diff options
| author | Chris Wilson <chris@chris-wilson.co.uk> | 2018-05-01 13:21:31 +0100 |
|---|---|---|
| committer | Chris Wilson <chris@chris-wilson.co.uk> | 2018-05-01 21:20:04 +0100 |
| commit | c5ce3b8df6c758169b5b5df5ee9adc4c39505d9b (patch) | |
| tree | 9649da236a8b5aee2e568f9cd8bc2a81961da139 /drivers/gpu/drm/i915 | |
| parent | 36cf89f53b0ccdbd6bdaedfe1435a574609f0de5 (diff) | |
drm/i915/execlists: Don't trigger preemption if complete
Due to the latency of the tasklet running from ksoftirqd, by the time we
process the execlist dequeue may be a long time behind the GPU. If the
request was completed when we ran reschedule, we will not have tweaked
its priority, but if it is still listed as being in-flight for dequeue
we will use it as a reference for the rest of the queue, including
requests from its own context which will now be at higher priority. This
can cause us to issue a preempt-to-idle request, even though the request
we want to preempt is already complete.
Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180501122131.19435-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915')
| -rw-r--r-- | drivers/gpu/drm/i915/intel_lrc.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 099995619472..774b2adc9211 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -185,7 +185,8 @@ static inline bool need_preempt(const struct intel_engine_cs *engine, int prio) { return (intel_engine_has_preemption(engine) && - __execlists_need_preempt(prio, rq_prio(last))); + __execlists_need_preempt(prio, rq_prio(last)) && + !i915_request_completed(last)); } /** |