drm/i915: Don't check for idleness before retiring after a GPU hang
authorChris Wilson <chris@chris-wilson.co.uk>
Tue, 9 Aug 2016 07:37:02 +0000 (08:37 +0100)
committerChris Wilson <chris@chris-wilson.co.uk>
Tue, 9 Aug 2016 08:11:59 +0000 (09:11 +0100)
commit87b723a16de9ff95e2b7d61dbd86bddd3c1716d9
tree340be3e996d993ae020381905d82663d6f7cf400
parent385384a82cb4d9d1725330fde293877c36c1dba2
drm/i915: Don't check for idleness before retiring after a GPU hang

When we force the cleanup after a GPU hang, we want to retire all
requests, or else we may leak them if truly wedged (and the GPU never
advances again). Converting to the active request helpers had the issue
of doing the check against busyness before reporting the request, so if
we claim the GPU had hung but this engine hadn't we could potential skip
the request cleanup - triggering the self-check BUG.

Fixes: dcff85c8443e ("drm/i915: Enable i915_gem_wait_for_idle() ...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470728222-10243-3-git-send-email-chris@chris-wilson.co.uk
drivers/gpu/drm/i915/i915_gem.c