Merge branch 'udp-tunnel-offloads-toggle'

Sabrina Dubroca says:

====================
Allow to switch off UDP-based tunnel offloads per netdevice

This patchset adds a new netdevice feature to toggle RX offloads of
UDP-based tunnel via ethtool. This is useful if the offload is causing
issues, for example if the hardware is buggy.

The feature is added to all devices providing the ->ndo_udp_tunnel_add
op, and enabled by default to preserve current behavior.

When the administrator disables this feature on a device, all
currently offloaded ports are cleared from the device.  When the
feature is turned on, the stack notifies the device about all current
ports.

v2:
 - rename feature bit to NETIF_F_RX_UDP_TUNNEL_PORT
 - rename ethtool feature to rx-udp_tunnel-port-offload
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 103 insertions, 17 deletions

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 0436a4283059..745d57ae95d7 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1016,16 +1016,22 @@ static struct device_type geneve_type = {
  * supply the listening GENEVE udp ports. Callers are expected
  * to implement the ndo_udp_tunnel_add.
  */
-static void geneve_push_rx_ports(struct net_device *dev)
+static void geneve_offload_rx_ports(struct net_device *dev, bool push)
 {
 	struct net *net = dev_net(dev);
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(gs, &gn->sock_list, list)
-		udp_tunnel_push_rx_port(dev, gs->sock,
-					UDP_TUNNEL_TYPE_GENEVE);
+	list_for_each_entry_rcu(gs, &gn->sock_list, list) {
+		if (push) {
+			udp_tunnel_push_rx_port(dev, gs->sock,
+						UDP_TUNNEL_TYPE_GENEVE);
+		} else {
+			udp_tunnel_drop_rx_port(dev, gs->sock,
+						UDP_TUNNEL_TYPE_GENEVE);
+		}
+	}
 	rcu_read_unlock();
 }
 
@@ -1560,8 +1566,14 @@ static int geneve_netdevice_event(struct notifier_block *unused,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
-		geneve_push_rx_ports(dev);
+	if (event == NETDEV_UDP_TUNNEL_PUSH_INFO ||
+	    event == NETDEV_UDP_TUNNEL_DROP_INFO) {
+		geneve_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO);
+	} else if (event == NETDEV_UNREGISTER) {
+		geneve_offload_rx_ports(dev, false);
+	} else if (event == NETDEV_REGISTER) {
+		geneve_offload_rx_ports(dev, true);
+	}
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 96aa7e6cf214..dbca067540d0 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2608,7 +2608,7 @@ static struct device_type vxlan_type = {
  * supply the listening VXLAN udp ports. Callers are expected
  * to implement the ndo_udp_tunnel_add.
  */
-static void vxlan_push_rx_ports(struct net_device *dev)
+static void vxlan_offload_rx_ports(struct net_device *dev, bool push)
 {
 	struct vxlan_sock *vs;
 	struct net *net = dev_net(dev);
@@ -2617,11 +2617,19 @@ static void vxlan_push_rx_ports(struct net_device *dev)
 
 	spin_lock(&vn->sock_lock);
 	for (i = 0; i < PORT_HASH_SIZE; ++i) {
-		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist)
-			udp_tunnel_push_rx_port(dev, vs->sock,
-						(vs->flags & VXLAN_F_GPE) ?
-						UDP_TUNNEL_TYPE_VXLAN_GPE :
-						UDP_TUNNEL_TYPE_VXLAN);
+		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) {
+			unsigned short type;
+
+			if (vs->flags & VXLAN_F_GPE)
+				type = UDP_TUNNEL_TYPE_VXLAN_GPE;
+			else
+				type = UDP_TUNNEL_TYPE_VXLAN;
+
+			if (push)
+				udp_tunnel_push_rx_port(dev, vs->sock, type);
+			else
+				udp_tunnel_drop_rx_port(dev, vs->sock, type);
+		}
 	}
 	spin_unlock(&vn->sock_lock);
 }
@@ -3630,10 +3638,15 @@ static int vxlan_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 
-	if (event == NETDEV_UNREGISTER)
+	if (event == NETDEV_UNREGISTER) {
+		vxlan_offload_rx_ports(dev, false);
 		vxlan_handle_lowerdev_unregister(vn, dev);
-	else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
-		vxlan_push_rx_ports(dev);
+	} else if (event == NETDEV_REGISTER) {
+		vxlan_offload_rx_ports(dev, true);
+	} else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO ||
+		   event == NETDEV_UDP_TUNNEL_DROP_INFO) {
+		vxlan_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO);
+	}
 
 	return NOTIFY_DONE;
 }
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index ebd273627334..dc8b4896b77b 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -75,6 +75,7 @@ enum {
 	NETIF_F_HW_TC_BIT,		/* Offload TC infrastructure */
 	NETIF_F_HW_ESP_BIT,		/* Hardware ESP transformation offload */
 	NETIF_F_HW_ESP_TX_CSUM_BIT,	/* ESP with TX checksum offload */
+	NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
 
