[libFuzzer] Make -merge=1 to reuse coverage information from the control file.
Summary:
This change allows to perform corpus merging in two steps. This is useful when
the user wants to address the following two points simultaneously:
1) Get trustworthy incremental stats for the coverage and corpus size changes
when adding new corpus units.
2) Make sure the shorter units will be preferred when two or more units give the
same unique signal (equivalent to the `REDUCE` logic).
This solution was brainstormed together with @kcc, hopefully it looks good to
the other people too. The proposed use case scenario:
1) We have a `fuzz_target` binary and `existing_corpus` directory.
2) We do fuzzing and write new units into the `new_corpus` directory.
3) We want to merge the new corpus into the existing corpus and satisfy the
points mentioned above.
4) We create an empty directory `merged_corpus` and run the first merge step:
`
./fuzz_target -merge=1 -merge_control_file=MCF ./merged_corpus ./existing_corpus
`
this provides the initial stats for `existing_corpus`, e.g. from the output:
`
MERGE-OUTER: 3 new files with 11 new features added; 11 new coverage edges
`
5) We recreate `merged_corpus` directory and run the second merge step:
`
./fuzz_target -merge=1 -merge_control_file=MCF ./merged_corpus ./existing_corpus ./new_corpus
`
this provides the final stats for the merged corpus, e.g. from the output:
`
MERGE-OUTER: 6 new files with 14 new features added; 14 new coverage edges
`
Alternative solutions to this approach are:
A) Store precise coverage information for every unit (not only unique signal).
B) Execute the same two steps without reusing the control file.
Either of these would be suboptimal as it would impose an extra disk or CPU load
respectively, which is bad given the quadratic complexity in the worst case.
Tested on Linux, Mac, Windows.
Reviewers: morehouse, metzman, hctim, kcc
Reviewed By: morehouse
Subscribers: JDevlieghere, delcypher, mgrang, #sanitizers, llvm-commits, kcc
Tags: #llvm, #sanitizers
Differential Revision: https://reviews.llvm.org/D66107
llvm-svn: 371620
GitOrigin-RevId: f054067f276d8951e5a0a8dbd009a16fa666d736
diff --git a/FuzzerDefs.h b/FuzzerDefs.h
index 320b37d..5dc2d8e 100644
--- a/FuzzerDefs.h
+++ b/FuzzerDefs.h
@@ -15,10 +15,11 @@
#include <cstddef>
#include <cstdint>
#include <cstring>
+#include <memory>
+#include <set>
#include <string>
#include <vector>
-#include <set>
-#include <memory>
+
// Platform detection.
#ifdef __linux__
diff --git a/FuzzerMerge.cpp b/FuzzerMerge.cpp
index c05c492..e3ad8b3 100644
--- a/FuzzerMerge.cpp
+++ b/FuzzerMerge.cpp
@@ -19,6 +19,7 @@
#include <iterator>
#include <set>
#include <sstream>
+#include <unordered_set>
namespace fuzzer {
@@ -221,7 +222,7 @@
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.
@@ -260,22 +261,39 @@
PrintStatsWrapper("DONE ");
}
-static void WriteNewControlFile(const std::string &CFPath,
- const Vector<SizedFile> &OldCorpus,
- const Vector<SizedFile> &NewCorpus) {
+static size_t WriteNewControlFile(const std::string &CFPath,
+ const Vector<SizedFile> &OldCorpus,
+ const Vector<SizedFile> &NewCorpus,
+ const Vector<MergeFileInfo> &KnownFiles) {
+ std::unordered_set<std::string> FilesToSkip;
+ for (auto &SF: KnownFiles)
+ FilesToSkip.insert(SF.Name);
+
+ Vector<std::string> FilesToUse;
+ auto MaybeUseFile = [=, &FilesToUse](std::string Name) {
+ if (FilesToSkip.find(Name) == FilesToSkip.end())
+ FilesToUse.push_back(Name);
+ };
+ for (auto &SF: OldCorpus)
+ MaybeUseFile(SF.File);
+ auto FilesToUseFromOldCorpus = FilesToUse.size();
+ for (auto &SF: NewCorpus)
+ MaybeUseFile(SF.File);
+
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";
+ ControlFile << FilesToUse.size() << "\n";
+ ControlFile << FilesToUseFromOldCorpus << "\n";
+ for (auto &FN: FilesToUse)
+ ControlFile << FN << "\n";
+
if (!ControlFile) {
Printf("MERGE-OUTER: failed to write to the control file: %s\n",
CFPath.c_str());
exit(1);
}
+
+ return FilesToUse.size();
}
// Outer process. Does not call the target code and thus should not fail.
@@ -291,12 +309,13 @@
bool V /*Verbose*/) {
if (NewCorpus.empty() && OldCorpus.empty()) return; // Nothing to merge.
size_t NumAttempts = 0;
+ Vector<MergeFileInfo> KnownFiles;
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)) {
+ if (M.Parse(IF, /*ParseCoverage=*/true)) {
VPrintf(V, "MERGE-OUTER: control file ok, %zd files total,"
" first not processed file %zd\n",
M.Files.size(), M.FirstNotProcessedFile);
@@ -305,12 +324,25 @@
"(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);
- }
+ // Merge has already been completed with the given merge control file.
+ if (M.Files.size() == OldCorpus.size() + NewCorpus.size()) {
+ VPrintf(
+ V,
+ "MERGE-OUTER: nothing to do, merge has been completed before\n");
+ exit(0);
+ }
- NumAttempts = M.Files.size() - M.FirstNotProcessedFile;
+ // Number of input files likely changed, start merge from scratch, but
+ // reuse coverage information from the given merge control file.
+ VPrintf(
+ V,
+ "MERGE-OUTER: starting merge from scratch, but reusing coverage "
+ "information from the given control file\n");
+ KnownFiles = M.Files;
+ } else {
+ // There is a merge in progress, continue.
+ NumAttempts = M.Files.size() - M.FirstNotProcessedFile;
+ }
} else {
VPrintf(V, "MERGE-OUTER: bad control file, will overwrite it\n");
}
@@ -318,10 +350,11 @@
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);
+ VPrintf(V, "MERGE-OUTER: "
+ "%zd files, %zd in the initial corpus, %zd processed earlier\n",
+ OldCorpus.size() + NewCorpus.size(), OldCorpus.size(),
+ KnownFiles.size());
+ NumAttempts = WriteNewControlFile(CFPath, OldCorpus, NewCorpus, KnownFiles);
}
// Execute the inner process until it passes.
@@ -358,6 +391,8 @@
VPrintf(V,
"MERGE-OUTER: consumed %zdMb (%zdMb rss) to parse the control file\n",
M.ApproximateMemoryConsumption() >> 20, GetPeakRSSMb());
+
+ M.Files.insert(M.Files.end(), KnownFiles.begin(), KnownFiles.end());
M.Merge(InitialFeatures, NewFeatures, InitialCov, NewCov, NewFiles);
VPrintf(V, "MERGE-OUTER: %zd new files with %zd new features added; "
"%zd new coverage edges\n",
