[modules] Load the ModuleOffsetMap from the module header lazily.

If we never need to map any ID within the module to its global ID, we don't
need the module offset map. If a compilation transitively depends on lots of
unused module files, this can result in a modest performance improvement.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@295517 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Serialization/ASTReader.h b/include/clang/Serialization/ASTReader.h
index acdcaaf60054b8bd0aa7538388b956814b6c1528..88e75d6a633ced4d3df6576483b02b90c964fbc5 100644 (file)
--- a/include/clang/Serialization/ASTReader.h
+++ b/include/clang/Serialization/ASTReader.h
@@ -1188,6 +1188,7 @@ private:
       std::string &SuggestedPredefines, bool ValidateDiagnosticOptions);
   ASTReadResult ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities);
   ASTReadResult ReadExtensionBlock(ModuleFile &F);
+  void ReadModuleOffsetMap(ModuleFile &F) const;
   bool ParseLineTable(ModuleFile &F, const RecordData &Record);
   bool ReadSourceManagerBlock(ModuleFile &F);
   llvm::BitstreamCursor &SLocCursorForID(int ID);
@@ -1322,9 +1323,9 @@ private:
   ///
   /// This routine should only be used for fatal errors that have to
   /// do with non-routine failures (e.g., corrupted AST file).
-  void Error(StringRef Msg);
+  void Error(StringRef Msg) const;
   void Error(unsigned DiagID, StringRef Arg1 = StringRef(),
-             StringRef Arg2 = StringRef());
+             StringRef Arg2 = StringRef()) const;
 
   ASTReader(const ASTReader &) = delete;
   void operator=(const ASTReader &) = delete;
@@ -1905,10 +1906,10 @@ public:
                                SmallVectorImpl<Decl *> *Decls = nullptr);
 
   /// \brief Report a diagnostic.
-  DiagnosticBuilder Diag(unsigned DiagID);
+  DiagnosticBuilder Diag(unsigned DiagID) const;
 
   /// \brief Report a diagnostic.
-  DiagnosticBuilder Diag(SourceLocation Loc, unsigned DiagID);
+  DiagnosticBuilder Diag(SourceLocation Loc, unsigned DiagID) const;
 
   IdentifierInfo *DecodeIdentifierInfo(serialization::IdentifierID ID);
 
@@ -2060,6 +2061,8 @@ public:
   /// location space into ours.
   SourceLocation TranslateSourceLocation(ModuleFile &ModuleFile,
                                          SourceLocation Loc) const {
+    if (!ModuleFile.ModuleOffsetMap.empty())
+      ReadModuleOffsetMap(ModuleFile);
     assert(ModuleFile.SLocRemap.find(Loc.getOffset()) !=
                ModuleFile.SLocRemap.end() &&
            "Cannot find offset to remap.");

diff --git a/include/clang/Serialization/Module.h b/include/clang/Serialization/Module.h
index 15cd8c22b3543c3ef85d1d453637912597121c12..2fd156ceb4f49e2768b9cc1bba15f5d9aff9fb37 100644 (file)
--- a/include/clang/Serialization/Module.h
+++ b/include/clang/Serialization/Module.h
@@ -201,6 +201,10 @@ public:
   /// file.
   std::vector<std::unique_ptr<ModuleFileExtensionReader>> ExtensionReaders;
 
+  /// The module offset map data for this file. If non-empty, the various
+  /// ContinuousRangeMaps described below have not yet been populated.
+  StringRef ModuleOffsetMap;
+
   // === Input Files ===
   /// \brief The cursor to the start of the input-files block.
   llvm::BitstreamCursor InputFilesCursor;

diff --git a/include/clang/Serialization/ModuleManager.h b/include/clang/Serialization/ModuleManager.h
index 0f4ec664864c3eae1c96893f359f28575faf6ff8..70c9d9e54073e9720ff5da5abe3c2ba651e4c470 100644 (file)
--- a/include/clang/Serialization/ModuleManager.h
+++ b/include/clang/Serialization/ModuleManager.h
@@ -160,10 +160,10 @@ public:
   ModuleFile &operator[](unsigned Index) const { return *Chain[Index]; }
   
   /// \brief Returns the module associated with the given name
-  ModuleFile *lookup(StringRef Name);
+  ModuleFile *lookup(StringRef Name) const;
 
   /// \brief Returns the module associated with the given module file.
-  ModuleFile *lookup(const FileEntry *File);
+  ModuleFile *lookup(const FileEntry *File) const;
 
   /// \brief Returns the in-memory (virtual file) buffer with the given name
   std::unique_ptr<llvm::MemoryBuffer> lookupBuffer(StringRef Name);

diff --git a/lib/Serialization/ASTReader.cpp b/lib/Serialization/ASTReader.cpp
index 452f5410a8cdaa890bca2558c867125885c11670..985d68e348ec08eed0141477b4a6893d4c6cf686 100644 (file)
--- a/lib/Serialization/ASTReader.cpp
+++ b/lib/Serialization/ASTReader.cpp
@@ -1107,7 +1107,7 @@ bool ASTReader::ReadVisibleDeclContextStorage(ModuleFile &M,
   return false;
 }
 
-void ASTReader::Error(StringRef Msg) {
+void ASTReader::Error(StringRef Msg) const {
   Error(diag::err_fe_pch_malformed, Msg);
   if (Context.getLangOpts().Modules && !Diags.isDiagnosticInFlight() &&
       !PP.getHeaderSearchInfo().getModuleCachePath().empty()) {
@@ -1117,7 +1117,7 @@ void ASTReader::Error(StringRef Msg) {
 }
 
 void ASTReader::Error(unsigned DiagID,
-                      StringRef Arg1, StringRef Arg2) {
+                      StringRef Arg1, StringRef Arg2) const {
   if (Diags.isDiagnosticInFlight())
     Diags.SetDelayedDiagnostic(DiagID, Arg1, Arg2);
   else
@@ -1584,7 +1584,11 @@ MacroInfo *ASTReader::ReadMacroRecord(ModuleFile &F, uint64_t Offset) {
 }
 
 PreprocessedEntityID
-ASTReader::getGlobalPreprocessedEntityID(ModuleFile &M, unsigned LocalID) const {
+ASTReader::getGlobalPreprocessedEntityID(ModuleFile &M,
+                                         unsigned LocalID) const {
+  if (!M.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(M);
+
   ContinuousRangeMap<uint32_t, int, 2>::const_iterator
     I = M.PreprocessedEntityRemap.find(LocalID - NUM_PREDEF_PP_ENTITY_IDS);
   assert(I != M.PreprocessedEntityRemap.end()
@@ -2935,83 +2939,9 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
       break;
     }
 
-    case MODULE_OFFSET_MAP: {
-      // Additional remapping information.
-      const unsigned char *Data = (const unsigned char*)Blob.data();
-      const unsigned char *DataEnd = Data + Blob.size();
-
-      // If we see this entry before SOURCE_LOCATION_OFFSETS, add placeholders.
-      if (F.SLocRemap.find(0) == F.SLocRemap.end()) {
-        F.SLocRemap.insert(std::make_pair(0U, 0));
-        F.SLocRemap.insert(std::make_pair(2U, 1));
-      }
-
-      // Continuous range maps we may be updating in our module.
-      typedef ContinuousRangeMap<uint32_t, int, 2>::Builder
-          RemapBuilder;
-      RemapBuilder SLocRemap(F.SLocRemap);
-      RemapBuilder IdentifierRemap(F.IdentifierRemap);
-      RemapBuilder MacroRemap(F.MacroRemap);
-      RemapBuilder PreprocessedEntityRemap(F.PreprocessedEntityRemap);
-      RemapBuilder SubmoduleRemap(F.SubmoduleRemap);
-      RemapBuilder SelectorRemap(F.SelectorRemap);
-      RemapBuilder DeclRemap(F.DeclRemap);
-      RemapBuilder TypeRemap(F.TypeRemap);
-
-      while (Data < DataEnd) {
-        using namespace llvm::support;
-        uint16_t Len = endian::readNext<uint16_t, little, unaligned>(Data);
-        StringRef Name = StringRef((const char*)Data, Len);
-        Data += Len;
-        ModuleFile *OM = ModuleMgr.lookup(Name);
-        if (!OM) {
-          std::string Msg =
-              "SourceLocation remap refers to unknown module, cannot find ";
-          Msg.append(Name);
-          Error(Msg);
-          return Failure;
-        }
-
-        uint32_t SLocOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t IdentifierIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t MacroIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t PreprocessedEntityIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t SubmoduleIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t SelectorIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t DeclIDOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-        uint32_t TypeIndexOffset =
-            endian::readNext<uint32_t, little, unaligned>(Data);
-
-        uint32_t None = std::numeric_limits<uint32_t>::max();
-
-        auto mapOffset = [&](uint32_t Offset, uint32_t BaseOffset,
-                             RemapBuilder &Remap) {
-          if (Offset != None)
-            Remap.insert(std::make_pair(Offset,
-                                        static_cast<int>(BaseOffset - Offset)));
-        };
-        mapOffset(SLocOffset, OM->SLocEntryBaseOffset, SLocRemap);
-        mapOffset(IdentifierIDOffset, OM->BaseIdentifierID, IdentifierRemap);
-        mapOffset(MacroIDOffset, OM->BaseMacroID, MacroRemap);
-        mapOffset(PreprocessedEntityIDOffset, OM->BasePreprocessedEntityID,
-                  PreprocessedEntityRemap);
-        mapOffset(SubmoduleIDOffset, OM->BaseSubmoduleID, SubmoduleRemap);
-        mapOffset(SelectorIDOffset, OM->BaseSelectorID, SelectorRemap);
-        mapOffset(DeclIDOffset, OM->BaseDeclID, DeclRemap);
-        mapOffset(TypeIndexOffset, OM->BaseTypeIndex, TypeRemap);
-
-        // Global -> local mappings.
-        F.GlobalToLocalDeclIDs[OM] = DeclIDOffset;
-      }
+    case MODULE_OFFSET_MAP:
+      F.ModuleOffsetMap = Blob;
       break;
-    }
 
     case SOURCE_MANAGER_LINE_TABLE:
       if (ParseLineTable(F, Record))
@@ -3348,6 +3278,87 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
   }
 }
 
+void ASTReader::ReadModuleOffsetMap(ModuleFile &F) const {
+  assert(!F.ModuleOffsetMap.empty() && "no module offset map to read");
+
+  // Additional remapping information.
+  const unsigned char *Data = (const unsigned char*)F.ModuleOffsetMap.data();
+  const unsigned char *DataEnd = Data + F.ModuleOffsetMap.size();
+  F.ModuleOffsetMap = StringRef();
+
+  // If we see this entry before SOURCE_LOCATION_OFFSETS, add placeholders.
+  if (F.SLocRemap.find(0) == F.SLocRemap.end()) {
+    F.SLocRemap.insert(std::make_pair(0U, 0));
+    F.SLocRemap.insert(std::make_pair(2U, 1));
+  }
+
+  // Continuous range maps we may be updating in our module.
+  typedef ContinuousRangeMap<uint32_t, int, 2>::Builder
+      RemapBuilder;
+  RemapBuilder SLocRemap(F.SLocRemap);
+  RemapBuilder IdentifierRemap(F.IdentifierRemap);
+  RemapBuilder MacroRemap(F.MacroRemap);
+  RemapBuilder PreprocessedEntityRemap(F.PreprocessedEntityRemap);
+  RemapBuilder SubmoduleRemap(F.SubmoduleRemap);
+  RemapBuilder SelectorRemap(F.SelectorRemap);
+  RemapBuilder DeclRemap(F.DeclRemap);
+  RemapBuilder TypeRemap(F.TypeRemap);
+
+  while (Data < DataEnd) {
+    // FIXME: Looking up dependency modules by filename is horrible.
+    using namespace llvm::support;
+    uint16_t Len = endian::readNext<uint16_t, little, unaligned>(Data);
+    StringRef Name = StringRef((const char*)Data, Len);
+    Data += Len;
+    ModuleFile *OM = ModuleMgr.lookup(Name);
+    if (!OM) {
+      std::string Msg =
+          "SourceLocation remap refers to unknown module, cannot find ";
+      Msg.append(Name);
+      Error(Msg);
+      return;
+    }
+
+    uint32_t SLocOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t IdentifierIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t MacroIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t PreprocessedEntityIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t SubmoduleIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t SelectorIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t DeclIDOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+    uint32_t TypeIndexOffset =
+        endian::readNext<uint32_t, little, unaligned>(Data);
+
+    uint32_t None = std::numeric_limits<uint32_t>::max();
+
+    auto mapOffset = [&](uint32_t Offset, uint32_t BaseOffset,
+                         RemapBuilder &Remap) {
+      if (Offset != None)
+        Remap.insert(std::make_pair(Offset,
+                                    static_cast<int>(BaseOffset - Offset)));
+    };
+    mapOffset(SLocOffset, OM->SLocEntryBaseOffset, SLocRemap);
+    mapOffset(IdentifierIDOffset, OM->BaseIdentifierID, IdentifierRemap);
+    mapOffset(MacroIDOffset, OM->BaseMacroID, MacroRemap);
+    mapOffset(PreprocessedEntityIDOffset, OM->BasePreprocessedEntityID,
+              PreprocessedEntityRemap);
+    mapOffset(SubmoduleIDOffset, OM->BaseSubmoduleID, SubmoduleRemap);
+    mapOffset(SelectorIDOffset, OM->BaseSelectorID, SelectorRemap);
+    mapOffset(DeclIDOffset, OM->BaseDeclID, DeclRemap);
+    mapOffset(TypeIndexOffset, OM->BaseTypeIndex, TypeRemap);
+
+    // Global -> local mappings.
+    F.GlobalToLocalDeclIDs[OM] = DeclIDOffset;
+  }
+}
+
 ASTReader::ASTReadResult
 ASTReader::ReadModuleMapFileBlock(RecordData &Record, ModuleFile &F,
                                   const ModuleFile *ImportedBy,
@@ -6434,6 +6445,9 @@ ASTReader::getGlobalTypeID(ModuleFile &F, unsigned LocalID) const {
   if (LocalIndex < NUM_PREDEF_TYPE_IDS)
     return LocalID;
 
+  if (!F.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(F);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = F.TypeRemap.find(LocalIndex - NUM_PREDEF_TYPE_IDS);
   assert(I != F.TypeRemap.end() && "Invalid index into type index remap");
@@ -6614,6 +6628,9 @@ ASTReader::getGlobalDeclID(ModuleFile &F, LocalDeclID LocalID) const {
   if (LocalID < NUM_PREDEF_DECL_IDS)
     return LocalID;
 
+  if (!F.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(F);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = F.DeclRemap.find(LocalID - NUM_PREDEF_DECL_IDS);
   assert(I != F.DeclRemap.end() && "Invalid index into decl index remap");
@@ -7788,6 +7805,9 @@ IdentifierID ASTReader::getGlobalIdentifierID(ModuleFile &M, unsigned LocalID) {
   if (LocalID < NUM_PREDEF_IDENT_IDS)
     return LocalID;
 
+  if (!M.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(M);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = M.IdentifierRemap.find(LocalID - NUM_PREDEF_IDENT_IDS);
   assert(I != M.IdentifierRemap.end()
@@ -7826,6 +7846,9 @@ MacroID ASTReader::getGlobalMacroID(ModuleFile &M, unsigned LocalID) {
   if (LocalID < NUM_PREDEF_MACRO_IDS)
     return LocalID;
 
+  if (!M.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(M);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = M.MacroRemap.find(LocalID - NUM_PREDEF_MACRO_IDS);
   assert(I != M.MacroRemap.end() && "Invalid index into macro index remap");
@@ -7838,6 +7861,9 @@ ASTReader::getGlobalSubmoduleID(ModuleFile &M, unsigned LocalID) {
   if (LocalID < NUM_PREDEF_SUBMODULE_IDS)
     return LocalID;
 
+  if (!M.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(M);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = M.SubmoduleRemap.find(LocalID - NUM_PREDEF_SUBMODULE_IDS);
   assert(I != M.SubmoduleRemap.end()
@@ -7966,6 +7992,9 @@ ASTReader::getGlobalSelectorID(ModuleFile &M, unsigned LocalID) const {
   if (LocalID < NUM_PREDEF_SELECTOR_IDS)
     return LocalID;
 
+  if (!M.ModuleOffsetMap.empty())
+    ReadModuleOffsetMap(M);
+
   ContinuousRangeMap<uint32_t, int, 2>::iterator I
     = M.SelectorRemap.find(LocalID - NUM_PREDEF_SELECTOR_IDS);
   assert(I != M.SelectorRemap.end()
@@ -8491,11 +8520,11 @@ CXXTemporary *ASTReader::ReadCXXTemporary(ModuleFile &F,
   return CXXTemporary::Create(Context, Decl);
 }
 
-DiagnosticBuilder ASTReader::Diag(unsigned DiagID) {
+DiagnosticBuilder ASTReader::Diag(unsigned DiagID) const {
   return Diag(CurrentImportLoc, DiagID);
 }
 
-DiagnosticBuilder ASTReader::Diag(SourceLocation Loc, unsigned DiagID) {
+DiagnosticBuilder ASTReader::Diag(SourceLocation Loc, unsigned DiagID) const {
   return Diags.Report(Loc, DiagID);
 }
 

diff --git a/lib/Serialization/ModuleManager.cpp b/lib/Serialization/ModuleManager.cpp
index b7ee30254ff1eea7d9d5b91c2f71a609893da304..f0654fc10b4a9c94a7fcd5870b1e381a7a98c0ad 100644 (file)
--- a/lib/Serialization/ModuleManager.cpp
+++ b/lib/Serialization/ModuleManager.cpp
@@ -27,7 +27,7 @@
 using namespace clang;
 using namespace serialization;
 
-ModuleFile *ModuleManager::lookup(StringRef Name) {
+ModuleFile *ModuleManager::lookup(StringRef Name) const {
   const FileEntry *Entry = FileMgr.getFile(Name, /*openFile=*/false,
                                            /*cacheFailure=*/false);
   if (Entry)
@@ -36,9 +36,8 @@ ModuleFile *ModuleManager::lookup(StringRef Name) {
   return nullptr;
 }
 
-ModuleFile *ModuleManager::lookup(const FileEntry *File) {
-  llvm::DenseMap<const FileEntry *, ModuleFile *>::iterator Known
-    = Modules.find(File);
+ModuleFile *ModuleManager::lookup(const FileEntry *File) const {
+  auto Known = Modules.find(File);
   if (Known == Modules.end())
     return nullptr;