[crt][fuzzer] Fix up various numeric conversions

[aarongreen]

Summary

Attempting to build a standalone libFuzzer in Fuchsia's default toolchain for the purpose of cross-compiling the unit tests revealed a number of not-quite-proper type conversions. Fuchsia's toolchain include -std=c++17 and -Werror, among others, leading to many errors like -Wshorten-64-to-32, -Wimplicit-float-conversion, etc.

Most of these have been addressed by simply making the conversion explicit with a static_cast. These typically fell into one of two categories: 1) conversions between types where high precision isn't critical, e.g. the "energy" calculations for InputInfo, and 2) conversions where the values will never reach the bits being truncated, e.g. DftTimeInSeconds is not going to exceed 136 years.

The major exception to this is the number of features: there are several places that treat features as size_t, and others as uint32_t. This change makes the decision to cap the features at 32 bits. The maximum value of a feature as produced by TracePC::CollectFeatures is roughly:

(NumPCsInPCTables + ValueBitMap::kMapSizeInBits + ExtraCountersBegin() - ExtraCountersEnd() + log2(SIZE_MAX)) * 8

It's conceivable for extremely large targets and/or extra counters that this limit could be reached. This shouldn't break fuzzing, but it will cause certain features to collide and lower the fuzzers overall precision. To address this, this change adds a warning to TracePC::PrintModuleInfo about excessive feature size if it is detected, and recommends refactoring the fuzzer into several smaller ones.

[charco]

LGTM, but someone else must approve

compiler-rt/lib/fuzzer/FuzzerCorpus.h

81–82

Do we really need long doubles here (and throughout this function)? Can we just use log?

[aarongreen]

compiler-rt/lib/fuzzer/FuzzerDictionary.h

29

I spent to much time in std=c++17... I need a message here.

[aarongreen]

Added a comment to the static_assert to make it -std=c++11 compatible.

[aarongreen]

compiler-rt/lib/fuzzer/FuzzerCorpus.h

81–82

I'm not certain. If neither kcc nor morehouse object, I'm completely open to running the tests with that modification and comparing the result.

[morehouse]

compiler-rt/lib/fuzzer/FuzzerCorpus.h

81–82

If tests pass with log, I'd prefer to just use that for simpler code.

compiler-rt/lib/fuzzer/FuzzerDataFlowTrace.h

72

Unintentional indent? Please remove.

[aarongreen]

Changed SumIncidence's type to double to reduce a lot of superfluous static_casting back a forth.

[aarongreen]

Fixed indent added by clang-format.

compiler-rt/lib/fuzzer/FuzzerDataFlowTrace.h

72

It seems the single space indent on the "public" keyword was throwing off clang-format.

compiler-rt/lib/fuzzer/FuzzerBuiltins.h

 namespace fuzzer {
 
 inline uint8_t  Bswap(uint8_t x)  { return x; }
 inline uint16_t Bswap(uint16_t x) { return __builtin_bswap16(x); }
 inline uint32_t Bswap(uint32_t x) { return __builtin_bswap32(x); }
 inline uint64_t Bswap(uint64_t x) { return __builtin_bswap64(x); }
 
 inline uint32_t Clzll(unsigned long long X) { return __builtin_clzll(X); }
-inline uint32_t Clz(unsigned long long X) { return __builtin_clz(X); }
 inline int Popcountll(unsigned long long X) { return __builtin_popcountll(X); }
 
 }  // namespace fuzzer
 
 #endif  // !LIBFUZZER_MSVC
 #endif  // LLVM_FUZZER_BUILTINS_H

compiler-rt/lib/fuzzer/FuzzerBuiltinsMsvc.h

if (_BitScanReverse(&LeadZeroIdx, static_cast<unsigned long>(X)))
     return static_cast<int>(63 - LeadZeroIdx);
 
 #else
   if (_BitScanReverse64(&LeadZeroIdx, X)) return 63 - LeadZeroIdx;
 #endif
   return 64;
 }
 
-inline uint32_t Clz(uint32_t X) {
-  unsigned long LeadZeroIdx = 0;
-  if (_BitScanReverse(&LeadZeroIdx, X)) return 31 - LeadZeroIdx;
-  return 32;
-}
-
 inline int Popcountll(unsigned long long X) {
 #if !defined(_M_ARM) && !defined(_M_X64)
   return __popcnt(X) + __popcnt(X >> 32);
 #else
   return __popcnt64(X);
 #endif
 }
 
 }  // namespace fuzzer
 
 #endif  // LIBFUZER_MSVC
 #endif  // LLVM_FUZZER_BUILTINS_MSVC_H

compiler-rt/lib/fuzzer/FuzzerCorpus.h

struct InputInfo {
   bool MayDeleteFile = false;
   bool Reduced = false;
   bool HasFocusFunction = false;
   Vector<uint32_t> UniqFeatureSet;
   Vector<uint8_t> DataFlowTraceForFocusFunction;
   // Power schedule.
   bool NeedsEnergyUpdate = false;
   double Energy = 0.0;
-  size_t SumIncidence = 0;
+  double SumIncidence = 0.0;
   Vector<std::pair<uint32_t, uint16_t>> FeatureFreqs;
 
   // Delete feature Idx and its frequency from FeatureFreqs.
   bool DeleteFeatureFreq(uint32_t Idx) {
     if (FeatureFreqs.empty())
       return false;
 
     // Binary search over local feature frequencies sorted by index.
struct InputInfo {
   // executed we assign fresh seeds maximum entropy and let II->Energy approach
   // the true entropy from above. If ScalePerExecTime is true, the computed
   // entropy is scaled based on how fast this input executes compared to the
   // average execution time of inputs. The faster an input executes, the more
   // energy gets assigned to the input.
   void UpdateEnergy(size_t GlobalNumberOfFeatures, bool ScalePerExecTime,
                     std::chrono::microseconds AverageUnitExecutionTime) {
     Energy = 0.0;
-    SumIncidence = 0;
+    SumIncidence = 0.0;
 
     // Apply add-one smoothing to locally discovered features.
     for (auto F : FeatureFreqs) {
-      size_t LocalIncidence = F.second + 1;
-      Energy -= LocalIncidence * logl(LocalIncidence);
+      double LocalIncidence = F.second + 1;
+      Energy -= LocalIncidence * log(LocalIncidence);
       SumIncidence += LocalIncidence;
     }
 
     // Apply add-one smoothing to locally undiscovered features.
-    //   PreciseEnergy -= 0; // since logl(1.0) == 0)
-    SumIncidence += (GlobalNumberOfFeatures - FeatureFreqs.size());
+    //   PreciseEnergy -= 0; // since log(1.0) == 0)
+    SumIncidence +=
+        static_cast<double>(GlobalNumberOfFeatures - FeatureFreqs.size());
 
     // Add a single locally abundant feature apply add-one smoothing.
-    size_t AbdIncidence = NumExecutedMutations + 1;
-    Energy -= AbdIncidence * logl(AbdIncidence);
+    double AbdIncidence = static_cast<double>(NumExecutedMutations + 1);
+    Energy -= AbdIncidence * log(AbdIncidence);
     SumIncidence += AbdIncidence;
 
     // Normalize.
     if (SumIncidence != 0)
-      Energy = (Energy / SumIncidence) + logl(SumIncidence);
+      Energy = Energy / SumIncidence + log(SumIncidence);
 
     if (ScalePerExecTime) {
       // Scaling to favor inputs with lower execution time.
       uint32_t PerfScore = 100;
       if (TimeOfUnit.count() > AverageUnitExecutionTime.count() * 10)
         PerfScore = 10;
       else if (TimeOfUnit.count() > AverageUnitExecutionTime.count() * 4)
         PerfScore = 25;
public:
   InputInfo *AddToCorpus(const Unit &U, size_t NumFeatures, bool MayDeleteFile,
                          bool HasFocusFunction, bool NeverReduce,
                          std::chrono::microseconds TimeOfUnit,
                          const Vector<uint32_t> &FeatureSet,
                          const DataFlowTrace &DFT, const InputInfo *BaseII) {
     assert(!U.empty());
     if (FeatureDebug)
       Printf("ADD_TO_CORPUS %zd NF %zd\n", Inputs.size(), NumFeatures);
+    // Inputs.size() is cast to uint32_t below.
+    assert(Inputs.size() < std::numeric_limits<uint32_t>::max());
     Inputs.push_back(new InputInfo());
     InputInfo &II = *Inputs.back();
     II.U = U;
     II.NumFeatures = NumFeatures;
     II.NeverReduce = NeverReduce;
     II.TimeOfUnit = TimeOfUnit;
     II.MayDeleteFile = MayDeleteFile;
     II.UniqFeatureSet = FeatureSet;
     II.HasFocusFunction = HasFocusFunction;
     // Assign maximal energy to the new seed.
     II.Energy = RareFeatures.empty() ? 1.0 : log(RareFeatures.size());
-    II.SumIncidence = RareFeatures.size();
+    II.SumIncidence = static_cast<double>(RareFeatures.size());
     II.NeedsEnergyUpdate = false;
     std::sort(II.UniqFeatureSet.begin(), II.UniqFeatureSet.end());
     ComputeSHA1(U.data(), U.size(), II.Sha1);
     auto Sha1Str = Sha1ToString(II.Sha1);
     Hashes.insert(Sha1Str);
     if (HasFocusFunction)
       if (auto V = DFT.Get(Sha1Str))
         II.DataFlowTraceForFocusFunction = *V;
void AddRareFeature(uint32_t Idx) {
     GlobalFeatureFreqs[Idx] = 0;
     for (auto II : Inputs) {
       II->DeleteFeatureFreq(Idx);
 
       // Apply add-one smoothing to this locally undiscovered feature.
       // Zero energy seeds will never be fuzzed and remain zero energy.
       if (II->Energy > 0.0) {
         II->SumIncidence += 1;
-        II->Energy += logl(II->SumIncidence) / II->SumIncidence;
+        II->Energy += log(II->SumIncidence) / II->SumIncidence;
       }
     }
 
     DistributionNeedsUpdate = true;
   }
 
   bool AddFeature(size_t Idx, uint32_t NewSize, bool Shrink) {
     assert(NewSize);
if (OldSize == 0 || (Shrink && OldSize > NewSize)) {
       } else {
         NumAddedFeatures++;
         if (Entropic.Enabled)
           AddRareFeature((uint32_t)Idx);
       }
       NumUpdatedFeatures++;
       if (FeatureDebug)
         Printf("ADD FEATURE %zd sz %d\n", Idx, NewSize);
-      SmallestElementPerFeature[Idx] = Inputs.size();
+      // Inputs.size() is guaranteed to be less than UINT32_MAX by AddToCorpus.
+      SmallestElementPerFeature[Idx] = static_cast<uint32_t>(Inputs.size());
       InputSizesPerFeature[Idx] = NewSize;
       return true;
     }
     return false;
   }
 
   // Increment frequency of feature Idx globally and locally.
   void UpdateFeatureFrequency(InputInfo *II, size_t Idx) {
public:
 
   size_t NumFeatures() const { return NumAddedFeatures; }
   size_t NumFeatureUpdates() const { return NumUpdatedFeatures; }
 
 private:
 
   static const bool FeatureDebug = false;
 
-  size_t GetFeature(size_t Idx) const { return InputSizesPerFeature[Idx]; }
+  uint32_t GetFeature(size_t Idx) const { return InputSizesPerFeature[Idx]; }
 
   void ValidateFeatureSet() {
     if (FeatureDebug)
       PrintFeatureSet();
     for (size_t Idx = 0; Idx < kFeatureSetSize; Idx++)
       if (GetFeature(Idx))
         Inputs[SmallestElementPerFeature[Idx]]->Tmp++;
     for (auto II: Inputs) {
if (Entropic.Enabled) {
         // If energy for all seeds is zero, fall back to vanilla schedule.
         if (Weights[i] > 0.0)
           VanillaSchedule = false;
       }
     }
 
     if (VanillaSchedule) {
       for (size_t i = 0; i < N; i++)
-        Weights[i] = Inputs[i]->NumFeatures
-                         ? (i + 1) * (Inputs[i]->HasFocusFunction ? 1000 : 1)
-                         : 0.;
+        Weights[i] =
+            Inputs[i]->NumFeatures
+                ? static_cast<double>((i + 1) *
+                                      (Inputs[i]->HasFocusFunction ? 1000 : 1))
     }
 
     if (FeatureDebug) {
       for (size_t i = 0; i < N; i++)
         Printf("%zd ", Inputs[i]->NumFeatures);
       Printf("SCORE\n");
       for (size_t i = 0; i < N; i++)
         Printf("%f ", Weights[i]);

compiler-rt/lib/fuzzer/FuzzerDataFlowTrace.h

 #include <string>
 
 namespace fuzzer {
 
 int CollectDataFlow(const std::string &DFTBinary, const std::string &DirPath,
                     const Vector<SizedFile> &CorporaFiles);
 
 class BlockCoverage {
- public:
+  // These functions guarantee no CoverageVector is longer than UINT32_MAX.
   bool AppendCoverage(std::istream &IN);
   bool AppendCoverage(const std::string &S);
 
   size_t NumCoveredFunctions() const { return Functions.size(); }
 
   uint32_t GetCounter(size_t FunctionId, size_t BasicBlockId) {
     auto It = Functions.find(FunctionId);
-    if (It == Functions.end()) return 0;
+    if (It == Functions.end())
+      return 0;
     const auto &Counters = It->second;
     if (BasicBlockId < Counters.size())
       return Counters[BasicBlockId];
     return 0;
   }
 
   uint32_t GetNumberOfBlocks(size_t FunctionId) {
     auto It = Functions.find(FunctionId);
     if (It == Functions.end()) return 0;
     const auto &Counters = It->second;
-    return Counters.size();
+    return static_cast<uint32_t>(Counters.size());
   }
 
   uint32_t GetNumberOfCoveredBlocks(size_t FunctionId) {
     auto It = Functions.find(FunctionId);
     if (It == Functions.end()) return 0;
     const auto &Counters = It->second;
     uint32_t Result = 0;
     for (auto Cnt: Counters)
       if (Cnt)
         Result++;
     return Result;
   }
 
   Vector<double> FunctionWeights(size_t NumFunctions) const;
   void clear() { Functions.clear(); }
 
- private:
-
   typedef Vector<uint32_t> CoverageVector;
 
   uint32_t NumberOfCoveredBlocks(const CoverageVector &Counters) const {
     uint32_t Res = 0;
     for (auto Cnt : Counters)
       if (Cnt)
         Res++;
     return Res;
   }
 
   uint32_t NumberOfUncoveredBlocks(const CoverageVector &Counters) const {
-    return Counters.size() - NumberOfCoveredBlocks(Counters);
+    return static_cast<uint32_t>(Counters.size()) -
+           NumberOfCoveredBlocks(Counters);
   }
 
   uint32_t SmallestNonZeroCounter(const CoverageVector &Counters) const {
     assert(!Counters.empty());
     uint32_t Res = Counters[0];
     for (auto Cnt : Counters)
       if (Cnt)
         Res = Min(Res, Cnt);

compiler-rt/lib/fuzzer/FuzzerDataFlowTrace.cpp

while (std::getline(IN, L, '\n')) {
     Vector<uint32_t> CoveredBlocks;
     while (true) {
       uint32_t BB = 0;
       SS >> BB;
       if (!SS) break;
       CoveredBlocks.push_back(BB);
     }
     if (CoveredBlocks.empty()) return false;
+    // Ensures no CoverageVector is longer than UINT32_MAX.
     uint32_t NumBlocks = CoveredBlocks.back();
     CoveredBlocks.pop_back();
     for (auto BB : CoveredBlocks)
       if (BB >= NumBlocks) return false;
     auto It = Functions.find(FunctionId);
     auto &Counters =
         It == Functions.end()
             ? Functions.insert({FunctionId, Vector<uint32_t>(NumBlocks)})
if (*FocusFunction == "auto") {
     auto Distribution = std::piecewise_constant_distribution<double>(
         Intervals.begin(), Intervals.end(), Weights.begin());
     FocusFuncIdx = static_cast<size_t>(Distribution(Rand));
     *FocusFunction = FunctionNames[FocusFuncIdx];
     assert(FocusFuncIdx < NumFunctions);
     Printf("INFO: AUTOFOCUS: %zd %s\n", FocusFuncIdx,
            FunctionNames[FocusFuncIdx].c_str());
     for (size_t i = 0; i < NumFunctions; i++) {
-      if (!Weights[i]) continue;
+      if (Weights[i] == 0.0)
+        continue;
       Printf("  [%zd] W %g\tBB-tot %u\tBB-cov %u\tEntryFreq %u:\t%s\n", i,
              Weights[i], Coverage.GetNumberOfBlocks(i),
              Coverage.GetNumberOfCoveredBlocks(i), Coverage.GetCounter(i, 0),
              FunctionNames[i].c_str());
     }
   }
 
   if (!NumFunctions || FocusFuncIdx == SIZE_MAX || Files.size() <= 1)

compiler-rt/lib/fuzzer/FuzzerDictionary.h

 #include <limits>
 
 namespace fuzzer {
 // A simple POD sized array of bytes.
 template <size_t kMaxSizeT> class FixedWord {
 public:
   static const size_t kMaxSize = kMaxSizeT;
   FixedWord() {}
-  FixedWord(const uint8_t *B, uint8_t S) { Set(B, S); }
+  FixedWord(const uint8_t *B, size_t S) { Set(B, S); }
 
