vendor/llvm-project/llvmorg-14-init-10186-gff7f2cfa959b

4 files changed, 196 insertions, 127 deletions

diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScanningService.cpp b/clang/lib/Tooling/DependencyScanning/DependencyScanningService.cpp
index 4f3e574719d2..4b6c87aba62f 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScanningService.cpp
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScanningService.cpp
@@ -15,9 +15,9 @@ using namespace dependencies;
 
 DependencyScanningService::DependencyScanningService(
     ScanningMode Mode, ScanningOutputFormat Format, bool ReuseFileManager,
-    bool SkipExcludedPPRanges)
+    bool SkipExcludedPPRanges, bool OptimizeArgs)
     : Mode(Mode), Format(Format), ReuseFileManager(ReuseFileManager),
-      SkipExcludedPPRanges(SkipExcludedPPRanges) {
+      SkipExcludedPPRanges(SkipExcludedPPRanges), OptimizeArgs(OptimizeArgs) {
   // Initialize targets for object file support.
   llvm::InitializeAllTargets();
   llvm::InitializeAllTargetMCs();
diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScanningTool.cpp b/clang/lib/Tooling/DependencyScanning/DependencyScanningTool.cpp
index 2fd12f7e12b1..739712baadd0 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScanningTool.cpp
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScanningTool.cpp
@@ -24,8 +24,6 @@ std::vector<std::string> FullDependencies::getAdditionalArgs(
       ClangModuleDeps, LookupPCMPath, LookupModuleDeps, PCMPaths, ModMapPaths);
   for (const std::string &PCMPath : PCMPaths)
     Ret.push_back("-fmodule-file=" + PCMPath);
-  for (const std::string &ModMapPath : ModMapPaths)
-    Ret.push_back("-fmodule-map-file=" + ModMapPath);
 
   return Ret;
 }
@@ -37,10 +35,8 @@ FullDependencies::getAdditionalArgsWithoutModulePaths() const {
       "-fno-implicit-module-maps",
   };
 
-  for (const PrebuiltModuleDep &PMD : PrebuiltModuleDeps) {
-    Args.push_back("-fmodule-file=" + PMD.ModuleName + "=" + PMD.PCMFile);
-    Args.push_back("-fmodule-map-file=" + PMD.ModuleMapFile);
-  }
+  for (const PrebuiltModuleDep &PMD : PrebuiltModuleDeps)
+    Args.push_back("-fmodule-file=" + PMD.PCMFile);
 
   return Args;
 }
@@ -50,7 +46,8 @@ DependencyScanningTool::DependencyScanningTool(
     : Worker(Service) {}
 
 llvm::Expected<std::string> DependencyScanningTool::getDependencyFile(
-    const tooling::CompilationDatabase &Compilations, StringRef CWD) {
+    const std::vector<std::string> &CommandLine, StringRef CWD,
+    llvm::Optional<StringRef> ModuleName) {
   /// Prints out all of the gathered dependencies into a string.
   class MakeDependencyPrinterConsumer : public DependencyConsumer {
   public:
@@ -102,17 +99,9 @@ llvm::Expected<std::string> DependencyScanningTool::getDependencyFile(
     std::vector<std::string> Dependencies;
   };
 
-  // We expect a single command here because if a source file occurs multiple
-  // times in the original CDB, then `computeDependencies` would run the
-  // `DependencyScanningAction` once for every time the input occured in the
-  // CDB. Instead we split up the CDB into single command chunks to avoid this
-  // behavior.
-  assert(Compilations.getAllCompileCommands().size() == 1 &&
-         "Expected a compilation database with a single command!");
-  std::string Input = Compilations.getAllCompileCommands().front().Filename;
-
   MakeDependencyPrinterConsumer Consumer;
-  auto Result = Worker.computeDependencies(Input, CWD, Compilations, Consumer);
+  auto Result =
+      Worker.computeDependencies(CWD, CommandLine, Consumer, ModuleName);
   if (Result)
     return std::move(Result);
   std::string Output;
@@ -122,8 +111,9 @@ llvm::Expected<std::string> DependencyScanningTool::getDependencyFile(
 
