[clang][serialization] NFCI: Avoid re-reading input file info

This patch resolves a FIXME that points out an inefficiency in first deserializing the input file info and the whole input file, which redundantly deserializes the input file info again.

Reviewed By: Bigcheese

Differential Revision: https://reviews.llvm.org/D137192

Author: jansvoboda11

clang/include/clang/Serialization/ASTReader.h

@@ -1247,18 +1247,8 @@ class ASTReader
   /// Reads a statement from the specified cursor.
   Stmt *ReadStmtFromStream(ModuleFile &F);
 
-  struct InputFileInfo {
-    std::string Filename;
-    uint64_t ContentHash;
-    off_t StoredSize;
-    time_t StoredTime;
-    bool Overridden;
-    bool Transient;
-    bool TopLevelModuleMap;
-  };
-
-  /// Reads the stored information about an input file.
-  InputFileInfo readInputFileInfo(ModuleFile &F, unsigned ID);
+  /// Retrieve the stored information about an input file.
+  serialization::InputFileInfo getInputFileInfo(ModuleFile &F, unsigned ID);
 
   /// Retrieve the file entry and 'overridden' bit for an input
   /// file in the given module file.

clang/include/clang/Serialization/ModuleFile.h

@@ -59,6 +59,17 @@ enum ModuleKind {
   MK_PrebuiltModule
 };
 
+/// The input file info that has been loaded from an AST file.
+struct InputFileInfo {
+  std::string Filename;
+  uint64_t ContentHash;
+  off_t StoredSize;
+  time_t StoredTime;
+  bool Overridden;
+  bool Transient;
+  bool TopLevelModuleMap;
+};
+
 /// The input file that has been loaded from this AST file, along with
 /// bools indicating whether this was an overridden buffer or if it was
 /// out-of-date or not-found.
@@ -235,6 +246,9 @@ class ModuleFile {
   /// The input files that have been loaded from this AST file.
   std::vector<InputFile> InputFilesLoaded;
 
+  /// The input file infos that have been loaded from this AST file.
+  std::vector<InputFileInfo> InputFileInfosLoaded;
+
   // All user input files reside at the index range [0, NumUserInputFiles), and
   // system input files reside at [NumUserInputFiles, InputFilesLoaded.size()).
   unsigned NumUserInputFiles = 0;

clang/lib/Serialization/ASTReader.cpp

@@ -2266,8 +2266,15 @@ bool ASTReader::shouldDisableValidationForFile(
   return false;
 }
 
-ASTReader::InputFileInfo
-ASTReader::readInputFileInfo(ModuleFile &F, unsigned ID) {
+InputFileInfo ASTReader::getInputFileInfo(ModuleFile &F, unsigned ID) {
+  // If this ID is bogus, just return an empty input file.
+  if (ID == 0 || ID > F.InputFileInfosLoaded.size())
+    return InputFileInfo();
+
+  // If we've already loaded this input file, return it.
+  if (!F.InputFileInfosLoaded[ID - 1].Filename.empty())
+    return F.InputFileInfosLoaded[ID - 1];
+
   // Go find this input file.
   BitstreamCursor &Cursor = F.InputFilesCursor;
   SavedStreamPosition SavedPosition(Cursor);
@@ -2320,6 +2327,9 @@ ASTReader::readInputFileInfo(ModuleFile &F, unsigned ID) {
   }
   R.ContentHash = (static_cast<uint64_t>(Record[1]) << 32) |
                   static_cast<uint64_t>(Record[0]);
+
+  // Note that we've loaded this input file info.
+  F.InputFileInfosLoaded[ID - 1] = R;
   return R;
 }
 
@@ -2344,7 +2354,7 @@ InputFile ASTReader::getInputFile(ModuleFile &F, unsigned ID, bool Complain) {
     consumeError(std::move(Err));
   }
 
-  InputFileInfo FI = readInputFileInfo(F, ID);
+  InputFileInfo FI = getInputFileInfo(F, ID);
   off_t StoredSize = FI.StoredSize;
   time_t StoredTime = FI.StoredTime;
   bool Overridden = FI.Overridden;
@@ -2691,7 +2701,7 @@ ASTReader::ReadControlBlock(ModuleFile &F,
                                                                 : NumUserInputs;
         for (unsigned I = 0; I < N; ++I) {
           bool IsSystem = I >= NumUserInputs;
-          InputFileInfo FI = readInputFileInfo(F, I+1);
+          InputFileInfo FI = getInputFileInfo(F, I + 1);
           Listener->visitInputFile(FI.Filename, IsSystem, FI.Overridden,
                                    F.Kind == MK_ExplicitModule ||
                                    F.Kind == MK_PrebuiltModule);
@@ -2968,6 +2978,7 @@ ASTReader::ReadControlBlock(ModuleFile &F,
       F.InputFileOffsets =
           (const llvm::support::unaligned_uint64_t *)Blob.data();
       F.InputFilesLoaded.resize(NumInputs);
+      F.InputFileInfosLoaded.resize(NumInputs);
       F.NumUserInputFiles = NumUserInputs;
       break;
     }
@@ -2983,7 +2994,7 @@ void ASTReader::readIncludedFiles(ModuleFile &F, StringRef Blob,
 
   for (unsigned I = 0; I < FileCount; ++I) {
     size_t ID = endian::readNext<uint32_t, little, unaligned>(D);
-    InputFileInfo IFI = readInputFileInfo(F, ID);
+    InputFileInfo IFI = getInputFileInfo(F, ID);
     if (llvm::ErrorOr<const FileEntry *> File =
             PP.getFileManager().getFile(IFI.Filename))
       PP.getIncludedFiles().insert(*File);
@@ -9217,9 +9228,8 @@ void ASTReader::visitTopLevelModuleMaps(
     llvm::function_ref<void(FileEntryRef FE)> Visitor) {
   unsigned NumInputs = MF.InputFilesLoaded.size();
   for (unsigned I = 0; I < NumInputs; ++I) {
-    InputFileInfo IFI = readInputFileInfo(MF, I + 1);
+    InputFileInfo IFI = getInputFileInfo(MF, I + 1);
     if (IFI.TopLevelModuleMap)
-      // FIXME: This unnecessarily re-reads the InputFileInfo.
       if (auto FE = getInputFile(MF, I + 1).getFile())
         Visitor(*FE);
   }