net: Add lease info to queue-get response

Populate nested lease info to the queue-get response that returns the
ifindex, queue id with type and optionally netns id if the device
resides in a different netns.

Example with ynl client:

  # ip a
  [...]
  4: enp10s0f0np0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 xdp/id:24 qdisc mq state UP group default qlen 1000
    link/ether e8:eb:d3:a3:43:f6 brd ff:ff:ff:ff:ff:ff
    inet 10.0.0.2/24 scope global enp10s0f0np0
       valid_lft forever preferred_lft forever
    inet6 fe80::eaeb:d3ff:fea3:43f6/64 scope link proto kernel_ll
       valid_lft forever preferred_lft forever
  [...]

  # ethtool -i enp10s0f0np0
  driver: mlx5_core
  [...]

  # ./pyynl/cli.py \
      --spec ~/netlink/specs/netdev.yaml \
      --do queue-get \
      --json '{"ifindex": 4, "id": 15, "type": "rx"}'
  {'id': 15,
   'ifindex': 4,
   'lease': {'ifindex': 8, 'netns-id': 0, 'queue': {'id': 1, 'type': 'rx'}},
   'napi-id': 8227,
   'type': 'rx',
   'xsk': {}}

  # ip netns list
  foo (id: 0)

  # ip netns exec foo ip a
  [...]
  8: nk@NONE: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
      link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
      inet6 fe80::200:ff:fe00:0/64 scope link proto kernel_ll
         valid_lft forever preferred_lft forever
  [...]

  # ip netns exec foo ethtool -i nk
  driver: netkit
  [...]

  # ip netns exec foo ls /sys/class/net/nk/queues/
  rx-0  rx-1  tx-0

  # ip netns exec foo ./pyynl/cli.py \
      --spec ~/netlink/specs/netdev.yaml \
      --do queue-get \
      --json '{"ifindex": 8, "id": 1, "type": "rx"}'
  {'id': 1, 'ifindex': 8, 'type': 'rx'}

Note that the caller of netdev_nl_queue_fill_one() holds the netdevice
lock. For the queue-get we do not lock both devices. When queues get
{un,}leased, both devices are locked, thus if __netif_get_rx_queue_peer()
returns true, the peer pointer points to a valid device. The netns-id
is fetched via peernet2id_alloc() similarly as done in OVS.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260115082603.219152-4-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 1cacc2451516ae92dbefda1f68f680acaff7ed94..de04fdfdad72be36f029743da1d36ee5226adc53 100644 (file)
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -63,4 +63,14 @@ void netdev_rx_queue_lease(struct netdev_rx_queue *rxq_dst,
                           struct netdev_rx_queue *rxq_src);
 void netdev_rx_queue_unlease(struct netdev_rx_queue *rxq_dst,
                             struct netdev_rx_queue *rxq_src);
+bool netif_rx_queue_lease_get_owner(struct net_device **dev, unsigned int *rxq);
+
+enum netif_lease_dir {
+       NETIF_VIRT_TO_PHYS,
+       NETIF_PHYS_TO_VIRT,
+};
+
+struct netdev_rx_queue *
+__netif_get_rx_queue_lease(struct net_device **dev, unsigned int *rxq,
+                          enum netif_lease_dir dir);
 #endif /* _LINUX_NETDEV_RX_QUEUE_H */

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index cd4dc4eef029c877fb5aec59b2666705ad278914..51c830f88f103f0c9d8172b8734d812174f7abe7 100644 (file)
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -391,8 +391,11 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
                         u32 q_idx, u32 q_type, const struct genl_info *info)
 {
        struct pp_memory_provider_params *params;
+       struct net_device *orig_netdev = netdev;
+       struct nlattr *nest_lease, *nest_queue;
        struct netdev_rx_queue *rxq;
        struct netdev_queue *txq;
+       u32 lease_q_idx = q_idx;
        void *hdr;
 
        hdr = genlmsg_iput(rsp, info);
@@ -410,6 +413,37 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
                if (nla_put_napi_id(rsp, rxq->napi))
                        goto nla_put_failure;
 
