[serialization] no transitive decl change

Author: ChuanqiXu9

clang/include/clang/AST/DeclBase.h

@@ -701,10 +701,7 @@ class alignas(8) Decl {
 
   /// Set the owning module ID.  This may only be called for
   /// deserialized Decls.
-  void setOwningModuleID(unsigned ID) {
-    assert(isFromASTFile() && "Only works on a deserialized declaration");
-    *((unsigned*)this - 2) = ID;
-  }
+  void setOwningModuleID(unsigned ID);
 
 public:
   /// Determine the availability of the given declaration.
@@ -777,19 +774,11 @@ class alignas(8) Decl {
 
   /// Retrieve the global declaration ID associated with this
   /// declaration, which specifies where this Decl was loaded from.
-  GlobalDeclID getGlobalID() const {
-    if (isFromASTFile())
-      return (*((const GlobalDeclID *)this - 1));
-    return GlobalDeclID();
-  }
+  GlobalDeclID getGlobalID() const;
 
   /// Retrieve the global ID of the module that owns this particular
   /// declaration.
-  unsigned getOwningModuleID() const {
-    if (isFromASTFile())
-      return *((const unsigned*)this - 2);
-    return 0;
-  }
+  unsigned getOwningModuleID() const;
 
 private:
   Module *getOwningModuleSlow() const;

clang/include/clang/AST/DeclID.h

@@ -19,6 +19,8 @@
 #include "llvm/ADT/DenseMapInfo.h"
 #include "llvm/ADT/iterator.h"
 
+#include <climits>
+
 namespace clang {
 
 /// Predefined declaration IDs.
@@ -107,12 +109,16 @@ class DeclIDBase {
   ///
   /// DeclID should only be used directly in serialization. All other users
   /// should use LocalDeclID or GlobalDeclID.
-  using DeclID = uint32_t;
+  using DeclID = uint64_t;
 
 protected:
   DeclIDBase() : ID(PREDEF_DECL_NULL_ID) {}
   explicit DeclIDBase(DeclID ID) : ID(ID) {}
 
+  explicit DeclIDBase(unsigned LocalID, unsigned ModuleFileIndex) {
+    ID = (DeclID)LocalID | ((DeclID)ModuleFileIndex << 32);
+  }
+
 public:
   DeclID get() const { return ID; }
 
@@ -124,6 +130,15 @@ class DeclIDBase {
 
   bool isInvalid() const { return ID == PREDEF_DECL_NULL_ID; }
 
+  unsigned getModuleFileIndex() const { return ID >> 32; }
+
+  unsigned getLocalDeclIndex() const {
+    // Implement it directly instead of calling `llvm::maskTrailingOnes` since
+    // we don't want `MathExtras.h` to be inclued here.
+    const unsigned Bits = CHAR_BIT * sizeof(DeclID);
+    return ID & (DeclID(-1) >> (Bits - 32));
+  }
+
   friend bool operator==(const DeclIDBase &LHS, const DeclIDBase &RHS) {
     return LHS.ID == RHS.ID;
   }
@@ -156,6 +171,9 @@ class LocalDeclID : public DeclIDBase {
   LocalDeclID(PredefinedDeclIDs ID) : Base(ID) {}
   explicit LocalDeclID(DeclID ID) : Base(ID) {}
 
+  explicit LocalDeclID(unsigned LocalID, unsigned ModuleFileIndex)
+      : Base(LocalID, ModuleFileIndex) {}
+
   LocalDeclID &operator++() {
     ++ID;
     return *this;
@@ -175,6 +193,9 @@ class GlobalDeclID : public DeclIDBase {
   GlobalDeclID() : Base() {}
   explicit GlobalDeclID(DeclID ID) : Base(ID) {}
 
+  explicit GlobalDeclID(unsigned LocalID, unsigned ModuleFileIndex)
+      : Base(LocalID, ModuleFileIndex) {}
+
   // For DeclIDIterator<GlobalDeclID> to be able to convert a GlobalDeclID
   // to a LocalDeclID.
   explicit operator LocalDeclID() const { return LocalDeclID(this->ID); }

clang/include/clang/Serialization/ASTBitCodes.h

@@ -255,6 +255,12 @@ class DeclOffset {
   }
 };
 
