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 <a...@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
>
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
