Re: [net-next PATCH v3 5/6] virtio_net: add XDP_TX support

["Michael S. Tsirkin" <mst@redhat.com>]

On Tue, Nov 29, 2016 at 12:11:08PM -0800, John Fastabend wrote:
> This adds support for the XDP_TX action to virtio_net. When an XDP
> program is run and returns the XDP_TX action the virtio_net XDP
> implementation will transmit the packet on a TX queue that aligns
> with the current CPU that the XDP packet was processed on.
> 
> Before sending the packet the header is zeroed.  Also XDP is expected
> to handle checksum correctly so no checksum offload  support is
> provided.
> 
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> ---
>  drivers/net/virtio_net.c |   59 ++++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 56 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index a1bfa99..9604e55 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -330,12 +330,40 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
>  	return skb;
>  }
>  
> +static void virtnet_xdp_xmit(struct virtnet_info *vi,
> +			     unsigned int qnum, struct xdp_buff *xdp)
> +{
> +	struct send_queue *sq = &vi->sq[qnum];
> +	struct virtio_net_hdr_mrg_rxbuf *hdr;
> +	unsigned int num_sg, len;
> +	void *xdp_sent;
> +
> +	/* Free up any pending old buffers before queueing new ones. */
> +	while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
> +		struct page *page = virt_to_head_page(xdp_sent);
> +
> +		put_page(page);
> +	}
> +
> +	/* Zero header and leave csum up to XDP layers */
> +	hdr = xdp->data;
> +	memset(hdr, 0, vi->hdr_len);
> +	hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
> +	hdr->hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;

Do we really want this?
This is CHECKSUM_UNNECESSARY.
Does not XDP pass checksummed packets?


> +
> +	num_sg = 1;
> +	sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);
> +	virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, xdp->data, GFP_ATOMIC);

This might fail. If it does, you want to at least free up the memory.

> +	virtqueue_kick(sq->vq);
> +}
> +
>  static u32 do_xdp_prog(struct virtnet_info *vi,
>  		       struct bpf_prog *xdp_prog,
>  		       struct page *page, int offset, int len)
>  {
>  	int hdr_padded_len;
>  	struct xdp_buff xdp;
> +	unsigned int qp;
>  	u32 act;
>  	u8 *buf;
>  
> @@ -353,9 +381,15 @@ static u32 do_xdp_prog(struct virtnet_info *vi,
>  	switch (act) {
>  	case XDP_PASS:
>  		return XDP_PASS;
> +	case XDP_TX:
> +		qp = vi->curr_queue_pairs -
> +			vi->xdp_queue_pairs +
> +			smp_processor_id();
> +		xdp.data = buf + (vi->mergeable_rx_bufs ? 0 : 4);
> +		virtnet_xdp_xmit(vi, qp, &xdp);
> +		return XDP_TX;
>  	default:
>  		bpf_warn_invalid_xdp_action(act);
> -	case XDP_TX:
>  	case XDP_ABORTED:
>  	case XDP_DROP:
>  		return XDP_DROP;
> @@ -387,8 +421,16 @@ static struct sk_buff *receive_big(struct net_device *dev,
>  	if (xdp_prog) {
>  		u32 act = do_xdp_prog(vi, xdp_prog, page, 0, len);
>  
> -		if (act == XDP_DROP)
> +		switch (act) {
> +		case XDP_PASS:
> +			break;
> +		case XDP_TX:
> +			rcu_read_unlock();
> +			goto xdp_xmit;
> +		case XDP_DROP:
> +		default:
>  			goto err_xdp;
> +		}
>  	}
>  	rcu_read_unlock();
>  
> @@ -403,6 +445,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
>  err:
>  	dev->stats.rx_dropped++;
>  	give_pages(rq, page);
> +xdp_xmit:
>  	return NULL;
>  }
>  
> @@ -421,6 +464,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>  	struct sk_buff *head_skb, *curr_skb;
>  	struct bpf_prog *xdp_prog;
>  
> +	head_skb = NULL;
> +
>  	rcu_read_lock();
>  	xdp_prog = rcu_dereference(rq->xdp_prog);
>  	if (xdp_prog) {
> @@ -432,8 +477,15 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>  		}
>  
>  		act = do_xdp_prog(vi, xdp_prog, page, offset, len);
> -		if (act == XDP_DROP)
> +		switch (act) {
> +		case XDP_PASS:
> +			break;
> +		case XDP_TX:
> +			goto xdp_xmit;
> +		case XDP_DROP:
> +		default:
>  			goto err_xdp;
> +		}
>  	}
>  	rcu_read_unlock();
>  
> @@ -510,6 +562,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>  err_buf:
>  	dev->stats.rx_dropped++;
>  	dev_kfree_skb(head_skb);
> +xdp_xmit:
>  	return NULL;
>  }
>