workqueue warnings in helper code

[Daniel Vetter]

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.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch