[analyzer] Add dangling internal buffer check.

This check will mark raw pointers to C++ standard library container internal
buffers 'released' when the objects themselves are destroyed. Such information
can be used by MallocChecker to warn about use-after-free problems.

In this first version, 'std::basic_string's are supported.

Differential Revision: https://reviews.llvm.org/D47135

llvm-svn: 334348
diff --git a/clang/lib/StaticAnalyzer/Checkers/AllocationState.h b/clang/lib/StaticAnalyzer/Checkers/AllocationState.h
new file mode 100644
index 0000000..f87c093
--- /dev/null
+++ b/clang/lib/StaticAnalyzer/Checkers/AllocationState.h
@@ -0,0 +1,28 @@
+//===--- AllocationState.h ------------------------------------- *- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_STATICANALYZER_CHECKERS_ALLOCATIONSTATE_H
+#define LLVM_CLANG_LIB_STATICANALYZER_CHECKERS_ALLOCATIONSTATE_H
+
+#include "clang/StaticAnalyzer/Core/PathSensitive/ProgramState.h"
+
+namespace clang {
+namespace ento {
+
+namespace allocation_state {
+
+ProgramStateRef markReleased(ProgramStateRef State, SymbolRef Sym,
+                             const Expr *Origin);
+
+} // end namespace allocation_state
+
+} // end namespace ento
+} // end namespace clang
+
+#endif
diff --git a/clang/lib/StaticAnalyzer/Checkers/CMakeLists.txt b/clang/lib/StaticAnalyzer/Checkers/CMakeLists.txt
index c1c1b99..c615ad8 100644
--- a/clang/lib/StaticAnalyzer/Checkers/CMakeLists.txt
+++ b/clang/lib/StaticAnalyzer/Checkers/CMakeLists.txt
@@ -27,6 +27,7 @@
   CloneChecker.cpp
   ConversionChecker.cpp
   CXXSelfAssignmentChecker.cpp
+  DanglingInternalBufferChecker.cpp
   DeadStoresChecker.cpp
   DebugCheckers.cpp
   DeleteWithNonVirtualDtorChecker.cpp
diff --git a/clang/lib/StaticAnalyzer/Checkers/DanglingInternalBufferChecker.cpp b/clang/lib/StaticAnalyzer/Checkers/DanglingInternalBufferChecker.cpp
new file mode 100644
index 0000000..e7884ee
--- /dev/null
+++ b/clang/lib/StaticAnalyzer/Checkers/DanglingInternalBufferChecker.cpp
@@ -0,0 +1,88 @@
+//=== DanglingInternalBufferChecker.cpp ---------------------------*- C++ -*--//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines a check that marks a raw pointer to a C++ standard library
+// container's inner buffer released when the object is destroyed. This
+// information can be used by MallocChecker to detect use-after-free problems.
+//
+//===----------------------------------------------------------------------===//
+
+#include "ClangSACheckers.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/PathSensitive/CallEvent.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
+#include "AllocationState.h"
+
+using namespace clang;
+using namespace ento;
+
+namespace {
+
+class DanglingInternalBufferChecker : public Checker<check::PostCall> {
+  CallDescription CStrFn;
+
+public:
+  DanglingInternalBufferChecker() : CStrFn("c_str") {}
+
+  /// Record the connection between the symbol returned by c_str() and the
+  /// corresponding string object region in the ProgramState. Mark the symbol
+  /// released if the string object is destroyed.
+  void checkPostCall(const CallEvent &Call, CheckerContext &C) const;
+};
+
+} // end anonymous namespace
+
+// FIXME: c_str() may be called on a string object many times, so it should
+// have a list of symbols associated with it.
+REGISTER_MAP_WITH_PROGRAMSTATE(RawPtrMap, const MemRegion *, SymbolRef)
+
+void DanglingInternalBufferChecker::checkPostCall(const CallEvent &Call,
+                                                  CheckerContext &C) const {
+  const auto *ICall = dyn_cast<CXXInstanceCall>(&Call);
+  if (!ICall)
+    return;
+
+  SVal Obj = ICall->getCXXThisVal();
+  const auto *TypedR = dyn_cast_or_null<TypedValueRegion>(Obj.getAsRegion());
+  if (!TypedR)
+    return;
+
+  auto *TypeDecl = TypedR->getValueType()->getAsCXXRecordDecl();
+  if (TypeDecl->getName() != "basic_string")
+    return;
+
+  ProgramStateRef State = C.getState();
+
+  if (Call.isCalled(CStrFn)) {
+    SVal RawPtr = Call.getReturnValue();
+    if (!RawPtr.isUnknown()) {
+      State = State->set<RawPtrMap>(TypedR, RawPtr.getAsSymbol());
+      C.addTransition(State);
+    }
+    return;
+  }
+
+  if (isa<CXXDestructorCall>(ICall)) {
+    if (State->contains<RawPtrMap>(TypedR)) {
+      const SymbolRef *StrBufferPtr = State->get<RawPtrMap>(TypedR);
+      // FIXME: What if Origin is null?
+      const Expr *Origin = Call.getOriginExpr();
+      State = allocation_state::markReleased(State, *StrBufferPtr, Origin);
+      C.addTransition(State);
+      return;
+    }
+  }
+}
+
+void ento::registerDanglingInternalBufferChecker(CheckerManager &Mgr) {
+  registerNewDeleteChecker(Mgr);
+  Mgr.registerChecker<DanglingInternalBufferChecker>();
+}
diff --git a/clang/lib/StaticAnalyzer/Checkers/MallocChecker.cpp b/clang/lib/StaticAnalyzer/Checkers/MallocChecker.cpp
index 341fdd2..2ab817a 100644
--- a/clang/lib/StaticAnalyzer/Checkers/MallocChecker.cpp
+++ b/clang/lib/StaticAnalyzer/Checkers/MallocChecker.cpp
@@ -30,6 +30,7 @@
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringExtras.h"
+#include "AllocationState.h"
 #include <climits>
 #include <utility>
 