-  void Set(const uint8_t *B, uint8_t S) {
+  void Set(const uint8_t *B, size_t S) {
+    static_assert(kMaxSizeT <= std::numeric_limits<uint8_t>::max(),
+                  "FixedWord::kMaxSizeT cannot fit in a uint8_t.");
     assert(S <= kMaxSize);
     memcpy(Data, B, S);
-    Size = S;
+    Size = static_cast<uint8_t>(S);
   }
 
   bool operator==(const FixedWord<kMaxSize> &w) const {
     return Size == w.Size && 0 == memcmp(Data, w.Data, Size);
   }
 
   static size_t GetMaxSize() { return kMaxSize; }
   const uint8_t *data() const { return Data; }

compiler-rt/lib/fuzzer/FuzzerDriver.cpp

for (size_t F = 0; F < kNumFlags; F++)
         Printf("WARNING: did you mean '%s' (single dash)?\n", Param + 1);
     return true;
   }
   for (size_t F = 0; F < kNumFlags; F++) {
     const char *Name = FlagDescriptions[F].Name;
     const char *Str = FlagValue(Param, Name);
     if (Str)  {
       if (FlagDescriptions[F].IntFlag) {
-        int Val = MyStol(Str);
-        *FlagDescriptions[F].IntFlag = Val;
+        auto Val = MyStol(Str);
+        *FlagDescriptions[F].IntFlag = static_cast<int>(Val);
         if (Flags.verbosity >= 2)
           Printf("Flag: %s %d\n", Name, Val);
         return true;
       } else if (FlagDescriptions[F].UIntFlag) {
-        unsigned int Val = std::stoul(Str);
-        *FlagDescriptions[F].UIntFlag = Val;
+        auto Val = std::stoul(Str);
+        *FlagDescriptions[F].UIntFlag = static_cast<unsigned int>(Val);
         if (Flags.verbosity >= 2)
           Printf("Flag: %s %u\n", Name, Val);
         return true;
       } else if (FlagDescriptions[F].StrFlag) {
         *FlagDescriptions[F].StrFlag = Str;
         if (Flags.verbosity >= 2)
           Printf("Flag: %s %s\n", Name, Str);
         return true;
int FuzzerDriver(int *argc, char ***argv, UserCallback Callback) {
   Entropic.FeatureFrequencyThreshold =
       Options.EntropicFeatureFrequencyThreshold;
   Entropic.NumberOfRarestFeatures = Options.EntropicNumberOfRarestFeatures;
   Entropic.ScalePerExecTime = Options.EntropicScalePerExecTime;
 
   unsigned Seed = Flags.seed;
   // Initialize Seed.
   if (Seed == 0)
-    Seed =
-        std::chrono::system_clock::now().time_since_epoch().count() + GetPid();
+    Seed = static_cast<unsigned>(
+        std::chrono::system_clock::now().time_since_epoch().count() + GetPid());
   if (Flags.verbosity)
     Printf("INFO: Seed: %u\n", Seed);
 
   if (Flags.collect_data_flow && !Flags.fork && !Flags.merge) {
     if (RunIndividualFiles)
       return CollectDataFlow(Flags.collect_data_flow, Flags.data_flow_trace,
                         ReadCorpora({}, *Inputs));
     else

compiler-rt/lib/fuzzer/FuzzerFork.cpp

if (size_t CorpusSubsetSize =
             std::min(Files.size(), (size_t)sqrt(Files.size() + 2))) {
       auto Time1 = std::chrono::system_clock::now();
       for (size_t i = 0; i < CorpusSubsetSize; i++) {
         auto &SF = Files[Rand->SkewTowardsLast(Files.size())];
         Seeds += (Seeds.empty() ? "" : ",") + SF;
         CollectDFT(SF);
       }
       auto Time2 = std::chrono::system_clock::now();
-      Job->DftTimeInSeconds = duration_cast<seconds>(Time2 - Time1).count();
+      auto DftTimeInSeconds = duration_cast<seconds>(Time2 - Time1).count();
+      assert(DftTimeInSeconds < std::numeric_limits<int>::max());
+      Job->DftTimeInSeconds = static_cast<int>(DftTimeInSeconds);
     }
     if (!Seeds.empty()) {
       Job->SeedListPath =
           DirPlusFile(TempDir, std::to_string(JobId) + ".seeds");
       WriteToFile(Seeds, Job->SeedListPath);
       Cmd.addFlag("seed_inputs", "@" + Job->SeedListPath);
     }
     Job->LogPath = DirPlusFile(TempDir, std::to_string(JobId) + ".log");

compiler-rt/lib/fuzzer/FuzzerLoop.cpp

 }
 
 void Fuzzer::PrintPulseAndReportSlowInput(const uint8_t *Data, size_t Size) {
   auto TimeOfUnit =
       duration_cast<seconds>(UnitStopTime - UnitStartTime).count();
   if (!(TotalNumberOfRuns & (TotalNumberOfRuns - 1)) &&
       secondsSinceProcessStartUp() >= 2)
     PrintStats("pulse ");
-  if (TimeOfUnit > TimeOfLongestUnitInSeconds * 1.1 &&
-      TimeOfUnit >= Options.ReportSlowUnits) {
+  auto Threshhold =
+      static_cast<long>(static_cast<double>(TimeOfLongestUnitInSeconds) * 1.1);
+  if (TimeOfUnit > Threshhold && TimeOfUnit >= Options.ReportSlowUnits) {
     TimeOfLongestUnitInSeconds = TimeOfUnit;
     Printf("Slowest unit: %zd s:\n", TimeOfLongestUnitInSeconds);
     WriteUnitToFileWithPrefix({Data, Data + Size}, "slow-unit-");
   }
 }
 
