net: l3mdev: Allow send on enslaved interface

Allow udp and raw sockets to send by oif that is an enslaved interface
versus the l3mdev/VRF device. For example, this allows BFD to use ifindex
from IP_PKTINFO on a receive to send a response without the need to
convert to the VRF index. It also allows ping and ping6 to work when
specifying an enslaved interface (e.g., ping -I swp1 <ip>) which is
a natural use case.

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

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 4b2461ae5d3b8d8ffe802b1848f17b12f826fa54..c8db55aa8280897c1a2cf5cc2c2f73aa84177b09 100644 (file)
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -648,6 +648,8 @@ static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
 
        fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF;
        fl4->flowi4_iif = LOOPBACK_IFINDEX;
+       /* make sure oif is set to VRF device for lookup */
+       fl4->flowi4_oif = dev->ifindex;
        fl4->flowi4_tos = tos & IPTOS_RT_MASK;
        fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
                             RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8c8c655bb2c41338e5a7498e2bf29c2c6497b9d3..a1f2830d811025e561c9739c79a5c218a3801977 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2146,6 +2146,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
        unsigned int flags = 0;
        struct fib_result res;
        struct rtable *rth;
+       int master_idx;
        int orig_oif;
        int err = -ENETUNREACH;
 
@@ -2155,6 +2156,9 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 
        orig_oif = fl4->flowi4_oif;
 
+       master_idx = l3mdev_master_ifindex_by_index(net, fl4->flowi4_oif);
+       if (master_idx)
+               fl4->flowi4_oif = master_idx;
        fl4->flowi4_iif = LOOPBACK_IFINDEX;
        fl4->flowi4_tos = tos & IPTOS_RT_MASK;
        fl4->flowi4_scope = ((tos & RTO_ONLINK) ?

diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 898d01e0f87b19f97219e44ff7e3db234f210c75..6651a78e100cdf987a5963fc84be5484221053ef 100644 (file)
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -112,12 +112,18 @@ struct dst_entry *l3mdev_get_rt6_dst(struct net *net,
        struct dst_entry *dst = NULL;
        struct net_device *dev;
 
-       dev = dev_get_by_index(net, fl6->flowi6_oif);
-       if (dev) {
-               if (netif_is_l3_master(dev) &&
+       if (fl6->flowi6_oif) {
+               rcu_read_lock();
+
+               dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
+               if (dev && netif_is_l3_slave(dev))
+                       dev = netdev_master_upper_dev_get_rcu(dev);
+
+               if (dev && netif_is_l3_master(dev) &&
                    dev->l3mdev_ops->l3mdev_get_rt6_dst)
                        dst = dev->l3mdev_ops->l3mdev_get_rt6_dst(dev, fl6);
-               dev_put(dev);
+
+               rcu_read_unlock();
        }
 
        return dst;
@@ -141,6 +147,9 @@ int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4)
                rcu_read_lock();
 
                dev = dev_get_by_index_rcu(net, ifindex);
+               if (dev && netif_is_l3_slave(dev))
+                       dev = netdev_master_upper_dev_get_rcu(dev);
+
                if (dev && netif_is_l3_master(dev) &&
                    dev->l3mdev_ops->l3mdev_get_saddr)
                        rc = dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4);