[HeaderSearch] Introduce LazyIdentifierInfoPtr for Controlling Macro in HeaderFileInfo

This patch is helpful to reduce 32 bits for HeaderFileInfo by combining
a uint32_t and pointer into a tagged pointer.

This is reviewed as part of
#92085 and required to be split
as a separate commit

Author: ChuanqiXu9

clang/include/clang/Lex/ExternalPreprocessorSource.h

@@ -42,6 +42,58 @@ class ExternalPreprocessorSource {
   virtual Module *getModule(unsigned ModuleID) = 0;
 };
 
+// Either a pointer to an IdentifierInfo of the controlling macro or the ID
+// number of the controlling macro.
+class LazyIdentifierInfoPtr {
+  // If the low bit is clear, a pointer to the IdentifierInfo. If the low
+  // bit is set, the upper 63 bits are the ID number.
+  mutable uint64_t Ptr = 0;
+
+public:
+  LazyIdentifierInfoPtr() = default;
+
+  explicit LazyIdentifierInfoPtr(const IdentifierInfo *Ptr)
+      : Ptr(reinterpret_cast<uint64_t>(Ptr)) {}
+
+  explicit LazyIdentifierInfoPtr(uint64_t ID) : Ptr((ID << 1) | 0x01) {
+    assert((ID << 1 >> 1) == ID && "ID must require < 63 bits");
+    if (ID == 0)
+      Ptr = 0;
+  }
+
+  LazyIdentifierInfoPtr &operator=(const IdentifierInfo *Ptr) {
+    this->Ptr = reinterpret_cast<uint64_t>(Ptr);
+    return *this;
+  }
+
+  LazyIdentifierInfoPtr &operator=(uint64_t ID) {
+    assert((ID << 1 >> 1) == ID && "IDs must require < 63 bits");
+    if (ID == 0)
+      Ptr = 0;
+    else
+      Ptr = (ID << 1) | 0x01;
+
+    return *this;
+  }
+
+  /// Whether this pointer is non-NULL.
+  ///
+  /// This operation does not require the AST node to be deserialized.
+  bool isValid() const { return Ptr != 0; }
+
+  /// Whether this pointer is currently stored as ID.
+  bool isID() const { return Ptr & 0x01; }
+
+  IdentifierInfo *getPtr() const {
+    assert(!isID());
+    return reinterpret_cast<IdentifierInfo *>(Ptr);
+  }
+
+  uint64_t getID() const {
+    assert(isID());
+    return Ptr >> 1;
+  }
+};
 }
 
 #endif

clang/include/clang/Lex/HeaderSearch.h

@@ -16,6 +16,7 @@
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Lex/DirectoryLookup.h"
+#include "clang/Lex/ExternalPreprocessorSource.h"
 #include "clang/Lex/HeaderMap.h"
 #include "clang/Lex/ModuleMap.h"
 #include "llvm/ADT/ArrayRef.h"
@@ -121,13 +122,6 @@ struct HeaderFileInfo {
   LLVM_PREFERRED_TYPE(bool)
   unsigned IsValid : 1;
 
-  /// The ID number of the controlling macro.
-  ///
-  /// This ID number will be non-zero when there is a controlling
-  /// macro whose IdentifierInfo may not yet have been loaded from
-  /// external storage.
-  unsigned ControllingMacroID = 0;
-
   /// If this file has a \#ifndef XXX (or equivalent) guard that
   /// protects the entire contents of the file, this is the identifier
   /// for the macro that controls whether or not it has any effect.
@@ -136,7 +130,7 @@ struct HeaderFileInfo {
   /// the controlling macro of this header, since
   /// getControllingMacro() is able to load a controlling macro from
   /// external storage.
-  const IdentifierInfo *ControllingMacro = nullptr;
+  LazyIdentifierInfoPtr LazyControllingMacro;
 
   /// If this header came from a framework include, this is the name
   /// of the framework.
@@ -582,7 +576,7 @@ class HeaderSearch {
   /// no-op \#includes.
   void SetFileControllingMacro(FileEntryRef File,
                                const IdentifierInfo *ControllingMacro) {
-    getFileInfo(File).ControllingMacro = ControllingMacro;
+    getFileInfo(File).LazyControllingMacro = ControllingMacro;
   }
 
