On Thu, 25 Jan 2024 18:19:12 +0800, Liang Chen <[email protected]> wrote:
> The RSS hash report is a feature that's part of the virtio specification.
> Currently, virtio backends like qemu, vdpa (mlx5), and potentially vhost
> (still a work in progress as per [1]) support this feature. While the
> capability to obtain the RSS hash has been enabled in the normal path,
> it's currently missing in the XDP path. Therefore, we are introducing
> XDP hints through kfuncs to allow XDP programs to access the RSS hash.
>
> 1.
> https://lore.kernel.org/all/[email protected]/#r
>
> Signed-off-by: Liang Chen <[email protected]>
> ---
> drivers/net/virtio_net.c | 98 +++++++++++++++++++++++++++++++++++-----
> 1 file changed, 86 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index d7ce4a1011ea..0c845f2223da 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -349,6 +349,12 @@ struct virtio_net_common_hdr {
> };
> };
>
> +struct virtnet_xdp_buff {
> + struct xdp_buff xdp;
> + u32 hash_value;
> + u16 hash_report;
> +};
> +
> static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
>
> static bool is_xdp_frame(void *ptr)
> @@ -1033,6 +1039,16 @@ static void put_xdp_frags(struct xdp_buff *xdp)
> }
> }
>
> +static void virtnet_xdp_save_rx_hash(struct virtnet_xdp_buff *virtnet_xdp,
> + struct net_device *dev,
> + struct virtio_net_hdr_v1_hash *hdr_hash)
> +{
> + if (dev->features & NETIF_F_RXHASH) {
> + virtnet_xdp->hash_value = __le32_to_cpu(hdr_hash->hash_value);
> + virtnet_xdp->hash_report = __le16_to_cpu(hdr_hash->hash_report);
Could we put the __leXX_to_cpu to virtnet_xdp_rx_hash?
Other looks good to me.
Reviewed-by: Xuan Zhuo <[email protected]>
Thanks.
> + }
> +}
> +
> static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
> struct net_device *dev,
> unsigned int *xdp_xmit,
> @@ -1199,9 +1215,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> unsigned int headroom = vi->hdr_len + header_offset;
> struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
> struct page *page = virt_to_head_page(buf);
> + struct virtnet_xdp_buff virtnet_xdp;
> struct page *xdp_page;
> + struct xdp_buff *xdp;
> unsigned int buflen;
> - struct xdp_buff xdp;
> struct sk_buff *skb;
> unsigned int metasize = 0;
> u32 act;
> @@ -1233,17 +1250,20 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> page = xdp_page;
> }
>
> - xdp_init_buff(&xdp, buflen, &rq->xdp_rxq);
> - xdp_prepare_buff(&xdp, buf + VIRTNET_RX_PAD + vi->hdr_len,
> + xdp = &virtnet_xdp.xdp;
> + xdp_init_buff(xdp, buflen, &rq->xdp_rxq);
> + xdp_prepare_buff(xdp, buf + VIRTNET_RX_PAD + vi->hdr_len,
> xdp_headroom, len, true);
>
> - act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats);
> + virtnet_xdp_save_rx_hash(&virtnet_xdp, dev, (void *)hdr);
> +
> + act = virtnet_xdp_handler(xdp_prog, xdp, dev, xdp_xmit, stats);
>
> switch (act) {
> case XDP_PASS:
> /* Recalculate length in case bpf program changed it */
> - len = xdp.data_end - xdp.data;
> - metasize = xdp.data - xdp.data_meta;
> + len = xdp->data_end - xdp->data;
> + metasize = xdp->data - xdp->data_meta;
> break;
>
> case XDP_TX:
> @@ -1254,7 +1274,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> goto err_xdp;
> }
>
> - skb = virtnet_build_skb(buf, buflen, xdp.data - buf, len);
> + skb = virtnet_build_skb(buf, buflen, xdp->data - buf, len);
> if (unlikely(!skb))
> goto err;
>
> @@ -1591,10 +1611,11 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
> struct page *page = virt_to_head_page(buf);
> int offset = buf - page_address(page);
> + struct virtnet_xdp_buff virtnet_xdp;
> unsigned int xdp_frags_truesz = 0;
> struct sk_buff *head_skb;
> unsigned int frame_sz;
> - struct xdp_buff xdp;
> + struct xdp_buff *xdp;
> void *data;
> u32 act;
> int err;
> @@ -1604,16 +1625,19 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> if (unlikely(!data))
> goto err_xdp;
>
> - err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz,
> + xdp = &virtnet_xdp.xdp;
> + err = virtnet_build_xdp_buff_mrg(dev, vi, rq, xdp, data, len, frame_sz,
> &num_buf, &xdp_frags_truesz, stats);
> if (unlikely(err))
> goto err_xdp;
>
> - act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats);
> + virtnet_xdp_save_rx_hash(&virtnet_xdp, dev, (void *)hdr);
> +
> + act = virtnet_xdp_handler(xdp_prog, xdp, dev, xdp_xmit, stats);
>
> switch (act) {
> case XDP_PASS:
> - head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
> + head_skb = build_skb_from_xdp_buff(dev, vi, xdp, xdp_frags_truesz);
> if (unlikely(!head_skb))
> break;
> return head_skb;
> @@ -1626,7 +1650,7 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> break;
> }
>
> - put_xdp_frags(&xdp);
> + put_xdp_frags(xdp);
>
> err_xdp:
> put_page(page);
> @@ -4579,6 +4603,55 @@ static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu)
> }
> }
>
> +static int virtnet_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
> + enum xdp_rss_hash_type *rss_type)
> +{
> + const struct virtnet_xdp_buff *virtnet_xdp = (void *)_ctx;
> +
> + if (!(virtnet_xdp->xdp.rxq->dev->features & NETIF_F_RXHASH))
> + return -ENODATA;
> +
> + switch (virtnet_xdp->hash_report) {
> + case VIRTIO_NET_HASH_REPORT_TCPv4:
> + *rss_type = XDP_RSS_TYPE_L4_IPV4_TCP;
> + break;
> + case VIRTIO_NET_HASH_REPORT_UDPv4:
> + *rss_type = XDP_RSS_TYPE_L4_IPV4_UDP;
> + break;
> + case VIRTIO_NET_HASH_REPORT_TCPv6:
> + *rss_type = XDP_RSS_TYPE_L4_IPV6_TCP;
> + break;
> + case VIRTIO_NET_HASH_REPORT_UDPv6:
> + *rss_type = XDP_RSS_TYPE_L4_IPV6_UDP;
> + break;
> + case VIRTIO_NET_HASH_REPORT_TCPv6_EX:
> + *rss_type = XDP_RSS_TYPE_L4_IPV6_TCP_EX;
> + break;
> + case VIRTIO_NET_HASH_REPORT_UDPv6_EX:
> + *rss_type = XDP_RSS_TYPE_L4_IPV6_UDP_EX;
> + break;
> + case VIRTIO_NET_HASH_REPORT_IPv4:
> + *rss_type = XDP_RSS_TYPE_L3_IPV4;
> + break;
> + case VIRTIO_NET_HASH_REPORT_IPv6:
> + *rss_type = XDP_RSS_TYPE_L3_IPV6;
> + break;
> + case VIRTIO_NET_HASH_REPORT_IPv6_EX:
> + *rss_type = XDP_RSS_TYPE_L3_IPV6_EX;
> + break;
> + case VIRTIO_NET_HASH_REPORT_NONE:
> + default:
> + *rss_type = XDP_RSS_TYPE_NONE;
> + }
> +
> + *hash = virtnet_xdp->hash_value;
> + return 0;
> +}
> +
> +static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = {
> + .xmo_rx_hash = virtnet_xdp_rx_hash,
> +};
> +
> static int virtnet_probe(struct virtio_device *vdev)
> {
> int i, err = -ENOMEM;
> @@ -4704,6 +4777,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> VIRTIO_NET_RSS_HASH_TYPE_UDP_EX);
>
> dev->hw_features |= NETIF_F_RXHASH;
> + dev->xdp_metadata_ops = &virtnet_xdp_metadata_ops;
> }
>
> if (vi->has_rss_hash_report)
> --
> 2.40.1
>
On Tue, Jan 30, 2024 at 7:53 PM Xuan Zhuo <[email protected]> wrote:
>
> On Thu, 25 Jan 2024 18:19:12 +0800, Liang Chen <[email protected]> wrote:
> > The RSS hash report is a feature that's part of the virtio specification.
> > Currently, virtio backends like qemu, vdpa (mlx5), and potentially vhost
> > (still a work in progress as per [1]) support this feature. While the
> > capability to obtain the RSS hash has been enabled in the normal path,
> > it's currently missing in the XDP path. Therefore, we are introducing
> > XDP hints through kfuncs to allow XDP programs to access the RSS hash.
> >
> > 1.
> > https://lore.kernel.org/all/[email protected]/#r
> >
> > Signed-off-by: Liang Chen <[email protected]>
> > ---
> > drivers/net/virtio_net.c | 98 +++++++++++++++++++++++++++++++++++-----
> > 1 file changed, 86 insertions(+), 12 deletions(-)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index d7ce4a1011ea..0c845f2223da 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -349,6 +349,12 @@ struct virtio_net_common_hdr {
> > };
> > };
> >
> > +struct virtnet_xdp_buff {
> > + struct xdp_buff xdp;
> > + u32 hash_value;
> > + u16 hash_report;
> > +};
> > +
> > static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> >
> > static bool is_xdp_frame(void *ptr)
> > @@ -1033,6 +1039,16 @@ static void put_xdp_frags(struct xdp_buff *xdp)
> > }
> > }
> >
> > +static void virtnet_xdp_save_rx_hash(struct virtnet_xdp_buff *virtnet_xdp,
> > + struct net_device *dev,
> > + struct virtio_net_hdr_v1_hash *hdr_hash)
> > +{
> > + if (dev->features & NETIF_F_RXHASH) {
> > + virtnet_xdp->hash_value = __le32_to_cpu(hdr_hash->hash_value);
> > + virtnet_xdp->hash_report = __le16_to_cpu(hdr_hash->hash_report);
>
> Could we put the __leXX_to_cpu to virtnet_xdp_rx_hash?
Sure. Thanks!
>
> Other looks good to me.
>
> Reviewed-by: Xuan Zhuo <[email protected]>
>
> Thanks.
>
>
> > + }
> > +}
> > +
> > static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
> > struct net_device *dev,
> > unsigned int *xdp_xmit,
> > @@ -1199,9 +1215,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> > unsigned int headroom = vi->hdr_len + header_offset;
> > struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
> > struct page *page = virt_to_head_page(buf);
> > + struct virtnet_xdp_buff virtnet_xdp;
> > struct page *xdp_page;
> > + struct xdp_buff *xdp;
> > unsigned int buflen;
> > - struct xdp_buff xdp;
> > struct sk_buff *skb;
> > unsigned int metasize = 0;
> > u32 act;
> > @@ -1233,17 +1250,20 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> > page = xdp_page;
> > }
> >
> > - xdp_init_buff(&xdp, buflen, &rq->xdp_rxq);
> > - xdp_prepare_buff(&xdp, buf + VIRTNET_RX_PAD + vi->hdr_len,
> > + xdp = &virtnet_xdp.xdp;
> > + xdp_init_buff(xdp, buflen, &rq->xdp_rxq);
> > + xdp_prepare_buff(xdp, buf + VIRTNET_RX_PAD + vi->hdr_len,
> > xdp_headroom, len, true);
> >
> > - act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats);
> > + virtnet_xdp_save_rx_hash(&virtnet_xdp, dev, (void *)hdr);
> > +
> > + act = virtnet_xdp_handler(xdp_prog, xdp, dev, xdp_xmit, stats);
> >
> > switch (act) {
> > case XDP_PASS:
> > /* Recalculate length in case bpf program changed it */
> > - len = xdp.data_end - xdp.data;
> > - metasize = xdp.data - xdp.data_meta;
> > + len = xdp->data_end - xdp->data;
> > + metasize = xdp->data - xdp->data_meta;
> > break;
> >
> > case XDP_TX:
> > @@ -1254,7 +1274,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
> > goto err_xdp;
> > }
> >
> > - skb = virtnet_build_skb(buf, buflen, xdp.data - buf, len);
> > + skb = virtnet_build_skb(buf, buflen, xdp->data - buf, len);
> > if (unlikely(!skb))
> > goto err;
> >
> > @@ -1591,10 +1611,11 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> > int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