@@ -45,7 +46,8 @@
   AF_CXXNew,
   AF_CXXNewArray,
   AF_IfNameIndex,
-  AF_Alloca
+  AF_Alloca,
+  AF_InternalBuffer
 };
 
 class RefState {
@@ -1467,6 +1469,7 @@
     case AF_CXXNew: os << "'new'"; return;
     case AF_CXXNewArray: os << "'new[]'"; return;
     case AF_IfNameIndex: os << "'if_nameindex()'"; return;
+    case AF_InternalBuffer: os << "container-specific allocator"; return;
     case AF_Alloca:
     case AF_None: llvm_unreachable("not a deallocation expression");
   }
@@ -1479,6 +1482,7 @@
     case AF_CXXNew: os << "'delete'"; return;
     case AF_CXXNewArray: os << "'delete[]'"; return;
     case AF_IfNameIndex: os << "'if_freenameindex()'"; return;
+    case AF_InternalBuffer: os << "container-specific deallocator"; return;
     case AF_Alloca:
     case AF_None: llvm_unreachable("suspicious argument");
   }
@@ -1653,7 +1657,9 @@
     return Optional<MallocChecker::CheckKind>();
   }
   case AF_CXXNew:
-  case AF_CXXNewArray: {
+  case AF_CXXNewArray:
+  // FIXME: Add new CheckKind for AF_InternalBuffer.
+  case AF_InternalBuffer: {
     if (IsALeakCheck) {
       if (ChecksEnabled[CK_NewDeleteLeaksChecker])
         return CK_NewDeleteLeaksChecker;
@@ -2991,6 +2997,20 @@
   }
 }
 
+namespace clang {
+namespace ento {
+namespace allocation_state {
+
+ProgramStateRef
+markReleased(ProgramStateRef State, SymbolRef Sym, const Expr *Origin) {
+  AllocationFamily Family = AF_InternalBuffer;
+  return State->set<RegionState>(Sym, RefState::getReleased(Family, Origin));
+}
+
+} // end namespace allocation_state
+} // end namespace ento
+} // end namespace clang
+
 void ento::registerNewDeleteLeaksChecker(CheckerManager &mgr) {
   registerCStringCheckerBasic(mgr);
   MallocChecker *checker = mgr.registerChecker<MallocChecker>();