vxlan: Support MC routing in the underlay

Locally-generated MC packets have so far not been subject to MC routing.
Instead an MC-enabled installation would maintain the MC routing tables,
and separately from that the list of interfaces to send packets to as part
of the VXLAN FDB and MDB.

In a previous patch, a ip_mr_output() and ip6_mr_output() routines were
added for IPv4 and IPv6. All locally generated MC traffic is now passed
through these functions. For reasons of backward compatibility, an SKB
(IPCB / IP6CB) flag guards the actual MC routing.

This patch adds logic to set the flag, and the UAPI to enable the behavior.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/d899655bb7e9b2521ee8c793e67056b9fd02ba12.1750113335.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 25 insertions, 3 deletions

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index b22f9866be8e..a6cc1de4d8b8 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2451,6 +2451,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	rcu_read_lock();
 	if (addr_family == AF_INET) {
 		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
+		u16 ipcb_flags = 0;
 		struct rtable *rt;
 		__be16 df = 0;
 		__be32 saddr;
@@ -2467,6 +2468,9 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 
+		if (flags & VXLAN_F_MC_ROUTE)
+			ipcb_flags |= IPSKB_MCROUTE;
+
 		if (!info) {
 			/* Bypass encapsulation if the destination is local */
 			err = encap_bypass_if_local(skb, dev, vxlan, AF_INET,
@@ -2522,11 +2526,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr,
 				    pkey->u.ipv4.dst, tos, ttl, df,
-				    src_port, dst_port, xnet, !udp_sum, 0);
+				    src_port, dst_port, xnet, !udp_sum,
+				    ipcb_flags);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
 		struct in6_addr saddr;
+		u16 ip6cb_flags = 0;
 
 		if (!ifindex)
 			ifindex = sock6->sock->sk->sk_bound_dev_if;
@@ -2542,6 +2548,9 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 
+		if (flags & VXLAN_F_MC_ROUTE)
+			ip6cb_flags |= IP6SKB_MCROUTE;
+
 		if (!info) {
 			u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags;
 
@@ -2587,7 +2596,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev,
 				     &saddr, &pkey->u.ipv6.dst, tos, ttl,
 				     pkey->label, src_port, dst_port, !udp_sum,
-				     0);
+				     ip6cb_flags);
 #endif
 	}
 	vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len);
@@ -3402,6 +3411,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_LOCALBYPASS]	= NLA_POLICY_MAX(NLA_U8, 1),
 	[IFLA_VXLAN_LABEL_POLICY]       = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX),
 	[IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)),
+	[IFLA_VXLAN_MC_ROUTE]		= NLA_POLICY_MAX(NLA_U8, 1),
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -4315,6 +4325,14 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 			return err;
 	}
 
+	if (data[IFLA_VXLAN_MC_ROUTE]) {
+		err = vxlan_nl2flag(conf, data, IFLA_VXLAN_MC_ROUTE,
+				    VXLAN_F_MC_ROUTE, changelink,
+				    true, extack);
+		if (err)
+			return err;
+	}
+
 	if (tb[IFLA_MTU]) {
 		if (changelink) {
 			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU],
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index e2f7ca045d3e..0ee50785f4f1 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -332,6 +332,7 @@ struct vxlan_dev {
 #define VXLAN_F_VNIFILTER               0x20000
 #define VXLAN_F_MDB			0x40000
 #define VXLAN_F_LOCALBYPASS		0x80000
+#define VXLAN_F_MC_ROUTE		0x100000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
@@ -353,7 +354,9 @@ struct vxlan_dev {
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
 					 VXLAN_F_COLLECT_METADATA  |	\
 					 VXLAN_F_VNIFILTER         |    \
-					 VXLAN_F_LOCALBYPASS)
+					 VXLAN_F_LOCALBYPASS       |	\
+					 VXLAN_F_MC_ROUTE          |	\
+					 0)
 
 struct net_device *vxlan_dev_create(struct net *net, const char *name,
 				    u8 name_assign_type, struct vxlan_config *conf);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3ad2d5d98034..873c285996fe 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1398,6 +1398,7 @@ enum {
 	IFLA_VXLAN_LOCALBYPASS,
 	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	IFLA_VXLAN_RESERVED_BITS,
+	IFLA_VXLAN_MC_ROUTE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)