[Intel-gfx] [CI] drm/i915/gt: Restore ce->signal flush before releasing virtual engine

[Chris Wilson]

Before we mark the virtual engine as no longer inflight, flush any
ongoing signaling that may be using the ce->signal_link along the
previous breadcrumbs. On switch to a new physical engine, that link will
be inserted into the new set of breadcrumbs, causing confusion to an
ongoing iterator.

This patch undoes a last minute mistake introduced into commit
bab0557c8dca ("drm/i915/gt: Remove virtual breadcrumb before transfer"),
to simplify later patches whereby instead of unconditionally applying the
flush, it was only applied if the request itself was going to be reused.

Fixes: bab0557c8dca ("drm/i915/gt: Remove virtual breadcrumb before transfer")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 32 ++++++++++---------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index a5b442683c18..db208bb59364 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -581,21 +581,6 @@ resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
 {
 	struct intel_engine_cs *engine = rq->engine;
 
-	/* Flush concurrent rcu iterators in signal_irq_work */
-	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) {
-		/*
-		 * After this point, the rq may be transferred to a new
-		 * sibling, so before we clear ce->inflight make sure that
-		 * the context has been removed from the b->signalers and
-		 * furthermore we need to make sure that the concurrent
-		 * iterator in signal_irq_work is no longer following
-		 * ce->signal_link.
-		 */
-		i915_request_cancel_breadcrumb(rq);
-		while (atomic_read(&engine->breadcrumbs->signaler_active))
-			cpu_relax();
-	}
-
 	spin_lock_irq(&engine->active.lock);
 
 	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
@@ -609,6 +594,19 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
 	struct intel_engine_cs *engine = rq->engine;
+	bool signals = !list_empty(&ce->signals);
+
+	/* Flush concurrent rcu iterators in signal_irq_work */
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
+		/*
+		 * After this point, the rq may be transferred to a new
+		 * sibling, so before we clear ce->inflight make sure that
+		 * the context has been removed from the b->signalers and
+		 * furthermore we need to make sure that the concurrent
+		 * iterator in signal_irq_work is no longer following
+		 * ce->signal_link.
+		 */
+		i915_request_cancel_breadcrumb(rq);
 
 	/*
 	 * This engine is now too busy to run this virtual request, so
@@ -622,6 +620,10 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 
 	if (READ_ONCE(ve->request))
 		tasklet_hi_schedule(&ve->base.execlists.tasklet);
+
+	/* Flush concurrent signal_irq_work before we reuse the link */
+	while (signals && atomic_read(&engine->breadcrumbs->signaler_active))
+		cpu_relax();
 }
 
 static inline void __execlists_schedule_out(struct i915_request *rq)
-- 
2.20.1