diff mbox series

[net-next,v3,3/8] virtio-net: xsk zero copy xmit setup

Message ID 20210331071139.15473-4-xuanzhuo@linux.alibaba.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series virtio-net support xdp socket zero copy xmit | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers success CCed 16 of 16 maintainers
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 89 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link

Commit Message

Xuan Zhuo March 31, 2021, 7:11 a.m. UTC 
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@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
---
 drivers/net/virtio_net.c | 66 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

Comments

Jason Wang April 6, 2021, 4:27 a.m. UTC | #1 
在 2021/3/31 下午3:11, Xuan Zhuo 写道:
> 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@linux.alibaba.com>
> Reviewed-by: Dust Li <dust.li@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
Magnus Karlsson April 7, 2021, 10:02 a.m. UTC | #2 
On Tue, Apr 6, 2021 at 3:13 PM Jason Wang <jasowang@redhat.com> wrote:
>
>
> 在 2021/3/31 下午3:11, Xuan Zhuo 写道:
> > 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@linux.alibaba.com>
> > Reviewed-by: Dust Li <dust.li@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?

There is already code in the common xsk part that tests for binding
multiple sockets to the same netdev and queue id (in an illegal way
that is). Does this code not work for you? If so, we should fix that
and not introduce a separate check down in the driver. Or maybe I
misunderstand your problem.

The code is here:

struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
                                            u16 queue_id)
{
        if (queue_id < dev->real_num_rx_queues)
                return dev->_rx[queue_id].pool;
        if (queue_id < dev->real_num_tx_queues)
                return dev->_tx[queue_id].pool;

        return NULL;
}

int xp_assign_dev(struct xsk_buff_pool *pool,
                  struct net_device *netdev, u16 queue_id, u16 flags)
{
        :
        :
        if (xsk_get_pool_from_qid(netdev, queue_id))
                return -EBUSY;


>
> > +
> > +     /* 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
>
diff mbox series

Patch

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;
+
+	if (qid >= vi->curr_queue_pairs)
+		return -EINVAL;
+
+	sq = &vi->sq[qid];
+
+	/* xsk zerocopy depend on the tx napi */
+	if (!sq->napi.weight)
+		return -EPERM;
+
+	rcu_read_lock();
+	if (rcu_dereference(sq->xsk.pool))
+		goto end;
+
+	/* 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. */
+
+	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;
+		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;
 	}