[analyzer] Add support for std::basic_string::data() in DanglingInternalBufferChecker

[rnkovacs]

Summary

+ Cleaned up test file a bit.

[xazax.hun]

LG!

[xazax.hun]

test/Analysis/dangling-internal-buffer.cpp

10

Note that these methods are const according to the standard. Even if it does not make any difference for this check we should follow the signatures. Also, from c++17 there is a non-const overload of data.

[rnkovacs]

test/Analysis/dangling-internal-buffer.cpp

10

Oh, right, thanks. Fixed here and in D48522.

lib/StaticAnalyzer/Checkers/DanglingInternalBufferChecker.cpp

 #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"
 
 using namespace clang;
 using namespace ento;
 
-// FIXME: c_str() may be called on a string object many times, so it should
-// have a list of symbols associated with it.
+// FIXME: member functions that return a pointer to the container's internal
+// buffer may be called on the object many times, so the object's memory
+// region should have a list of pointer symbols associated with it.
 REGISTER_MAP_WITH_PROGRAMSTATE(RawPtrMap, const MemRegion *, SymbolRef)
 
 namespace {
 
 class DanglingInternalBufferChecker
     : public Checker<check::DeadSymbols, check::PostCall> {
-  CallDescription CStrFn;
+  CallDescription CStrFn, DataFn;
 
 public:
   class DanglingBufferBRVisitor
       : public BugReporterVisitorImpl<DanglingBufferBRVisitor> {
     SymbolRef PtrToBuf;
 
   public:
     DanglingBufferBRVisitor(SymbolRef Sym) : PtrToBuf(Sym) {}
bool isSymbolTracked(ProgramStateRef State, SymbolRef Sym) {
       for (const auto Entry : Map) {
         if (Entry.second == Sym)
           return true;
       }
       return false;
     }
   };
 
-  DanglingInternalBufferChecker() : CStrFn("c_str") {}
+  DanglingInternalBufferChecker() : CStrFn("c_str"), DataFn("data") {}
 
   /// 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;
 
   /// Clean up the ProgramState map.
   void checkDeadSymbols(SymbolReaper &SymReaper, CheckerContext &C) const;
if (!TypedR)
     return;
 
   auto *TypeDecl = TypedR->getValueType()->getAsCXXRecordDecl();
   if (TypeDecl->getName() != "basic_string")
     return;
 
   ProgramStateRef State = C.getState();
 
-  if (Call.isCalled(CStrFn)) {
+  if (Call.isCalled(CStrFn) || Call.isCalled(DataFn)) {
     SVal RawPtr = Call.getReturnValue();
     if (!RawPtr.isUnknown()) {
       State = State->set<RawPtrMap>(TypedR, RawPtr.getAsSymbol());
       C.addTransition(State);
     }
     return;
   }
 

test/Analysis/dangling-internal-buffer.cpp

 //RUN: %clang_analyze_cc1 -analyzer-checker=alpha.cplusplus.DanglingInternalBuffer %s -analyzer-output=text -verify
 
 namespace std {
 
 template< typename CharT >
 class basic_string {
 public:
   ~basic_string();
   const CharT *c_str();
+  const CharT *data();
 };
 
 typedef basic_string<char> string;
 typedef basic_string<wchar_t> wstring;
 typedef basic_string<char16_t> u16string;
 typedef basic_string<char32_t> u32string;
 
 } // end namespace std
 
 void consume(const char *) {}
 void consume(const wchar_t *) {}
 void consume(const char16_t *) {}
 void consume(const char32_t *) {}
 
-void deref_after_scope_char() {
+void deref_after_scope_char_cstr() {
   const char *c;
   {
     std::string s;
     c = s.c_str(); // expected-note {{Pointer to dangling buffer was obtained here}}
   } // expected-note {{Internal buffer is released because the object was destroyed}}
+  std::string s;
+  const char *c2 = s.c_str();
   consume(c); // expected-warning {{Use of memory after it is freed}}
   // expected-note@-1 {{Use of memory after it is freed}}
 }
 
-void deref_after_scope_char2() {
+void deref_after_scope_char_data() {
   const char *c;
   {
     std::string s;
-    c = s.c_str(); // expected-note {{Pointer to dangling buffer was obtained here}}
+    c = s.data(); // expected-note {{Pointer to dangling buffer was obtained here}}
   } // expected-note {{Internal buffer is released because the object was destroyed}}
   std::string s;
-  const char *c2 = s.c_str();
+  const char *c2 = s.data();
   consume(c); // expected-warning {{Use of memory after it is freed}}
   // expected-note@-1 {{Use of memory after it is freed}}
 }
 
-void deref_after_scope_wchar_t() {
+void deref_after_scope_wchar_t_cstr() {
   const wchar_t *w;
   {
     std::wstring ws;
     w = ws.c_str(); // expected-note {{Pointer to dangling buffer was obtained here}}
   } // expected-note {{Internal buffer is released because the object was destroyed}}
+  std::wstring ws;
+  const wchar_t *w2 = ws.c_str();
   consume(w); // expected-warning {{Use of memory after it is freed}}
   // expected-note@-1 {{Use of memory after it is freed}}
 }
 
-void deref_after_scope_char16_t() {
+void deref_after_scope_wchar_t_data() {
+  const wchar_t *w;
+  {
+    std::wstring ws;
+    w = ws.data(); // expected-note {{Pointer to dangling buffer was obtained here}}
+  } // expected-note {{Internal buffer is released because the object was destroyed}}
+  std::wstring ws;
+  const wchar_t *w2 = ws.data();
+  consume(w); // expected-warning {{Use of memory after it is freed}}
+  // expected-note@-1 {{Use of memory after it is freed}}
+}
+
+void deref_after_scope_char16_t_cstr() {
   const char16_t *c16;
   {
     std::u16string s16;
     c16 = s16.c_str(); // expected-note {{Pointer to dangling buffer was obtained here}}
   } // expected-note {{Internal buffer is released because the object was destroyed}}
+  std::u16string s16;
+  const char16_t *c16_2 = s16.c_str();
   consume(c16); // expected-warning {{Use of memory after it is freed}}
   // expected-note@-1 {{Use of memory after it is freed}}
 }
 
-void deref_after_scope_char32_t() {
+void deref_after_scope_char32_t_data() {
   const char32_t *c32;
   {
     std::u32string s32;
-    c32 = s32.c_str(); // expected-note {{Pointer to dangling buffer was obtained here}}
+    c32 = s32.data(); // expected-note {{Pointer to dangling buffer was obtained here}}
   } // expected-note {{Internal buffer is released because the object was destroyed}}
+  std::u32string s32;
+  const char32_t *c32_2 = s32.data();
   consume(c32); // expected-warning {{Use of memory after it is freed}}
   // expected-note@-1 {{Use of memory after it is freed}}
 }
 
-void deref_after_scope_ok() {
+void deref_after_scope_cstr_ok() {
   const char *c;
   std::string s;
   {
     c = s.c_str();
   }
   consume(c); // no-warning
 }
+
+void deref_after_scope_data_ok() {
+  const char *c;
+  std::string s;
+  {
+    c = s.data();
+  }
+  consume(c); // no-warning
+}