[libFuzzer] remove the data-flow-trace (DFT) python scripts; their functionality is now part of libFuzzer proper; also write functions.txt to the disk only if this file doesn't exist yet
llvm-svn: 361452
GitOrigin-RevId: eac9a7830b6b8442762a89f1439f14a0311b6648
diff --git a/FuzzerDataFlowTrace.cpp b/FuzzerDataFlowTrace.cpp
index 74bfa8f..c67238e 100644
--- a/FuzzerDataFlowTrace.cpp
+++ b/FuzzerDataFlowTrace.cpp
@@ -310,11 +310,14 @@
OF << C << std::endl;
}
RemoveFile(Temp);
- // Write functions.txt.
- Command Cmd;
- Cmd.addArgument(DFTBinary);
- Cmd.setOutputFile(DirPlusFile(DirPath, "functions.txt"));
- ExecuteCommand(Cmd);
+ // Write functions.txt if it's currently empty or doesn't exist.
+ auto FunctionsTxtPath = DirPlusFile(DirPath, "functions.txt");
+ if (FileToString(FunctionsTxtPath).empty()) {
+ Command Cmd;
+ Cmd.addArgument(DFTBinary);
+ Cmd.setOutputFile(FunctionsTxtPath);
+ ExecuteCommand(Cmd);
+ }
return 0;
}
diff --git a/scripts/collect_data_flow.py b/scripts/collect_data_flow.py
deleted file mode 100755
index bd601eb..0000000
--- a/scripts/collect_data_flow.py
+++ /dev/null
@@ -1,80 +0,0 @@
-#!/usr/bin/env python3
-#===- lib/fuzzer/scripts/collect_data_flow.py ------------------------------===#
-#
-# 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
-#
-#===------------------------------------------------------------------------===#
-# Runs the data-flow tracer several times on the same input in order to collect
-# the complete trace for all input bytes (running it on all bytes at once
-# may fail if DFSan runs out of labels).
-# Usage:
-#
-# # Collect dataflow for one input, store it in OUTPUT (default is stdout)
-# collect_data_flow.py BINARY INPUT [OUTPUT]
-#
-# # Collect dataflow for all inputs in CORPUS_DIR, store them in OUTPUT_DIR
-# collect_data_flow.py BINARY CORPUS_DIR OUTPUT_DIR
-#===------------------------------------------------------------------------===#
-import atexit
-import hashlib
-import sys
-import os
-import subprocess
-import tempfile
-import shutil
-
-tmpdir = ""
-
-def cleanup(d):
- print("removing: %s" % d)
- shutil.rmtree(d)
-
-def collect_dataflow_for_corpus(self, exe, corpus_dir, output_dir):
- print("Collecting dataflow for corpus: %s output_dir: %s" % (corpus_dir,
- output_dir))
- assert not os.path.exists(output_dir)
- os.mkdir(output_dir)
- for root, dirs, files in os.walk(corpus_dir):
- for f in files:
- path = os.path.join(root, f)
- with open(path, 'rb') as fh:
- data = fh.read()
- sha1 = hashlib.sha1(data).hexdigest()
- output = os.path.join(output_dir, sha1)
- subprocess.call([self, exe, path, output])
- functions_txt = open(os.path.join(output_dir, "functions.txt"), "w")
- subprocess.call([exe], stdout=functions_txt)
-
-
-def main(argv):
- exe = argv[1]
- inp = argv[2]
- if os.path.isdir(inp):
- return collect_dataflow_for_corpus(argv[0], exe, inp, argv[3])
- size = os.path.getsize(inp)
- q = [[0, size]]
- tmpdir = tempfile.mkdtemp(prefix="libfuzzer-tmp-")
- atexit.register(cleanup, tmpdir)
- print("tmpdir: ", tmpdir)
- outputs = []
- while len(q):
- r = q.pop()
- print("******* Trying: ", r)
- tmpfile = os.path.join(tmpdir, str(r[0]) + "-" + str(r[1]))
- ret = subprocess.call([exe, str(r[0]), str(r[1]), inp, tmpfile])
- if ret and r[1] - r[0] >= 2:
- q.append([r[0], (r[1] + r[0]) // 2])
- q.append([(r[1] + r[0]) // 2, r[1]])
- else:
- outputs.append(tmpfile)
- print("******* Success: ", r)
- f = sys.stdout
- if len(argv) >= 4:
- f = open(argv[3], "w")
- merge = os.path.join(os.path.dirname(argv[0]), "merge_data_flow.py")
- subprocess.call([merge] + outputs, stdout=f)
-
-if __name__ == '__main__':
- main(sys.argv)
diff --git a/scripts/merge_data_flow.py b/scripts/merge_data_flow.py
deleted file mode 100755
index 9f69018..0000000
--- a/scripts/merge_data_flow.py
+++ /dev/null
@@ -1,58 +0,0 @@
-#!/usr/bin/env python3
-#===- lib/fuzzer/scripts/merge_data_flow.py ------------------------------===#
-#
-# 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
-#
-#===------------------------------------------------------------------------===#
-# Merge several data flow traces into one.
-# Usage:
-# merge_data_flow.py trace1 trace2 ... > result
-#===------------------------------------------------------------------------===#
-import sys
-import fileinput
-from array import array
-
-def Merge(a, b):
- res = array('b')
- for i in range(0, len(a)):
- res.append(ord('1' if a[i] == '1' or b[i] == '1' else '0'))
- return res.tostring().decode('utf-8')
-
-def main(argv):
- D = {}
- C = {}
- # read the lines.
- for line in fileinput.input():
- # collect the coverage.
- if line.startswith('C'):
- COV = line.strip().split(' ')
- F = COV[0];
- if not F in C:
- C[F] = {0}
- for B in COV[1:]:
- C[F].add(int(B))
- continue
- # collect the data flow trace.
- [F,BV] = line.strip().split(' ')
- if F in D:
- D[F] = Merge(D[F], BV)
- else:
- D[F] = BV;
- # print the combined data flow trace.
- for F in D.keys():
- if isinstance(D[F], str):
- value = D[F]
- else:
- value = D[F].decode('utf-8')
- print("%s %s" % (F, value))
- # print the combined coverage
- for F in C.keys():
- print("%s" % F, end="")
- for B in list(C[F])[1:]:
- print(" %s" % B, end="")
- print()
-
-if __name__ == '__main__':
- main(sys.argv)
