[Intel-gfx] [PATCH 13/21] drm/i915/guc: Add support for resume-parsing wq item

[Michal Wajdeczko]

Since fw version 25.161, GuC lets us know when an engine had to be reset
due to a hang in another dependent engine, by setting BIT(engine_class) in
the queue_engine_error field. GuC will ignore any other wq item until this
flag is cleared.

To restart the workqueue processing for that engine, we must insert a
special wq item called resume-parsing and wait until the queue_engine_error
field is updated.

Signed-off-by: Michel Thierry <michel.thierry at intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
Cc: Michel Thierry <michel.thierry at intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar at intel.com>
Cc: MichaĹ Winiarski <michal.winiarski at intel.com>
Cc: Tomasz Lis <tomasz.lis at intel.com>
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 92 +++++++++++++++++++++++++++--
 1 file changed, 86 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 378f97e..5df0204 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -411,6 +411,77 @@ static void guc_stage_desc_fini(struct intel_guc *guc,
 	desc->wq_size = 0;
 }
 
+static u32 get_wq_offset(struct guc_process_desc *desc)
+{
+	const size_t wqi_size = sizeof(struct guc_wq_item);
+	u32 wq_off;
+
+	/*
+	 * Free space is guaranteed, either by normal port submission or
+	 * because we waited for the wq_resume to be processed.
+	 */
+	wq_off = READ_ONCE(desc->tail);
+	GEM_BUG_ON(CIRC_SPACE(wq_off, READ_ONCE(desc->head),
+			      GUC_WQ_SIZE) < wqi_size);
+	GEM_BUG_ON(wq_off & (wqi_size - 1));
+
+	return wq_off;
+}
+
+static void write_wqi(struct guc_process_desc *desc, u32 wq_off)
+{
+	const size_t wqi_size = sizeof(struct guc_wq_item);
+
+	WRITE_ONCE(desc->tail, (wq_off + wqi_size) & (GUC_WQ_SIZE - 1));
+}
+
+static void guc_append_wq_resume_parsing_item(struct intel_guc_client *client,
+					      struct intel_engine_cs *engine)
+{
+	struct guc_process_desc *desc = __get_process_desc(client);
+	const u32 target_engine = engine->guc_id;
+	const u32 wqi_resume = WQ_TYPE_RESUME |
+			       (target_engine << WQ_TARGET_SHIFT) |
+			       (0 << WQ_LEN_SHIFT);
+	const u32 wqi_noop = WQ_TYPE_NOOP |
+			    (target_engine << WQ_TARGET_SHIFT) |
+			    (0 << WQ_LEN_SHIFT);
+	struct guc_wq_item *wqi;
+	u32 wq_off;
+
+	lockdep_assert_held(&client->wq_lock);
+
+	wq_off = get_wq_offset(desc);
+	wqi = client->vaddr + wq_off + GUC_DB_SIZE;
+
+	/*
+	 * Submit 4 wq_items (1 RESUME_WQ_PARSING followed by 3 NOOPs) in
+	 * order to keep it the same size as a 'normal' wq_item.
+	 */
+	wqi->header = wqi_resume;
+	wqi->context_desc = wqi_noop;
+	wqi->submit_element_info = wqi_noop;
+	wqi->fence_id = wqi_noop;
+
+	write_wqi(desc, wq_off);
+}
+
+#define GUC_WAIT_FOR_ENGINE_ERROR_CLEANED_MS 10
+
+static void guc_wait_wq_resumed(struct intel_guc_client *client,
+				struct intel_engine_cs *engine)
+{
+	struct guc_process_desc *desc = __get_process_desc(client);
+	const u32 target_engine_class = engine->guc_class;
+
+	lockdep_assert_held(&client->wq_lock);
+
+	/* must wait for the flag to be cleared */
+	WARN_ON(wait_for_atomic(!(desc->queue_engine_error &
+				  BIT(target_engine_class)),
+				GUC_WAIT_FOR_ENGINE_ERROR_CLEANED_MS));
+}
+
 /* Construct a Work Item and append it to the GuC's Work Queue */
 static void guc_wq_item_append(struct intel_guc_client *client,
 			       struct intel_context *ce,
@@ -438,11 +509,7 @@ static void guc_wq_item_append(struct intel_guc_client *client,
 	/* We expect the WQ to be active if we're appending items to it */
 	GEM_BUG_ON(desc->wq_status != WQ_STATUS_ACTIVE);
 
-	/* Free space is guaranteed. */
-	wq_off = READ_ONCE(desc->tail);
-	GEM_BUG_ON(CIRC_SPACE(wq_off, READ_ONCE(desc->head),
-			      GUC_WQ_SIZE) < wqi_size);
-	GEM_BUG_ON(wq_off & (wqi_size - 1));
+	wq_off = get_wq_offset(desc);
 
 	/* WQ starts from the page after doorbell / process_desc */
 	wqi = client->vaddr + wq_off + GUC_DB_SIZE;
@@ -465,7 +532,7 @@ static void guc_wq_item_append(struct intel_guc_client *client,
 	}
 
 	/* Make the update visible to GuC */
-	WRITE_ONCE(desc->tail, (wq_off + wqi_size) & (GUC_WQ_SIZE - 1));
+	write_wqi(desc, wq_off);
 }
 
 static void guc_reset_wq(struct intel_guc_client *client)
@@ -497,6 +564,14 @@ static void guc_ring_doorbell(struct intel_guc_client *client)
 	GEM_BUG_ON(db->db_status != GUC_DOORBELL_ENABLED);
 }
 
+static bool guc_needs_wq_resume_parsing_item(struct intel_guc_client *client,
+					     u32 target_engine_class)
+{
+	struct guc_process_desc *desc = __get_process_desc(client);
+
+	return desc->queue_engine_error & BIT(target_engine_class);
+}
+
 static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_guc_client *client = guc->execbuf_client;
@@ -507,6 +582,11 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 
 	spin_lock(&client->wq_lock);
 
+	if (guc_needs_wq_resume_parsing_item(client, engine->guc_class)) {
+		guc_append_wq_resume_parsing_item(client, engine);
+		guc_wait_wq_resumed(client, engine);
+	}
+
 	guc_wq_item_append(client, ce, engine->guc_id, ctx_desc,
 			   ring_tail, rq->global_seqno);
 	guc_ring_doorbell(client);
-- 
1.9.1