On 07/17/2012 10:57 AM, Willy Tarreau wrote:
> Hi John,
>
> On Tue, Jul 17, 2012 at 01:33:47PM -0400, John Stultz wrote:
>> I've already done backports to all the stable kernels to 2.6.32, and
>> will send out the rest soon.
> That's very much appreciated, thank you! Do not hesitate to send me
> your reproducers, I'll happily run some tests.

Attached are two tests. One is general exerciser of the leapsecond code 
(leap-a-day) which also notes if it sees the hrtimer/futuex early 
expiration issue, and the other is a much faster (almost immediate) 
reproducer for the leapsecond deadlock (leapcrash).

The leapcrash test will likely wedge unpatched systems in hardirq 
context, and has caused lost (dirty) data in my testing, so BEWARE!
RUN AT YOUR OWN RISK!

And of course, the leap-a-day has the same potential, but doesn't tickle 
the deadlock issue as aggressively.

thanks
-john