Re: perf: fuzzer gets CPU stuck in perf_callchain()
From: Vince Weaver
Date: Thu Feb 19 2015 - 12:03:13 EST
On Thu, 19 Feb 2015, Peter Zijlstra wrote:
> On Thu, Feb 19, 2015 at 11:54:40AM -0500, Vince Weaver wrote:
> > Another bug found by the perf_fuzzer(). I think this one is different
> > than the one I sent the other day, it looks like something is going
> > very wrong in perf_callchain().
> > This one is reasonably reproducible, if there's any extra debugging that I
> > can add. This is on a Haswell machine with git as of a few days ago.
> Aw man, and I had such good hopes with you saying it took 4 days to find
> problems :/
> I'll try and get some time to stare at both.
well if it's any comfort it is definitely on the order of days now before
issues crop up (rather than minutes). And the Haswell machine is the
problem-causing one. I also have a core2 and a Cortex-A9 machine fuzzing
away and they've been at it a week now without turning up anything.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/