drm/i915/display: Apply interactive priority to explicit flip fences

Currently, if a modeset/pageflip needs to wait for render completion to
an object, we boost the priority of that rendering above all other work.
We can apply the same interactive priority boosting to explicit fences
that we can unwrap into a native i915_request (i.e. sync_file).

Signed-off-by: Chris Wilson <[e-mail]>
Cc: Tvrtko Ursulin <[e-mail]>
Cc: Ville Syrjälä <[e-mail]>
Reviewed-by: Ville Syrjälä <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/i915/display/intel_display.c

···
 		intel_unpin_fb_vma(vma, old_plane_state->flags);
 }
 
-static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
-{
-	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_DISPLAY),
-	};
-
-	i915_gem_object_wait_priority(obj, 0, &attr);
-}
-
 /**
  * intel_prepare_plane_fb - Prepare fb for usage on plane
  * @_plane: drm plane to prepare for
···
 intel_prepare_plane_fb(struct drm_plane *_plane,
 		       struct drm_plane_state *_new_plane_state)
 {
+	struct i915_sched_attr attr = {
+		.priority = I915_USER_PRIORITY(I915_PRIORITY_DISPLAY),
+	};
 	struct intel_plane *plane = to_intel_plane(_plane);
 	struct intel_plane_state *new_plane_state =
 		to_intel_plane_state(_new_plane_state);
···
 	}
 
 	if (new_plane_state->uapi.fence) { /* explicit fencing */
+		i915_gem_fence_wait_priority(new_plane_state->uapi.fence,
+					     &attr);
 		ret = i915_sw_fence_await_dma_fence(&state->commit_ready,
 						    new_plane_state->uapi.fence,
 						    i915_fence_timeout(dev_priv),
···
 	if (ret)
 		return ret;
 
-	fb_obj_bump_render_priority(obj);
+	i915_gem_object_wait_priority(obj, 0, &attr);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB);
 
 	if (!new_plane_state->uapi.fence) { /* implicit fencing */

drivers/gpu/drm/i915/gem/i915_gem_object.h

···
 		obj->cache_dirty = true;
 }
 
+void i915_gem_fence_wait_priority(struct dma_fence *fence,
+				  const struct i915_sched_attr *attr);
+
 int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 unsigned int flags,
 			 long timeout);

drivers/gpu/drm/i915/gem/i915_gem_wait.c

···
  */
 
 #include <linux/dma-fence-array.h>
+#include <linux/dma-fence-chain.h>
 #include <linux/jiffies.h>
 
 #include "gt/intel_engine.h"
···
 		unsigned int count, i;
 		int ret;
 
-		ret = dma_resv_get_fences_rcu(resv,
-							&excl, &count, &shared);
+		ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared);
 		if (ret)
 			return ret;
 
···
 	return timeout;
 }
 
-static void __fence_set_priority(struct dma_fence *fence,
-				 const struct i915_sched_attr *attr)
+static void fence_set_priority(struct dma_fence *fence,
+			       const struct i915_sched_attr *attr)
 {
 	struct i915_request *rq;
 	struct intel_engine_cs *engine;
···
 	rq = to_request(fence);
 	engine = rq->engine;
 
-	local_bh_disable();
 	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule)
 		engine->schedule(rq, attr);
 	rcu_read_unlock();
-	local_bh_enable(); /* kick the tasklets if queues were reprioritised */
 }
 
-static void fence_set_priority(struct dma_fence *fence,
-			       const struct i915_sched_attr *attr)
+static inline bool __dma_fence_is_chain(const struct dma_fence *fence)
 {
+	return fence->ops == &dma_fence_chain_ops;
+}
+
+void i915_gem_fence_wait_priority(struct dma_fence *fence,
+				  const struct i915_sched_attr *attr)
+{
+	if (dma_fence_is_signaled(fence))
+		return;
+
+	local_bh_disable();
+
 	/* Recurse once into a fence-array */
 	if (dma_fence_is_array(fence)) {
 		struct dma_fence_array *array = to_dma_fence_array(fence);
 		int i;
 
 		for (i = 0; i < array->num_fences; i++)
-			__fence_set_priority(array->fences[i], attr);
+			fence_set_priority(array->fences[i], attr);
+	} else if (__dma_fence_is_chain(fence)) {
+		struct dma_fence *iter;
+
+		/* The chain is ordered; if we boost the last, we boost all */
+		dma_fence_chain_for_each(iter, fence) {
+			fence_set_priority(to_dma_fence_chain(iter)->fence,
+					   attr);
+			break;
+		}
+		dma_fence_put(iter);
 	} else {
-		__fence_set_priority(fence, attr);
+		fence_set_priority(fence, attr);
 	}
+
+	local_bh_enable(); /* kick the tasklets if queues were reprioritised */
 }
 
 int
···
 		int ret;
 
 		ret = dma_resv_get_fences_rcu(obj->base.resv,
-							&excl, &count, &shared);
+					      &excl, &count, &shared);
 		if (ret)
 			return ret;
 
 		for (i = 0; i < count; i++) {
-			fence_set_priority(shared[i], attr);
+			i915_gem_fence_wait_priority(shared[i], attr);
 			dma_fence_put(shared[i]);
 		}
 
···
 	}
 
 	if (excl) {
-		fence_set_priority(excl, attr);
+		i915_gem_fence_wait_priority(excl, attr);
 		dma_fence_put(excl);
 	}
 	return 0;