drm/v3d: Refactor job management.

The CL submission had two jobs embedded in an exec struct.  When I
added TFU support, I had to replicate some of the exec stuff and some
of the job stuff.  As I went to add CSD, it became clear that actually
what was in exec should just be in the two CL jobs, and it would let
us share a lot more code between the 4 queues.

v2: Fix missing error path in TFU ioctl's bo[] allocation.

Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190416225856.20264-3-eric@anholt.net
Acked-by: Rob Clark <robdclark@gmail.com>

4 files changed, 380 insertions, 329 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 67c323e781f9..f82f8be04bd8 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -67,8 +67,8 @@ struct v3d_dev {
 
 	struct work_struct overflow_mem_work;
 
-	struct v3d_exec_info *bin_job;
-	struct v3d_exec_info *render_job;
+	struct v3d_bin_job *bin_job;
+	struct v3d_render_job *render_job;
 	struct v3d_tfu_job *tfu_job;
 
 	struct v3d_queue_state queue[V3D_MAX_QUEUES];
@@ -117,7 +117,7 @@ struct v3d_bo {
 	struct drm_mm_node node;
 
 	/* List entry for the BO's position in
-	 * v3d_exec_info->unref_list
+	 * v3d_render_job->unref_list
 	 */
 	struct list_head unref_head;
 };
@@ -157,7 +157,15 @@ to_v3d_fence(struct dma_fence *fence)
 struct v3d_job {
 	struct drm_sched_job base;
 
-	struct v3d_exec_info *exec;
+	struct kref refcount;
+
+	struct v3d_dev *v3d;
+
+	/* This is the array of BOs that were looked up at the start
+	 * of submission.
+	 */
+	struct drm_gem_object **bo;
+	u32 bo_count;
 
 	/* An optional fence userspace can pass in for the job to depend on. */
 	struct dma_fence *in_fence;
@@ -165,59 +173,53 @@ struct v3d_job {
 	/* v3d fence to be signaled by IRQ handler when the job is complete. */
 	struct dma_fence *irq_fence;
 
+	/* scheduler fence for when the job is considered complete and
+	 * the BO reservations can be released.
+	 */
+	struct dma_fence *done_fence;
+
+	/* Callback for the freeing of the job on refcount going to 0. */
+	void (*free)(struct kref *ref);
+};
+
+struct v3d_bin_job {
+	struct v3d_job base;
+
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
 
 	u32 timedout_ctca, timedout_ctra;
-};
 
-struct v3d_exec_info {
-	struct v3d_dev *v3d;
+	/* Corresponding render job, for attaching our overflow memory. */
+	struct v3d_render_job *render;
+
+	/* Submitted tile memory allocation start/size, tile state. */
+	u32 qma, qms, qts;
+};
 
-	struct v3d_job bin, render;
+struct v3d_render_job {
+	struct v3d_job base;
 
-	/* Fence for when the scheduler considers the binner to be
-	 * done, for render to depend on.
+	/* Optional fence for the binner, to depend on before starting
+	 * our job.
 	 */
 	struct dma_fence *bin_done_fence;
 
-	/* Fence for when the scheduler considers the render to be
-	 * done, for when the BOs reservations should be complete.
-	 */
-	struct dma_fence *render_done_fence;
-
-	struct kref refcount;
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
 
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct drm_gem_object **bo;
-	u32 bo_count;
+	u32 timedout_ctca, timedout_ctra;
 
 	/* List of overflow BOs used in the job that need to be
 	 * released once the job is complete.
 	 */
 	struct list_head unref_list;
-
-	/* Submitted tile memory allocation start/size, tile state. */
-	u32 qma, qms, qts;
 };
 
 struct v3d_tfu_job {
-	struct drm_sched_job base;
+	struct v3d_job base;
 
 	struct drm_v3d_submit_tfu args;
-
-	/* An optional fence userspace can pass in for the job to depend on. */
-	struct dma_fence *in_fence;
-
-	/* v3d fence to be signaled by IRQ handler when the job is complete. */
-	struct dma_fence *irq_fence;
-
-	struct v3d_dev *v3d;
-
-	struct kref refcount;
-
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct drm_gem_object *bo[4];
 };
 
 /**
@@ -283,8 +285,7 @@ int v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
-void v3d_exec_put(struct v3d_exec_info *exec);
-void v3d_tfu_job_put(struct v3d_tfu_job *exec);
+void v3d_job_put(struct v3d_job *job);
 void v3d_reset(struct v3d_dev *v3d);
 void v3d_invalidate_caches(struct v3d_dev *v3d);
 
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index aa0397d12847..350a269a7b58 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -193,18 +193,6 @@ v3d_invalidate_caches(struct v3d_dev *v3d)
 	v3d_invalidate_slices(v3d, 0);
 }
 
-static void
-v3d_attach_object_fences(struct drm_gem_object **bos, int bo_count,
-			 struct dma_fence *fence)
-{
-	int i;
-
-	for (i = 0; i < bo_count; i++) {
-		/* XXX: Use shared fences for read-only objects. */
-		reservation_object_add_excl_fence(bos[i]->resv, fence);
-	}
-}
-
 /* Takes the reservation lock on all the BOs being referenced, so that
  * at queue submit time we can update the reservations.
  *
@@ -239,11 +227,11 @@ v3d_lock_bo_reservations(struct drm_gem_object **bos,
 }
 
 /**
- * v3d_cl_lookup_bos() - Sets up exec->bo[] with the GEM objects
+ * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects
  * referenced by the job.
  * @dev: DRM device
  * @file_priv: DRM file for this fd
- * @exec: V3D job being set up
+ * @job: V3D job being set up
  *
  * The command validator needs to reference BOs by their index within
  * the submitted job's BO list.  This does the validation of the job's
@@ -253,18 +241,19 @@ v3d_lock_bo_reservations(struct drm_gem_object **bos,
  * failure, because that will happen at v3d_exec_cleanup() time.
  */
 static int
-v3d_cl_lookup_bos(struct drm_device *dev,
-		  struct drm_file *file_priv,
-		  struct drm_v3d_submit_cl *args,
-		  struct v3d_exec_info *exec)
+v3d_lookup_bos(struct drm_device *dev,
+	       struct drm_file *file_priv,
+	       struct v3d_job *job,
+	       u64 bo_handles,
+	       u32 bo_count)
 {
 	u32 *handles;
 	int ret = 0;
 	int i;
 
-	exec->bo_count = args->bo_handle_count;
+	job->bo_count = bo_count;
 
-	if (!exec->bo_count) {
+	if (!job->bo_count) {
 		/* See comment on bo_index for why we have to check
 		 * this.
 		 */
@@ -272,15 +261,15 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	exec->bo = kvmalloc_array(exec->bo_count,
-				  sizeof(struct drm_gem_cma_object *),
-				  GFP_KERNEL | __GFP_ZERO);
-	if (!exec->bo) {
+	job->bo = kvmalloc_array(job->bo_count,
+				 sizeof(struct drm_gem_cma_object *),
+				 GFP_KERNEL | __GFP_ZERO);
+	if (!job->bo) {
 		DRM_DEBUG("Failed to allocate validated BO pointers\n");
 		return -ENOMEM;
 	}
 
-	handles = kvmalloc_array(exec->bo_count, sizeof(u32), GFP_KERNEL);
+	handles = kvmalloc_array(job->bo_count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
 		DRM_DEBUG("Failed to allocate incoming GEM handles\n");
@@ -288,15 +277,15 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 	}
 
 	if (copy_from_user(handles,
-			   (void __user *)(uintptr_t)args->bo_handles,
-			   exec->bo_count * sizeof(u32))) {
+			   (void __user *)(uintptr_t)bo_handles,
+			   job->bo_count * sizeof(u32))) {
 		ret = -EFAULT;
 		DRM_DEBUG("Failed to copy in GEM handles\n");
 		goto fail;
 	}
 
 	spin_lock(&file_priv->table_lock);
-	for (i = 0; i < exec->bo_count; i++) {
+	for (i = 0; i < job->bo_count; i++) {
 		struct drm_gem_object *bo = idr_find(&file_priv->object_idr,
 						     handles[i]);
 		if (!bo) {
@@ -307,7 +296,7 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		exec->bo[i] = bo;
+		job->bo[i] = bo;
 	}
 	spin_unlock(&file_priv->table_lock);
 
