net: dsa: Link aggregation support

Monitor the following events and notify the driver when:

- A DSA port joins/leaves a LAG.
- A LAG, made up of DSA ports, joins/leaves a bridge.
- A DSA port in a LAG is enabled/disabled (enabled meaning
  "distributing" in 802.3ad LACP terms).

When a LAG joins a bridge, the DSA subsystem will treat that as each
individual port joining the bridge. The driver may look at the port's
LAG device pointer to see if it is associated with any LAG, if that is
required. This is analogue to how switchdev events are replicated out
to all lower devices when reaching e.g. a LAG.

Drivers can optionally request that DSA maintain a linear mapping from
a LAG ID to the corresponding netdev by setting ds->num_lag_ids to the
desired size.

In the event that the hardware is not capable of offloading a
particular LAG for any reason (the typical case being use of exotic
modes like broadcast), DSA will take a hands-off approach, allowing
the LAG to be formed as a pure software construct. This is reported
back through the extended ACK, but is otherwise transparent to the
user.

Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 79 insertions, 0 deletions

diff --git a/net/dsa/port.c b/net/dsa/port.c
index e59bf66c4c0d..f5b0f72ee7cd 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -191,6 +191,85 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br)
 	dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 }
 
+int dsa_port_lag_change(struct dsa_port *dp,
+			struct netdev_lag_lower_state_info *linfo)
+{
+	struct dsa_notifier_lag_info info = {
+		.sw_index = dp->ds->index,
+		.port = dp->index,
+	};
+	bool tx_enabled;
+
+	if (!dp->lag_dev)
+		return 0;
+
+	/* On statically configured aggregates (e.g. loadbalance
+	 * without LACP) ports will always be tx_enabled, even if the
+	 * link is down. Thus we require both link_up and tx_enabled
+	 * in order to include it in the tx set.
+	 */
+	tx_enabled = linfo->link_up && linfo->tx_enabled;
+
+	if (tx_enabled == dp->lag_tx_enabled)
+		return 0;
+
+	dp->lag_tx_enabled = tx_enabled;
+
+	return dsa_port_notify(dp, DSA_NOTIFIER_LAG_CHANGE, &info);
+}
+
+int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag,
+		      struct netdev_lag_upper_info *uinfo)
+{
+	struct dsa_notifier_lag_info info = {
+		.sw_index = dp->ds->index,
+		.port = dp->index,
+		.lag = lag,
+		.info = uinfo,
+	};
+	int err;
+
+	dsa_lag_map(dp->ds->dst, lag);
+	dp->lag_dev = lag;
+
+	err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_JOIN, &info);
+	if (err) {
+		dp->lag_dev = NULL;
+		dsa_lag_unmap(dp->ds->dst, lag);
+	}
+
+	return err;
+}
+
+void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag)
+{
+	struct dsa_notifier_lag_info info = {
+		.sw_index = dp->ds->index,
+		.port = dp->index,
+		.lag = lag,
+	};
+	int err;
+
+	if (!dp->lag_dev)
+		return;
+
+	/* Port might have been part of a LAG that in turn was
+	 * attached to a bridge.
+	 */
+	if (dp->bridge_dev)
+		dsa_port_bridge_leave(dp, dp->bridge_dev);
+
+	dp->lag_tx_enabled = false;
+	dp->lag_dev = NULL;
+
+	err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info);
+	if (err)
+		pr_err("DSA: failed to notify DSA_NOTIFIER_LAG_LEAVE: %d\n",
+		       err);
+
+	dsa_lag_unmap(dp->ds->dst, lag);
+}
+
 /* Must be called under rcu_read_lock() */
 static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp,
 					      bool vlan_filtering)