   /// Determine whether this file is intended to be safe from

clang/lib/Lex/HeaderSearch.cpp

@@ -60,19 +60,21 @@ ALWAYS_ENABLED_STATISTIC(NumSubFrameworkLookups,
 
 const IdentifierInfo *
 HeaderFileInfo::getControllingMacro(ExternalPreprocessorSource *External) {
-  if (ControllingMacro) {
-    if (ControllingMacro->isOutOfDate()) {
-      assert(External && "We must have an external source if we have a "
-                         "controlling macro that is out of date.");
-      External->updateOutOfDateIdentifier(*ControllingMacro);
-    }
-    return ControllingMacro;
-  }
+  if (LazyControllingMacro.isID()) {
+    if (!External)
+      return nullptr;
 
-  if (!ControllingMacroID || !External)
-    return nullptr;
+    LazyControllingMacro =
+        External->GetIdentifier(LazyControllingMacro.getID());
+    return LazyControllingMacro.getPtr();
+  }
 
-  ControllingMacro = External->GetIdentifier(ControllingMacroID);
+  IdentifierInfo *ControllingMacro = LazyControllingMacro.getPtr();
+  if (ControllingMacro && ControllingMacro->isOutOfDate()) {
+    assert(External && "We must have an external source if we have a "
+                       "controlling macro that is out of date.");
+    External->updateOutOfDateIdentifier(*ControllingMacro);
+  }
   return ControllingMacro;
 }
 
@@ -1348,10 +1350,8 @@ static void mergeHeaderFileInfo(HeaderFileInfo &HFI,
   mergeHeaderFileInfoModuleBits(HFI, OtherHFI.isModuleHeader,
                                 OtherHFI.isTextualModuleHeader);
 
-  if (!HFI.ControllingMacro && !HFI.ControllingMacroID) {
-    HFI.ControllingMacro = OtherHFI.ControllingMacro;
-    HFI.ControllingMacroID = OtherHFI.ControllingMacroID;
-  }
+  if (!HFI.LazyControllingMacro.isValid())
+    HFI.LazyControllingMacro = OtherHFI.LazyControllingMacro;
 
   HFI.DirInfo = OtherHFI.DirInfo;
   HFI.External = (!HFI.IsValid || HFI.External);
@@ -1426,8 +1426,7 @@ bool HeaderSearch::isFileMultipleIncludeGuarded(FileEntryRef File) const {
   // once. Note that we dor't check for #import, because that's not a property
   // of the file itself.
   if (auto *HFI = getExistingFileInfo(File))
-    return HFI->isPragmaOnce || HFI->ControllingMacro ||
-           HFI->ControllingMacroID;
+    return HFI->isPragmaOnce || HFI->LazyControllingMacro.isValid();
   return false;
 }
 

clang/lib/Serialization/ASTReader.cpp

@@ -2092,7 +2092,7 @@ HeaderFileInfoTrait::ReadData(internal_key_ref key, const unsigned char *d,
   HFI.isPragmaOnce |= (Flags >> 4) & 0x01;
   HFI.DirInfo = (Flags >> 1) & 0x07;
   HFI.IndexHeaderMapHeader = Flags & 0x01;
-  HFI.ControllingMacroID = Reader.getGlobalIdentifierID(
+  HFI.LazyControllingMacro = Reader.getGlobalIdentifierID(
       M, endian::readNext<uint32_t, llvm::endianness::little>(d));
   if (unsigned FrameworkOffset =
           endian::readNext<uint32_t, llvm::endianness::little>(d)) {

clang/lib/Serialization/ASTWriter.cpp

@@ -2028,10 +2028,11 @@ namespace {
                           | Data.HFI.IndexHeaderMapHeader;
       LE.write<uint8_t>(Flags);
 
-      if (!Data.HFI.ControllingMacro)
-        LE.write<uint32_t>(Data.HFI.ControllingMacroID);
+      if (Data.HFI.LazyControllingMacro.isID())
+        LE.write<IdentifierID>(Data.HFI.LazyControllingMacro.getID());
       else
-        LE.write<uint32_t>(Writer.getIdentifierRef(Data.HFI.ControllingMacro));
+        LE.write<IdentifierID>(
+            Writer.getIdentifierRef(Data.HFI.LazyControllingMacro.getPtr()));
 
       unsigned Offset = 0;
       if (!Data.HFI.Framework.empty()) {