net: dsa: allow the DSA master to be seen and changed through rtnetlink

Some DSA switches have multiple CPU ports, which can be used to improve
CPU termination throughput, but DSA, through dsa_tree_setup_cpu_ports(),
sets up only the first one, leading to suboptimal use of hardware.

The desire is to not change the default configuration but to permit the
user to create a dynamic mapping between individual user ports and the
CPU port that they are served by, configurable through rtnetlink. It is
also intended to permit load balancing between CPU ports, and in that
case, the foreseen model is for the DSA master to be a bonding interface
whose lowers are the physical DSA masters.

To that end, we create a struct rtnl_link_ops for DSA user ports with
the "dsa" kind. We expose the IFLA_DSA_MASTER link attribute that
contains the ifindex of the newly desired DSA master.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 130 insertions, 0 deletions

diff --git a/net/dsa/port.c b/net/dsa/port.c
index 4183e60db4f9..e557b42de9f2 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/if_bridge.h>
+#include <linux/netdevice.h>
 #include <linux/notifier.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
@@ -1374,6 +1375,135 @@ int dsa_port_mrp_del_ring_role(const struct dsa_port *dp,
 	return ds->ops->port_mrp_del_ring_role(ds, dp->index, mrp);
 }
 
+static int dsa_port_assign_master(struct dsa_port *dp,
+				  struct net_device *master,
+				  struct netlink_ext_ack *extack,
+				  bool fail_on_err)
+{
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index, err;
+
+	err = ds->ops->port_change_master(ds, port, master, extack);
+	if (err && !fail_on_err)
+		dev_err(ds->dev, "port %d failed to assign master %s: %pe\n",
+			port, master->name, ERR_PTR(err));
+
+	if (err && fail_on_err)
+		return err;
+
+	dp->cpu_dp = master->dsa_ptr;
+
+	return 0;
+}
+
+/* Change the dp->cpu_dp affinity for a user port. Note that both cross-chip
+ * notifiers and drivers have implicit assumptions about user-to-CPU-port
+ * mappings, so we unfortunately cannot delay the deletion of the objects
+ * (switchdev, standalone addresses, standalone VLANs) on the old CPU port
+ * until the new CPU port has been set up. So we need to completely tear down
+ * the old CPU port before changing it, and restore it on errors during the
+ * bringup of the new one.
+ */
+int dsa_port_change_master(struct dsa_port *dp, struct net_device *master,
+			   struct netlink_ext_ack *extack)
+{
+	struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp);
+	struct net_device *old_master = dsa_port_to_master(dp);
+	struct net_device *dev = dp->slave;
+	struct dsa_switch *ds = dp->ds;
+	bool vlan_filtering;
+	int err, tmp;
+
+	/* Bridges may hold host FDB, MDB and VLAN objects. These need to be
+	 * migrated, so dynamically unoffload and later reoffload the bridge
+	 * port.
+	 */
+	if (bridge_dev) {
+		dsa_port_pre_bridge_leave(dp, bridge_dev);
+		dsa_port_bridge_leave(dp, bridge_dev);
+	}
+
+	/* The port might still be VLAN filtering even if it's no longer
+	 * under a bridge, either due to ds->vlan_filtering_is_global or
+	 * ds->needs_standalone_vlan_filtering. In turn this means VLANs
+	 * on the CPU port.
+	 */
+	vlan_filtering = dsa_port_is_vlan_filtering(dp);
+	if (vlan_filtering) {
+		err = dsa_slave_manage_vlan_filtering(dev, false);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to remove standalone VLANs");
+			goto rewind_old_bridge;
+		}
+	}
+
+	/* Standalone addresses, and addresses of upper interfaces like
+	 * VLAN, LAG, HSR need to be migrated.
+	 */
+	dsa_slave_unsync_ha(dev);
+
+	err = dsa_port_assign_master(dp, master, extack, true);
+	if (err)
+		goto rewind_old_addrs;
+
+	dsa_slave_sync_ha(dev);
+
+	if (vlan_filtering) {
+		err = dsa_slave_manage_vlan_filtering(dev, true);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to restore standalone VLANs");
+			goto rewind_new_addrs;
+		}
+	}
+
+	if (bridge_dev) {
+		err = dsa_port_bridge_join(dp, bridge_dev, extack);
+		if (err && err == -EOPNOTSUPP) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to reoffload bridge");
+			goto rewind_new_vlan;
+		}
+	}
+
+	return 0;
+
+rewind_new_vlan:
+	if (vlan_filtering)
+		dsa_slave_manage_vlan_filtering(dev, false);
+
+rewind_new_addrs:
+	dsa_slave_unsync_ha(dev);
+
+	dsa_port_assign_master(dp, old_master, NULL, false);
+
+/* Restore the objects on the old CPU port */
+rewind_old_addrs:
+	dsa_slave_sync_ha(dev);
+
+	if (vlan_filtering) {
+		tmp = dsa_slave_manage_vlan_filtering(dev, true);
+		if (tmp) {
+			dev_err(ds->dev,
+				"port %d failed to restore standalone VLANs: %pe\n",
+				dp->index, ERR_PTR(tmp));
+		}
+	}
+
+rewind_old_bridge:
+	if (bridge_dev) {
+		tmp = dsa_port_bridge_join(dp, bridge_dev, extack);
+		if (tmp) {
+			dev_err(ds->dev,
+				"port %d failed to rejoin bridge %s: %pe\n",
+				dp->index, bridge_dev->name, ERR_PTR(tmp));
+		}
+	}
+
+	return err;
+}
+
 void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp,
 			       const struct dsa_device_ops *tag_ops)
 {