drm/i915: Distinguish last emitted request from last submitted request
authorChris Wilson <chris@chris-wilson.co.uk>
Fri, 7 Oct 2016 06:53:24 +0000 (07:53 +0100)
committerJani Nikula <jani.nikula@intel.com>
Mon, 10 Oct 2016 13:06:43 +0000 (16:06 +0300)
commit9b05a6099ed67c2a92e7e5d9032536f1c08169a6
treef41e0dd5e560968d5574b9596fdf2d0d669a42eb
parent16c83fad79ca912b8b5bbdcb5272794a2be41262
drm/i915: Distinguish last emitted request from last submitted request

In order not to trigger hangcheck on a idle-but-waiting engine, we need
to distinguish between the pending request queue and the actual
execution queue. This is done later in "drm/i915: Enable multiple
timelines" but for now we need a temporary fix to prevent blaming the
wrong engine for a GPU hang.

(Note that this causes a temporary subtle change in how we decide when
to allow a waitboost to be re-awarded back to the waiter, the temporary
effect is that if the wait is upon the most current execution the wait
is given for free, instead of checking to see if the client stalled
itself. This will be repaired in "drm/i915: Enable multiple timelines".)

Fixes: 0a046a0e93d2 ("drm/i915: Nonblocking request submission")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98104
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161007065327.24515-1-chris@chris-wilson.co.uk
(cherry picked from commit 8687b3ec852e89630bac650f15136811c7b4c1dc)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
drivers/gpu/drm/i915/i915_gem_request.c
drivers/gpu/drm/i915/intel_ringbuffer.h