[clang] Update ModuleMap::getModuleMapFile* to use FileEntryRef

Update SourceManager::ContentCache::OrigEntry to keep the original
FileEntryRef, and use that to enable ModuleMap::getModuleMapFile* to
return the original FileEntryRef. This change should be NFC for
most users of SourceManager::ContentCache, but it could affect behaviour
for users of getNameAsRequested such as in compileModuleImpl. I have not
found a way to detect that difference without additional functional
changes, other than incidental cases like changes from / to \ on
Windows so there is no new test.

Differential Revision: https://reviews.llvm.org/D135220

clang/include/clang/Basic/FileEntry.h

@@ -341,6 +341,23 @@ static_assert(
         OptionalFileEntryRefDegradesToFileEntryPtr>::value,
     "OptionalFileEntryRefDegradesToFileEntryPtr should be trivially copyable");
 
+inline bool operator==(const FileEntry *LHS,
+                       const Optional<FileEntryRef> &RHS) {
+  return LHS == (RHS ? &RHS->getFileEntry() : nullptr);
+}
+inline bool operator==(const Optional<FileEntryRef> &LHS,
+                       const FileEntry *RHS) {
+  return (LHS ? &LHS->getFileEntry() : nullptr) == RHS;
+}
+inline bool operator!=(const FileEntry *LHS,
+                       const Optional<FileEntryRef> &RHS) {
+  return !(LHS == RHS);
+}
+inline bool operator!=(const Optional<FileEntryRef> &LHS,
+                       const FileEntry *RHS) {
+  return !(LHS == RHS);
+}
+
 /// Cached information about one file (either on disk
 /// or in the virtual file system).
 ///

clang/include/clang/Basic/SourceManager.h

@@ -139,8 +139,9 @@ class alignas(8) ContentCache {
   /// It is possible for this to be NULL if the ContentCache encapsulates
   /// an imaginary text buffer.
   ///
-  /// FIXME: Turn this into a FileEntryRef and remove Filename.
-  const FileEntry *OrigEntry;
+  /// FIXME: Make non-optional using a virtual file as needed, remove \c
+  /// Filename and use \c OrigEntry.getNameAsRequested() instead.
+  OptionalFileEntryRefDegradesToFileEntryPtr OrigEntry;
 
   /// References the file which the contents were actually loaded from.
   ///
@@ -177,9 +178,13 @@ class alignas(8) ContentCache {
 
   mutable unsigned IsBufferInvalid : 1;
 
-  ContentCache(const FileEntry *Ent = nullptr) : ContentCache(Ent, Ent) {}
+  ContentCache()
+      : OrigEntry(None), ContentsEntry(nullptr), BufferOverridden(false),
+        IsFileVolatile(false), IsTransient(false), IsBufferInvalid(false) {}
+
+  ContentCache(FileEntryRef Ent) : ContentCache(Ent, Ent) {}
 
-  ContentCache(const FileEntry *Ent, const FileEntry *contentEnt)
+  ContentCache(FileEntryRef Ent, const FileEntry *contentEnt)
       : OrigEntry(Ent), ContentsEntry(contentEnt), BufferOverridden(false),
         IsFileVolatile(false), IsTransient(false), IsBufferInvalid(false) {}
 
@@ -660,7 +665,7 @@ class SourceManager : public RefCountedBase<SourceManager> {
   struct OverriddenFilesInfoTy {
     /// Files that have been overridden with the contents from another
     /// file.
-    llvm::DenseMap<const FileEntry *, const FileEntry *> OverriddenFiles;
+    llvm::DenseMap<const FileEntry *, FileEntryRef> OverriddenFiles;
 
     /// Files that were overridden with a memory buffer.
     llvm::DenseSet<const FileEntry *> OverriddenFilesWithBuffer;
@@ -978,8 +983,7 @@ class SourceManager : public RefCountedBase<SourceManager> {
   ///
   /// \param NewFile the file whose contents will be used as the
   /// data instead of the contents of the given source file.
-  void overrideFileContents(const FileEntry *SourceFile,
-                            const FileEntry *NewFile);
+  void overrideFileContents(const FileEntry *SourceFile, FileEntryRef NewFile);
 
   /// Returns true if the file contents have been overridden.
   bool isFileOverridden(const FileEntry *File) const {
@@ -1044,8 +1048,8 @@ class SourceManager : public RefCountedBase<SourceManager> {
 
   /// Returns the FileEntryRef for the provided FileID.
   Optional<FileEntryRef> getFileEntryRefForID(FileID FID) const {
-    if (auto *Entry = getFileEntryForID(FID))
-      return Entry->getLastRef();
+    if (auto *Entry = getSLocEntryForFile(FID))
+      return Entry->getFile().getContentCache().OrigEntry;
     return None;
   }
 

clang/include/clang/Lex/ModuleMap.h

@@ -607,7 +607,7 @@ class ModuleMap {
   ///
   /// \returns The file entry for the module map file containing the given
   /// module, or nullptr if the module definition was inferred.
-  const FileEntry *getContainingModuleMapFile(const Module *Module) const;
+  Optional<FileEntryRef> getContainingModuleMapFile(const Module *Module) const;
 
   /// Get the module map file that (along with the module name) uniquely
   /// identifies this module.
@@ -618,7 +618,7 @@ class ModuleMap {
   /// of inferred modules, returns the module map that allowed the inference
   /// (e.g. contained 'module *'). Otherwise, returns
   /// getContainingModuleMapFile().
-  const FileEntry *getModuleMapFileForUniquing(const Module *M) const;
+  Optional<FileEntryRef> getModuleMapFileForUniquing(const Module *M) const;
 
   void setInferredModuleAllowedBy(Module *M, const FileEntry *ModMap);
 

clang/lib/Basic/SourceManager.cpp

@@ -399,8 +399,7 @@ ContentCache &SourceManager::getOrCreateContentCache(FileEntryRef FileEnt,
   if (OverriddenFilesInfo) {
     // If the file contents are overridden with contents from another file,
     // pass that file to ContentCache.
-    llvm::DenseMap<const FileEntry *, const FileEntry *>::iterator
-        overI = OverriddenFilesInfo->OverriddenFiles.find(FileEnt);
+    auto overI = OverriddenFilesInfo->OverriddenFiles.find(FileEnt);
     if (overI == OverriddenFilesInfo->OverriddenFiles.end())
       new (Entry) ContentCache(FileEnt);
     else
@@ -695,14 +694,18 @@ void SourceManager::overrideFileContents(
 }
 
 void SourceManager::overrideFileContents(const FileEntry *SourceFile,
-                                         const FileEntry *NewFile) {
-  assert(SourceFile->getSize() == NewFile->getSize() &&
+                                         FileEntryRef NewFile) {
+  assert(SourceFile->getSize() == NewFile.getSize() &&
          "Different sizes, use the FileManager to create a virtual file with "
          "the correct size");
   assert(FileInfos.count(SourceFile) == 0 &&
          "This function should be called at the initialization stage, before "
          "any parsing occurs.");
-  getOverriddenFilesInfo().OverriddenFiles[SourceFile] = NewFile;
+  // FileEntryRef is not default-constructible.
+  auto Pair = getOverriddenFilesInfo().OverriddenFiles.insert(
+      std::make_pair(SourceFile, NewFile));
+  if (!Pair.second)
+    Pair.first->second = NewFile;
 }
 
 Optional<FileEntryRef>

clang/lib/Frontend/CompilerInstance.cpp

@@ -423,15 +423,15 @@ static void InitializeFileRemapping(DiagnosticsEngine &Diags,
   // Remap files in the source manager (with other files).
   for (const auto &RF : InitOpts.RemappedFiles) {
     // Find the file that we're mapping to.
-    auto ToFile = FileMgr.getFile(RF.second);
+    Optional<FileEntryRef> ToFile = FileMgr.getOptionalFileRef(RF.second);
     if (!ToFile) {
       Diags.Report(diag::err_fe_remap_missing_to_file) << RF.first << RF.second;
       continue;
     }
 
     // Create the file entry for the file that we're mapping from.
     const FileEntry *FromFile =
-        FileMgr.getVirtualFile(RF.first, (*ToFile)->getSize(), 0);
+        FileMgr.getVirtualFile(RF.first, ToFile->getSize(), 0);
     if (!FromFile) {
       Diags.Report(diag::err_fe_remap_missing_from_file) << RF.first;
       continue;
@@ -1278,19 +1278,17 @@ compileModuleImpl(CompilerInstance &ImportingInstance, SourceLocation ImportLoc,
          Instance.getFrontendOpts().AllowPCMWithCompilerErrors;
 }
 
-static const FileEntry *getPublicModuleMap(const FileEntry *File,
-                                           FileManager &FileMgr) {
-  StringRef Filename = llvm::sys::path::filename(File->getName());
-  SmallString<128> PublicFilename(File->getDir()->getName());
+static Optional<FileEntryRef> getPublicModuleMap(FileEntryRef File,
+                                                 FileManager &FileMgr) {
+  StringRef Filename = llvm::sys::path::filename(File.getName());
+  SmallString<128> PublicFilename(File.getDir().getName());
   if (Filename == "module_private.map")
     llvm::sys::path::append(PublicFilename, "module.map");
   else if (Filename == "module.private.modulemap")
     llvm::sys::path::append(PublicFilename, "module.modulemap");
   else
-    return nullptr;
-  if (auto FE = FileMgr.getFile(PublicFilename))
-    return *FE;
-  return nullptr;
+    return None;
+  return FileMgr.getOptionalFileRef(PublicFilename);
 }
 
 /// Compile a module file for the given module in a separate compiler instance,
@@ -1306,19 +1304,16 @@ static bool compileModule(CompilerInstance &ImportingInstance,
   ModuleMap &ModMap
     = ImportingInstance.getPreprocessor().getHeaderSearchInfo().getModuleMap();
   bool Result;
-  if (const FileEntry *ModuleMapFile =
+  if (Optional<FileEntryRef> ModuleMapFile =
           ModMap.getContainingModuleMapFile(Module)) {
     // Canonicalize compilation to start with the public module map. This is
     // vital for submodules declarations in the private module maps to be
     // correctly parsed when depending on a top level module in the public one.
-    if (const FileEntry *PublicMMFile = getPublicModuleMap(
-            ModuleMapFile, ImportingInstance.getFileManager()))
+    if (Optional<FileEntryRef> PublicMMFile = getPublicModuleMap(
+            *ModuleMapFile, ImportingInstance.getFileManager()))
       ModuleMapFile = PublicMMFile;
 
-    // FIXME: Update header search to keep FileEntryRef rather than rely on
-    // getLastRef().
-    StringRef ModuleMapFilePath =
-        ModuleMapFile->getLastRef().getNameAsRequested();
+    StringRef ModuleMapFilePath = ModuleMapFile->getNameAsRequested();
 
     // Use the module map where this module resides.
     Result = compileModuleImpl(
@@ -1346,7 +1341,7 @@ static bool compileModule(CompilerInstance &ImportingInstance,
         [&](CompilerInstance &Instance) {
       std::unique_ptr<llvm::MemoryBuffer> ModuleMapBuffer =
           llvm::MemoryBuffer::getMemBuffer(InferredModuleMapContent);
-      ModuleMapFile = Instance.getFileManager().getVirtualFile(
+      const FileEntry *ModuleMapFile = Instance.getFileManager().getVirtualFile(
           FakeModuleMapFile, InferredModuleMapContent.size(), 0);
       Instance.getSourceManager().overrideFileContents(
           ModuleMapFile, std::move(ModuleMapBuffer));

clang/lib/Lex/HeaderSearch.cpp

@@ -170,11 +170,11 @@ void HeaderSearch::getHeaderMapFileNames(
 }
 
 std::string HeaderSearch::getCachedModuleFileName(Module *Module) {
-  const FileEntry *ModuleMap =
+  Optional<FileEntryRef> ModuleMap =
       getModuleMap().getModuleMapFileForUniquing(Module);
   // The ModuleMap maybe a nullptr, when we load a cached C++ module without
   // *.modulemap file. In this case, just return an empty string.
-  if (ModuleMap == nullptr)
+  if (!ModuleMap)
     return {};
   return getCachedModuleFileName(Module->Name, ModuleMap->getName());
 }
@@ -211,7 +211,7 @@ std::string HeaderSearch::getPrebuiltModuleFileName(StringRef ModuleName,
 }
 
