Merge drm/drm-next into drm-misc-next

drm-misc-next hasn't been updated in a while and I need a post -rc2
state to merge some vc4 patches.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

1 files changed, 127 insertions, 41 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 3839712ebd23..820a1f38b271 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg)
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
-
 	rq->capture_list = NULL;
 
 	init_llist_head(&rq->execute_cb);
@@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
-	kref_init(&rq->fence.refcount);
-	rq->fence.flags = 0;
-	rq->fence.error = 0;
-	INIT_LIST_HEAD(&rq->fence.cb_list);
-
 	ret = intel_timeline_get_seqno(tl, rq, &seqno);
 	if (ret)
 		goto err_free;
 
-	rq->fence.context = tl->fence_context;
-	rq->fence.seqno = seqno;
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
+		       tl->fence_context, seqno);
 
 	RCU_INIT_POINTER(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;
@@ -1152,6 +1145,12 @@ __emit_semaphore_wait(struct i915_request *to,
 	return 0;
 }
 
+static bool
+can_use_semaphore_wait(struct i915_request *to, struct i915_request *from)
+{
+	return to->engine->gt->ggtt == from->engine->gt->ggtt;
+}
+
 static int
 emit_semaphore_wait(struct i915_request *to,
 		    struct i915_request *from,
@@ -1160,6 +1159,9 @@ emit_semaphore_wait(struct i915_request *to,
 	const intel_engine_mask_t mask = READ_ONCE(from->engine)->mask;
 	struct i915_sw_fence *wait = &to->submit;
 
+	if (!can_use_semaphore_wait(to, from))
+		goto await_fence;
+
 	if (!intel_context_use_semaphores(to->context))
 		goto await_fence;
 
@@ -1263,7 +1265,8 @@ __i915_request_await_execution(struct i915_request *to,
 	 * immediate execution, and so we must wait until it reaches the
 	 * active slot.
 	 */
-	if (intel_engine_has_semaphores(to->engine) &&
+	if (can_use_semaphore_wait(to, from) &&
+	    intel_engine_has_semaphores(to->engine) &&
 	    !i915_request_has_initial_breadcrumb(to)) {
 		err = __emit_semaphore_wait(to, from, from->fence.seqno - 1);
 		if (err < 0)
@@ -1332,6 +1335,25 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
 	return err;
 }
 
+static inline bool is_parallel_rq(struct i915_request *rq)
+{
+	return intel_context_is_parallel(rq->context);
+}
+
+static inline struct intel_context *request_to_parent(struct i915_request *rq)
+{
+	return intel_context_to_parent(rq->context);
+}
+
+static bool is_same_parallel_context(struct i915_request *to,
+				     struct i915_request *from)
+{
+	if (is_parallel_rq(to))
+		return request_to_parent(to) == request_to_parent(from);
+
+	return false;
+}
+
 int
 i915_request_await_execution(struct i915_request *rq,
 			     struct dma_fence *fence)
@@ -1363,11 +1385,14 @@ i915_request_await_execution(struct i915_request *rq,
 		 * want to run our callback in all cases.
 		 */
 
-		if (dma_fence_is_i915(fence))
+		if (dma_fence_is_i915(fence)) {
+			if (is_same_parallel_context(rq, to_request(fence)))
+				continue;
 			ret = __i915_request_await_execution(rq,
 							     to_request(fence));
-		else
+		} else {
 			ret = i915_request_await_external(rq, fence);
+		}
 		if (ret < 0)
 			return ret;
 	} while (--nchild);
@@ -1468,10 +1493,13 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 						 fence))
 			continue;
 
-		if (dma_fence_is_i915(fence))
+		if (dma_fence_is_i915(fence)) {
+			if (is_same_parallel_context(rq, to_request(fence)))
+				continue;
 			ret = i915_request_await_request(rq, to_request(fence));
-		else
+		} else {
 			ret = i915_request_await_external(rq, fence);
+		}
 		if (ret < 0)
 			return ret;
 
@@ -1523,35 +1551,51 @@ i915_request_await_object(struct i915_request *to,
 }
 
 static struct i915_request *
-__i915_request_add_to_timeline(struct i915_request *rq)
+__i915_request_ensure_parallel_ordering(struct i915_request *rq,
+					struct intel_timeline *timeline)
 {
-	struct intel_timeline *timeline = i915_request_timeline(rq);
 	struct i915_request *prev;
 
