| Message ID | 20250225020455.212895-4-jdamato@fastly.com (mailing list archive) |
|---|---|
| State | New |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | virtio-net: Link queues to NAPIs | expand |
On Tue, Feb 25, 2025 at 10:05 AM Joe Damato <jdamato@fastly.com> wrote: > > Use netif_queue_set_napi to map NAPIs to queue IDs so that the mapping > can be accessed by user apps, taking care to hold RTNL as needed. I may miss something but I wonder whether letting the caller hold the lock is better. More below. > > $ ethtool -i ens4 | grep driver > driver: virtio_net > > $ sudo ethtool -L ens4 combined 4 > > $ ./tools/net/ynl/pyynl/cli.py \ > --spec Documentation/netlink/specs/netdev.yaml \ > --dump queue-get --json='{"ifindex": 2}' > [{'id': 0, 'ifindex': 2, 'napi-id': 8289, 'type': 'rx'}, > {'id': 1, 'ifindex': 2, 'napi-id': 8290, 'type': 'rx'}, > {'id': 2, 'ifindex': 2, 'napi-id': 8291, 'type': 'rx'}, > {'id': 3, 'ifindex': 2, 'napi-id': 8292, 'type': 'rx'}, > {'id': 0, 'ifindex': 2, 'type': 'tx'}, > {'id': 1, 'ifindex': 2, 'type': 'tx'}, > {'id': 2, 'ifindex': 2, 'type': 'tx'}, > {'id': 3, 'ifindex': 2, 'type': 'tx'}] > > Note that virtio_net has TX-only NAPIs which do not have NAPI IDs, so > the lack of 'napi-id' in the above output is expected. > > Signed-off-by: Joe Damato <jdamato@fastly.com> > --- > drivers/net/virtio_net.c | 73 ++++++++++++++++++++++++++++------------ > 1 file changed, 52 insertions(+), 21 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index e578885c1093..13bb4a563073 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -2807,6 +2807,20 @@ static void skb_recv_done(struct virtqueue *rvq) > virtqueue_napi_schedule(&rq->napi, rvq); > } > > +static void virtnet_queue_set_napi(struct net_device *dev, > + struct napi_struct *napi, > + enum netdev_queue_type q_type, int qidx, > + bool need_rtnl) > +{ > + if (need_rtnl) > + rtnl_lock(); > + > + netif_queue_set_napi(dev, qidx, q_type, napi); > + > + if (need_rtnl) > + rtnl_unlock(); > +} > + > static void virtnet_napi_do_enable(struct virtqueue *vq, > struct napi_struct *napi) > { > @@ -2821,15 +2835,21 @@ static void virtnet_napi_do_enable(struct virtqueue *vq, > local_bh_enable(); > } > > -static void virtnet_napi_enable(struct receive_queue *rq) > +static void virtnet_napi_enable(struct receive_queue *rq, bool need_rtnl) > { > + struct virtnet_info *vi = rq->vq->vdev->priv; > + int qidx = vq2rxq(rq->vq); > + > virtnet_napi_do_enable(rq->vq, &rq->napi); > + virtnet_queue_set_napi(vi->dev, &rq->napi, > + NETDEV_QUEUE_TYPE_RX, qidx, need_rtnl); > } > > -static void virtnet_napi_tx_enable(struct send_queue *sq) > +static void virtnet_napi_tx_enable(struct send_queue *sq, bool need_rtnl) > { > struct virtnet_info *vi = sq->vq->vdev->priv; > struct napi_struct *napi = &sq->napi; > + int qidx = vq2txq(sq->vq); > > if (!napi->weight) > return; > @@ -2843,20 +2863,31 @@ static void virtnet_napi_tx_enable(struct send_queue *sq) > } > > virtnet_napi_do_enable(sq->vq, napi); > + virtnet_queue_set_napi(vi->dev, napi, NETDEV_QUEUE_TYPE_TX, qidx, > + need_rtnl); > } > > -static void virtnet_napi_tx_disable(struct send_queue *sq) > +static void virtnet_napi_tx_disable(struct send_queue *sq, bool need_rtnl) > { > + struct virtnet_info *vi = sq->vq->vdev->priv; > struct napi_struct *napi = &sq->napi; > + int qidx = vq2txq(sq->vq); > > - if (napi->weight) > + if (napi->weight) { > + virtnet_queue_set_napi(vi->dev, NULL, NETDEV_QUEUE_TYPE_TX, > + qidx, need_rtnl); > napi_disable(napi); > + } > } > > -static void virtnet_napi_disable(struct receive_queue *rq) > +static void virtnet_napi_disable(struct receive_queue *rq, bool need_rtnl) > { > + struct virtnet_info *vi = rq->vq->vdev->priv; > struct napi_struct *napi = &rq->napi; > + int qidx = vq2rxq(rq->vq); > > + virtnet_queue_set_napi(vi->dev, NULL, NETDEV_QUEUE_TYPE_TX, qidx, > + need_rtnl); > napi_disable(napi); > } > > @@ -2870,9 +2901,9 @@ static void refill_work(struct work_struct *work) > for (i = 0; i < vi->curr_queue_pairs; i++) { > struct receive_queue *rq = &vi->rq[i]; > > - virtnet_napi_disable(rq); > + virtnet_napi_disable(rq, true); > still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); > - virtnet_napi_enable(rq); > + virtnet_napi_enable(rq, true); > > /* In theory, this can happen: if we don't get any buffers in > * we will *never* try to fill again. > @@ -3069,8 +3100,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget) > > static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) > { > - virtnet_napi_tx_disable(&vi->sq[qp_index]); > - virtnet_napi_disable(&vi->rq[qp_index]); > + virtnet_napi_tx_disable(&vi->sq[qp_index], false); > + virtnet_napi_disable(&vi->rq[qp_index], false); > xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); > } > > @@ -3089,8 +3120,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) > if (err < 0) > goto err_xdp_reg_mem_model; > > - virtnet_napi_enable(&vi->rq[qp_index]); > - virtnet_napi_tx_enable(&vi->sq[qp_index]); > + virtnet_napi_enable(&vi->rq[qp_index], false); > + virtnet_napi_tx_enable(&vi->sq[qp_index], false); > > return 0; > > @@ -3342,7 +3373,7 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) > bool running = netif_running(vi->dev); > > if (running) { > - virtnet_napi_disable(rq); > + virtnet_napi_disable(rq, true); During the resize, the rtnl lock has been held on the ethtool path rtnl_lock(); rc = __dev_ethtool(net, ifr, useraddr, ethcmd, state); rtnl_unlock(); virtnet_rx_resize() virtnet_rx_pause() and in the case of XSK binding, I see ASSERT_RTNL in xp_assign_dev() at least. Thanks
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index e578885c1093..13bb4a563073 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2807,6 +2807,20 @@ static void skb_recv_done(struct virtqueue *rvq) virtqueue_napi_schedule(&rq->napi, rvq); } +static void virtnet_queue_set_napi(struct net_device *dev, + struct napi_struct *napi, + enum netdev_queue_type q_type, int qidx, + bool need_rtnl) +{ + if (need_rtnl) + rtnl_lock(); + + netif_queue_set_napi(dev, qidx, q_type, napi); + + if (need_rtnl) + rtnl_unlock(); +} + static void virtnet_napi_do_enable(struct virtqueue *vq, struct napi_struct *napi) { @@ -2821,15 +2835,21 @@ static void virtnet_napi_do_enable(struct virtqueue *vq, local_bh_enable(); } -static void virtnet_napi_enable(struct receive_queue *rq) +static void virtnet_napi_enable(struct receive_queue *rq, bool need_rtnl) { + struct virtnet_info *vi = rq->vq->vdev->priv; + int qidx = vq2rxq(rq->vq); + virtnet_napi_do_enable(rq->vq, &rq->napi); + virtnet_queue_set_napi(vi->dev, &rq->napi, + NETDEV_QUEUE_TYPE_RX, qidx, need_rtnl); } -static void virtnet_napi_tx_enable(struct send_queue *sq) +static void virtnet_napi_tx_enable(struct send_queue *sq, bool need_rtnl) { struct virtnet_info *vi = sq->vq->vdev->priv; struct napi_struct *napi = &sq->napi; + int qidx = vq2txq(sq->vq); if (!napi->weight) return; @@ -2843,20 +2863,31 @@ static void virtnet_napi_tx_enable(struct send_queue *sq) } virtnet_napi_do_enable(sq->vq, napi); + virtnet_queue_set_napi(vi->dev, napi, NETDEV_QUEUE_TYPE_TX, qidx, + need_rtnl); } -static void virtnet_napi_tx_disable(struct send_queue *sq) +static void virtnet_napi_tx_disable(struct send_queue *sq, bool need_rtnl) { + struct virtnet_info *vi = sq->vq->vdev->priv; struct napi_struct *napi = &sq->napi; + int qidx = vq2txq(sq->vq); - if (napi->weight) + if (napi->weight) { + virtnet_queue_set_napi(vi->dev, NULL, NETDEV_QUEUE_TYPE_TX, + qidx, need_rtnl); napi_disable(napi); + } } -static void virtnet_napi_disable(struct receive_queue *rq) +static void virtnet_napi_disable(struct receive_queue *rq, bool need_rtnl) { + struct virtnet_info *vi = rq->vq->vdev->priv; struct napi_struct *napi = &rq->napi; + int qidx = vq2rxq(rq->vq); + virtnet_queue_set_napi(vi->dev, NULL, NETDEV_QUEUE_TYPE_TX, qidx, + need_rtnl); napi_disable(napi); } @@ -2870,9 +2901,9 @@ static void refill_work(struct work_struct *work) for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; - virtnet_napi_disable(rq); + virtnet_napi_disable(rq, true); still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); - virtnet_napi_enable(rq); + virtnet_napi_enable(rq, true); /* In theory, this can happen: if we don't get any buffers in * we will *never* try to fill again. @@ -3069,8 +3100,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget) static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) { - virtnet_napi_tx_disable(&vi->sq[qp_index]); - virtnet_napi_disable(&vi->rq[qp_index]); + virtnet_napi_tx_disable(&vi->sq[qp_index], false); + virtnet_napi_disable(&vi->rq[qp_index], false); xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); } @@ -3089,8 +3120,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - virtnet_napi_enable(&vi->rq[qp_index]); - virtnet_napi_tx_enable(&vi->sq[qp_index]); + virtnet_napi_enable(&vi->rq[qp_index], false); + virtnet_napi_tx_enable(&vi->sq[qp_index], false); return 0; @@ -3342,7 +3373,7 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) bool running = netif_running(vi->dev); if (running) { - virtnet_napi_disable(rq); + virtnet_napi_disable(rq, true); virtnet_cancel_dim(vi, &rq->dim); } } @@ -3355,7 +3386,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) schedule_delayed_work(&vi->refill, 0); if (running) - virtnet_napi_enable(rq); + virtnet_napi_enable(rq, true); } static int virtnet_rx_resize(struct virtnet_info *vi, @@ -3384,7 +3415,7 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq) qindex = sq - vi->sq; if (running) - virtnet_napi_tx_disable(sq); + virtnet_napi_tx_disable(sq, true); txq = netdev_get_tx_queue(vi->dev, qindex); @@ -3418,7 +3449,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq) __netif_tx_unlock_bh(txq); if (running) - virtnet_napi_tx_enable(sq); + virtnet_napi_tx_enable(sq, true); } static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, @@ -5961,8 +5992,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_disable(&vi->rq[i]); - virtnet_napi_tx_disable(&vi->sq[i]); + virtnet_napi_disable(&vi->rq[i], false); + virtnet_napi_tx_disable(&vi->sq[i], false); } } @@ -5999,8 +6030,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (old_prog) bpf_prog_put(old_prog); if (netif_running(dev)) { - virtnet_napi_enable(&vi->rq[i]); - virtnet_napi_tx_enable(&vi->sq[i]); + virtnet_napi_enable(&vi->rq[i], false); + virtnet_napi_tx_enable(&vi->sq[i], false); } } @@ -6015,8 +6046,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_enable(&vi->rq[i]); - virtnet_napi_tx_enable(&vi->sq[i]); + virtnet_napi_enable(&vi->rq[i], false); + virtnet_napi_tx_enable(&vi->sq[i], false); } } if (prog)
Use netif_queue_set_napi to map NAPIs to queue IDs so that the mapping can be accessed by user apps, taking care to hold RTNL as needed. $ ethtool -i ens4 | grep driver driver: virtio_net $ sudo ethtool -L ens4 combined 4 $ ./tools/net/ynl/pyynl/cli.py \ --spec Documentation/netlink/specs/netdev.yaml \ --dump queue-get --json='{"ifindex": 2}' [{'id': 0, 'ifindex': 2, 'napi-id': 8289, 'type': 'rx'}, {'id': 1, 'ifindex': 2, 'napi-id': 8290, 'type': 'rx'}, {'id': 2, 'ifindex': 2, 'napi-id': 8291, 'type': 'rx'}, {'id': 3, 'ifindex': 2, 'napi-id': 8292, 'type': 'rx'}, {'id': 0, 'ifindex': 2, 'type': 'tx'}, {'id': 1, 'ifindex': 2, 'type': 'tx'}, {'id': 2, 'ifindex': 2, 'type': 'tx'}, {'id': 3, 'ifindex': 2, 'type': 'tx'}] Note that virtio_net has TX-only NAPIs which do not have NAPI IDs, so the lack of 'napi-id' in the above output is expected. Signed-off-by: Joe Damato <jdamato@fastly.com> --- drivers/net/virtio_net.c | 73 ++++++++++++++++++++++++++++------------ 1 file changed, 52 insertions(+), 21 deletions(-)