Re: [bpf-next V1 PATCH 8/8] bpf/xdp: devmap can avoid calling ndo_xdp_flush
From: Jesper Dangaard Brouer <hidden>
Date: 2018-05-31 07:49:08
From: Jesper Dangaard Brouer <hidden>
Date: 2018-05-31 07:49:08
On Wed, 30 May 2018 15:06:27 -0700 Song Liu [off-list ref] wrote:
quoted
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 04fbd75a5274..9c846a7a8cff 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c@@ -217,7 +217,7 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) } static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq) + struct xdp_bulk_queue *bq, bool flush)How about we use "int flags" instead of "bool flush" for easier extension?
This is an internal function in devmap.c, so we can change it completely as we like. But I do see your point, and will change this to match the flags type of ndo_xdp_xmit, because that allows us to pass this directly to that function without any conditional statements (although I was expecting to compiler to optimized this out anyway). -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer