summaryrefslogtreecommitdiff
path: root/lib/fuzzer/FuzzerMerge.cpp
blob: c05c49225ea3b6c4d9f3609fc29663f367181c4f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
//===- FuzzerMerge.cpp - merging corpora ----------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
// Merging corpora.
//===----------------------------------------------------------------------===//

#include "FuzzerCommand.h"
#include "FuzzerMerge.h"
#include "FuzzerIO.h"
#include "FuzzerInternal.h"
#include "FuzzerTracePC.h"
#include "FuzzerUtil.h"

#include <fstream>
#include <iterator>
#include <set>
#include <sstream>

namespace fuzzer {

bool Merger::Parse(const std::string &Str, bool ParseCoverage) {
  std::istringstream SS(Str);
  return Parse(SS, ParseCoverage);
}

void Merger::ParseOrExit(std::istream &IS, bool ParseCoverage) {
  if (!Parse(IS, ParseCoverage)) {
    Printf("MERGE: failed to parse the control file (unexpected error)\n");
    exit(1);
  }
}

// The control file example:
//
// 3 # The number of inputs
// 1 # The number of inputs in the first corpus, <= the previous number
// file0
// file1
// file2  # One file name per line.
// STARTED 0 123  # FileID, file size
// FT 0 1 4 6 8  # FileID COV1 COV2 ...
// COV 0 7 8 9 # FileID COV1 COV1
// STARTED 1 456  # If FT is missing, the input crashed while processing.
// STARTED 2 567
// FT 2 8 9
// COV 2 11 12
bool Merger::Parse(std::istream &IS, bool ParseCoverage) {
  LastFailure.clear();
  std::string Line;

  // Parse NumFiles.
  if (!std::getline(IS, Line, '\n')) return false;
  std::istringstream L1(Line);
  size_t NumFiles = 0;
  L1 >> NumFiles;
  if (NumFiles == 0 || NumFiles > 10000000) return false;

  // Parse NumFilesInFirstCorpus.
  if (!std::getline(IS, Line, '\n')) return false;
  std::istringstream L2(Line);
  NumFilesInFirstCorpus = NumFiles + 1;
  L2 >> NumFilesInFirstCorpus;
  if (NumFilesInFirstCorpus > NumFiles) return false;

  // Parse file names.
  Files.resize(NumFiles);
  for (size_t i = 0; i < NumFiles; i++)
    if (!std::getline(IS, Files[i].Name, '\n'))
      return false;

  // Parse STARTED, FT, and COV lines.
  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;
    if (Marker == "STARTED") {
      // STARTED FILE_ID FILE_SIZE
      if (ExpectedStartMarker != N)
        return false;
      ISS1 >> Files[ExpectedStartMarker].Size;
      LastSeenStartMarker = ExpectedStartMarker;
      assert(ExpectedStartMarker < Files.size());
      ExpectedStartMarker++;
    } else if (Marker == "FT") {
      // FT FILE_ID COV1 COV2 COV3 ...
      size_t CurrentFileIdx = N;
      if (CurrentFileIdx != LastSeenStartMarker)
        return false;
      LastSeenStartMarker = kInvalidStartMarker;
      if (ParseCoverage) {
        TmpFeatures.clear();  // use a vector from outer scope to avoid resizes.
        while (ISS1 >> N)
          TmpFeatures.push_back(N);
        std::sort(TmpFeatures.begin(), TmpFeatures.end());
        Files[CurrentFileIdx].Features = TmpFeatures;
      }
    } else if (Marker == "COV") {
      size_t CurrentFileIdx = N;
      if (ParseCoverage)
        while (ISS1 >> N)
          if (PCs.insert(N).second)
            Files[CurrentFileIdx].Cov.push_back(N);
    } else {
      return false;
    }
  }
  if (LastSeenStartMarker != kInvalidStartMarker)
    LastFailure = Files[LastSeenStartMarker].Name;

  FirstNotProcessedFile = ExpectedStartMarker;
  return true;
}

size_t Merger::ApproximateMemoryConsumption() const  {
  size_t Res = 0;
  for (const auto &F: Files)
    Res += sizeof(F) + F.Features.size() * sizeof(F.Features[0]);
  return Res;
}

// Decides which files need to be merged (add those to NewFiles).
// Returns the number of new features added.
size_t Merger::Merge(const Set<uint32_t> &InitialFeatures,
                     Set<uint32_t> *NewFeatures,
                     const Set<uint32_t> &InitialCov, Set<uint32_t> *NewCov,
                     Vector<std::string> *NewFiles) {
  NewFiles->clear();
  assert(NumFilesInFirstCorpus <= Files.size());
  Set<uint32_t> AllFeatures = InitialFeatures;

