Am Samstag, 16. Oktober 2021, 12:53:50 CEST schrieb Nicolas Frattaroli: > In cases where both rx and tx lrck are synced to the same source, > the resets for rx and tx need to be triggered simultaneously, > according to the downstream driver. > > As there is no reset API to atomically bulk (de)assert two resets > at once, what the driver did was implement half a reset controller > specific to Rockchip, which tried to write the registers for the > resets within one write ideally or several writes within an irqsave > section. > > This of course violates abstractions quite badly. The driver should > not write to the CRU's registers directly. > > In practice, for the cases I tested the driver with, which is audio > playback, replacing the synchronised asserts with just individual > ones does not seem to make any difference. > > If it turns out that this breaks something in the future, it should > be fixed through the specification and implementation of an atomic > bulk reset API, not with a CRU hack. > > Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@xxxxxxxxx> Reviewed-by: Heiko Stuebner <heiko@xxxxxxxxx>
