net: allow binding socket in a VRF when there's an unbound socket

Change the inet socket lookup to avoid packets arriving on a device
enslaved to an l3mdev from matching unbound sockets by removing the
wildcard for non sk_bound_dev_if and instead relying on check against
the secondary device index, which will be 0 when the input device is
not enslaved to an l3mdev and so match against an unbound socket and
not match when the input device is enslaved.

Change the socket binding to take the l3mdev into account to allow an
unbound socket to not conflict sockets bound to an l3mdev given the
datapath isolation now guaranteed.

Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 25 insertions, 8 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 15e7f7915a21..5c63449130d9 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -183,7 +183,9 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
 	int i, low, high, attempt_half;
 	struct inet_bind_bucket *tb;
 	u32 remaining, offset;
+	int l3mdev;
 
+	l3mdev = inet_sk_bound_l3mdev(sk);
 	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
 other_half_scan:
 	inet_get_local_port_range(net, &low, &high);
@@ -219,7 +221,8 @@ other_parity_scan:
 						  hinfo->bhash_size)];
 		spin_lock_bh(&head->lock);
 		inet_bind_bucket_for_each(tb, &head->chain)
-			if (net_eq(ib_net(tb), net) && tb->port == port) {
+			if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+			    tb->port == port) {
 				if (!inet_csk_bind_conflict(sk, tb, false, false))
 					goto success;
 				goto next_port;
@@ -293,6 +296,9 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb = NULL;
 	kuid_t uid = sock_i_uid(sk);
+	int l3mdev;
+
+	l3mdev = inet_sk_bound_l3mdev(sk);
 
 	if (!port) {
 		head = inet_csk_find_open_port(sk, &tb, &port);
@@ -306,11 +312,12 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 					  hinfo->bhash_size)];
 	spin_lock_bh(&head->lock);
 	inet_bind_bucket_for_each(tb, &head->chain)
-		if (net_eq(ib_net(tb), net) && tb->port == port)
+		if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+		    tb->port == port)
 			goto tb_found;
 tb_not_found:
 	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
-				     net, head, port);
+				     net, head, port, l3mdev);
 	if (!tb)
 		goto fail_unlock;
 tb_found:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 411dd7a90046..40d722ab1738 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -65,12 +65,14 @@ static u32 sk_ehashfn(const struct sock *sk)
 struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 						 struct net *net,
 						 struct inet_bind_hashbucket *head,
-						 const unsigned short snum)
+						 const unsigned short snum,
+						 int l3mdev)
 {
 	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
 	if (tb) {
 		write_pnet(&tb->ib_net, net);
+		tb->l3mdev    = l3mdev;
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
@@ -135,6 +137,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 			table->bhash_size);
 	struct inet_bind_hashbucket *head = &table->bhash[bhash];
 	struct inet_bind_bucket *tb;
+	int l3mdev;
 
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +146,8 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 		return -ENOENT;
 	}
 	if (tb->port != port) {
+		l3mdev = inet_sk_bound_l3mdev(sk);
+
 		/* NOTE: using tproxy and redirecting skbs to a proxy
 		 * on a different listener port breaks the assumption
 		 * that the listener socket's icsk_bind_hash is the same
@@ -150,12 +155,13 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 		 * create a new bind bucket for the child here. */
 		inet_bind_bucket_for_each(tb, &head->chain) {
 			if (net_eq(ib_net(tb), sock_net(sk)) &&
-			    tb->port == port)
+			    tb->l3mdev == l3mdev && tb->port == port)
 				break;
 		}
 		if (!tb) {
 			tb = inet_bind_bucket_create(table->bind_bucket_cachep,
-						     sock_net(sk), head, port);
+						     sock_net(sk), head, port,
+						     l3mdev);
 			if (!tb) {
 				spin_unlock(&head->lock);
 				return -ENOMEM;
@@ -675,6 +681,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	u32 remaining, offset;
 	int ret, i, low, high;
 	static u32 hint;
+	int l3mdev;
 
 	if (port) {
 		head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -693,6 +700,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		return ret;
 	}
 
+	l3mdev = inet_sk_bound_l3mdev(sk);
+
 	inet_get_local_port_range(net, &low, &high);
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	remaining = high - low;
@@ -719,7 +728,8 @@ other_parity_scan:
 		 * the established check is already unique enough.
 		 */
 		inet_bind_bucket_for_each(tb, &head->chain) {
-			if (net_eq(ib_net(tb), net) && tb->port == port) {
+			if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+			    tb->port == port) {
 				if (tb->fastreuse >= 0 ||
 				    tb->fastreuseport >= 0)
 					goto next_port;
@@ -732,7 +742,7 @@ other_parity_scan:
 		}
 
 		tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
-					     net, head, port);
+					     net, head, port, l3mdev);
 		if (!tb) {
 			spin_unlock_bh(&head->lock);
 			return -ENOMEM;