[Intel-gfx] [PATCH 1/2] drm/i915: Keep a count of requests waiting for a slot on GPU

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Keep a per-engine number of runnable (waiting for GPU time) requests.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_request.c | 5 +++++
 drivers/gpu/drm/i915/intel_engine_cs.c  | 5 +++--
 drivers/gpu/drm/i915/intel_lrc.c        | 1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h | 8 ++++++++
 4 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 7325469ce754..e3c74cafa7d4 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -480,6 +480,9 @@ 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);
@@ -525,6 +528,8 @@ 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 d53680c08cb0..cc9d60130ddd 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1675,12 +1675,13 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 	u64 addr;
 
 	drm_printf(m, "%s\n", engine->name);
-	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 %d\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,
+		   INTEL_GEN(dev_priv) >= 8 ? engine->queued : -1);
 	drm_printf(m, "\tReset count: %d\n",
 		   i915_reset_engine_count(error, engine));
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 570864583e28..c4c53ad67b4c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -953,6 +953,7 @@ static void insert_request(struct intel_engine_cs *engine,
 {
 	struct i915_priolist *p = lookup_priolist(engine, pt, prio);
 
+	engine->queued++;
 	list_add_tail(&pt->link, &ptr_mask_bits(p, 1)->requests);
 	if (ptr_unmask_bits(p, 1))
 		tasklet_hi_schedule(&engine->execlists.tasklet);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 37a389ff031e..fe1651ec9756 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -297,6 +297,14 @@ 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.
+	 *
+	 * Valid only with execlists and GuC submissions backends.
+	 */
+	unsigned int queued;
 
 	struct drm_i915_gem_object *default_state;
 
-- 
2.14.1