Reland [clang][modules-driver] Add scanner to detect C++20 module presence

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -577,6 +577,13 @@ def err_drv_reduced_module_output_overrided : Warning<
   "please consider use '-fmodule-output=' to specify the output file for reduced BMI explicitly">,
   InGroup<DiagGroup<"reduced-bmi-output-overrided">>;
 
+def remark_found_cxx20_module_usage : Remark<
+  "found C++20 module usage in file '%0'">,
+  InGroup<ModulesDriver>;
+def remark_performing_driver_managed_module_build : Remark<
+  "performing driver managed module build">,
+  InGroup<ModulesDriver>;
+
 def warn_drv_delayed_template_parsing_after_cxx20 : Warning<
   "-fdelayed-template-parsing is deprecated after C++20">,
   InGroup<DiagGroup<"delayed-template-parsing-in-cxx20">>;

clang/include/clang/Basic/DiagnosticGroups.td

@@ -628,6 +628,7 @@ def ModuleConflict : DiagGroup<"module-conflict">;
 def ModuleFileExtension : DiagGroup<"module-file-extension">;
 def ModuleIncludeDirectiveTranslation : DiagGroup<"module-include-translation">;
 def ModuleMap : DiagGroup<"module-map">;
+def ModulesDriver : DiagGroup<"modules-driver">;
 def RoundTripCC1Args : DiagGroup<"round-trip-cc1-args">;
 def NewlineEOF : DiagGroup<"newline-eof">;
 def Nullability : DiagGroup<"nullability">;

clang/include/clang/Driver/Driver.h

@@ -504,6 +504,9 @@ class Driver {
 
   /// BuildActions - Construct the list of actions to perform for the
   /// given arguments, which are only done for a single architecture.
+  /// If the compilation is an explicit module build, delegates to
+  /// BuildDriverManagedModuleBuildActions. Otherwise, BuildDefaultActions is
+  /// used.
   ///
   /// \param C - The compilation that is being built.
   /// \param Args - The input arguments.
@@ -789,6 +792,35 @@ class Driver {
   /// compilation based on which -f(no-)?lto(=.*)? option occurs last.
   void setLTOMode(const llvm::opt::ArgList &Args);
 
+  /// BuildDefaultActions - Constructs the list of actions to perform
+  /// for the provided arguments, which are only done for a single architecture.
+  ///
+  /// \param C - The compilation that is being built.
+  /// \param Args - The input arguments.
+  /// \param Actions - The list to store the resulting actions onto.
+  void BuildDefaultActions(Compilation &C, llvm::opt::DerivedArgList &Args,
+                           const InputList &Inputs, ActionList &Actions) const;
+
+  /// BuildDriverManagedModuleBuildActions - Performs a dependency
+  /// scan and constructs the list of actions to perform for dependency order
+  /// and the provided arguments. This is only done for a single a architecture.
+  ///
+  /// \param C - The compilation that is being built.
+  /// \param Args - The input arguments.
+  /// \param Actions - The list to store the resulting actions onto.
+  void BuildDriverManagedModuleBuildActions(Compilation &C,
+                                            llvm::opt::DerivedArgList &Args,
+                                            const InputList &Inputs,
+                                            ActionList &Actions) const;
+
+  /// Scans the leading lines of the C++ source inputs to detect C++20 module
+  /// usage.
+  ///
+  /// \returns True if module usage is detected, false otherwise, or an error on
+  /// read failure.
+  llvm::ErrorOr<bool>
+  ScanInputsForCXX20ModulesUsage(const InputList &Inputs) const;
+
   /// Retrieves a ToolChain for a particular \p Target triple.
   ///
   /// Will cache ToolChains for the life of the driver object, and create them

clang/include/clang/Driver/Options.td

@@ -3262,6 +3262,13 @@ def modules_reduced_bmi : Flag<["-"], "fmodules-reduced-bmi">,
   HelpText<"Generate the reduced BMI">,
   MarshallingInfoFlag<FrontendOpts<"GenReducedBMI">>;
 
+def fmodules_driver : Flag<["-"], "fmodules-driver">,
+  Group<f_Group>, Visibility<[ClangOption]>,
+  HelpText<"Enable support for driver managed module builds (experimental)">;
+def fno_modules_driver : Flag<["-"], "fno-modules-driver">,
+  Group<f_Group>, Visibility<[ClangOption]>,
+  HelpText<"Disable support for driver managed module builds (experimental)">;
+
 def experimental_modules_reduced_bmi : Flag<["-"], "fexperimental-modules-reduced-bmi">,
   Group<f_Group>, Visibility<[ClangOption, CC1Option]>, Alias<modules_reduced_bmi>;
 

clang/include/clang/Lex/DependencyDirectivesScanner.h

@@ -136,6 +136,13 @@ void printDependencyDirectivesAsSource(
     ArrayRef<dependency_directives_scan::Directive> Directives,
     llvm::raw_ostream &OS);
 
+/// Scan an input source buffer for C++20 named module usage.
+///
+/// \param Source The input source buffer.
+///
+/// \returns true if any C++20 named modules related directive was found.
+bool scanInputForCXX20ModulesUsage(StringRef Source);
+
 /// Functor that returns the dependency directives for a given file.
 class DependencyDirectivesGetter {
 public:

clang/lib/Driver/Driver.cpp

@@ -66,6 +66,7 @@
 #include "clang/Driver/Tool.h"
 #include "clang/Driver/ToolChain.h"
 #include "clang/Driver/Types.h"
+#include "clang/Lex/DependencyDirectivesScanner.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/StringExtras.h"
@@ -4290,6 +4291,12 @@ void Driver::handleArguments(Compilation &C, DerivedArgList &Args,
     YcArg = nullptr;
   }
 
+  if (Args.hasArgNoClaim(options::OPT_fmodules_driver))
+    // TODO: Check against all incompatible -fmodules-driver arguments
+    if (!ModulesModeCXX20) {
+      Args.eraseArg(options::OPT_fmodules_driver);
+    }
+
   Arg *FinalPhaseArg;
   phases::ID FinalPhase = getFinalPhase(Args, &FinalPhaseArg);
 
@@ -4416,6 +4423,35 @@ void Driver::handleArguments(Compilation &C, DerivedArgList &Args,
   }
 }
 
+static bool hasCXXModuleInputType(const Driver::InputList &Inputs) {
+  const auto IsTypeCXXModule = [](const auto &Input) -> bool {
+    const auto TypeID = Input.first;
+    return (TypeID == types::TY_CXXModule);
+  };
+  return llvm::any_of(Inputs, IsTypeCXXModule);
+}
+
+llvm::ErrorOr<bool>
+Driver::ScanInputsForCXX20ModulesUsage(const InputList &Inputs) const {
+  const auto CXXInputs = llvm::make_filter_range(
+      Inputs, [](const auto &Input) { return types::isCXX(Input.first); });
+
+  for (const auto &Input : CXXInputs) {
+    StringRef Filename = Input.second->getSpelling();
+    auto ErrOrBuffer = VFS->getBufferForFile(Filename);
+    if (!ErrOrBuffer)
+      return ErrOrBuffer.getError();
+    const auto Buffer = std::move(*ErrOrBuffer);
+
+    if (scanInputForCXX20ModulesUsage(Buffer->getBuffer())) {
+      Diags.Report(diag::remark_found_cxx20_module_usage) << Filename;
+      return true;
+    }
+  }
+
+  return false;
+}
+
 void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
                           const InputList &Inputs, ActionList &Actions) const {
   llvm::PrettyStackTraceString CrashInfo("Building compilation actions");
@@ -4427,6 +4463,33 @@ void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
 
   handleArguments(C, Args, Inputs, Actions);
 