  // What features are in the initial corpus?
  for (size_t i = 0; i < NumFilesInFirstCorpus; i++) {
    auto &Cur = Files[i].Features;
    AllFeatures.insert(Cur.begin(), Cur.end());
  }
  // Remove all features that we already know from all other inputs.
  for (size_t i = NumFilesInFirstCorpus; i < Files.size(); i++) {
    auto &Cur = Files[i].Features;
    Vector<uint32_t> Tmp;
    std::set_difference(Cur.begin(), Cur.end(), AllFeatures.begin(),
                        AllFeatures.end(), std::inserter(Tmp, Tmp.begin()));
    Cur.swap(Tmp);
  }

  // Sort. Give preference to
  //   * smaller files
  //   * files with more features.
  std::sort(Files.begin() + NumFilesInFirstCorpus, Files.end(),
            [&](const MergeFileInfo &a, const MergeFileInfo &b) -> bool {
              if (a.Size != b.Size)
                return a.Size < b.Size;
              return a.Features.size() > b.Features.size();
            });

  // One greedy pass: add the file's features to AllFeatures.
  // If new features were added, add this file to NewFiles.
  for (size_t i = NumFilesInFirstCorpus; i < Files.size(); i++) {
    auto &Cur = Files[i].Features;
    // Printf("%s -> sz %zd ft %zd\n", Files[i].Name.c_str(),
    //       Files[i].Size, Cur.size());
    bool FoundNewFeatures = false;
    for (auto Fe: Cur) {
      if (AllFeatures.insert(Fe).second) {
        FoundNewFeatures = true;
        NewFeatures->insert(Fe);
      }
    }
    if (FoundNewFeatures)
      NewFiles->push_back(Files[i].Name);
    for (auto Cov : Files[i].Cov)
      if (InitialCov.find(Cov) == InitialCov.end())
        NewCov->insert(Cov);
  }
  return NewFeatures->size();
}

Set<uint32_t> Merger::AllFeatures() const {
  Set<uint32_t> S;
  for (auto &File : Files)
    S.insert(File.Features.begin(), File.Features.end());
  return S;
}

// Inner process. May crash if the target crashes.
void Fuzzer::CrashResistantMergeInternalStep(const std::string &CFPath) {
  Printf("MERGE-INNER: using the control file '%s'\n", CFPath.c_str());
  Merger M;
  std::ifstream IF(CFPath);
  M.ParseOrExit(IF, false);
  IF.close();
  if (!M.LastFailure.empty())
    Printf("MERGE-INNER: '%s' caused a failure at the previous merge step\n",
           M.LastFailure.c_str());

  Printf("MERGE-INNER: %zd total files;"
         " %zd processed earlier; will process %zd files now\n",
         M.Files.size(), M.FirstNotProcessedFile,
         M.Files.size() - M.FirstNotProcessedFile);

  std::ofstream OF(CFPath, std::ofstream::out | std::ofstream::app);
  Set<size_t> AllFeatures;
  auto PrintStatsWrapper = [this, &AllFeatures](const char* Where) {
    this->PrintStats(Where, "\n", 0, AllFeatures.size());
  };
  Set<const TracePC::PCTableEntry *> AllPCs;
  for (size_t i = M.FirstNotProcessedFile; i < M.Files.size(); i++) {
    Fuzzer::MaybeExitGracefully();
    auto U = FileToVector(M.Files[i].Name);
    if (U.size() > MaxInputLen) {
      U.resize(MaxInputLen);
      U.shrink_to_fit();
    }
    std::ostringstream StartedLine;
    // Write the pre-run marker.
    OF << "STARTED " << i << " " << U.size() << "\n";
    OF.flush();  // Flush is important since Command::Execute may crash.
    // Run.
    TPC.ResetMaps();
    ExecuteCallback(U.data(), U.size());
    // Collect coverage. We are iterating over the files in this order:
    // * First, files in the initial corpus ordered by size, smallest first.
    // * Then, all other files, smallest first.
    // So it makes no sense to record all features for all files, instead we
    // only record features that were not seen before.
    Set<size_t> UniqFeatures;
    TPC.CollectFeatures([&](size_t Feature) {
      if (AllFeatures.insert(Feature).second)
        UniqFeatures.insert(Feature);
    });
    TPC.UpdateObservedPCs();
    // Show stats.
    if (!(TotalNumberOfRuns & (TotalNumberOfRuns - 1)))
      PrintStatsWrapper("pulse ");
    if (TotalNumberOfRuns == M.NumFilesInFirstCorpus)
      PrintStatsWrapper("LOADED");
    // Write the post-run marker and the coverage.
    OF << "FT " << i;
    for (size_t F : UniqFeatures)
      OF << " " << F;
    OF << "\n";
    OF << "COV " << i;
    TPC.ForEachObservedPC([&](const TracePC::PCTableEntry *TE) {
      if (AllPCs.insert(TE).second)
        OF << " " << TPC.PCTableEntryIdx(TE);
    });
    OF << "\n";
    OF.flush();
  }
  PrintStatsWrapper("DONE  ");
}

static void WriteNewControlFile(const std::string &CFPath,
                                const Vector<SizedFile> &OldCorpus,
                                const Vector<SizedFile> &NewCorpus) {
  RemoveFile(CFPath);
  std::ofstream ControlFile(CFPath);
  ControlFile << (OldCorpus.size() + NewCorpus.size()) << "\n";
  ControlFile << OldCorpus.size() << "\n";
  for (auto &SF: OldCorpus)
    ControlFile << SF.File << "\n";
  for (auto &SF: NewCorpus)
    ControlFile << SF.File << "\n";
  if (!ControlFile) {
    Printf("MERGE-OUTER: failed to write to the control file: %s\n",
           CFPath.c_str());
    exit(1);
  }
}

// Outer process. Does not call the target code and thus should not fail.
void CrashResistantMerge(const Vector<std::string> &Args,
                         const Vector<SizedFile> &OldCorpus,
                         const Vector<SizedFile> &NewCorpus,
                         Vector<std::string> *NewFiles,
                         const Set<uint32_t> &InitialFeatures,
                         Set<uint32_t> *NewFeatures,
                         const Set<uint32_t> &InitialCov,
                         Set<uint32_t> *NewCov,
                         const std::string &CFPath,
                         bool V /*Verbose*/) {
  if (NewCorpus.empty() && OldCorpus.empty()) return;  // Nothing to merge.
  size_t NumAttempts = 0;
  if (FileSize(CFPath)) {
    VPrintf(V, "MERGE-OUTER: non-empty control file provided: '%s'\n",
           CFPath.c_str());
    Merger M;
    std::ifstream IF(CFPath);
    if (M.Parse(IF, /*ParseCoverage=*/false)) {
      VPrintf(V, "MERGE-OUTER: control file ok, %zd files total,"
             " first not processed file %zd\n",
             M.Files.size(), M.FirstNotProcessedFile);
      if (!M.LastFailure.empty())
        VPrintf(V, "MERGE-OUTER: '%s' will be skipped as unlucky "
               "(merge has stumbled on it the last time)\n",
               M.LastFailure.c_str());
      if (M.FirstNotProcessedFile >= M.Files.size()) {
        VPrintf(
            V, "MERGE-OUTER: nothing to do, merge has been completed before\n");
        exit(0);
      }

      NumAttempts = M.Files.size() - M.FirstNotProcessedFile;
    } else {
      VPrintf(V, "MERGE-OUTER: bad control file, will overwrite it\n");
    }
  }

  if (!NumAttempts) {
    // The supplied control file is empty or bad, create a fresh one.
    NumAttempts = OldCorpus.size() + NewCorpus.size();
    VPrintf(V, "MERGE-OUTER: %zd files, %zd in the initial corpus\n",
            NumAttempts, OldCorpus.size());
    WriteNewControlFile(CFPath, OldCorpus, NewCorpus);
  }

  // Execute the inner process until it passes.
  // Every inner process should execute at least one input.
  Command BaseCmd(Args);
  BaseCmd.removeFlag("merge");
  BaseCmd.removeFlag("fork");
  BaseCmd.removeFlag("collect_data_flow");
  for (size_t Attempt = 1; Attempt <= NumAttempts; Attempt++) {
    Fuzzer::MaybeExitGracefully();
    VPrintf(V, "MERGE-OUTER: attempt %zd\n", Attempt);
    Command Cmd(BaseCmd);
    Cmd.addFlag("merge_control_file", CFPath);
    Cmd.addFlag("merge_inner", "1");
    if (!V) {
      Cmd.setOutputFile(getDevNull());
      Cmd.combineOutAndErr();
    }
    auto ExitCode = ExecuteCommand(Cmd);
    if (!ExitCode) {
      VPrintf(V, "MERGE-OUTER: succesfull in %zd attempt(s)\n", Attempt);
      break;
    }
  }
  // Read the control file and do the merge.
  Merger M;
  std::ifstream IF(CFPath);
  IF.seekg(0, IF.end);
  VPrintf(V, "MERGE-OUTER: the control file has %zd bytes\n",
          (size_t)IF.tellg());
  IF.seekg(0, IF.beg);
  M.ParseOrExit(IF, true);
  IF.close();
  VPrintf(V,
          "MERGE-OUTER: consumed %zdMb (%zdMb rss) to parse the control file\n",
          M.ApproximateMemoryConsumption() >> 20, GetPeakRSSMb());
  M.Merge(InitialFeatures, NewFeatures, InitialCov, NewCov, NewFiles);
  VPrintf(V, "MERGE-OUTER: %zd new files with %zd new features added; "
          "%zd new coverage edges\n",
         NewFiles->size(), NewFeatures->size(), NewCov->size());
}

} // namespace fuzzer