4 files changed, 376 insertions, 259 deletions

diff --git a/compiler-rt/include/fuzzer/FuzzedDataProvider.h b/compiler-rt/include/fuzzer/FuzzedDataProvider.h
index 3e069eba69b4..83bcd0134a7d 100644
--- a/compiler-rt/include/fuzzer/FuzzedDataProvider.h
+++ b/compiler-rt/include/fuzzer/FuzzedDataProvider.h
@@ -34,272 +34,354 @@ class FuzzedDataProvider {
       : data_ptr_(data), remaining_bytes_(size) {}
   ~FuzzedDataProvider() = default;
 
-  // 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) {
-    num_bytes = std::min(num_bytes, remaining_bytes_);
-    return ConsumeBytes<T>(num_bytes, num_bytes);
-  }
-
-  // Similar to |ConsumeBytes|, but also appends the terminator value at the end
-  // of the resulting vector. Useful, when a mutable null-terminated C-string is
-  // needed, for example. But that is a rare case. Better avoid it, if possible,
-  // and prefer using |ConsumeBytes| or |ConsumeBytesAsString| methods.
+  // 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) {
-    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::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) {
-    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_),
-        num_bytes);
-    Advance(num_bytes);
-    return result;
-  }
+  std::vector<T> ConsumeBytesWithTerminator(size_t num_bytes, T terminator = 0);
+  template <typename T> std::vector<T> ConsumeRemainingBytes();
 
-  // 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.");
+  // 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();
 
-    if (min > max)
-      abort();
+  // Methods returning integer values.
+  template <typename T> T ConsumeIntegral();
+  template <typename T> T ConsumeIntegralInRange(T min, T max);
 
-    // 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;
-    }
+  // Methods returning floating point values.
+  template <typename T> T ConsumeFloatingPoint();
+  template <typename T> T ConsumeFloatingPointInRange(T min, T max);
 
-    // Avoid division by 0, in case |range + 1| results in overflow.
-    if (range != std::numeric_limits<decltype(range)>::max())
-      result = result % (range + 1);
+  // 0 <= return value <= 1.
+  template <typename T> T ConsumeProbability();
 
-    return static_cast<T>(min + result);
-  }
+  bool ConsumeBool();
 
-  // 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) {
-    // 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
-    // will be lengthened to include those new characters, resulting in a more
-    // stable fuzzer than picking the length of a string independently from
-    // picking its contents.
-    std::string result;
-
-    // Reserve the anticipated capaticity to prevent several reallocations.
-    result.reserve(std::min(max_length, remaining_bytes_));
-    for (size_t i = 0; i < max_length && remaining_bytes_ != 0; ++i) {
-      char next = ConvertUnsignedToSigned<char>(data_ptr_[0]);
-      Advance(1);
-      if (next == '\\' && remaining_bytes_ != 0) {
-        next = ConvertUnsignedToSigned<char>(data_ptr_[0]);
-        Advance(1);
-        if (next != '\\')
-          break;
-      }
-      result += next;
-    }
+  // Returns a value chosen from the given enum.
+  template <typename T> T ConsumeEnum();
 
-    result.shrink_to_fit();
-    return result;
-  }
+  // 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);
 
-  // Returns a std::vector containing all remaining bytes of the input data.
-  template <typename T> std::vector<T> ConsumeRemainingBytes() {
-    return ConsumeBytes<T>(remaining_bytes_);
-  }
+  // Writes data to the given destination and returns number of bytes written.
+  size_t ConsumeData(void *destination, size_t num_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() {
-    return ConsumeBytesAsString(remaining_bytes_);
-  }
+  // Reports the remaining bytes available for fuzzed input.
+  size_t remaining_bytes() { return 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() {
-    return ConsumeIntegralInRange(std::numeric_limits<T>::min(),
-                                  std::numeric_limits<T>::max());
-  }
+ private:
+  FuzzedDataProvider(const FuzzedDataProvider &) = delete;
+  FuzzedDataProvider &operator=(const FuzzedDataProvider &) = delete;
 
-  // Reads one byte and returns a bool, or false when no data remains.
-  bool ConsumeBool() { return 1 & ConsumeIntegral<uint8_t>(); }
+  void CopyAndAdvance(void *destination, size_t num_bytes);
 
