udp_tunnel: remove rtnl_lock dependency

Stanislav Fomichev · kuba-moo · commit 1ead7501094c · 2025-06-18T18:53:51.000-07:00
Drivers that are using ops lock and don't depend on RTNL lock still need to manage it because udp_tunnel's RTNL dependency. Introduce new udp_tunnel_nic_lock and use it instead of rtnl_lock. Drop non-UDP_TUNNEL_NIC_INFO_MAY_SLEEP mode from udp_tunnel infra (udp_tunnel_nic_device_sync_work needs to grab udp_tunnel_nic_lock mutex and might sleep). Cover more places in v4: - netlink - udp_tunnel_notify_add_rx_port (ndo_open) - triggers udp_tunnel_nic_device_sync_work - udp_tunnel_notify_del_rx_port (ndo_stop) - triggers udp_tunnel_nic_device_sync_work - udp_tunnel_get_rx_info (__netdev_update_features) - triggers NETDEV_UDP_TUNNEL_PUSH_INFO - udp_tunnel_drop_rx_info (__netdev_update_features) - triggers NETDEV_UDP_TUNNEL_DROP_INFO - udp_tunnel_nic_reset_ntf (ndo_open) - notifiers - udp_tunnel_nic_netdevice_event, depending on the event: - triggers NETDEV_UDP_TUNNEL_PUSH_INFO - triggers NETDEV_UDP_TUNNEL_DROP_INFO - ethnl_tunnel_info_reply_size - udp_tunnel_nic_set_port_priv (two intel drivers) Cc: Michael Chan <michael.chan@broadcom.com> Suggested-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Stanislav Fomichev <stfomichev@gmail.com> Link: https://patch.msgid.link/20250616162117.287806-4-stfomichev@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10219,8 +10219,7 @@ static int bnx2x_udp_tunnel_sync(struct net_device *netdev, unsigned int table)
 
 static const struct udp_tunnel_nic_info bnx2x_udp_tunnels = {
 	.sync_table	= bnx2x_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15573,17 +15573,15 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta
 static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
 	},
 }, bnxt_udp_tunnels_p7 = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4031,8 +4031,7 @@ static int be_vxlan_unset_port(struct net_device *netdev, unsigned int table,
 static const struct udp_tunnel_nic_info be_udp_tunnels = {
 	.set_port	= be_vxlan_set_port,
 	.unset_port	= be_vxlan_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
 	},
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -15895,7 +15895,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port;
 	pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port;
-	pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
 	pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared;
 	pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS;
 	pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4767,7 +4767,6 @@ int ice_init_dev(struct ice_pf *pf)
 
 	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
 	pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port;
-	pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
 	pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared;
 	if (pf->hw.tnl.valid_count[TNL_VXLAN]) {
 		pf->hw.udp_tunnel_nic.tables[0].n_entries =
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2670,8 +2670,7 @@ static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 
 static const struct udp_tunnel_nic_info mlx4_udp_tunnels = {
 	.sync_table	= mlx4_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
 	},
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5351,8 +5351,7 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv)
 
 	priv->nic_info.set_port = mlx5e_vxlan_set_port;
 	priv->nic_info.unset_port = mlx5e_vxlan_unset_port;
-	priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-				UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
+	priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
 	priv->nic_info.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN;
 	/* Don't count the space hard-coded to the IANA port */
 	priv->nic_info.tables[0].n_entries =
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2394,8 +2394,7 @@ static int nfp_udp_tunnel_sync(struct net_device *netdev, unsigned int table)
 
