drm/sched: add DRM_SCHED_FENCE_DONT_PIPELINE flag

Setting this flag on a scheduler fence prevents pipelining of jobs
depending on this fence. In other words we always insert a full CPU
round trip before dependent jobs are pushed to the pipeline.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2113#note_1579296Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Acked-by: NLuben Tuikov <luben.tuikov@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014081553.114899-1-christian.koenig@amd.com

drivers/gpu/drm/scheduler/sched_entity.c

@@ -385,7 +385,8 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 	}
 
 	s_fence = to_drm_sched_fence(fence);
-	if (s_fence && s_fence->sched == sched) {
+	if (s_fence && s_fence->sched == sched &&
+	    !test_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &fence->flags)) {
 
 		/*
 		 * Fence is from the same scheduler, only need to wait for

include/drm/gpu_scheduler.h

@@ -32,6 +32,15 @@
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
+/**
+ * DRM_SCHED_FENCE_DONT_PIPELINE - Prefent dependency pipelining
+ *
+ * Setting this flag on a scheduler fence prevents pipelining of jobs depending
+ * on this fence. In other words we always insert a full CPU round trip before
+ * dependen jobs are pushed to the hw queue.
+ */
+#define DRM_SCHED_FENCE_DONT_PIPELINE	DMA_FENCE_FLAG_USER_BITS
+
 struct drm_gem_object;
 
 struct drm_gpu_scheduler;