Re: sched: spinlock recursion in sched_rr_get_interval

[Sasha Levin <sasha.levin@oracle.com>]

On 07/07/2014 04:05 PM, Peter Zijlstra wrote:
> On Mon, Jul 07, 2014 at 09:55:43AM -0400, Sasha Levin wrote:
>> I've also had this one, which looks similar:
>> 
>> [10375.005884] BUG: spinlock recursion on CPU#0, modprobe/10965 [10375.006573]  lock: 0xffff8803a0fd7740, .magic: dead4ead, .owner: modprobe/10965, .owner_cpu: 15 [10375.007412] CPU: 0 PID: 10965 Comm: modprobe Tainted: G        W      3.16.0-rc3-next-20140704-sasha-00023-g26c0906-dirty #765
> 
> Something's fucked; so we have:
> 
> debug_spin_lock_before() SPIN_BUG_ON(lock->owner == current, "recursion");
> 
> Causing that, _HOWEVER_ look at .owner_cpu and the reporting cpu!! How can the lock owner, own the lock on cpu 15 and again contend with it on CPU 0. That's impossible.
> 
> About when-ish did you start seeing things like this? Lemme go stare hard at recent changes.
> 

~next-20140704 I guess, about when I reported the original issue.


Thanks,
Sasha