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@gmail.com>

Reviewed-by: Heiko Stuebner <heiko@sntech.de>



_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel