Add Clang attribute to ensure that fields are initialized explicitly

higher-performance · higher-performance · commit dc565488caf2 · 2024-09-04T14:18:27.000-04:00
diff --git a/clang/include/clang/AST/CXXRecordDeclDefinitionBits.def b/clang/include/clang/AST/CXXRecordDeclDefinitionBits.def
@@ -119,6 +119,14 @@ FIELD(HasInitMethod, 1, NO_MERGE)
 /// within anonymous unions or structs.
 FIELD(HasInClassInitializer, 1, NO_MERGE)
 
+/// Custom attribute that is True if any field is marked as explicit in a type
+/// without a user-provided default constructor, or if this is the case for any
+/// base classes and/or member variables whose types are aggregates.
+///
+/// In this case, default-construction is diagnosed, as it would not explicitly
+/// initialize the field.
+FIELD(HasUninitializedExplicitInitFields, 1, NO_MERGE)
+
 /// True if any field is of reference type, and does not have an
 /// in-class initializer.
 ///
diff --git a/clang/include/clang/AST/DeclCXX.h b/clang/include/clang/AST/DeclCXX.h
@@ -1152,6 +1152,11 @@ class CXXRecordDecl : public RecordDecl {
   /// structs).
   bool hasInClassInitializer() const { return data().HasInClassInitializer; }
 
+  bool hasUninitializedExplicitInitFields() const {
+    return !isUnion() && !hasUserProvidedDefaultConstructor() &&
+           data().HasUninitializedExplicitInitFields;
+  }
+
   /// Whether this class or any of its subobjects has any members of
   /// reference type which would make value-initialization ill-formed.
   ///
diff --git a/clang/include/clang/Basic/Attr.td b/clang/include/clang/Basic/Attr.td
@@ -1823,6 +1823,14 @@ def Leaf : InheritableAttr {
   let SimpleHandler = 1;
 }
 
+def ExplicitInit : InheritableAttr {
+  let Spellings = [Clang<"requires_explicit_initialization", 0>];
+  let Subjects = SubjectList<[Field], ErrorDiag>;
+  let Documentation = [ExplicitInitDocs];
+  let LangOpts = [CPlusPlus];
+  let SimpleHandler = 1;
+}
+
 def LifetimeBound : DeclOrTypeAttr {
   let Spellings = [Clang<"lifetimebound", 0>];
   let Subjects = SubjectList<[ParmVar, ImplicitObjectParameter], ErrorDiag>;
diff --git a/clang/include/clang/Basic/AttrDocs.td b/clang/include/clang/Basic/AttrDocs.td
@@ -1419,6 +1419,35 @@ is not specified.
   }];
 }
 
+def ExplicitInitDocs : Documentation {
+  let Category = DocCatField;
+  let Content = [{
+The ``clang::requires_explicit_initialization`` attribute indicates that the
+field of an aggregate must be initialized explicitly by users when the class
+is constructed. Its usage is invalid on non-aggregates.
+
+Example usage:
+
+.. code-block:: c++
+
+  struct some_aggregate {
+    int x;
+    int y [[clang::requires_explicit_initialization]];
+  };
+
+  some_aggregate create() {
+    return {.x = 1};  // error: y is not initialized explicitly
+  }
+
+This attribute is *not* a memory safety feature, and is *not* intended to guard
+against use of uninitialized memory.
+Rather, its intended use is in structs that represent "parameter objects", to
+allow extending them while ensuring that callers do not forget to specify
+values for newly added fields ("parameters").
+
+  }];
+}
+
 def NoUniqueAddressDocs : Documentation {
   let Category = DocCatField;
   let Content = [{
diff --git a/clang/include/clang/Basic/DiagnosticGroups.td b/clang/include/clang/Basic/DiagnosticGroups.td
@@ -787,6 +787,7 @@ def Trigraphs      : DiagGroup<"trigraphs">;
 def UndefinedReinterpretCast : DiagGroup<"undefined-reinterpret-cast">;
 def ReinterpretBaseClass : DiagGroup<"reinterpret-base-class">;
 def Unicode  : DiagGroup<"unicode">;
+def UninitializedExplicitInit : DiagGroup<"uninitialized-explicit-init">;
 def UninitializedMaybe : DiagGroup<"conditional-uninitialized">;
 def UninitializedSometimes : DiagGroup<"sometimes-uninitialized">;
 def UninitializedStaticSelfInit : DiagGroup<"static-self-init">;
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -2332,6 +2332,9 @@ def err_init_reference_member_uninitialized : Error<
   "reference member of type %0 uninitialized">;
 def note_uninit_reference_member : Note<
   "uninitialized reference member is here">;
+def warn_field_requires_explicit_init : Warning<
+  "field %0 is not explicitly initialized, but was marked as requiring "
+  "explicit initialization">, InGroup<UninitializedExplicitInit>;
 def warn_field_is_uninit : Warning<"field %0 is uninitialized when used here">,
   InGroup<Uninitialized>;
 def warn_base_class_is_uninit : Warning<
diff --git a/clang/lib/AST/DeclCXX.cpp b/clang/lib/AST/DeclCXX.cpp
@@ -81,6 +81,7 @@ CXXRecordDecl::DefinitionData::DefinitionData(CXXRecordDecl *D)
       HasPrivateFields(false), HasProtectedFields(false),
       HasPublicFields(false), HasMutableFields(false), HasVariantMembers(false),
       HasOnlyCMembers(true), HasInitMethod(false), HasInClassInitializer(false),
+      HasUninitializedExplicitInitFields(false),
       HasUninitializedReferenceMember(false), HasUninitializedFields(false),
       HasInheritedConstructor(false), HasInheritedDefaultConstructor(false),
       HasInheritedAssignment(false),
@@ -1108,6 +1109,10 @@ void CXXRecordDecl::addedMember(Decl *D) {
     } else if (!T.isCXX98PODType(Context))
       data().PlainOldData = false;
 
