From: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
Keep a per-engine number of runnable (waiting for GPU time) requests.
v2:
* Move queued increment from insert_request to execlist_submit_request to
avoid bumping when re-ordering for priority.
* Support the counter on the ringbuffer submission path as well, albeit
just notionally. (Chris Wilson)
v3:
* Rebase.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_request.c | 7 +++++++
drivers/gpu/drm/i915/intel_engine_cs.c | 5 +++--
drivers/gpu/drm/i915/intel_lrc.c | 2 ++
drivers/gpu/drm/i915/intel_ringbuffer.h | 6 ++++++
4 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 72bdc203716f..dc85445221e7 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -502,6 +502,9 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request)
engine->emit_breadcrumb(request,
request->ring->vaddr + request->postfix);
+ GEM_BUG_ON(engine->queued == 0);
+ engine->queued--;
+
spin_lock(&request->timeline->lock);
list_move_tail(&request->link, &timeline->requests);
spin_unlock(&request->timeline->lock);
@@ -517,6 +520,8 @@ void i915_gem_request_submit(struct drm_i915_gem_request *request)
/* Will be called from irq-context when using foreign fences. */
spin_lock_irqsave(&engine->timeline->lock, flags);
+ engine->queued++;
+
__i915_gem_request_submit(request);
spin_unlock_irqrestore(&engine->timeline->lock, flags);
@@ -548,6 +553,8 @@ void __i915_gem_request_unsubmit(struct drm_i915_gem_request *request)
timeline = request->timeline;
GEM_BUG_ON(timeline == engine->timeline);
+ engine->queued++;
+
spin_lock(&timeline->lock);
list_move(&request->link, &timeline->requests);
spin_unlock(&timeline->lock);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index b221610f2365..062c7ff88413 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1725,12 +1725,13 @@ void intel_engine_dump(struct intel_engine_cs *engine,
if (i915_terminally_wedged(&engine->i915->gpu_error))
drm_printf(m, "*** WEDGED ***\n");
- drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
+ drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d, queued %u\n",
intel_engine_get_seqno(engine),
intel_engine_last_submit(engine),
engine->hangcheck.seqno,
jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
- engine->timeline->inflight_seqnos);
+ engine->timeline->inflight_seqnos,
+ engine->queued);
drm_printf(m, "\tReset count: %d (global %d)\n",
i915_reset_engine_count(error, engine),
i915_reset_count(error));
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ff25f209d0a5..24ce781d39b7 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -965,6 +965,8 @@ static void execlists_submit_request(struct drm_i915_gem_request *request)
/* Will be called from irq-context when using foreign fences. */
spin_lock_irqsave(&engine->timeline->lock, flags);
+ engine->queued++;
+
insert_request(engine, &request->priotree, request->priotree.priority);
GEM_BUG_ON(!engine->execlists.first);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 27a0c47db51e..332f728ac6b3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -302,6 +302,12 @@ struct intel_engine_cs {
struct intel_ring *buffer;
struct intel_timeline *timeline;
+ /**
+ * @queued: Number of runnable requests submitted to the backend.
+ *
+ * Count of requests waiting for the GPU to execute them.
+ */
+ unsigned int queued;
struct drm_i915_gem_object *default_state;
--
2.14.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
