From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesper Dangaard Brouer Date: Wed, 9 Sep 2020 17:37:14 +0200 Subject: [Intel-wired-lan] [PATCH bpf-next 0/6] xsk: exit NAPI loop when AF_XDP Rx ring is full In-Reply-To: <11f663ec-5ea7-926c-370d-0b67d3052583@nvidia.com> References: <20200904135332.60259-1-bjorn.topel@gmail.com> <0257f769-0f43-a5b7-176d-7c5ff8eaac3a@intel.com> <11f663ec-5ea7-926c-370d-0b67d3052583@nvidia.com> Message-ID: <20200909173714.25a3ce43@carbon> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: intel-wired-lan@osuosl.org List-ID: On Tue, 8 Sep 2020 13:32:01 +0300 Maxim Mikityanskiy wrote: > From the driver API perspective, I would prefer to see a simpler API if > possible. The current API exposes things that the driver shouldn't know > (BPF map type), and requires XSK-specific handling. It would be better > if some specific error code returned from xdp_do_redirect was reserved > to mean "exit NAPI early if you support it". This way we wouldn't need > two new helpers, two xdp_do_redirect functions, and this approach would > be extensible to other non-XSK use cases without further changes in the > driver, and also the logic to opt-in the feature could be put inside the > kernel. I agree. -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer