[clang][AST] Support AST files larger than 512M

Summary:
Clang uses 32-bit integers for storing bit offsets from the beginning of
the file that results in 512M limit on AST file. This diff replaces
absolute offsets with relative offsets from the beginning of
corresponding data structure when it is possible. And uses 64-bit
offsets for DeclOffests and TypeOffssts because these coder AST
section may easily exceeds 512M alone.

This diff breaks AST file format compatibility so VERSION_MAJOR bumped.

Test Plan:
Existing clang AST serialization tests
Tested on clangd with ~700M and ~900M preamble files

Reviewers: rsmith, dexonsmith

Subscribers: ilya-biryukov, kadircet, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D76594

Author: dmpolukhin

clang/include/clang/Serialization/ASTBitCodes.h

@@ -41,7 +41,7 @@ namespace serialization {
     /// Version 4 of AST files also requires that the version control branch and
     /// revision match exactly, since there is no backward compatibility of
     /// AST files at this time.
-    const unsigned VERSION_MAJOR = 9;
+    const unsigned VERSION_MAJOR = 10;
 
     /// AST file minor version number supported by this version of
     /// Clang.
@@ -181,7 +181,7 @@ namespace serialization {
       /// Raw source location of end of range.
       unsigned End;
 
-      /// Offset in the AST file.
+      /// Offset in the AST file relative to ModuleFile::MacroOffsetsBase.
       uint32_t BitOffset;
 
       PPEntityOffset(SourceRange R, uint32_t BitOffset)
@@ -221,12 +221,18 @@ namespace serialization {
       /// Raw source location.
       unsigned Loc = 0;
 
-      /// Offset in the AST file.
-      uint32_t BitOffset = 0;
+      /// Offset in the AST file. Split 64-bit integer into low/high parts
+      /// to keep structure alignment 32-bit and don't have padding gap.
+      /// This structure is serialized "as is" to the AST file and undefined
+      /// value in the padding affects AST hash.
+      uint32_t BitOffsetLow = 0;
+      uint32_t BitOffsetHigh = 0;
 
       DeclOffset() = default;
-      DeclOffset(SourceLocation Loc, uint32_t BitOffset)
-        : Loc(Loc.getRawEncoding()), BitOffset(BitOffset) {}
+      DeclOffset(SourceLocation Loc, uint64_t BitOffset) {
+        setLocation(Loc);
+        setBitOffset(BitOffset);
+      }
 
       void setLocation(SourceLocation L) {
         Loc = L.getRawEncoding();
@@ -235,6 +241,15 @@ namespace serialization {
       SourceLocation getLocation() const {
         return SourceLocation::getFromRawEncoding(Loc);
       }
+
+      void setBitOffset(uint64_t Offset) {
+        BitOffsetLow = Offset;
+        BitOffsetHigh = Offset >> 32;
+      }
+
+      uint64_t getBitOffset() const {
+        return BitOffsetLow | (uint64_t(BitOffsetHigh) << 32);
+      }
     };
 
     /// The number of predefined preprocessed entity IDs.

clang/include/clang/Serialization/ASTReader.h

@@ -723,9 +723,10 @@ class ASTReader
 
   struct PendingMacroInfo {
     ModuleFile *M;
-    uint64_t MacroDirectivesOffset;
+    /// Offset relative to ModuleFile::MacroOffsetsBase.
+    uint32_t MacroDirectivesOffset;
 
-    PendingMacroInfo(ModuleFile *M, uint64_t MacroDirectivesOffset)
+    PendingMacroInfo(ModuleFile *M, uint32_t MacroDirectivesOffset)
         : M(M), MacroDirectivesOffset(MacroDirectivesOffset) {}
   };
 
@@ -2205,7 +2206,7 @@ class ASTReader
   /// \param MacroDirectivesOffset Offset of the serialized macro directive
   /// history.
   void addPendingMacro(IdentifierInfo *II, ModuleFile *M,
-                       uint64_t MacroDirectivesOffset);
+                       uint32_t MacroDirectivesOffset);
 
   /// Read the set of macros defined by this external macro source.
   void ReadDefinedMacros() override;

clang/include/clang/Serialization/ASTWriter.h

@@ -243,7 +243,7 @@ class ASTWriter : public ASTDeserializationListener,
 
   /// Offset of each type in the bitstream, indexed by
   /// the type's ID.
-  std::vector<uint32_t> TypeOffsets;
+  std::vector<uint64_t> TypeOffsets;
 
   /// The first ID number we can use for our own identifiers.
   serialization::IdentID FirstIdentID = serialization::NUM_PREDEF_IDENT_IDS;
@@ -277,7 +277,8 @@ class ASTWriter : public ASTDeserializationListener,
   /// The macro infos to emit.
   std::vector<MacroInfoToEmitData> MacroInfosToEmit;
 
-  llvm::DenseMap<const IdentifierInfo *, uint64_t> IdentMacroDirectivesOffsetMap;
+  llvm::DenseMap<const IdentifierInfo *, uint32_t>
+      IdentMacroDirectivesOffsetMap;
 
   /// @name FlushStmt Caches
   /// @{
@@ -464,7 +465,8 @@ class ASTWriter : public ASTDeserializationListener,
                                const Preprocessor &PP);
   void WritePreprocessor(const Preprocessor &PP, bool IsModule);
   void WriteHeaderSearch(const HeaderSearch &HS);
-  void WritePreprocessorDetail(PreprocessingRecord &PPRec);
+  void WritePreprocessorDetail(PreprocessingRecord &PPRec,
+                               uint64_t MacroOffsetsBase);
   void WriteSubmodules(Module *WritingModule);
 
   void WritePragmaDiagnosticMappings(const DiagnosticsEngine &Diag,
@@ -588,7 +590,7 @@ class ASTWriter : public ASTDeserializationListener,
   /// Determine the ID of an already-emitted macro.
   serialization::MacroID getMacroID(MacroInfo *MI);
 
-  uint64_t getMacroDirectivesOffset(const IdentifierInfo *Name);
+  uint32_t getMacroDirectivesOffset(const IdentifierInfo *Name);
 
   /// Emit a reference to a type.
   void AddTypeRef(QualType T, RecordDataImpl &Record);

clang/include/clang/Serialization/ModuleFile.h

@@ -251,6 +251,10 @@ class ModuleFile {
   /// The base offset in the source manager's view of this module.
   unsigned SLocEntryBaseOffset = 0;
 
+  /// Base file offset for the offsets in SLocEntryOffsets. Real file offset
+  /// for the entry is SLocEntryOffsetsBase + SLocEntryOffsets[i].
+  uint64_t SLocEntryOffsetsBase = 0;
+
   /// Offsets for all of the source location entries in the
   /// AST file.
   const uint32_t *SLocEntryOffsets = nullptr;
@@ -302,6 +306,10 @@ class ModuleFile {
   /// The number of macros in this AST file.
   unsigned LocalNumMacros = 0;
 
+  /// Base file offset for the offsets in MacroOffsets. Real file offset for
+  /// the entry is MacroOffsetsBase + MacroOffsets[i].
+  uint64_t MacroOffsetsBase = 0;
+
   /// Offsets of macros in the preprocessor block.
   ///
   /// This array is indexed by the macro ID (-1), and provides
@@ -450,7 +458,7 @@ class ModuleFile {
 
   /// Offset of each type within the bitstream, indexed by the
   /// type ID, or the representation of a Type*.
-  const uint32_t *TypeOffsets = nullptr;
+  const uint64_t *TypeOffsets = nullptr;
 
   /// Base type ID for types local to this module as represented in
   /// the global type ID space.

