On Mon, Jan 17, 2022 at 06:28:24PM +0100, Lorenzo Bianconi wrote:
> BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
> {
> void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
> void *data_end = xdp->data_end + offset;
>
> + if (unlikely(xdp_buff_has_frags(xdp))) { /* xdp multi-frags */
> + if (offset < 0)
> + return bpf_xdp_multi_frags_shrink_tail(xdp, -offset);
> +
> + return bpf_xdp_multi_frags_increase_tail(xdp, offset);
> + }
"multi frags" isn't quite correct here and in other places.
It sounds like watery water.
Saying "xdp frags" is enough to explain that xdp has fragments.
Either multiple fragments or just one fragment doesn't matter.
I think it would be cleaner to drop "multi".
