fuzz: Update FuzzedDataProvider.h from upstream (LLVM)

Upstream revision: 6d0488f75b/compiler-rt/include/fuzzer/FuzzedDataProvider.h

Changes:
* [compiler-rt] FuzzedDataProvider: add ConsumeData and method.
* [compiler-rt] Fix a typo in a comment in FuzzedDataProvider.h.
* [compiler-rt] Add ConsumeRandomLengthString() version without arguments.
* [compiler-rt] Refactor FuzzedDataProvider for better readability.
* [compiler-rt] FuzzedDataProvider: make linter happy.
* [compiler-rt] Mark FDP non-template methods inline to avoid ODR violations.

src/test/fuzz/FuzzedDataProvider.h

@@ -34,11 +34,74 @@ class FuzzedDataProvider {
       : data_ptr_(data), remaining_bytes_(size) {}
   ~FuzzedDataProvider() = default;
 
+  // See the implementation below (after the class definition) for more verbose
+  // comments for each of the methods.
+
+  // Methods returning std::vector of bytes. These are the most popular choice
+  // when splitting fuzzing input into pieces, as every piece is put into a
+  // separate buffer (i.e. ASan would catch any under-/overflow) and the memory
+  // will be released automatically.
+  template <typename T> std::vector<T> ConsumeBytes(size_t num_bytes);
+  template <typename T>
+  std::vector<T> ConsumeBytesWithTerminator(size_t num_bytes, T terminator = 0);
+  template <typename T> std::vector<T> ConsumeRemainingBytes();
+
+  // Methods returning strings. Use only when you need a std::string or a null
+  // terminated C-string. Otherwise, prefer the methods returning std::vector.
+  std::string ConsumeBytesAsString(size_t num_bytes);
+  std::string ConsumeRandomLengthString(size_t max_length);
+  std::string ConsumeRandomLengthString();
+  std::string ConsumeRemainingBytesAsString();
+
+  // Methods returning integer values.
+  template <typename T> T ConsumeIntegral();
+  template <typename T> T ConsumeIntegralInRange(T min, T max);
+
+  // Methods returning floating point values.
+  template <typename T> T ConsumeFloatingPoint();
+  template <typename T> T ConsumeFloatingPointInRange(T min, T max);
+
+  // 0 <= return value <= 1.
+  template <typename T> T ConsumeProbability();
+
+  bool ConsumeBool();
+
+  // Returns a value chosen from the given enum.
+  template <typename T> T ConsumeEnum();
+
+  // Returns a value from the given array.
+  template <typename T, size_t size> T PickValueInArray(const T (&array)[size]);
+  template <typename T> T PickValueInArray(std::initializer_list<const T> list);
+
+  // Writes data to the given destination and returns number of bytes written.
+  size_t ConsumeData(void *destination, size_t num_bytes);
+
+  // Reports the remaining bytes available for fuzzed input.
+  size_t remaining_bytes() { return remaining_bytes_; }
+
+ private:
+  FuzzedDataProvider(const FuzzedDataProvider &) = delete;
+  FuzzedDataProvider &operator=(const FuzzedDataProvider &) = delete;
+
+  void CopyAndAdvance(void *destination, size_t num_bytes);
+
+  void Advance(size_t num_bytes);
+
+  template <typename T>
+  std::vector<T> ConsumeBytes(size_t size, size_t num_bytes);
+
+  template <typename TS, typename TU> TS ConvertUnsignedToSigned(TU value);
+
+  const uint8_t *data_ptr_;
+  size_t remaining_bytes_;
+};
+
 // Returns a std::vector containing |num_bytes| of input data. If fewer than
 // |num_bytes| of data remain, returns a shorter std::vector containing all
 // of the data that's left. Can be used with any byte sized type, such as
 // char, unsigned char, uint8_t, etc.
-  template <typename T> std::vector<T> ConsumeBytes(size_t num_bytes) {
+template <typename T>
+std::vector<T> FuzzedDataProvider::ConsumeBytes(size_t num_bytes) {
   num_bytes = std::min(num_bytes, remaining_bytes_);
   return ConsumeBytes<T>(num_bytes, num_bytes);
 }
@@ -48,71 +111,41 @@ class FuzzedDataProvider {
 // needed, for example. But that is a rare case. Better avoid it, if possible,
 // and prefer using |ConsumeBytes| or |ConsumeBytesAsString| methods.
 template <typename T>
-  std::vector<T> ConsumeBytesWithTerminator(size_t num_bytes,
+std::vector<T> FuzzedDataProvider::ConsumeBytesWithTerminator(size_t num_bytes,
-                                            T terminator = 0) {
+                                                              T terminator) {
   num_bytes = std::min(num_bytes, remaining_bytes_);
   std::vector<T> result = ConsumeBytes<T>(num_bytes + 1, num_bytes);
   result.back() = terminator;
   return result;
 }
 
+// Returns a std::vector containing all remaining bytes of the input data.
+template <typename T>
+std::vector<T> FuzzedDataProvider::ConsumeRemainingBytes() {
+  return ConsumeBytes<T>(remaining_bytes_);
+}
+
 // Returns a std::string containing |num_bytes| of input data. Using this and
 // |.c_str()| on the resulting string is the best way to get an immutable
 // null-terminated C string. If fewer than |num_bytes| of data remain, returns
 // a shorter std::string containing all of the data that's left.
-  std::string ConsumeBytesAsString(size_t num_bytes) {
+inline std::string FuzzedDataProvider::ConsumeBytesAsString(size_t num_bytes) {
   static_assert(sizeof(std::string::value_type) == sizeof(uint8_t),
                 "ConsumeBytesAsString cannot convert the data to a string.");
 
   num_bytes = std::min(num_bytes, remaining_bytes_);
   std::string result(
-        reinterpret_cast<const std::string::value_type *>(data_ptr_),
+      reinterpret_cast<const std::string::value_type *>(data_ptr_), num_bytes);
-        num_bytes);
   Advance(num_bytes);
   return result;
 }
 
-  // Returns a number in the range [min, max] by consuming bytes from the
-  // input data. The value might not be uniformly distributed in the given
-  // range. If there's no input data left, always returns |min|. |min| must
-  // be less than or equal to |max|.
-  template <typename T> T ConsumeIntegralInRange(T min, T max) {
-    static_assert(std::is_integral<T>::value, "An integral type is required.");
-    static_assert(sizeof(T) <= sizeof(uint64_t), "Unsupported integral type.");
-
-    if (min > max)
-      abort();
-
-    // Use the biggest type possible to hold the range and the result.
-    uint64_t range = static_cast<uint64_t>(max) - min;
-    uint64_t result = 0;
-    size_t offset = 0;
-
-    while (offset < sizeof(T) * CHAR_BIT && (range >> offset) > 0 &&
-           remaining_bytes_ != 0) {
-      // Pull bytes off the end of the seed data. Experimentally, this seems to
-      // allow the fuzzer to more easily explore the input space. This makes
-      // sense, since it works by modifying inputs that caused new code to run,
-      // and this data is often used to encode length of data read by
-      // |ConsumeBytes|. Separating out read lengths makes it easier modify the
-      // contents of the data that is actually read.
-      --remaining_bytes_;
-      result = (result << CHAR_BIT) | data_ptr_[remaining_bytes_];
-      offset += CHAR_BIT;
-    }
-
-    // Avoid division by 0, in case |range + 1| results in overflow.
-    if (range != std::numeric_limits<decltype(range)>::max())
-      result = result % (range + 1);
-
-    return static_cast<T>(min + result);
-  }
-
 // Returns a std::string of length from 0 to |max_length|. When it runs out of
 // input data, returns what remains of the input. Designed to be more stable
 // with respect to a fuzzer inserting characters than just picking a random
 // length and then consuming that many bytes with |ConsumeBytes|.
-  std::string ConsumeRandomLengthString(size_t max_length) {
+inline std::string
+FuzzedDataProvider::ConsumeRandomLengthString(size_t max_length) {
   // Reads bytes from the start of |data_ptr_|. Maps "\\" to "\", and maps "\"
   // followed by anything else to the end of the string. As a result of this
   // logic, a fuzzer can insert characters into the string, and the string
@@ -139,75 +172,67 @@ class FuzzedDataProvider {
   return result;
 }
 
