[PATCH 5/5] post-process-csb

[Chris Wilson]

---
 drivers/gpu/drm/i915/gt/intel_engine_types.h | 13 +++++++++
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 28 +++++++++++++++++---
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 073c3769e8cc..31cf60cef5a8 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -208,6 +208,10 @@ struct intel_engine_execlists {
 	 * @active: the currently known context executing on HW
 	 */
 	struct i915_request * const *active;
+	/**
+	 * @inactive: the current vacancy of completed CS
+	 */
+	struct i915_request **inactive;
 	/**
 	 * @inflight: the set of contexts submitted and acknowleged by HW
 	 *
@@ -225,6 +229,15 @@ struct intel_engine_execlists {
 	 * preemption or idle-to-active event.
 	 */
 	struct i915_request *pending[EXECLIST_MAX_PORTS + 1];
+	/**
+	 * @post: the set of completed context switches
+	 *
+	 * Since we may want to stagger the processing of the CS switches
+	 * with the next submission, so that the context are notionally
+	 * kept in flight across the dequeue, we defer scheduling out of
+	 * the completed context switches.
+	 */
+	struct i915_request *post[2 * EXECLIST_MAX_PORTS + 1];
 
 	/**
 	 * @port_mask: number of execlist ports - 1
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 5f33342c15e2..355b5383d3dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2055,9 +2055,10 @@ static void set_preempt_timeout(struct intel_engine_cs *engine,
 		     active_preempt_timeout(engine, rq));
 }
 
-static inline void clear_ports(struct i915_request **ports, int count)
+static inline struct i915_request **
+clear_ports(struct i915_request **ports, int count)
 {
-	memset_p((void **)ports, NULL, count);
+	return memset_p((void **)ports, NULL, count);
 }
 
 static void execlists_dequeue(struct intel_engine_cs *engine)
@@ -2455,6 +2456,10 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 {
 	struct i915_request * const *port;
 
+	for (port = execlists->post; *port; port++)
+		execlists_schedule_out(*port);
+	clear_ports(execlists->post, ARRAY_SIZE(execlists->post));
+
 	for (port = execlists->pending; *port; port++)
 		execlists_schedule_out(*port);
 	clear_ports(execlists->pending, ARRAY_SIZE(execlists->pending));
@@ -2622,7 +2627,7 @@ static void process_csb(struct intel_engine_cs *engine)
 			/* cancel old inflight, prepare for switch */
 			trace_ports(execlists, "preempted", old);
 			while (*old)
-				execlists_schedule_out(*old++);
+				*execlists->inactive++ = *old++;
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
@@ -2679,7 +2684,7 @@ static void process_csb(struct intel_engine_cs *engine)
 					     regs[CTX_RING_TAIL]);
 			}
 
-			execlists_schedule_out(*execlists->active++);
+			*execlists->inactive++ = *execlists->active++;
 
 			GEM_BUG_ON(execlists->active - execlists->inflight >
 				   execlists_num_ports(execlists));
@@ -2703,6 +2708,18 @@ static void process_csb(struct intel_engine_cs *engine)
 	invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
 }
 
+static void post_process_csb(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const el = &engine->execlists;
+	struct i915_request **port;
+
+	GEM_BUG_ON(el->post[2 * EXECLIST_MAX_PORTS]);
+
+	for (port = el->post; *port; port++)
+		execlists_schedule_out(*port);
+	el->inactive = clear_ports(el->post, port - el->post);
+}
+
 static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->active.lock);
@@ -3133,6 +3150,8 @@ static void execlists_submission_tasklet(unsigned long data)
 		if (unlikely(timeout && preempt_timeout(engine)))
 			execlists_reset(engine, "preemption time out");
 	}
+
+	post_process_csb(engine);
 }
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
@@ -4176,6 +4195,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	mb();
 
 	process_csb(engine); /* drain preemption events */
+	post_process_csb(engine);
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
 	reset_csb_pointers(engine);
-- 
2.20.1