@@ -317,67 +306,44 @@ fail:
 }
 
 static void
-v3d_exec_cleanup(struct kref *ref)
+v3d_job_free(struct kref *ref)
 {
-	struct v3d_exec_info *exec = container_of(ref, struct v3d_exec_info,
-						  refcount);
-	struct v3d_dev *v3d = exec->v3d;
-	unsigned int i;
-	struct v3d_bo *bo, *save;
-
-	dma_fence_put(exec->bin.in_fence);
-	dma_fence_put(exec->render.in_fence);
-
-	dma_fence_put(exec->bin.irq_fence);
-	dma_fence_put(exec->render.irq_fence);
-
-	dma_fence_put(exec->bin_done_fence);
-	dma_fence_put(exec->render_done_fence);
-
-	for (i = 0; i < exec->bo_count; i++)
-		drm_gem_object_put_unlocked(exec->bo[i]);
-	kvfree(exec->bo);
+	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+	int i;
 
-	list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) {
-		drm_gem_object_put_unlocked(&bo->base.base);
+	for (i = 0; i < job->bo_count; i++) {
+		if (job->bo[i])
+			drm_gem_object_put_unlocked(job->bo[i]);
 	}
+	kvfree(job->bo);
 
-	pm_runtime_mark_last_busy(v3d->dev);
-	pm_runtime_put_autosuspend(v3d->dev);
+	dma_fence_put(job->in_fence);
+	dma_fence_put(job->irq_fence);
+	dma_fence_put(job->done_fence);
 
-	kfree(exec);
-}
+	pm_runtime_mark_last_busy(job->v3d->dev);
+	pm_runtime_put_autosuspend(job->v3d->dev);
 
-void v3d_exec_put(struct v3d_exec_info *exec)
-{
-	kref_put(&exec->refcount, v3d_exec_cleanup);
+	kfree(job);
 }
 
 static void
-v3d_tfu_job_cleanup(struct kref *ref)
+v3d_render_job_free(struct kref *ref)
 {
-	struct v3d_tfu_job *job = container_of(ref, struct v3d_tfu_job,
-					       refcount);
-	struct v3d_dev *v3d = job->v3d;
-	unsigned int i;
-
-	dma_fence_put(job->in_fence);
-	dma_fence_put(job->irq_fence);
+	struct v3d_render_job *job = container_of(ref, struct v3d_render_job,
+						  base.refcount);
+	struct v3d_bo *bo, *save;
 
-	for (i = 0; i < ARRAY_SIZE(job->bo); i++) {
-		if (job->bo[i])
-			drm_gem_object_put_unlocked(job->bo[i]);
+	list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) {
+		drm_gem_object_put_unlocked(&bo->base.base);
 	}
 
-	pm_runtime_mark_last_busy(v3d->dev);
-	pm_runtime_put_autosuspend(v3d->dev);
-
-	kfree(job);
+	v3d_job_free(ref);
 }
 
-void v3d_tfu_job_put(struct v3d_tfu_job *job)
+void v3d_job_put(struct v3d_job *job)
 {
-	kref_put(&job->refcount, v3d_tfu_job_cleanup);
+	kref_put(&job->refcount, job->free);
 }
 
