[PATCH 28/28] direct-submit

Chris Wilson chris at chris-wilson.co.uk
Tue May 15 22:23:58 UTC 2018


---
 drivers/gpu/drm/i915/i915_irq.c  | 10 ++----
 drivers/gpu/drm/i915/intel_lrc.c | 62 ++++++++++++++++++--------------
 2 files changed, 37 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b3daee06e0d6..6ccb5c43fed1 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1465,22 +1465,16 @@ static void
 gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	bool tasklet = false;
 
-	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
 		execlists_process_csb(engine);
-		tasklet = true;
-	}
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
 		if (intel_engine_uses_guc(engine))
-			tasklet = true;
+			tasklet_hi_schedule(&execlists->tasklet);
 
 		notify_ring(engine);
 	}
-
-	if (tasklet)
-		tasklet_hi_schedule(&execlists->tasklet);
 }
 
 static void gen8_gt_irq_ack(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 8df623d6d442..48769128cfd1 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -565,7 +565,7 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
-static bool __execlists_dequeue(struct intel_engine_cs *engine)
+static void __execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -577,7 +577,11 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->timeline.lock);
 
-	/* Hardware submission is through 2 ports. Conceptually each port
+	if (execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
+		return;
+
+	/*
+	 * Hardware submission is through 2 ports. Conceptually each port
 	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
 	 * static for a context, and unique to each, so we only execute
 	 * requests belonging to a single context from each ring. RING_HEAD
@@ -611,8 +615,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(!execlists_is_active(execlists,
 						EXECLISTS_ACTIVE_USER));
 		GEM_BUG_ON(!port_count(&port[0]));
-		if (port_count(&port[0]) > 1)
-			return false;
 
 		/*
 		 * If we write to ELSP a second time before the HW has had
@@ -622,11 +624,11 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * the HW to indicate that it has had a chance to respond.
 		 */
 		if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK))
-			return false;
+			return;
 
 		if (need_preempt(engine, last, execlists->queue_priority)) {
 			inject_preempt_context(engine);
-			return false;
+			return;
 		}
 
 		/*
@@ -651,7 +653,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * priorities of the ports haven't been switch.
 		 */
 		if (port_count(&port[1]))
-			return false;
+			return;
 
 		/*
 		 * WaIdleLiteRestore:bdw,skl
@@ -751,8 +753,10 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
 	execlists->first = rb;
-	if (submit)
+	if (submit) {
 		port_assign(port, last);
+		execlists_submit_ports(engine);
+	}
 
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
@@ -761,24 +765,17 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 	if (last)
 		execlists_user_begin(execlists, execlists->port);
 
-	return submit;
+	GEM_BUG_ON(port_isset(execlists->port) &&
+		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
 }
 
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
-	bool submit;
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-	submit = __execlists_dequeue(engine);
+	__execlists_dequeue(engine);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
-	if (submit)
-		execlists_submit_ports(engine);
-
-	GEM_BUG_ON(port_isset(execlists->port) &&
-		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
 }
 
 void
@@ -966,6 +963,8 @@ void execlists_process_csb(struct intel_engine_cs *engine)
 
 	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
 
+	spin_lock(&engine->timeline.lock);
+
 	do {
 		struct i915_request *rq;
 		unsigned int status;
@@ -1084,6 +1083,9 @@ void execlists_process_csb(struct intel_engine_cs *engine)
 	writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
 	       execlists->csb_read);
 	execlists->csb_head = head;
+
+	__execlists_dequeue(engine);
+	spin_unlock(&engine->timeline.lock);
 }
 
 /*
@@ -1109,8 +1111,7 @@ static void execlists_submission_tasklet(unsigned long data)
 	 */
 	GEM_BUG_ON(!engine->i915->gt.awake);
 
-	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
-		execlists_dequeue(engine);
+	execlists_dequeue(engine);
 
 	/* If the engine is now idle, so should be the flag; and vice versa. */
 	GEM_BUG_ON(execlists_is_active(&engine->execlists,
@@ -1126,16 +1127,20 @@ static void queue_request(struct intel_engine_cs *engine,
 		      &lookup_priolist(engine, prio)->requests);
 }
 
-static void __submit_queue(struct intel_engine_cs *engine, int prio)
+static void __update_queue(struct intel_engine_cs *engine, int prio)
 {
 	engine->execlists.queue_priority = prio;
-	tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
 static void submit_queue(struct intel_engine_cs *engine, int prio)
 {
-	if (prio > engine->execlists.queue_priority)
-		__submit_queue(engine, prio);
+	if (prio > engine->execlists.queue_priority) {
+		__update_queue(engine, prio);
+		if (!intel_engine_uses_guc(engine))
+			__execlists_dequeue(engine);
+		else
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+	}
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -1147,11 +1152,12 @@ static void execlists_submit_request(struct i915_request *request)
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	queue_request(engine, &request->sched, rq_prio(request));
-	submit_queue(engine, rq_prio(request));
 
 	GEM_BUG_ON(!engine->execlists.first);
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
+	submit_queue(engine, rq_prio(request));
+
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
@@ -1278,8 +1284,10 @@ static void execlists_schedule(struct i915_request *request,
 		}
 
 		if (prio > engine->execlists.queue_priority &&
-		    i915_sw_fence_done(&sched_to_request(node)->submit))
-			__submit_queue(engine, prio);
+		    i915_sw_fence_done(&sched_to_request(node)->submit)) {
+			__update_queue(engine, prio);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+		}
 	}
 
 	spin_unlock_irq(&engine->timeline.lock);
-- 
2.17.0



More information about the Intel-gfx-trybot mailing list