-  // Returns a copy of the value selected from the given fixed-size |array|.
-  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)];
-  }
+  void Advance(size_t num_bytes);
 
   template <typename T>
-  T 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));
-  }
-
-  // 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 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)));
-  }
+  std::vector<T> ConsumeBytes(size_t size, size_t num_bytes);
 
-  // Returns a floating point number in the range [0.0, 1.0]. If there's no
-  // input data left, always returns 0.
-  template <typename T> T ConsumeProbability() {
-    static_assert(std::is_floating_point<T>::value,
-                  "A floating point type is required.");
+  template <typename TS, typename TU> TS ConvertUnsignedToSigned(TU value);
 
-    // 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;
+  const uint8_t *data_ptr_;
+  size_t remaining_bytes_;
+};
 
-    T result = static_cast<T>(ConsumeIntegral<IntegralType>());
-    result /= static_cast<T>(std::numeric_limits<IntegralType>::max());
-    return result;
+// 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> FuzzedDataProvider::ConsumeBytes(size_t num_bytes) {
+  num_bytes = std::min(num_bytes, remaining_bytes_);
+  return ConsumeBytes<T>(num_bytes, num_bytes);
+}
+
+// Similar to |ConsumeBytes|, but also appends the terminator value at the end
+// of the resulting vector. Useful, when a mutable null-terminated C-string is
+// 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> FuzzedDataProvider::ConsumeBytesWithTerminator(size_t num_bytes,
+                                                              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.
+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_), num_bytes);
+  Advance(num_bytes);
+  return 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|.
+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
+  // will be lengthened to include those new characters, resulting in a more
+  // stable fuzzer than picking the length of a string independently from
+  // picking its contents.
+  std::string result;
+
+  // Reserve the anticipated capaticity to prevent several reallocations.
+  result.reserve(std::min(max_length, remaining_bytes_));
+  for (size_t i = 0; i < max_length && remaining_bytes_ != 0; ++i) {
+    char next = ConvertUnsignedToSigned<char>(data_ptr_[0]);
+    Advance(1);
+    if (next == '\\' && remaining_bytes_ != 0) {
+      next = ConvertUnsignedToSigned<char>(data_ptr_[0]);
+      Advance(1);
+      if (next != '\\')
+        break;
+    }
+    result += next;
   }
 
-  // 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() {
-    return ConsumeFloatingPointInRange<T>(std::numeric_limits<T>::lowest(),
-                                          std::numeric_limits<T>::max());
+  result.shrink_to_fit();
+  return result;
+}
+
+// Returns a std::string of length from 0 to |remaining_bytes_|.
+inline std::string FuzzedDataProvider::ConsumeRandomLengthString() {
+  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.
+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 FuzzedDataProvider::ConsumeIntegral() {
+  return ConsumeIntegralInRange(std::numeric_limits<T>::min(),
+                                std::numeric_limits<T>::max());
+}
+
+// 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 FuzzedDataProvider::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;
   }
 
-  // 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) {
-    if (min > max)
-      abort();
-
-    T range = .0;
-    T result = min;
-    constexpr T zero(.0);
-    if (max > zero && min < zero && max > min + std::numeric_limits<T>::max()) {
-      // The diff |max - min| would overflow the given floating point type. Use
-      // the half of the diff as the range and consume a bool to decide whether
-      // the result is in the first of the second part of the diff.
-      range = (max / 2.0) - (min / 2.0);
-      if (ConsumeBool()) {
-        result += range;
-      }
-    } else {
-      range = max - min;
+  // 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 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 FuzzedDataProvider::ConsumeFloatingPoint() {
+  return ConsumeFloatingPointInRange<T>(std::numeric_limits<T>::lowest(),
+                                        std::numeric_limits<T>::max());
+}
+
+// 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 FuzzedDataProvider::ConsumeFloatingPointInRange(T min, T max) {
+  if (min > max)
+    abort();
+
+  T range = .0;
+  T result = min;
+  constexpr T zero(.0);
+  if (max > zero && min < zero && max > min + std::numeric_limits<T>::max()) {
+    // The diff |max - min| would overflow the given floating point type. Use
+    // the half of the diff as the range and consume a bool to decide whether
+    // the result is in the first of the second part of the diff.
+    range = (max / 2.0) - (min / 2.0);
+    if (ConsumeBool()) {
+      result += range;
     }
-
-    return result + range * ConsumeProbability<T>();
+  } else {
+    range = max - min;
   }
 
