On Tue, Dec 15, 2020 at 09:23:38AM +0100, Guido Günther wrote:

It can take multiple iterations until all components for an attached DSI bridge are up leading to several:

[ 3.796425] mxsfb 30320000.lcd-controller: Cannot connect bridge: -517 [ 3.816952] mxsfb 30320000.lcd-controller: [drm:mxsfb_probe [mxsfb]] *ERROR* failed to attach bridge: -517

Silence this by checking for -EPROBE_DEFER and using dev_err_probe() so we set a deferred reason in case a dependency fails to probe (which quickly happens on small config/DT changes due to the rather long probe chain which can include bridges, phys, panels, backights, leds, etc.).

This also removes the only DRM_DEV_ERROR() usage, the rest of the driver uses dev_err().

Signed-off-by: Guido Günther agx@sigxcpu.org Fixes: c42001e357f7 ("drm: mxsfb: Use drm_panel_bridge")

Queued up for 5.11, thanks for your patch. -Daniel

---

drivers/gpu/drm/mxsfb/mxsfb_drv.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index 6faf17b6408d..6da93551e2e5 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -134,11 +134,8 @@ static int mxsfb_attach_bridge(struct mxsfb_drm_private *mxsfb) return -ENODEV;

ret = drm_bridge_attach(&mxsfb->encoder, bridge, NULL, 0);

• if (ret) {

• DRM_DEV_ERROR(drm->dev,
  

• 	      "failed to attach bridge: %d\n", ret);
  

• return ret;
  

• }

• if (ret)

• return dev_err_probe(drm->dev, ret, "Failed to attach bridge\n");
  
  

  mxsfb->bridge = bridge;

@@ -212,7 +209,8 @@ static int mxsfb_load(struct drm_device *drm,

ret = mxsfb_attach_bridge(mxsfb); if (ret) {

• dev_err(drm->dev, "Cannot connect bridge: %d\n", ret);
  

• if (ret != -EPROBE_DEFER)
  

• 	dev_err(drm->dev, "Cannot connect bridge: %d\n", ret);
  

  goto err_vblank; }

-- 2.29.2