[Bounds Safety][NFC] Add SemaBoundsSafety class and move existing Sema checks there

clang/include/clang/Sema/Sema.h

@@ -173,6 +173,7 @@ class QualType;
 class SemaAMDGPU;
 class SemaARM;
 class SemaAVR;
+class SemaBoundsSafety;
 class SemaBPF;
 class SemaCodeCompletion;
 class SemaCUDA;
@@ -1151,6 +1152,11 @@ class Sema final : public SemaBase {
     return *AVRPtr;
   }
 
+  SemaBoundsSafety &BoundsSafety() {
+    assert(BoundsSafetyPtr);
+    return *BoundsSafetyPtr;
+  }
+
   SemaBPF &BPF() {
     assert(BPFPtr);
     return *BPFPtr;
@@ -1294,6 +1300,7 @@ class Sema final : public SemaBase {
   std::unique_ptr<SemaAMDGPU> AMDGPUPtr;
   std::unique_ptr<SemaARM> ARMPtr;
   std::unique_ptr<SemaAVR> AVRPtr;
+  std::unique_ptr<SemaBoundsSafety> BoundsSafetyPtr;
   std::unique_ptr<SemaBPF> BPFPtr;
   std::unique_ptr<SemaCodeCompletion> CodeCompletionPtr;
   std::unique_ptr<SemaCUDA> CUDAPtr;

clang/include/clang/Sema/SemaBoundsSafety.h

@@ -0,0 +1,42 @@
+//===---- SemaBoundsSafety.h - Bounds Safety specific routines-*- C++ -*---===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This file declares semantic analysis functions specific to `-fbounds-safety`
+/// (Bounds Safety) and also its attributes when used without `-fbounds-safety`
+/// (e.g. `counted_by`)
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_SEMA_SEMABOUNDSSAFETY_H
+#define LLVM_CLANG_SEMA_SEMABOUNDSSAFETY_H
+
+#include "clang/Sema/SemaBase.h"
+#include "llvm/ADT/SmallVector.h"
+
+namespace clang {
+class CountAttributedType;
+class Decl;
+class Expr;
+class FieldDecl;
+class NamedDecl;
+class ParsedAttr;
+class TypeCoupledDeclRefInfo;
+
+class SemaBoundsSafety : public SemaBase {
+public:
+  SemaBoundsSafety(Sema &S);
+
+  bool CheckCountedByAttrOnField(
+      FieldDecl *FD, Expr *E,
+      llvm::SmallVectorImpl<TypeCoupledDeclRefInfo> &Decls, bool CountInBytes,
+      bool OrNull);
+};
+
+} // namespace clang
+
+#endif //  LLVM_CLANG_SEMA_SEMABOUNDSSAFETY_H

clang/lib/Sema/CMakeLists.txt

@@ -36,6 +36,7 @@ add_clang_library(clangSema
   SemaAvailability.cpp
   SemaBPF.cpp
   SemaBase.cpp
+  SemaBoundsSafety.cpp
   SemaCXXScopeSpec.cpp
   SemaCast.cpp
   SemaChecking.cpp

clang/lib/Sema/Sema.cpp

@@ -45,6 +45,7 @@
 #include "clang/Sema/SemaARM.h"
 #include "clang/Sema/SemaAVR.h"
 #include "clang/Sema/SemaBPF.h"
+#include "clang/Sema/SemaBoundsSafety.h"
 #include "clang/Sema/SemaCUDA.h"
 #include "clang/Sema/SemaCodeCompletion.h"
 #include "clang/Sema/SemaConsumer.h"
@@ -224,6 +225,7 @@ Sema::Sema(Preprocessor &pp, ASTContext &ctxt, ASTConsumer &consumer,
       AMDGPUPtr(std::make_unique<SemaAMDGPU>(*this)),
       ARMPtr(std::make_unique<SemaARM>(*this)),
       AVRPtr(std::make_unique<SemaAVR>(*this)),
+      BoundsSafetyPtr(std::make_unique<SemaBoundsSafety>(*this)),
       BPFPtr(std::make_unique<SemaBPF>(*this)),
       CodeCompletionPtr(
           std::make_unique<SemaCodeCompletion>(*this, CodeCompleter)),