+// The unaligned decl ID used in the Blobs of bistreams.
+using unalighed_decl_id_t =
+    llvm::support::detail::packed_endian_specific_integral<
+        serialization::DeclID, llvm::endianness::native,
+        llvm::support::unaligned>;
+
 /// The number of predefined preprocessed entity IDs.
 const unsigned int NUM_PREDEF_PP_ENTITY_IDS = 1;
 

clang/include/clang/Serialization/ASTReader.h

@@ -501,12 +501,6 @@ class ASTReader
   /// = I + 1 has already been loaded.
   llvm::PagedVector<Decl *> DeclsLoaded;
 
-  using GlobalDeclMapType = ContinuousRangeMap<GlobalDeclID, ModuleFile *, 4>;
-
-  /// Mapping from global declaration IDs to the module in which the
-  /// declaration resides.
-  GlobalDeclMapType GlobalDeclMap;
-
   using FileOffset = std::pair<ModuleFile *, uint64_t>;
   using FileOffsetsTy = SmallVector<FileOffset, 2>;
   using DeclUpdateOffsetsMap = llvm::DenseMap<GlobalDeclID, FileOffsetsTy>;
@@ -589,10 +583,11 @@ class ASTReader
 
   struct FileDeclsInfo {
     ModuleFile *Mod = nullptr;
-    ArrayRef<LocalDeclID> Decls;
+    ArrayRef<serialization::unalighed_decl_id_t> Decls;
 
     FileDeclsInfo() = default;
-    FileDeclsInfo(ModuleFile *Mod, ArrayRef<LocalDeclID> Decls)
+    FileDeclsInfo(ModuleFile *Mod,
+                  ArrayRef<serialization::unalighed_decl_id_t> Decls)
         : Mod(Mod), Decls(Decls) {}
   };
 
@@ -601,11 +596,7 @@ class ASTReader
 
   /// An array of lexical contents of a declaration context, as a sequence of
   /// Decl::Kind, DeclID pairs.
-  using unalighed_decl_id_t =
-      llvm::support::detail::packed_endian_specific_integral<
-          serialization::DeclID, llvm::endianness::native,
-          llvm::support::unaligned>;
-  using LexicalContents = ArrayRef<unalighed_decl_id_t>;
+  using LexicalContents = ArrayRef<serialization::unalighed_decl_id_t>;
 
   /// Map from a DeclContext to its lexical contents.
   llvm::DenseMap<const DeclContext*, std::pair<ModuleFile*, LexicalContents>>
@@ -1486,22 +1477,23 @@ class ASTReader
                                unsigned ClientLoadCapabilities);
 
 public:
-  class ModuleDeclIterator : public llvm::iterator_adaptor_base<
-                                 ModuleDeclIterator, const LocalDeclID *,
-                                 std::random_access_iterator_tag, const Decl *,
-                                 ptrdiff_t, const Decl *, const Decl *> {
+  class ModuleDeclIterator
+      : public llvm::iterator_adaptor_base<
+            ModuleDeclIterator, const serialization::unalighed_decl_id_t *,
+            std::random_access_iterator_tag, const Decl *, ptrdiff_t,
+            const Decl *, const Decl *> {
     ASTReader *Reader = nullptr;
     ModuleFile *Mod = nullptr;
 
   public:
     ModuleDeclIterator() : iterator_adaptor_base(nullptr) {}
 
     ModuleDeclIterator(ASTReader *Reader, ModuleFile *Mod,
-                       const LocalDeclID *Pos)
+                       const serialization::unalighed_decl_id_t *Pos)
         : iterator_adaptor_base(Pos), Reader(Reader), Mod(Mod) {}
 
     value_type operator*() const {
-      return Reader->GetDecl(Reader->getGlobalDeclID(*Mod, *I));
+      return Reader->GetDecl(Reader->getGlobalDeclID(*Mod, (LocalDeclID)*I));
     }
 
     value_type operator->() const { return **this; }
@@ -1541,6 +1533,9 @@ class ASTReader
              StringRef Arg2 = StringRef(), StringRef Arg3 = StringRef()) const;
   void Error(llvm::Error &&Err) const;
 
+  /// Translate a \param GlobalDeclID to the index of DeclsLoaded array.
+  unsigned translateGlobalDeclIDToIndex(GlobalDeclID ID) const;
+
 public:
   /// Load the AST file and validate its contents against the given
   /// Preprocessor.
@@ -1912,7 +1907,8 @@ class ASTReader
 
   /// Retrieve the module file that owns the given declaration, or NULL
   /// if the declaration is not from a module file.
-  ModuleFile *getOwningModuleFile(const Decl *D);
+  ModuleFile *getOwningModuleFile(const Decl *D) const;
+  ModuleFile *getOwningModuleFile(GlobalDeclID ID) const;
 
