diff mbox series

[net-next,v1,09/19] virtio_net: xsk: bind/unbind xsk

Message ID 20231016120033.26933-10-xuanzhuo@linux.alibaba.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series virtio-net: support AF_XDP zero copy | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches (and no cover letter)
netdev/tree_selection success Clearly marked for net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1360 this patch: 1360
netdev/cc_maintainers success CCed 14 of 14 maintainers
netdev/build_clang success Errors and warnings before: 1385 this patch: 1385
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1387 this patch: 1387
netdev/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: line length of 83 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 92 exceeds 80 columns WARNING: line length of 96 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Xuan Zhuo Oct. 16, 2023, noon UTC 
This patch implement the logic of bind/unbind xsk pool to sq and rq.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 drivers/net/virtio/Makefile     |   2 +-
 drivers/net/virtio/main.c       |  10 +-
 drivers/net/virtio/virtio_net.h |  18 ++++
 drivers/net/virtio/xsk.c        | 186 ++++++++++++++++++++++++++++++++
 drivers/net/virtio/xsk.h        |   7 ++
 5 files changed, 216 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/virtio/xsk.c
 create mode 100644 drivers/net/virtio/xsk.h

Comments

Jason Wang Oct. 20, 2023, 6:51 a.m. UTC | #1 
On Mon, Oct 16, 2023 at 8:01 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
>
> This patch implement the logic of bind/unbind xsk pool to sq and rq.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> ---
>  drivers/net/virtio/Makefile     |   2 +-
>  drivers/net/virtio/main.c       |  10 +-
>  drivers/net/virtio/virtio_net.h |  18 ++++
>  drivers/net/virtio/xsk.c        | 186 ++++++++++++++++++++++++++++++++
>  drivers/net/virtio/xsk.h        |   7 ++
>  5 files changed, 216 insertions(+), 7 deletions(-)
>  create mode 100644 drivers/net/virtio/xsk.c
>  create mode 100644 drivers/net/virtio/xsk.h
>
> diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
> index 15ed7c97fd4f..8c2a884d2dba 100644
> --- a/drivers/net/virtio/Makefile
> +++ b/drivers/net/virtio/Makefile
> @@ -5,4 +5,4 @@
>
>  obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
>
> -virtio_net-y := main.o
> +virtio_net-y := main.o xsk.o
> diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
> index 02d27101fef1..38733a782f12 100644
> --- a/drivers/net/virtio/main.c
> +++ b/drivers/net/virtio/main.c
> @@ -8,7 +8,6 @@
>  #include <linux/etherdevice.h>
>  #include <linux/module.h>
>  #include <linux/virtio.h>
> -#include <linux/virtio_net.h>
>  #include <linux/bpf.h>
>  #include <linux/bpf_trace.h>
>  #include <linux/scatterlist.h>
> @@ -139,9 +138,6 @@ struct virtio_net_common_hdr {
>         };
>  };
>
> -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
> -static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> -
>  static void *xdp_to_ptr(struct xdp_frame *ptr)
>  {
>         return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
> @@ -3664,6 +3660,8 @@ 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;
>         }
> @@ -3849,7 +3847,7 @@ static void free_receive_page_frags(struct virtnet_info *vi)
>                 }
>  }
>
> -static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
> +void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
>  {
>         if (!virtnet_is_xdp_frame(buf))
>                 dev_kfree_skb(buf);
> @@ -3857,7 +3855,7 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
>                 xdp_return_frame(virtnet_ptr_to_xdp(buf));
>  }
>
> -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
> +void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
>  {
>         struct virtnet_info *vi = vq->vdev->priv;
>         int i = vq2rxq(vq);
> diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
> index cc742756e19a..9e69b6c5921b 100644
> --- a/drivers/net/virtio/virtio_net.h
> +++ b/drivers/net/virtio/virtio_net.h
> @@ -5,6 +5,8 @@
>
>  #include <linux/ethtool.h>
>  #include <linux/average.h>
> +#include <linux/virtio_net.h>
> +#include <net/xdp_sock_drv.h>
>
>  #define VIRTIO_XDP_FLAG        BIT(0)
>  #define VIRTIO_XMIT_DATA_MASK (VIRTIO_XDP_FLAG)
> @@ -94,6 +96,11 @@ struct virtnet_sq {
>         bool do_dma;
>
>         struct virtnet_sq_dma_head dmainfo;
> +       struct {
> +               struct xsk_buff_pool __rcu *pool;
> +
> +               dma_addr_t hdr_dma_address;
> +       } xsk;
>  };
>
>  /* Internal representation of a receive virtqueue */
> @@ -134,6 +141,13 @@ struct virtnet_rq {
>
>         /* Do dma by self */
>         bool do_dma;
> +
> +       struct {
> +               struct xsk_buff_pool __rcu *pool;
> +
> +               /* xdp rxq used by xsk */
> +               struct xdp_rxq_info xdp_rxq;
> +       } xsk;
>  };
>
>  struct virtnet_info {
> @@ -218,6 +232,8 @@ struct virtnet_info {
>         struct failover *failover;
>  };
>
> +#include "xsk.h"
> +

Any reason we don't do it with other headers?

