[clang] [clang][analyzer]Add C++ polymorphic ptr arithmetic checker (PR #82977)

[via cfe-commits]

================
@@ -0,0 +1,178 @@
+//=== PolymorphicPtrArithmetic.cpp ------------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This checker reports pointer arithmetic operations on arrays of
+// polymorphic objects, where the array has the type of its base class.
+// Corresponds to the CTR56-CPP. Do not use pointer arithmetic on
+// polymorphic objects
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/StaticAnalyzer/Checkers/BuiltinCheckerRegistration.h"
+#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
+#include "clang/StaticAnalyzer/Core/BugReporter/BugType.h"
+#include "clang/StaticAnalyzer/Core/BugReporter/CommonBugCategories.h"
+#include "clang/StaticAnalyzer/Core/Checker.h"
+#include "clang/StaticAnalyzer/Core/CheckerManager.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/CallEvent.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/DynamicType.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/ProgramStateTrait.h"
+
+using namespace clang;
+using namespace ento;
+
+namespace {
+class PolymorphicPtrArithmeticChecker
+    : public Checker<check::PreStmt<BinaryOperator>,
+                     check::PreStmt<ArraySubscriptExpr>> {
+  const BugType BT{this,
+                   "Pointer arithmetic on polymorphic objects is undefined"};
+
+protected:
+  class PtrCastVisitor : public BugReporterVisitor {
+  public:
+    void Profile(llvm::FoldingSetNodeID &ID) const override {
+      static int X = 0;
+      ID.AddPointer(&X);
+    }
+    PathDiagnosticPieceRef VisitNode(const ExplodedNode *N,
+                                     BugReporterContext &BRC,
+                                     PathSensitiveBugReport &BR) override;
+  };
+
+  void checkTypedExpr(const Expr *E, CheckerContext &C) const;
+
+public:
+  void checkPreStmt(const BinaryOperator *B, CheckerContext &C) const;
+  void checkPreStmt(const ArraySubscriptExpr *B, CheckerContext &C) const;
+};
+} // namespace
+
+void PolymorphicPtrArithmeticChecker::checkPreStmt(const BinaryOperator *B,
+                                                   CheckerContext &C) const {
+  if (!B->isAdditiveOp())
+    return;
+
+  bool IsLHSPtr = B->getLHS()->getType()->isAnyPointerType();
+  bool IsRHSPtr = B->getRHS()->getType()->isAnyPointerType();
+  if (!IsLHSPtr && !IsRHSPtr)
+    return;
+
+  const Expr *E = IsLHSPtr ? B->getLHS() : B->getRHS();
+
+  checkTypedExpr(E, C);
+}
+
+void PolymorphicPtrArithmeticChecker::checkPreStmt(const ArraySubscriptExpr *B,
+                                                   CheckerContext &C) const {
+  bool IsLHSPtr = B->getLHS()->getType()->isAnyPointerType();
+  bool IsRHSPtr = B->getRHS()->getType()->isAnyPointerType();
+  if (!IsLHSPtr && !IsRHSPtr)
+    return;
+
+  const Expr *E = IsLHSPtr ? B->getLHS() : B->getRHS();
+
+  checkTypedExpr(E, C);
+}
+
+void PolymorphicPtrArithmeticChecker::checkTypedExpr(const Expr *E,
+                                                     CheckerContext &C) const {
+  const MemRegion *MR = C.getSVal(E).getAsRegion();
+  if (!MR)
+    return;
+
+  const auto *BaseClassRegion = MR->getAs<TypedValueRegion>();
+  const auto *DerivedClassRegion = MR->getBaseRegion()->getAs<SymbolicRegion>();
+  if (!BaseClassRegion || !DerivedClassRegion)
+    return;
+
+  const auto *BaseClass = BaseClassRegion->getValueType()->getAsCXXRecordDecl();
+  const auto *DerivedClass =
+      DerivedClassRegion->getSymbol()->getType()->getPointeeCXXRecordDecl();
+  if (!BaseClass || !DerivedClass)
+    return;
+
+  if (!BaseClass->hasDefinition() || !DerivedClass->hasDefinition())
+    return;
+
+  if (!DerivedClass->isDerivedFrom(BaseClass))
+    return;
+
+  ExplodedNode *N = C.generateNonFatalErrorNode();
+  if (!N)
+    return;
+
+  SmallString<256> Buf;
+  llvm::raw_svector_ostream OS(Buf);
+
+  QualType SourceType = BaseClassRegion->getValueType();
+  QualType TargetType =
+      DerivedClassRegion->getSymbol()->getType()->getPointeeType();
+
+  OS << "Doing pointer arithmetic with '" << TargetType.getAsString()
+     << "' objects as their base class '"
+     << SourceType.getAsString(C.getASTContext().getPrintingPolicy())
----------------
NagyDonat wrote:

What's the reason for using the printing policy on just one of the two `getAsString()` calls?

https://github.com/llvm/llvm-project/pull/82977