On 05/02/2018 01:01 PM, Björn Töpel wrote:
> From: Björn Töpel <bjorn.to...@intel.com>
>
> Here the actual receive functions of AF_XDP are implemented, that in a
> later commit, will be called from the XDP layers.
>
> There's one set of functions for the XDP_DRV side and another for
> XDP_SKB (generic).
>
> A new XDP API, xdp_return_buff, is also introduced.
>
> Adding xdp_return_buff, which is analogous to xdp_return_frame, but
> acts upon an struct xdp_buff. The API will be used by AF_XDP in future
> commits.
>
> Support for the poll syscall is also implemented.
>
> v2: xskq_validate_id did not update cons_tail.
> The entries variable was calculated twice in xskq_nb_avail.
> Squashed xdp_return_buff commit.
>
> Signed-off-by: Björn Töpel <bjorn.to...@intel.com>
> ---
> include/net/xdp.h | 1 +
> include/net/xdp_sock.h | 22 ++++++++++
> net/core/xdp.c | 15 +++++--
> net/xdp/xdp_umem.h | 18 ++++++++
> net/xdp/xsk.c | 73 ++++++++++++++++++++++++++++++-
> net/xdp/xsk_queue.h | 114
> ++++++++++++++++++++++++++++++++++++++++++++++++-
> 6 files changed, 238 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/xdp.h b/include/net/xdp.h
> index 137ad5f9f40f..0b689cf561c7 100644
> --- a/include/net/xdp.h
> +++ b/include/net/xdp.h
> @@ -104,6 +104,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff
> *xdp)
> }
>
> void xdp_return_frame(struct xdp_frame *xdpf);
> +void xdp_return_buff(struct xdp_buff *xdp);
>
> int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
> struct net_device *dev, u32 queue_index);
[...]
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index bf2c97b87992..4e1e6c581e1d 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -41,6 +41,74 @@ static struct xdp_sock *xdp_sk(struct sock *sk)
> return (struct xdp_sock *)sk;
> }
>
> +static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
> +{
> + u32 *id, len = xdp->data_end - xdp->data;
> + void *buffer;
> + int err = 0;
> +
> + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
> + return -EINVAL;
> +
> + id = xskq_peek_id(xs->umem->fq);
> + if (!id)
> + return -ENOSPC;
> +
> + buffer = xdp_umem_get_data_with_headroom(xs->umem, *id);
> + memcpy(buffer, xdp->data, len);
> + err = xskq_produce_batch_desc(xs->rx, *id, len,
> + xs->umem->frame_headroom);
> + if (!err)
> + xskq_discard_id(xs->umem->fq);
> +
> + return err;
> +}
> +
> +int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
> +{
> + int err;
> +
> + err = __xsk_rcv(xs, xdp);
> + if (likely(!err))
> + xdp_return_buff(xdp);
> + else
> + xs->rx_dropped++;
This is triggered from __bpf_tx_xdp_map() -> __xsk_map_redirect().
Should this be percpu counter instead?
> + return err;
> +}
> +
> +void xsk_flush(struct xdp_sock *xs)
> +{
> + xskq_produce_flush_desc(xs->rx);
> + xs->sk.sk_data_ready(&xs->sk);
> +}
> +
> +int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
> +{
> + int err;
> +
> + err = __xsk_rcv(xs, xdp);
> + if (!err)
> + xsk_flush(xs);
> + else
> + xs->rx_dropped++;
> +
> + return err;
> +}
> +
