backend-drm: improve atomic commit failure handling

When an atomic commit fails then the output will be stuck in
REPAINT_AWAITING_COMPLETION state. It is waiting for a vblank event that was
never scheduled.
If the error is EBUSY then it can be expected to be a transient error. So
propagate the error and schedule a new repaint in the core compositor.

This is necessary because there are some circumstances when the commit can fail
unexpectedly:
- With 'state_invalid == true' one commit will disable all planes. If another
  commit for a different output is triggered immediately afterwards, then this
  commit can temporarily fail with EBUSY because it tries to use the same
  planes.
- At least with i915, if one commit enables an output then a second commit for a
  different output immediately afterwards can temporarily fail with EBUSY. This
  is probably caused by some hardware interdependency.

Signed-off-by: Michael Olbrich <m.olbrich@pengutronix.de>

2 files changed, 26 insertions, 6 deletions

diff --git a/libweston/backend-drm/drm.c b/libweston/backend-drm/drm.c
index c8bec7e4..79ab239d 100644
--- a/libweston/backend-drm/drm.c
+++ b/libweston/backend-drm/drm.c
@@ -593,8 +593,8 @@ drm_output_start_repaint_loop(struct weston_output *output_base)
 	if (ret != 0) {
 		weston_log("applying repaint-start state failed: %s\n",
 			   strerror(errno));
-		if (ret == -EACCES)
-			return -1;
+		if (ret == -EACCES || ret == -EBUSY)
+			return ret;
 		goto finish_frame;
 	}
 
@@ -657,7 +657,7 @@ drm_repaint_flush(struct weston_compositor *compositor)
 	drm_debug(b, "[repaint] flushed pending_state %p\n", pending_state);
 	device->repaint_data = NULL;
 
-	return (ret == -EACCES) ? -1 : 0;
+	return (ret == -EACCES || ret == -EBUSY) ? ret : 0;
 }
 
 /**
diff --git a/libweston/compositor.c b/libweston/compositor.c
index 89fe410e..9c1768d2 100644
--- a/libweston/compositor.c
+++ b/libweston/compositor.c
@@ -3405,6 +3405,20 @@ output_repaint_timer_arm(struct weston_compositor *compositor)
 	wl_event_source_timer_update(compositor->repaint_timer, msec_to_next);
 }
 
+static void
+weston_output_schedule_repaint_restart(struct weston_output *output)
+{
+	assert(output->repaint_status == REPAINT_AWAITING_COMPLETION);
+	/* The device was busy so try again one frame later */
+	timespec_add_nsec(&output->next_repaint, &output->next_repaint,
+			  millihz_to_nsec(output->current_mode->refresh));
+	output->repaint_status = REPAINT_SCHEDULED;
+	TL_POINT(output->compositor, "core_repaint_restart",
+		 TLP_OUTPUT(output), TLP_END);
+	output_repaint_timer_arm(output->compositor);
+	weston_output_damage(output);
+}
+
 static int
 output_repaint_timer_handler(void *data)
 {
@@ -3435,8 +3449,12 @@ output_repaint_timer_handler(void *data)
 
 	if (ret != 0) {
 		wl_list_for_each(output, &compositor->output_list, link) {
-			if (output->repainted)
-				weston_output_schedule_repaint_reset(output);
+			if (output->repainted) {
+				if (ret == -EBUSY)
+					weston_output_schedule_repaint_restart(output);
+				else
+					weston_output_schedule_repaint_reset(output);
+			}
 		}
 	}
 
@@ -3583,7 +3601,9 @@ idle_repaint(void *data)
 	output->repaint_status = REPAINT_AWAITING_COMPLETION;
 	output->idle_repaint_source = NULL;
 	ret = output->start_repaint_loop(output);
-	if (ret != 0)
+	if (ret == -EBUSY)
+		weston_output_schedule_repaint_restart(output);
+	else if (ret != 0)
 		weston_output_schedule_repaint_reset(output);
 }