switchdev: implement IPv4 fib ndo wrappers

Flesh out ndo wrappers to call into device driver.  To call into device driver,
the wrapper must interate over route's nexthops to ensure all nexthop devs
belong to the same switch device.  Currently, there is no support for route's
nexthops spanning offloaded and non-offloaded devices, or spanning ports of
multiple offload devices.

Since switch device ports may be stacked under virtual interfaces (bonds and/or
bridges), and the route's nexthop may be on the virtual interface, the wrapper
will traverse the nexthop dev down to the base dev.  It's the base dev that's
passed to the switchdev driver's ndo ops.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 96 insertions, 2 deletions

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 81c4c02..99907d8 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -227,6 +227,65 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
 }
 EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink);
 
+static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct net_device *lower_dev;
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	/* Recusively search down until we find a sw port dev.
+	 * (A sw port dev supports ndo_switch_parent_id_get).
+	 */
+
+	if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD &&
+	    ops->ndo_switch_parent_id_get)
+		return dev;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		port_dev = netdev_switch_get_lowest_dev(lower_dev);
+		if (port_dev)
+			return port_dev;
+	}
+
+	return NULL;
+}
+
+static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
+{
+	struct netdev_phys_item_id psid;
+	struct netdev_phys_item_id prev_psid;
+	struct net_device *dev = NULL;
+	int nhsel;
+
+	/* For this route, all nexthop devs must be on the same switch. */
+
+	for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+		const struct fib_nh *nh = &fi->fib_nh[nhsel];
+
+		if (!nh->nh_dev)
+			return NULL;
+
+		dev = netdev_switch_get_lowest_dev(nh->nh_dev);
+		if (!dev)
+			return NULL;
+
+		if (netdev_switch_parent_id_get(dev, &psid))
+			return NULL;
+
+		if (nhsel > 0) {
+			if (prev_psid.id_len != psid.id_len)
+				return NULL;
+			if (memcmp(prev_psid.id, psid.id, psid.id_len))
+				return NULL;
+		}
+
+		prev_psid = psid;
+	}
+
+	return dev;
+}
+
 /**
  *	netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch
  *
@@ -242,11 +301,27 @@ EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink);
 int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 			       u8 tos, u8 type, u32 tb_id)
 {
+	struct net_device *dev;
+	const struct net_device_ops *ops;
+	int err = 0;
+
 	/* Don't offload route if using custom ip rules */
 	if (fi->fib_net->ipv4.fib_has_custom_rules)
 		return 0;
 
-	return 0;
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->netdev_ops;
+
+	if (ops->ndo_switch_fib_ipv4_add) {
+		err = ops->ndo_switch_fib_ipv4_add(dev, htonl(dst), dst_len,
+						   fi, tos, type, tb_id);
+		if (!err)
+			fi->fib_flags |= RTNH_F_EXTERNAL;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL(netdev_switch_fib_ipv4_add);
 
@@ -265,6 +340,25 @@ EXPORT_SYMBOL(netdev_switch_fib_ipv4_add);
 int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 			       u8 tos, u8 type, u32 tb_id)
 {
-	return 0;
+	struct net_device *dev;
+	const struct net_device_ops *ops;
+	int err = 0;
+
+	if (!(fi->fib_flags & RTNH_F_EXTERNAL))
+		return 0;
+
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->netdev_ops;
+
+	if (ops->ndo_switch_fib_ipv4_del) {
+		err = ops->ndo_switch_fib_ipv4_del(dev, htonl(dst), dst_len,
+						   fi, tos, type, tb_id);
+		if (!err)
+			fi->fib_flags &= ~RTNH_F_EXTERNAL;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL(netdev_switch_fib_ipv4_del);