-  // Returns a std::vector containing all remaining bytes of the input data.
+// Returns a std::string of length from 0 to |remaining_bytes_|.
-  template <typename T> std::vector<T> ConsumeRemainingBytes() {
+inline std::string FuzzedDataProvider::ConsumeRandomLengthString() {
-    return ConsumeBytes<T>(remaining_bytes_);
+  return ConsumeRandomLengthString(remaining_bytes_);
 }
 
 // Returns a std::string containing all remaining bytes of the input data.
 // Prefer using |ConsumeRemainingBytes| unless you actually need a std::string
 // object.
-  std::string ConsumeRemainingBytesAsString() {
+inline std::string FuzzedDataProvider::ConsumeRemainingBytesAsString() {
   return ConsumeBytesAsString(remaining_bytes_);
 }
 
 // Returns a number in the range [Type's min, Type's max]. The value might
 // not be uniformly distributed in the given range. If there's no input data
 // left, always returns |min|.
-  template <typename T> T ConsumeIntegral() {
+template <typename T> T FuzzedDataProvider::ConsumeIntegral() {
   return ConsumeIntegralInRange(std::numeric_limits<T>::min(),
                                 std::numeric_limits<T>::max());
 }
 
-  // Reads one byte and returns a bool, or false when no data remains.
+// Returns a number in the range [min, max] by consuming bytes from the
-  bool ConsumeBool() { return 1 & ConsumeIntegral<uint8_t>(); }
+// input data. The value might not be uniformly distributed in the given
-
+// range. If there's no input data left, always returns |min|. |min| must
-  // Returns a copy of the value selected from the given fixed-size |array|.
+// be less than or equal to |max|.
-  template <typename T, size_t size>
-  T PickValueInArray(const T (&array)[size]) {
-    static_assert(size > 0, "The array must be non empty.");
-    return array[ConsumeIntegralInRange<size_t>(0, size - 1)];
-  }
-
 template <typename T>
-  T PickValueInArray(std::initializer_list<const T> list) {
+T FuzzedDataProvider::ConsumeIntegralInRange(T min, T max) {
-    // TODO(Dor1s): switch to static_assert once C++14 is allowed.
+  static_assert(std::is_integral<T>::value, "An integral type is required.");
-    if (!list.size())
+  static_assert(sizeof(T) <= sizeof(uint64_t), "Unsupported integral type.");
+
+  if (min > max)
     abort();
 
-    return *(list.begin() + ConsumeIntegralInRange<size_t>(0, list.size() - 1));
+  // Use the biggest type possible to hold the range and the result.
-  }
+  uint64_t range = static_cast<uint64_t>(max) - min;
+  uint64_t result = 0;
+  size_t offset = 0;
 
-  // Returns an enum value. The enum must start at 0 and be contiguous. It must
+  while (offset < sizeof(T) * CHAR_BIT && (range >> offset) > 0 &&
-  // also contain |kMaxValue| aliased to its largest (inclusive) value. Such as:
+         remaining_bytes_ != 0) {
-  // enum class Foo { SomeValue, OtherValue, kMaxValue = OtherValue };
+    // Pull bytes off the end of the seed data. Experimentally, this seems to
-  template <typename T> T ConsumeEnum() {
+    // allow the fuzzer to more easily explore the input space. This makes
-    static_assert(std::is_enum<T>::value, "|T| must be an enum type.");
+    // sense, since it works by modifying inputs that caused new code to run,
-    return static_cast<T>(ConsumeIntegralInRange<uint32_t>(
+    // and this data is often used to encode length of data read by
-        0, static_cast<uint32_t>(T::kMaxValue)));
+    // |ConsumeBytes|. Separating out read lengths makes it easier modify the
+    // contents of the data that is actually read.
+    --remaining_bytes_;
+    result = (result << CHAR_BIT) | data_ptr_[remaining_bytes_];
+    offset += CHAR_BIT;
   }
 