   /// Returns the source location for the decl \p ID.
   SourceLocation getSourceLocationForDeclID(GlobalDeclID ID);

clang/include/clang/Serialization/ModuleFile.h

@@ -454,23 +454,11 @@ class ModuleFile {
   /// by the declaration ID (-1).
   const DeclOffset *DeclOffsets = nullptr;
 
-  /// Base declaration ID for declarations local to this module.
-  serialization::DeclID BaseDeclID = 0;
-
-  /// Remapping table for declaration IDs in this module.
-  ContinuousRangeMap<serialization::DeclID, int, 2> DeclRemap;
-
-  /// Mapping from the module files that this module file depends on
-  /// to the base declaration ID for that module as it is understood within this
-  /// module.
-  ///
-  /// This is effectively a reverse global-to-local mapping for declaration
-  /// IDs, so that we can interpret a true global ID (for this translation unit)
-  /// as a local ID (for this module file).
-  llvm::DenseMap<ModuleFile *, serialization::DeclID> GlobalToLocalDeclIDs;
+  /// Base declaration index in ASTReader for declarations local to this module.
+  unsigned BaseDeclIndex = 0;
 
   /// Array of file-level DeclIDs sorted by file.
-  const LocalDeclID *FileSortedDecls = nullptr;
+  const serialization::unalighed_decl_id_t *FileSortedDecls = nullptr;
   unsigned NumFileSortedDecls = 0;
 
   /// Array of category list location information within this

clang/include/clang/Serialization/ModuleManager.h

@@ -46,7 +46,7 @@ namespace serialization {
 /// Manages the set of modules loaded by an AST reader.
 class ModuleManager {
   /// The chain of AST files, in the order in which we started to load
-  /// them (this order isn't really useful for anything).
+  /// them.
   SmallVector<std::unique_ptr<ModuleFile>, 2> Chain;
 
   /// The chain of non-module PCH files. The first entry is the one named

clang/lib/AST/DeclBase.cpp

@@ -74,18 +74,16 @@ void *Decl::operator new(std::size_t Size, const ASTContext &Context,
                          GlobalDeclID ID, std::size_t Extra) {
   // Allocate an extra 8 bytes worth of storage, which ensures that the
   // resulting pointer will still be 8-byte aligned.
-  static_assert(sizeof(unsigned) * 2 >= alignof(Decl),
-                "Decl won't be misaligned");
+  static_assert(sizeof(uint64_t) >= alignof(Decl), "Decl won't be misaligned");
   void *Start = Context.Allocate(Size + Extra + 8);
   void *Result = (char*)Start + 8;
 
-  unsigned *PrefixPtr = (unsigned *)Result - 2;
+  uint64_t *PrefixPtr = (uint64_t *)Result - 1;
 
-  // Zero out the first 4 bytes; this is used to store the owning module ID.
-  PrefixPtr[0] = 0;
+  *PrefixPtr = ID.get();
 
-  // Store the global declaration ID in the second 4 bytes.
-  PrefixPtr[1] = ID.get();
+  // We leave the upper 16 bits to store the module IDs.
+  assert(*PrefixPtr < llvm::maskTrailingOnes<uint64_t>(48));
 
   return Result;
 }
@@ -111,6 +109,28 @@ void *Decl::operator new(std::size_t Size, const ASTContext &Ctx,
   return ::operator new(Size + Extra, Ctx);
 }
 
+GlobalDeclID Decl::getGlobalID() const {
+  if (!isFromASTFile())
+    return GlobalDeclID();
+  uint64_t ID = *((const uint64_t *)this - 1);
+  return GlobalDeclID(ID & llvm::maskTrailingOnes<uint64_t>(48));
+}
+
+unsigned Decl::getOwningModuleID() const {
+  if (!isFromASTFile())
+    return 0;
+
+  uint64_t ID = *((const uint64_t *)this - 1);
+  return ID >> 48;
+}
+
+void Decl::setOwningModuleID(unsigned ID) {
+  assert(isFromASTFile() && "Only works on a deserialized declaration");
+  uint64_t *IDAddress = (uint64_t *)this - 1;
+  assert(!((*IDAddress) >> 48) && "We should only set the module ID once");
+  *IDAddress |= (uint64_t)ID << 48;
+}
+
 Module *Decl::getOwningModuleSlow() const {
   assert(isFromASTFile() && "Not from AST file?");
   return getASTContext().getExternalSource()->getModule(getOwningModuleID());