Re: [PATCH net-next v4 09/15] virtio_net: xsk: bind/unbind xsk

[Xuan Zhuo <xuanzhuo@linux.alibaba.com>]

On Wed, 12 Jun 2024 19:43:01 -0400, "Michael S. Tsirkin" <mst@redhat.com> wrote:
> On Tue, Jun 11, 2024 at 07:41:41PM +0800, Xuan Zhuo wrote:
> > This patch implement the logic of bind/unbind xsk pool to sq and rq.
> >
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
>
> I'd just squash with previous patch. This one is hard to review in
> isolation.

Why?

The previous patch is to supply a API to switch to premapped mode for sq.

This is to introduce the xsk. This patch just use the API.
I do not think we should merge these two patch.

Thanks.


>
> > ---
> >  drivers/net/virtio_net.c | 199 +++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 199 insertions(+)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 4968ab7eb5a4..c82a0691632c 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -26,6 +26,7 @@
> >  #include <net/netdev_rx_queue.h>
> >  #include <net/netdev_queues.h>
> >  #include <uapi/linux/virtio_ring.h>
> > +#include <net/xdp_sock_drv.h>
> >
> >  static int napi_weight = NAPI_POLL_WEIGHT;
> >  module_param(napi_weight, int, 0444);
> > @@ -57,6 +58,8 @@ DECLARE_EWMA(pkt_len, 0, 64)
> >
> >  #define VIRTNET_DRIVER_VERSION "1.0.0"
> >
> > +static struct virtio_net_hdr_mrg_rxbuf xsk_hdr;
> > +
> >  static const unsigned long guest_offloads[] = {
> >  	VIRTIO_NET_F_GUEST_TSO4,
> >  	VIRTIO_NET_F_GUEST_TSO6,
> > @@ -320,6 +323,12 @@ struct send_queue {
> >  	bool premapped;
> >
> >  	struct virtnet_sq_dma_info dmainfo;
> > +
> > +	struct {
> > +		struct xsk_buff_pool *pool;
> > +
> > +		dma_addr_t hdr_dma_address;
> > +	} xsk;
> >  };
> >
> >  /* Internal representation of a receive virtqueue */
> > @@ -371,6 +380,13 @@ struct receive_queue {
> >
> >  	/* Record the last dma info to free after new pages is allocated. */
> >  	struct virtnet_rq_dma *last_dma;
> > +
> > +	struct {
> > +		struct xsk_buff_pool *pool;
> > +
> > +		/* xdp rxq used by xsk */
> > +		struct xdp_rxq_info xdp_rxq;
> > +	} xsk;
> >  };
> >
> >  /* This structure can contain rss message with maximum settings for indirection table and keysize
> > @@ -5168,6 +5184,187 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
> >  	return virtnet_set_guest_offloads(vi, offloads);
> >  }
> >
> > +static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queue *rq,
> > +				    struct xsk_buff_pool *pool)
> > +{
> > +	int err, qindex;
> > +
> > +	qindex = rq - vi->rq;
> > +
> > +	if (pool) {
> > +		err = xdp_rxq_info_reg(&rq->xsk.xdp_rxq, vi->dev, qindex, rq->napi.napi_id);
> > +		if (err < 0)
> > +			return err;
> > +
> > +		err = xdp_rxq_info_reg_mem_model(&rq->xsk.xdp_rxq,
> > +						 MEM_TYPE_XSK_BUFF_POOL, NULL);
> > +		if (err < 0) {
> > +			xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
> > +			return err;
> > +		}
> > +
> > +		xsk_pool_set_rxq_info(pool, &rq->xsk.xdp_rxq);
> > +	}
> > +
> > +	virtnet_rx_pause(vi, rq);
> > +
> > +	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf);
> > +	if (err) {
> > +		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
> > +
> > +		pool = NULL;
> > +	}
> > +
> > +	if (!pool)
> > +		xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
> > +
> > +	rq->xsk.pool = pool;
> > +
> > +	virtnet_rx_resume(vi, rq);
> > +
> > +	return err;
> > +}
> > +
> > +static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
> > +				    struct send_queue *sq,
> > +				    struct xsk_buff_pool *pool)
> > +{
> > +	int err, qindex;
> > +
> > +	qindex = sq - vi->sq;
> > +
> > +	virtnet_tx_pause(vi, sq);
> > +
> > +	err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf);
> > +	if (err)
> > +		netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err);
> > +	else
> > +		err = virtnet_sq_set_premapped(sq, !!pool);
> > +
> > +	if (err)
> > +		pool = NULL;
> > +
> > +	sq->xsk.pool = pool;
> > +
> > +	virtnet_tx_resume(vi, sq);
> > +
> > +	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 receive_queue *rq;
> > +	struct send_queue *sq;
> > +	struct device *dma_dev;
> > +	dma_addr_t hdr_dma;
> > +	int err;
> > +
> > +	/* In big_packets mode, xdp cannot work, so there is no need to
> > +	 * initialize xsk of rq.
> > +	 *
> > +	 * Support for small mode firstly.
> > +	 */
> > +	if (vi->big_packets)
> > +		return -ENOENT;
> > +
> > +	if (qid >= vi->curr_queue_pairs)
> > +		return -EINVAL;
> > +
> > +	sq = &vi->sq[qid];
> > +	rq = &vi->rq[qid];
> > +
> > +	/* xsk tx zerocopy depend on the tx napi.
> > +	 *
> > +	 * All xsk packets are actually consumed and sent out from the xsk tx
> > +	 * queue under the tx napi mechanism.
> > +	 */
> > +	if (!sq->napi.weight)
> > +		return -EPERM;
> > +
> > +	/* For the xsk, the tx and rx should have the same device. But
> > +	 * vq->dma_dev allows every vq has the respective dma dev. So I check
> > +	 * the dma dev of vq and sq is the same dev.
> > +	 */
> > +	if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq))
> > +		return -EPERM;
> > +
> > +	dma_dev = virtqueue_dma_dev(rq->vq);
> > +	if (!dma_dev)
> > +		return -EPERM;
> > +
> > +	hdr_dma = dma_map_single(dma_dev, &xsk_hdr, vi->hdr_len, DMA_TO_DEVICE);
> > +	if (dma_mapping_error(dma_dev, hdr_dma))
> > +		return -ENOMEM;
> > +
> > +	err = xsk_pool_dma_map(pool, dma_dev, 0);
> > +	if (err)
> > +		goto err_xsk_map;
> > +
> > +	err = virtnet_rq_bind_xsk_pool(vi, rq, pool);
> > +	if (err)
> > +		goto err_rq;
> > +
> > +	err = virtnet_sq_bind_xsk_pool(vi, sq, pool);
> > +	if (err)
> > +		goto err_sq;
> > +
> > +	/* Now, we do not support tx offset, so all the tx virtnet hdr is zero.
> > +	 * So all the tx packets can share a single hdr.
> > +	 */
> > +	sq->xsk.hdr_dma_address = hdr_dma;
> > +
> > +	return 0;
> > +
> > +err_sq:
> > +	virtnet_rq_bind_xsk_pool(vi, rq, NULL);
> > +err_rq:
> > +	xsk_pool_dma_unmap(pool, 0);
> > +err_xsk_map:
> > +	dma_unmap_single(dma_dev, hdr_dma, vi->hdr_len, DMA_TO_DEVICE);
> > +	return err;
> > +}
> > +
> > +static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
> > +{
> > +	struct virtnet_info *vi = netdev_priv(dev);
> > +	struct xsk_buff_pool *pool;
> > +	struct device *dma_dev;
> > +	struct receive_queue *rq;
> > +	struct send_queue *sq;
> > +	int err1, err2;
> > +
> > +	if (qid >= vi->curr_queue_pairs)
> > +		return -EINVAL;
> > +
> > +	sq = &vi->sq[qid];
> > +	rq = &vi->rq[qid];
> > +
> > +	pool = sq->xsk.pool;
> > +
> > +	err1 = virtnet_sq_bind_xsk_pool(vi, sq, NULL);
> > +	err2 = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
> > +
> > +	xsk_pool_dma_unmap(pool, 0);
> > +
> > +	dma_dev = virtqueue_dma_dev(rq->vq);
> > +
> > +	dma_unmap_single(dma_dev, sq->xsk.hdr_dma_address, vi->hdr_len, DMA_TO_DEVICE);
> > +
> > +	return err1 | err2;
> > +}
> > +
> > +static int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp)
> > +{
> > +	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);
> > +}
> > +
> >  static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
> >  			   struct netlink_ext_ack *extack)
> >  {
> > @@ -5293,6 +5490,8 @@ 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:
> > +		return virtnet_xsk_pool_setup(dev, xdp);
> >  	default:
> >  		return -EINVAL;
> >  	}
> > --
> > 2.32.0.3.g01195cf9f
>