On 07/05/2018 14:57, Chris Wilson wrote:
When called from process context tasklet_schedule() defers itself to
ksoftirqd. From experience this may cause unacceptable latencies of over
200ms in executing the submission tasklet, our goal is to reprioritise
the HW execution queue and trigger HW preemption immediately, so disable
bh over the call to schedule and force the tasklet to run afterwards if
scheduled.
v2: Keep rcu_read_lock() around for PREEMPT_RCU
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5ece6ae4bdff..89bf5d67cb74 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -578,10 +578,12 @@ static void __fence_set_priority(struct dma_fence *fence,
rq = to_request(fence);
engine = rq->engine;
- rcu_read_lock();
+ local_bh_disable();
+ rcu_read_lock(); /* RCU serialisation for set-wedged protection */
if (engine->schedule)
engine->schedule(rq, attr);
rcu_read_unlock();
+ local_bh_enable(); /* kick the tasklets if queues were reprioritised */
}
static void fence_set_priority(struct dma_fence *fence,
Is the sequence not the wrong way around? I would expect disable
preemption, then disable softirq, order for disable, on ofc opposite for
enable.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
