D5462: fuzz: new fuzzer for revlog's parse_index2 method

[durin42 (Augie Fackler)]

durin42 created this revision.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.

REPOSITORY
  rHG Mercurial

REVISION DETAIL
  https://phab.mercurial-scm.org/D5462

AFFECTED FILES
  contrib/fuzz/Makefile
  contrib/fuzz/revlog.cc
  contrib/fuzz/revlog_corpus.py

CHANGE DETAILS

diff --git a/contrib/fuzz/revlog_corpus.py b/contrib/fuzz/revlog_corpus.py
new file mode 100644
--- /dev/null
+++ b/contrib/fuzz/revlog_corpus.py
@@ -0,0 +1,28 @@
+from __future__ import absolute_import, print_function
+
+import argparse
+import os
+import zipfile
+
+ap = argparse.ArgumentParser()
+ap.add_argument("out", metavar="some.zip", type=str, nargs=1)
+args = ap.parse_args()
+
+reporoot = os.path.normpath(os.path.join(os.path.dirname(__file__),
+                                         '..', '..'))
+# typically a standalone index
+changelog = os.path.join(reporoot, '.hg', 'store', '00changelog.i')
+# an inline revlog with only a few revisions
+contributing = os.path.join(
+    reporoot, '.hg', 'store', 'data', 'contrib', 'fuzz', 'mpatch.cc.i')
+
+print(changelog, os.path.exists(changelog))
+print(contributing, os.path.exists(contributing))
+
+with zipfile.ZipFile(args.out[0], "w", zipfile.ZIP_STORED) as zf:
+    if os.path.exists(changelog):
+        with open(changelog) as f:
+            zf.writestr("00changelog.i", f.read())
+    if os.path.exists(contributing):
+        with open(contributing) as f:
+            zf.writestr("contributing.i", f.read())
diff --git a/contrib/fuzz/revlog.cc b/contrib/fuzz/revlog.cc
new file mode 100644
--- /dev/null
+++ b/contrib/fuzz/revlog.cc
@@ -0,0 +1,47 @@
+#include <Python.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <string>
+
+#include "pyutil.h"
+
+extern "C" {
+
+static PyCodeObject *code;
+
+extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
+{
+	contrib::initpy(*argv[0]);
+	code = (PyCodeObject *)Py_CompileString(R"py(
+from parsers import parse_index2
+for inline in (True, False):
+    try:
+        index, cache = parse_index2(data, inline)
+    except Exception as e:
+        pass
+        # uncomment this print if you're editing this Python code
+        # to debug failures.
+        # print e
+)py",
+	                                        "fuzzer", Py_file_input);
+	return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size)
+{
+	PyObject *text =
+	    PyBytes_FromStringAndSize((const char *)Data, (Py_ssize_t)Size);
+	PyObject *locals = PyDict_New();
+	PyDict_SetItemString(locals, "data", text);
+	PyObject *res = PyEval_EvalCode(code, contrib::pyglobals(), locals);
+	if (!res) {
+		PyErr_Print();
+	}
+	Py_XDECREF(res);
+	Py_DECREF(locals);
+	Py_DECREF(text);
+	return 0; // Non-zero return values are reserved for future use.
+}
+}
diff --git a/contrib/fuzz/Makefile b/contrib/fuzz/Makefile
--- a/contrib/fuzz/Makefile
+++ b/contrib/fuzz/Makefile
@@ -124,12 +124,23 @@
 manifest_corpus.zip:
 	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
 
+revlog_fuzzer: sanpy revlog.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
+	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
+	  -Wno-register -Wno-macro-redefined \
+	  -I../../mercurial revlog.cc \
+	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
+	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
+	  -o $$OUT/revlog_fuzzer
+
+revlog_corpus.zip:
+	python revlog_corpus.py $$OUT/revlog_fuzzer_seed_corpus.zip
+
 clean:
 	$(RM) *.o *_fuzzer \
 	  bdiff \
 	  mpatch \
 	  xdiff
 
-oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer manifest_fuzzer manifest_corpus.zip
+oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip
 
 .PHONY: all clean oss-fuzz sanpy



To: durin42, #hg-reviewers
Cc: mercurial-devel