drm/i915/gem: Remove engine auto-magic with FENCE_SUBMIT (v2)

Even though FENCE_SUBMIT is only documented to wait until the request in
the in-fence starts instead of waiting until it completes, it has a bit
more magic than that.  If FENCE_SUBMIT is used to submit something to a
balanced engine, we would wait to assign engines until the primary
request was ready to start and then attempt to assign it to a different
engine than the primary.  There is an IGT test (the bonded-slice subtest
of gem_exec_balancer) which exercises this by submitting a primary batch
to a specific VCS and then using FENCE_SUBMIT to submit a secondary
which can run on any VCS and have i915 figure out which VCS to run it on
such that they can run in parallel.

However, this functionality has never been used in the real world.  The
media driver (the only user of FENCE_SUBMIT) always picks exactly two
physical engines to bond and never asks us to pick which to use.

v2 (Daniel Vetter):
 - Mention the exact IGT test this breaks
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-11-jason@jlekstrand.net

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -3484,7 +3484,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		if (args->flags & I915_EXEC_FENCE_SUBMIT)
 			err = i915_request_await_execution(eb.request,
 							   in_fence,
-							   eb.engine->bond_execute);
+							   NULL);
 		else
 			err = i915_request_await_dma_fence(eb.request,
 							   in_fence);

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -416,13 +416,6 @@ struct intel_engine_cs {
 	 */
 	void		(*submit_request)(struct i915_request *rq);
 
-	/*
-	 * Called on signaling of a SUBMIT_FENCE, passing along the signaling
-	 * request down to the bonded pairs.
-	 */
-	void            (*bond_execute)(struct i915_request *rq,
-					struct dma_fence *signal);
-
 	void		(*release)(struct intel_engine_cs *engine);
 
 	struct intel_engine_execlists execlists;

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

@@ -3655,22 +3655,6 @@ static void virtual_submit_request(struct i915_request *rq)
 	spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags);
 }
 
-static void
-virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
-{
-	intel_engine_mask_t allowed, exec;
-
-	allowed = ~to_request(signal)->engine->mask;
-
-	/* Restrict the bonded request to run on only the available engines */
-	exec = READ_ONCE(rq->execution_mask);
-	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
-		;
-
-	/* Prevent the master from being re-run on the bonded engines */
-	to_request(signal)->execution_mask &= ~allowed;
-}
-
 struct intel_context *
 intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count)
@@ -3731,7 +3715,6 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	ve->base.sched_engine->schedule = i915_schedule;
 	ve->base.sched_engine->kick_backend = kick_execlists;
 	ve->base.submit_request = virtual_submit_request;
-	ve->base.bond_execute = virtual_bond_execute;
 
 	INIT_LIST_HEAD(virtual_queue(ve));
 	tasklet_setup(&ve->base.sched_engine->tasklet, virtual_submission_tasklet);