> > struct page *page = virt_to_head_page(buf);
> > int offset = buf - page_address(page);
> > + struct virtnet_xdp_buff virtnet_xdp;
> > unsigned int xdp_frags_truesz = 0;
> > struct sk_buff *head_skb;
> > unsigned int frame_sz;
> > - struct xdp_buff xdp;
> > + struct xdp_buff *xdp;
> > void *data;
> > u32 act;
> > int err;
> > @@ -1604,16 +1625,19 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> > if (unlikely(!data))
> > goto err_xdp;
> >
> > - err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz,
> > + xdp = &virtnet_xdp.xdp;
> > + err = virtnet_build_xdp_buff_mrg(dev, vi, rq, xdp, data, len, frame_sz,
> > &num_buf, &xdp_frags_truesz, stats);
> > if (unlikely(err))
> > goto err_xdp;
> >
> > - act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats);
> > + virtnet_xdp_save_rx_hash(&virtnet_xdp, dev, (void *)hdr);
> > +
> > + act = virtnet_xdp_handler(xdp_prog, xdp, dev, xdp_xmit, stats);
> >
> > switch (act) {
> > case XDP_PASS:
> > - head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
> > + head_skb = build_skb_from_xdp_buff(dev, vi, xdp, xdp_frags_truesz);
> > if (unlikely(!head_skb))
> > break;
> > return head_skb;
> > @@ -1626,7 +1650,7 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
> > break;
> > }
> >
> > - put_xdp_frags(&xdp);
> > + put_xdp_frags(xdp);
> >
> > err_xdp:
> > put_page(page);
> > @@ -4579,6 +4603,55 @@ static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu)
> > }
> > }
> >
> > +static int virtnet_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
> > + enum xdp_rss_hash_type *rss_type)
> > +{
> > + const struct virtnet_xdp_buff *virtnet_xdp = (void *)_ctx;
> > +
> > + if (!(virtnet_xdp->xdp.rxq->dev->features & NETIF_F_RXHASH))
> > + return -ENODATA;
> > +
> > + switch (virtnet_xdp->hash_report) {
> > + case VIRTIO_NET_HASH_REPORT_TCPv4:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV4_TCP;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_UDPv4:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV4_UDP;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_TCPv6:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV6_TCP;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_UDPv6:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV6_UDP;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_TCPv6_EX:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV6_TCP_EX;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_UDPv6_EX:
> > + *rss_type = XDP_RSS_TYPE_L4_IPV6_UDP_EX;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_IPv4:
> > + *rss_type = XDP_RSS_TYPE_L3_IPV4;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_IPv6:
> > + *rss_type = XDP_RSS_TYPE_L3_IPV6;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_IPv6_EX:
> > + *rss_type = XDP_RSS_TYPE_L3_IPV6_EX;
> > + break;
> > + case VIRTIO_NET_HASH_REPORT_NONE:
> > + default:
> > + *rss_type = XDP_RSS_TYPE_NONE;
> > + }
> > +
> > + *hash = virtnet_xdp->hash_value;
> > + return 0;
> > +}
> > +
> > +static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = {
> > + .xmo_rx_hash = virtnet_xdp_rx_hash,
> > +};
> > +
> > static int virtnet_probe(struct virtio_device *vdev)
> > {
> > int i, err = -ENOMEM;
> > @@ -4704,6 +4777,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> > VIRTIO_NET_RSS_HASH_TYPE_UDP_EX);
> >
> > dev->hw_features |= NETIF_F_RXHASH;
> > + dev->xdp_metadata_ops = &virtnet_xdp_metadata_ops;
> > }
> >
> > if (vi->has_rss_hash_report)
> > --
> > 2.40.1
> >