[PATCH 2/7] drm/i915: Keep a count of requests waiting for a slot on GPU

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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.

v4:
 * Rename and move the stats into a container structure. (Chris Wilson)

v5:
 * Re-order fields in struct intel_engine_cs. (Chris Wilson)

v6-v8:
 * Rebases.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
 drivers/gpu/drm/i915/i915_request.c     | 7 +++++++
 drivers/gpu/drm/i915/intel_engine_cs.c  | 5 +++--
 drivers/gpu/drm/i915/intel_lrc.c        | 1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h | 9 +++++++++
 4 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 43c7134a9b93..2052028c1d68 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -525,6 +525,9 @@ void __i915_request_submit(struct i915_request *request)
 	engine->emit_breadcrumb(request,
 				request->ring->vaddr + request->postfix);
 
+	GEM_BUG_ON(engine->request_stats.runnable == 0);
+	engine->request_stats.runnable--;
+
 	spin_lock(&request->timeline->lock);
 	list_move_tail(&request->link, &timeline->requests);
 	spin_unlock(&request->timeline->lock);
@@ -542,6 +545,8 @@ void i915_request_submit(struct i915_request *request)
 	/* Will be called from irq-context when using foreign fences. */
 	spin_lock_irqsave(&engine->timeline->lock, flags);
 
+	engine->request_stats.runnable++;
+
 	__i915_request_submit(request);
 
 	spin_unlock_irqrestore(&engine->timeline->lock, flags);
@@ -581,6 +586,8 @@ void __i915_request_unsubmit(struct i915_request *request)
 	timeline = request->timeline;
 	GEM_BUG_ON(timeline == engine->timeline);
 
+	engine->request_stats.runnable++;
+
 	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 337dfa56a738..3726544cfb00 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1917,12 +1917,13 @@ 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, runnable %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->request_stats.runnable);
 	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 53f1c009ed7b..46bacd98a360 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1033,6 +1033,7 @@ static void execlists_submit_request(struct i915_request *request)
 
 	queue_request(engine, &request->priotree, rq_prio(request));
 	submit_queue(engine, rq_prio(request));
+	engine->request_stats.runnable++;
 
 	GEM_BUG_ON(!engine->execlists.first);
 	GEM_BUG_ON(list_empty(&request->priotree.link));
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 828a1f924405..e98e007cb96b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -338,6 +338,15 @@ struct intel_engine_cs {
 
 	struct drm_i915_gem_object *default_state;
 
+	struct {
+		/**
+		 * @runnable: Number of runnable requests sent to the backend.
+		 *
+		 * Count of requests waiting for the GPU to execute them.
+		 */
+		unsigned int runnable;
+	} request_stats;
+
 	atomic_t irq_count;
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux