On 04.10.2023 21:55:41, Vincent Mailhol wrote: > On Wed. 4 Oct. 2023 at 18:24, Marc Kleine-Budde <mkl@xxxxxxxxxxxxxx> wrote: > > The current at91_can driver uses NAPI to handle RX'ed CAN frames, the > > RX IRQ is disabled an a NAPI poll is scheduled. Then in at91_poll_rx() > ^^ > > and > > > the RX'ed CAN frames are tried to read in order from the device. > > > > This approach has 2 drawbacks: > > > > - Under high system load it might take too long from the initial RX > > IRQ to the NAPI poll function to run. This causes RX buffer > > overflows. > > - The algorithm to read the CAN frames in order is not bullet proof > > and may fail under certain use cases/system loads. > > > > The rx-offload helper fixes these problems by reading the RX'ed CAN > > frames in the interrupt handler and adding it a list sorted by RX > ^ > > adding it *to* a list? both fixed. Thanks, Marc -- Pengutronix e.K. | Marc Kleine-Budde | Embedded Linux | https://www.pengutronix.de | Vertretung Nürnberg | Phone: +49-5121-206917-129 | Amtsgericht Hildesheim, HRA 2686 | Fax: +49-5121-206917-9 |
Attachment:
signature.asc
Description: PGP signature