 int
@@ -413,6 +379,77 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
+static int
+v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
+	     struct v3d_job *job, void (*free)(struct kref *ref),
+	     u32 in_sync)
+{
+	int ret;
+
+	job->v3d = v3d;
+	job->free = free;
+
+	ret = pm_runtime_get_sync(v3d->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_syncobj_find_fence(file_priv, in_sync, 0, 0, &job->in_fence);
+	if (ret == -EINVAL) {
+		pm_runtime_put_autosuspend(v3d->dev);
+		return ret;
+	}
+
+	kref_init(&job->refcount);
+
+	return 0;
+}
+
+static int
+v3d_push_job(struct v3d_file_priv *v3d_priv,
+	     struct v3d_job *job, enum v3d_queue queue)
+{
+	int ret;
+
+	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
+				 v3d_priv);
+	if (ret)
+		return ret;
+
+	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+	/* put by scheduler job completion */
+	kref_get(&job->refcount);
+
+	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[queue]);
+
+	return 0;
+}
+
+static void
+v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
+					 struct v3d_job *job,
+					 struct ww_acquire_ctx *acquire_ctx,
+					 u32 out_sync)
+{
+	struct drm_syncobj *sync_out;
+	int i;
+
+	for (i = 0; i < job->bo_count; i++) {
+		/* XXX: Use shared fences for read-only objects. */
+		reservation_object_add_excl_fence(job->bo[i]->resv,
+						  job->done_fence);
+	}
+
+	drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
+
+	/* Update the return sync object for the job */
+	sync_out = drm_syncobj_find(file_priv, out_sync);
+	if (sync_out) {
+		drm_syncobj_replace_fence(sync_out, job->done_fence);
+		drm_syncobj_put(sync_out);
+	}
+}
+
 /**
  * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D.
  * @dev: DRM device
@@ -432,9 +469,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct drm_v3d_submit_cl *args = data;
-	struct v3d_exec_info *exec;
+	struct v3d_bin_job *bin = NULL;
+	struct v3d_render_job *render;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
 	int ret = 0;
 
 	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
@@ -444,100 +481,83 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
-	if (!exec)
+	render = kcalloc(1, sizeof(*render), GFP_KERNEL);
+	if (!render)
 		return -ENOMEM;
 
-	ret = pm_runtime_get_sync(v3d->dev);
-	if (ret < 0) {
-		kfree(exec);
+	render->start = args->rcl_start;
+	render->end = args->rcl_end;
+	INIT_LIST_HEAD(&render->unref_list);
+
+	ret = v3d_job_init(v3d, file_priv, &render->base,
+			   v3d_render_job_free, args->in_sync_rcl);
+	if (ret) {
+		kfree(render);
 		return ret;
 	}
 
-	kref_init(&exec->refcount);
+	if (args->bcl_start != args->bcl_end) {
+		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
+		if (!bin)
+			return -ENOMEM;
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
-				     0, 0, &exec->bin.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+		ret = v3d_job_init(v3d, file_priv, &bin->base,
+				   v3d_job_free, args->in_sync_bcl);
+		if (ret) {
+			v3d_job_put(&render->base);
+			return ret;
+		}
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
-				     0, 0, &exec->render.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+		bin->start = args->bcl_start;
+		bin->end = args->bcl_end;
+		bin->qma = args->qma;
+		bin->qms = args->qms;
+		bin->qts = args->qts;
+		bin->render = render;
+	}
 
-	exec->qma = args->qma;
-	exec->qms = args->qms;
-	exec->qts = args->qts;
-	exec->bin.exec = exec;
-	exec->bin.start = args->bcl_start;
-	exec->bin.end = args->bcl_end;
-	exec->render.exec = exec;
-	exec->render.start = args->rcl_start;
-	exec->render.end = args->rcl_end;
-	exec->v3d = v3d;
-	INIT_LIST_HEAD(&exec->unref_list);
-
-	ret = v3d_cl_lookup_bos(dev, file_priv, args, exec);
+	ret = v3d_lookup_bos(dev, file_priv, &render->base,
+			     args->bo_handles, args->bo_handle_count);
 	if (ret)
 		goto fail;
 
-	ret = v3d_lock_bo_reservations(exec->bo, exec->bo_count,
+	ret = v3d_lock_bo_reservations(render->base.bo, render->base.bo_count,
 				       &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	if (exec->bin.start != exec->bin.end) {
-		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d_priv->sched_entity[V3D_BIN],
-					 v3d_priv);
+	if (bin) {
+		ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
 		if (ret)
 			goto fail_unreserve;
 
-		exec->bin_done_fence =
-			dma_fence_get(&exec->bin.base.s_fence->finished);
-
-		kref_get(&exec->refcount); /* put by scheduler job completion */
-		drm_sched_entity_push_job(&exec->bin.base,
-					  &v3d_priv->sched_entity[V3D_BIN]);
+		render->bin_done_fence = dma_fence_get(bin->base.done_fence);
 	}
 
-	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d_priv->sched_entity[V3D_RENDER],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &render->base, V3D_RENDER);
 	if (ret)
 		goto fail_unreserve;
-
-	exec->render_done_fence =
-		dma_fence_get(&exec->render.base.s_fence->finished);
-
-	kref_get(&exec->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&exec->render.base,
-				  &v3d_priv->sched_entity[V3D_RENDER]);
 	mutex_unlock(&v3d->sched_lock);
 
-	v3d_attach_object_fences(exec->bo, exec->bo_count,
-				 exec->render_done_fence);
-
-	drm_gem_unlock_reservations(exec->bo, exec->bo_count, &acquire_ctx);
-
-	/* Update the return sync object for the */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out, exec->render_done_fence);
-		drm_syncobj_put(sync_out);
-	}
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &render->base, &acquire_ctx,
+						 args->out_sync);
 
-	v3d_exec_put(exec);
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	drm_gem_unlock_reservations(exec->bo, exec->bo_count, &acquire_ctx);
+	drm_gem_unlock_reservations(render->base.bo,
+				    render->base.bo_count, &acquire_ctx);
 fail:
-	v3d_exec_put(exec);
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return ret;
 }
@@ -560,10 +580,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 	struct drm_v3d_submit_tfu *args = data;
 	struct v3d_tfu_job *job;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
-	struct dma_fence *sched_done_fence;
 	int ret = 0;
-	int bo_count;
 
 	trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia);
 
@@ -571,81 +588,71 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 	if (!job)
 		return -ENOMEM;
 
-	ret = pm_runtime_get_sync(v3d->dev);
-	if (ret < 0) {
+	ret = v3d_job_init(v3d, file_priv, &job->base,
+			   v3d_job_free, args->in_sync);
+	if (ret) {
 		kfree(job);
 		return ret;
 	}
 
-	kref_init(&job->refcount);
-
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync,
-				     0, 0, &job->in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
+			       sizeof(*job->base.bo), GFP_KERNEL);
+	if (!job->base.bo) {
+		v3d_job_put(&job->base);
+		return -ENOMEM;
+	}
 
 	job->args = *args;
-	job->v3d = v3d;
 
 	spin_lock(&file_priv->table_lock);
-	for (bo_count = 0; bo_count < ARRAY_SIZE(job->bo); bo_count++) {
+	for (job->base.bo_count = 0;
+	     job->base.bo_count < ARRAY_SIZE(args->bo_handles);
+	     job->base.bo_count++) {
 		struct drm_gem_object *bo;
 
-		if (!args->bo_handles[bo_count])
+		if (!args->bo_handles[job->base.bo_count])
 			break;
 
 		bo = idr_find(&file_priv->object_idr,
-			      args->bo_handles[bo_count]);
+			      args->bo_handles[job->base.bo_count]);
 		if (!bo) {
 			DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
-				  bo_count, args->bo_handles[bo_count]);
+				  job->base.bo_count,
+				  args->bo_handles[job->base.bo_count]);
 			ret = -ENOENT;
 			spin_unlock(&file_priv->table_lock);
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		job->bo[bo_count] = bo;
+		job->base.bo[job->base.bo_count] = bo;
 	}
 	spin_unlock(&file_priv->table_lock);
 
-	ret = v3d_lock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+	ret = v3d_lock_bo_reservations(job->base.bo, job->base.bo_count,
+				       &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	ret = drm_sched_job_init(&job->base,
-				 &v3d_priv->sched_entity[V3D_TFU],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &job->base, V3D_TFU);
 	if (ret)
 		goto fail_unreserve;
-
-	sched_done_fence = dma_fence_get(&job->base.s_fence->finished);
-
-	kref_get(&job->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[V3D_TFU]);
 	mutex_unlock(&v3d->sched_lock);
 
-	v3d_attach_object_fences(job->bo, bo_count, sched_done_fence);
-
-	drm_gem_unlock_reservations(job->bo, bo_count, &acquire_ctx);
-
-	/* Update the return sync object */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out, sched_done_fence);
-		drm_syncobj_put(sync_out);
-	}
-	dma_fence_put(sched_done_fence);
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &job->base, &acquire_ctx,
+						 args->out_sync);
 
-	v3d_tfu_job_put(job);
+	v3d_job_put(&job->base);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	drm_gem_unlock_reservations(job->bo, bo_count, &acquire_ctx);
+	drm_gem_unlock_reservations(job->base.bo, job->base.bo_count,
+				    &acquire_ctx);
 fail:
-	v3d_tfu_job_put(job);
+	v3d_job_put(&job->base);
 
 	return ret;
 }
@@ -703,7 +710,7 @@ v3d_gem_destroy(struct drm_device *dev)
 
 	v3d_sched_fini(v3d);
 
-	/* Waiting for exec to finish would need to be done before
+	/* Waiting for jobs to finish would need to be done before
 	 * unregistering V3D.
 	 */
 	WARN_ON(v3d->bin_job);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index aa0a180ae700..ce373ffd6380 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -62,7 +62,7 @@ v3d_overflow_mem_work(struct work_struct *work)
 	}
 
 	drm_gem_object_get(obj);
-	list_add_tail(&bo->unref_head, &v3d->bin_job->unref_list);
+	list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list);
 	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
 
 	V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
@@ -96,7 +96,7 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FLDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->bin_job->bin.irq_fence);
+			to_v3d_fence(v3d->bin_job->base.irq_fence);
 
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -105,7 +105,7 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FRDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->render_job->render.irq_fence);
+			to_v3d_fence(v3d->render_job->base.irq_fence);
 
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -141,7 +141,7 @@ v3d_hub_irq(int irq, void *arg)
 
 	if (intsts & V3D_HUB_INT_TFUC) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->tfu_job->irq_fence);
+			to_v3d_fence(v3d->tfu_job->base.irq_fence);
 
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index e740f3b99aa5..739f399308ce 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -30,43 +30,44 @@ to_v3d_job(struct drm_sched_job *sched_job)
 	return container_of(sched_job, struct v3d_job, base);
 }
 
-static struct v3d_tfu_job *
-to_tfu_job(struct drm_sched_job *sched_job)
+static struct v3d_bin_job *
+to_bin_job(struct drm_sched_job *sched_job)
 {
-	return container_of(sched_job, struct v3d_tfu_job, base);
+	return container_of(sched_job, struct v3d_bin_job, base.base);
 }
 
-static void
-v3d_job_free(struct drm_sched_job *sched_job)
+static struct v3d_render_job *
+to_render_job(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
-
-	drm_sched_job_cleanup(sched_job);
+	return container_of(sched_job, struct v3d_render_job, base.base);
+}
 
-	v3d_exec_put(job->exec);
+static struct v3d_tfu_job *
+to_tfu_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_tfu_job, base.base);
 }
 
 static void
-v3d_tfu_job_free(struct drm_sched_job *sched_job)
+v3d_job_free(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_job *job = to_v3d_job(sched_job);
 
 	drm_sched_job_cleanup(sched_job);
-
-	v3d_tfu_job_put(job);
+	v3d_job_put(job);
 }
 
 /**
- * Returns the fences that the bin or render job depends on, one by one.
- * v3d_job_run() won't be called until all of them have been signaled.
+ * Returns the fences that the job depends on, one by one.
+ *
+ * If placed in the scheduler's .dependency method, the corresponding
+ * .run_job won't be called until all of them have been signaled.
  */
 static struct dma_fence *
 v3d_job_dependency(struct drm_sched_job *sched_job,
 		   struct drm_sched_entity *s_entity)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
 	struct dma_fence *fence;
 
 	fence = job->in_fence;
@@ -75,113 +76,132 @@ v3d_job_dependency(struct drm_sched_job *sched_job,
 		return fence;
 	}
 
-	if (q == V3D_RENDER) {
-		/* If we had a bin job, the render job definitely depends on
-		 * it. We first have to wait for bin to be scheduled, so that
-		 * its done_fence is created.
-		 */
-		fence = exec->bin_done_fence;
-		if (fence) {
-			exec->bin_done_fence = NULL;
-			return fence;
-		}
-	}
-
 	/* XXX: Wait on a fence for switching the GMP if necessary,
 	 * and then do so.
 	 */
 
-	return fence;
+	return NULL;
 }
 
 /**
- * Returns the fences that the TFU job depends on, one by one.
- * v3d_tfu_job_run() won't be called until all of them have been
- * signaled.
+ * Returns the fences that the render job depends on, one by one.
+ * v3d_job_run() won't be called until all of them have been signaled.
  */
 static struct dma_fence *
-v3d_tfu_job_dependency(struct drm_sched_job *sched_job,
-		       struct drm_sched_entity *s_entity)
+v3d_render_job_dependency(struct drm_sched_job *sched_job,
+			  struct drm_sched_entity *s_entity)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_render_job *job = to_render_job(sched_job);
 	struct dma_fence *fence;
 
-	fence = job->in_fence;
+	fence = v3d_job_dependency(sched_job, s_entity);
+	if (fence)
+		return fence;
+
+	/* If we had a bin job, the render job definitely depends on
+	 * it. We first have to wait for bin to be scheduled, so that
+	 * its done_fence is created.
+	 */
+	fence = job->bin_done_fence;
 	if (fence) {
-		job->in_fence = NULL;
+		job->bin_done_fence = NULL;
 		return fence;
 	}
 
-	return NULL;
+	return fence;
 }
 
-static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
+static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	struct v3d_dev *v3d = exec->v3d;
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	unsigned long irqflags;
 
-	if (unlikely(job->base.s_fence->finished.error))
+	if (unlikely(job->base.base.s_fence->finished.error))
 		return NULL;
 
 	/* Lock required around bin_job update vs
 	 * v3d_overflow_mem_work().
 	 */
 	spin_lock_irqsave(&v3d->job_lock, irqflags);
-	if (q == V3D_BIN) {
-		v3d->bin_job = job->exec;
-
-		/* Clear out the overflow allocation, so we don't
-		 * reuse the overflow attached to a previous job.
-		 */
-		V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
-	} else {
-		v3d->render_job = job->exec;
-	}
+	v3d->bin_job = job;
+	/* Clear out the overflow allocation, so we don't
+	 * reuse the overflow attached to a previous job.
+	 */
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
 	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
 
-	/* Can we avoid this flush when q==RENDER?  We need to be
-	 * careful of scheduling, though -- imagine job0 rendering to
-	 * texture and job1 reading, and them being executed as bin0,
-	 * bin1, render0, render1, so that render1's flush at bin time
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_BIN);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	if (job->qma) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, job->qma);
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, job->qms);
+	}
+	if (job->qts) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
+			       V3D_CLE_CT0QTS_ENABLE |
+			       job->qts);
+	}
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QEA, job->end);
+
+	return fence;
+}
+
+static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
+	v3d->render_job = job;
+
+	/* Can we avoid this flush?  We need to be careful of
+	 * scheduling, though -- imagine job0 rendering to texture and
+	 * job1 reading, and them being executed as bin0, bin1,
+	 * render0, render1, so that render1's flush at bin time
 	 * wasn't enough.
 	 */
 	v3d_invalidate_caches(v3d);
 
-	fence = v3d_fence_create(v3d, q);
+	fence = v3d_fence_create(v3d, V3D_RENDER);
 	if (IS_ERR(fence))
 		return NULL;
 
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
-	trace_v3d_submit_cl(dev, q == V3D_RENDER, to_v3d_fence(fence)->seqno,
+	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
-	if (q == V3D_BIN) {
-		if (exec->qma) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, exec->qma);
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, exec->qms);
-		}
-		if (exec->qts) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
-				       V3D_CLE_CT0QTS_ENABLE |
-				       exec->qts);
-		}
-	} else {
-		/* XXX: Set the QCFG */
-	}
+	/* XXX: Set the QCFG */
 
 	/* Set the current and end address of the control list.
 	 * Writing the end register is what starts the job.
 	 */
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQBA(q), job->start);
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQEA(q), job->end);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QEA, job->end);
 
 	return fence;
 }
@@ -190,7 +210,7 @@ static struct dma_fence *
 v3d_tfu_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_tfu_job *job = to_tfu_job(sched_job);
-	struct v3d_dev *v3d = job->v3d;
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
@@ -199,9 +219,9 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 		return NULL;
 
 	v3d->tfu_job = job;
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
@@ -251,25 +271,23 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	mutex_unlock(&v3d->reset_lock);
 }
 
+/* If the current address or return address have changed, then the GPU
+ * has probably made progress and we should delay the reset.  This
+ * could fail if the GPU got in an infinite loop in the CL, but that
+ * is pretty unlikely outside of an i-g-t testcase.
+ */
 static void
-v3d_job_timedout(struct drm_sched_job *sched_job)
+v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
+		    u32 *timedout_ctca, u32 *timedout_ctra)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	struct v3d_dev *v3d = exec->v3d;
-	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
-	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
-
-	/* If the current address or return address have changed, then
-	 * the GPU has probably made progress and we should delay the
-	 * reset.  This could fail if the GPU got in an infinite loop
-	 * in the CL, but that is pretty unlikely outside of an i-g-t
-	 * testcase.
-	 */
-	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
-		job->timedout_ctca = ctca;
-		job->timedout_ctra = ctra;
+	struct v3d_dev *v3d = job->v3d;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
+
+	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
+		*timedout_ctca = ctca;
+		*timedout_ctra = ctra;
 		return;
 	}
 
@@ -277,25 +295,50 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 }
 
 static void
+v3d_bin_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_BIN,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
+v3d_render_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_RENDER,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
 v3d_tfu_job_timedout(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_job *job = to_v3d_job(sched_job);
 
 	v3d_gpu_reset_for_timeout(job->v3d, sched_job);
 }
 
-static const struct drm_sched_backend_ops v3d_sched_ops = {
+static const struct drm_sched_backend_ops v3d_bin_sched_ops = {
 	.dependency = v3d_job_dependency,
-	.run_job = v3d_job_run,
-	.timedout_job = v3d_job_timedout,
-	.free_job = v3d_job_free
+	.run_job = v3d_bin_job_run,
+	.timedout_job = v3d_bin_job_timedout,
+	.free_job = v3d_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_render_sched_ops = {
+	.dependency = v3d_render_job_dependency,
+	.run_job = v3d_render_job_run,
+	.timedout_job = v3d_render_job_timedout,
+	.free_job = v3d_job_free,
 };
 
 static const struct drm_sched_backend_ops v3d_tfu_sched_ops = {
-	.dependency = v3d_tfu_job_dependency,
+	.dependency = v3d_job_dependency,
 	.run_job = v3d_tfu_job_run,
 	.timedout_job = v3d_tfu_job_timedout,
-	.free_job = v3d_tfu_job_free
+	.free_job = v3d_job_free,
 };
 
 int
@@ -307,7 +350,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	int ret;
 
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
-			     &v3d_sched_ops,
+			     &v3d_bin_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_bin");
@@ -317,7 +360,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	}
 
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
-			     &v3d_sched_ops,
+			     &v3d_render_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_render");