>  static inline bool virtnet_is_xdp_frame(void *ptr)
>  {
>         return (unsigned long)ptr & VIRTIO_XDP_FLAG;
> @@ -308,4 +324,6 @@ void virtnet_rx_pause(struct virtnet_info *vi, struct virtnet_rq *rq);
>  void virtnet_rx_resume(struct virtnet_info *vi, struct virtnet_rq *rq);
>  void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);
>  void virtnet_tx_resume(struct virtnet_info *vi, struct virtnet_sq *sq);
> +void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> +void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
>  #endif
> diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
> new file mode 100644
> index 000000000000..dddd01962a3f
> --- /dev/null
> +++ b/drivers/net/virtio/xsk.c
> @@ -0,0 +1,186 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +/*
> + * virtio-net xsk
> + */
> +
> +#include "virtio_net.h"
> +
> +static struct virtio_net_hdr_mrg_rxbuf xsk_hdr;
> +
> +static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct virtnet_rq *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);
> +       } else {
> +               xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
> +       }
> +
> +       virtnet_rx_pause(vi, rq);
> +
> +       err = virtqueue_reset(rq->vq, virtnet_rq_free_unused_buf);
> +       if (err)
> +               netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
> +
> +       if (pool && err)
> +               xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
> +       else
> +               rcu_assign_pointer(rq->xsk.pool, pool);
> +
> +       virtnet_rx_resume(vi, rq);
> +
> +       return err;
> +}
> +
> +static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
> +                                   struct virtnet_sq *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);
> +
> +       if (pool) {
> +               if (!err)
> +                       rcu_assign_pointer(sq->xsk.pool, pool);
> +       } else {
> +               rcu_assign_pointer(sq->xsk.pool, NULL);
> +       }
> +
> +       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 virtnet_rq *rq;
> +       struct virtnet_sq *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.
> +        */
> +       if (vi->big_packets && !vi->mergeable_rx_bufs)
> +               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;
> +
> +       if (!rq->do_dma || !sq->do_dma)
> +               return -EPERM;
> +
> +       if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq))
> +               return -EPERM;

Any reason we need this check? Is there any code that has this
assumption? E.g dma sync in XDP_TX?

> +
> +       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;
> +
> +       sq->xsk.hdr_dma_address = hdr_dma;

I think we probably need some comments to explain why a single hdr can
work. Like it means we use the same hdr for all XSK packets?

> +
> +       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 virtnet_rq *rq;
> +       struct virtnet_sq *sq;
> +       int err1, err2;
> +
> +       if (qid >= vi->curr_queue_pairs)
> +               return -EINVAL;
> +
> +       sq = &vi->sq[qid];
> +       rq = &vi->rq[qid];
> +
> +       dma_dev = virtqueue_dma_dev(rq->vq);
> +
> +       /* Sync with the XSK wakeup and NAPI. */
> +       synchronize_net();

Any reason we couldn't do bind_xsk_pool(NULL) here? It seems easier.

