Re: [RFC PATCH 4/5] mlx4: add support for fast rx drop bpf program

[Jesper Dangaard Brouer <brouer@redhat.com>]

On Fri,  1 Apr 2016 18:21:57 -0700
Brenden Blanco <bblanco@plumgrid.com> wrote:

> @@ -840,6 +843,21 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
>  		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
>  			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
>  
> +		/* A bpf program gets first chance to drop the packet. It may
> +		 * read bytes but not past the end of the frag. A non-zero
> +		 * return indicates packet should be dropped.
> +		 */
> +		if (prog) {
> +			struct ethhdr *ethh;
> +
> +			ethh = (struct ethhdr *)(page_address(frags[0].page) +
> +						 frags[0].page_offset);
> +			if (mlx4_call_bpf(prog, ethh, length)) {
> +				priv->stats.rx_dropped++;
> +				goto next;
> +			}
> +		}
> +

For future API, I can imagine more return codes being needed.

For forwarding I could imagine returning "STOLEN", which should not
increment rx_dropped.

One could also imagine supporting tcpdump/af_packet like facilities at
this packet-page level (e.g. af_packet queue packets into a RX ring
buffer, later processed/read async). It could return "SHARED", bumping
refcnt on page, and indicate page is now read-only. Thus, affecting
drivers processing flow.

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer