ipv4: Implement IP_UNICAST_IF socket option.

The IP_UNICAST_IF feature is needed by the Wine project.  This patch
implements the feature by setting the outgoing interface in a similar
fashion to that of IP_MULTICAST_IF.  A separate option is needed to
handle this feature since the existing options do not provide all of
the characteristics required by IP_UNICAST_IF, a summary is provided
below.

SO_BINDTODEVICE:
* SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF
does not.  From reading some old mailing list articles my
understanding is that SO_BINDTODEVICE requires administrative
privileges because it can override the administrator's routing
settings.
* The SO_BINDTODEVICE option restricts both outbound and inbound
traffic, IP_UNICAST_IF only impacts outbound traffic.

IP_PKTINFO:
* Since IP_PKTINFO and IP_UNICAST_IF are independent options,
implementing IP_UNICAST_IF with IP_PKTINFO will likely break some
applications.
* Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly
complicates the Wine codebase and reduces the socket performance
(doing this requires a lot of extra communication between the
"server" and "user" layers).

bind():
* bind() does not work on broadcast packets, IP_UNICAST_IF is
specifically intended to work with broadcast packets.
* Like SO_BINDTODEVICE, bind() restricts both outbound and inbound
traffic.

Signed-off-by: Erich E. Hoover <ehoover@mines.edu>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 39 insertions, 3 deletions

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8aa87c19fa00..9125529dab95 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -469,6 +469,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
                              (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
                              (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) |
                              (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) ||
+            optname == IP_UNICAST_IF ||
             optname == IP_MULTICAST_TTL ||
             optname == IP_MULTICAST_ALL ||
             optname == IP_MULTICAST_LOOP ||
@@ -628,6 +629,35 @@ static int do_ip_setsockopt(struct sock *sk, int level,
                         goto e_inval;
                 inet->mc_loop = !!val;
                 break;
+        case IP_UNICAST_IF:
+        {
+                struct net_device *dev = NULL;
+                int ifindex;
+
+                if (optlen != sizeof(int))
+                        goto e_inval;
+
+                ifindex = (__force int)ntohl((__force __be32)val);
+                if (ifindex == 0) {
+                        inet->uc_index = 0;
+                        err = 0;
+                        break;
+                }
+
+                dev = dev_get_by_index(sock_net(sk), ifindex);
+                err = -EADDRNOTAVAIL;
+                if (!dev)
+                        break;
+                dev_put(dev);
+
+                err = -EINVAL;
+                if (sk->sk_bound_dev_if)
+                        break;
+
+                inet->uc_index = ifindex;
+                err = 0;
+                break;
+        }
         case IP_MULTICAST_IF:
         {
                 struct ip_mreqn mreq;
@@ -1178,6 +1208,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
         case IP_MULTICAST_LOOP:
                 val = inet->mc_loop;
                 break;
+        case IP_UNICAST_IF:
+                val = (__force int)htonl((__u32) inet->uc_index);
+                break;
         case IP_MULTICAST_IF:
         {
                 struct in_addr addr;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index aea5a199c37a..cfc82cf339f6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -556,7 +556,8 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         ipc.oif = inet->mc_index;
                 if (!saddr)
                         saddr = inet->mc_addr;
-        }
+        } else if (!ipc.oif)
+                ipc.oif = inet->uc_index;
 
         flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
                            RT_SCOPE_UNIVERSE, sk->sk_protocol,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 3ccda5ae8a27..ab466305b629 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         ipc.oif = inet->mc_index;
                 if (!saddr)
                         saddr = inet->mc_addr;
-        }
+        } else if (!ipc.oif)
+                ipc.oif = inet->uc_index;
 
         flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
                            RT_SCOPE_UNIVERSE,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5d075b5f70fc..cd99f1a0f59f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -917,7 +917,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                 if (!saddr)
                         saddr = inet->mc_addr;
                 connected = 0;
-        }
+        } else if (!ipc.oif)
+                ipc.oif = inet->uc_index;
 
         if (connected)
                 rt = (struct rtable *)sk_dst_check(sk, 0);