clang/lib/Serialization/ASTReader.cpp

@@ -1470,6 +1470,7 @@ bool ASTReader::ReadSLocEntry(int ID) {
 
   ModuleFile *F = GlobalSLocEntryMap.find(-ID)->second;
   if (llvm::Error Err = F->SLocEntryCursor.JumpToBit(
+          F->SLocEntryOffsetsBase +
           F->SLocEntryOffsets[ID - F->SLocEntryBaseID])) {
     Error(std::move(Err));
     return true;
@@ -1932,9 +1933,8 @@ HeaderFileInfoTrait::ReadData(internal_key_ref key, const unsigned char *d,
   return HFI;
 }
 
-void ASTReader::addPendingMacro(IdentifierInfo *II,
-                                ModuleFile *M,
-                                uint64_t MacroDirectivesOffset) {
+void ASTReader::addPendingMacro(IdentifierInfo *II, ModuleFile *M,
+                                uint32_t MacroDirectivesOffset) {
   assert(NumCurrentElementsDeserializing > 0 &&"Missing deserialization guard");
   PendingMacroIDs[II].push_back(PendingMacroInfo(M, MacroDirectivesOffset));
 }
@@ -2099,7 +2099,8 @@ void ASTReader::resolvePendingMacro(IdentifierInfo *II,
 
   BitstreamCursor &Cursor = M.MacroCursor;
   SavedStreamPosition SavedPosition(Cursor);
-  if (llvm::Error Err = Cursor.JumpToBit(PMInfo.MacroDirectivesOffset)) {
+  if (llvm::Error Err =
+          Cursor.JumpToBit(M.MacroOffsetsBase + PMInfo.MacroDirectivesOffset)) {
     Error(std::move(Err));
     return;
   }
@@ -3098,7 +3099,7 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
         Error("duplicate TYPE_OFFSET record in AST file");
         return Failure;
       }
-      F.TypeOffsets = (const uint32_t *)Blob.data();
+      F.TypeOffsets = reinterpret_cast<const uint64_t *>(Blob.data());
       F.LocalNumTypes = Record[0];
       unsigned LocalBaseTypeIndex = Record[1];
       F.BaseTypeIndex = getTotalNumTypes();
@@ -3376,6 +3377,7 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
       F.SLocEntryOffsets = (const uint32_t *)Blob.data();
       F.LocalNumSLocEntries = Record[0];
       unsigned SLocSpaceSize = Record[1];
+      F.SLocEntryOffsetsBase = Record[2];
       std::tie(F.SLocEntryBaseID, F.SLocEntryBaseOffset) =
           SourceMgr.AllocateLoadedSLocEntries(F.LocalNumSLocEntries,
                                               SLocSpaceSize);
@@ -3694,6 +3696,7 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
       F.MacroOffsets = (const uint32_t *)Blob.data();
       F.LocalNumMacros = Record[0];
       unsigned LocalBaseMacroID = Record[1];
+      F.MacroOffsetsBase = Record[2];
       F.BaseMacroID = getTotalNumMacros();
 
       if (F.LocalNumMacros > 0) {
@@ -5907,8 +5910,8 @@ PreprocessedEntity *ASTReader::ReadPreprocessedEntity(unsigned Index) {
   }
 
   SavedStreamPosition SavedPosition(M.PreprocessorDetailCursor);
-  if (llvm::Error Err =
-          M.PreprocessorDetailCursor.JumpToBit(PPOffs.BitOffset)) {
+  if (llvm::Error Err = M.PreprocessorDetailCursor.JumpToBit(
+          M.MacroOffsetsBase + PPOffs.BitOffset)) {
     Error(std::move(Err));
     return nullptr;
   }
@@ -8427,7 +8430,8 @@ MacroInfo *ASTReader::getMacro(MacroID ID) {
     assert(I != GlobalMacroMap.end() && "Corrupted global macro map");
     ModuleFile *M = I->second;
     unsigned Index = ID - M->BaseMacroID;
-    MacrosLoaded[ID] = ReadMacroRecord(*M, M->MacroOffsets[Index]);
+    MacrosLoaded[ID] =
+        ReadMacroRecord(*M, M->MacroOffsetsBase + M->MacroOffsets[Index]);
 
     if (DeserializationListener)
       DeserializationListener->MacroRead(ID + NUM_PREDEF_MACRO_IDS,

clang/lib/Serialization/ASTReaderDecl.cpp

@@ -2870,7 +2870,7 @@ ASTReader::DeclCursorForID(DeclID ID, SourceLocation &Loc) {
   const DeclOffset &DOffs =
       M->DeclOffsets[ID - M->BaseDeclID - NUM_PREDEF_DECL_IDS];
   Loc = TranslateSourceLocation(*M, DOffs.getLocation());
-  return RecordLocation(M, DOffs.BitOffset);
+  return RecordLocation(M, DOffs.getBitOffset());
 }
 
