Merge branch 'bpf_setsockopt-SO_BINDTODEVICE'

Ferenc Fejes says:

====================
This option makes it possible to programatically bind sockets
to netdevices. With the help of this option sockets
of VRF unaware applications could be distributed between
multiple VRFs with an eBPF program. This lets the applications
benefit from multiple possible routes.

v2:
- splitting up the patch to three parts
- lock_sk parameter for optional locking in sock_bindtoindex - Stanislav Fomichev
- testing the SO_BINDTODEVICE option - Andrii Nakryiko
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 35 insertions, 7 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 85ff827aab73..ae82bcb03124 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4248,6 +4248,9 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			   char *optval, int optlen, u32 flags)
 {
+	char devname[IFNAMSIZ];
+	struct net *net;
+	int ifindex;
 	int ret = 0;
 	int val;
 
@@ -4257,7 +4260,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 	sock_owned_by_me(sk);
 
 	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int))
+		if (optlen != sizeof(int) && optname != SO_BINDTODEVICE)
 			return -EINVAL;
 		val = *((int *)optval);
 
@@ -4298,6 +4301,29 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				sk_dst_reset(sk);
 			}
 			break;
+		case SO_BINDTODEVICE:
+			ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+			optlen = min_t(long, optlen, IFNAMSIZ - 1);
+			strncpy(devname, optval, optlen);
+			devname[optlen] = 0;
+
+			ifindex = 0;
+			if (devname[0] != '\0') {
+				struct net_device *dev;
+
+				ret = -ENODEV;
+
+				net = sock_net(sk);
+				dev = dev_get_by_name(net, devname);
+				if (!dev)
+					break;
+				ifindex = dev->ifindex;
+				dev_put(dev);
+			}
+			ret = sock_bindtoindex(sk, ifindex, false);
+#endif
+			break;
 		default:
 			ret = -EINVAL;
 		}
diff --git a/net/core/sock.c b/net/core/sock.c
index 61ec573221a6..6c4acf1f0220 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -594,13 +594,15 @@ out:
 	return ret;
 }
 
-int sock_bindtoindex(struct sock *sk, int ifindex)
+int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
 {
 	int ret;
 
-	lock_sock(sk);
+	if (lock_sk)
+		lock_sock(sk);
 	ret = sock_bindtoindex_locked(sk, ifindex);
-	release_sock(sk);
+	if (lock_sk)
+		release_sock(sk);
 
 	return ret;
 }
@@ -646,7 +648,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 			goto out;
 	}
 
-	return sock_bindtoindex(sk, index);
+	return sock_bindtoindex(sk, index, true);
 out:
 #endif
 
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 2158e8bddf41..3eecba0874aa 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -22,7 +22,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		goto error;
 
 	if (cfg->bind_ifindex) {
-		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex);
+		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true);
 		if (err < 0)
 			goto error;
 	}
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index 2e0ad1bc84a8..cdc4d4ee2420 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -30,7 +30,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 			goto error;
 	}
 	if (cfg->bind_ifindex) {
-		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex);
+		err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true);
 		if (err < 0)
 			goto error;
 	}