 llvm::Expected<FullDependenciesResult>
 DependencyScanningTool::getFullDependencies(
-    const tooling::CompilationDatabase &Compilations, StringRef CWD,
-    const llvm::StringSet<> &AlreadySeen) {
+    const std::vector<std::string> &CommandLine, StringRef CWD,
+    const llvm::StringSet<> &AlreadySeen,
+    llvm::Optional<StringRef> ModuleName) {
   class FullDependencyPrinterConsumer : public DependencyConsumer {
   public:
     FullDependencyPrinterConsumer(const llvm::StringSet<> &AlreadySeen)
@@ -180,24 +170,15 @@ DependencyScanningTool::getFullDependencies(
   private:
     std::vector<std::string> Dependencies;
     std::vector<PrebuiltModuleDep> PrebuiltModuleDeps;
-    std::unordered_map<std::string, ModuleDeps> ClangModuleDeps;
+    std::map<std::string, ModuleDeps> ClangModuleDeps;
     std::string ContextHash;
     std::vector<std::string> OutputPaths;
     const llvm::StringSet<> &AlreadySeen;
   };
 
-  // We expect a single command here because if a source file occurs multiple
-  // times in the original CDB, then `computeDependencies` would run the
-  // `DependencyScanningAction` once for every time the input occured in the
-  // CDB. Instead we split up the CDB into single command chunks to avoid this
-  // behavior.
-  assert(Compilations.getAllCompileCommands().size() == 1 &&
-         "Expected a compilation database with a single command!");
-  std::string Input = Compilations.getAllCompileCommands().front().Filename;
-
   FullDependencyPrinterConsumer Consumer(AlreadySeen);
   llvm::Error Result =
-      Worker.computeDependencies(Input, CWD, Compilations, Consumer);
+      Worker.computeDependencies(CWD, CommandLine, Consumer, ModuleName);
   if (Result)
     return std::move(Result);
   return Consumer.getFullDependencies();
diff --git a/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp b/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
index d651ff23b387..7fdc49271791 100644
--- a/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
+++ b/clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp
@@ -133,6 +133,16 @@ deduceDepTarget(const std::string &OutputFile,
   return makeObjFileName(InputFiles.front().getFile());
 }
 
+/// Sanitize diagnostic options for dependency scan.
+static void sanitizeDiagOpts(DiagnosticOptions &DiagOpts) {
+  // Don't print 'X warnings and Y errors generated'.
+  DiagOpts.ShowCarets = false;
+  // Don't write out diagnostic file.
+  DiagOpts.DiagnosticSerializationFile.clear();
+  // Don't treat warnings as errors.
+  DiagOpts.Warnings.push_back("no-error");
+}
+
 /// A clang tool that runs the preprocessor in a mode that's optimized for
 /// dependency scanning for the given compiler invocation.
 class DependencyScanningAction : public tooling::ToolAction {
@@ -141,10 +151,11 @@ public:
       StringRef WorkingDirectory, DependencyConsumer &Consumer,
       llvm::IntrusiveRefCntPtr<DependencyScanningWorkerFilesystem> DepFS,
       ExcludedPreprocessorDirectiveSkipMapping *PPSkipMappings,
-      ScanningOutputFormat Format)
+      ScanningOutputFormat Format, bool OptimizeArgs,
+      llvm::Optional<StringRef> ModuleName = None)
       : WorkingDirectory(WorkingDirectory), Consumer(Consumer),
-        DepFS(std::move(DepFS)), PPSkipMappings(PPSkipMappings),
-        Format(Format) {}
+        DepFS(std::move(DepFS)), PPSkipMappings(PPSkipMappings), Format(Format),
+        OptimizeArgs(OptimizeArgs), ModuleName(ModuleName) {}
 
   bool runInvocation(std::shared_ptr<CompilerInvocation> Invocation,
                      FileManager *FileMgr,
@@ -154,39 +165,34 @@ public:
     CompilerInvocation OriginalInvocation(*Invocation);
 
     // Create a compiler instance to handle the actual work.
-    CompilerInstance Compiler(std::move(PCHContainerOps));
-    Compiler.setInvocation(std::move(Invocation));
+    CompilerInstance ScanInstance(std::move(PCHContainerOps));
+    ScanInstance.setInvocation(std::move(Invocation));
 
