contrib/fuzz/revlog.cc

stream-clone: smoothly detect and handle a case were a revlog is split

This detect and handle the most common case for a race condition around stream
and revlog splitting. The one were the revlog is split between the initial
collection of data and the time were we start considering stream that data.

In such case, we repatch an inlined version of that revlog together when this
happens. This is necessary as stream-v2 promised a specific number of bytes and
a specific number of files to the client. In stream-v3, we will have the
opportunity to just send a split revlog instead.

Getting a better version of the protocol for stream-v3 is still useful, but it
is no longer a blocket to fix that race condition.

Note that another, rarer race condition exist, were the revlog is split while
we creating the revlog and extracing content from it. This can be dealt with
later.

#include <Python.h>
#include <assert.h>
#include <stdlib.h>
#include <unistd.h>

#include <string>

#include "pyutil.h"

extern "C" {

static PYCODETYPE *code;

extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
{
	contrib::initpy(*argv[0]);
	code = (PYCODETYPE *)Py_CompileString(R"py(
for inline in (True, False):
    try:
        index, cache = parsers.parse_index2(data, inline)
        index.slicechunktodensity(list(range(len(index))), 0.5, 262144)
        index.stats()
        index.findsnapshots({}, 0, len(index) - 1)
        10 in index
        for rev in range(len(index)):
            index.reachableroots(0, [len(index)-1], [rev])
            node = index[rev][7]
            partial = index.shortest(node)
            index.partialmatch(node[:partial])
            index.deltachain(rev, None, True)
    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)
{
	// Don't allow fuzzer inputs larger than 60k, since we'll just bog
	// down and not accomplish much.
	if (Size > 60000) {
		return 0;
	}
	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.
}
}