 ASTReader::RecordLocation ASTReader::getLocalBitOffset(uint64_t GlobalOffset) {

clang/lib/Serialization/ASTWriter.cpp

@@ -1893,6 +1893,7 @@ void ASTWriter::WriteSourceManagerBlock(SourceManager &SourceMgr,
   // Write out the source location entry table. We skip the first
   // entry, which is always the same dummy entry.
   std::vector<uint32_t> SLocEntryOffsets;
+  uint64_t SLocEntryOffsetsBase = Stream.GetCurrentBitNo();
   RecordData PreloadSLocs;
   SLocEntryOffsets.reserve(SourceMgr.local_sloc_entry_size() - 1);
   for (unsigned I = 1, N = SourceMgr.local_sloc_entry_size();
@@ -1903,7 +1904,9 @@ void ASTWriter::WriteSourceManagerBlock(SourceManager &SourceMgr,
     assert(&SourceMgr.getSLocEntry(FID) == SLoc);
 
     // Record the offset of this source-location entry.
-    SLocEntryOffsets.push_back(Stream.GetCurrentBitNo());
+    uint64_t Offset = Stream.GetCurrentBitNo() - SLocEntryOffsetsBase;
+    assert((Offset >> 32) == 0 && "SLocEntry offset too large");
+    SLocEntryOffsets.push_back(Offset);
 
     // Figure out which record code to use.
     unsigned Code;
@@ -2011,12 +2014,14 @@ void ASTWriter::WriteSourceManagerBlock(SourceManager &SourceMgr,
   Abbrev->Add(BitCodeAbbrevOp(SOURCE_LOCATION_OFFSETS));
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 16)); // # of slocs
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 16)); // total size
+  Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 32)); // base offset
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob)); // offsets
   unsigned SLocOffsetsAbbrev = Stream.EmitAbbrev(std::move(Abbrev));
   {
     RecordData::value_type Record[] = {
         SOURCE_LOCATION_OFFSETS, SLocEntryOffsets.size(),
-        SourceMgr.getNextLocalOffset() - 1 /* skip dummy */};
+        SourceMgr.getNextLocalOffset() - 1 /* skip dummy */,
+        SLocEntryOffsetsBase};
     Stream.EmitRecordWithBlob(SLocOffsetsAbbrev, Record,
                               bytes(SLocEntryOffsets));
   }
@@ -2093,9 +2098,11 @@ static bool shouldIgnoreMacro(MacroDirective *MD, bool IsModule,
 /// Writes the block containing the serialized form of the
 /// preprocessor.
 void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
+  uint64_t MacroOffsetsBase = Stream.GetCurrentBitNo();
+
   PreprocessingRecord *PPRec = PP.getPreprocessingRecord();
   if (PPRec)
-    WritePreprocessorDetail(*PPRec);
+    WritePreprocessorDetail(*PPRec, MacroOffsetsBase);
 
   RecordData Record;
   RecordData ModuleMacroRecord;
@@ -2156,7 +2163,8 @@ void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
   // identifier they belong to.
   for (const IdentifierInfo *Name : MacroIdentifiers) {
     MacroDirective *MD = PP.getLocalMacroDirectiveHistory(Name);
-    auto StartOffset = Stream.GetCurrentBitNo();
+    uint64_t StartOffset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+    assert((StartOffset >> 32) == 0 && "Macro identifiers offset too large");
 
