Messages in this thread | | | From | Vince Weaver <> | Date | Wed, 10 Sep 2014 09:18:35 -0400 (EDT) | Subject | Re: perf: perf_fuzzer triggers instant reboot |
| |
On Wed, 10 Sep 2014, Peter Zijlstra wrote: > > Sasha reported something from his KVM based fuzzing, maybe that's the > same. But that x86_exceptions thing is interesting, lemme go look at > that first.
that's what got me looking at things again, the trinity reports. Though I think those involve CPU hotplugging which my fuzzer shouldn't trigger.
I do think this is the same memory corruption/reboot bug that I reported back in February (the thread is "perf_fuzzer compiled for x32 causes reboot" but I wasn't able to isolate the problem then either.
Somehow something is stomping over memory with a forking workload (likely an improper free with RCU like we've seen before) but the fact that it causes a reboot immediately makes it *really* hard to debug this.
I'm not sure about the tracing issue, possibly it's just a side effect of memory being corrupted by the same bug. In case it's relevant here's the trace-cmd I was trying to use:
trace-cmd record -e raw_syscalls -p function -l '*perf*' -n 'perf_event_task_tick' -l 'x86*' -l 'intel*' -P 2807
Vince
| |