mirror of
https://github.com/Gericom/teak-llvm.git
synced 2025-06-22 21:15:40 -04:00
2946cd7010
to reflect the new license. We understand that people may be surprised that we're moving the header entirely to discuss the new license. We checked this carefully with the Foundation's lawyer and we believe this is the correct approach. Essentially, all code in the project is now made available by the LLVM project under our new license, so you will see that the license headers include that license only. Some of our contributors have contributed code under our old license, and accordingly, we have retained a copy of our old license notice in the top-level files in each project and repository. llvm-svn: 351636
79 lines
2.6 KiB
Python
Executable File
79 lines
2.6 KiB
Python
Executable File
#!/usr/bin/env python
|
|
#===- 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)
|
|
sha1 = hashlib.sha1(open(path).read()).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)
|