net: mscc: ocelot: rebalance LAGs on link up/down events

At present there is an issue when ocelot is offloading a bonding
interface, but one of the links of the physical ports goes down. Traffic
keeps being hashed towards that destination, and of course gets dropped
on egress.

Monitor the netdev notifier events emitted by the bonding driver for
changes in the physical state of lower interfaces, to determine which
ports are active and which ones are no longer.

Then extend ocelot_get_bond_mask to return either the configured bonding
interfaces, or the active ones, depending on a boolean argument. The
code that does rebalancing only needs to do so among the active ports,
whereas the bridge forwarding mask and the logical port IDs still need
to look at the permanently bonded ports.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 32 insertions, 9 deletions

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 380a5a661702..f8b85ab8be5d 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -889,7 +889,8 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL(ocelot_get_ts_info);
 
-static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond)
+static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond,
+				bool only_active_ports)
 {
 	u32 mask = 0;
 	int port;
@@ -900,8 +901,12 @@ static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond)
 		if (!ocelot_port)
 			continue;
 
-		if (ocelot_port->bond == bond)
+		if (ocelot_port->bond == bond) {
+			if (only_active_ports && !ocelot_port->lag_tx_active)
+				continue;
+
 			mask |= BIT(port);
+		}
 	}
 
 	return mask;
@@ -960,8 +965,10 @@ void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot)
 			struct net_device *bond = ocelot_port->bond;
 
 			mask = ocelot->bridge_fwd_mask & ~BIT(port);
-			if (bond)
-				mask &= ~ocelot_get_bond_mask(ocelot, bond);
+			if (bond) {
+				mask &= ~ocelot_get_bond_mask(ocelot, bond,
+							      false);
+			}
 		} else {
 			/* Standalone ports forward only to DSA tag_8021q CPU
 			 * ports (if those exist), or to the hardware CPU port
@@ -1298,20 +1305,20 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
 	/* Now, set PGIDs for each active LAG */
 	for (lag = 0; lag < ocelot->num_phys_ports; lag++) {
 		struct net_device *bond = ocelot->ports[lag]->bond;
-		int num_ports_in_lag = 0;
+		int num_active_ports = 0;
 		unsigned long bond_mask;
 		u8 aggr_idx[16];
 
 		if (!bond || (visited & BIT(lag)))
 			continue;
 
-		bond_mask = ocelot_get_bond_mask(ocelot, bond);
+		bond_mask = ocelot_get_bond_mask(ocelot, bond, true);
 
 		for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) {
 			// Destination mask
 			ocelot_write_rix(ocelot, bond_mask,
 					 ANA_PGID_PGID, port);
-			aggr_idx[num_ports_in_lag++] = port;
+			aggr_idx[num_active_ports++] = port;
 		}
 
 		for_each_aggr_pgid(ocelot, i) {
@@ -1319,7 +1326,11 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
 
 			ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i);
 			ac &= ~bond_mask;
-			ac |= BIT(aggr_idx[i % num_ports_in_lag]);
+			/* Don't do division by zero if there was no active
+			 * port. Just make all aggregation codes zero.
+			 */
+			if (num_active_ports)
+				ac |= BIT(aggr_idx[i % num_active_ports]);
 			ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i);
 		}
 
@@ -1356,7 +1367,8 @@ static void ocelot_setup_logical_port_ids(struct ocelot *ocelot)
 
 		bond = ocelot_port->bond;
 		if (bond) {
-			int lag = __ffs(ocelot_get_bond_mask(ocelot, bond));
+			int lag = __ffs(ocelot_get_bond_mask(ocelot, bond,
+							     false));
 
 			ocelot_rmw_gix(ocelot,
 				       ANA_PORT_PORT_CFG_PORTID_VAL(lag),
@@ -1399,6 +1411,17 @@ void ocelot_port_lag_leave(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL(ocelot_port_lag_leave);
 
+void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+	ocelot_port->lag_tx_active = lag_tx_active;
+
+	/* Rebalance the LAGs */
+	ocelot_set_aggr_pgids(ocelot);
+}
+EXPORT_SYMBOL(ocelot_port_lag_change);
+
 /* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu.
  * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG.
  * In the special case that it's the NPI port that we're configuring, the