+               if (netif_rx_queue_lease_get_owner(&netdev, &lease_q_idx)) {
+                       struct net *net, *peer_net;
+
+                       nest_lease = nla_nest_start(rsp, NETDEV_A_QUEUE_LEASE);
+                       if (!nest_lease)
+                               goto nla_put_failure;
+                       nest_queue = nla_nest_start(rsp, NETDEV_A_LEASE_QUEUE);
+                       if (!nest_queue)
+                               goto nla_put_failure;
+                       if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, lease_q_idx))
+                               goto nla_put_failure;
+                       if (nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type))
+                               goto nla_put_failure;
+                       nla_nest_end(rsp, nest_queue);
+                       if (nla_put_u32(rsp, NETDEV_A_LEASE_IFINDEX,
+                                       READ_ONCE(netdev->ifindex)))
+                               goto nla_put_failure;
+                       rcu_read_lock();
+                       peer_net = dev_net_rcu(netdev);
+                       net = dev_net_rcu(orig_netdev);
+                       if (!net_eq(net, peer_net)) {
+                               s32 id = peernet2id_alloc(net, peer_net, GFP_ATOMIC);
+
+                               if (nla_put_s32(rsp, NETDEV_A_LEASE_NETNS_ID, id))
+                                       goto nla_put_failure_unlock;
+                       }
+                       rcu_read_unlock();
+                       nla_nest_end(rsp, nest_lease);
+                       netdev = orig_netdev;
+               }
+
                params = &rxq->mp_params;
                if (params->mp_ops &&
                    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
@@ -437,6 +471,8 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 
        return 0;
 
+nla_put_failure_unlock:
+       rcu_read_unlock();
 nla_put_failure:
        genlmsg_cancel(rsp, hdr);
        return -EMSGSIZE;

diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 830c1a964c36deab4598b7c85411ce8877bd33d9..61fe25817e98d3e2be28b4ecb78955d4f89df9c8 100644 (file)
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -40,6 +40,51 @@ bool netif_rxq_is_leased(struct net_device *dev, unsigned int rxq_idx)
        return false;
 }
 
+static bool netif_lease_dir_ok(const struct net_device *dev,
+                              enum netif_lease_dir dir)
+{
+       if (dir == NETIF_VIRT_TO_PHYS && !dev->dev.parent)
+               return true;
+       if (dir == NETIF_PHYS_TO_VIRT && dev->dev.parent)
+               return true;
+       return false;
+}
+
+struct netdev_rx_queue *
+__netif_get_rx_queue_lease(struct net_device **dev, unsigned int *rxq_idx,
+                          enum netif_lease_dir dir)
+{
+       struct net_device *orig_dev = *dev;
+       struct netdev_rx_queue *rxq = __netif_get_rx_queue(orig_dev, *rxq_idx);
+
+       if (rxq->lease) {
+               if (!netif_lease_dir_ok(orig_dev, dir))
+                       return NULL;
+               rxq = rxq->lease;
+               *rxq_idx = get_netdev_rx_queue_index(rxq);
+               *dev = rxq->dev;
+       }
+       return rxq;
+}
+
+bool netif_rx_queue_lease_get_owner(struct net_device **dev,
+                                   unsigned int *rxq_idx)
+{
+       struct net_device *orig_dev = *dev;
+       struct netdev_rx_queue *rxq;
+
+       /* The physical device needs to be locked. If there is indeed a lease,
+        * then the virtual device holds a reference on the physical device
+        * and the lease stays active until the virtual device is torn down.
+        * When queues get {un,}leased both devices are always locked.
+        */
+       netdev_ops_assert_locked(orig_dev);
+       rxq = __netif_get_rx_queue_lease(dev, rxq_idx, NETIF_PHYS_TO_VIRT);
+       if (rxq && orig_dev != *dev)
+               return true;
+       return false;
+}
+
 /* See also page_pool_is_unreadable() */
 bool netif_rxq_has_unreadable_mp(struct net_device *dev, unsigned int rxq_idx)
 {