[PATCH 12/12] scripts/oss-fuzz: Add crash trace minimization script

[Alexander Bulekov]

Once we find a crash, we can convert it into a QTest trace. Usually this
trace will contain many operations that are unneeded to reproduce the
crash. This script tries to minimize the crashing trace, by removing
operations and trimming QTest bufwrite(write addr len data...) commands.

Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
---
I know its hard to make sense of this patch and the previous one without
a real example, but I didn't want to delay sending this set. I'll try to
find and old crash (maybe for one of the e1000e bugs) and show exactly
how I go from binary libFuzzer blob to qtest reproducer.

 scripts/oss-fuzz/minimize_qtest_trace.py | 117 +++++++++++++++++++++++
 1 file changed, 117 insertions(+)
 create mode 100755 scripts/oss-fuzz/minimize_qtest_trace.py

diff --git a/scripts/oss-fuzz/minimize_qtest_trace.py 
b/scripts/oss-fuzz/minimize_qtest_trace.py
new file mode 100755
index 0000000000..c318032049
--- /dev/null
+++ b/scripts/oss-fuzz/minimize_qtest_trace.py
@@ -0,0 +1,117 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+This takes a crashing qtest trace and tries to remove superflous operations
+"""
+
+import sys
+import os
+import subprocess
+import time
+
+QEMU_ARGS = None
+QEMU_PATH = None
+TIMEOUT = 5
+CRASH_TOKEN = None
+
+
+def usage():
+    sys.exit("""\
+Usage: QEMU_PATH="/path/to/qemu" QEMU_ARGS="args" {} input_trace output_trace
+By default, will try to use the second-to-last line in the output to identify
+whether the crash occred. Optionally, manually set a string that idenitifes the
+crash by setting CRASH_TOKEN=
+""".format((sys.argv[0])))
+
+
+def check_if_trace_crashes(trace, path):
+    global CRASH_TOKEN
+    with open(path, "w") as tracefile:
+        tracefile.write("".join(trace))
+    rc = subprocess.Popen("timeout -s 9 {}s {} {} 2>&1 < {}".format(TIMEOUT,
+                          QEMU_PATH, QEMU_ARGS, path),
+                          shell=True, stdin=subprocess.PIPE,
+                          stdout=subprocess.PIPE)
+    stdo, None = rc.communicate()
+    output = stdo.decode('unicode_escape')
+    if rc.returncode == 137:    # Timed Out
+        return False
+    if len(output.splitlines()) < 2:
+        return False
+
+    if CRASH_TOKEN is None:
+        CRASH_TOKEN = output.splitlines()[-2]
+
+    return CRASH_TOKEN in output
+
+
+def minimize_trace(inpath, outpath):
+    global TIMEOUT
+    with open(inpath) as f:
+        trace = f.readlines()
+    start = time.time()
+    if not check_if_trace_crashes(trace, outpath):
+        sys.exit("The input qtest trace didn't cause a crash...")
+    end = time.time()
+    print("Crashed in {} seconds".format(end-start))
+    TIMEOUT = (end-start)*5
+    print("Setting the timeout for {} seconds".format(TIMEOUT))
+    print("Identifying Crashes by this string: {}".format(CRASH_TOKEN))
+
+    i = 0
+    newtrace = trace[:]
+    while i < len(newtrace):
+        prior = newtrace[i]
+        # Try to remove the line completely
+        newtrace[i] = ""
+        if check_if_trace_crashes(newtrace, outpath):
+            i += 1
+            continue
+        newtrace[i] = prior
+        # Try to split up writes into multiple commands, each of which can be
+        # removed.
+        if newtrace[i].startswith("write "):
+            addr = int(newtrace[i].split()[1], 16)
+            length = int(newtrace[i].split()[2], 16)
+            data = newtrace[i].split()[3][2:]
+            if length > 1:
+                leftlength = int(length/2)
+                rightlength = length - leftlength
+                newtrace.insert(i+1, "")
+                while leftlength > 0:
+                    newtrace[i] = "write {} {} 0x{}\n".format(
+                            hex(addr),
+                            hex(leftlength),
+                            data[:leftlength*2])
+                    newtrace[i+1] = "write {} {} 0x{}\n".format(
+                            hex(addr+leftlength),
+                            hex(rightlength),
+                            data[leftlength*2:])
+                    if check_if_trace_crashes(newtrace, outpath):
+                        break
+                    else:
+                        leftlength -= 1
+                        rightlength += 1
+                if check_if_trace_crashes(newtrace, outpath):
+                    i -= 1
+                else:
+                    newtrace[i] = prior
+                    del newtrace[i+1]
+        i += 1
+    check_if_trace_crashes(newtrace, outpath)
+
+
+if __name__ == '__main__':
+    if len(sys.argv) < 3:
+        usage()
+
+    QEMU_PATH = os.getenv("QEMU_PATH")
+    QEMU_ARGS = os.getenv("QEMU_ARGS")
+    if QEMU_PATH is None or QEMU_ARGS is None:
+        usage()
+    if "accel" not in QEMU_ARGS:
+        QEMU_ARGS += " -accel qtest"
+    CRASH_TOKEN = os.getenv(CRASH_TOKEN)
+    QEMU_ARGS += " -qtest stdio -monitor none -serial none "
+    minimize_trace(sys.argv[1], sys.argv[2])
-- 
2.27.0