 static void WriteFeatureSetToFile(const std::string &FeaturesDir,
                                   const std::string &FileName,
static void WriteEdgeToMutationGraphFile(const std::string &MutationGraphFile,
   AppendToFile(OutputString, MutationGraphFile);
 }
 
 bool Fuzzer::RunOne(const uint8_t *Data, size_t Size, bool MayDeleteFile,
                     InputInfo *II, bool ForceAddToCorpus,
                     bool *FoundUniqFeatures) {
   if (!Size)
     return false;
+  // Largest input length should be INT_MAX.
+  assert(Size < std::numeric_limits<uint32_t>::max());
 
   ExecuteCallback(Data, Size);
   auto TimeOfUnit = duration_cast<microseconds>(UnitStopTime - UnitStartTime);
 
   UniqFeatureSetTmp.clear();
   size_t FoundUniqFeaturesOfII = 0;
   size_t NumUpdatesBefore = Corpus.NumFeatureUpdates();
-  TPC.CollectFeatures([&](size_t Feature) {
-    if (Corpus.AddFeature(Feature, Size, Options.Shrink))
+  TPC.CollectFeatures([&](uint32_t Feature) {
+    if (Corpus.AddFeature(Feature, static_cast<uint32_t>(Size), Options.Shrink))
       UniqFeatureSetTmp.push_back(Feature);
     if (Options.Entropic)
       Corpus.UpdateFeatureFrequency(II, Feature);
     if (Options.ReduceInputs && II && !II->NeverReduce)
       if (std::binary_search(II->UniqFeatureSet.begin(),
                              II->UniqFeatureSet.end(), Feature))
         FoundUniqFeaturesOfII++;
   });

compiler-rt/lib/fuzzer/FuzzerMerge.cpp

bool Merger::Parse(std::istream &IS, bool ParseCoverage) {
   size_t ExpectedStartMarker = 0;
   const size_t kInvalidStartMarker = -1;
   size_t LastSeenStartMarker = kInvalidStartMarker;
   Vector<uint32_t> TmpFeatures;
   Set<uint32_t> PCs;
   while (std::getline(IS, Line, '\n')) {
     std::istringstream ISS1(Line);
     std::string Marker;
-    size_t N;
-    ISS1 >> Marker;
-    ISS1 >> N;
+    uint32_t N;
+    if (!(ISS1 >> Marker) || !(ISS1 >> N))
+      return false;
     if (Marker == "STARTED") {
       // STARTED FILE_ID FILE_SIZE
       if (ExpectedStartMarker != N)
         return false;
       ISS1 >> Files[ExpectedStartMarker].Size;
       LastSeenStartMarker = ExpectedStartMarker;
       assert(ExpectedStartMarker < Files.size());
       ExpectedStartMarker++;

compiler-rt/lib/fuzzer/FuzzerMutate.cpp

else
     Mutators = DefaultMutators;
 
   if (EF->LLVMFuzzerCustomCrossOver)
     Mutators.push_back(
         {&MutationDispatcher::Mutate_CustomCrossOver, "CustomCrossOver"});
 }
 
 static char RandCh(Random &Rand) {
-  if (Rand.RandBool()) return Rand(256);
+  if (Rand.RandBool())
+    return static_cast<char>(Rand(256));
   const char Special[] = "!*'();:@&=+$,/?%#[]012Az-`~.\xff\x00";
   return Special[Rand(sizeof(Special) - 1)];
 }
 
 size_t MutationDispatcher::Mutate_Custom(uint8_t *Data, size_t Size,
                                          size_t MaxSize) {
-  return EF->LLVMFuzzerCustomMutator(Data, Size, MaxSize, Rand.Rand());
+  return EF->LLVMFuzzerCustomMutator(Data, Size, MaxSize,
+                                     Rand.Rand<unsigned int>());
 }
 
 size_t MutationDispatcher::Mutate_CustomCrossOver(uint8_t *Data, size_t Size,
                                                   size_t MaxSize) {
   if (Size == 0)
     return 0;
   if (!CrossOverWith) return 0;
   const Unit &Other = *CrossOverWith;
   if (Other.empty())
     return 0;
   CustomCrossOverInPlaceHere.resize(MaxSize);
   auto &U = CustomCrossOverInPlaceHere;
   size_t NewSize = EF->LLVMFuzzerCustomCrossOver(
-      Data, Size, Other.data(), Other.size(), U.data(), U.size(), Rand.Rand());
+      Data, Size, Other.data(), Other.size(), U.data(), U.size(),
+      Rand.Rand<unsigned int>());
   if (!NewSize)
     return 0;
   assert(NewSize <= MaxSize && "CustomCrossOver returned overisized unit");
   memcpy(Data, U.data(), NewSize);
   return NewSize;
 }
 
 size_t MutationDispatcher::Mutate_ShuffleBytes(uint8_t *Data, size_t Size,
size_t MutationDispatcher::Mutate_InsertRepeatedBytes(uint8_t *Data,
   if (Size + kMinBytesToInsert >= MaxSize) return 0;
   size_t MaxBytesToInsert = std::min(MaxSize - Size, (size_t)128);
   size_t N = Rand(MaxBytesToInsert - kMinBytesToInsert + 1) + kMinBytesToInsert;
   assert(Size + N <= MaxSize && N);
   size_t Idx = Rand(Size + 1);
   // Insert new values at Data[Idx].
   memmove(Data + Idx + N, Data + Idx, Size - Idx);
   // Give preference to 0x00 and 0xff.
-  uint8_t Byte = Rand.RandBool() ? Rand(256) : (Rand.RandBool() ? 0 : 255);
+  uint8_t Byte = static_cast<uint8_t>(
+      Rand.RandBool() ? Rand(256) : (Rand.RandBool() ? 0 : 255));
   for (size_t i = 0; i < N; i++)
     Data[Idx + i] = Byte;
   return Size + N;
 }
 
 size_t MutationDispatcher::Mutate_ChangeByte(uint8_t *Data, size_t Size,
                                              size_t MaxSize) {
   if (Size > MaxSize) return 0;

 }
 
 
 template <class T>
 DictionaryEntry MutationDispatcher::MakeDictionaryEntryFromCMP(
     T Arg1, T Arg2, const uint8_t *Data, size_t Size) {
   if (Rand.RandBool()) Arg1 = Bswap(Arg1);
   if (Rand.RandBool()) Arg2 = Bswap(Arg2);
-  T Arg1Mutation = Arg1 + Rand(-1, 1);
-  T Arg2Mutation = Arg2 + Rand(-1, 1);
+  T Arg1Mutation = static_cast<T>(Arg1 + Rand(-1, 1));
+  T Arg2Mutation = static_cast<T>(Arg2 + Rand(-1, 1));
   return MakeDictionaryEntryFromCMP(&Arg1, &Arg2, &Arg1Mutation, &Arg2Mutation,
                                     sizeof(Arg1), Data, Size);
 }
 
 DictionaryEntry MutationDispatcher::MakeDictionaryEntryFromCMP(
     const Word &Arg1, const Word &Arg2, const uint8_t *Data, size_t Size) {
   return MakeDictionaryEntryFromCMP(Arg1.data(), Arg2.data(), Arg1.data(),
                                     Arg2.data(), Arg1.size(), Data, Size);
 }
 
 size_t MutationDispatcher::Mutate_AddWordFromTORC(
     uint8_t *Data, size_t Size, size_t MaxSize) {
   Word W;
   DictionaryEntry DE;
   switch (Rand(4)) {
   case 0: {
-    auto X = TPC.TORC8.Get(Rand.Rand());
+    auto X = TPC.TORC8.Get(Rand.Rand<size_t>());
     DE = MakeDictionaryEntryFromCMP(X.A, X.B, Data, Size);
   } break;
   case 1: {
-    auto X = TPC.TORC4.Get(Rand.Rand());
+    auto X = TPC.TORC4.Get(Rand.Rand<size_t>());
     if ((X.A >> 16) == 0 && (X.B >> 16) == 0 && Rand.RandBool())
       DE = MakeDictionaryEntryFromCMP((uint16_t)X.A, (uint16_t)X.B, Data, Size);
     else
       DE = MakeDictionaryEntryFromCMP(X.A, X.B, Data, Size);
   } break;
   case 2: {
-    auto X = TPC.TORCW.Get(Rand.Rand());
+    auto X = TPC.TORCW.Get(Rand.Rand<size_t>());
     DE = MakeDictionaryEntryFromCMP(X.A, X.B, Data, Size);
   } break;
   case 3: if (Options.UseMemmem) {
-    auto X = TPC.MMT.Get(Rand.Rand());
+      auto X = TPC.MMT.Get(Rand.Rand<size_t>());
       DE = DictionaryEntry(X);
   } break;
   default:
     assert(0);
   }
   if (!DE.GetW().size()) return 0;
   Size = ApplyDictionaryEntry(Data, Size, MaxSize, DE);
   if (!Size) return 0;
   DictionaryEntry &DERef =

 
 template<class T>
 size_t ChangeBinaryInteger(uint8_t *Data, size_t Size, Random &Rand) {
   if (Size < sizeof(T)) return 0;
   size_t Off = Rand(Size - sizeof(T) + 1);
   assert(Off + sizeof(T) <= Size);
   T Val;
   if (Off < 64 && !Rand(4)) {
-    Val = Size;
+    Val = static_cast<T>(Size);
     if (Rand.RandBool())
       Val = Bswap(Val);
   } else {
     memcpy(&Val, Data + Off, sizeof(Val));
-    T Add = Rand(21);
+    T Add = static_cast<T>(Rand(21));
     Add -= 10;
     if (Rand.RandBool())
       Val = Bswap(T(Bswap(Val) + Add)); // Add assuming different endiannes.
     else
       Val = Val + Add;               // Add assuming current endiannes.
     if (Add == 0 || Rand.RandBool()) // Maybe negate.
       Val = -Val;
   }

compiler-rt/lib/fuzzer/FuzzerRandom.h

 
 #include <random>
 
 namespace fuzzer {
 class Random : public std::minstd_rand {
  public:
   Random(unsigned int seed) : std::minstd_rand(seed) {}
   result_type operator()() { return this->std::minstd_rand::operator()(); }
-  size_t Rand() { return this->operator()(); }
-  size_t RandBool() { return Rand() % 2; }
+  template <typename T>
+  typename std::enable_if<std::is_integral<T>::value, T>::type Rand() {
+    return static_cast<T>(this->operator()());
+  }
+  size_t RandBool() { return this->operator()() % 2; }
   size_t SkewTowardsLast(size_t n) {
     size_t T = this->operator()(n * n);
-    size_t Res = sqrt(T);
+    size_t Res = static_cast<size_t>(sqrt(T));
     return Res;
   }
-  size_t operator()(size_t n) { return n ? Rand() % n : 0; }
-  intptr_t operator()(intptr_t From, intptr_t To) {
+  template <typename T>
+  typename std::enable_if<std::is_integral<T>::value, T>::type operator()(T n) {
+    return n ? Rand<T>() % n : 0;
+  }
+  template <typename T>
+  typename std::enable_if<std::is_integral<T>::value, T>::type
+  operator()(T From, T To) {
     assert(From < To);
-    intptr_t RangeSize = To - From + 1;
-    return operator()(RangeSize) + From;
+    auto RangeSize = static_cast<unsigned long long>(To) -
+                     static_cast<unsigned long long>(From) + 1;
+    return static_cast<T>(this->operator()(RangeSize) + From);
   }
 };
 
