net: Allow accepted sockets to be bound to l3mdev domain

Allow accepted sockets to derive their sk_bound_dev_if setting from the
l3mdev domain in which the packets originated. A sysctl setting is added
to control the behavior which is similar to sk_mark and
sysctl_tcp_fwmark_accept.

This effectively allow a process to have a "VRF-global" listen socket,
with child sockets bound to the VRF device in which the packet originated.
A similar behavior can be achieved using sk_mark, but a solution using marks
is incomplete as it does not handle duplicate addresses in different L3
domains/VRFs. Allowing sockets to inherit the sk_bound_dev_if from l3mdev
domain provides a complete solution.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 0 deletions

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 625bdf95d673..012b1f91f3ec 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -28,6 +28,7 @@
 #include <net/request_sock.h>
 #include <net/netns/hash.h>
 #include <net/tcp_states.h>
+#include <net/l3mdev.h>
 
 /** struct ip_options - IP Options
  *
@@ -113,6 +114,19 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 	return sk->sk_mark;
 }
 
+static inline int inet_request_bound_dev_if(const struct sock *sk,
+					    struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	struct net *net = sock_net(sk);
+
+	if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
+		return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
+#endif
+
+	return sk->sk_bound_dev_if;
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;