[PATCH net-next v9 03/14] net: Add lease info to queue-get response

[Daniel Borkmann <daniel@iogearbox.net>]

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 when using AF_XDP via queue leasing:

  # 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
  [...]

  # ynl --family netdev --output-json --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 ynl --family netdev --output-json --do queue-get \
        --json '{"ifindex": 8, "id": 1, "type": "rx"}'
  {"id": 1, "type": "rx", "ifindex": 8, "xsk": {}}

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_lease()
returns a lease pointer, it 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>
---
 include/net/netdev_rx_queue.h | 14 ++++++++
 net/core/netdev-genl.c        | 66 ++++++++++++++++++++++++++++++++---
 net/core/netdev_rx_queue.c    | 54 ++++++++++++++++++++++++++++
 3 files changed, 130 insertions(+), 4 deletions(-)

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 1d41c253f0a3..7e98c679ea84 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -67,6 +67,20 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 	return index;
 }
 
+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);
+
+struct netdev_rx_queue *
+netif_get_rx_queue_lease_locked(struct net_device **dev, unsigned int *rxq);
+void netif_put_rx_queue_lease_locked(struct net_device *orig_dev,
+				     struct net_device *dev);
+
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);
 void netdev_rx_queue_lease(struct netdev_rx_queue *rxq_dst,
 			   struct netdev_rx_queue *rxq_src);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 7cfa479689f1..6ec48e212a24 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -386,12 +386,63 @@ static int nla_put_napi_id(struct sk_buff *skb, const struct napi_struct *napi)
 	return 0;
 }
 
+static int
+netdev_nl_queue_fill_lease(struct sk_buff *rsp, struct net_device *netdev,
+			   u32 q_idx, u32 q_type)
+{
+	struct net_device *orig_netdev = netdev;
+	struct nlattr *nest_lease, *nest_queue;
+	struct netdev_rx_queue *rxq;
+	struct net *net, *peer_net;
+
+	rxq = __netif_get_rx_queue_lease(&netdev, &q_idx,
+					 NETIF_PHYS_TO_VIRT);
+	if (!rxq || orig_netdev == netdev)
+		return 0;
+
+	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, 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);
+	return 0;
+
+nla_put_failure_unlock:
+	rcu_read_unlock();
+nla_put_failure:
+	return -ENOMEM;
+}
+
 static int
 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 netdev_rx_queue *rxq;
+	struct net_device *orig_netdev = netdev;
+	struct netdev_rx_queue *rxq, *rxq_lease;
 	struct netdev_queue *txq;
 	void *hdr;
 
@@ -409,17 +460,22 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		rxq = __netif_get_rx_queue(netdev, q_idx);
 		if (nla_put_napi_id(rsp, rxq->napi))
 			goto nla_put_failure;
+		if (netdev_nl_queue_fill_lease(rsp, netdev, q_idx, q_type))
+			goto nla_put_failure;
 
+		rxq_lease = netif_get_rx_queue_lease_locked(&netdev, &q_idx);
+		if (rxq_lease)
+			rxq = rxq_lease;
 		params = &rxq->mp_params;
 		if (params->mp_ops &&
 		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
-			goto nla_put_failure;
+			goto nla_put_failure_lease;
 #ifdef CONFIG_XDP_SOCKETS
 		if (rxq->pool)
 			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
-				goto nla_put_failure;
+				goto nla_put_failure_lease;
 #endif
-
+		netif_put_rx_queue_lease_locked(orig_netdev, netdev);
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
@@ -437,6 +493,8 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 
 	return 0;
 
+nla_put_failure_lease:
+	netif_put_rx_queue_lease_locked(orig_netdev, netdev);
 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 a1f23c2c96d4..a4d8cad6db74 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -41,6 +41,60 @@ bool netif_rxq_is_leased(struct net_device *dev, unsigned int rxq_idx)
 	return false;
 }
 
+/* Virtual devices eligible for leasing have no dev->dev.parent, while
+ * physical devices always have one. Use this to enforce the correct
+ * lease traversal direction.
+ */
+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;
+}
+
+struct netdev_rx_queue *
+netif_get_rx_queue_lease_locked(struct net_device **dev, unsigned int *rxq_idx)
+{
+	struct net_device *orig_dev = *dev;
+	struct netdev_rx_queue *rxq;
+
+	/* Locking order is always from the virtual to the physical device
+	 * see netdev_nl_queue_create_doit().
+	 */
+	netdev_ops_assert_locked(orig_dev);
+	rxq = __netif_get_rx_queue_lease(dev, rxq_idx, NETIF_VIRT_TO_PHYS);
+	if (rxq && orig_dev != *dev)
+		netdev_lock(*dev);
+	return rxq;
+}
+
+void netif_put_rx_queue_lease_locked(struct net_device *orig_dev,
+				     struct net_device *dev)
+{
+	if (orig_dev != dev)
+		netdev_unlock(dev);
+}
+
 /* See also page_pool_is_unreadable() */
 bool netif_rxq_has_unreadable_mp(struct net_device *dev, unsigned int rxq_idx)
 {
-- 
2.43.0