 static const struct udp_tunnel_nic_info nfp_udp_tunnels = {
 	.sync_table     = nfp_udp_tunnel_sync,
-	.flags          = UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags          = UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables         = {
 		{
 			.n_entries      = NFP_NET_N_VXLAN_PORTS,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -987,20 +987,17 @@ static int qede_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 
 static const struct udp_tunnel_nic_info qede_udp_tunnels_both = {
 	.sync_table	= qede_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
 	},
 }, qede_udp_tunnels_vxlan = {
 	.sync_table	= qede_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 	},
 }, qede_udp_tunnels_geneve = {
 	.sync_table	= qede_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
 	},
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -486,7 +486,6 @@ static int qlcnic_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 
 static const struct udp_tunnel_nic_info qlcnic_udp_tunnels = {
 	.sync_table	= qlcnic_udp_tunnel_sync,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
 	},
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
@@ -3985,7 +3985,6 @@ static int efx_ef10_udp_tnl_unset_port(struct net_device *dev,
 static const struct udp_tunnel_nic_info efx_ef10_udp_tunnels = {
 	.set_port	= efx_ef10_udp_tnl_set_port,
 	.unset_port	= efx_ef10_udp_tnl_unset_port,
-	.flags          = UDP_TUNNEL_NIC_INFO_MAY_SLEEP,
 	.tables         = {
 		{
 			.n_entries = 16,
diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c
@@ -112,12 +112,10 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,
 	struct net_device *dev = file->private_data;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	rtnl_lock();
 	if (dev->reg_state == NETREG_REGISTERED) {
 		memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
 		udp_tunnel_nic_reset_ntf(dev);
 	}
-	rtnl_unlock();
 
 	return count;
 }
@@ -181,8 +179,6 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 		info->sync_table = NULL;
 	}
 
-	if (ns->udp_ports.sleep)
-		info->flags |= UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
 	if (nsim_dev->udp_ports.open_only)
 		info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY;
 	if (nsim_dev->udp_ports.ipv4_only)
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
@@ -130,22 +130,6 @@ void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
 void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
 void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);
 
-static inline void udp_tunnel_get_rx_info(struct net_device *dev)
-{
-	ASSERT_RTNL();
-	if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-		return;
-	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
-}
-
-static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
-{
-	ASSERT_RTNL();
-	if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
-		return;
-	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev);
-}
-
 /* Transmit the skb using UDP encapsulation. */
 void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
@@ -222,19 +206,17 @@ static inline void udp_tunnel_encap_enable(struct sock *sk)
 #define UDP_TUNNEL_NIC_MAX_TABLES	4
 
 enum udp_tunnel_nic_info_flags {
-	/* Device callbacks may sleep */
-	UDP_TUNNEL_NIC_INFO_MAY_SLEEP	= BIT(0),
 	/* Device only supports offloads when it's open, all ports
 	 * will be removed before close and re-added after open.
 	 */
-	UDP_TUNNEL_NIC_INFO_OPEN_ONLY	= BIT(1),
+	UDP_TUNNEL_NIC_INFO_OPEN_ONLY	= BIT(0),
 	/* Device supports only IPv4 tunnels */
-	UDP_TUNNEL_NIC_INFO_IPV4_ONLY	= BIT(2),
+	UDP_TUNNEL_NIC_INFO_IPV4_ONLY	= BIT(1),
 	/* Device has hard-coded the IANA VXLAN port (4789) as VXLAN.
 	 * This port must not be counted towards n_entries of any table.
 	 * Driver will not receive any callback associated with port 4789.
 	 */
-	UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN	= BIT(3),
+	UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN	= BIT(2),
 };
 
 struct udp_tunnel_nic;
@@ -325,6 +307,9 @@ struct udp_tunnel_nic_ops {
 	size_t (*dump_size)(struct net_device *dev, unsigned int table);
 	int (*dump_write)(struct net_device *dev, unsigned int table,
 			  struct sk_buff *skb);
+	void (*assert_locked)(struct net_device *dev);
+	void (*lock)(struct net_device *dev);
+	void (*unlock)(struct net_device *dev);
 };
 
 #ifdef CONFIG_INET
@@ -353,8 +338,29 @@ static inline void
 udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
 			     unsigned int idx, u8 priv)
 {
-	if (udp_tunnel_nic_ops)
+	if (udp_tunnel_nic_ops) {
+		udp_tunnel_nic_ops->lock(dev);
 		udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
+		udp_tunnel_nic_ops->unlock(dev);
+	}
+}
+
+static inline void udp_tunnel_nic_assert_locked(struct net_device *dev)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->assert_locked(dev);
+}
+
+static inline void udp_tunnel_nic_lock(struct net_device *dev)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->lock(dev);
+}
+
+static inline void udp_tunnel_nic_unlock(struct net_device *dev)
+{
+	if (udp_tunnel_nic_ops)
+		udp_tunnel_nic_ops->unlock(dev);
 }
 
 static inline void
@@ -396,17 +402,50 @@ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
 static inline size_t
 udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table)
 {
+	size_t ret;
+
 	if (!udp_tunnel_nic_ops)
 		return 0;
-	return udp_tunnel_nic_ops->dump_size(dev, table);
+
+	udp_tunnel_nic_ops->lock(dev);
+	ret = udp_tunnel_nic_ops->dump_size(dev, table);
+	udp_tunnel_nic_ops->unlock(dev);
+
+	return ret;
 }
 
 static inline int
 udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table,
 			  struct sk_buff *skb)
 {
+	int ret;
+
 	if (!udp_tunnel_nic_ops)
 		return 0;
-	return udp_tunnel_nic_ops->dump_write(dev, table, skb);
+
+	udp_tunnel_nic_ops->lock(dev);
+	ret = udp_tunnel_nic_ops->dump_write(dev, table, skb);
+	udp_tunnel_nic_ops->unlock(dev);
+
+	return ret;
+}
+
+static inline void udp_tunnel_get_rx_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+	udp_tunnel_nic_assert_locked(dev);
+	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
 }
+
+static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+	udp_tunnel_nic_assert_locked(dev);
+	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev);
+}
+
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
@@ -10771,12 +10771,14 @@ int __netdev_update_features(struct net_device *dev)
 			 * *before* calling udp_tunnel_get_rx_info,
 			 * but *after* calling udp_tunnel_drop_rx_info.
 			 */
+			udp_tunnel_nic_lock(dev);
 			if (features & NETIF_F_RX_UDP_TUNNEL_PORT) {
 				dev->features = features;
 				udp_tunnel_get_rx_info(dev);
 			} else {
 				udp_tunnel_drop_rx_info(dev);
 			}
+			udp_tunnel_nic_unlock(dev);
 		}
 
 		if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) {
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
@@ -134,15 +134,17 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
 	struct udp_tunnel_info ti;
 	struct net_device *dev;
 
+	ASSERT_RTNL();
+
 	ti.type = type;
 	ti.sa_family = sk->sk_family;
 	ti.port = inet_sk(sk)->inet_sport;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
+		udp_tunnel_nic_lock(dev);
 		udp_tunnel_nic_add_port(dev, &ti);
+		udp_tunnel_nic_unlock(dev);
 	}
-	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
 
@@ -154,15 +156,17 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
 	struct udp_tunnel_info ti;
 	struct net_device *dev;
 
+	ASSERT_RTNL();
+
 	ti.type = type;
 	ti.sa_family = sk->sk_family;
 	ti.port = inet_sk(sk)->inet_sport;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
+		udp_tunnel_nic_lock(dev);
 		udp_tunnel_nic_del_port(dev, &ti);
+		udp_tunnel_nic_unlock(dev);
 	}
-	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
 
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c

Original file line number	Diff line number	Diff line change
`@@ -2394,8 +2394,7 @@ static int nfp_udp_tunnel_sync(struct net_device *netdev, unsigned int table)`
`2394`	`2394`
`2395`	`2395`	`static const struct udp_tunnel_nic_info nfp_udp_tunnels = {`
`2396`	`2396`	`.sync_table = nfp_udp_tunnel_sync,`
`2397`		`- .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP \|`
`2398`		`- UDP_TUNNEL_NIC_INFO_OPEN_ONLY,`
	`2397`	`+ .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY,`
`2399`	`2398`	`.tables = {`
`2400`	`2399`	`{`
`2401`	`2400`	`.n_entries = NFP_NET_N_VXLAN_PORTS,`