-  // 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 Advance(size_t num_bytes) {
-    if (num_bytes > remaining_bytes_)
+  return result + range * ConsumeProbability<T>();
+}
+
+// Returns a floating point number in the range [0.0, 1.0]. If there's no
+// 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.");
+
+  // 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>());
+  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;
+}
+
+// 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();
+
+  data_ptr_ += num_bytes;
+  remaining_bytes_ -= num_bytes;
+}
+
+template <typename T>
+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
+  // odds of having a vector object with capacity being equal to the length.
+  // That part is always implementation specific, but at least both libc++ and
+  // libstdc++ allocate the requested number of bytes in that constructor,
+  // which seems to be a natural choice for other implementations as well.
+  // To increase the odds even more, we also call |shrink_to_fit| below.
+  std::vector<T> result(size);
+  if (size == 0) {
+    if (num_bytes != 0)
       abort();
-
-    data_ptr_ += num_bytes;
-    remaining_bytes_ -= num_bytes;
-  }
-
-  template <typename T>
-  std::vector<T> ConsumeBytes(size_t size, size_t num_bytes_to_consume) {
-    static_assert(sizeof(T) == sizeof(uint8_t), "Incompatible data type.");
-
-    // The point of using the size-based constructor below is to increase the
-    // odds of having a vector object with capacity being equal to the length.
-    // That part is always implementation specific, but at least both libc++ and
-    // libstdc++ allocate the requested number of bytes in that constructor,
-    // which seems to be a natural choice for other implementations as well.
-    // 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)
-        abort();
-      return result;
-    }
-
-    std::memcpy(result.data(), data_ptr_, num_bytes_to_consume);
-    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
-    // a buffer which is larger than the actual amount of data we put inside it.
-    result.shrink_to_fit();
     return result;
   }
 
-  template <typename TS, typename TU> TS 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.");
-
-    // TODO(Dor1s): change to `if constexpr` once C++17 becomes mainstream.
-    if (std::numeric_limits<TS>::is_modulo)
-      return static_cast<TS>(value);
-
-    // Avoid using implementation-defined unsigned to signer conversions.
-    // To learn more, see https://stackoverflow.com/questions/13150449.
-    if (value <= std::numeric_limits<TS>::max()) {
-      return static_cast<TS>(value);
-    } else {
-      constexpr auto TS_min = std::numeric_limits<TS>::min();
-      return TS_min + static_cast<char>(value - TS_min);
-    }
+  CopyAndAdvance(result.data(), num_bytes);
+
+  // Even though |shrink_to_fit| is also implementation specific, we expect it
+  // to provide an additional assurance in case vector's constructor allocated
+  // a buffer which is larger than the actual amount of data we put inside it.
+  result.shrink_to_fit();
+  return result;
+}
+
+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.");
+
+  // TODO(Dor1s): change to `if constexpr` once C++17 becomes mainstream.
+  if (std::numeric_limits<TS>::is_modulo)
+    return static_cast<TS>(value);
+
+  // 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);
+  } else {
+    constexpr auto TS_min = std::numeric_limits<TS>::min();
+    return TS_min + static_cast<char>(value - TS_min);
   }
-
-  const uint8_t *data_ptr_;
-  size_t remaining_bytes_;
-};
+}
 
 #endif // LLVM_FUZZER_FUZZED_DATA_PROVIDER_H_
diff --git a/compiler-rt/include/profile/InstrProfData.inc b/compiler-rt/include/profile/InstrProfData.inc
index 99f41d8fef07..a6913527e67f 100644
--- a/compiler-rt/include/profile/InstrProfData.inc
+++ b/compiler-rt/include/profile/InstrProfData.inc
@@ -198,6 +198,14 @@ VALUE_PROF_KIND(IPVK_Last, IPVK_MemOPSize, "last")
 #undef VALUE_PROF_KIND
 /* VALUE_PROF_KIND end */
 
