Virtualization - Apr 2021 - [PATCH net-next v3 3/8] virtio-net: xsk zero copy xmit setup

? 2021/3/31 ??3:11, Xuan Zhuo ??:
> xsk is a high-performance packet receiving and sending technology.
>
> This patch implements the binding and unbinding operations of xsk and
> the virtio-net queue for xsk zero copy xmit.
>
> The xsk zero copy xmit depends on tx napi. So if tx napi is not opened,
> an error will be reported. And the entire operation is under the
> protection of rtnl_lock
>
> Signed-off-by: Xuan Zhuo <xuanzhuo at linux.alibaba.com>
> Reviewed-by: Dust Li <dust.li at linux.alibaba.com>
> ---
>   drivers/net/virtio_net.c | 66 ++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 66 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index bb4ea9dbc16b..4e25408a2b37 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -22,6 +22,7 @@
>   #include <net/route.h>
>   #include <net/xdp.h>
>   #include <net/net_failover.h>
> +#include <net/xdp_sock_drv.h>
>   
>   static int napi_weight = NAPI_POLL_WEIGHT;
>   module_param(napi_weight, int, 0444);
> @@ -133,6 +134,11 @@ struct send_queue {
>   	struct virtnet_sq_stats stats;
>   
>   	struct napi_struct napi;
> +
> +	struct {
> +		/* xsk pool */
> +		struct xsk_buff_pool __rcu *pool;
> +	} xsk;
>   };
>   
>   /* Internal representation of a receive virtqueue */
> @@ -2526,11 +2532,71 @@ static int virtnet_xdp_set(struct net_device *dev,
struct bpf_prog *prog,
>   	return err;
>   }
>   
> +static int virtnet_xsk_pool_enable(struct net_device *dev,
> +				   struct xsk_buff_pool *pool,
> +				   u16 qid)
> +{
> +	struct virtnet_info *vi = netdev_priv(dev);
> +	struct send_queue *sq;
> +	int ret = -EBUSY;

I'd rather move this under the check of xsk.pool.

> +
> +	if (qid >= vi->curr_queue_pairs)
> +		return -EINVAL;
> +
> +	sq = &vi->sq[qid];
> +
> +	/* xsk zerocopy depend on the tx napi */

Need more comments to explain why tx NAPI is required here.

And what's more important, tx NAPI could be enabled/disable via ethtool, 
what if the NAPI is disabled after xsk is enabled?

> +	if (!sq->napi.weight)
> +		return -EPERM;
> +
> +	rcu_read_lock();
> +	if (rcu_dereference(sq->xsk.pool))
> +		goto end;

Under what condition can we reach here?

> +
> +	/* Here is already protected by rtnl_lock, so rcu_assign_pointer is
> +	 * safe.
> +	 */
> +	rcu_assign_pointer(sq->xsk.pool, pool);
> +	ret = 0;
> +end:
> +	rcu_read_unlock();
> +
> +	return ret;
> +}
> +
> +static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
> +{
> +	struct virtnet_info *vi = netdev_priv(dev);
> +	struct send_queue *sq;
> +
> +	if (qid >= vi->curr_queue_pairs)
> +		return -EINVAL;
> +
> +	sq = &vi->sq[qid];
> +
> +	/* Here is already protected by rtnl_lock, so rcu_assign_pointer is
> +	 * safe.
> +	 */
> +	rcu_assign_pointer(sq->xsk.pool, NULL);
> +
> +	synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */

Since rtnl is held here, I guess it's better to use synchornize_net().

> +
> +	return 0;
> +}
> +
>   static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
>   {
>   	switch (xdp->command) {
>   	case XDP_SETUP_PROG:
>   		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
> +	case XDP_SETUP_XSK_POOL:
> +		/* virtio net not use dma before call vring api */
> +		xdp->xsk.check_dma = false;

I think it's better not open code things like this. How about introduce 
new parameters in xp_assign_dev()?

> +		if (xdp->xsk.pool)
> +			return virtnet_xsk_pool_enable(dev, xdp->xsk.pool,
> +						       xdp->xsk.queue_id);
> +		else
> +			return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id);
>   	default:
>   		return -EINVAL;
>   	}

Thanks