drm/i915/execlists: Tweak virtual unsubmission

Since commit e2144503 ("drm/i915: Prevent bonded requests from
overtaking each other on preemption") we have restricted requests to run
on their chosen engine across preemption events. We can take this
restriction into account to know that we will want to resubmit those
requests onto the same physical engine, and so can shortcircuit the
virtual engine selection process and keep the request on the same
engine during unwind.

References: e2144503 ("drm/i915: Prevent bonded requests from overtaking each other on preemption")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Ramlingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191013203012.25208-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -847,7 +847,6 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	list_for_each_entry_safe_reverse(rq, rn,
 					 &engine->active.requests,
 					 sched.link) {
-		struct intel_engine_cs *owner;
 
 		if (i915_request_completed(rq))
 			continue; /* XXX */
@@ -862,8 +861,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 		 * engine so that it can be moved across onto another physical
 		 * engine as load dictates.
 		 */
-		owner = rq->hw_context->engine;
-		if (likely(owner == engine)) {
+		if (likely(rq->execution_mask == engine->mask)) {
 			GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
 			if (rq_prio(rq) != prio) {
 				prio = rq_prio(rq);
@@ -874,6 +872,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			active = rq;
 		} else {
+			struct intel_engine_cs *owner = rq->hw_context->engine;
+
 			/*
 			 * Decouple the virtual breadcrumb before moving it
 			 * back to the virtual engine -- we don't want the

drivers/gpu/drm/i915/i915_request.c

@@ -649,6 +649,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->gem_context = ce->gem_context;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
+	rq->execution_mask = ce->engine->mask;
 
 	rcu_assign_pointer(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;
@@ -671,7 +672,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->batch = NULL;
 	rq->capture_list = NULL;
 	rq->flags = 0;
-	rq->execution_mask = ALL_ENGINES;
 
 	INIT_LIST_HEAD(&rq->execute_cb);