workqueue warnings in helper code

[Dave Airlie]

On Fri, Jun 28, 2013 at 7:15 PM, Daniel Vetter <daniel.vetter at ffwll.ch> wrote:
> On Fri, Jun 28, 2013 at 7:26 AM, Dave Airlie <airlied at gmail.com> wrote:
>>>
>>> this showed up in drm-next on my radeon and udl drivers, I haven't
>>> bisected it yet, it may not even be your fault :-)
>>>
>>>  if (WARN_ON(!list_empty(&work->entry))) {
>>>
>>> is the line in the workqueue code.
>>
>> As expected, reverting "drm: kms_helper: don't lose hotplug event"
>>
>> stops the warnings here.
>
> I've looked a bit into this and I think we need to have a separate
> work struct for recovering these lost hotplug events since the
> continuous self-rearming case is a real risk (e.g. if a connector
> flip-flops all the time). At least I don't see a sane way to block out
> re-arming with the current code in a simple way. So reverting the
> offender seems like the right thing and I'll go back to the drawing
> board for 3.12.

Okay done, thanks for investigating.

Dave.