Since we use a flag within i915_request.flags to indicate when we have
boosted the request (so that we only apply the boost) once, this can be
used as the serialisation with i915_request_retire() to avoid having to
explicitly take the i915_request.lock which is more heavily contended.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/gt/debugfs_gt_pm.c | 2 +-
drivers/gpu/drm/i915/gt/intel_rps.c | 23 +++++++++++------------
drivers/gpu/drm/i915/gt/intel_rps_types.h | 2 +-
drivers/gpu/drm/i915/i915_debugfs.c | 2 +-
drivers/gpu/drm/i915/i915_request.c | 4 +---
5 files changed, 15 insertions(+), 18 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
index a0f10e8bbd21..d4f4452ce5ed 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -578,7 +578,7 @@ static int rps_boost_show(struct seq_file *m, void *data)
intel_gpu_freq(rps, rps->efficient_freq),
intel_gpu_freq(rps, rps->boost_freq));
- seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
+ seq_printf(m, "Wait boosts: %d\n", READ_ONCE(rps->boosts));
if (INTEL_GEN(i915) >= 6 && intel_rps_is_active(rps)) {
struct intel_uncore *uncore = gt->uncore;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index f74d5e09e176..146a956ed12d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -917,28 +917,27 @@ void intel_rps_park(struct intel_rps *rps)
void intel_rps_boost(struct i915_request *rq)
{
- struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
- unsigned long flags;
-
- if (i915_request_signaled(rq) || !intel_rps_is_active(rps))
+ if (i915_request_signaled(rq) || i915_request_has_waitboost(rq))
return;
/* Serializes with i915_request_retire() */
- spin_lock_irqsave(&rq->lock, flags);
- if (!i915_request_has_waitboost(rq) &&
- !dma_fence_is_signaled_locked(&rq->fence)) {
- set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
+ if (!test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) {
+ struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
+
+ if (atomic_fetch_inc(&rps->num_waiters))
+ return;
+
+ if (!intel_rps_is_active(rps))
+ return;
GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
rq->fence.context, rq->fence.seqno);
- if (!atomic_fetch_inc(&rps->num_waiters) &&
- READ_ONCE(rps->cur_freq) < rps->boost_freq)
+ if (READ_ONCE(rps->cur_freq) < rps->boost_freq)
schedule_work(&rps->work);
- atomic_inc(&rps->boosts);
+ WRITE_ONCE(rps->boosts, rps->boosts + 1); /* debug only */
}
- spin_unlock_irqrestore(&rq->lock, flags);
}
int intel_rps_set(struct intel_rps *rps, u8 val)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps_types.h b/drivers/gpu/drm/i915/gt/intel_rps_types.h
index 38083f0402d9..029fe13cf303 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps_types.h
@@ -93,7 +93,7 @@ struct intel_rps {
} power;
atomic_t num_waiters;
- atomic_t boosts;
+ unsigned int boosts;
/* manual wa residency calculations */
struct intel_rps_ei ei;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7332478a3dd5..de8e0e44cfb6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -811,7 +811,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
intel_gpu_freq(rps, rps->efficient_freq),
intel_gpu_freq(rps, rps->boost_freq));
- seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
+ seq_printf(m, "Wait boosts: %d\n", READ_ONCE(rps->boosts));
return 0;
}
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 03ac6eead4db..8db3391d8625 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -307,10 +307,8 @@ bool i915_request_retire(struct i915_request *rq)
spin_unlock_irq(&rq->lock);
}
- if (i915_request_has_waitboost(rq)) {
- GEM_BUG_ON(!atomic_read(&rq->engine->gt->rps.num_waiters));
+ if (test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags))
atomic_dec(&rq->engine->gt->rps.num_waiters);
- }
/*
* We only loosely track inflight requests across preemption,
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