 }  // namespace fuzzer
 
 #endif  // LLVM_FUZZER_RANDOM_H

compiler-rt/lib/fuzzer/FuzzerSHA1.cpp

void sha1_hashBlock(sha1nfo *s) {
   }
   s->state[0] += a;
   s->state[1] += b;
   s->state[2] += c;
   s->state[3] += d;
   s->state[4] += e;
 }
 
-void sha1_addUncounted(sha1nfo *s, uint8_t data) {
-  uint8_t * const b = (uint8_t*) s->buffer;
+// Adds the least significant byte of |data|.
+void sha1_addUncounted(sha1nfo *s, uint32_t data) {
+  uint8_t *const b = (uint8_t *)s->buffer;
 #ifdef SHA_BIG_ENDIAN
-  b[s->bufferOffset] = data;
+  b[s->bufferOffset] = static_cast<uint8_t>(data);
 #else
-  b[s->bufferOffset ^ 3] = data;
+  b[s->bufferOffset ^ 3] = static_cast<uint8_t>(data);
 #endif
   s->bufferOffset++;
   if (s->bufferOffset == BLOCK_LENGTH) {
     sha1_hashBlock(s);
     s->bufferOffset = 0;
   }
 }
 

compiler-rt/lib/fuzzer/FuzzerTracePC.h

public:
   void HandleCallerCallee(uintptr_t Caller, uintptr_t Callee);
   template <class T> void HandleCmp(uintptr_t PC, T Arg1, T Arg2);
   size_t GetTotalPCCoverage();
   void SetUseCounters(bool UC) { UseCounters = UC; }
   void SetUseValueProfileMask(uint32_t VPMask) { UseValueProfileMask = VPMask; }
   void SetPrintNewPCs(bool P) { DoPrintNewPCs = P; }
   void SetPrintNewFuncs(size_t P) { NumPrintNewFuncs = P; }
   void UpdateObservedPCs();
-  template <class Callback> void CollectFeatures(Callback CB) const;
+  template <class Callback> size_t CollectFeatures(Callback CB) const;
 
   void ResetMaps() {
     ValueProfileMap.Reset();
     ClearExtraCounters();
     ClearInlineCounters();
   }
 
   void ClearInlineCounters();
unsigned CounterToFeature(T Counter) {
     else if (Counter >= 16) Bit = 5;
     else if (Counter >= 8) Bit = 4;
     else if (Counter >= 4) Bit = 3;
     else if (Counter >= 3) Bit = 2;
     else if (Counter >= 2) Bit = 1;
     return Bit;
 }
 
-template <class Callback>  // void Callback(size_t Feature)
-ATTRIBUTE_NO_SANITIZE_ADDRESS
-ATTRIBUTE_NOINLINE
-void TracePC::CollectFeatures(Callback HandleFeature) const {
+template <class Callback> // void Callback(uint32_t Feature)
+ATTRIBUTE_NO_SANITIZE_ADDRESS ATTRIBUTE_NOINLINE size_t
+TracePC::CollectFeatures(Callback HandleFeature) const {
   auto Handle8bitCounter = [&](size_t FirstFeature,
                                size_t Idx, uint8_t Counter) {
     if (UseCounters)
-      HandleFeature(FirstFeature + Idx * 8 + CounterToFeature(Counter));
+      HandleFeature(static_cast<uint32_t>(FirstFeature + Idx * 8 +
+                                          CounterToFeature(Counter)));
     else
-      HandleFeature(FirstFeature + Idx);
+      HandleFeature(static_cast<uint32_t>(FirstFeature + Idx));
   };
 
   size_t FirstFeature = 0;
 
   for (size_t i = 0; i < NumModules; i++) {
     for (size_t r = 0; r < Modules[i].NumRegions; r++) {
       if (!Modules[i].Regions[r].Enabled) continue;
       FirstFeature += 8 * ForEachNonZeroByte(Modules[i].Regions[r].Start,
                                              Modules[i].Regions[r].Stop,
                                              FirstFeature, Handle8bitCounter);
     }
   }
 
   FirstFeature +=
       8 * ForEachNonZeroByte(ExtraCountersBegin(), ExtraCountersEnd(),
                              FirstFeature, Handle8bitCounter);
 
   if (UseValueProfileMask) {
     ValueProfileMap.ForEach([&](size_t Idx) {
-      HandleFeature(FirstFeature + Idx);
+      HandleFeature(static_cast<uint32_t>(FirstFeature + Idx));
     });
     FirstFeature += ValueProfileMap.SizeInBits();
   }
 
   // Step function, grows similar to 8 * Log_2(A).
-  auto StackDepthStepFunction = [](uint32_t A) -> uint32_t {
-    if (!A) return A;
-    uint32_t Log2 = Log(A);
-    if (Log2 < 3) return A;
+  auto StackDepthStepFunction = [](size_t A) -> size_t {
+    if (!A)
+      return A;
+    auto Log2 = Log(A);
+    if (Log2 < 3)
+      return A;
     Log2 -= 3;
     return (Log2 + 1) * 8 + ((A >> Log2) & 7);
   };
   assert(StackDepthStepFunction(1024) == 64);
   assert(StackDepthStepFunction(1024 * 4) == 80);
   assert(StackDepthStepFunction(1024 * 1024) == 144);
 
-  if (auto MaxStackOffset = GetMaxStackOffset())
-    HandleFeature(FirstFeature + StackDepthStepFunction(MaxStackOffset / 8));
+  if (auto MaxStackOffset = GetMaxStackOffset()) {
+    HandleFeature(static_cast<uint32_t>(
+        FirstFeature + StackDepthStepFunction(MaxStackOffset / 8)));
+    FirstFeature += StackDepthStepFunction(std::numeric_limits<size_t>::max());
+  }
+
+  return FirstFeature;
 }
 
 extern TracePC TPC;
 
 }  // namespace fuzzer
 
 #endif  // LLVM_FUZZER_TRACE_PC

compiler-rt/lib/fuzzer/FuzzerTracePC.cpp

if (NumInline8bitCounters && NumInline8bitCounters != NumPCsInPCTables) {
              "please contact the libFuzzer developers.\n"
              "Also check https://bugs.llvm.org/show_bug.cgi?id=34636\n"
              "for possible workarounds (tl;dr: don't use the old GNU ld)\n");
       _Exit(1);
     }
   }
   if (size_t NumExtraCounters = ExtraCountersEnd() - ExtraCountersBegin())
     Printf("INFO: %zd Extra Counters\n", NumExtraCounters);
+
+  size_t MaxFeatures = CollectFeatures([](uint32_t) {});
+  if (MaxFeatures > std::numeric_limits<uint32_t>::max())
+    Printf("WARNING: The coverage PC tables may produce up to %zu features.\n"
+           "This exceeds the maximum 32-bit value. Some features may be\n"
+           "ignored, and fuzzing may become less precise. If possible,\n"
+           "consider refactoring the fuzzer into several smaller fuzzers\n"
+           "linked against only a portion of the current target.\n",
+           MaxFeatures);
 }
 
 ATTRIBUTE_NO_SANITIZE_ALL
 void TracePC::HandleCallerCallee(uintptr_t Caller, uintptr_t Callee) {
   const uintptr_t kBits = 12;
   const uintptr_t kMask = (1 << kBits) - 1;
   uintptr_t Idx = (Caller & kMask) | ((Callee & kMask) << kBits);
   ValueProfileMap.AddValueModPrime(Idx);
for (size_t i = 0; i < Len; i++) {
     B2[i] = A2[i];
     size_t T = B1[i];
     Hash ^= (T << 8) | B2[i];
   }
   size_t I = 0;
   uint8_t HammingDistance = 0;
   for (; I < Len; I++) {
     if (B1[I] != B2[I] || (StopAtZero && B1[I] == 0)) {
-      HammingDistance = Popcountll(B1[I] ^ B2[I]);
+      HammingDistance = static_cast<uint8_t>(Popcountll(B1[I] ^ B2[I]));
       break;
     }
   }
   size_t PC = reinterpret_cast<size_t>(caller_pc);
   size_t Idx = (PC & 4095) | (I << 12);
   Idx += HammingDistance;
   ValueProfileMap.AddValue(Idx);
   TORCW.Insert(Idx ^ Hash, Word(B1, Len), Word(B2, Len));

compiler-rt/lib/fuzzer/FuzzerUtil.h

 void DiscardOutput(int Fd);
 
 std::string DisassembleCmd(const std::string &FileName);
 
 std::string SearchRegexCmd(const std::string &Regex);
 
 size_t SimpleFastHash(const uint8_t *Data, size_t Size);
 
-inline uint32_t Log(uint32_t X) { return 32 - Clz(X) - 1; }
+inline size_t Log(size_t X) {
+  return static_cast<size_t>((sizeof(unsigned long long) * 8) - Clzll(X) - 1);
+}
 
 inline size_t PageSize() { return 4096; }
 inline uint8_t *RoundUpByPage(uint8_t *P) {
   uintptr_t X = reinterpret_cast<uintptr_t>(P);
   size_t Mask = PageSize() - 1;
   X = (X + Mask) & ~Mask;
   return reinterpret_cast<uint8_t *>(X);
 }

compiler-rt/lib/fuzzer/FuzzerUtil.cpp

if (V =='\\') {
         continue;
       }
       // Handle '\xAB'
       if (Pos + 3 <= R && Str[Pos + 1] == 'x'
            && isxdigit(Str[Pos + 2]) && isxdigit(Str[Pos + 3])) {
         char Hex[] = "0xAA";
         Hex[2] = Str[Pos + 2];
         Hex[3] = Str[Pos + 3];
-        U->push_back(strtol(Hex, nullptr, 16));
+        U->push_back(static_cast<uint8_t>(strtol(Hex, nullptr, 16)));
         Pos += 3;
         continue;
       }
       return false;  // Invalid escape.
     } else {
       // Any other character.
       U->push_back(V);
     }

compiler-rt/lib/fuzzer/FuzzerUtilFuchsia.cpp

int ExecuteCommand(const Command &Cmd) {
   zx_info_process_t Info;
   if ((rc = _zx_object_get_info(ProcessHandle, ZX_INFO_PROCESS, &Info,
                                 sizeof(Info), nullptr, nullptr)) != ZX_OK) {
     Printf("libFuzzer: unable to get return code from '%s': %s\n", Argv[0],
            _zx_status_get_string(rc));
     return rc;
   }
 
-  return Info.return_code;
+  return static_cast<int>(Info.return_code);
 }
 
 bool ExecuteCommand(const Command &BaseCmd, std::string *CmdOutput) {
   auto LogFilePath = TempPath("SimPopenOut", ".txt");
   Command Cmd(BaseCmd);
   Cmd.setOutputFile(LogFilePath);
   int Ret = ExecuteCommand(Cmd);
   *CmdOutput = FileToString(LogFilePath);