Thanks


> +
> +       dma_unmap_single(dma_dev, sq->xsk.hdr_dma_address, vi->hdr_len, DMA_TO_DEVICE);
> +
> +       rcu_read_lock();
> +       pool = rcu_dereference(sq->xsk.pool);
> +       xsk_pool_dma_unmap(pool, 0);
> +       rcu_read_unlock();
> +
> +       err1 = virtnet_sq_bind_xsk_pool(vi, sq, NULL);
> +       err2 = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
> +
> +       return err1 | err2;
> +}
> +
> +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);
> +}
> diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
> new file mode 100644
> index 000000000000..1918285c310c
> --- /dev/null
> +++ b/drivers/net/virtio/xsk.h
> @@ -0,0 +1,7 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +
> +#ifndef __XSK_H__
> +#define __XSK_H__
> +
> +int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp);
> +#endif
> --
> 2.32.0.3.g01195cf9f
>
Xuan Zhuo Oct. 20, 2023, 7:28 a.m. UTC | #2 
On Fri, 20 Oct 2023 14:51:15 +0800, Jason Wang <jasowang@redhat.com> wrote:
> On Mon, Oct 16, 2023 at 8:01 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
> >
> > This patch implement the logic of bind/unbind xsk pool to sq and rq.
> >
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > ---
> >  drivers/net/virtio/Makefile     |   2 +-
> >  drivers/net/virtio/main.c       |  10 +-
> >  drivers/net/virtio/virtio_net.h |  18 ++++
> >  drivers/net/virtio/xsk.c        | 186 ++++++++++++++++++++++++++++++++
> >  drivers/net/virtio/xsk.h        |   7 ++
> >  5 files changed, 216 insertions(+), 7 deletions(-)
> >  create mode 100644 drivers/net/virtio/xsk.c
> >  create mode 100644 drivers/net/virtio/xsk.h
> >
> > diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
> > index 15ed7c97fd4f..8c2a884d2dba 100644
> > --- a/drivers/net/virtio/Makefile
> > +++ b/drivers/net/virtio/Makefile
> > @@ -5,4 +5,4 @@
> >
> >  obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
> >
> > -virtio_net-y := main.o
> > +virtio_net-y := main.o xsk.o
> > diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
> > index 02d27101fef1..38733a782f12 100644
> > --- a/drivers/net/virtio/main.c
> > +++ b/drivers/net/virtio/main.c
> > @@ -8,7 +8,6 @@
> >  #include <linux/etherdevice.h>
> >  #include <linux/module.h>
> >  #include <linux/virtio.h>
> > -#include <linux/virtio_net.h>
> >  #include <linux/bpf.h>
> >  #include <linux/bpf_trace.h>
> >  #include <linux/scatterlist.h>
> > @@ -139,9 +138,6 @@ struct virtio_net_common_hdr {
> >         };
> >  };
> >
> > -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
> > -static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> > -
> >  static void *xdp_to_ptr(struct xdp_frame *ptr)
> >  {
> >         return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
> > @@ -3664,6 +3660,8 @@ 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;
> >         }
> > @@ -3849,7 +3847,7 @@ static void free_receive_page_frags(struct virtnet_info *vi)
> >                 }
> >  }
> >
> > -static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
> > +void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
> >  {
> >         if (!virtnet_is_xdp_frame(buf))
> >                 dev_kfree_skb(buf);
> > @@ -3857,7 +3855,7 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
> >                 xdp_return_frame(virtnet_ptr_to_xdp(buf));
> >  }
> >
> > -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
> > +void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
> >  {
> >         struct virtnet_info *vi = vq->vdev->priv;
> >         int i = vq2rxq(vq);
> > diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
> > index cc742756e19a..9e69b6c5921b 100644
> > --- a/drivers/net/virtio/virtio_net.h
> > +++ b/drivers/net/virtio/virtio_net.h
> > @@ -5,6 +5,8 @@
> >
> >  #include <linux/ethtool.h>
> >  #include <linux/average.h>
> > +#include <linux/virtio_net.h>
> > +#include <net/xdp_sock_drv.h>
> >
> >  #define VIRTIO_XDP_FLAG        BIT(0)
> >  #define VIRTIO_XMIT_DATA_MASK (VIRTIO_XDP_FLAG)
> > @@ -94,6 +96,11 @@ struct virtnet_sq {
> >         bool do_dma;
> >
> >         struct virtnet_sq_dma_head dmainfo;
> > +       struct {
> > +               struct xsk_buff_pool __rcu *pool;
> > +
> > +               dma_addr_t hdr_dma_address;
> > +       } xsk;
> >  };
> >
> >  /* Internal representation of a receive virtqueue */
> > @@ -134,6 +141,13 @@ struct virtnet_rq {
> >
> >         /* Do dma by self */
> >         bool do_dma;
> > +
> > +       struct {
> > +               struct xsk_buff_pool __rcu *pool;
> > +
> > +               /* xdp rxq used by xsk */
> > +               struct xdp_rxq_info xdp_rxq;
> > +       } xsk;
> >  };
> >
> >  struct virtnet_info {
> > @@ -218,6 +232,8 @@ struct virtnet_info {
> >         struct failover *failover;
> >  };
> >
> > +#include "xsk.h"
> > +
>
> Any reason we don't do it with other headers?