+#undef COVMAP_V2_OR_V3
+#ifdef COVMAP_V2
+#define COVMAP_V2_OR_V3
+#endif
+#ifdef COVMAP_V3
+#define COVMAP_V2_OR_V3
+#endif
+
 /* COVMAP_FUNC_RECORD start */
 /* Definition of member fields of the function record structure in coverage
  * map.
@@ -214,16 +222,30 @@ COVMAP_FUNC_RECORD(const IntPtrT, llvm::Type::getInt8PtrTy(Ctx), \
 COVMAP_FUNC_RECORD(const uint32_t, llvm::Type::getInt32Ty(Ctx), NameSize, \
                    llvm::ConstantInt::get(llvm::Type::getInt32Ty(Ctx), \
                    NameValue.size()))
-#else
+#endif
+#ifdef COVMAP_V2_OR_V3
 COVMAP_FUNC_RECORD(const int64_t, llvm::Type::getInt64Ty(Ctx), NameRef, \
-                   llvm::ConstantInt::get(llvm::Type::getInt64Ty(Ctx), \
-                   llvm::IndexedInstrProf::ComputeHash(NameValue)))
+                   llvm::ConstantInt::get( \
+                     llvm::Type::getInt64Ty(Ctx), NameHash))
 #endif
 COVMAP_FUNC_RECORD(const uint32_t, llvm::Type::getInt32Ty(Ctx), DataSize, \
-                   llvm::ConstantInt::get(llvm::Type::getInt32Ty(Ctx),\
-                   CoverageMapping.size()))
+                   llvm::ConstantInt::get( \
+                     llvm::Type::getInt32Ty(Ctx), CoverageMapping.size()))
 COVMAP_FUNC_RECORD(const uint64_t, llvm::Type::getInt64Ty(Ctx), FuncHash, \
-                   llvm::ConstantInt::get(llvm::Type::getInt64Ty(Ctx), FuncHash))
+                   llvm::ConstantInt::get( \
+                     llvm::Type::getInt64Ty(Ctx), FuncHash))
+#ifdef COVMAP_V3
+COVMAP_FUNC_RECORD(const uint64_t, llvm::Type::getInt64Ty(Ctx), FilenamesRef, \
+                   llvm::ConstantInt::get( \
+                     llvm::Type::getInt64Ty(Ctx), FilenamesRef))
+COVMAP_FUNC_RECORD(const char, \
+                   llvm::ArrayType::get(llvm::Type::getInt8Ty(Ctx), \
+                                        CoverageMapping.size()), \
+                   CoverageMapping,
+                   llvm::ConstantDataArray::getRaw( \
+                     CoverageMapping, CoverageMapping.size(), \
+                     llvm::Type::getInt8Ty(Ctx)))
+#endif
 #undef COVMAP_FUNC_RECORD
 /* COVMAP_FUNC_RECORD end.  */
 
@@ -236,7 +258,7 @@ COVMAP_FUNC_RECORD(const uint64_t, llvm::Type::getInt64Ty(Ctx), FuncHash, \
 #define INSTR_PROF_DATA_DEFINED
 #endif
 COVMAP_HEADER(uint32_t, Int32Ty, NRecords, \
-              llvm::ConstantInt::get(Int32Ty,  FunctionRecords.size()))
+              llvm::ConstantInt::get(Int32Ty, NRecords))
 COVMAP_HEADER(uint32_t, Int32Ty, FilenamesSize, \
               llvm::ConstantInt::get(Int32Ty, FilenamesSize))
 COVMAP_HEADER(uint32_t, Int32Ty, CoverageSize, \
@@ -267,6 +289,9 @@ INSTR_PROF_SECT_ENTRY(IPSK_vnodes, \
 INSTR_PROF_SECT_ENTRY(IPSK_covmap, \
                       INSTR_PROF_QUOTE(INSTR_PROF_COVMAP_COMMON), \
                       INSTR_PROF_COVMAP_COFF, "__LLVM_COV,")
+INSTR_PROF_SECT_ENTRY(IPSK_covfun, \
+                      INSTR_PROF_QUOTE(INSTR_PROF_COVFUN_COMMON), \
+                      INSTR_PROF_COVFUN_COFF, "__LLVM_COV,")
 INSTR_PROF_SECT_ENTRY(IPSK_orderfile, \
                       INSTR_PROF_QUOTE(INSTR_PROF_ORDERFILE_COMMON), \
                       INSTR_PROF_QUOTE(INSTR_PROF_ORDERFILE_COFF), "__DATA,")
@@ -632,9 +657,9 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 /* Raw profile format version (start from 1). */
 #define INSTR_PROF_RAW_VERSION 5
 /* Indexed profile format version (start from 1). */
-#define INSTR_PROF_INDEX_VERSION 5
-/* Coverage mapping format vresion (start from 0). */
-#define INSTR_PROF_COVMAP_VERSION 2
+#define INSTR_PROF_INDEX_VERSION 6
+/* Coverage mapping format version (start from 0). */
+#define INSTR_PROF_COVMAP_VERSION 3
 
 /* Profile version is always of type uint64_t. Reserve the upper 8 bits in the
  * version for other variants of profile. We set the lowest bit of the upper 8
@@ -661,6 +686,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 #define INSTR_PROF_VALS_COMMON __llvm_prf_vals
 #define INSTR_PROF_VNODES_COMMON __llvm_prf_vnds
 #define INSTR_PROF_COVMAP_COMMON __llvm_covmap
+#define INSTR_PROF_COVFUN_COMMON __llvm_covfun
 #define INSTR_PROF_ORDERFILE_COMMON __llvm_orderfile
 /* Windows section names. Because these section names contain dollar characters,
  * they must be quoted.
@@ -671,6 +697,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 #define INSTR_PROF_VALS_COFF ".lprfv$M"
 #define INSTR_PROF_VNODES_COFF ".lprfnd$M"
 #define INSTR_PROF_COVMAP_COFF ".lcovmap$M"
+#define INSTR_PROF_COVFUN_COFF ".lcovfun$M"
 #define INSTR_PROF_ORDERFILE_COFF ".lorderfile$M"
 
 #ifdef _WIN32
@@ -685,6 +712,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 /* Value profile nodes section. */
 #define INSTR_PROF_VNODES_SECT_NAME INSTR_PROF_VNODES_COFF
 #define INSTR_PROF_COVMAP_SECT_NAME INSTR_PROF_COVMAP_COFF
+#define INSTR_PROF_COVFUN_SECT_NAME INSTR_PROF_COVFUN_COFF
 #define INSTR_PROF_ORDERFILE_SECT_NAME INSTR_PROF_ORDERFILE_COFF
 #else
 /* Runtime section names and name strings.  */
@@ -698,6 +726,7 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 /* Value profile nodes section. */
 #define INSTR_PROF_VNODES_SECT_NAME INSTR_PROF_QUOTE(INSTR_PROF_VNODES_COMMON)
 #define INSTR_PROF_COVMAP_SECT_NAME INSTR_PROF_QUOTE(INSTR_PROF_COVMAP_COMMON)
+#define INSTR_PROF_COVFUN_SECT_NAME INSTR_PROF_QUOTE(INSTR_PROF_COVFUN_COMMON)
 /* Order file instrumentation. */
 #define INSTR_PROF_ORDERFILE_SECT_NAME                                         \
   INSTR_PROF_QUOTE(INSTR_PROF_ORDERFILE_COMMON)
@@ -752,3 +781,5 @@ typedef struct InstrProfValueData {
 #else
 #undef INSTR_PROF_DATA_DEFINED
 #endif
+
+#undef COVMAP_V2_OR_V3
diff --git a/compiler-rt/include/sanitizer/linux_syscall_hooks.h b/compiler-rt/include/sanitizer/linux_syscall_hooks.h
index a1794b71af50..56eae3d40f96 100644
--- a/compiler-rt/include/sanitizer/linux_syscall_hooks.h
+++ b/compiler-rt/include/sanitizer/linux_syscall_hooks.h
@@ -1845,6 +1845,10 @@
 #define __sanitizer_syscall_post_rt_sigaction(res, signum, act, oldact, sz)    \
   __sanitizer_syscall_post_impl_rt_sigaction(res, (long)signum, (long)act,     \
                                              (long)oldact, (long)sz)
+#define __sanitizer_syscall_pre_sigaltstack(ss, oss)                           \
+  __sanitizer_syscall_pre_impl_sigaltstack((long)ss, (long)oss)
+#define __sanitizer_syscall_post_sigaltstack(res, ss, oss)                     \
+  __sanitizer_syscall_post_impl_sigaltstack(res, (long)ss, (long)oss)
 