 std::string HeaderSearch::getPrebuiltImplicitModuleFileName(Module *Module) {
-  const FileEntry *ModuleMap =
+  Optional<FileEntryRef> ModuleMap =
       getModuleMap().getModuleMapFileForUniquing(Module);
   StringRef ModuleName = Module->Name;
   StringRef ModuleMapPath = ModuleMap->getName();

clang/lib/Lex/ModuleMap.cpp

@@ -609,7 +609,7 @@ ModuleMap::findOrCreateModuleForHeaderInUmbrellaDir(const FileEntry *File) {
       UmbrellaModule = UmbrellaModule->Parent;
 
     if (UmbrellaModule->InferSubmodules) {
-      const FileEntry *UmbrellaModuleMap =
+      OptionalFileEntryRefDegradesToFileEntryPtr UmbrellaModuleMap =
           getModuleMapFileForUniquing(UmbrellaModule);
 
       // Infer submodules for each of the directories we found between
@@ -1023,9 +1023,11 @@ Module *ModuleMap::inferFrameworkModule(const DirectoryEntry *FrameworkDir,
     // If we're not allowed to infer a framework module, don't.
     if (!canInfer)
       return nullptr;
-  } else
-    ModuleMapFile = getModuleMapFileForUniquing(Parent);
-
+  } else {
+    OptionalFileEntryRefDegradesToFileEntryPtr ModuleMapRef =
+        getModuleMapFileForUniquing(Parent);
+    ModuleMapFile = ModuleMapRef;
+  }
 
   // Look for an umbrella header.
   SmallString<128> UmbrellaName = StringRef(FrameworkDir->getName());
@@ -1277,19 +1279,21 @@ void ModuleMap::excludeHeader(Module *Mod, Module::Header Header) {
   Mod->Headers[Module::HK_Excluded].push_back(std::move(Header));
 }
 
-const FileEntry *
+Optional<FileEntryRef>
 ModuleMap::getContainingModuleMapFile(const Module *Module) const {
   if (Module->DefinitionLoc.isInvalid())
-    return nullptr;
+    return None;
 
-  return SourceMgr.getFileEntryForID(
-           SourceMgr.getFileID(Module->DefinitionLoc));
+  return SourceMgr.getFileEntryRefForID(
+      SourceMgr.getFileID(Module->DefinitionLoc));
 }
 
-const FileEntry *ModuleMap::getModuleMapFileForUniquing(const Module *M) const {
+Optional<FileEntryRef>
+ModuleMap::getModuleMapFileForUniquing(const Module *M) const {
   if (M->IsInferred) {
     assert(InferredModuleAllowedBy.count(M) && "missing inferred module map");
-    return InferredModuleAllowedBy.find(M)->second;
+    // FIXME: Update InferredModuleAllowedBy to use FileEntryRef.
+    return InferredModuleAllowedBy.find(M)->second->getLastRef();
   }
   return getContainingModuleMapFile(M);
 }

clang/lib/Serialization/ASTReader.cpp

@@ -3919,7 +3919,8 @@ ASTReader::ReadModuleMapFileBlock(RecordData &Record, ModuleFile &F,
     Module *M =
         PP.getHeaderSearchInfo().lookupModule(F.ModuleName, F.ImportLoc);
     auto &Map = PP.getHeaderSearchInfo().getModuleMap();
-    const FileEntry *ModMap = M ? Map.getModuleMapFileForUniquing(M) : nullptr;
+    Optional<FileEntryRef> ModMap =
+        M ? Map.getModuleMapFileForUniquing(M) : None;
     // Don't emit module relocation error if we have -fno-validate-pch
     if (!bool(PP.getPreprocessorOpts().DisablePCHOrModuleValidation &
               DisableValidationForModuleKind::Module) &&

clang/lib/Serialization/ASTWriter.cpp

@@ -193,13 +193,13 @@ std::set<const FileEntry *> GetAllModuleMaps(const HeaderSearch &HS,
     auto *CurrentModule = ModulesToProcess.pop_back_val();
     ProcessedModules.insert(CurrentModule);
 
-    auto *ModuleMapFile =
+    Optional<FileEntryRef> ModuleMapFile =
         HS.getModuleMap().getModuleMapFileForUniquing(CurrentModule);
     if (!ModuleMapFile) {
       continue;
     }
 
-    ModuleMaps.insert(ModuleMapFile);
+    ModuleMaps.insert(*ModuleMapFile);
 
     for (auto *ImportedModule : (CurrentModule)->Imports) {
       if (!ImportedModule ||

clang/lib/Tooling/DependencyScanning/ModuleDepCollector.cpp

@@ -227,7 +227,7 @@ void ModuleDepCollector::applyDiscoveredDependencies(CompilerInvocation &CI) {
   if (llvm::any_of(CI.getFrontendOpts().Inputs, needsModules)) {
     Preprocessor &PP = ScanInstance.getPreprocessor();
     if (Module *CurrentModule = PP.getCurrentModuleImplementation())
-      if (const FileEntry *CurrentModuleMap =
+      if (Optional<FileEntryRef> CurrentModuleMap =
               PP.getHeaderSearchInfo()
                   .getModuleMap()
                   .getModuleMapFileForUniquing(CurrentModule))
@@ -406,13 +406,13 @@ ModuleID ModuleDepCollectorPP::handleTopLevelModule(const Module *M) {
   MD.ImplicitModulePCMPath = std::string(M->getASTFile()->getName());
   MD.IsSystem = M->IsSystem;
 
-  const FileEntry *ModuleMap = MDC.ScanInstance.getPreprocessor()
-                                   .getHeaderSearchInfo()
-                                   .getModuleMap()
-                                   .getModuleMapFileForUniquing(M);
+  Optional<FileEntryRef> ModuleMap = MDC.ScanInstance.getPreprocessor()
+                                         .getHeaderSearchInfo()
+                                         .getModuleMap()
+                                         .getModuleMapFileForUniquing(M);
 
   if (ModuleMap) {
-    StringRef Path = ModuleMap->tryGetRealPathName();
+    StringRef Path = ModuleMap->getFileEntry().tryGetRealPathName();
     if (Path.empty())
       Path = ModuleMap->getName();
     MD.ClangModuleMapFile = std::string(Path);

clang/test/Modules/malformed.cpp

@@ -3,9 +3,9 @@
 //
 // RUN: rm -rf %t
 // RUN: cd %S
-// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="a1.h" %s 2>&1 | FileCheck %s --check-prefix=CHECK-A
-// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="b1.h" %s 2>&1 | FileCheck %s --check-prefix=CHECK-B
-// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="c.h" malformed.cpp 2>&1 | FileCheck %s --check-prefix=CHECK-C
+// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="a1.h" %s 2>&1 | sed 's:\\\\\?:/:g' | FileCheck %s --check-prefix=CHECK-A
+// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="b1.h" %s 2>&1 | sed 's:\\\\\?:/:g' | FileCheck %s --check-prefix=CHECK-B
+// RUN: not %clang_cc1 -fmodules -fimplicit-module-maps -fmodules-cache-path=%t -I Inputs/malformed -DHEADER="c.h" malformed.cpp 2>&1 | sed 's:\\\\\?:/:g' | FileCheck %s --check-prefix=CHECK-C
 
 #define STR2(x) #x
 #define STR(x) STR2(x)

clang/tools/libclang/CIndexInclusionStack.cpp

@@ -59,8 +59,8 @@ void getInclusions(bool IsLocal, unsigned n, CXTranslationUnit TU,
 
     // Callback to the client.
     // FIXME: We should have a function to construct CXFiles.
-    CB(static_cast<CXFile>(
-           const_cast<FileEntry *>(FI.getContentCache().OrigEntry)),
+    CB(static_cast<CXFile>(const_cast<FileEntry *>(
+           static_cast<const FileEntry *>(FI.getContentCache().OrigEntry))),
        InclusionStack.data(), InclusionStack.size(), clientData);
   }
 }