Because xsk.h will reference the struct virtnet_sq..., if we put xsk.h
at the start of virtio_net.h, the gcc will not happy.
But the virtio-net.h references the api(virtnet_ptr_to_xsk) of the xsk.h.


>
> >  static inline bool virtnet_is_xdp_frame(void *ptr)
> >  {
> >         return (unsigned long)ptr & VIRTIO_XDP_FLAG;
> > @@ -308,4 +324,6 @@ void virtnet_rx_pause(struct virtnet_info *vi, struct virtnet_rq *rq);
> >  void virtnet_rx_resume(struct virtnet_info *vi, struct virtnet_rq *rq);
> >  void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);
> >  void virtnet_tx_resume(struct virtnet_info *vi, struct virtnet_sq *sq);
> > +void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> > +void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
> >  #endif
> > diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
> > new file mode 100644
> > index 000000000000..dddd01962a3f
> > --- /dev/null
> > +++ b/drivers/net/virtio/xsk.c
> > @@ -0,0 +1,186 @@

[...]

> > +
> > +       if (!rq->do_dma || !sq->do_dma)
> > +               return -EPERM;
> > +
> > +       if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq))
> > +               return -EPERM;
>
> Any reason we need this check? Is there any code that has this
> assumption? E.g dma sync in XDP_TX?

For the xsk, the tx and rx should have the same dev.
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.

>
> > +
> > +       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;
> > +
> > +       sq->xsk.hdr_dma_address = hdr_dma;
>
> I think we probably need some comments to explain why a single hdr can
> work. Like it means we use the same hdr for all XSK packets?

Will fix.

>
> > +
> > +       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 virtnet_rq *rq;
> > +       struct virtnet_sq *sq;
> > +       int err1, err2;
> > +
> > +       if (qid >= vi->curr_queue_pairs)
> > +               return -EINVAL;
> > +
> > +       sq = &vi->sq[qid];
> > +       rq = &vi->rq[qid];
> > +
> > +       dma_dev = virtqueue_dma_dev(rq->vq);
> > +
> > +       /* Sync with the XSK wakeup and NAPI. */
> > +       synchronize_net();
>
> Any reason we couldn't do bind_xsk_pool(NULL) here? It seems easier.

Do you mean rcu_assign_pointer() is enough?

Let me check it.

Thanks


>
> Thanks
>
>
> > +
> > +       dma_unmap_single(dma_dev, sq->xsk.hdr_dma_address, vi->hdr_len, DMA_TO_DEVICE);
> > +
> > +       rcu_read_lock();
> > +       pool = rcu_dereference(sq->xsk.pool);
> > +       xsk_pool_dma_unmap(pool, 0);
> > +       rcu_read_unlock();
> > +
> > +       err1 = virtnet_sq_bind_xsk_pool(vi, sq, NULL);
> > +       err2 = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
> > +
> > +       return err1 | err2;
> > +}
> > +
> > +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);
> > +}
> > diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
> > new file mode 100644
> > index 000000000000..1918285c310c
> > --- /dev/null
> > +++ b/drivers/net/virtio/xsk.h
> > @@ -0,0 +1,7 @@
> > +/* SPDX-License-Identifier: GPL-2.0-or-later */
> > +
> > +#ifndef __XSK_H__
> > +#define __XSK_H__
> > +
> > +int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp);
> > +#endif
> > --
> > 2.32.0.3.g01195cf9f
> >
>
diff mbox series

Patch

diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
index 15ed7c97fd4f..8c2a884d2dba 100644
--- a/drivers/net/virtio/Makefile
+++ b/drivers/net/virtio/Makefile
@@ -5,4 +5,4 @@ 
 
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
 
-virtio_net-y := main.o
+virtio_net-y := main.o xsk.o
diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
index 02d27101fef1..38733a782f12 100644
--- a/drivers/net/virtio/main.c
+++ b/drivers/net/virtio/main.c
@@ -8,7 +8,6 @@ 
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/virtio.h>
-#include <linux/virtio_net.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/scatterlist.h>
@@ -139,9 +138,6 @@  struct virtio_net_common_hdr {
 	};
 };
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
-static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
-
 static void *xdp_to_ptr(struct xdp_frame *ptr)
 {
 	return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
@@ -3664,6 +3660,8 @@  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;
 	}
@@ -3849,7 +3847,7 @@  static void free_receive_page_frags(struct virtnet_info *vi)
 		}
 }
 
-static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
+void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 {
 	if (!virtnet_is_xdp_frame(buf))
 		dev_kfree_skb(buf);
@@ -3857,7 +3855,7 @@  static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 		xdp_return_frame(virtnet_ptr_to_xdp(buf));
 }
 