     // Emit the macro directives in reverse source order.
     for (; MD; MD = MD->getPrevious()) {
@@ -2229,14 +2237,12 @@ void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
 
     // Record the local offset of this macro.
     unsigned Index = ID - FirstMacroID;
-    if (Index == MacroOffsets.size())
-      MacroOffsets.push_back(Stream.GetCurrentBitNo());
-    else {
-      if (Index > MacroOffsets.size())
-        MacroOffsets.resize(Index + 1);
+    if (Index >= MacroOffsets.size())
+      MacroOffsets.resize(Index + 1);
 
-      MacroOffsets[Index] = Stream.GetCurrentBitNo();
-    }
+    uint64_t Offset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+    assert((Offset >> 32) == 0 && "Macro offset too large");
+    MacroOffsets[Index] = Offset;
 
     AddIdentifierRef(Name, Record);
     AddSourceLocation(MI->getDefinitionLoc(), Record);
@@ -2287,17 +2293,20 @@ void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
   Abbrev->Add(BitCodeAbbrevOp(MACRO_OFFSET));
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // # of macros
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // first ID
+  Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 32));   // base offset
   Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob));
 
   unsigned MacroOffsetAbbrev = Stream.EmitAbbrev(std::move(Abbrev));
   {
     RecordData::value_type Record[] = {MACRO_OFFSET, MacroOffsets.size(),
-                                       FirstMacroID - NUM_PREDEF_MACRO_IDS};
+                                       FirstMacroID - NUM_PREDEF_MACRO_IDS,
+                                       MacroOffsetsBase};
     Stream.EmitRecordWithBlob(MacroOffsetAbbrev, Record, bytes(MacroOffsets));
   }
 }
 
-void ASTWriter::WritePreprocessorDetail(PreprocessingRecord &PPRec) {
+void ASTWriter::WritePreprocessorDetail(PreprocessingRecord &PPRec,
+                                        uint64_t MacroOffsetsBase) {
   if (PPRec.local_begin() == PPRec.local_end())
     return;
 
@@ -2334,8 +2343,10 @@ void ASTWriter::WritePreprocessorDetail(PreprocessingRecord &PPRec) {
        (void)++E, ++NumPreprocessingRecords, ++NextPreprocessorEntityID) {
     Record.clear();
 
+    uint64_t Offset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+    assert((Offset >> 32) == 0 && "Preprocessed entity offset too large");
     PreprocessedEntityOffsets.push_back(
-        PPEntityOffset((*E)->getSourceRange(), Stream.GetCurrentBitNo()));
+        PPEntityOffset((*E)->getSourceRange(), Offset));
 
     if (auto *MD = dyn_cast<MacroDefinitionRecord>(*E)) {
       // Record this macro definition's ID.
@@ -5144,7 +5155,7 @@ MacroID ASTWriter::getMacroID(MacroInfo *MI) {
   return MacroIDs[MI];
 }
 
-uint64_t ASTWriter::getMacroDirectivesOffset(const IdentifierInfo *Name) {
+uint32_t ASTWriter::getMacroDirectivesOffset(const IdentifierInfo *Name) {
   return IdentMacroDirectivesOffsetMap.lookup(Name);
 }
 

clang/lib/Serialization/ASTWriterDecl.cpp

@@ -2434,12 +2434,12 @@ void ASTWriter::WriteDecl(ASTContext &Context, Decl *D) {
   SourceLocation Loc = D->getLocation();
   unsigned Index = ID - FirstDeclID;
   if (DeclOffsets.size() == Index)
-    DeclOffsets.push_back(DeclOffset(Loc, Offset));
+    DeclOffsets.emplace_back(Loc, Offset);
   else if (DeclOffsets.size() < Index) {
     // FIXME: Can/should this happen?
     DeclOffsets.resize(Index+1);
     DeclOffsets[Index].setLocation(Loc);
-    DeclOffsets[Index].BitOffset = Offset;
+    DeclOffsets[Index].setBitOffset(Offset);
   } else {
     llvm_unreachable("declarations should be emitted in ID order");
   }