clang/lib/Sema/SemaBoundsSafety.cpp

@@ -0,0 +1,198 @@
+//===---- SemaBoundsSafety.h - Bounds Safety specific routines-*- C++ -*---===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This file declares semantic analysis functions specific to `-fbounds-safety`
+/// (Bounds Safety) and also its attributes when used without `-fbounds-safety`
+/// (e.g. `counted_by`)
+///
+//===----------------------------------------------------------------------===//
+
+#include "clang/Sema/SemaBoundsSafety.h"
+#include "clang/Basic/DiagnosticSema.h"
+#include "clang/Lex/Lexer.h"
+#include "clang/Sema/Sema.h"
+
+namespace clang {
+SemaBoundsSafety::SemaBoundsSafety(Sema &S) : SemaBase(S) {}
+
+static CountAttributedType::DynamicCountPointerKind
+getCountAttrKind(bool CountInBytes, bool OrNull) {
+  if (CountInBytes)
+    return OrNull ? CountAttributedType::SizedByOrNull
+                  : CountAttributedType::SizedBy;
+  return OrNull ? CountAttributedType::CountedByOrNull
+                : CountAttributedType::CountedBy;
+}
+
+static const RecordDecl *GetEnclosingNamedOrTopAnonRecord(const FieldDecl *FD) {
+  const auto *RD = FD->getParent();
+  // An unnamed struct is anonymous struct only if it's not instantiated.
+  // However, the struct may not be fully processed yet to determine
+  // whether it's anonymous or not. In that case, this function treats it as
+  // an anonymous struct and tries to find a named parent.
+  while (RD && (RD->isAnonymousStructOrUnion() ||
+                (!RD->isCompleteDefinition() && RD->getName().empty()))) {
+    const auto *Parent = dyn_cast<RecordDecl>(RD->getParent());
+    if (!Parent)
+      break;
+    RD = Parent;
+  }
+  return RD;
+}
+
+enum class CountedByInvalidPointeeTypeKind {
+  INCOMPLETE,
+  SIZELESS,
+  FUNCTION,
+  FLEXIBLE_ARRAY_MEMBER,
+  VALID,
+};
+
+bool SemaBoundsSafety::CheckCountedByAttrOnField(
+    FieldDecl *FD, Expr *E,
+    llvm::SmallVectorImpl<TypeCoupledDeclRefInfo> &Decls, bool CountInBytes,
+    bool OrNull) {
+  // Check the context the attribute is used in
+
+  unsigned Kind = getCountAttrKind(CountInBytes, OrNull);
+
+  if (FD->getParent()->isUnion()) {
+    Diag(FD->getBeginLoc(), diag::err_count_attr_in_union)
+        << Kind << FD->getSourceRange();
+    return true;
+  }
+
+  const auto FieldTy = FD->getType();
+  if (FieldTy->isArrayType() && (CountInBytes || OrNull)) {
+    Diag(FD->getBeginLoc(),
+         diag::err_count_attr_not_on_ptr_or_flexible_array_member)
+        << Kind << FD->getLocation() << /* suggest counted_by */ 1;
+    return true;
+  }
+  if (!FieldTy->isArrayType() && !FieldTy->isPointerType()) {
+    Diag(FD->getBeginLoc(),
+         diag::err_count_attr_not_on_ptr_or_flexible_array_member)
+        << Kind << FD->getLocation() << /* do not suggest counted_by */ 0;
+    return true;
+  }
+
+  LangOptions::StrictFlexArraysLevelKind StrictFlexArraysLevel =
+      LangOptions::StrictFlexArraysLevelKind::IncompleteOnly;
+  if (FieldTy->isArrayType() &&
+      !Decl::isFlexibleArrayMemberLike(getASTContext(), FD, FieldTy,
+                                       StrictFlexArraysLevel, true)) {
+    Diag(FD->getBeginLoc(),
+         diag::err_counted_by_attr_on_array_not_flexible_array_member)
+        << Kind << FD->getLocation();
+    return true;
+  }
+
+  CountedByInvalidPointeeTypeKind InvalidTypeKind =
+      CountedByInvalidPointeeTypeKind::VALID;
+  QualType PointeeTy;
+  int SelectPtrOrArr = 0;
+  if (FieldTy->isPointerType()) {
+    PointeeTy = FieldTy->getPointeeType();
+    SelectPtrOrArr = 0;
+  } else {
+    assert(FieldTy->isArrayType());
+    const ArrayType *AT = getASTContext().getAsArrayType(FieldTy);
+    PointeeTy = AT->getElementType();
+    SelectPtrOrArr = 1;
+  }
+  // Note: The `Decl::isFlexibleArrayMemberLike` check earlier on means
+  // only `PointeeTy->isStructureTypeWithFlexibleArrayMember()` is reachable
+  // when `FieldTy->isArrayType()`.
+  bool ShouldWarn = false;
+  if (PointeeTy->isIncompleteType() && !CountInBytes) {
+    InvalidTypeKind = CountedByInvalidPointeeTypeKind::INCOMPLETE;
+  } else if (PointeeTy->isSizelessType()) {
+    InvalidTypeKind = CountedByInvalidPointeeTypeKind::SIZELESS;
+  } else if (PointeeTy->isFunctionType()) {
+    InvalidTypeKind = CountedByInvalidPointeeTypeKind::FUNCTION;
+  } else if (PointeeTy->isStructureTypeWithFlexibleArrayMember()) {
+    if (FieldTy->isArrayType()) {
+      // This is a workaround for the Linux kernel that has already adopted
+      // `counted_by` on a FAM where the pointee is a struct with a FAM. This
+      // should be an error because computing the bounds of the array cannot be
+      // done correctly without manually traversing every struct object in the
+      // array at runtime. To allow the code to be built this error is
+      // downgraded to a warning.
+      ShouldWarn = true;
+    }
+    InvalidTypeKind = CountedByInvalidPointeeTypeKind::FLEXIBLE_ARRAY_MEMBER;
+  }
+
+  if (InvalidTypeKind != CountedByInvalidPointeeTypeKind::VALID) {
+    unsigned DiagID = ShouldWarn
+                          ? diag::warn_counted_by_attr_elt_type_unknown_size
+                          : diag::err_counted_by_attr_pointee_unknown_size;
+    Diag(FD->getBeginLoc(), DiagID)
+        << SelectPtrOrArr << PointeeTy << (int)InvalidTypeKind
+        << (ShouldWarn ? 1 : 0) << Kind << FD->getSourceRange();
+    return true;
+  }
+
+  // Check the expression
+
+  if (!E->getType()->isIntegerType() || E->getType()->isBooleanType()) {
+    Diag(E->getBeginLoc(), diag::err_count_attr_argument_not_integer)
+        << Kind << E->getSourceRange();
+    return true;
+  }
+
+  auto *DRE = dyn_cast<DeclRefExpr>(E);
+  if (!DRE) {
+    Diag(E->getBeginLoc(),
+         diag::err_count_attr_only_support_simple_decl_reference)
+        << Kind << E->getSourceRange();
+    return true;
+  }
+
+  auto *CountDecl = DRE->getDecl();
+  FieldDecl *CountFD = dyn_cast<FieldDecl>(CountDecl);
+  if (auto *IFD = dyn_cast<IndirectFieldDecl>(CountDecl)) {
+    CountFD = IFD->getAnonField();
+  }
+  if (!CountFD) {
+    Diag(E->getBeginLoc(), diag::err_count_attr_must_be_in_structure)
+        << CountDecl << Kind << E->getSourceRange();
+
+    Diag(CountDecl->getBeginLoc(),
+         diag::note_flexible_array_counted_by_attr_field)
+        << CountDecl << CountDecl->getSourceRange();
+    return true;
+  }
+
+  if (FD->getParent() != CountFD->getParent()) {
+    if (CountFD->getParent()->isUnion()) {
+      Diag(CountFD->getBeginLoc(), diag::err_count_attr_refer_to_union)
+          << Kind << CountFD->getSourceRange();
+      return true;
+    }
+    // Whether CountRD is an anonymous struct is not determined at this
+    // point. Thus, an additional diagnostic in case it's not anonymous struct
+    // is done later in `Parser::ParseStructDeclaration`.
+    auto *RD = GetEnclosingNamedOrTopAnonRecord(FD);
+    auto *CountRD = GetEnclosingNamedOrTopAnonRecord(CountFD);
+
+    if (RD != CountRD) {
+      Diag(E->getBeginLoc(), diag::err_count_attr_param_not_in_same_struct)
+          << CountFD << Kind << FieldTy->isArrayType() << E->getSourceRange();
+      Diag(CountFD->getBeginLoc(),
+           diag::note_flexible_array_counted_by_attr_field)
+          << CountFD << CountFD->getSourceRange();
+      return true;
+    }
+  }
+
+  Decls.push_back(TypeCoupledDeclRefInfo(CountFD, /*IsDref*/ false));
+  return false;
+}
+
+} // namespace clang