-static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
+void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
 {
 	struct virtnet_info *vi = vq->vdev->priv;
 	int i = vq2rxq(vq);
diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
index cc742756e19a..9e69b6c5921b 100644
--- a/drivers/net/virtio/virtio_net.h
+++ b/drivers/net/virtio/virtio_net.h
@@ -5,6 +5,8 @@ 
 
 #include <linux/ethtool.h>
 #include <linux/average.h>
+#include <linux/virtio_net.h>
+#include <net/xdp_sock_drv.h>
 
 #define VIRTIO_XDP_FLAG	BIT(0)
 #define VIRTIO_XMIT_DATA_MASK (VIRTIO_XDP_FLAG)
@@ -94,6 +96,11 @@  struct virtnet_sq {
 	bool do_dma;
 
 	struct virtnet_sq_dma_head dmainfo;
+	struct {
+		struct xsk_buff_pool __rcu *pool;
+
+		dma_addr_t hdr_dma_address;
+	} xsk;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -134,6 +141,13 @@  struct virtnet_rq {
 
 	/* Do dma by self */
 	bool do_dma;
+
+	struct {
+		struct xsk_buff_pool __rcu *pool;
+
+		/* xdp rxq used by xsk */
+		struct xdp_rxq_info xdp_rxq;
+	} xsk;
 };
 
 struct virtnet_info {
@@ -218,6 +232,8 @@  struct virtnet_info {
 	struct failover *failover;
 };
 
+#include "xsk.h"
+
 static inline bool virtnet_is_xdp_frame(void *ptr)
 {
 	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
@@ -308,4 +324,6 @@  void virtnet_rx_pause(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_rx_resume(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);
 void virtnet_tx_resume(struct virtnet_info *vi, struct virtnet_sq *sq);
+void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
+void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
 #endif
diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
new file mode 100644
index 000000000000..dddd01962a3f
--- /dev/null
+++ b/drivers/net/virtio/xsk.c
@@ -0,0 +1,186 @@ 
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * virtio-net xsk
+ */
+
+#include "virtio_net.h"
+
+static struct virtio_net_hdr_mrg_rxbuf xsk_hdr;
+
+static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct virtnet_rq *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);
+	} else {
+		xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
+	}
+
+	virtnet_rx_pause(vi, rq);
+
+	err = virtqueue_reset(rq->vq, virtnet_rq_free_unused_buf);
+	if (err)
+		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
+
+	if (pool && err)
+		xdp_rxq_info_unreg(&rq->xsk.xdp_rxq);
+	else
+		rcu_assign_pointer(rq->xsk.pool, pool);
+
+	virtnet_rx_resume(vi, rq);
+
+	return err;
+}
+
+static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
+				    struct virtnet_sq *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);
+
+	if (pool) {
+		if (!err)
+			rcu_assign_pointer(sq->xsk.pool, pool);
+	} else {
+		rcu_assign_pointer(sq->xsk.pool, NULL);
+	}
+
+	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 virtnet_rq *rq;
+	struct virtnet_sq *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.
+	 */
+	if (vi->big_packets && !vi->mergeable_rx_bufs)
+		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;
+
+	if (!rq->do_dma || !sq->do_dma)
+		return -EPERM;
+
+	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;
+
+	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 virtnet_rq *rq;
+	struct virtnet_sq *sq;
+	int err1, err2;
+
+	if (qid >= vi->curr_queue_pairs)
+		return -EINVAL;
+
+	sq = &vi->sq[qid];
+	rq = &vi->rq[qid];
+
+	dma_dev = virtqueue_dma_dev(rq->vq);
+
+	/* Sync with the XSK wakeup and NAPI. */
+	synchronize_net();
+
+	dma_unmap_single(dma_dev, sq->xsk.hdr_dma_address, vi->hdr_len, DMA_TO_DEVICE);
+
+	rcu_read_lock();
+	pool = rcu_dereference(sq->xsk.pool);
+	xsk_pool_dma_unmap(pool, 0);
+	rcu_read_unlock();
+
+	err1 = virtnet_sq_bind_xsk_pool(vi, sq, NULL);
+	err2 = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
+
+	return err1 | err2;
+}
+
+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);
+}
diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
new file mode 100644
index 000000000000..1918285c310c
--- /dev/null
+++ b/drivers/net/virtio/xsk.h
@@ -0,0 +1,7 @@ 
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __XSK_H__
+#define __XSK_H__
+
+int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp);
+#endif