drm/vc4: improve throughput by pipelining binning and rendering jobs

The hardware provides us with separate threads for binning and
rendering, and the existing model waits for them both to complete
before submitting the next job.

Splitting the binning and rendering submissions reduces idle time and
gives us approx 20-30% speedup with some x11perf tests such as -line10
and -tilerect1.  Improves openarena performance by 1.01897% +/-
0.247857% (n=16).

Thanks to anholt for suggesting this.

v2: Rebase on the spurious resets fix (change by anholt).

Signed-off-by: Varad Gautam <varadgautam@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Eric Anholt <eric@anholt.net>

1 files changed, 28 insertions, 9 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index f53fe6c..fa2ad15 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -52,7 +52,7 @@ struct vc4_dev {
 	/* Protects bo_cache and the BO stats. */
 	struct mutex bo_lock;
 
-	/* Sequence number for the last job queued in job_list.
+	/* Sequence number for the last job queued in bin_job_list.
 	 * Starts at 0 (no jobs emitted).
 	 */
 	uint64_t emit_seqno;
@@ -62,11 +62,19 @@ struct vc4_dev {
 	 */
 	uint64_t finished_seqno;
 
-	/* List of all struct vc4_exec_info for jobs to be executed.
-	 * The first job in the list is the one currently programmed
-	 * into ct0ca/ct1ca for execution.
+	/* List of all struct vc4_exec_info for jobs to be executed in
+	 * the binner.  The first job in the list is the one currently
+	 * programmed into ct0ca for execution.
 	 */
-	struct list_head job_list;
+	struct list_head bin_job_list;
+
+	/* List of all struct vc4_exec_info for jobs that have
+	 * completed binning and are ready for rendering.  The first
+	 * job in the list is the one currently programmed into ct1ca
+	 * for execution.
+	 */
+	struct list_head render_job_list;
+
 	/* List of the finished vc4_exec_infos waiting to be freed by
 	 * job_done_work.
 	 */
@@ -296,11 +304,20 @@ struct vc4_exec_info {
 };
 
 static inline struct vc4_exec_info *
-vc4_first_job(struct vc4_dev *vc4)
+vc4_first_bin_job(struct vc4_dev *vc4)
+{
+	if (list_empty(&vc4->bin_job_list))
+		return NULL;
+	return list_first_entry(&vc4->bin_job_list, struct vc4_exec_info, head);
+}
+
+static inline struct vc4_exec_info *
+vc4_first_render_job(struct vc4_dev *vc4)
 {
-	if (list_empty(&vc4->job_list))
+	if (list_empty(&vc4->render_job_list))
 		return NULL;
-	return list_first_entry(&vc4->job_list, struct vc4_exec_info, head);
+	return list_first_entry(&vc4->render_job_list,
+				struct vc4_exec_info, head);
 }
 
 /**
@@ -414,7 +431,9 @@ int vc4_wait_seqno_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 int vc4_wait_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
-void vc4_submit_next_job(struct drm_device *dev);
+void vc4_submit_next_bin_job(struct drm_device *dev);
+void vc4_submit_next_render_job(struct drm_device *dev);
+void vc4_move_job_to_render(struct drm_device *dev, struct vc4_exec_info *exec);
 int vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno,
 		       uint64_t timeout_ns, bool interruptible);
 void vc4_job_handle_completed(struct vc4_dev *vc4);