RE: [PATCH net-next v4] xen networking: add basic XDP support for xen-netfront

[Paul Durrant <xadimgnik@gmail.com>]

> -----Original Message-----
> From: Denis Kirjanov <kda@linux-powerpc.org>
> Sent: 16 March 2020 13:10
> To: netdev@vger.kernel.org
> Cc: jgross@suse.com; ilias.apalodimas@linaro.org; wei.liu@kernel.org; paul@xen.org; Denis Kirjanov
> <kda@linux-powerpc.org>
> Subject: [PATCH net-next v4] xen networking: add basic XDP support for xen-netfront
> 
> The patch adds a basic XDP processing to xen-netfront driver.
> 
> We ran an XDP program for an RX response received from netback
> driver. Also we request xen-netback to adjust data offset for
> bpf_xdp_adjust_head() header space for custom headers.
> 
> v4:
> - added verbose patch descriprion
> - don't expose the XDP headroom offset to the domU guest
> - add a modparam to netback to toggle XDP offset
> - don't process jumbo frames for now
> 
> v3:
> - added XDP_TX support (tested with xdping echoserver)
> - added XDP_REDIRECT support (tested with modified xdp_redirect_kern)
> - moved xdp negotiation to xen-netback
> 
> v2:
> - avoid data copying while passing to XDP
> - tell xen-netback that we need the headroom space
> 
> Signed-off-by: Denis Kirjanov <kda@linux-powerpc.org>
> ---
>  drivers/net/xen-netback/common.h  |   2 +
>  drivers/net/xen-netback/netback.c |   7 ++
>  drivers/net/xen-netback/rx.c      |   7 +-
>  drivers/net/xen-netback/xenbus.c  |  28 +++++
>  drivers/net/xen-netfront.c        | 240 +++++++++++++++++++++++++++++++++++++-
>  5 files changed, 282 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
> index 05847eb..4a148d6 100644
> --- a/drivers/net/xen-netback/common.h
> +++ b/drivers/net/xen-netback/common.h
> @@ -280,6 +280,7 @@ struct xenvif {
>  	u8 ip_csum:1;
>  	u8 ipv6_csum:1;
>  	u8 multicast_control:1;
> +	u8 xdp_enabled:1;
> 
>  	/* Is this interface disabled? True when backend discovers
>  	 * frontend is rogue.
> @@ -395,6 +396,7 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
>  irqreturn_t xenvif_interrupt(int irq, void *dev_id);
> 
>  extern bool separate_tx_rx_irq;
> +extern bool provides_xdp_headroom;
> 
>  extern unsigned int rx_drain_timeout_msecs;
>  extern unsigned int rx_stall_timeout_msecs;
> diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
> index 315dfc6..6dfca72 100644
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -96,6 +96,13 @@
>  module_param_named(hash_cache_size, xenvif_hash_cache_size, uint, 0644);
>  MODULE_PARM_DESC(hash_cache_size, "Number of flows in the hash cache");
> 
> +/* The module parameter tells that we have to put data
> + * for xen-netfront with the XDP_PACKET_HEADROOM offset
> + * needed for XDP processing
> + */
> +bool provides_xdp_headroom = true;
> +module_param(provides_xdp_headroom, bool, 0644);
> +
>  static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
>  			       u8 status);
> 
> diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
> index ef58870..aba826b 100644
> --- a/drivers/net/xen-netback/rx.c
> +++ b/drivers/net/xen-netback/rx.c
> @@ -33,6 +33,11 @@
>  #include <xen/xen.h>
>  #include <xen/events.h>
> 
> +static inline int xenvif_rx_xdp_offset(struct xenvif *vif)
> +{
> +	return (vif->xdp_enabled ? XDP_PACKET_HEADROOM : 0);
> +}
> +

No need for the brackets here.

[snip]
> @@ -167,6 +175,9 @@ struct netfront_rx_info {
>  	struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
>  };
> 
> +static int xennet_xdp_xmit(struct net_device *dev, int n,
> +			   struct xdp_frame **frames, u32 flags);
> +
>  static void skb_entry_set_link(union skb_entry *list, unsigned short id)
>  {
>  	list->link = id;
> @@ -406,7 +417,8 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
>  			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
>  			queue->grant_tx_page[id] = NULL;
>  			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
> -			dev_kfree_skb_irq(skb);
> +			if (skb)
> +				dev_kfree_skb_irq(skb);

Can you drop this? I said previously that it is unnecessary.

  Paul