-    // Don't print 'X warnings and Y errors generated'.
-    Compiler.getDiagnosticOpts().ShowCarets = false;
-    // Don't write out diagnostic file.
-    Compiler.getDiagnosticOpts().DiagnosticSerializationFile.clear();
-    // Don't treat warnings as errors.
-    Compiler.getDiagnosticOpts().Warnings.push_back("no-error");
     // Create the compiler's actual diagnostics engine.
-    Compiler.createDiagnostics(DiagConsumer, /*ShouldOwnClient=*/false);
-    if (!Compiler.hasDiagnostics())
+    sanitizeDiagOpts(ScanInstance.getDiagnosticOpts());
+    ScanInstance.createDiagnostics(DiagConsumer, /*ShouldOwnClient=*/false);
+    if (!ScanInstance.hasDiagnostics())
       return false;
 
-    Compiler.getPreprocessorOpts().AllowPCHWithDifferentModulesCachePath = true;
+    ScanInstance.getPreprocessorOpts().AllowPCHWithDifferentModulesCachePath =
+        true;
 
     FileMgr->getFileSystemOpts().WorkingDir = std::string(WorkingDirectory);
-    Compiler.setFileManager(FileMgr);
-    Compiler.createSourceManager(*FileMgr);
+    ScanInstance.setFileManager(FileMgr);
+    ScanInstance.createSourceManager(*FileMgr);
 
     llvm::StringSet<> PrebuiltModulesInputFiles;
     // Store the list of prebuilt module files into header search options. This
     // will prevent the implicit build to create duplicate modules and will
     // force reuse of the existing prebuilt module files instead.
-    if (!Compiler.getPreprocessorOpts().ImplicitPCHInclude.empty())
+    if (!ScanInstance.getPreprocessorOpts().ImplicitPCHInclude.empty())
       visitPrebuiltModule(
-          Compiler.getPreprocessorOpts().ImplicitPCHInclude, Compiler,
-          Compiler.getHeaderSearchOpts().PrebuiltModuleFiles,
+          ScanInstance.getPreprocessorOpts().ImplicitPCHInclude, ScanInstance,
+          ScanInstance.getHeaderSearchOpts().PrebuiltModuleFiles,
           PrebuiltModulesInputFiles, /*VisitInputFiles=*/DepFS != nullptr);
 
     // Use the dependency scanning optimized file system if requested to do so.
     if (DepFS) {
-      const CompilerInvocation &CI = Compiler.getInvocation();
       DepFS->clearIgnoredFiles();
       // Ignore any files that contributed to prebuilt modules. The implicit
       // build validates the modules by comparing the reported sizes of their
@@ -197,20 +203,20 @@ public:
       // Add any filenames that were explicity passed in the build settings and
       // that might be opened, as we want to ensure we don't run source
       // minimization on them.
-      for (const auto &Entry : CI.getHeaderSearchOpts().UserEntries)
-        DepFS->ignoreFile(Entry.Path);
-      for (const auto &Entry : CI.getHeaderSearchOpts().VFSOverlayFiles)
-        DepFS->ignoreFile(Entry);
+      for (const auto &E : ScanInstance.getHeaderSearchOpts().UserEntries)
+        DepFS->ignoreFile(E.Path);
+      for (const auto &F : ScanInstance.getHeaderSearchOpts().VFSOverlayFiles)
+        DepFS->ignoreFile(F);
 
       // Support for virtual file system overlays on top of the caching
       // filesystem.
       FileMgr->setVirtualFileSystem(createVFSFromCompilerInvocation(
-          CI, Compiler.getDiagnostics(), DepFS));
+          ScanInstance.getInvocation(), ScanInstance.getDiagnostics(), DepFS));
 
       // Pass the skip mappings which should speed up excluded conditional block
       // skipping in the preprocessor.
       if (PPSkipMappings)
-        Compiler.getPreprocessorOpts()
+        ScanInstance.getPreprocessorOpts()
             .ExcludedConditionalDirectiveSkipMappings = PPSkipMappings;
     }
 
@@ -222,35 +228,43 @@ public:
     // which ensures that the compiler won't create new dependency collectors,
     // and thus won't write out the extra '.d' files to disk.
     auto Opts = std::make_unique<DependencyOutputOptions>();
-    std::swap(*Opts, Compiler.getInvocation().getDependencyOutputOpts());
+    std::swap(*Opts, ScanInstance.getInvocation().getDependencyOutputOpts());
     // We need at least one -MT equivalent for the generator of make dependency
     // files to work.
     if (Opts->Targets.empty())
-      Opts->Targets = {deduceDepTarget(Compiler.getFrontendOpts().OutputFile,
-                                       Compiler.getFrontendOpts().Inputs)};
+      Opts->Targets = {
+          deduceDepTarget(ScanInstance.getFrontendOpts().OutputFile,
+                          ScanInstance.getFrontendOpts().Inputs)};
     Opts->IncludeSystemHeaders = true;
 
     switch (Format) {
     case ScanningOutputFormat::Make:
-      Compiler.addDependencyCollector(
+      ScanInstance.addDependencyCollector(
           std::make_shared<DependencyConsumerForwarder>(std::move(Opts),
                                                         Consumer));
       break;
     case ScanningOutputFormat::Full:
-      Compiler.addDependencyCollector(std::make_shared<ModuleDepCollector>(
-          std::move(Opts), Compiler, Consumer, std::move(OriginalInvocation)));
+      ScanInstance.addDependencyCollector(std::make_shared<ModuleDepCollector>(
+          std::move(Opts), ScanInstance, Consumer,
+          std::move(OriginalInvocation), OptimizeArgs));
       break;
     }
 
     // Consider different header search and diagnostic options to create
     // different modules. This avoids the unsound aliasing of module PCMs.
     //
-    // TODO: Implement diagnostic bucketing and header search pruning to reduce
-    // the impact of strict context hashing.
-    Compiler.getHeaderSearchOpts().ModulesStrictContextHash = true;
+    // TODO: Implement diagnostic bucketing to reduce the impact of strict
+    // context hashing.
+    ScanInstance.getHeaderSearchOpts().ModulesStrictContextHash = true;
+
+    std::unique_ptr<FrontendAction> Action;
+
+    if (ModuleName.hasValue())
+      Action = std::make_unique<GetDependenciesByModuleNameAction>(*ModuleName);
+    else
+      Action = std::make_unique<ReadPCHAndPreprocessAction>();
 
-    auto Action = std::make_unique<ReadPCHAndPreprocessAction>();
-    const bool Result = Compiler.ExecuteAction(*Action);
+    const bool Result = ScanInstance.ExecuteAction(*Action);
     if (!DepFS)
       FileMgr->clearStatCache();
     return Result;
@@ -262,15 +276,15 @@ private:
   llvm::IntrusiveRefCntPtr<DependencyScanningWorkerFilesystem> DepFS;
   ExcludedPreprocessorDirectiveSkipMapping *PPSkipMappings;
   ScanningOutputFormat Format;
+  bool OptimizeArgs;
+  llvm::Optional<StringRef> ModuleName;
 };
 
 } // end anonymous namespace
 
 DependencyScanningWorker::DependencyScanningWorker(
     DependencyScanningService &Service)
-    : Format(Service.getFormat()) {
-  DiagOpts = new DiagnosticOptions();
-
+    : Format(Service.getFormat()), OptimizeArgs(Service.canOptimizeArgs()) {
   PCHContainerOps = std::make_shared<PCHContainerOperations>();
   PCHContainerOps->registerReader(
       std::make_unique<ObjectFilePCHContainerReader>());
@@ -279,7 +293,12 @@ DependencyScanningWorker::DependencyScanningWorker(
   PCHContainerOps->registerWriter(
       std::make_unique<ObjectFilePCHContainerWriter>());
 
-  RealFS = llvm::vfs::createPhysicalFileSystem();
+  auto OverlayFS = llvm::makeIntrusiveRefCnt<llvm::vfs::OverlayFileSystem>(
+      llvm::vfs::createPhysicalFileSystem());
+  InMemoryFS = llvm::makeIntrusiveRefCnt<llvm::vfs::InMemoryFileSystem>();
+  OverlayFS->pushOverlay(InMemoryFS);
+  RealFS = OverlayFS;
+
   if (Service.canSkipExcludedPPRanges())
     PPSkipMappings =
         std::make_unique<ExcludedPreprocessorDirectiveSkipMapping>();
@@ -290,36 +309,64 @@ DependencyScanningWorker::DependencyScanningWorker(
     Files = new FileManager(FileSystemOptions(), RealFS);
 }
 
-static llvm::Error runWithDiags(
-    DiagnosticOptions *DiagOpts,
-    llvm::function_ref<bool(DiagnosticConsumer &DC)> BodyShouldSucceed) {
+static llvm::Error
+runWithDiags(DiagnosticOptions *DiagOpts,
+             llvm::function_ref<bool(DiagnosticConsumer &, DiagnosticOptions &)>
+                 BodyShouldSucceed) {
+  sanitizeDiagOpts(*DiagOpts);
+
   // Capture the emitted diagnostics and report them to the client
   // in the case of a failure.
   std::string DiagnosticOutput;
   llvm::raw_string_ostream DiagnosticsOS(DiagnosticOutput);
   TextDiagnosticPrinter DiagPrinter(DiagnosticsOS, DiagOpts);
 
-  if (BodyShouldSucceed(DiagPrinter))
+  if (BodyShouldSucceed(DiagPrinter, *DiagOpts))
     return llvm::Error::success();
   return llvm::make_error<llvm::StringError>(DiagnosticsOS.str(),
                                              llvm::inconvertibleErrorCode());
 }
 
 llvm::Error DependencyScanningWorker::computeDependencies(
-    const std::string &Input, StringRef WorkingDirectory,
-    const CompilationDatabase &CDB, DependencyConsumer &Consumer) {
+    StringRef WorkingDirectory, const std::vector<std::string> &CommandLine,
+    DependencyConsumer &Consumer, llvm::Optional<StringRef> ModuleName) {
+  // Reset what might have been modified in the previous worker invocation.
   RealFS->setCurrentWorkingDirectory(WorkingDirectory);
-  return runWithDiags(DiagOpts.get(), [&](DiagnosticConsumer &DC) {
-    /// Create the tool that uses the underlying file system to ensure that any
-    /// file system requests that are made by the driver do not go through the
-    /// dependency scanning filesystem.
-    tooling::ClangTool Tool(CDB, Input, PCHContainerOps, RealFS, Files);
-    Tool.clearArgumentsAdjusters();
-    Tool.setRestoreWorkingDir(false);
-    Tool.setPrintErrorMessage(false);
-    Tool.setDiagnosticConsumer(&DC);
-    DependencyScanningAction Action(WorkingDirectory, Consumer, DepFS,
-                                    PPSkipMappings.get(), Format);
-    return !Tool.run(&Action);
-  });
+  if (Files)
+    Files->setVirtualFileSystem(RealFS);
+
+  llvm::IntrusiveRefCntPtr<FileManager> CurrentFiles =
+      Files ? Files : new FileManager(FileSystemOptions(), RealFS);
+
+  Optional<std::vector<std::string>> ModifiedCommandLine;
+  if (ModuleName.hasValue()) {
+    ModifiedCommandLine = CommandLine;
+    InMemoryFS->addFile(*ModuleName, 0, llvm::MemoryBuffer::getMemBuffer(""));
+    ModifiedCommandLine->emplace_back(*ModuleName);
+  }
+
+  const std::vector<std::string> &FinalCommandLine =
+      ModifiedCommandLine ? *ModifiedCommandLine : CommandLine;
+
+  std::vector<const char *> FinalCCommandLine(CommandLine.size(), nullptr);
+  llvm::transform(CommandLine, FinalCCommandLine.begin(),
+                  [](const std::string &Str) { return Str.c_str(); });
+
+  return runWithDiags(CreateAndPopulateDiagOpts(FinalCCommandLine).release(),
+                      [&](DiagnosticConsumer &DC, DiagnosticOptions &DiagOpts) {
+                        DependencyScanningAction Action(
+                            WorkingDirectory, Consumer, DepFS,
+                            PPSkipMappings.get(), Format, OptimizeArgs,
+                            ModuleName);
+                        // Create an invocation that uses the underlying file
+                        // system to ensure that any file system requests that
+                        // are made by the driver do not go through the
+                        // dependency scanning filesystem.
+                        ToolInvocation Invocation(FinalCommandLine, &Action,
+                                                  CurrentFiles.get(),
+                                                  PCHContainerOps);
+                        Invocation.setDiagnosticConsumer(&DC);
+                        Invocation.setDiagnosticOptions(&DiagOpts);
+                        return Invocation.run();
+                      });
 }
diff --git a/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp b/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
index 88cee63c98aa..383a850301a1 100644
--- a/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
+++ b/clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp
@@ -1,9 +1,8 @@
 //===- ModuleDepCollector.cpp - Callbacks to collect deps -------*- C++ -*-===//
 //
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
@@ -18,11 +17,26 @@ using namespace clang;
 using namespace tooling;
 using namespace dependencies;
 
+static void optimizeHeaderSearchOpts(HeaderSearchOptions &Opts,
+                                     ASTReader &Reader,
+                                     const serialization::ModuleFile &MF) {
+  // Only preserve search paths that were used during the dependency scan.
+  std::vector<HeaderSearchOptions::Entry> Entries = Opts.UserEntries;
+  Opts.UserEntries.clear();
+  for (unsigned I = 0; I < Entries.size(); ++I)
+    if (MF.SearchPathUsage[I])
+      Opts.UserEntries.push_back(Entries[I]);
+}
+
 CompilerInvocation ModuleDepCollector::makeInvocationForModuleBuildWithoutPaths(
-    const ModuleDeps &Deps) const {
+    const ModuleDeps &Deps,
+    llvm::function_ref<void(CompilerInvocation &)> Optimize) const {
   // Make a deep copy of the original Clang invocation.
   CompilerInvocation CI(OriginalInvocation);
 
+  CI.getLangOpts()->resetNonModularOptions();
+  CI.getPreprocessorOpts().resetNonModularOptions();
+
   // Remove options incompatible with explicit module build.
   CI.getFrontendOpts().Inputs.clear();
   CI.getFrontendOpts().OutputFile.clear();
@@ -34,12 +48,18 @@ CompilerInvocation ModuleDepCollector::makeInvocationForModuleBuildWithoutPaths(
   CI.getLangOpts()->ImplicitModules = false;
 
   // Report the prebuilt modules this module uses.
-  for (const auto &PrebuiltModule : Deps.PrebuiltModuleDeps) {
+  for (const auto &PrebuiltModule : Deps.PrebuiltModuleDeps)
     CI.getFrontendOpts().ModuleFiles.push_back(PrebuiltModule.PCMFile);
-    CI.getFrontendOpts().ModuleMapFiles.push_back(PrebuiltModule.ModuleMapFile);
-  }
 
-  CI.getPreprocessorOpts().ImplicitPCHInclude.clear();
+  Optimize(CI);
+
+  // The original invocation probably didn't have strict context hash enabled.
+  // We will use the context hash of this invocation to distinguish between
+  // multiple incompatible versions of the same module and will use it when
+  // reporting dependencies to the clients. Let's make sure we're using
+  // **strict** context hash in order to prevent accidental sharing of
+  // incompatible modules (e.g. with differences in search paths).
+  CI.getHeaderSearchOpts().ModulesStrictContextHash = true;
 
   return CI;
 }
@@ -62,7 +82,7 @@ serializeCompilerInvocation(const CompilerInvocation &CI) {
 std::vector<std::string> ModuleDeps::getCanonicalCommandLine(
     std::function<StringRef(ModuleID)> LookupPCMPath,
     std::function<const ModuleDeps &(ModuleID)> LookupModuleDeps) const {
-  CompilerInvocation CI(Invocation);
+  CompilerInvocation CI(BuildInvocation);
   FrontendOptions &FrontendOpts = CI.getFrontendOpts();
 
   InputKind ModuleMapInputKind(FrontendOpts.DashX.getLanguage(),
@@ -79,7 +99,7 @@ std::vector<std::string> ModuleDeps::getCanonicalCommandLine(
 
 std::vector<std::string>
 ModuleDeps::getCanonicalCommandLineWithoutModulePaths() const {
-  return serializeCompilerInvocation(Invocation);
+  return serializeCompilerInvocation(BuildInvocation);
 }
 
 void dependencies::detail::collectPCMAndModuleMapPaths(
@@ -112,15 +132,15 @@ void ModuleDepCollectorPP::FileChanged(SourceLocation Loc,
                                        FileID PrevFID) {
   if (Reason != PPCallbacks::EnterFile)
     return;
-  
+
   // This has to be delayed as the context hash can change at the start of
   // `CompilerInstance::ExecuteAction`.
   if (MDC.ContextHash.empty()) {
-    MDC.ContextHash = Instance.getInvocation().getModuleHash();
+    MDC.ContextHash = MDC.ScanInstance.getInvocation().getModuleHash();
     MDC.Consumer.handleContextHash(MDC.ContextHash);
   }
 
-  SourceManager &SM = Instance.getSourceManager();
+  SourceManager &SM = MDC.ScanInstance.getSourceManager();
 
   // Dependency generation really does want to go all the way to the
   // file entry for a source location to find out what is depended on.
@@ -163,12 +183,14 @@ void ModuleDepCollectorPP::handleImport(const Module *Imported) {
 }
 
 void ModuleDepCollectorPP::EndOfMainFile() {
-  FileID MainFileID = Instance.getSourceManager().getMainFileID();
-  MDC.MainFile = std::string(
-      Instance.getSourceManager().getFileEntryForID(MainFileID)->getName());
+  FileID MainFileID = MDC.ScanInstance.getSourceManager().getMainFileID();
+  MDC.MainFile = std::string(MDC.ScanInstance.getSourceManager()
+                                 .getFileEntryForID(MainFileID)
+                                 ->getName());
 
-  if (!Instance.getPreprocessorOpts().ImplicitPCHInclude.empty())
-    MDC.FileDeps.push_back(Instance.getPreprocessorOpts().ImplicitPCHInclude);
+  if (!MDC.ScanInstance.getPreprocessorOpts().ImplicitPCHInclude.empty())
+    MDC.FileDeps.push_back(
+        MDC.ScanInstance.getPreprocessorOpts().ImplicitPCHInclude);
 
   for (const Module *M : DirectModularDeps) {
     // A top-level module might not be actually imported as a module when
@@ -207,15 +229,16 @@ ModuleID ModuleDepCollectorPP::handleTopLevelModule(const Module *M) {
   MD.ImplicitModulePCMPath = std::string(M->getASTFile()->getName());
   MD.IsSystem = M->IsSystem;
 
-  const FileEntry *ModuleMap = Instance.getPreprocessor()
+  const FileEntry *ModuleMap = MDC.ScanInstance.getPreprocessor()
                                    .getHeaderSearchInfo()
                                    .getModuleMap()
                                    .getModuleMapFileForUniquing(M);
   MD.ClangModuleMapFile = std::string(ModuleMap ? ModuleMap->getName() : "");
 
   serialization::ModuleFile *MF =
-      MDC.Instance.getASTReader()->getModuleManager().lookup(M->getASTFile());
-  MDC.Instance.getASTReader()->visitInputFiles(
+      MDC.ScanInstance.getASTReader()->getModuleManager().lookup(
+          M->getASTFile());
+  MDC.ScanInstance.getASTReader()->visitInputFiles(
       *MF, true, true, [&](const serialization::InputFile &IF, bool isSystem) {
         // __inferred_module.map is the result of the way in which an implicit
         // module build handles inferred modules. It adds an overlay VFS with
@@ -232,10 +255,16 @@ ModuleID ModuleDepCollectorPP::handleTopLevelModule(const Module *M) {
   // Add direct prebuilt module dependencies now, so that we can use them when
   // creating a CompilerInvocation and computing context hash for this
   // ModuleDeps instance.
-  addDirectPrebuiltModuleDeps(M, MD);
+  llvm::DenseSet<const Module *> SeenModules;
+  addAllSubmodulePrebuiltDeps(M, MD, SeenModules);
 
-  MD.Invocation = MDC.makeInvocationForModuleBuildWithoutPaths(MD);
-  MD.ID.ContextHash = MD.Invocation.getModuleHash();
+  MD.BuildInvocation = MDC.makeInvocationForModuleBuildWithoutPaths(
+      MD, [&](CompilerInvocation &BuildInvocation) {
+        if (MDC.OptimizeArgs)
+          optimizeHeaderSearchOpts(BuildInvocation.getHeaderSearchOpts(),
+                                   *MDC.ScanInstance.getASTReader(), *MF);
+      });
+  MD.ID.ContextHash = MD.BuildInvocation.getModuleHash();
 
   llvm::DenseSet<const Module *> AddedModules;
   addAllSubmoduleDeps(M, MD, AddedModules);
@@ -243,12 +272,23 @@ ModuleID ModuleDepCollectorPP::handleTopLevelModule(const Module *M) {
   return MD.ID;
 }
 
-void ModuleDepCollectorPP::addDirectPrebuiltModuleDeps(const Module *M,
-                                                       ModuleDeps &MD) {
+void ModuleDepCollectorPP::addAllSubmodulePrebuiltDeps(
+    const Module *M, ModuleDeps &MD,
+    llvm::DenseSet<const Module *> &SeenSubmodules) {
+  addModulePrebuiltDeps(M, MD, SeenSubmodules);
+
+  for (const Module *SubM : M->submodules())
+    addAllSubmodulePrebuiltDeps(SubM, MD, SeenSubmodules);
+}
+
+void ModuleDepCollectorPP::addModulePrebuiltDeps(
+    const Module *M, ModuleDeps &MD,
+    llvm::DenseSet<const Module *> &SeenSubmodules) {
   for (const Module *Import : M->Imports)
     if (Import->getTopLevelModule() != M->getTopLevelModule())
-      if (MDC.isPrebuiltModule(Import))
-        MD.PrebuiltModuleDeps.emplace_back(Import);
+      if (MDC.isPrebuiltModule(Import->getTopLevelModule()))
+        if (SeenSubmodules.insert(Import->getTopLevelModule()).second)
+          MD.PrebuiltModuleDeps.emplace_back(Import->getTopLevelModule());
 }
 
 void ModuleDepCollectorPP::addAllSubmoduleDeps(
@@ -274,13 +314,14 @@ void ModuleDepCollectorPP::addModuleDep(
 }
 
 ModuleDepCollector::ModuleDepCollector(
-    std::unique_ptr<DependencyOutputOptions> Opts, CompilerInstance &I,
-    DependencyConsumer &C, CompilerInvocation &&OriginalCI)
-    : Instance(I), Consumer(C), Opts(std::move(Opts)),
-      OriginalInvocation(std::move(OriginalCI)) {}
+    std::unique_ptr<DependencyOutputOptions> Opts,
+    CompilerInstance &ScanInstance, DependencyConsumer &C,
+    CompilerInvocation &&OriginalCI, bool OptimizeArgs)
+    : ScanInstance(ScanInstance), Consumer(C), Opts(std::move(Opts)),
+      OriginalInvocation(std::move(OriginalCI)), OptimizeArgs(OptimizeArgs) {}
 
 void ModuleDepCollector::attachToPreprocessor(Preprocessor &PP) {
-  PP.addPPCallbacks(std::make_unique<ModuleDepCollectorPP>(Instance, *this));
+  PP.addPPCallbacks(std::make_unique<ModuleDepCollectorPP>(*this));
 }
 
 void ModuleDepCollector::attachToASTReader(ASTReader &R) {}
@@ -288,7 +329,7 @@ void ModuleDepCollector::attachToASTReader(ASTReader &R) {}
 bool ModuleDepCollector::isPrebuiltModule(const Module *M) {
   std::string Name(M->getTopLevelModuleName());
   const auto &PrebuiltModuleFiles =
-      Instance.getHeaderSearchOpts().PrebuiltModuleFiles;
+      ScanInstance.getHeaderSearchOpts().PrebuiltModuleFiles;
   auto PrebuiltModuleFileIt = PrebuiltModuleFiles.find(Name);
   if (PrebuiltModuleFileIt == PrebuiltModuleFiles.end())
     return false;