-  // Returns a floating point number in the range [0.0, 1.0]. If there's no
+  // Avoid division by 0, in case |range + 1| results in overflow.
-  // input data left, always returns 0.
+  if (range != std::numeric_limits<decltype(range)>::max())
-  template <typename T> T ConsumeProbability() {
+    result = result % (range + 1);
-    static_assert(std::is_floating_point<T>::value,
-                  "A floating point type is required.");
-
-    // Use different integral types for different floating point types in order
-    // to provide better density of the resulting values.
-    using IntegralType =
-        typename std::conditional<(sizeof(T) <= sizeof(uint32_t)), uint32_t,
-                                  uint64_t>::type;
 
-    T result = static_cast<T>(ConsumeIntegral<IntegralType>());
+  return static_cast<T>(min + result);
-    result /= static_cast<T>(std::numeric_limits<IntegralType>::max());
-    return result;
 }
 
 // Returns a floating point value in the range [Type's lowest, Type's max] by
 // consuming bytes from the input data. If there's no input data left, always
 // returns approximately 0.
-  template <typename T> T ConsumeFloatingPoint() {
+template <typename T> T FuzzedDataProvider::ConsumeFloatingPoint() {
   return ConsumeFloatingPointInRange<T>(std::numeric_limits<T>::lowest(),
                                         std::numeric_limits<T>::max());
 }
@@ -215,7 +240,8 @@ class FuzzedDataProvider {
 // Returns a floating point value in the given range by consuming bytes from
 // the input data. If there's no input data left, returns |min|. Note that
 // |min| must be less than or equal to |max|.
-  template <typename T> T ConsumeFloatingPointInRange(T min, T max) {
+template <typename T>
+T FuzzedDataProvider::ConsumeFloatingPointInRange(T min, T max) {
   if (min > max)
     abort();
 
@@ -237,14 +263,74 @@ class FuzzedDataProvider {
   return result + range * ConsumeProbability<T>();
 }
 
-  // Reports the remaining bytes available for fuzzed input.
+// Returns a floating point number in the range [0.0, 1.0]. If there's no
-  size_t remaining_bytes() { return remaining_bytes_; }
+// input data left, always returns 0.
+template <typename T> T FuzzedDataProvider::ConsumeProbability() {
+  static_assert(std::is_floating_point<T>::value,
+                "A floating point type is required.");
 
- private:
+  // Use different integral types for different floating point types in order
-  FuzzedDataProvider(const FuzzedDataProvider &) = delete;
+  // to provide better density of the resulting values.
-  FuzzedDataProvider &operator=(const FuzzedDataProvider &) = delete;
+  using IntegralType =
+      typename std::conditional<(sizeof(T) <= sizeof(uint32_t)), uint32_t,
+                                uint64_t>::type;
+
+  T result = static_cast<T>(ConsumeIntegral<IntegralType>());
+  result /= static_cast<T>(std::numeric_limits<IntegralType>::max());
+  return result;
+}
+
+// Reads one byte and returns a bool, or false when no data remains.
+inline bool FuzzedDataProvider::ConsumeBool() {
+  return 1 & ConsumeIntegral<uint8_t>();
+}
+
+// Returns an enum value. The enum must start at 0 and be contiguous. It must
+// also contain |kMaxValue| aliased to its largest (inclusive) value. Such as:
+// enum class Foo { SomeValue, OtherValue, kMaxValue = OtherValue };
+template <typename T> T FuzzedDataProvider::ConsumeEnum() {
+  static_assert(std::is_enum<T>::value, "|T| must be an enum type.");
+  return static_cast<T>(
+      ConsumeIntegralInRange<uint32_t>(0, static_cast<uint32_t>(T::kMaxValue)));
+}
+
+// Returns a copy of the value selected from the given fixed-size |array|.
+template <typename T, size_t size>
+T FuzzedDataProvider::PickValueInArray(const T (&array)[size]) {
+  static_assert(size > 0, "The array must be non empty.");
+  return array[ConsumeIntegralInRange<size_t>(0, size - 1)];
+}
+
+template <typename T>
+T FuzzedDataProvider::PickValueInArray(std::initializer_list<const T> list) {
+  // TODO(Dor1s): switch to static_assert once C++14 is allowed.
+  if (!list.size())
+    abort();
+
+  return *(list.begin() + ConsumeIntegralInRange<size_t>(0, list.size() - 1));
+}
+
+// Writes |num_bytes| of input data to the given destination pointer. If there
+// is not enough data left, writes all remaining bytes. Return value is the
+// number of bytes written.
+// In general, it's better to avoid using this function, but it may be useful
+// in cases when it's necessary to fill a certain buffer or object with
+// fuzzing data.
+inline size_t FuzzedDataProvider::ConsumeData(void *destination,
+                                              size_t num_bytes) {
+  num_bytes = std::min(num_bytes, remaining_bytes_);
+  CopyAndAdvance(destination, num_bytes);
+  return num_bytes;
+}
 
-  void Advance(size_t num_bytes) {
+// Private methods.
+inline void FuzzedDataProvider::CopyAndAdvance(void *destination,
+                                               size_t num_bytes) {
+  std::memcpy(destination, data_ptr_, num_bytes);
+  Advance(num_bytes);
+}
+
+inline void FuzzedDataProvider::Advance(size_t num_bytes) {
   if (num_bytes > remaining_bytes_)
     abort();
 
@@ -253,7 +339,7 @@ class FuzzedDataProvider {
 }
 
 template <typename T>
-  std::vector<T> ConsumeBytes(size_t size, size_t num_bytes_to_consume) {
+std::vector<T> FuzzedDataProvider::ConsumeBytes(size_t size, size_t num_bytes) {
   static_assert(sizeof(T) == sizeof(uint8_t), "Incompatible data type.");
 
   // The point of using the size-based constructor below is to increase the
@@ -264,13 +350,12 @@ class FuzzedDataProvider {
   // To increase the odds even more, we also call |shrink_to_fit| below.
   std::vector<T> result(size);
   if (size == 0) {
-      if (num_bytes_to_consume != 0)
+    if (num_bytes != 0)
       abort();
     return result;
   }
 
-    std::memcpy(result.data(), data_ptr_, num_bytes_to_consume);
+  CopyAndAdvance(result.data(), num_bytes);
-    Advance(num_bytes_to_consume);
 
   // Even though |shrink_to_fit| is also implementation specific, we expect it
   // to provide an additional assurance in case vector's constructor allocated
@@ -279,7 +364,8 @@ class FuzzedDataProvider {
   return result;
 }
 
-  template <typename TS, typename TU> TS ConvertUnsignedToSigned(TU value) {
+template <typename TS, typename TU>
+TS FuzzedDataProvider::ConvertUnsignedToSigned(TU value) {
   static_assert(sizeof(TS) == sizeof(TU), "Incompatible data types.");
   static_assert(!std::numeric_limits<TU>::is_signed,
                 "Source type must be unsigned.");
@@ -288,7 +374,7 @@ class FuzzedDataProvider {
   if (std::numeric_limits<TS>::is_modulo)
     return static_cast<TS>(value);
 
-    // Avoid using implementation-defined unsigned to signer conversions.
+  // Avoid using implementation-defined unsigned to signed conversions.
   // To learn more, see https://stackoverflow.com/questions/13150449.
   if (value <= std::numeric_limits<TS>::max()) {
     return static_cast<TS>(value);
@@ -298,8 +384,4 @@ class FuzzedDataProvider {
   }
 }
 
-  const uint8_t *data_ptr_;
-  size_t remaining_bytes_;
-};
-
 #endif // LLVM_FUZZER_FUZZED_DATA_PROVIDER_H_