 	/*
 	 * Add your fresh new feature above and remember to update
@@ -138,6 +139,7 @@ enum {
 #define NETIF_F_HW_TC		__NETIF_F(HW_TC)
 #define NETIF_F_HW_ESP		__NETIF_F(HW_ESP)
 #define NETIF_F_HW_ESP_TX_CSUM	__NETIF_F(HW_ESP_TX_CSUM)
+#define	NETIF_F_RX_UDP_TUNNEL_PORT  __NETIF_F(RX_UDP_TUNNEL_PORT)
 
 #define for_each_netdev_feature(mask_addr, bit)	\
 	for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 614642eb7eb7..3a3cdc1b1f31 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2317,6 +2317,7 @@ struct netdev_lag_lower_state_info {
 #define NETDEV_PRECHANGEUPPER	0x001A
 #define NETDEV_CHANGELOWERSTATE	0x001B
 #define NETDEV_UDP_TUNNEL_PUSH_INFO	0x001C
+#define NETDEV_UDP_TUNNEL_DROP_INFO	0x001D
 #define NETDEV_CHANGE_TX_QUEUE_LEN	0x001E
 
 int register_netdevice_notifier(struct notifier_block *nb);
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 02c5be037451..10cce0dd4450 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -115,6 +115,8 @@ struct udp_tunnel_info {
 /* Notify network devices of offloadable types */
 void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
 			     unsigned short type);
+void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type);
 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);
 
@@ -124,6 +126,12 @@ static inline void udp_tunnel_get_rx_info(struct net_device *dev)
 	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
 }
 
+static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	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,
diff --git a/net/core/dev.c b/net/core/dev.c
index 509af6ce8831..8ea6b4b42611 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -144,6 +144,7 @@
 #include <linux/netfilter_ingress.h>
 #include <linux/crash_dump.h>
 #include <linux/sctp.h>
+#include <net/udp_tunnel.h>
 
 #include "net-sysfs.h"
 
@@ -7327,8 +7328,27 @@ sync_lower:
 	netdev_for_each_lower_dev(dev, lower, iter)
 		netdev_sync_lower_features(dev, lower, features);
 
-	if (!err)
+	if (!err) {
+		netdev_features_t diff = features ^ dev->features;
+
+		if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) {
+			/* udp_tunnel_{get,drop}_rx_info both need
+			 * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the
+			 * device, or they won't do anything.
+			 * Thus we need to update dev->features
+			 * *before* calling udp_tunnel_get_rx_info,
+			 * but *after* calling udp_tunnel_drop_rx_info.
+			 */
+			if (features & NETIF_F_RX_UDP_TUNNEL_PORT) {
+				dev->features = features;
+				udp_tunnel_get_rx_info(dev);
+			} else {
+				udp_tunnel_drop_rx_info(dev);
+			}
+		}
+
 		dev->features = features;
+	}
 
 	return err < 0 ? 0 : 1;
 }
@@ -7530,6 +7550,12 @@ int register_netdevice(struct net_device *dev)
 	 */
 	dev->hw_features |= NETIF_F_SOFT_FEATURES;
 	dev->features |= NETIF_F_SOFT_FEATURES;
+
+	if (dev->netdev_ops->ndo_udp_tunnel_add) {
+		dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT;
+		dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT;
+	}
+
 	dev->wanted_features = dev->features & dev->hw_features;
 
 	if (!(dev->flags & IFF_LOOPBACK))
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 78408ab77a10..b987bc475fc8 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -105,6 +105,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_HW_TC_BIT] =		 "hw-tc-offload",
 	[NETIF_F_HW_ESP_BIT] =		 "esp-hw-offload",
 	[NETIF_F_HW_ESP_TX_CSUM_BIT] =	 "esp-tx-csum-hw-offload",
+	[NETIF_F_RX_UDP_TUNNEL_PORT_BIT] =	 "rx-udp_tunnel-port-offload",
 };
 
 static const char
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 58bd39fb14b4..6539ff15e9a3 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -82,7 +82,8 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct udp_tunnel_info ti;
 
-	if (!dev->netdev_ops->ndo_udp_tunnel_add)
+	if (!dev->netdev_ops->ndo_udp_tunnel_add ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
 		return;
 
 	ti.type = type;
@@ -93,6 +94,24 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
 
+void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_del ||
+	    !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port);
+
 /* Notify netdevs that UDP port started listening */
 void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
 {
@@ -109,6 +128,8 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
 	for_each_netdev_rcu(net, dev) {
 		if (!dev->netdev_ops->ndo_udp_tunnel_add)
 			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
 		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
 	}
 	rcu_read_unlock();
@@ -131,6 +152,8 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
 	for_each_netdev_rcu(net, dev) {
 		if (!dev->netdev_ops->ndo_udp_tunnel_del)
 			continue;
+		if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
+			continue;
 		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
 	}
 	rcu_read_unlock();