+    if (Field->hasAttr<ExplicitInitAttr>() && !Field->hasInClassInitializer()) {
+      data().HasUninitializedExplicitInitFields = true;
+    }
+
     if (T->isReferenceType()) {
       if (!Field->hasInClassInitializer())
         data().HasUninitializedReferenceMember = true;
@@ -1359,6 +1364,10 @@ void CXXRecordDecl::addedMember(Decl *D) {
         if (!FieldRec->hasCopyAssignmentWithConstParam())
           data().ImplicitCopyAssignmentHasConstParam = false;
 
+        if (FieldRec->hasUninitializedExplicitInitFields() &&
+            FieldRec->isAggregate() && !Field->hasInClassInitializer())
+          data().HasUninitializedExplicitInitFields = true;
+
         if (FieldRec->hasUninitializedReferenceMember() &&
             !Field->hasInClassInitializer())
           data().HasUninitializedReferenceMember = true;
@@ -2133,6 +2142,18 @@ void CXXRecordDecl::completeDefinition(CXXFinalOverriderMap *FinalOverriders) {
   for (conversion_iterator I = conversion_begin(), E = conversion_end();
        I != E; ++I)
     I.setAccess((*I)->getAccess());
+
+  ASTContext &Context = getASTContext();
+  if (!Context.getLangOpts().CPlusPlus20 && hasUserDeclaredConstructor()) {
+    // Diagnose any aggregate behavior changes in C++20
+    for (field_iterator I = field_begin(), E = field_end(); I != E; ++I) {
+      if (const auto *attr = I->getAttr<ExplicitAttr>()) {
+        Context.getDiagnostics().Report(
+            getLocation(), diag::warn_cxx20_compat_aggregate_init_with_ctors)
+            << attr->getRange() << Context.getRecordType(this);
+      }
+    }
+  }
 }
 
 bool CXXRecordDecl::mayBeAbstract() const {
diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
@@ -5942,6 +5942,10 @@ static void handleNoMergeAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
   D->addAttr(NoMergeAttr::Create(S.Context, AL));
 }
 
+static void handleExplicitInitAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
+  D->addAttr(ExplicitInitAttr::Create(S.Context, AL));
+}
+
 static void handleNoUniqueAddressAttr(Sema &S, Decl *D, const ParsedAttr &AL) {
   D->addAttr(NoUniqueAddressAttr::Create(S.Context, AL));
 }
@@ -6847,6 +6851,9 @@ ProcessDeclAttribute(Sema &S, Scope *scope, Decl *D, const ParsedAttr &AL,
   case ParsedAttr::AT_NoMerge:
     handleNoMergeAttr(S, D, AL);
     break;
+  case ParsedAttr::AT_ExplicitInit:
+    handleExplicitInitAttr(S, D, AL);
+    break;
   case ParsedAttr::AT_NoUniqueAddress:
     handleNoUniqueAddressAttr(S, D, AL);
     break;
diff --git a/clang/lib/Sema/SemaInit.cpp b/clang/lib/Sema/SemaInit.cpp
@@ -743,6 +743,12 @@ void InitListChecker::FillInEmptyInitForField(unsigned Init, FieldDecl *Field,
         ILE->updateInit(SemaRef.Context, Init, Filler);
       return;
     }
+
+    if (Field->hasAttr<ExplicitInitAttr>()) {
+      SemaRef.Diag(ILE->getExprLoc(), diag::warn_field_requires_explicit_init)
+          << Field;
+    }
+
     // C++1y [dcl.init.aggr]p7:
     //   If there are fewer initializer-clauses in the list than there are
     //   members in the aggregate, then each member not explicitly initialized
@@ -4548,6 +4554,13 @@ static void TryConstructorInitialization(Sema &S,
 
   CXXConstructorDecl *CtorDecl = cast<CXXConstructorDecl>(Best->Function);
   if (Result != OR_Deleted) {
+    if (!IsListInit && Kind.getKind() == InitializationKind::IK_Default &&
+        DestRecordDecl != nullptr && DestRecordDecl->isAggregate() &&
+        DestRecordDecl->hasUninitializedExplicitInitFields()) {
+      S.Diag(Kind.getLocation(), diag::warn_field_requires_explicit_init)
+          << "in class";
+    }
+
     // C++11 [dcl.init]p6:
     //   If a program calls for the default initialization of an object
     //   of a const-qualified type T, T shall be a class type with a
diff --git a/clang/test/Misc/pragma-attribute-supported-attributes-list.test b/clang/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -76,6 +76,7 @@
 // CHECK-NEXT: EnumExtensibility (SubjectMatchRule_enum)
 // CHECK-NEXT: Error (SubjectMatchRule_function)
 // CHECK-NEXT: ExcludeFromExplicitInstantiation (SubjectMatchRule_variable, SubjectMatchRule_function, SubjectMatchRule_record)
+// CHECK-NEXT: ExplicitInit (SubjectMatchRule_field)
 // CHECK-NEXT: ExternalSourceSymbol ((SubjectMatchRule_record, SubjectMatchRule_enum, SubjectMatchRule_enum_constant, SubjectMatchRule_field, SubjectMatchRule_function, SubjectMatchRule_namespace, SubjectMatchRule_objc_category, SubjectMatchRule_objc_implementation, SubjectMatchRule_objc_interface, SubjectMatchRule_objc_method, SubjectMatchRule_objc_property, SubjectMatchRule_objc_protocol, SubjectMatchRule_record, SubjectMatchRule_type_alias, SubjectMatchRule_variable))
 // CHECK-NEXT: FlagEnum (SubjectMatchRule_enum)
 // CHECK-NEXT: Flatten (SubjectMatchRule_function)
diff --git a/clang/test/SemaCXX/uninitialized.cpp b/clang/test/SemaCXX/uninitialized.cpp
@@ -1472,3 +1472,25 @@ template<typename T> struct Outer {
   };
 };
 Outer<int>::Inner outerinner;
+
+void aggregate() {
+  struct B {
+    [[clang::requires_explicit_initialization]] int f1;
+  };
+
+  struct S : B { // expected-warning {{uninitialized}}
+    int f2;
+    int f3 [[clang::requires_explicit_initialization]];
+  };
+
+#if __cplusplus >= 202002L
+  S a({}, 0);  // expected-warning {{'f1' is not explicitly initialized}} expected-warning {{'f3' is not explicitly initialized}}
+#endif
+  S b{.f3 = 1}; // expected-warning {{'f1' is not explicitly initialized}}
+  S c{.f2 = 5}; // expected-warning {{'f1' is not explicitly initialized}} expected-warning {{'f3' is not explicitly initialized}} expected-warning {{'f3' is not explicitly initialized}}
+  c = {{}, 0};  // expected-warning {{'f1' is not explicitly initialized}} expected-warning {{'f3' is not explicitly initialized}}
+  S d; // expected-warning {{not explicitly initialized}} expected-note {{constructor}}
+  (void)b;
+  (void)c;
+  (void)d;
+}
