[PATCH 75/91] drm/i915/guc: Implement multi-lrc reset

Matthew Brost matthew.brost at intel.com
Tue Jul 20 05:34:47 UTC 2021


Update context and full GPU reset to work with multi-lrc. The idea is
parent context tracks all the active requests inflight for itself and
its' children. The parent context owns the reset replaying / canceling
requests as needed.

Signed-off-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.c       | 12 +++--
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 54 ++++++++++++++-----
 2 files changed, 47 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index dd7484c52916..c4ec136d1a83 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -604,20 +604,22 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 
 struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 {
+	struct intel_context *parent = intel_context_is_child(ce) ?
+		ce->parent : ce;
 	struct i915_request *rq, *active = NULL;
 	unsigned long flags;
 
 	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
 
-	spin_lock_irqsave(&ce->guc_active.lock, flags);
-	list_for_each_entry_reverse(rq, &ce->guc_active.requests,
+	spin_lock_irqsave(&parent->guc_active.lock, flags);
+	list_for_each_entry_reverse(rq, &parent->guc_active.requests,
 				    sched.link) {
-		if (i915_request_completed(rq))
+		if (i915_request_completed(rq) && rq->context == ce)
 			break;
 
-		active = rq;
+		active = (rq->context == ce) ? rq : active;
 	}
-	spin_unlock_irqrestore(&ce->guc_active.lock, flags);
+	spin_unlock_irqrestore(&parent->guc_active.lock, flags);
 
 	return active;
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 86691e4b6ee5..a5b2b997d645 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -810,6 +810,11 @@ static inline int rq_prio(const struct i915_request *rq)
 	return rq->sched.attr.priority;
 }
 
+static inline bool is_multi_lrc(struct intel_context *ce)
+{
+	return intel_context_is_parallel(ce);
+}
+
 static inline bool is_multi_lrc_rq(struct i915_request *rq)
 {
 	return intel_context_is_parallel(rq->context);
@@ -1371,6 +1376,8 @@ __unwind_incomplete_requests(struct intel_context *ce)
 		ce->engine->sched_engine;
 	unsigned long flags;
 
+	GEM_BUG_ON(intel_context_is_child(ce));
+
 	spin_lock_irqsave(&sched_engine->lock, flags);
 	spin_lock(&ce->guc_active.lock);
 	list_for_each_entry_safe(rq, rn,
@@ -1403,8 +1410,12 @@ __unwind_incomplete_requests(struct intel_context *ce)
 
 static void __guc_reset_context(struct intel_context *ce, bool stalled)
 {
+	bool local_stalled;
 	struct i915_request *rq;
 	u32 head;
+	int i, number_children = ce->guc_number_children;
+
+	GEM_BUG_ON(intel_context_is_child(ce));
 
 	intel_context_get(ce);
 
@@ -1416,22 +1427,32 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	 */
 	clr_context_enabled(ce);
 
-	rq = intel_context_find_active_request(ce);
-	if (!rq) {
-		head = ce->ring->tail;
-		stalled = false;
-		goto out_replay;
-	}
+	for (i = 0; i < number_children + 1; ++i) {
+		if (!intel_context_is_pinned(ce))
+			goto next_context;
+
+		local_stalled = false;
+		rq = intel_context_find_active_request(ce);
+		if (!rq) {
+			head = ce->ring->tail;
+			goto out_replay;
+		}
 
-	if (!i915_request_started(rq))
-		stalled = false;
+		GEM_BUG_ON(i915_active_is_idle(&ce->active));
+		head = intel_ring_wrap(ce->ring, rq->head);
 
-	GEM_BUG_ON(i915_active_is_idle(&ce->active));
-	head = intel_ring_wrap(ce->ring, rq->head);
-	__i915_request_reset(rq, stalled);
+		if (i915_request_started(rq))
+			local_stalled = true;
 
+		__i915_request_reset(rq, local_stalled && stalled);
 out_replay:
-	guc_reset_state(ce, head, stalled);
+		guc_reset_state(ce, head, local_stalled && stalled);
+next_context:
+		if (i != number_children)
+			ce = list_next_entry(ce, guc_child_link);
+	}
+	ce = intel_context_to_parent(ce);
+
 	__unwind_incomplete_requests(ce);
 	ce->guc_num_rq_submit_no_id = 0;
 	intel_context_put(ce);
@@ -1447,9 +1468,11 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
 		return;
 
 	xa_for_each(&guc->context_lookup, index, ce)
-		if (intel_context_is_pinned(ce))
+		if (intel_context_is_pinned(ce) &&
+		    !intel_context_is_child(ce))
 			__guc_reset_context(ce, stalled);
 
+	/* GuC is blown away, drop all references to contexts */
 	xa_destroy(&guc->context_lookup);
 }
 
@@ -1532,7 +1555,8 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 	int i;
 
 	xa_for_each(&guc->context_lookup, index, ce)
-		if (intel_context_is_pinned(ce))
+		if (intel_context_is_pinned(ce) &&
+		    !intel_context_is_child(ce))
 			guc_cancel_context_requests(ce);
 
 	for (i = 0; i < GUC_SUBMIT_ENGINE_MAX; ++i)
@@ -2795,6 +2819,8 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
 	intel_wakeref_t wakeref;
 	unsigned long flags;
 
+	GEM_BUG_ON(intel_context_is_child(ce));
+
 	gse_flush_submissions(ce_to_gse(ce));
 
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
-- 
2.28.0



More information about the Intel-gfx-trybot mailing list