 // And now a few syscalls we don't handle yet.
 #define __sanitizer_syscall_pre_afs_syscall(...)
@@ -1912,7 +1916,6 @@
 #define __sanitizer_syscall_pre_setreuid32(...)
 #define __sanitizer_syscall_pre_set_thread_area(...)
 #define __sanitizer_syscall_pre_setuid32(...)
-#define __sanitizer_syscall_pre_sigaltstack(...)
 #define __sanitizer_syscall_pre_sigreturn(...)
 #define __sanitizer_syscall_pre_sigsuspend(...)
 #define __sanitizer_syscall_pre_stty(...)
@@ -1992,7 +1995,6 @@
 #define __sanitizer_syscall_post_setreuid32(res, ...)
 #define __sanitizer_syscall_post_set_thread_area(res, ...)
 #define __sanitizer_syscall_post_setuid32(res, ...)
-#define __sanitizer_syscall_post_sigaltstack(res, ...)
 #define __sanitizer_syscall_post_sigreturn(res, ...)
 #define __sanitizer_syscall_post_sigsuspend(res, ...)
 #define __sanitizer_syscall_post_stty(res, ...)
@@ -3075,6 +3077,8 @@ void __sanitizer_syscall_pre_impl_rt_sigaction(long signum, long act,
                                                long oldact, long sz);
 void __sanitizer_syscall_post_impl_rt_sigaction(long res, long signum, long act,
                                                 long oldact, long sz);
+void __sanitizer_syscall_pre_impl_sigaltstack(long ss, long oss);
+void __sanitizer_syscall_post_impl_sigaltstack(long res, long ss, long oss);
 #ifdef __cplusplus
 }  // extern "C"
 #endif
diff --git a/compiler-rt/include/sanitizer/tsan_interface.h b/compiler-rt/include/sanitizer/tsan_interface.h
index 011b23350cac..96b8ad58541c 100644
--- a/compiler-rt/include/sanitizer/tsan_interface.h
+++ b/compiler-rt/include/sanitizer/tsan_interface.h
@@ -38,34 +38,34 @@ void __tsan_release(void *addr);
 
 // Mutex has static storage duration and no-op constructor and destructor.
 // This effectively makes tsan ignore destroy annotation.
-const unsigned __tsan_mutex_linker_init      = 1 << 0;
+static const unsigned __tsan_mutex_linker_init      = 1 << 0;
 // Mutex is write reentrant.
-const unsigned __tsan_mutex_write_reentrant  = 1 << 1;
+static const unsigned __tsan_mutex_write_reentrant  = 1 << 1;
 // Mutex is read reentrant.
-const unsigned __tsan_mutex_read_reentrant   = 1 << 2;
+static const unsigned __tsan_mutex_read_reentrant   = 1 << 2;
 // Mutex does not have static storage duration, and must not be used after
 // its destructor runs.  The opposite of __tsan_mutex_linker_init.
 // If this flag is passed to __tsan_mutex_destroy, then the destruction
 // is ignored unless this flag was previously set on the mutex.
-const unsigned __tsan_mutex_not_static       = 1 << 8;
+static const unsigned __tsan_mutex_not_static       = 1 << 8;
 
 // Mutex operation flags:
 
 // Denotes read lock operation.
-const unsigned __tsan_mutex_read_lock        = 1 << 3;
+static const unsigned __tsan_mutex_read_lock        = 1 << 3;
 // Denotes try lock operation.
-const unsigned __tsan_mutex_try_lock         = 1 << 4;
+static const unsigned __tsan_mutex_try_lock         = 1 << 4;
 // Denotes that a try lock operation has failed to acquire the mutex.
-const unsigned __tsan_mutex_try_lock_failed  = 1 << 5;
+static const unsigned __tsan_mutex_try_lock_failed  = 1 << 5;
 // Denotes that the lock operation acquires multiple recursion levels.
 // Number of levels is passed in recursion parameter.
 // This is useful for annotation of e.g. Java builtin monitors,
 // for which wait operation releases all recursive acquisitions of the mutex.
-const unsigned __tsan_mutex_recursive_lock   = 1 << 6;
+static const unsigned __tsan_mutex_recursive_lock   = 1 << 6;
 // Denotes that the unlock operation releases all recursion levels.
 // Number of released levels is returned and later must be passed to
 // the corresponding __tsan_mutex_post_lock annotation.
-const unsigned __tsan_mutex_recursive_unlock = 1 << 7;
+static const unsigned __tsan_mutex_recursive_unlock = 1 << 7;
 
 // Annotate creation of a mutex.
 // Supported flags: mutex creation flags.
@@ -152,7 +152,7 @@ void __tsan_set_fiber_name(void *fiber, const char *name);
 
 // Flags for __tsan_switch_to_fiber:
 // Do not establish a happens-before relation between fibers
-const unsigned __tsan_switch_to_fiber_no_sync = 1 << 0;
+static const unsigned __tsan_switch_to_fiber_no_sync = 1 << 0;
 
 #ifdef __cplusplus
 }  // extern "C"