drm/i915: Move the final intel_gpu_reset() to after declaring wedged
authorChris Wilson <chris@chris-wilson.co.uk>
Fri, 9 Feb 2018 11:40:56 +0000 (11:40 +0000)
committerChris Wilson <chris@chris-wilson.co.uk>
Mon, 12 Feb 2018 10:37:52 +0000 (10:37 +0000)
commitad5169070713cee0be9f533a8f39b2903b7833d8
tree673841db6e75b4e1b458305f5b5cd04171599d32
parent0f550a21247f6029bba036c06fef8de78dddaa69
drm/i915: Move the final intel_gpu_reset() to after declaring wedged

If we fail to reset the GPU (i915_reset()), we do one final
intel_gpu_reset() attempt as we mark the device wedged. The idea here is
even though the GPU has proven unreliable (and so we want to stop using
it for the time being), we don't want it spinning away in the background
whilst the driver idles so we try to reset it one more time. However, we
want to dump the i915_gem_set_wedged() debugging info before we do, so
that we can see the accurate state of the GPU when it failed.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180209114056.9957-1-chris@chris-wilson.co.uk
drivers/gpu/drm/i915/i915_drv.c