On Fri, Jun 28, 2013 at 7:15 PM, Daniel Vetter <daniel.vetter@xxxxxxxx> wrote: > On Fri, Jun 28, 2013 at 7:26 AM, Dave Airlie <airlied@xxxxxxxxx> 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. _______________________________________________ dri-devel mailing list dri-devel@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/dri-devel