      SmallVectorImpl<char> &Buffer,
                      InMemoryModuleCache &ModuleCache,
                      ArrayRef<std::shared_ptr<ModuleFileExtension>> Extensions,
-                     bool IncludeTimestamps, bool BuildingImplicitModule)
+                     bool IncludeTimestamps, bool BuildingImplicitModule,
+                     bool GeneratingThinBMI)
     : Stream(Stream), Buffer(Buffer), ModuleCache(ModuleCache),
       IncludeTimestamps(IncludeTimestamps),
-      BuildingImplicitModule(BuildingImplicitModule) {
+      BuildingImplicitModule(BuildingImplicitModule),
+      GeneratingThinBMI(GeneratingThinBMI) {
   for (const auto &Ext : Extensions) {
     if (auto Writer = Ext->createExtensionWriter(*this))
       ModuleFileExtensionWriters.push_back(std::move(Writer));
@@ -5403,18 +5405,20 @@ void ASTWriter::WriteDeclUpdatesBlocks(RecordDataImpl &OffsetsRecord) {
 
     // Add a trailing update record, if any. These must go last because we
     // lazily load their attached statement.
-    if (HasUpdatedBody) {
-      const auto *Def = cast<FunctionDecl>(D);
-      Record.push_back(UPD_CXX_ADDED_FUNCTION_DEFINITION);
-      Record.push_back(Def->isInlined());
-      Record.AddSourceLocation(Def->getInnerLocStart());
-      Record.AddFunctionDefinition(Def);
-    } else if (HasAddedVarDefinition) {
-      const auto *VD = cast<VarDecl>(D);
-      Record.push_back(UPD_CXX_ADDED_VAR_DEFINITION);
-      Record.push_back(VD->isInline());
-      Record.push_back(VD->isInlineSpecified());
-      Record.AddVarDeclInit(VD);
+    if (!GeneratingThinBMI || MayDefAffectABI(D)) {
+      if (HasUpdatedBody) {
+        const auto *Def = cast<FunctionDecl>(D);
+        Record.push_back(UPD_CXX_ADDED_FUNCTION_DEFINITION);
+        Record.push_back(Def->isInlined());
+        Record.AddSourceLocation(Def->getInnerLocStart());
+        Record.AddFunctionDefinition(Def);
+      } else if (HasAddedVarDefinition) {
+        const auto *VD = cast<VarDecl>(D);
+        Record.push_back(UPD_CXX_ADDED_VAR_DEFINITION);
+        Record.push_back(VD->isInline());
+        Record.push_back(VD->isInlineSpecified());
+        Record.AddVarDeclInit(VD);
+      }
     }
 
     OffsetsRecord.push_back(GetDeclRef(D));