+  if (Args.hasFlag(options::OPT_fmodules_driver,
+                   options::OPT_fno_modules_driver, false)) {
+    // TODO: Move the logic for implicitly enabling explicit-module-builds out
+    // of -fmodules-driver once it is no longer experimental.
+    // Currently, this serves diagnostic purposes only.
+    bool UsesCXXModules = hasCXXModuleInputType(Inputs);
+    if (!UsesCXXModules) {
+      const auto ErrOrScanResult = ScanInputsForCXX20ModulesUsage(Inputs);
+      if (!ErrOrScanResult) {
+        Diags.Report(diag::err_cannot_open_file)
+            << ErrOrScanResult.getError().message();
+        return;
+      }
+      UsesCXXModules = *ErrOrScanResult;
+    }
+    if (UsesCXXModules)
+      BuildDriverManagedModuleBuildActions(C, Args, Inputs, Actions);
+    return;
+  }
+
+  BuildDefaultActions(C, Args, Inputs, Actions);
+}
+
+void Driver::BuildDefaultActions(Compilation &C, DerivedArgList &Args,
+                                 const InputList &Inputs,
+                                 ActionList &Actions) const {
+
   bool UseNewOffloadingDriver =
       C.isOffloadingHostKind(Action::OFK_OpenMP) ||
       C.isOffloadingHostKind(Action::OFK_SYCL) ||
@@ -4710,6 +4773,13 @@ void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
   Args.ClaimAllArgs(options::OPT_cl_ignored_Group);
 }
 
+void Driver::BuildDriverManagedModuleBuildActions(
+    Compilation &C, llvm::opt::DerivedArgList &Args, const InputList &Inputs,
+    ActionList &Actions) const {
+  Diags.Report(diag::remark_performing_driver_managed_module_build);
+  return;
+}
+
 /// Returns the canonical name for the offloading architecture when using a HIP
 /// or CUDA architecture.
 static StringRef getCanonicalArchString(Compilation &C,

clang/lib/Lex/DependencyDirectivesScanner.cpp

@@ -83,6 +83,8 @@ struct Scanner {
   /// \returns True on error.
   bool scan(SmallVectorImpl<Directive> &Directives);
 
+  friend bool clang::scanInputForCXX20ModulesUsage(StringRef Source);
+
 private:
   /// Lexes next token and advances \p First and the \p Lexer.
   [[nodiscard]] dependency_directives_scan::Token &
@@ -1075,3 +1077,50 @@ void clang::printDependencyDirectivesAsSource(
     }
   }
 }
+
+static void skipUntilMaybeCXX20ModuleDirective(const char *&First,
+                                               const char *const End) {
+  assert(First <= End);
+  while (First != End) {
+    if (*First == '#') {
+      ++First;
+      skipToNewlineRaw(First, End);
+    }
+    skipWhitespace(First, End);
+    if (const auto Len = isEOL(First, End)) {
+      First += Len;
+      continue;
+    }
+    break;
+  }
+}
+
+bool clang::scanInputForCXX20ModulesUsage(StringRef Source) {
+  const char *First = Source.begin();
+  const char *const End = Source.end();
+  skipUntilMaybeCXX20ModuleDirective(First, End);
+  if (First == End)
+    return false;
+
+  // Check if the next token can even be a module directive before creating a
+  // full lexer.
+  if (!(*First == 'i' || *First == 'e' || *First == 'm'))
+    return false;
+
+  llvm::SmallVector<dependency_directives_scan::Token> Tokens;
+  Scanner S(StringRef(First, End - First), Tokens, nullptr, SourceLocation());
+  if (S.lexModule(First, End))
+    return false;
+  auto IsCXXNamedModuleDirective = [](const DirectiveWithTokens &D) {
+    switch (D.Kind) {
+    case dependency_directives_scan::cxx_module_decl:
+    case dependency_directives_scan::cxx_import_decl:
+    case dependency_directives_scan::cxx_export_module_decl:
+    case dependency_directives_scan::cxx_export_import_decl:
+      return true;
+    default:
+      return false;
+    }
+  };
+  return llvm::any_of(S.DirsWithToks, IsCXXNamedModuleDirective);
+}