-	/*
-	 * Dependency tracking and request ordering along the timeline
-	 * is special cased so that we can eliminate redundant ordering
-	 * operations while building the request (we know that the timeline
-	 * itself is ordered, and here we guarantee it).
-	 *
-	 * As we know we will need to emit tracking along the timeline,
-	 * we embed the hooks into our request struct -- at the cost of
-	 * having to have specialised no-allocation interfaces (which will
-	 * be beneficial elsewhere).
-	 *
-	 * A second benefit to open-coding i915_request_await_request is
-	 * that we can apply a slight variant of the rules specialised
-	 * for timelines that jump between engines (such as virtual engines).
-	 * If we consider the case of virtual engine, we must emit a dma-fence
-	 * to prevent scheduling of the second request until the first is
-	 * complete (to maximise our greedy late load balancing) and this
-	 * precludes optimising to use semaphores serialisation of a single
-	 * timeline across engines.
-	 */
+	GEM_BUG_ON(!is_parallel_rq(rq));
+
+	prev = request_to_parent(rq)->parallel.last_rq;
+	if (prev) {
+		if (!__i915_request_is_complete(prev)) {
+			i915_sw_fence_await_sw_fence(&rq->submit,
+						     &prev->submit,
+						     &rq->submitq);
+
+			if (rq->engine->sched_engine->schedule)
+				__i915_sched_node_add_dependency(&rq->sched,
+								 &prev->sched,
+								 &rq->dep,
+								 0);
+		}
+		i915_request_put(prev);
+	}
+
+	request_to_parent(rq)->parallel.last_rq = i915_request_get(rq);
+
+	return to_request(__i915_active_fence_set(&timeline->last_request,
+						  &rq->fence));
+}
+
+static struct i915_request *
+__i915_request_ensure_ordering(struct i915_request *rq,
+			       struct intel_timeline *timeline)
+{
+	struct i915_request *prev;
+
+	GEM_BUG_ON(is_parallel_rq(rq));
+
 	prev = to_request(__i915_active_fence_set(&timeline->last_request,
 						  &rq->fence));
+
 	if (prev && !__i915_request_is_complete(prev)) {
 		bool uses_guc = intel_engine_uses_guc(rq->engine);
+		bool pow2 = is_power_of_2(READ_ONCE(prev->engine)->mask |
+					  rq->engine->mask);
+		bool same_context = prev->context == rq->context;
 
 		/*
 		 * The requests are supposed to be kept in order. However,
@@ -1559,13 +1603,11 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 		 * is used as a barrier for external modification to this
 		 * context.
 		 */
-		GEM_BUG_ON(prev->context == rq->context &&
+		GEM_BUG_ON(same_context &&
 			   i915_seqno_passed(prev->fence.seqno,
 					     rq->fence.seqno));
 
-		if ((!uses_guc &&
-		     is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) ||
-		    (uses_guc && prev->context == rq->context))
+		if ((same_context && uses_guc) || (!uses_guc && pow2))
 			i915_sw_fence_await_sw_fence(&rq->submit,
 						     &prev->submit,
 						     &rq->submitq);
@@ -1580,6 +1622,50 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
+	return prev;
+}
+
+static struct i915_request *
+__i915_request_add_to_timeline(struct i915_request *rq)
+{
+	struct intel_timeline *timeline = i915_request_timeline(rq);
+	struct i915_request *prev;
+
+	/*
+	 * Dependency tracking and request ordering along the timeline
+	 * is special cased so that we can eliminate redundant ordering
+	 * operations while building the request (we know that the timeline
+	 * itself is ordered, and here we guarantee it).
+	 *
+	 * As we know we will need to emit tracking along the timeline,
+	 * we embed the hooks into our request struct -- at the cost of
+	 * having to have specialised no-allocation interfaces (which will
+	 * be beneficial elsewhere).
+	 *
+	 * A second benefit to open-coding i915_request_await_request is
+	 * that we can apply a slight variant of the rules specialised
+	 * for timelines that jump between engines (such as virtual engines).
+	 * If we consider the case of virtual engine, we must emit a dma-fence
+	 * to prevent scheduling of the second request until the first is
+	 * complete (to maximise our greedy late load balancing) and this
+	 * precludes optimising to use semaphores serialisation of a single
+	 * timeline across engines.
+	 *
+	 * We do not order parallel submission requests on the timeline as each
+	 * parallel submission context has its own timeline and the ordering
+	 * rules for parallel requests are that they must be submitted in the
+	 * order received from the execbuf IOCTL. So rather than using the
+	 * timeline we store a pointer to last request submitted in the
+	 * relationship in the gem context and insert a submission fence
+	 * between that request and request passed into this function or
+	 * alternatively we use completion fence if gem context has a single
+	 * timeline and this is the first submission of an execbuf IOCTL.
+	 */
+	if (likely(!is_parallel_rq(rq)))
+		prev = __i915_request_ensure_ordering(rq, timeline);
+	else
+		prev = __i915_request_ensure_parallel_ordering(rq, timeline);
+
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before
@@ -1835,7 +1921,7 @@ long i915_request_wait(struct i915_request *rq,
 	 * completion. That requires having a good predictor for the request
 	 * duration, which we currently lack.
 	 */
-	if (IS_ACTIVE(CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT) &&
+	if (CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT &&
 	    __i915_spin_request(rq, state))
 		goto out;